Reading additional input from stdin...
OpenAI Codex v0.125.0 (research preview)
--------
workdir: /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
model: gpt-5.5
provider: openai
approval: never
sandbox: read-only
reasoning effort: medium
reasoning summaries: none
session id: 019dcb17-f484-7fb2-aae8-471dced10262
--------
user
I'm debugging the search bug — what should I look at first? Recommend a starting spec or set of files.
hook: SessionStart
hook: SessionStart
hook: SessionStart Completed
hook: SessionStart Completed
hook: UserPromptSubmit
hook: UserPromptSubmit
hook: UserPromptSubmit Completed
hook: UserPromptSubmit Completed
codex
I’ll ground this in the repo rather than guessing from the phrase “search bug.” I’m going to look for recent search-related specs and the code paths they point at, then give you the shortest sensible starting route.
mcp: spec_kit_memory/memory_match_triggers started
mcp: spec_kit_memory/memory_match_triggers (failed)
user cancelled MCP tool call
mcp: spec_kit_memory/memory_context started
mcp: spec_kit_memory/memory_context (failed)
user cancelled MCP tool call
codex
Memory lookup didn’t return usable context, so I’ll fall back to local evidence: specs first, then exact search-related paths. If the spec names are sane, that usually beats starting in implementation code cold.
exec
/bin/zsh -lc "rg --files specs | rg 'search|find|query|index|coco|memory'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 exited 1 in 0ms:
rg: specs: IO error for operation on specs: No such file or directory (os error 2)

exec
/bin/zsh -lc "rg --files | rg '(search|coco|memory|code-graph|index)'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml
.opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml
.opencode/commands/spec_kit/deep-research.md
.opencode/agents/deep-research.md
.opencode/plugins/spec-kit-compact-code-graph.js
.opencode/commands/doctor/assets/doctor_code-graph_apply.yaml
.opencode/commands/doctor/assets/doctor_code-graph_confirm.yaml
.opencode/commands/doctor/assets/doctor_code-graph_auto.yaml
.opencode/commands/doctor/assets/doctor_code-graph_apply-confirm.yaml
.opencode/commands/doctor/code-graph.md
.opencode/commands/memory/README.txt
.opencode/commands/memory/save.md
.opencode/commands/memory/manage.md
.opencode/commands/memory/learn.md
.opencode/commands/memory/search.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/external_reference.md
.opencode/skills/cli-gemini/manual_testing_playbook/03--built-in-tools/003-save-memory-persistence.md
.opencode/skills/cli-gemini/manual_testing_playbook/03--built-in-tools/001-google-web-search-grounding.md
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/spec.md
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/plan.md
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/tasks.md
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/description.json
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/031-sk-coco-index-cmd-integration/graph-metadata.json
.opencode/skills/sk-deep-research/README.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/spec.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/plan.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/checklist.md
.opencode/skills/sk-deep-research/assets/prompt_pack_iteration.md.tmpl
.opencode/skills/sk-deep-research/assets/deep_research_config.json
.opencode/skills/sk-deep-research/assets/deep_research_dashboard.md
.opencode/skills/sk-deep-research/assets/runtime_capabilities.json
.opencode/skills/sk-deep-research/assets/deep_research_strategy.md
.opencode/skills/sk-deep-research/SKILL.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/spec.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/plan.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/scratch/cross-cli-auto-usage-test-results.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/tasks.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/description.json
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/graph-metadata.json
.opencode/skills/mcp-code-mode/mcp_server/index.ts
.opencode/skills/sk-deep-research/scripts/reduce-state.cjs
.opencode/skills/sk-deep-research/scripts/runtime-capabilities.cjs
.opencode/skills/sk-deep-research/feature_catalog/04--research-output/02-negative-knowledge.md
.opencode/skills/sk-deep-research/feature_catalog/04--research-output/01-progressive-synthesis.md
.opencode/skills/cli-gemini/manual_testing_playbook/04--agent-routing/003-deep-research-agent-grounding.md
.opencode/skills/sk-deep-research/feature_catalog/02--state-management/03-config-management.md
.opencode/skills/sk-deep-research/feature_catalog/02--state-management/01-jsonl-state-log.md
.opencode/skills/sk-deep-research/feature_catalog/02--state-management/02-strategy-tracking.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/scratch/test-results-dr028-030.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/scratch/test-results-dr020-023.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/scratch/test-results-dr024-027.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/tasks.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/description.json
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/graph-metadata.json
.opencode/skills/sk-deep-research/feature_catalog/03--convergence/03-quality-guards.md
.opencode/skills/sk-deep-research/feature_catalog/03--convergence/01-three-signal-model.md
.opencode/skills/sk-deep-research/feature_catalog/03--convergence/04-graph-convergence.md
.opencode/skills/sk-deep-research/feature_catalog/03--convergence/02-stuck-detection.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/decision-record.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/spec.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/plan.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/checklist.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/research.md
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/022-mcp-coco-integration/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/scratch/meta-review.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/scratch/improvement-proposals.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/tasks.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/description.json
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/deep-research-strategy.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/05-memory-save.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/06-resource-map-emission.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/01-initialization.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/04-synthesis.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/02-iteration-dispatch.md
.opencode/skills/sk-deep-research/feature_catalog/01--loop-lifecycle/03-convergence-check.md
.opencode/skills/sk-deep-research/feature_catalog/feature_catalog.md
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/README.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/handover.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/spec.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/plan.md
.opencode/skills/cli-codex/manual_testing_playbook/08--built-in-tools/002-search-exec-mode.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/research.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/research/deep-research-state.jsonl
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/deep-research-strategy.md
.opencode/skills/sk-deep-research/references/quick_reference.md
.opencode/skills/sk-deep-research/references/convergence.md
.opencode/skills/sk-deep-research/references/state_format.md
.opencode/skills/sk-deep-research/references/spec_check_protocol.md
.opencode/skills/sk-deep-research/references/loop_protocol.md
.opencode/skills/sk-deep-research/references/capability_matrix.md
.opencode/skills/sk-deep-research/graph-metadata.json
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-014.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-011.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-012.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-013.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/research.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/decision-record.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/spec.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/plan.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/checklist.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/tasks.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/description.json
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/graph-metadata.json
.opencode/skills/cli-codex/manual_testing_playbook/04--agent-routing/005-research-profile.md
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/iterations/iteration-001.md
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/iterations/iteration-002.md
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/iterations/iteration-003.md
.opencode/skills/sk-deep-research/scripts/tests/fixtures/interrupted-session/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/iteration-004.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/iteration-005.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/iteration-001.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/iteration-002.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/iteration-003.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/archive-research-v1/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/playbook-results-wave1.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/playbook-results-wave3.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/consistency-sweep-checks-1-4.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/playbook-results-wave2.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/scratch/consistency-sweep-checks-5-7.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/tasks.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/description.json
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/graph-metadata.json
.opencode/skills/sk-deep-research/manual_testing_playbook/manual_testing_playbook.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/deep-research-strategy.md
.opencode/skills/sk-deep-research/manual_testing_playbook/01--entry-points-and-modes/002-confirm-mode-checkpointed-execution.md
.opencode/skills/sk-deep-research/manual_testing_playbook/01--entry-points-and-modes/001-auto-mode-deep-research-kickoff.md
.opencode/skills/sk-deep-research/manual_testing_playbook/01--entry-points-and-modes/003-parameterized-invocation-max-iterations-convergence.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/spec.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/plan.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/checklist.md
.opencode/skills/cli-codex/manual_testing_playbook/06--integration-patterns/002-web-search.md
.opencode/skills/mcp-code-mode/manual_testing_playbook/06--third-party-via-cm/004-notion-search-workspace.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/checklist.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/research.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/deep-research-state.jsonl
.opencode/skills/cli-copilot/manual_testing_playbook/05--session-continuity/001-repository-memory-recall.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/research/iterations/iteration-008.md
.opencode/skills/sk-deep-research/manual_testing_playbook/02--initialization-and-state-setup/027-research-charter-validation.md
.opencode/skills/sk-deep-research/manual_testing_playbook/02--initialization-and-state-setup/006-invalid-or-contradictory-state-halts-for-repair.md
.opencode/skills/sk-deep-research/manual_testing_playbook/02--initialization-and-state-setup/004-fresh-initialization-creates-canonical-state-files.md
.opencode/skills/sk-deep-research/manual_testing_playbook/02--initialization-and-state-setup/005-resume-classification-from-valid-prior-state.md
.opencode/skills/mcp-code-mode/manual_testing_playbook/01--core-tools/002-search-tools-relevance.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/scratch/codex-gpt54-deep-research.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/scratch/wave1-cross-runtime-audit.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/scratch/wave1-repo-recon.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/scratch/wave1-prior-context.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/scratch/improvement-proposals-v3.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/scratch/wave3-quality-review.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/tasks.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/description.json
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/graph-metadata.json
.opencode/skills/sk-deep-research/manual_testing_playbook/06--synthesis-save-and-guardrails/027-resource-map-emission.md
.opencode/skills/sk-deep-research/manual_testing_playbook/05--pause-resume-and-fault-tolerance/017-malformed-jsonl-lines-are-skipped-with-defaults.md
.opencode/skills/sk-deep-research/manual_testing_playbook/06--synthesis-save-and-guardrails/026-ruled-out-directions-in-synthesis.md
.opencode/skills/sk-deep-research/manual_testing_playbook/06--synthesis-save-and-guardrails/019-final-synthesis-memory-save-and-guardrail-behavior.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/checklist.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/009-strategy-next-focus-and-exhausted-approach-discipline.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/024-dashboard-generation-after-iteration.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/028-focus-track-labels-in-dashboard.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/025-novelty-justification-in-jsonl.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/008-iteration-writes-iteration-jsonl-and-strategy-update.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/029-graph-events-emission.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/010-progressive-synthesis-behavior-for-research-md.md
.opencode/skills/sk-deep-research/manual_testing_playbook/03--iteration-execution-and-state-discipline/007-iteration-reads-state-before-research.md
.opencode/skills/sk-deep-research/manual_testing_playbook/05--pause-resume-and-fault-tolerance/016-resume-after-pause-sentinel-removal.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/scratch/codex-gpt54-deep-research.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/spec.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/decision-record.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/spec.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/plan.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/checklist.md
.opencode/skills/sk-deep-research/manual_testing_playbook/05--pause-resume-and-fault-tolerance/018-jsonl-reconstruction-from-iteration-files.md
.opencode/skills/sk-deep-research/manual_testing_playbook/05--pause-resume-and-fault-tolerance/015-pause-sentinel-halts-between-iterations.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/029-insight-status-prevents-false-stuck.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/020-quality-guard-source-diversity.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/033-graph-aware-stop-gate.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/012-stop-when-all-key-questions-are-answered.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/032-blocked-stop-reducer-surfacing.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/011-stop-on-max-iterations.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/022-quality-guard-no-single-weak-source.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/031-graph-convergence-signals.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/014-stuck-recovery-widens-focus-and-continues.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/021-quality-guard-focus-alignment.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/023-convergence-passes-guard-fails-override.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/013-composite-convergence-stop-behavior.md
.opencode/skills/sk-deep-research/manual_testing_playbook/04--convergence-and-recovery/030-thought-status-convergence-handling.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/checklist.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/tasks.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/description.json
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/README.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/spec.md
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/plan.md
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/checklist.md
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/tasks.md
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/description.json
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/z_archive/014-cmd-memory-output/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/scratch/codex-gpt54-deep-research.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/plan.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/research-ideas.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/research.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/fix-log.txt
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/checklist.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/fix-dispatch.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/post-fix-review-log.txt
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/copilot-review-remaining.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/deep-review-config.json
.opencode/skills/mcp-coco-index/assets/config_templates.md
.opencode/skills/mcp-coco-index/SKILL.md
.opencode/skills/mcp-coco-index/scripts/update.sh
.opencode/skills/mcp-coco-index/scripts/doctor.sh
.opencode/skills/mcp-coco-index/scripts/install.sh
.opencode/skills/mcp-coco-index/scripts/ensure_ready.sh
.opencode/skills/mcp-coco-index/scripts/common.sh
.opencode/skills/mcp-coco-index/INSTALL_GUIDE.md
.opencode/skills/cli-opencode/manual_testing_playbook/04--agent-routing/006-deep-research-agent-iterations.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/checklist.md
.opencode/skills/cli-opencode/manual_testing_playbook/06--integration-patterns/002-memory-epilogue-handback.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/manual_testing_playbook.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-034.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-041.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-024.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-030.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-020.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-045.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-014.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-031.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-021.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-044.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-015.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-035.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-050.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-011.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-040.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-025.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-032.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-017.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-046.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-038.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-028.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-049.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-018.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-048.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-019.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-039.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-022.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-029.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/copilot-review-20.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-016.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-047.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/deep-review-state.jsonl
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-036.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/fix-log.txt
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-043.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/dispatch-log.txt
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-012.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-026.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-037.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-042.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-013.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-027.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-033.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/iterations/iteration-023.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/03--configuration/004-root-path-env-var-override.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/03--configuration/003-status-verification.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/03--configuration/001-default-model-verification.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/03--configuration/002-project-settings-inspection.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/07--code-graph-integration/001-query-intent-semantic-routing.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/07--code-graph-integration/002-hybrid-query-merges-results.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/07--code-graph-integration/003-session-resume-includes-cocoindex.md
.opencode/skills/mcp-coco-index/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/checklist.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/003-language-filter-multi.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/004-path-filter.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/001-basic-semantic-search.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/005-combined-filters.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/007-no-refresh-search.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/006-result-limit.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/008-concurrent-refresh-race.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/02--mcp-search-tool/002-language-filter-single.md
.opencode/skills/mcp-coco-index/tests/test_settings.py
.opencode/skills/mcp-coco-index/tests/test_client.py
.opencode/skills/mcp-coco-index/tests/test_e2e.py
.opencode/skills/mcp-coco-index/tests/test_config.py
.opencode/skills/mcp-coco-index/tests/test_backward_compat.py
.opencode/skills/mcp-coco-index/tests/test_daemon.py
.opencode/skills/mcp-coco-index/tests/test_cli_helpers.py
.opencode/skills/mcp-coco-index/tests/test_e2e_daemon.py
.opencode/skills/mcp-coco-index/tests/test_protocol.py
.opencode/skills/mcp-coco-index/tests/conftest.py
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/deep-review-config.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/scratch/codex-gpt54-deep-research.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/05--skill-advisor-integration/001-semantic-flag-routing.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/05--skill-advisor-integration/002-pre-computed-hits-routing.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-020.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-015.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/research.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-state.jsonl
.opencode/skills/mcp-coco-index/references/search_patterns.md
.opencode/skills/mcp-coco-index/references/settings_reference.md
.opencode/skills/mcp-coco-index/references/tool_reference.md
.opencode/skills/mcp-coco-index/references/cross_cli_playbook.md
.opencode/skills/mcp-coco-index/references/downstream_adoption_checklist.md
.opencode/skills/mcp-coco-index/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/deep-review-state.jsonl
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/deep-review-dashboard.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/deep-review-findings-registry.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/deep-review-strategy.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/review-report.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/post-fix-review.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/dispatch-20-iterations.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/fix-dispatch.sh
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/copilot-review-log.txt
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/checklist.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/01--core-cli-commands/002-full-index-build.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/01--core-cli-commands/004-cli-search-with-filters.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/01--core-cli-commands/003-incremental-index.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/01--core-cli-commands/005-index-reset-destructive.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/01--core-cli-commands/001-project-initialization.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/checklist.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/06--error-handling/001-no-results-graceful-handling.md
.opencode/skills/sk-deep-review/feature_catalog/01--loop-lifecycle/05-memory-save.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/scratch/codex-gpt54-deep-research.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/04--daemon-lifecycle/001-daemon-auto-start.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/04--daemon-lifecycle/002-daemon-status-inspection.md
.opencode/skills/mcp-coco-index/manual_testing_playbook/04--daemon-lifecycle/003-helper-script-readiness.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/README.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/decision-record.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/checklist.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/scratch/codex-gpt54-deep-research.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/scratch/closing-review.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/README.md
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/checklist.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/research.md
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/deep-research-dashboard.md
.opencode/specs/skilled-agent-orchestration/039-cmd-spec-kit-codex-skill-routing/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/checklist.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/description.json
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/spec.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/plan.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/checklist.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/tasks.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/description.json
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/decision-record.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/spec.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/plan.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/checklist.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/tasks.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/description.json
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/checklist.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/implementation-summary.md
.opencode/skills/sk-deep-review/manual_testing_playbook/06--synthesis-save-and-guardrails/027-final-synthesis-memory-save-and-guardrail-behavior.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/description.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/description.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/changelog/changelog-028-001-sk-deep-research-improvements.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/changelog/changelog-028-002-sk-deep-review-improvements.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/deep-research-strategy.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/recommendations-sk-deep-review.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/001-shared-payload-provenance-layer/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/decision-record.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/deep-research-dashboard.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/deep-research-state.jsonl
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/recommendations-sk-deep-research.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/research.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/description.json
.opencode/skills/system-spec-kit/mcp_server/tools/index.ts
.opencode/skills/system-spec-kit/mcp_server/tools/memory-tools.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/handlers/index.ts
.opencode/specs/skilled-agent-orchestration/z_archive/018-sk-code-opencode-refinement/research/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/005-code-graph-auto-reindex-parity/graph-metadata.json
.opencode/skills/system-spec-kit/feature_catalog/20--remediation-revalidation/02-memory-health-auto-repair.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/031-copilot-startup-hook-wiring/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/spec.md
.opencode/skills/system-spec-kit/mcp_server/plugin_bridges/spec-kit-compact-code-graph-bridge.mjs
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/checklist.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-088.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-089.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-034.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-065.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-051.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-041.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-086.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-075.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-024.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-055.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-061.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-030.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-082.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-020.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-071.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-045.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-014.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-054.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-060.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-031.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-083.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-021.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-070.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-044.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-015.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-035.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-064.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-050.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-011.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-040.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-087.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-074.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-025.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-057.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-090.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-032.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-063.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-073.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-022.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-080.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-016.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-047.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-067.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-036.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-053.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-043.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-012.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-026.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-077.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-084.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-066.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-037.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-052.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-042.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-013.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-027.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-076.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-085.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-056.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-033.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-062.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-072.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-023.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-081.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-017.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-046.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-038.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-069.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-079.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-028.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-059.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-049.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-018.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-058.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-048.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-019.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-039.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-068.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-078.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/research/iterations/iteration-029.md
.opencode/skills/system-spec-kit/feature_catalog/05--lifecycle/08-constitutional-memory-end-to-end-lifecycle.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/002-opencode-transport-adapter/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/prompt/claude-code-graph-runtime-retest.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/prompt/codex-code-graph-runtime-retest.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/prompt/gemini-code-graph-runtime-retest.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/deep-review-config.json
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/08-code-graph-edge-explanation-blast-radius-uplift.md
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/07-learning-history-memorygetlearninghistory.md
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/02-causal-graph-statistics-memorycausalstats.md
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/01-causal-edge-creation-memorycausallink.md
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/04-causal-chain-tracing-memorydriftwhy.md
.opencode/skills/system-spec-kit/feature_catalog/06--analysis/03-causal-edge-deletion-memorycausalunlink.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/004-cross-runtime-startup-surfacing-parity/graph-metadata.json
.opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/01-1-search-pipeline-features-speckit.md
.opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/11-memory-roadmap-capability-flags.md
.opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/04-4-memory-and-storage.md
.opencode/skills/cli-claude-code/manual_testing_playbook/04--agent-routing/007-research-agent-investigation.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/02-precompact-hook.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/23-tool-routing-enforcement.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/09-cocoindex-bridge-context.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/07-structural-code-indexer.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/06-runtime-detection.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/16-mcp-auto-priming.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/04-stop-token-tracking.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/13-tree-sitter-wasm-parser.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/11-working-set-tracker.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/05-cross-runtime-fallback.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/15-code-graph-auto-trigger.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/12-compact-merger.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/20-passive-context-enrichment.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/25-resource-map-template.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/17-session-health-tool.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/10-budget-allocator.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/22-context-preservation-metrics.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/21-gemini-cli-hooks.md
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/03-session-start-priming.md
.opencode/skills/system-spec-kit/feature_catalog/14--pipeline-architecture/07-search-pipeline-safety.md
.opencode/skills/system-spec-kit/feature_catalog/14--pipeline-architecture/25-code-graph-phase-dag-runner.md
.opencode/skills/system-spec-kit/feature_catalog/14--pipeline-architecture/02-mpab-chunk-to-memory-aggregation.md
.opencode/skills/system-spec-kit/feature_catalog/14--pipeline-architecture/18-atomic-write-then-index-api.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/003-code-graph-operations-hardening/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/archived/iteration-009.md
.opencode/skills/mcp-chrome-devtools/manual_testing_playbook/02--protocol-discovery/003-search-cdp-method.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/03-single-and-folder-delete-memorydelete.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/10-per-memory-history-log.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/04-tier-based-bulk-deletion-memorybulkdelete.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md
.opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md
.opencode/skills/system-spec-kit/scripts/loaders/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/deep-research-strategy.md
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md
.opencode/skills/system-spec-kit/scripts/extractors/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/deep-research-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/findings-registry.json
.opencode/specs/system-spec-kit/024-compact-code-graph/030-opencode-graph-plugin/research/deep-research-state.jsonl
.opencode/skills/system-spec-kit/scripts/ops/heal-index-drift.sh
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/16-dry-run-preflight-for-memory-save.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/17-outsourced-agent-memory-capture.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/26-spec-doc-structure-validator.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/21-assistive-reconsolidation.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/02-signal-vocabulary-expansion.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/01-verify-fix-verify-memory-quality-loop.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/10-auto-entity-extraction.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/14-quality-gate-timer-persistence.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/25-indexing-runtime-bootstrap-api.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/05-pre-storage-quality-gate.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/15-deferred-lexical-only-indexing.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/08-anchor-aware-chunk-thinning.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/23-hybrid-decay-policy.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/19-post-save-quality-review.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/07-smarter-memory-content-generation.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/11-content-aware-memory-filename-generation.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/06-reconsolidation-on-save.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/28-memory-causal-trust-display.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/09-encoding-intent-capture-at-index-time.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/04-spec-folder-description-discovery.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/27-canonical-continuity-save-substrate.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/18-session-enrichment-and-alignment-guards.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/03-pre-flight-token-budget-validation.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/24-save-quality-gate-exceptions.md
.opencode/skills/system-spec-kit/feature_catalog/13--memory-quality-and-indexing/13-entity-normalization-consolidation.md
.opencode/skills/system-spec-kit/feature_catalog/10--graph-signal-activation/08-graph-and-cognitive-memory-fixes.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/027-opencode-structural-priming/graph-metadata.json
.opencode/skills/system-spec-kit/feature_catalog/03--discovery/02-system-statistics-memorystats.md
.opencode/skills/system-spec-kit/feature_catalog/03--discovery/03-health-diagnostics-memoryhealth.md
.opencode/skills/system-spec-kit/feature_catalog/03--discovery/01-memory-browser-memorylist.md
.opencode/skills/system-spec-kit/feature_catalog/08--bug-fixes-and-data-integrity/11-working-memory-timestamp-fix.md
.opencode/skills/system-spec-kit/feature_catalog/15--retrieval-enhancements/05-memory-summary-search-channel.md
.opencode/skills/system-spec-kit/feature_catalog/15--retrieval-enhancements/02-constitutional-memory-as-expert-knowledge-injection.md
.opencode/skills/system-spec-kit/feature_catalog/15--retrieval-enhancements/01-dual-scope-memory-auto-surface.md
.opencode/skills/system-spec-kit/feature_catalog/15--retrieval-enhancements/14-community-search-fallback.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/deep-review-config.json
.opencode/skills/system-spec-kit/scripts/config/index.ts
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/17-memory-roadmap-baseline-snapshot.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/plan.md
.opencode/skills/system-spec-kit/scripts/optimizer/search.cjs
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts
.opencode/skills/system-spec-kit/feature_catalog/16--tooling-and-scripts/33-memory-quality-kpi-reporting.md
.opencode/skills/system-spec-kit/feature_catalog/16--tooling-and-scripts/25-memory-maintenance-and-migration-clis.md
.opencode/skills/system-spec-kit/feature_catalog/16--tooling-and-scripts/13-constitutional-memory-manager-command.md
.opencode/skills/system-spec-kit/feature_catalog/16--tooling-and-scripts/34-research-metadata-backfill.md
.opencode/skills/system-spec-kit/scripts/lib/validate-memory-quality.ts
.opencode/skills/system-spec-kit/scripts/lib/memory-frontmatter.ts
.opencode/skills/system-spec-kit/scripts/lib/memory-telemetry.ts
.opencode/skills/system-spec-kit/feature_catalog/18--ux-hooks/10-atomic-save-parity-and-partial-indexing-hints.md
.opencode/skills/system-spec-kit/feature_catalog/18--ux-hooks/02-memory-health-autorepair-metadata.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/deep-review-config.json
.opencode/skills/system-spec-kit/templates/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/013-correctness-boundary-repair/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/lib/errors/index.ts
.opencode/skills/sk-code-web/references/research/multi_agent_patterns.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/09-tool-result-extraction-to-working-memory.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/10-fast-delegated-search-memory-quick-search.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/06-bm25-trigger-phrase-re-index-gate.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/08-quality-aware-3-tier-search-fallback.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/02-semantic-and-lexical-search-memorysearch.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/03-trigger-phrase-matching-memorymatchtriggers.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/12-search-api-surface.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/01-unified-context-retrieval-memorycontext.md
.opencode/skills/system-spec-kit/feature_catalog/01--retrieval/04-hybrid-search-pipeline.md
.opencode/skills/system-spec-kit/scripts/memory/backfill-research-metadata.ts
.opencode/skills/system-spec-kit/scripts/memory/migrate-trigger-phrase-residual.ts
.opencode/skills/system-spec-kit/scripts/memory/cleanup-orphaned-vectors.ts
.opencode/skills/system-spec-kit/scripts/memory/generate-context.ts
.opencode/skills/system-spec-kit/scripts/memory/ast-parser.ts
.opencode/skills/system-spec-kit/scripts/memory/validate-memory-quality.ts
.opencode/skills/system-spec-kit/scripts/memory/rebuild-auto-entities.ts
.opencode/skills/system-spec-kit/scripts/memory/reindex-embeddings.ts
.opencode/skills/system-spec-kit/scripts/memory/cleanup-index-scope-violations.ts
.opencode/skills/system-spec-kit/scripts/memory/README.md
.opencode/skills/system-spec-kit/scripts/memory/fix-memory-h1.mjs
.opencode/skills/system-spec-kit/scripts/memory/rank-memories.ts
.opencode/skills/system-spec-kit/scripts/memory/backfill-frontmatter.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/checklist.md
.opencode/skills/system-spec-kit/manual_testing_playbook/20--remediation-revalidation/226-memory-health-auto-repair.md
.opencode/skills/system-spec-kit/mcp_server/lib/eval/memory-state-baseline.ts
.opencode/skills/system-spec-kit/scripts/test-fixtures/011-anchors-duplicate-ids/memory/context.md
.opencode/skills/system-spec-kit/references/cli/memory_handback.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/README.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/031-normalized-analytics-reader/graph-metadata.json
.opencode/skills/system-spec-kit/scripts/spec-folder/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/020-query-routing-integration/graph-metadata.json
.opencode/skills/system-spec-kit/scripts/renderers/index.ts
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/019-causal-edge-creation-memory-causal-link.md
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/025-learning-history-memory-get-learning-history.md
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/026-code-graph-edge-explanation-blast-radius-uplift.md
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/021-causal-edge-deletion-memory-causal-unlink.md
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/022-causal-chain-tracing-memory-drift-why.md
.opencode/skills/system-spec-kit/manual_testing_playbook/06--analysis/020-causal-graph-statistics-memory-causal-stats.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/checklist.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/06--auto-indexing/001-derived-extraction.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/06--auto-indexing/005-anti-stuffing.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/06--auto-indexing/002-sanitizer-boundaries.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/06--auto-indexing/003-provenance-and-trust-lanes.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/06--auto-indexing/004-corpus-df-idf.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/plan.md
.opencode/skills/system-spec-kit/templates/sharded/spec-index.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/034-workflow-split-and-token-insight-contracts/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/decision-record.md
.opencode/skills/system-spec-kit/manual_testing_playbook/19--feature-flag-reference/125-memory-roadmap-capability-flags.md
.opencode/skills/system-spec-kit/manual_testing_playbook/19--feature-flag-reference/028-1-search-pipeline-features-speckit.md
.opencode/skills/system-spec-kit/manual_testing_playbook/19--feature-flag-reference/031-4-memory-and-storage.md
.opencode/skills/system-spec-kit/references/memory/epistemic_vectors.md
.opencode/skills/system-spec-kit/references/memory/trigger_config.md
.opencode/skills/system-spec-kit/references/memory/embedding_resilience.md
.opencode/skills/system-spec-kit/references/memory/memory_system.md
.opencode/skills/system-spec-kit/references/memory/save_workflow.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/033-fts-forced-degrade-hardening/graph-metadata.json
.opencode/skills/system-spec-kit/manual_testing_playbook/14--pipeline-architecture/050-mpab-chunk-to-memory-aggregation-r1.md
.opencode/skills/system-spec-kit/manual_testing_playbook/14--pipeline-architecture/271-code-graph-phase-dag-runner.md
.opencode/skills/system-spec-kit/manual_testing_playbook/14--pipeline-architecture/067-search-pipeline-safety.md
.opencode/skills/system-spec-kit/manual_testing_playbook/14--pipeline-architecture/203-atomic-write-then-index-api.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/plan.md
.opencode/skills/system-spec-kit/manual_testing_playbook/04--maintenance/014-workspace-scanning-and-indexing-memory-index-scan.md
.opencode/skills/system-spec-kit/scripts/core/memory-metadata.ts
.opencode/skills/system-spec-kit/scripts/core/find-predecessor-memory.ts
.opencode/skills/system-spec-kit/scripts/core/index.ts
.opencode/skills/system-spec-kit/scripts/core/memory-indexer.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/deep-review-config.json
.opencode/skills/system-spec-kit/scripts/test-fixtures/015-anchors-no-memory/spec.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/015-anchors-no-memory/plan.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/015-anchors-no-memory/tasks.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/015-anchors-no-memory/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/014-hook-durability-auto-enrichment/graph-metadata.json
.opencode/skills/system-spec-kit/manual_testing_playbook/18--ux-hooks/210-memory-health-autorepair-metadata.md
.opencode/skills/system-spec-kit/manual_testing_playbook/18--ux-hooks/214-atomic-save-parity-and-partial-indexing-hints.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/007-valid-anchors/memory/context.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/015-tree-sitter-migration/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/001-precompact-hook/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-013-correctness-boundary-repair.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-025-tool-routing-enforcement.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-008-structural-indexer.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-004-cross-runtime-fallback.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-009-code-graph-storage-query.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-019-code-graph-auto-trigger.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-011-compaction-working-set.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-014-hook-durability-auto-enrichment.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-001-precompact-hook.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-012-cocoindex-ux-utilization.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-007-testing-validation.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-028-startup-highlights-remediation.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-021-cross-runtime-instruction-parity.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-015-tree-sitter-migration.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-018-non-hook-auto-priming.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-006-documentation-alignment.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-root.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-002-session-start-hook.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-020-query-routing-integration.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-024-hookless-priming-optimization.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-029-review-remediation.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-030-opencode-graph-plugin.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-022-gemini-hook-porting.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-005-command-agent-alignment.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-026-session-start-injection-debug.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-003-stop-hook-tracking.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-010-cocoindex-bridge-context.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-017-tree-sitter-classifier-fixes.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-027-opencode-structural-priming.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-016-cross-runtime-ux.md
.opencode/specs/system-spec-kit/024-compact-code-graph/changelog/changelog-024-023-context-preservation-metrics.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/048-with-memory-placeholders/spec.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/048-with-memory-placeholders/plan.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/048-with-memory-placeholders/tasks.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/048-with-memory-placeholders/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/plan.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/073-quality-gate-timer-persistence.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/069-entity-normalization-consolidation.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/132-description-json-schema-field-validation.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/201-spec-doc-structure-validator-and-continuity-frontmatter.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/045-smarter-memory-content-generation-s1.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/039-verify-fix-verify-memory-quality-loop-pi-a5.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/047-encoding-intent-capture-at-index-time-r16.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/003-context-save-index-update.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/043-pre-storage-quality-gate-tm-04.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/203-memory-causal-trust-display.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/042-spec-folder-description-discovery-pi-b3.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/006-session-enrichment-and-alignment-guardrails.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/041-pre-flight-token-budget-validation-pi-a3.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/046-anchor-aware-chunk-thinning-r7.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/202-canonical-continuity-save-substrate.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/040-signal-vocabulary-expansion-tm-08.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/131-description-json-batch-backfill-validation-pi-b3.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/119-memory-filename-uniqueness-ensureuniquememoryfilename.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/005-outsourced-agent-memory-capture-round-trip.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/048-auto-entity-extraction-r10.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/111-deferred-lexical-only-indexing.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/199-content-aware-memory-filename-generation.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/044-reconsolidation-on-save-tm-06.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/177-hybrid-decay-policy-speckit-hybrid-decay-policy.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/178-save-quality-gate-exceptions-speckit-save-quality-gate-exceptions.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/155-post-save-quality-review.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/165-assistive-reconsolidation-speckit-assistive-reconsolidation.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/092-implemented-auto-entity-extraction-r10.md
.opencode/skills/system-spec-kit/manual_testing_playbook/13--memory-quality-and-indexing/133-dry-run-preflight-for-memory-save.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/257-working-set-compaction.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/254-code-graph-scan-query.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/255-cocoindex-code-graph-routing.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/256-budget-allocator.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/267-tool-routing-enforcement.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/258-compact-merger-assembly.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/259-tree-sitter-parser.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/261-mcp-auto-priming.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/251-stop-hook-saves.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/270-resource-map-template.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/253-runtime-detection.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/248-precompact-hook.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/249-session-start-compact.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/250-session-start-startup.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/263-session-resume.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/260-code-graph-auto-trigger.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/264-query-intent-routing.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/262-session-health.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/275-code-graph-readiness-contract.md
.opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/048-with-memory-placeholders/memory/context.md
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/auto-promotion.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/learned-feedback.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-relevance.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/hyde.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-flags.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/feedback-denylist.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/session-boost.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/surrogate-storage.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-calibration.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/embedding-expansion.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/reranker.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/encoding-intent.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/memory-summaries.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/query-surrogates.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/anchor-metadata.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/query-decomposer.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/spec-folder-hierarchy.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-store.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/query-router.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/query-expander.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/retrieval-directives.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/entity-linker.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/tfidf-summarizer.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/dynamic-token-budget.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-types.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/cross-encoder.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/causal-boost.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/deterministic-extractor.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/session-transition.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/sqlite-fts.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-search-fn.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/query-classifier.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/session-state.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/bm25-index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-aliases.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-representation.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/community-search.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/chunk-reassembly.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-impl.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/fsrs.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-enforcement.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/progressive-disclosure.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/local-reranker.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/deep-review-config.json
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/007-memory-metadata-update-memory-update.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/009-tier-based-bulk-deletion-memory-bulk-delete.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/006-memory-indexing-memory-save.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/101-memory-delete-confirm-schema-tightening.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/010-validation-feedback-memory-validate.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/008-single-and-folder-delete-memory-delete.md
.opencode/skills/system-spec-kit/manual_testing_playbook/02--mutation/008-feature-09-direct-manual-scenario-per-memory-history-log.md
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/ranking-contract.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/orchestrator.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2b-enrichment.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-queries.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-cache.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/artifact-routing.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/004-cross-runtime-fallback/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/007-testing-validation/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/archived/iteration-009.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/002-semantic-and-lexical-search-memory-search.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/003-trigger-phrase-matching-memory-match-triggers.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/189-tool-result-extraction-to-working-memory.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/185-memory-search-command-routing.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/187-quick-search-memory-quick-search.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/109-quality-aware-3-tier-search-fallback.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/001-unified-context-retrieval-memory-context.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/002-targeted-memory-lookup.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/004-hybrid-search-pipeline.md
.opencode/skills/system-spec-kit/manual_testing_playbook/01--retrieval/086-bm25-trigger-phrase-re-index-gate.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/plan.md
.opencode/skills/system-spec-kit/mcp_server/lib/storage/incremental-index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/working-memory.ts
.opencode/skills/system-spec-kit/manual_testing_playbook/10--graph-signal-activation/081-graph-and-cognitive-memory-fixes.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-011.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-012.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/checklist.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/012-anchors-empty-memory/spec.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/012-anchors-empty-memory/plan.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/012-anchors-empty-memory/tasks.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/012-anchors-empty-memory/implementation-summary.md
.opencode/skills/system-spec-kit/manual_testing_playbook/09--evaluation-and-measurement/126-memory-roadmap-baseline-snapshot.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/deep-review-config.json
.opencode/skills/system-spec-kit/manual_testing_playbook/03--discovery/011-memory-browser-memory-list.md
.opencode/skills/system-spec-kit/manual_testing_playbook/03--discovery/013-health-diagnostics-memory-health.md
.opencode/skills/system-spec-kit/manual_testing_playbook/03--discovery/012-system-statistics-memory-stats.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts
.opencode/skills/system-spec-kit/mcp_server/lib/utils/index-scope.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/README.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/026-session-start-injection-debug/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/03-provenance-and-trust-lanes.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/06-df-idf-corpus.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/05-anti-stuffing.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/02-sanitizer.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/04-sync.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/02--auto-indexing/01-derived-extraction.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/005-command-agent-alignment/graph-metadata.json
.opencode/skills/system-spec-kit/manual_testing_playbook/15--retrieval-enhancements/055-dual-scope-memory-auto-surface-tm-05.md
.opencode/skills/system-spec-kit/manual_testing_playbook/15--retrieval-enhancements/059-memory-summary-search-channel-r8.md
.opencode/skills/system-spec-kit/manual_testing_playbook/15--retrieval-enhancements/056-constitutional-memory-as-expert-knowledge-injection-pi-a4.md
.opencode/skills/system-spec-kit/manual_testing_playbook/15--retrieval-enhancements/093-implemented-memory-summary-generation-r8.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/012-cocoindex-ux-utilization/graph-metadata.json
.opencode/skills/system-spec-kit/scripts/test-fixtures/013-anchors-multiple-files/memory/invalid.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/013-anchors-multiple-files/memory/valid.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/plan.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/147-constitutional-memory-manager-command.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/247-memory-quality-kpi-reporting.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/271-research-metadata-backfill.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/239-memory-maintenance-and-migration-clis.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/186-memory-manage-command-routing.md
.opencode/skills/system-spec-kit/manual_testing_playbook/16--tooling-and-scripts/149-rendered-memory-template-contract.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/plan.md
.opencode/skills/system-spec-kit/scripts/test-fixtures/047-with-extra-files/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/scripts/reindex-embeddings.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/deep-review-config.json
.opencode/skills/system-spec-kit/shared/review-research-paths.cjs
.opencode/skills/system-spec-kit/scripts/utils/index.ts
.opencode/skills/system-spec-kit/scripts/utils/memory-frontmatter.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/008-structural-indexer/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/023-context-preservation-metrics/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/017-tree-sitter-classifier-fixes/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/plan.md
.opencode/skills/system-spec-kit/mcp_server/configs/search-weights.json
.opencode/skills/system-spec-kit/scripts/test-fixtures/008-invalid-anchors/memory/context.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/plan.md
.opencode/skills/system-spec-kit/shared/parsing/memory-template-contract.ts
.opencode/skills/system-spec-kit/shared/parsing/memory-sufficiency.ts
.opencode/skills/system-spec-kit/shared/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts
.opencode/skills/system-spec-kit/mcp_server/hooks/index.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/fixtures/lifecycle/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/lib/learning/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/022-gemini-hook-porting/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/lib/config/memory-types.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/019-code-graph-auto-trigger/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/024-hookless-priming-optimization/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/plan.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tools/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/plan.md
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/bench/code-graph-parse-latency.bench.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/bench/code-graph-query-latency.bench.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/bench/code-graph-query-latency.baseline.json
.opencode/skills/system-spec-kit/scripts/tests/validate-memory-quality-v8-regex-narrow.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/optimizer-search.vitest.ts
.opencode/skills/system-spec-kit/shared/algorithms/index.ts
.opencode/skills/system-spec-kit/mcp_server/utils/index.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-types.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-ingest.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-bulk-delete.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-triggers.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/handlers/skill-graph/index.ts
.opencode/skills/system-spec-kit/mcp_server/formatters/index.ts
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts
.opencode/skills/system-spec-kit/mcp_server/core/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/README.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/handlers/save/index.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/save/atomic-index-memory.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-delete.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-update.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-list.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index-discovery.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/006-documentation-alignment/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/plan.md
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/index.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-utils.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index-alias.ts
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/deep-research-strategy.md
.opencode/skills/system-spec-kit/mcp_server/tests/save-index-exports.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/deep-research-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/025-tool-routing-enforcement/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/021-cross-runtime-instruction-parity/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-ux-regressions.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context.resume-gate-d.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-extended.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-integration.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/hybrid-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/regression-010-index-large-files.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-limits-scoring.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/029-review-remediation/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-010.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-004.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-005.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-001.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-011.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-006.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-002.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-012.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-003.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-013.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-007.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-008.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/iterations/iteration-009.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/research.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/deep-research-config.json
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/deep-research-dashboard.md
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/findings-registry.json
.opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/research/deep-research-state.jsonl
.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-ingest-edge.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-extended.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tools/code-graph-tools.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tools/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/010-cocoindex-bridge-context/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/index.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-reindex.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/plan.md
.opencode/skills/system-spec-kit/scripts/tests/memory-quality-phase2-pr3.test.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-learn-command-docs.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/api/index.ts
.opencode/skills/system-spec-kit/mcp_server/api/search.ts
.opencode/skills/system-spec-kit/mcp_server/api/indexing.ts
.opencode/skills/system-spec-kit/mcp_server/tests/incremental-index-v2.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/workflow-memory-tracking.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/full-spec-doc-indexing.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-governance.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-planner-first.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/working-memory-event-decay.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-benchmark-memory-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-flags.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-crud.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/community-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/compat/index.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoint-working-memory.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-health-edge.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-list-edge.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/hybrid-search-context-headers.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-constitutional-memory.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-update-constitutional-guard.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/working-memory.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/028-startup-highlights-remediation/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-eval-channels.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context-eval-channels.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-impl.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-embedding-semantic-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts
.opencode/skills/system-spec-kit/scripts/migrate-deep-research-paths.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-pipeline-regressions.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/backfill-research-metadata.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-sufficiency.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/test-memory-quality-lane.js
.opencode/skills/system-spec-kit/scripts/tests/validate-memory-quality-v12-normalization.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/runtime-memory-inputs.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/review-research-paths.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/deep-research-reducer.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-template-contract.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-quality-phase6-migration.test.ts
.opencode/skills/system-spec-kit/scripts/tests/deep-research-contract-parity.vitest.ts
.opencode/skills/system-spec-kit/scripts/tests/memory-quality-phase3-pr6.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/plan.md
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/structural-indexer.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/index.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/indexer-types.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/assets/code-graph-gold-queries.json
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-ops-hardening.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-siblings-readiness.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-verify.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-context-handler.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-indexer.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-seed-resolver.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-scan.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-ingest.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/016-cross-runtime-ux/graph-metadata.json
.opencode/specs/skilled-agent-orchestration/049-mcp-testing-playbooks/research.md
.opencode/skills/system-spec-kit/mcp_server/tests/incremental-index.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/003-stop-hook-tracking/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/011-compaction-working-set/graph-metadata.json
.opencode/skills/system-spec-kit/mcp_server/tests/search-results-format.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/graph-search-fn.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-triggers.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-review-config.json
.opencode/specs/system-spec-kit/z_archive/008-codex-system-wide-audit/scratch/legacy-memory-quarantine/15-02-26_17-31__codex-system-wide-audit.md
.opencode/specs/system-spec-kit/z_archive/008-codex-system-wide-audit/scratch/legacy-memory-quarantine/15-02-26_17-22__codex-system-wide-audit.md
.opencode/specs/system-spec-kit/z_archive/008-codex-system-wide-audit/scratch/legacy-memory-quarantine/15-02-26_17-29__codex-system-wide-audit.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-098.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-088.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-099.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-089.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-065.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-096.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-051.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-111.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-101.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-041.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-086.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-075.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-055.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-115.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-061.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-092.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-082.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-071.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-105.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-045.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-054.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-114.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-120.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-060.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-093.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-083.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-070.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-104.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-044.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-064.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-097.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-050.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-110.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-100.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-087.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-074.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-057.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-117.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-063.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-073.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-080.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-107.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-047.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-094.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-067.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-053.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-113.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-103.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-043.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-077.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-084.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-095.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-066.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-052.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-112.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-102.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-042.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-076.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-085.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-056.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-116.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-091.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-062.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-072.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-081.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-106.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-046.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-069.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-079.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-059.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-119.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-109.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-049.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-058.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-118.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-108.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-048.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-068.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-078.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-111-120.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/019-readme-and-summary-with-hvr/scratch/legacy-memory-quarantine/20-02-26_07-05__readme-and-summary-with-hvr.md
.opencode/specs/system-spec-kit/z_archive/019-readme-and-summary-with-hvr/scratch/legacy-memory-quarantine/19-02-26_21-46__readme-and-summary-with-hvr.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/deep-review-config.json
.opencode/skills/system-spec-kit/mcp_server/tests/memory-types.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-archival.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-lineage-backfill.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-dedup-order.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-delete-cascade.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-tools.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-state-baseline.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index-cooldown.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-roadmap-flags.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-ux-hooks.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-parser.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context-session-state.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/decision-record.md
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/plan.md
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-020.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-014.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-015.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-011.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-016.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-012.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-013.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-017.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-018.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/iterations/iteration-019.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-research-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/review/deep-research-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/checklist.md
.opencode/skills/system-spec-kit/mcp_server/tests/atomic-index-memory.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-memory-tiers.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-store.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-lineage-state.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-summaries.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-integration.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-4-stage-search-pipeline.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/code-graph-db.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/018-non-hook-auto-priming/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/032-cached-summary-fidelity-gates/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/plan.md
.opencode/specs/system-spec-kit/z_archive/015-anchor-enforcement-automation/scratch/legacy-memory-quarantine/17-02-26_08-42__anchor-enforcement-automation.md
.opencode/specs/system-spec-kit/z_archive/015-anchor-enforcement-automation/scratch/legacy-memory-quarantine/17-02-26_09-11__anchor-enforcement-automation.md
.opencode/specs/system-spec-kit/024-compact-code-graph/scratch/continuation-prompt.md
.opencode/specs/system-spec-kit/024-compact-code-graph/scratch/implementation-orchestration-prompt.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/spec.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/plan.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/decision-record.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/spec.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/plan.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/checklist.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/tasks.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/description.json
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/016-index-workflows-code/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/015-anchor-enforcement-automation/research/research.md
.opencode/skills/system-spec-kit/mcp_server/tests/hybrid-search-flags.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-context.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-compatibility.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/integration-search-pipeline.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/index-scope.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-stats-edge.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/bm25-index.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-parser-extended.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-store-remediation.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/deep-review-config.json
.opencode/specs/system-spec-kit/024-compact-code-graph/scratch/audit-2026-04-24/findings-content.md
.opencode/specs/system-spec-kit/024-compact-code-graph/scratch/audit-2026-04-24/findings-metadata.md
.opencode/specs/system-spec-kit/024-compact-code-graph/scratch/audit-2026-04-24/consolidated-findings.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/checklist.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/tasks.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/description.json
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/implementation-summary.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/graph-metadata.json
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/review-report.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/deep-review-state.jsonl
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-003-canonical-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP3-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC3-synthetic-bigrams.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-005b-clean.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-broken-D8.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-002b-proposition-overlap.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC3-standalone-stopwords.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP2-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP5-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-004a-completed-closure-triple.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC1-truncation.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC2-degraded-fallback.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-004a-in-progress.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP4-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC4-importance-tier.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-broken-D4.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-002a-blank-observation-titles.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC8-clean.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC6-provenance.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-broken-D1.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-005b-frontmatter-mirror.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP7-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC3-path-fragment.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP-clean.json
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/deep-review-config.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/migration/F-MIG-003-title-overlap.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/migration/F-MIG-002-clean.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/migration/F-MIG-001-junk-residual.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC3-happy-path.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC2-authored-decisions.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP1-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-005a-anchor-scaffolding.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-CHECK-DUP6-trigger.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-001-trigger-cluster.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC3-suspicious-prefix.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-004b-last-clipping.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-broken-D7.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-DUP-003-tree-thinning-files.json
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/009-code-graph-storage-query/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/plan.md
.opencode/changelog/mcp-coco-index/v1.1.0.0.md
.opencode/changelog/mcp-coco-index/v1.0.0.0.md
.opencode/changelog/mcp-coco-index/v1.2.0.0.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/024-compact-code-graph/002-session-start-hook/review/review-report.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/miss/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/ultra-think-review.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/deep-review-config.json
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/miss/memory/06-04-26_09-00__orphan-notes.md
.opencode/specs/system-spec-kit/z_archive/018-mcp-issues-after-update/scratch/legacy-memory-quarantine/18-02-26_09-47__mcp-issues-after-update.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/ambiguity/spec.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/ambiguity/memory/06-04-26_09-00__candidate-b.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/ambiguity/memory/06-04-26_09-00__candidate-a.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/handover.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-002-scope-governance.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-003-error-handling.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-004-handler-defaults.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-001-stage4-filter.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-005-feature-flags.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/checklist.md
.opencode/changelog/12--sk-deep-research/v1.8.0.0.md
.opencode/changelog/12--sk-deep-research/v1.4.0.0.md
.opencode/changelog/12--sk-deep-research/v1.2.1.0.md
.opencode/changelog/12--sk-deep-research/v1.2.0.0.md
.opencode/changelog/12--sk-deep-research/v1.6.0.0.md
.opencode/changelog/12--sk-deep-research/v1.6.1.0.md
.opencode/changelog/12--sk-deep-research/v1.10.0.0.md
.opencode/changelog/12--sk-deep-research/v1.3.0.0.md
.opencode/changelog/12--sk-deep-research/v1.6.3.0.md
.opencode/changelog/12--sk-deep-research/v1.1.0.0.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/hit/spec.md
.opencode/changelog/12--sk-deep-research/v1.7.0.0.md
.opencode/changelog/12--sk-deep-research/v1.9.0.0.md
.opencode/changelog/12--sk-deep-research/v1.5.0.0.md
.opencode/changelog/12--sk-deep-research/v1.2.2.0.md
.opencode/changelog/12--sk-deep-research/v1.6.2.0.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/spec.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/plan.md
.opencode/changelog/17--mcp-coco-index/v1.1.0.0.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/tasks.md
.opencode/changelog/17--mcp-coco-index/v1.0.0.0.md
.opencode/changelog/17--mcp-coco-index/v1.2.0.0.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/hit/memory/06-04-26_12-30__project-notes.md
.opencode/skills/system-spec-kit/scripts/tests/fixtures/memory-quality/F-AC5-lineage/hit/memory/06-04-26_12-05__deep-research-run-8.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/020-post-release-fixes/review/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/020-post-release-fixes/review/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/scratch/legacy-memory-quarantine/16-02-26_10-53__full-spec-doc-indexing.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/scratch/legacy-memory-quarantine/16-02-26_08-38__full-spec-doc-indexing.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/tasks.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/description.json
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/009-full-spec-doc-indexing/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/019-rewrite-repo-readme/scratch/research-brief.md
.opencode/changelog/sk-deep-research/v1.7.0.0.md
.opencode/changelog/sk-deep-research/v1.9.0.0.md
.opencode/changelog/sk-deep-research/v1.5.0.0.md
.opencode/changelog/sk-deep-research/v1.2.2.0.md
.opencode/changelog/sk-deep-research/v1.6.2.0.md
.opencode/changelog/sk-deep-research/v1.1.0.0.md
.opencode/changelog/sk-deep-research/v1.6.3.0.md
.opencode/changelog/sk-deep-research/v1.3.0.0.md
.opencode/changelog/sk-deep-research/v1.10.0.0.md
.opencode/changelog/sk-deep-research/v1.6.0.0.md
.opencode/changelog/sk-deep-research/v1.6.1.0.md
.opencode/changelog/sk-deep-research/v1.8.0.0.md
.opencode/changelog/sk-deep-research/v1.4.0.0.md
.opencode/changelog/sk-deep-research/v1.2.1.0.md
.opencode/changelog/sk-deep-research/v1.2.0.0.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/002-agentic-adoption/008-continuity-and-memory-ux-integration/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/checklist.md
.opencode/specs/system-spec-kit/z_archive/012-spec-doc-anchor-tags/scratch/legacy-memory-quarantine/16-02-26_14-12__spec-doc-anchor-tags.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/historical-memory-remediation-slice-b-final/manifest.json
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/historical-memory-remediation-slice-b-final/summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/deep-review-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/decision-record.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/plan.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/legacy-memory-quarantine/05-03-26_07-47__sqlite-to-turso.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/legacy-memory-quarantine/05-03-26_09-18__sqlite-to-turso.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/legacy-memory-quarantine/05-03-26_07-56__sqlite-to-turso.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/scratch/reaudit-2026-03-23/codex53-verifier.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/scratch/reaudit-2026-03-23/opus-review.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/scratch/reaudit-2026-03-23/gpt54-analyst.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/013-memory-quality-and-indexing/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/007-upgrade-level-script/scratch/legacy-memory-quarantine/15-02-26_14-28__upgrade-level-script.md
.opencode/specs/system-spec-kit/z_archive/007-upgrade-level-script/scratch/legacy-memory-quarantine/15-02-26_15-53__upgrade-level-script.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/plan.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/historical-memory-remediation-slice-b-apply/manifest.json
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/scratch/historical-memory-remediation-slice-b-apply/summary.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/decision-record.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/spec.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/plan.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/checklist.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/tasks.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/description.json
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/README.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/decision-record.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/consolidated-research-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/README.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/002-persist-tuned-thresholds/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/deep-review-config.json
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/003 - gaps-and-workarounds-sqlite-to-turso.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/004 - analysis-sqlite-to-libsql-migration.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/005 - recommendations-sqlite-to-libsql-migration.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/001 - analysis-sqlite-to-turso-migration.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/006 - gaps-and-workarounds-sqlite-to-libsql.md
.opencode/specs/system-spec-kit/z_future/sqlite-to-turso/research/002 - recommendations-sqlite-to-turso-migration.md
.opencode/specs/system-spec-kit/z_archive/014-memory-index-txt-support/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-011.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-012.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-013.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-research-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/decision-record.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/decision-record.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/010-graph-signal-activation/scratch/legacy-memory-quarantine/12-03-26_13-51__graph-signal-activation.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/010-graph-signal-activation/scratch/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/010-graph-signal-activation/scratch/legacy-memory-quarantine/12-03-26_13-52__graph-signal-activation.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/README.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/005-e2e-integration-test/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/008-create-sh-phase-parent/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/006-generate-context-subfolder/scratch/legacy-memory-quarantine/15-02-26_13-39__generate-context-subfolder.md
.opencode/specs/system-spec-kit/z_archive/006-generate-context-subfolder/scratch/legacy-memory-quarantine/15-02-26_13-40__generate-context-subfolder.md
.opencode/specs/system-spec-kit/z_archive/006-generate-context-subfolder/scratch/legacy-memory-quarantine/15-02-26_13-56__generate-context-subfolder.md
.opencode/specs/system-spec-kit/z_archive/006-generate-context-subfolder/scratch/legacy-memory-quarantine/15-02-26_13-28__generate-context-subfolder.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/deep-research-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/012-memory-save-quality-pipeline/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/006 - recommendations-codex-3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/003 - analysis-codex-2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/016 - synthesis-final-v2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/010 - recommendations-gemini-2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/014 - synthesis-adjusted-gemini.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/002 - recommendations-codex-1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/013 - synthesis-final-recommendations.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/005 - analysis-codex-3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/007 - analysis-gemini-1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/011 - analysis-gemini-3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/009 - analysis-gemini-2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/012 - recommendations-gemini-3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/008 - recommendations-gemini-1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/004 - recommendations-codex-2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/015 - synthesis-adjusted-codex.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/research/001 - analysis-codex-1.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/handover.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/decision-record.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/spec.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/plan.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/checklist.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/tasks.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/description.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/013-fsrs-memory-decay-study/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/README.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/004-fix-access-signal-path/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/ultra-think-review.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-codex-A3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-codex-A2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-003-copilot-C1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-copilot-C2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-copilot-C3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-codex-A2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-codex-A3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-003-codex-A1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-copilot-C3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-copilot-C2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-copilot-C1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-copilot-C1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-001-codex-A1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/scratch/agent-output-iter-002-codex-A1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/deep-research-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/README.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/003-real-feedback-labels/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/handover.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/decision-record.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/plan.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/spec.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/plan.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/checklist.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/tasks.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/description.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/002-hybrid-rag-adoption/002-memory-review-tool/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-014.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-015.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-011.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-016.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-012.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-013.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-017.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-018.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/009-reindex-validator-false-positives/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/review/deep-research-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/review/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/002-indexing-normalization/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-010-search-retrieval-quality-fixes.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-013-fts5-fix-and-search-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-011-indexing-and-adaptive-fusion.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-007-hybrid-search-null-db-fix.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-008-spec-memory-compliance-audit.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-012-memory-save-quality-pipeline.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/changelog/changelog-009-reindex-validator-false-positives.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/064-bug-analysis-and-fix/scratch/legacy-memory-quarantine/15-01-26_11-52__bug-analysis-and-fix.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/scratch/diagnosis-findings.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/scratch/diagnosis-trace.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/009-graph-retrieval-improvements/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/scratch/agent-03-refs-memory-validation.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/scratch/agent-04-memory-deep.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/04-grouped-by-type.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/p1-fix-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-10.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/23-indent-level-hierarchy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-04.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/17-progressive-disclosure.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-05.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/19-condensed-header.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/03-table-layout.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/29-adaptive-density.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/02-two-line-card.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/20-score-only-no-bar.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-01.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/p0-fix-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/13-right-aligned-score.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/11-sparkline-bar.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/14-emoji-type-badges.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/15-ascii-box-card.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/25-hybrid-compact-detail.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/18-color-coded-sidebar.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/30-recommended-synthesis.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/05-minimal-one-liner.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/06-indented-tree.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/09-split-panel.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-08.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/21-folderless-with-tooltip.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/28-channel-annotated.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-09.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/22-pipe-separated.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/scratch/audit-v3-c04-memory-pipeline-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/064-bug-analysis-and-fix/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/022-spec-doc-indexing-bypass/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/scratch/legacy-memory-quarantine/15-03-26_11-31__manual-context-save.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/scratch/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-09.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-08.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-03.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-07.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-06.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-02.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-05.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-01.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-10.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/deep-research/research-04.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/01-compact-type-first.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/07-score-heatmap.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/16-horizontal-rule-separator.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/27-dot-leader.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-06.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/10-tag-cloud.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/24-metadata-footer.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-02.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-03.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/08-numbered-list.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/26-two-column-kv.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/review-07.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/scratch/12-breadcrumb-folder.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/scratch/fix-anchors.py
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/research.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/scratch/implement-prompt.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/006-default-on-boost-rollout/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/research/discovery-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/008-spec-memory-compliance-audit/research/hard-block-memories.txt
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/description.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/README.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/002-babysitter-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/012-handover-triggers/scratch/legacy-memory-quarantine/17-12-25_16-19__handover-triggers.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/deep-review-config.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/checklist.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/scratch/research-brief.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/016-rewrite-memory-mcp-readme/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/scratch/audit-v3-c03-search-scoring-analysis.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-034.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-024.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-030.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-020.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-014.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-031.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-021.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-015.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-035.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-011.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-040.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-025.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-032.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-022.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-016.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-036.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-012.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-026.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-037.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-013.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-027.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-033.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-023.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-017.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-038.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-028.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-018.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-019.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-039.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/iterations/iteration-029.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/review-report.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/review/review-report-v1-original-audit.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/decision-record.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/graph-metadata.json
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/001-wire-promotion-gate/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/changes-manifest.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/decision-record.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/prompt.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/002-recommendations-cognitive-memory-upgrade.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/001-analysis-cognitive-memory-systems.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/scratch/archive-prior-session/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/scratch/archive-prior-session/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-deferred-agent4.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/doc-alignment-agent3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/phase-13-fix-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-triage-agent2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-deferred-agent1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-triage-agent3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-deferred-agent5.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/doc-alignment-agent2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-deferred-agent2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/doc-alignment-agent1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-triage-agent4.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/phase-12-fix-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-triage-agent5.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-deferred-agent3.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/doc-alignment-agent4.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/scratch/p2-triage-agent1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/079-speckit-cognitive-memory/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/018-rewrite-system-speckit-readme/scratch/research-brief.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/011-skill-alignment/002-skill-review-post-022/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/010-template-compliance-enforcement/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/decision-record.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/026-memory-database-refinement/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/017-governance/scratch/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/017-governance/scratch/legacy-memory-quarantine/12-03-26_18-50__governance.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/02-01-26_14-09__generate-context-modularization.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/01-01-26_18-04__generate-context-modularization.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/deep-research-round2-2026-03-26.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/01-01-26_17-45__generate-context-modularization-spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/02-01-26_12-50__generate-context-modularization.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/02-01-26_10-38__generate-context-modularization.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/scratch/legacy-memory-quarantine/02-01-26_08-20__generate-context-modularization.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/024-codex-memory-mcp-fix/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/scratch/z-archive-prior-audit/legacy-memory-quarantine/06-03-26_11-58__phase-8-architecture-boundaries.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/005-architecture-audit/scratch/z-archive-prior-audit/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/058-generate-context-modularization/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/deep-research-gap-report-2026-03-26.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/015-runtime-contract-and-indexability/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/013-memory-quality-and-indexing/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/research/deep-research-round2-2026-03-26.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/research/deep-research-gap-report-2026-03-26.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/scratch/agents/fix-04-master-index.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/scratch/agents/agent-15-flags-indexes.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/006-feature-catalog/scratch/agents/agent-10-memory-quality.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-010.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/scratch/archive-research-2026-03-22/iteration-009.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/016-speckit-yaml-integration/scratch/legacy-memory-quarantine/16-12-24_21-45__speckit-yaml-semantic-memory.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/004-maintenance/scratch/legacy-memory-quarantine/12-03-26_17-06__maintenance.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/004-maintenance/scratch/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/004-maintenance/scratch/legacy-memory-quarantine/12-03-26_16-35__maintenance.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/017-stateless-spec-passing/scratch/legacy-memory-quarantine/22-12-25_09-51__stateless-spec-passing.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/prompts/flawless-json-memory-pipeline-research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/014-agents-md-alignment/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/054-remaining-bugs-remediation/scratch/legacy-memory-quarantine/01-01-26_15-02__remaining-bugs-remediation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/054-remaining-bugs-remediation/scratch/legacy-memory-quarantine/01-01-26_14-13__remaining-bugs-remediation.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/decision-record.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/002-versioned-memory-state/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/handover.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/decision-record.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/research.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/002-mex-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/scratch/archive-2026-03-25/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/scratch/archive-2026-03-25/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/test-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/scratch/archive-round-1/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/scratch/archive-round-1/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/scratch/archive-round-1/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/decision-record.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/checklist.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/phase-research-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/scratch/historical-memory-remediation-check/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/scratch/historical-memory-remediation-check/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/001-mvp-monolithic/scratch/legacy-memory-quarantine/24-12-25_13-25__path-scoped-rules.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/001-mvp-monolithic/scratch/legacy-memory-quarantine/24-12-25_12-33__path-scoped-rules.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/001-mvp-monolithic/scratch/legacy-memory-quarantine/24-12-25_14-04__path-scoped-rules.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/001-mvp-monolithic/scratch/legacy-memory-quarantine/24-12-25_12-41__path-scoped-rules.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/006-shared-memory-rollout/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/015-manual-testing-per-playbook/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_13-56__speckit-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_15-36__speckit-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_12-03__speckit-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_15-48__speckit-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_15-13__speckit-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/019-speckit-refinement/scratch/legacy-memory-quarantine/23-12-25_12-52__speckit-refinement.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/001-initial-enrichment/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/decision-record.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/012-command-alignment/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/scratch/search-backup-20260116.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-memory-index-commands/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/research.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/005-mempalace/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/01-high-signal.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/06-no-placeholders.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/07-key-topics.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/09-actionable.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/03-decision-present.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/02-clean-spec-folder.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/05-no-contamination.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/04-semantic-fields.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/10-balanced.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/good/08-clean-metadata.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/decision-record.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/004-indexing-and-coherence/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/02-na-leakage.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/01-placeholder-tbd.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/08-zero-message-and-v4.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/10-compound-defects.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/05-empty-triggers.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/03-malformed-spec-folder.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/09-mixed-placeholder-boilerplate.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/04-fallback-decision.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/06-contamination-and-v5.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmarks/bad/07-legacy-path-and-v1.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/legacy-memory-quarantine/15-02-26_11-25__system-spec-kit.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/legacy-memory-quarantine/15-02-26_17-25__script-audit-comprehensive.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/legacy-memory-quarantine/15-02-26_13-19__script-audit-comprehensive.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/legacy-memory-quarantine/15-02-26_11-06__script-audit-comprehensive.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/legacy-memory-quarantine/15-02-26_11-11__system-spec-kit.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/review-agent-05-memory.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/build-agent-05-memory-verify.md
.opencode/specs/system-spec-kit/z_archive/004-script-audit-comprehensive/scratch/context-agent-05-memory-indexing.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/performance-benchmark-metrics.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-05-memori.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/t066-user-satisfaction-survey.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/chk-210-closure-evidence-2026-02-19.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-04-memos.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase2-extraction-metrics.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/eval-dataset-100-coverage.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase3-telemetry-dashboard.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-06-survey-outcomes.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/implementation-summary.md.rej.orig
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/eval-dataset-1000.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/implementation-summary.md.orig
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/chk-181-remediation-report.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-10-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/implementation-summary.md.rej
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase2-manual-save-comparison.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-kpi-14day.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/test-results.md.orig
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-01-tech-lead-approval-packet.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/test-results.md.rej
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-09-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-03-product-owner-approval-packet.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/chk-029-manual-test-protocol.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/t054-tech-lead-signoff-phase2.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-legacy-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-07-gwyer-hybrid-rag-project.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-07-kpi-closure-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/t061-t065-staged-rollout-monitoring.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-12-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase2-mrr-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-03-cognee.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-legacy-after.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-kpi-sample.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/eval-dataset-1000-coverage.md
.opencode/specs/system-spec-kit/z_archive/005-upgrade-speckit-docs/scratch/legacy-memory-quarantine/15-02-26_15-50__upgrade-speckit-docs.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-06-conan505-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/chk-029-manual-test-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/t027-tech-lead-signoff-phase1.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase-package-mapping-verification.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-05-staged-rollout-evidence.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/016-json-mode-hybrid-enrichment/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-25_11-39__docs-alignment-v12.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-25_00-00__v12-references-removed.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-25_12-45__session-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-25_11-45__docs-alignment-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-25_13-30__command-alignment.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/scratch/legacy-memory-quarantine/16-12-24_00-00__memory-docs-cleanup.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/006-auto-indexing/fix-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-live-check/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-live-check/summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/20-02-26_08-04__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/19-02-26_09-15__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/19-02-26_15-19__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/18-02-26_17-38__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/19-02-26_08-52__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/19-02-26_08-43__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/18-02-26_17-25__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/18-02-26_08-44__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/legacy-memory-quarantine/18-02-26_23-01__mcp-working-memory-hybrid-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase1-5-eval-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase3-telemetry-dashboard.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-benchmark-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/performance-benchmark-report.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/eval-dataset-100.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/test-results-vs-pre-update-mcp-server-2026-02-19.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/t028-t055-dark-launch-checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-02-data-reviewer-approval-packet.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-baseline.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/final-metrics.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-final/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-final/summary.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/research.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/003-modus-memory-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/007-ralph-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/003-claude-code-mastery-project-starter-kit-main/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/007-system-spec-kit-rename/scratch/legacy-memory-quarantine/17-12-25_08-52__system-spec-kit-rename.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/007-system-spec-kit-rename/scratch/legacy-memory-quarantine/17-12-25_08-41__system-spec-kit-rename.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/039-node-modules-consolidation/scratch/legacy-memory-quarantine/25-12-25_18-55__node-modules-consolidation.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/02-git-branch.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/27-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/10-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/48-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/25-npm---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/11-git-status.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/15-npm---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/18-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/40-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/09-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/34-node---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/01-git-status.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/39-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/47-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/24-node---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/manifest.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/14-node---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/23-git-log.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/28-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/04-node---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/12-git-branch.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/45-npm---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/44-node---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/20-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/17-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/43-git-log.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/33-git-log.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/19-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/50-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/36-python3---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/21-git-status.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/42-git-branch.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/13-git-log.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/08-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/46-python3---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/32-git-branch.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/03-git-log.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/49-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/06-python3---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/37-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/07-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/30-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/16-python3---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/22-git-branch.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/05-npm---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/41-git-status.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/38-ls--la.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/31-git-status.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/35-npm---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/26-python3---version.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration-inputs/29-ls--la.txt
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/scratch/legacy-memory-quarantine/19-02-26_08-52__memory-quality-qp-0-4.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/003-memory-quality-qp-0-4/graph-metadata.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_11-16__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_11-55__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_11-22__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/02-02-26_17-53__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_11-53__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_10-53__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_14-15__speckit-reimagined-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/02-02-26_17-45__speckit-reimagined.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/082-speckit-reimagined/scratch/legacy-memory-quarantine/01-02-26_12-19__speckit-reimagined.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-003-gpt54.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-002-gpt54.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-002-opus.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-003-opus.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-001-opus.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-002-codex53.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-001-codex53.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-001-gpt54.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/iterations/iteration-003-codex53.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/mcp_tool_adapter.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/068-constitutional-readme-fix/scratch/legacy-memory-quarantine/16-01-26_09-05__constitutional-readme-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/test-fixtures/invalid-anchors/scratch/legacy-memory-quarantine/context.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/legacy-memory-quarantine/13-03-26_18-00__hydra-baseline-controls-delivered.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/perplexity_recommendations.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/perplexity_research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/002 - recommendations-turso-migration-and-hydradb-inspired-roadmap.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/001 - analysis-hydradb-architecture-and-turso-fit.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/008-hydra-db-based-features/research/recommendations_markovian_architectures.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/processors/markdown_processor.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/processors/__init__.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/processors/document_processor.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/processors/embedding_processor.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/graphrag_mcp_tool.py
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/019-architecture-remediation/scratch/codex-4-memory-system.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/019-architecture-remediation/scratch/wave3-research.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/AGENTS.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/index.ts
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/tsconfig.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/README.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-final-2/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-final-2/summary.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-apply/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-apply/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/026-docs-alignment/scratch/legacy-memory-quarantine/16-02-26_14-50__docs-alignment-complete.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/scratch/legacy-memory-quarantine/19-02-26_08-52__foundation-phases-0-1-1-5.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/utils/query_utils.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/utils/qdrant_utils.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/001-foundation-phases-0-1-1-5/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/utils/__init__.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/utils/neo4j_utils.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/__init__.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/config.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/query_engine.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/docs/installation.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/docs/configuration.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/docs/architecture.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/opencode-working-memory/LICENSE
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/quality-legacy-baseline.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/redaction-calibration.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-02-baban-paper.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase3-user-survey-results.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase2-closure-metrics.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-08-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-04-dark-launch-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase1-5-context-error-telemetry.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-01-mem0.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/full-verification-and-results-2026-02-19.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/phase1-eval-results.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/test-results-composite.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/test-report.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/findings.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/checklist.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-live-check-2/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-live-check-2/summary.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/research.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/004-opencode-mnemosyne-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/database/qdrant_manager.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/database/neo4j_manager.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/src/database/__init__.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/136 - analysis-working-memory-hybrid-rag-systems.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/136 - recommendations-working-memory-hybrid-rag-adoption.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/research.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/136 - recommendations-external-memory-rag-adoption-for-speckit.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/136 - prioritized-implementation-backlog-post-research.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/research/136 - analysis-external-memory-rag-systems-for-speckit.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/021-memory-choice-enforcement/scratch/legacy-memory-quarantine/17-12-25_08-08__memory-choice-enforcement.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/legacy-memory-quarantine/20-02-26_17-45__spec-kit-phase-system.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/legacy-memory-quarantine/20-02-26_16-42__spec-kit-phase-system.md
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-preapply/manifest.json
.opencode/specs/system-spec-kit/z_archive/021-spec-kit-phase-system/scratch/historical-memory-remediation-slice-b-preapply/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/verification/high-fixes-5-8.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/verification/high-fixes-1-4.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/verification/high-fixes-9-12.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/verification/crit-fixes.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/your_docs_here/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/your_docs_here/sample.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/006-babysitter-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/test-fixtures/valid-anchors/scratch/legacy-memory-quarantine/context.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/run-all-tests.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-069-core.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/test-utils.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-069-integration.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/integration.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-070-scoring.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-071-scripts.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/run-all-tests.sh
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-071-templates.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/spec-070-composite.test.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/tests/cognitive-module.test.js
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/008-xethryon/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/data/qdrant/.gitkeep
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/data/.gitkeep
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/scans/all-test-files.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/scans/spec-069-tests.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/scans/deprecated-files.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/scans/spec-070-tests.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/072-speckit-template-memory-ranking-release/scans/spec-071-tests.md
.opencode/specs/system-spec-kit/z_archive/010-documentation-alignment/scratch/legacy-memory-quarantine/16-02-26_11-43__spec126-documentation-alignment.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/README.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/decision-record.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/checklist.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/description.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-speckit-reimagined-bug-fixes/scratch/legacy-memory-quarantine/03-02-26_17-28__speckit-reimagined-bug-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-speckit-reimagined-bug-fixes/scratch/legacy-memory-quarantine/03-02-26_19-50__speckit-reimagined-bug-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-speckit-reimagined-bug-fixes/scratch/legacy-memory-quarantine/03-02-26_17-56__audit-fixes.md
.opencode/specs/system-spec-kit/z_archive/017-command-adherence/scratch/legacy-memory-quarantine/17-02-26_18-19__command-adherence.md
.opencode/specs/system-spec-kit/z_archive/017-command-adherence/scratch/legacy-memory-quarantine/18-02-26_08-33__command-adherence.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/data/input/.gitkeep
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-cleanup-pass/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-cleanup-pass/summary.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-04-agent-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/research-findings.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-03-command-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/changelog-reference.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/decision-record.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/phase-research-prompt.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/data/neo4j/.gitkeep
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/.env.example
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/docker-compose.yml
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/AI_ENTRY.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-post-fix/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-post-fix/summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/research-reconciliation-checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/z-archive-deep-research-config-v1.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/scratch/legacy-memory-quarantine/24-12-25_15-45__modular-architecture.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/scratch/legacy-memory-quarantine/24-12-25_15-27__modular-architecture.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/scratch/legacy-memory-quarantine/24-12-25_15-36__modular-architecture.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/023-path-scoped-rules/002-modular-architecture/scratch/legacy-memory-quarantine/24-12-25_14-51__modular-architecture.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-06-global-readme-update/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/research.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-10.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-20.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-14.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-04.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-15.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-05.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-11.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-01.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-16.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-06.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-12.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-02.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-13.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/ownership-matrix.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-03.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-17.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-07.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-18.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-08.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-19.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/scratch/impl-wave1/agent-09.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/c136-11-evidence.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/scripts/verify_db_structure.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/scripts/import_docs.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/scripts/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/scripts/query_demo.py
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-07-github-release/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation/summary.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/066-context-server-modularization/scratch/legacy-memory-quarantine/15-01-26_16-58__context-server-modularization.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-02-skill-speckit-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/database_setup.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/scratch/legacy-memory-quarantine/03-02-25_00-00__verification-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/083-memory-command-consolidation/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/test_db_connection/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/test_db_connection/connection_info.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/test_db_connection/check_databases.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/test_db_connection/test_connections.py
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/setup.sh
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/research-source-08-reliable-rag.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/requirements.txt
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/LICENSE
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final-post/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final-post/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/048-system-analysis/scratch/legacy-memory-quarantine/30-12-25_14-00__system-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/048-system-analysis/scratch/legacy-memory-quarantine/30-12-25_14-45__system-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/053-script-analysis-testing/scratch/legacy-memory-quarantine/31-12-25_19-46__script-analysis-testing.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-01-readme-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/archive/legacy-research-log/research-dashboard-legacy.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/research/archive/legacy-research-log/research-log-legacy.jsonl
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/033-ux-deep-analysis/scratch/legacy-memory-quarantine/25-12-25_11-36__ux-deep-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/033-ux-deep-analysis/scratch/legacy-memory-quarantine/25-12-25_15-28__ux-deep-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/033-ux-deep-analysis/scratch/legacy-memory-quarantine/25-12-25_11-07__ux-deep-analysis.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/research.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/deep-research-config.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/findings-registry.json
.opencode/specs/system-spec-kit/z_future/hybrid-rag-fusion-upgrade/001-research-hybrid-rag-fusion-systems/001-engram-main/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/testing/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/testing/connection_info.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/checklist.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/007-documentation-alignment/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/dead-code-unused-analysis.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/index.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/query.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/testing.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/error_handling.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/connection.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/scratch/graphrag-hybrid/guides/mcp/examples.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/decision-record.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/spec.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/plan.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/changes.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/checklist.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/tasks.md
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/description.json
.opencode/specs/system-spec-kit/z_archive/013-memory-overhaul-and-agent-upgrade-release/task-05-changelog-updates/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/research-reconciliation-master.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/049-system-analysis-bugs/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-6/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-6/summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/decision-record.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/075-post-speckit-template-upgrade-command-allignment/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-3/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-3/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/037-post-merge-refinement-2/scratch/legacy-memory-quarantine/16-02-26_14-50__session-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/037-post-merge-refinement-2/scratch/legacy-memory-quarantine/25-12-25_19-06__post-merge-refinement-2.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/037-post-merge-refinement-2/scratch/legacy-memory-quarantine/25-12-25_18-59__post-merge-refinement-2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/research-reconciliation-decisions.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/research-reconciliation-impl-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/scratch/legacy-memory-quarantine/16-12-25_00-00__anchor-id-validation-warning.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/scratch/legacy-memory-quarantine/16-12-25_20-48__anchor-enforcement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/scratch/legacy-memory-quarantine/16-12-25_20-27__anchor-enforcement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/scratch/legacy-memory-quarantine/16-12-25_00-00__anchor-enforcement-complete.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-structural-fix/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-structural-fix/summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/z-archive-deep-research-state-v1.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/research-reconciliation-spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/scratch/legacy-memory-quarantine/19-02-26_08-52__extraction-rollout-phases-2-3.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/description.json
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/002-extraction-rollout-phases-2-3/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/scratch/legacy-memory-quarantine/17-12-24_00-00__rename-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/scratch/legacy-memory-quarantine/17-12-25_00-00__testing-continuation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/scratch/legacy-memory-quarantine/17-12-25_00-00__verification-complete.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-4/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-4/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/scratch/legacy-memory-quarantine/22-12-25_14-51__memory-alignment-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/028-memory-alignment-fix/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/005-speckit-consolidation/scratch/legacy-memory-quarantine/17-12-25_00-00__speckit-consolidation-complete.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile-apply/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile-apply/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/files-changed.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/decision-record.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/test-results.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/feature-overview.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-audit/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-audit/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/context-index.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/024-comprehensive-alignment-fix/scratch/legacy-memory-quarantine/24-12-25_19-48__comprehensive-alignment-fix.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply/summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final-post-cleanup-2/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final-post-cleanup-2/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/013-memory-command-notation/fix-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/009-speckit-testing/scratch/legacy-memory-quarantine/17-12-25_00-00__speckit-testing-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/011-docs-alignment/scratch/legacy-memory-quarantine/17-12-25_00-00__speckit-docs-alignment-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/031-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_19-52__comprehensive-bug-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/089-speckit-reimagined-refinement/scratch/legacy-memory-quarantine/06-02-26_16-32__speckit-reimagined-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/089-speckit-reimagined-refinement/scratch/legacy-memory-quarantine/06-02-26_12-47__speckit-reimagined-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/089-speckit-reimagined-refinement/scratch/legacy-memory-quarantine/06-02-26_11-57__speckit-reimagined-refinement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/089-speckit-reimagined-refinement/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/test/test-folder-scoring.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/fsrs-algorithm-research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/021-runtime-contract-and-indexability/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/scratch/legacy-memory-quarantine/16-12-25_15-19__skill-alignment-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/070-memory-ranking/scratch/legacy-memory-quarantine/16-01-26_14-02__memory-ranking.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/008-rename-memory-check/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/001-scratch-enforcement/scratch/legacy-memory-quarantine/13-12-25_00-00__scratch-enforcement-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/001-scratch-enforcement/scratch/legacy-memory-quarantine/13-12-25_00-00__verification-and-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/memory-mcp-test-plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/decision-record.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/files-touched.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/final-recommendation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/004-memory-hook-cleanup/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/004-memory-hook-cleanup/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/004-memory-hook-cleanup/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/004-memory-hook-cleanup/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/004-memory-hook-cleanup/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/032-system-health-audit/index.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent-10-e2e/test-folder-a/scratch/legacy-memory-quarantine/test-memory-a.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/018-generate-context-fix/scratch/legacy-memory-quarantine/17-12-25_08-21__generate-context-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/018-generate-context-fix/scratch/legacy-memory-quarantine/17-12-25_07-37__generate-context-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/018-generate-context-fix/scratch/legacy-memory-quarantine/17-12-25_07-43__generate-context-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/018-generate-context-fix/scratch/legacy-memory-quarantine/16-02-26_14-50__implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/018-generate-context-fix/scratch/legacy-memory-quarantine/17-12-25_07-34__generate-context-fix.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/e2e-test-memory.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile-post/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile-post/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/scratch/legacy-memory-quarantine/23-01-26_20-17__speckit-upgrade-from-research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/scratch/legacy-memory-quarantine/23-01-26_20-35__speckit-upgrade-from-research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/26-12-25_09-02__speckit-test-suite.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/26-12-25_08-58__speckit-test-suite.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/26-12-25_09-04__speckit-test-suite.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/e2e-test-memory.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/26-12-25_09-11__speckit-test-suite.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/test-memory.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/legacy-memory-quarantine/26-12-25_10-09__speckit-test-suite.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/phase-quarantine/024-runtime-contract-and-indexability/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/084-generate-context-template-warnings/scratch/legacy-memory-quarantine/03-02-26_19-40__generate-context-template-warnings.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/084-generate-context-template-warnings/scratch/legacy-memory-quarantine/03-02-26_19-39__generate-context-template-warnings.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/084-generate-context-template-warnings/scratch/legacy-memory-quarantine/03-02-26_19-50__generate-context-template-warnings.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/084-generate-context-template-warnings/scratch/legacy-memory-quarantine/03-02-26_19-44__from-anobel.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/084-generate-context-template-warnings/scratch/legacy-memory-quarantine/03-02-26_19-44__generate-context-template-warnings.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/032-system-health-audit/scratch/legacy-memory-quarantine/25-12-25_10-02__system-health-audit.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/052-codebase-fixes/scratch/legacy-memory-quarantine/31-12-25_19-45__codebase-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/052-codebase-fixes/scratch/legacy-memory-quarantine/31-12-25_19-44__codebase-fixes.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent-02-search/TEST-REPORT.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/research/empirica-synthesis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/research/hooks-synthesis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/research/superego-synthesis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/research/smart-ralph-synthesis.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent-10-e2e/test-folder-b/scratch/legacy-memory-quarantine/test-memory-b.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/legacy-memory-quarantine/README.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/legacy-memory-quarantine/08-03-26_20-47__fixes-for-memory-pipeline-contamination.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/legacy-memory-quarantine/15-03-26_12-27__i-m-starting-with-the-repo-s-own-runbook-and.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/legacy-memory-quarantine/15-03-26_12-25__how-is-used-later-in-the-template-to-match-th.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/legacy-memory-quarantine/09-03-26_11-28__fixed-all-13-review-findings-from-gpt-5-4-triple.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-8.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/iterations/iteration-9.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent3/test-memory.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-audit/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-audit/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/056-spec-kit-references-reorganization/scratch/legacy-memory-quarantine/01-01-26_16-46__spec-kit-references-reorganization.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/065-anchor-system-implementation/scratch/fixture-memory.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/z-archive-deep-research-strategy-v1.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/088-speckit-known-limitations-remediation/scratch/legacy-memory-quarantine/05-02-26_15-58__speckit-known-limitations-remediation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-8.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/prompts/iteration-9.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/001-test-agent-08/scratch/legacy-memory-quarantine/26-12-25_09-04__test-agent-08.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/065-anchor-system-implementation/scratch/legacy-memory-quarantine/15-01-26_13-59__anchor-system-implementation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/065-anchor-system-implementation/scratch/legacy-memory-quarantine/15-01-26_13-32__anchor-system-implementation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/065-anchor-system-implementation/scratch/legacy-memory-quarantine/15-01-26_13-31__anchor-system-implementation.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/090-opencode-naming-conventions/scratch/legacy-memory-quarantine/06-02-26_18-46__opencode-naming-conventions.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-2/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-2/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-5/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-5/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/innovation-catalog.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/context-index.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-10.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-8.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-9.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-5.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-7.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-3.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-1.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-6.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-4.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deltas/iter-2.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final-post-cleanup/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final-post-cleanup/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/scratch/legacy-memory-quarantine/24-12-25_13-22__gate3-enforcement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/scratch/legacy-memory-quarantine/16-02-26_14-50__implementation-summary-v3.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/scratch/legacy-memory-quarantine/24-12-25_12-44__gate3-enforcement.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/scratch/legacy-memory-quarantine/16-02-26_14-50__constitutional-gate-rules.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/scratch/legacy-memory-quarantine/16-02-26_14-50__handover.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/030-gate3-enforcement/constitutional-memory-draft.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-final/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/047-constitutional-readme/scratch/legacy-memory-quarantine/27-12-25_11-55__constitutional-readme.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final-clean/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-final-clean/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/scratch/phase-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/scratch/100-percent-completion-closeout.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/context-index.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent-06-delete/scratch/legacy-memory-quarantine/test-delete-memory.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/scratch/legacy-memory-quarantine/01-01-26_15-57__cognitive-memory-upgrade.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/044-speckit-test-suite/scratch/test-agent-04-crud/scratch/legacy-memory-quarantine/test-crud-memory.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/055-cognitive-memory-upgrade/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-4/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-4/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/scratch/phase-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/CONTEXT.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/handover.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/decision-record.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/checklist.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/022-database-disambiguation/scratch/legacy-memory-quarantine/17-12-25_08-38__database-disambiguation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/iterations/iteration-008.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-speckit-bug-remediation/scratch/legacy-memory-quarantine/28-01-26_18-36__speckit-bug-remediation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/research/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/interim-synthesis-41-iterations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/findings-registry-segment-2.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/FINAL-synthesis-and-review.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/interim-synthesis-38-iterations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/segment-2-synthesis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-09__roampal-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-10__roampal-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-49__roampal-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-08__roampal-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-37__roampal-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/scratch/legacy-memory-quarantine/17-12-25_14-00__roampal-analysis.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/067-voyage-4-upgrade/scratch/legacy-memory-quarantine/15-01-26_19-02__voyage-4-upgrade.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/interim-synthesis-32-iterations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/interim-synthesis-47-iterations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/interim-synthesis-44-iterations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/closing-pass-notes.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/prompts/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/run-iterations.sh
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/001-memory-repo-analysis/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-056.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-054.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-052.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-055.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-053.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/deltas/iter-051.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-048.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-6-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-11-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/copilot-phase-1-audit-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/spec-doc-phase-3-validation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/deep-research-prompt-master-consolidation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-14-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-3-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/phase3-final-audit.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-5-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-12-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/research.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-051.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-041.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-055.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-045.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-054.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-044.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-050.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-057.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-047.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-053.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-043.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-052.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-042.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-056.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-046.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-049.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-16-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-1-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/copilot-phase-3-validate-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-7-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-10-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/copilot-phase-2-create-patch-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/spec-doc-phase-2-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-17-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/spec-doc-audit.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-18-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-4-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-13-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-9-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-15-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-2-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/phase3-integrity-audit.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/iteration-8-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-3/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final-3/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/020-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-06__comprehensive-bug-fix.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/phase3-validator-logs/postfix-summary.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/scratch/phase3-validator-logs/summary.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-post-apply/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-post-apply/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/002-copilot-hook-followup-deep-review-remediation/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/scratch/phase-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/context-index.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-final/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/scratch/legacy-memory-quarantine/16-02-26_14-50__implementation-summary-v2.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/scratch/legacy-memory-quarantine/16-02-26_14-50__session-context.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/scratch/test-bun-sqlite.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/handover.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-structural-final/manifest.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/003-memory-plugin-debugging/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/specs-wide-memory-remediation-structural-final/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/context-index.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-8.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/iterations/iteration-9.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-last-mile/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/prompts/research-prompt-implementation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/prompts/README.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/prompts/research-prompt-impact.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/implementation-design.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-10.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-8.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-9.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-5.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-7.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-3.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-1.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-6.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-4.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/deltas/iter-2.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/scratch/phase-research-prompt.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/phase-root-merge-note.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-5/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-5/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-8.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/research/001-copilot-hook-gap-deep-review-remediation/prompts/iteration-9.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/scratch/legacy-memory-quarantine/25-12-24_00-00__memory-system-merger.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/scratch/legacy-memory-quarantine/25-12-25_17-47__memory-speckit-merger.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/scratch/legacy-memory-quarantine/25-12-25_18-17__memory-speckit-merger.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/000-dynamic-capture-deprecation/003-multi-cli-parity/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-2/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/rigorous-memory-contract-apply-2/summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/verification-guide.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/scratch/legacy-memory-quarantine/16-02-26_14-50__documentation-updates.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/scratch/legacy-memory-quarantine/16-02-26_14-50__implementation-complete.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/scratch/legacy-memory-quarantine/16-02-26_14-50__comprehensive-analysis.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/description.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/graph-metadata.json
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/scratch/legacy-memory-quarantine/16-02-26_14-50__final-verification.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/027-memory-plugin-and-refinement/002-memory-plugin/scratch/legacy-memory-quarantine/16-02-26_14-50__mcp-server-fixes.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/testing/rollback.sh
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/testing/memory-restart.sh
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/testing/test-suite.sh
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/testing/README.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/035-memory-speckit-merger/testing/validation-checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/review/codex-and-code-graph-hook-deep-dive.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/03-scripts.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/04-templates.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/07-sub-readmes.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/05-commands-agents-docs.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/02-handlers.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/06-skill-surface-exhaustive.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/resource-map/01-schema.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/phase-017-rerun-seed.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/verify-phases-review.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-final-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/autonomous-execution-runbook.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-partial-generic/manifest.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/scratch/historical-memory-remediation-partial-generic/summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/compliance-manifest.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/research-pipeline-improvements.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/README.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/15--retrieval-enhancements.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/05--lifecycle.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/11--scoring-and-calibration.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/07--evaluation.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/01--retrieval.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/05--lifecycle.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/22--context-preservation-and-code-graph.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/17--governance.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/10--graph-signal-activation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/02--mutation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/19--feature-flag-reference.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/22--context-preservation-and-code-graph.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/01--retrieval.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/12--query-intelligence.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/18--ux-hooks.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/manual-playbook-results.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/16--tooling-and-scripts.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/17--governance.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/03--discovery.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/16--tooling-and-scripts.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/14--pipeline-architecture.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/13--memory-quality-and-indexing.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/03--discovery.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/manual-playbook-results.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/14--pipeline-architecture.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/21--implement-and-remove-deprecated-features.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/20--remediation-revalidation.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/21--implement-and-remove-deprecated-features.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/20--remediation-revalidation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/19--feature-flag-reference.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/18--ux-hooks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/10--graph-signal-activation.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/06--analysis.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/06--analysis.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/07--evaluation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/09--evaluation-and-measurement.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/09--evaluation-and-measurement.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/04--maintenance.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/13--memory-quality-and-indexing.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/08--bug-fixes-and-data-integrity.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/04--maintenance.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/12--query-intelligence.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/11--scoring-and-calibration.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/02--mutation.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/08--bug-fixes-and-data-integrity.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/gate-i-execution-report/15--retrieval-enhancements.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/scratch/shared-memory-audit.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/scratch/phase-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/iterations/iteration-009.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-19-checklist-assessment.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-18-cross-file-consistency.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-09-p2-fixes.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-13-alignment-drift.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-10-p3-and-regressions.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-04-alignment-medium.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-08-p1-fixes-part2.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-07-p1-fixes-part1.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-11-build-and-tests.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-01-alignment-extractors-large.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-22-spec-completeness.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-17-readme-verification.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-15-manual-tests-edge.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-05-alignment-small.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-20-error-paths.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-14-manual-tests-happy.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-23-final-synthesis.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-21-security-reaudit.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-16-feature-catalog-entry.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-02-alignment-workflow.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-12-runtime-quality.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-06-p0-fixes.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/qa/qa-03-alignment-collect.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/checklist.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/description.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/018-memory-save-quality-fixes/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/003-continuity-refactor-gates/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/iterations/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/iterations/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/iterations/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/iterations/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/iterations/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-051.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-041.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-055.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-045.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-054.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-060.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-044.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-050.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-040.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-057.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-047.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-053.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-043.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-052.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-042.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-056.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-046.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-059.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-049.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-058.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-048.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-039.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/prompts/synthesis.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C05.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C15.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C01.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C11.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C10.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C04.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C20.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C14.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C09.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C19.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C08.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C18.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C03.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C13.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C07.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C17.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C06.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C16.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C02.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/audits/audit-C12.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/live-cli-proof-2026-03-17.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/resource-map.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA9-C13-null-safety.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA6-C08-opencode-capture.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA2-C04-file-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA4-C05-spec-folder-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA5-O09-session-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R05-claude-code-logs.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R02-opencode-capture-analysis.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA5-O08-opencode-capture.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA4-C06-git-context-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-O20-quality-score.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R06-quality-scoring-gap.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R07-input-normalizer-enhancement.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA8-O13-dataflow.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA8-O17-contamination-bypass.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-O18-opus-synthesis.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA7-C12-contamination-types.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-deep-research-scratch.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA5-O10-decision-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-C19-test-recommendations.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA9-C17-regression.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA9-C16-test-coverage.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA9-C14-execsync-security.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA2-C02-collect-session-data.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA1-O03-input-normalizer.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-O19-reconciliation.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA3-O05-spec-folder-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R09-observation-decision-building.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA3-O07-integration.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA2-C03-input-normalizer.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA6-C10-decision-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA8-O14-type-contracts.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/RCA-memory-corruption-investigation.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-C20-remediation-plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA7-C11-config-filewriter.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R04-spec-folder-mining.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA3-O06-git-context-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA8-O15-imports.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R08-file-detection-enhancement.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA4-C07-integration.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R03-git-history-mining.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R01-code-path-trace.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA7-O12-slug-types.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA1-O04-file-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA7-O11-config-filewriter.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA2-C01-workflow.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA1-O01-workflow.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA8-O16-provenance.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA10-C18-copilot-synthesis.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA6-C09-session-extractor.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA1-O02-collect-session-data.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/R10-integration-architecture.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/agent-outputs/stateless-research/audit-QA9-C15-fs-security.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/prompts/README.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/graph-metadata.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis/analysis-X03.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis/analysis-X02.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis/analysis-X05.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis/analysis-X01.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/analysis/analysis-X04.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/remediation-manifest.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-2-review.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-3-review.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-1-planner-output.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-3-planner-output.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-2-planner-output.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-1-review.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/scratch/transcripts-snapshot/transcript-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/001-search-fusion-routing-research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-06-postflight-delta.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-04-workflow-triple.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-05-action-map.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-01-crypto-id.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-02-batch-rollback.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-07-config-wiring.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/009-perfect-session-capturing/research/fixes/fix-03-decision-confidence.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deep-review-impl-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/review-impl-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deep-review-impl-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deep-review-impl-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/review-impl-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deep-review-impl-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-025.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-033.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-048.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-009.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-029.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-044.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-013.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-005.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-052.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-053.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-004.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-012.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-045.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-028.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-008.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-049.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-032.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-024.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-039.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-042.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-015.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-003.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-054.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-023.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-035.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-019.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-058.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-059.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-018.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-034.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-022.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-055.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-002.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-014.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-043.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-038.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-056.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-001.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-017.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-040.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-037.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-060.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-021.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-020.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-036.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-041.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-016.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-057.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-031.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-027.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-050.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-007.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-011.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-046.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-047.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-010.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-006.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-051.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-026.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deltas/delta-030.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/research/next-research-paths.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deep-review-impl-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/implement-012-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/prompts/implement-codex.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-8.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/prompts/iteration-9.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deep-review-impl-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/scratch/cli-codex-review-2026-04-26.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/005-search-fusion-tuning-followup-review/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/008-graph-metadata-validation-followup-review/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/phrasing-audit.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/deep-review-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/scratch/archive-pass2/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/scratch/archive-pass2/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-034.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-030.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-031.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-035.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-032.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-036.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-026.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-037.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-027.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-033.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-038.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-028.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-029.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-advisor-phrase-booster-tuning/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/context-index.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/review-report.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/013-agents-alignment/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/run-all.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/dispatch-cli-opencode.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-prompts/deep-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/blocker.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-self-contained-package/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/Q1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/I2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/S1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/I3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/S3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/Q3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/I1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/Q2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/prompts/S2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/dispatch-cli-codex.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/scripts/dispatch-cli-copilot.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/review-report.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/iterations/iteration-001-codex53.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/iterations/iteration-001-gpt54.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/research.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/deep-research-config.json
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/004-ux-hooks-automation/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/validation-strict.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/001-search-fusion-tuning-prompts/deep-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/001-advisor-hook-baseline-research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/008-cmd-memory-speckit-revisit/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-prompts/deep-research-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/assets/code-graph-gold-queries.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/assets/recovery-playbook.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/assets/exclude-rule-confidence.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/assets/staleness-model.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/003-advisor-gap-investigation/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/runner-extend.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q3/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-024.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/scratch/codex-runner.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/scratch/readme-cleanup-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-021.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-025.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-022.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/scratch/sk-code-opencode-audit-prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/scratch/remediation-runner.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-023.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/research/002-advisor-hook-followup-research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/scratch/sk-code-opencode-audit-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/runner.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/scratch/test-prompts-all-clis.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/prompts/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/decision-record.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-007.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-010.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-006.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-001.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-003.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-002.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-005.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-009.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-008.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/deltas/iteration-004.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/runner.sh
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/B3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/applied/F35-calibration.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/code-graph-zero-calls-investigation.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/strategy-v2-iter020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/research-v2-iter020-snapshot.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/findings-registry-v1-iter010.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/dashboard-v2-iter020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/spec-pre-phase-decomposition.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/checklist-pre-phase-decomposition.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/research-v3-iter025-pre-expansion-snapshot.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/plan-pre-phase-decomposition.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/tasks-pre-phase-decomposition.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/research-v1-iter010-snapshot.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/research/archive/strategy-v1-iter010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-007.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-011.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-010.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-006.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-001.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-003.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-002.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-005.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-009.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-008.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-004.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/research/deltas/iteration-012.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-09.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-10.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-08.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-02.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-04.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-06.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-01.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-03.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-07.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deltas/iter-05.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/research_archive/rename-pivot-2026-04-26-pt-01/001-memory-terminology-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-020.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-014.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-015.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-011.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-016.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-012.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-013.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-017.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-018.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/iterations/iteration-019.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q2/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/030-code-graph-gap-investigation-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/prompts/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/prompts/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-hook-improvements-pt-02/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/research/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/013-code-graph-zero-calls-pt-03/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-008.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-013.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-011.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-015.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-017.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-012.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-016.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-014.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-018.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-019.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-020.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/research/015-code-graph-advisor-refinement-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I2/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I2/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deep-research-strategy.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-06.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-02.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-03.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-07.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-08.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-09.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-10.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-04.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-05.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/iterations/iteration-01.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/research.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/deep-research-dashboard.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/research/028-code-graph-hook-improvements-pt-01/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deep-research-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-010.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-009.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-008.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/findings-registry.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deep-review-state.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/iterations/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-007.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deep-research-config.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/fix-B4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/fix-B5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/fix-B1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-4.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-5.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-1.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-6.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/iteration-7.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/fix-B2.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/prompts/fix-B3.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/codex-skipped-research-recommendations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-007.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-003.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-004.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-005.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-001.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-006.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/prompts/iteration-002.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-001.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-003.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-005.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-002.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-004.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/research/deltas/iter-006.jsonl
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/codex-root-cause-memory-quality-gates.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-review-research-suggestions.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S3/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/manual-test-prompts-029-hooks/code-graph-hooks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/prompts/agent-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/refactor-surveys.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/cross-project-comparisons.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/architecture-audits.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/technical-investigations.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/pattern-mining.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/README.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/scratch/deep-research-prompts/unknown-unknowns.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S2/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/S1/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-brief.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/description.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/graph-metadata.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/checklist.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-codex-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-codex-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-codex-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/I1/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-opencode-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-opencode-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-opencode-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-copilot-1/meta.json
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-copilot-1/output.txt
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/runs/Q1/cli-copilot-1/prompt.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/scratch/manual-playbook-results/203/13--memory-quality-and-indexing.json

exec
/bin/zsh -lc "rg -n \"search bug|search|query|CocoIndex|coco|memory_search|memory_context|memory_quick_search\" specs .opencode -g '"'!*node_modules*'"' -g '"'!*.png'"' -g '"'!*.jpg'"'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 exited 2 in 321ms:
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/spec.md:141:| `graph-search-fn.ts` | Modify | S4: Spec folder hierarchy traversal |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/spec.md:209:- **NFR-P02**: N3-lite consolidation runs as weekly batch — no impact on query-time latency
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/spec.md:249:| Research | 8/20 | Research complete (142 analysis); algorithms identified but implementation details TBD |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/spec.md:274:Research evidence: See research documents `9 - analysis-pageindex-systems-architecture.md`, `9 - recommendations-pageindex-patterns-for-speckit.md`, `9 - pageindex-tree-search-analysis.md` in the parent research/ folder.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:35:- What worked and why: Tracing the documented emit commands against the actual helper interfaces exposed the mid-flight recovery gap much faster than searching for every possible artifact.
.opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md:12:This tool scans your project folders for new or changed files and adds them to the searchable knowledge base. It is like a librarian walking through the stacks every day to catalog new arrivals and update records for books that have been revised. Files that have not changed are skipped to save time. If a file fails to process, the system remembers and retries it next time.
.opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md:18:This is the tool that keeps the spec-doc record database synchronized with the filesystem. Without it, new or modified memory files would be invisible to search.
.opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md:20:Spec documents are still indexed by default. When a scan touches `spec.md`, `plan.md`, `tasks.md`, `checklist.md`, `decision-record.md`, `implementation-summary.md`, `research/research.md`, or `handover.md`, it routes that save through `memory_save` in warn-only quality mode so validation problems remain visible without dropping the document out of retrieval.
.opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md:22:The scanner discovers files from three sources: constitutional files under `.opencode/skills/*/constitutional/` (currently `.md`, excluding `README.md`/`README.txt`), canonical spec documents (`spec.md`, `plan.md`, `tasks.md`, `checklist.md`, `decision-record.md`, `implementation-summary.md`, `research/research.md`, `handover.md`), and graph metadata files (`graph-metadata.json`). The retired `specs/**/memory/*.md` surface is no longer discovered and the runtime rejects saves into it. Canonical path deduplication prevents the same file from being indexed twice under different paths (the `specs/` vs `.opencode/specs/` alias problem).
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/16-mcp-auto-priming.md:13:The spec-doc record-surface hook tracks session priming state. On the first tool call of any session, it assembles a PrimePackage with constitutional memories, code graph status snapshot, and any triggered memories from the current prompt. This package is injected into the MCP response hints, giving the AI runtime immediate context without requiring an explicit memory_context call. Subsequent tool calls skip priming (one-shot behavior). Priming status is exposed via session_health. Priming is now session-scoped via a Set<string> of primed session IDs rather than a process-global boolean, correctly handling multiple concurrent sessions.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:38:**Deep Research Addendum (2026-03-26)**
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:40:A 12-agent deep research campaign (~3.3M tokens, GPT-5.4 high/xhigh via Codex CLI) cross-referenced the audit against current source code and feature catalog. Key findings:
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:49:Full details: `../006-feature-catalog/research/deep-research-gap-report-2026-03-26.md` and `../006-feature-catalog/research/deep-research-round2-2026-03-26.md`.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:114:| 12 | `012-query-intelligence/` | 11 | Query Intelligence |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:142:| 1 | `001-retrieval/` | Audit 11 retrieval features (memory_context, memory_search, memory_continue, etc.) | None | Coverage sync required (8M/2P + 1 pending) |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:153:| 12 | `012-query-intelligence/` | Audit 11 query intelligence features | None | Complete (8M/3P) |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:190:| `012-query-intelligence/` | Query-intelligence audit packet | Live Query Intelligence catalog + 007 audit method | Phase findings and implementation summary | `007-code-audit-per-feature-catalog` |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:300:| Research | 15/20 | Source code investigation per feature |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:364:### Deep Research Gap Analysis
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/spec.md:366:A post-audit deep research cycle (10 iterations, 11 questions answered) identified five systemic gaps:
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md:12:This is the shared structural context contract for the code-graph family. It replaced inline readiness helpers in `query.ts` and propagated the same vocabulary to the other read and maintenance handlers that previously exposed inconsistent or missing readiness blocks.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md:23:- `queryTrustStateFromFreshness()`
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md:27:Commit `f253194bf` then propagated that contract to the six sibling handlers: `query.ts`, `scan.ts`, `status.ts`, `context.ts`, `ccc-status.ts`, `ccc-reindex.ts`, and `ccc-feedback.ts`.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md:31:The result is a single readiness surface across the code-graph family: callers can rely on `canonicalReadiness` and `trustState` being shaped by the same helper module instead of reconstructing per-handler differences. Downstream handlers can then add surface-specific metadata without changing that shared readiness vocabulary. The current example is `code_graph_context`, whose blocked path returns `status: "blocked"` plus `queryMode`, `blocked`, `degraded`, `graphAnswersOmitted`, `requiredAction`, `blockReason`, and `lastPersistedAt` while still embedding the shared readiness block under `data.readiness` and echoing `canonicalReadiness` and `trustState` at the top level.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/24-code-graph-readiness-contract.md:42:| `mcp_server/code_graph/handlers/query.ts` | Handler | Query-time readiness projection and graph metadata envelope |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:82:- [ ] `memory_search` returns unique results
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:351:When embedding regeneration fails after title change, metadata still updates but search is stale.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:492:Some documentation uses `leann_search()` while actual tool name is `leann_leann_search()`.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:497:| AGENTS.md | 482 | `leann_search()` | `leann_leann_search()` |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:498:| mcp-code-mode/SKILL.md | 480 | `leann_search({...})` | `leann_leann_search({...})` |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:502:- [ ] grep for `leann_search\(` (without double leann) returns no results
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/046-post-release-refinement-1/tasks.md:632:- **File:** `.opencode/commands/search/index.md`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/plan.md:254:2. **Selective cleanup**: Remove auto-created edges via `created_by='auto'` query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/plan.md:255:3. **Selective cleanup**: Remove auto-extracted entities via `created_by='auto'` query
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md:161:  - [x] search.md: Line 586
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md:174:  - [x] spec_kit_research_auto.yaml: 4 refs
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md:175:  - [x] spec_kit_research_confirm.yaml: 4 refs
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md:234:  - [x] `memory_search` tool accessible
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/025-system-memory-rename/tasks.md:242:  - [x] `/memory:search` command loads
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:7:1. The exact `/spec_kit:resume` -> `memory_context` invocation
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:18:1. `/spec_kit:resume` calls `memory_context` with the same four-field payload in both auto and confirm YAMLs: `input: "resume previous work continue session"`, `mode: "resume"`, `specFolder: "{...}"`, `includeContent: true`. The interactive workflow defines that payload once in `memory_loading.mcp_integration.parameters` and again in `workflow.step_3_load_memory.mcp_tool.parameters`; the autonomous workflow does the same in its `memory_loading` and `step_2_load_memory` blocks. The exact invocation is:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:19:   `memory_context({ input: "resume previous work continue session", mode: "resume", specFolder: "{spec_folder_path|detected_spec_folder}", includeContent: true })`. [.opencode/commands/spec_kit/assets/spec_kit_resume_confirm.yaml:81-85] [.opencode/commands/spec_kit/assets/spec_kit_resume_confirm.yaml:182-186] [.opencode/commands/spec_kit/assets/spec_kit_resume_auto.yaml:78-82] [.opencode/commands/spec_kit/assets/spec_kit_resume_auto.yaml:138-142]
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:21:2. `profile: "resume"` is missing from every executable `memory_context` parameter block in the resume workflow, even though the MCP contract explicitly supports `profile` for `memory_context` and enumerates `resume` as a valid value. In other words, the resume command is only selecting `mode: "resume"` today; it is not requesting the response formatter meant for resume-shaped output. The gaps are the four YAML parameter blocks above, while the schema and allowed-parameter lists already expose `profile`. [.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:40-44] [.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:100-116] [.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:453-455]
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:34:   `/memory:save` itself; `/spec_kit:handover` (it both mandates `generate-context.js` after handover and separately recommends `/memory:save`); `/spec_kit:plan`; `/spec_kit:implement`; `/spec_kit:complete`; `/spec_kit:debug`; `/spec_kit:deep-research`; and `/spec_kit:deep-review`. Today each of those workflows still documents a manual save boundary, so a future "Stop hook already saved context" rule would need to either suppress, downgrade, or conditionalize those instructions. [.opencode/commands/memory/save.md:73-75] [.opencode/commands/spec_kit/handover.md:215-216] [.opencode/commands/spec_kit/handover.md:256-264] [.opencode/commands/spec_kit/plan.md:303-315] [.opencode/commands/spec_kit/implement.md:195-201] [.opencode/commands/spec_kit/complete.md:311-315] [.opencode/commands/spec_kit/debug.md:304-309] [.opencode/commands/spec_kit/deep-research.md:198-209] [.opencode/commands/spec_kit/deep-review.md:234-245]
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:43:memory_context({
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:78:.opencode/commands/memory/search.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:81:.opencode/commands/spec_kit/deep-research.md
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:109:1. The executable resume workflow is still missing `profile: "resume"` in all four `memory_context` parameter blocks even though the tool contract already supports it.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:115:1. Add `profile: "resume"` to all four `memory_context` invocations in:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/iterations/iteration-029.md:122:   `handover`, `plan`, `implement`, `complete`, `debug`, `deep-research`, and `deep-review`.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json:3:  "packet_id": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json:4:  "spec_folder": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json:5:  "parent_id": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json:105:        "name": "Research Ref",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/graph-metadata.json:195:    "causal_summary": "Feedback & Quality Learning closes the loop between retrieval and ranking by collecting implicit signals from the calling AI and using them to improve future results. The D4 deep-research agent discovered the system is **more mature than expected**: quality gates already exist in `save-quality-gate.ts` (0.4 density, 0.92 dedup, 50 char min), reconsolidation exists in `reconsolidation-bridge.ts` (opt-in, checkpoint-gated), and learned feedback exists in `learned-feedback.ts` with 10 safeguards. The real gap is **signal collection from the calling AI**, not safeguard design.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:4:This iteration investigated D5 by tracing the active deep-research and deep-review stop path from the live auto YAML convergence steps into any shared convergence or contradiction helpers. The goal was to verify whether contradiction-aware blocking is live before STOP, or whether it still depends on shared graph wiring that the current workflows never invoke.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:7:- The live deep-research stop path still uses an inline 3-signal vote plus `checkQualityGuards(state, strategy)` and never names any graph or contradiction helper in the active convergence step, even while calling the graph-aware model "experimental/reference-only" for live runs (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:10:- The published deep-research contract says that when `graphEvents` exist, "the reducer builds an in-memory coverage graph and derives additional signals for the legal-stop gate evaluation," including graph coverage sub-checks (`.opencode/skills/sk-deep-research/references/convergence.md:1181-1205`). The live research reducer does not implement that bridge: its only imports are `fs` and `path`, and its convergence score is taken from `latestIteration.convergenceSignals?.compositeStop` or `latestIteration?.newInfoRatio` rather than any graph helper (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:15:- This is not limited to one loop. Both research and review convergence references promise graph-aware gate participation, but both active auto workflows keep STOP evaluation inline and local (`.opencode/skills/sk-deep-research/references/convergence.md:1181-1205`, `.opencode/skills/sk-deep-review/references/convergence.md:661-683`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:343-375`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:21:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:22:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:23:- .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:25:- .opencode/skills/sk-deep-research/references/convergence.md:1181-1205
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:27:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:28:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:35:- What worked and why: Reading the live auto YAML convergence steps beside the reducer imports made the reachable stop path much clearer than repo-wide helper searches alone.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:40:Rotate to D1 and test whether the research loop is missing convergence signals that the shared graph stack already knows how to compute. The next productive pass is to compare the live deep-research 3-signal stop math against the shared graph/MCP signal set (`contradictionDensity`, `sourceDiversity`, `evidenceDepth`, `claimVerificationRate`) and determine which of those are now concrete runtime gaps versus deliberate non-adoption.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/17-memory-roadmap-baseline-snapshot.md:12:Before rolling out a big upgrade, you want to take a "before" photo so you can compare it with the "after." This feature captures a snapshot of how the indexed-continuity store is performing right now, including how many searches are happening and whether the storage is set up correctly. That snapshot becomes the baseline you measure progress against during the rollout.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/checklist.md:46:- [x] CHK-S6-004b [P0] weight_history logging verified functional before any N3-lite Hebbian cycle runs — **EVIDENCE**: T001d complete; `weight_history` table created in migration v18 at mcp_server/lib/search/vector-index-schema.ts:529-544; `logWeightChange()` at mcp_server/lib/storage/causal-edges.ts:597-614 records before/after values; T-WH-01,T-WH-02 at mcp_server/tests/n3lite-consolidation.vitest.ts:219,236; T001d schema at mcp_server/tests/causal-fixes.vitest.ts:34-36 [EVIDENCE: documented in the phase packet and preserved during release normalization.]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/checklist.md:118:- [x] CHK-S6-060b [P1] S4 hierarchy traversal functional — **EVIDENCE**: active graph retrieval now augments results from `queryHierarchyMemories()` when `specFolder` is provided; pipeline test confirms `specFolder` propagation into graph search [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/checklist.md:121:- [x] CHK-S6-064 [P1] N3-lite edge bounds enforced — MAX_EDGES_PER_NODE=20, MAX_STRENGTH_INCREASE=0.05/cycle — **EVIDENCE**: `insertEdge()` rejects 21st auto edge (T-BOUNDS-02); Hebbian query now selects `created_by` so auto cap is enforced during strengthening (T-HEB-06); runtime hook executes on weekly cadence when enabled (T-CONS-05). [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/checklist.md:143:  - PI-A2 fallback chain integrated for empty graph query results
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/spec.md:170:| Research | 9/20 | Must trace each feature to source |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:2:title: "Feature Specif [system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:3:description: "Parent phase coordinating 5 sub-phases of research-driven improvements to the Hybrid RAG Fusion system across fusion scoring, query intelligence, graph retrieval, feedback learning, and retrieval UX."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:5:  - "research refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:8:  - "research-based improvements"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:9:  - "fusion query graph feedback ux"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:15:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:25:# Feature Specification: Research-Based Refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:49:The deep research (spec `019-deep-research-rag-improvement`) produced 29 prioritized recommendations from 5 GPT 5.4 agents (1.35M tokens, ~52 web searches). The key finding: the system is more mature than expected — the gap is **calibration and wiring**, not missing code. Flat heuristic constants (k=60, convergence +0.10, graph boost 1.5x, FSRS decay, Stage 2 signal weights) need data-driven calibration. Graph value lies in typed traversal, not community detection. Feedback needs an event ledger before any learned ranking.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:53:Turn the 29 research recommendations into 5 implementable sub-phases, each with concrete requirements, implementation phases, feature flags, and files to change.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:61:- 29 research recommendations across 5 dimensions
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:64:- New modules for feedback logging, graph lifecycle, query decomposition, result explainability
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:74:### Research Source
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:76:All recommendations come from the Phase 11 research output (historical, original path `019-deep-research-rag-improvement` no longer exists).
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:85:| 2 | `002-query-intelligence-reformulation/` | Decomposition, concept routing, LLM reformulation | #10, #11, #12, #24, #25 | Implemented |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:97:| REQ-011-002 | Implement D2 query intelligence and reformulation (5 items) | 002 | P1 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:103:| REQ-011-008 | Simple-query fast path latency preserved (sub-second p95) | All | P0 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:113:- SC-011-005: Simple-query p95 latency unchanged (regression test)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:130:| Dependency | D1 needs D3 graph signals for query-aware graph weight | D1 Phase C blocked | Execute D3 Phase A in Wave 1 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:134:| Risk | LLM reformulation adds latency to query path | Medium | Gate to deep/complex queries only; cache results |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:142:- Research source was in the Phase 11 scratch artifacts (original path `019-deep-research-rag-improvement/scratch/` no longer exists).
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:150:- 29 research recommendations from 5 GPT 5.4 agents
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md:151:- Research-based calibration and improvements
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:2:title: "Deep Research Report: Compact Code Graph — Complete Findings [system-spec-kit/024-compact-code-graph/research]"
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:3:description: "This research addresses two interconnected problems"
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:6:  - "research"
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:12:contextType: "research"
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:15:    packet_pointer: "system-spec-kit/024-compact-code-graph/research"
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:20:    key_files: ["research.md"]
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:23:# Deep Research Report: Compact Code Graph — Complete Findings
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:25:> **120 iterations across 9 segments** | final synthesis updated through Segment 9: OpenCode prompt-schema regression research
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:33:This research addresses two interconnected problems:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:37:2. **Code Graph** (Segments 1, 4): How to add structural code understanding to improve AI context selection, compaction quality, and recovery speed. Solution: Clean-room code graph channel using tree-sitter, integrated into the existing MCP search pipeline.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:49:| CocoIndex integration | **USE** — existing semantic layer, complements structural code graph | Iterations 036-045 + CocoIndex skill analysis |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:50:| CocoIndex ↔ Code Graph bridge | **BUILD** — file-range seeds, 1-hop expansion, reverse semantic augmentation | Iterations 046-055 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:51:| Token budget allocation | **FLOORS + OVERFLOW** — constitutional 700, graph 1200, CocoIndex 900, triggered 400, overflow 800 | Iteration 049 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:54:Fix `/spec_kit:resume` to pass `profile: "resume"` — verified defect in all 4 YAML blocks causing search-style output instead of compact recovery brief (Iteration 029).
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:70:                       └── memory_context(mode:"resume", profile:"resume")
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:87:**memory_context Resume Flow** (Iteration 017):
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:88:- Resume brief lives in **inner** `memory_search` envelope, NOT outer `memory_context` envelope
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:92:  - memory_context layer: **2000** tokens
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:94:- `SPECKIT_AUTO_RESUME` only gates post-search working-memory injection
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:125:- Mint via `memory_context` on first contact, reuse `effectiveSessionId` thereafter
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:164:## Part III: Code Graph — Comprehensive Research (Segment 4, Iterations 36-45)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:174:| **Sourcegraph Cody** | Hybrid search + code graph + `symf` + agentic | **Explicit code graph** | Not public |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:230:**Compression ratios** (from research):
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:311:| **Query layer** | ast-grep | MIT | Structural search on top of tree-sitter |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:325:| `code_graph_query` | L2/L3 (focused) | Exact structural query for symbols/edges |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:341:| **Semantic** | Conceptual similarity, natural-language relevance | Embeddings, memory search |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:383:│  │ Memory  │  │  Code    │  │ CocoIndex │  │
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:391:│       memory_context + code_graph_context    │
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:392:│       + cocoindex_code search                │
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:410:│  │ CocoIndex (.cocoindex_code/)         │   │
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:422:5. **Phase 009**: SQLite storage + code_graph_scan/query/status tools (2-3 days)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:423:6. **Phase 010**: code_graph_context + CocoIndex bridge — seed normalization, reverse semantic augmentation (3-4 days)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:436:| 3 | 016-035 | Implementation research (GPT-5.4) | 0.41-0.90 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:437:| 4 | 036-045 | Code graph research (GPT-5.4) | 0.73-0.88 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:438:| 5 | 046-055 | CocoIndex + Code Graph integration | 0.49-0.76 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:444:**Method**: Segments 1-2 mixed orchestrator + codex agents. Segments 3-5 GPT-5.4 agents via `codex exec -m gpt-5.4 -c model_reasoning_effort="high" --full-auto`, dispatched in parallel waves. Segment 6 used Claude Opus deep-research iterations. Segment 7 used GPT-5.4 via Copilot CLI for verification, runtime deep dives, and review revalidation.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:446:*Segment 7 local artifacts available at final synthesis time span iterations `076-089`, `091`, and the canonical `deep-research-state.jsonl`; standalone markdown files for `090`, `092`, `093`, and `094` were not present in the working tree, so their outputs are reconstructed in Part XI from the available evidence.*
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:457:| 017 | 166 | memory_context resume flow |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:462:| 022 | — | Query router & hybrid search (pending) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:473:| 033 | 48 | CocoIndex integration options |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:486:| 046 | 284 | CocoIndex ↔ Code Graph bridge design |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:487:| 047 | 70 | tree-sitter ↔ CocoIndex chunk alignment |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:494:| 054 | 549 | code_graph_context API with CocoIndex seeds |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:499:## Part VI: CocoIndex Integration Impact
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:501:### What CocoIndex Already Covers
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:503:CocoIndex Code is deployed as an MCP server providing semantic code search via vector embeddings:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:507:- **MCP tool**: single `search` endpoint for AI agent integration
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:514:| Build semantic index for code recall | **DROP** | CocoIndex already provides this |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:515:| Choose code embedding model | **DROP** | CocoIndex uses voyage-code-3 / all-MiniLM-L6-v2 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:516:| Implement code chunking for embeddings | **DROP** | CocoIndex handles function-level chunking |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:517:| Dual-index retrieval (code + text) | **DROP** | Already exists: CocoIndex (code) + Memory DB (text) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:518:| tree-sitter + SQLite structural graph | **KEEP** | Structural relationships CocoIndex can't provide |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:519:| code_graph_query / code_graph_context MCP tools | **KEEP** | Structural query API, not semantic |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:520:| Incremental graph updates (chokidar + git) | **KEEP** | Graph-specific, independent of CocoIndex |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:524:| Code graph API accepts CocoIndex results as seeds | **MODIFY** | Structural expansion of semantic hits |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:525:| Reranking uses graph edges for CocoIndex results | **MODIFY** | Structurally connected results rank higher |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:526:| Query-intent routing for code tasks | **MODIFY** | Route structural → code_graph, semantic → CocoIndex |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:527:| CocoIndex ↔ Code Graph bridge | **ADD** | Bidirectional enrichment between systems |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:533:| "Find code related to X" | CocoIndex (semantic) | Code graph (expand neighbors) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:536:| "How does retry logic work?" | CocoIndex (semantic) | Code graph (trace call chain) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:543:PreCompact pipeline (enriched with CocoIndex):
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:545:  2. CocoIndex: semantic neighbors of active symbols  ← EXISTING MCP
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:556:CocoIndex covering semantic search means the code graph can be **purely structural** and much simpler. No embeddings, no chunking, no vector search in the code graph at all. It becomes a lightweight relationship index that answers "what connects to what" while CocoIndex answers "what resembles what." The two complement each other without overlap.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:560:**Bridge Design** (iter 046): `code_graph_context` accepts file-range seeds directly from CocoIndex. Execution is parallel-then-sequential: Stage A (parallel semantic + graph bootstrap) → Stage B (cross-expansion) → Stage C (late fusion). Latency budget: <2s for PreCompact.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:562:**Chunk Alignment** (iter 047): CocoIndex uses structure-aware character chunking (~1000 chars), not true AST function-level splitting. Seed-to-node resolution: exact symbol → enclosing symbol → file anchor.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:564:**Intent Router** (iter 048): New top-level router separate from existing `query-router.ts`. Routes structural→code_graph, semantic→CocoIndex, session→Memory. MVP: keyword heuristics with telemetry.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:566:**Token Budget** (iter 049): Floors + overflow pool model. Constitutional 700, Graph 1200, CocoIndex 900, Triggered 400, Overflow 800. When a source is empty, its floor redistributes to overflow. Priority: constitutional > graph > CocoIndex > triggered.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:568:**Repo Maps** (iter 050): Query-ranked dynamic maps using typed graph edges + CocoIndex relevance scores. Improves on aider's flat reference counting.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:570:**Index Coordination** (iter 051): Independent refresh cycles for CocoIndex and Code Graph. Freshness state exposed in API. No shared event bus needed for v1.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:572:**Merge Strategy** (iter 052): Constitutional → graph → CocoIndex → triggered. Structured output sections. File-level deduplication.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:576:**API Design** (iter 054): Three query modes — neighborhood (expand around seeds), outline (structural overview), impact (reverse dependency). Seed types: CocoIndexSeed, ManualSeed, GraphSeed. Normalized to ArtifactRef internally.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:588:| Code Graph Query API | 5 missing operations: `extends_from/to`, `implements`, `tested_by/tests`, `contains/contained_by`, `search` | P2 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:590:| Budget Allocator | Needs adaptive weighting by query intent (structural→more graph, semantic→more CocoIndex), usage-based learning, dynamic overflow proportional to context budget, source-quality scoring | P2 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:592:| Hook System | Needs incremental graph refresh on Stop hook, pre-compaction graph snapshot, hook-based CocoIndex re-index trigger, cross-runtime parity patterns | P1 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:594:Key fix: **tree-sitter WASM migration** (web-tree-sitter + language grammars) resolves the endLine bug and enables accurate CALLS detection, DECORATES/OVERRIDES extraction, and proper nesting awareness. Dual-mode parser (tree-sitter primary, regex fallback) preserves backward compatibility. ~1.5MB additional WASM files (revised down from initial 8-15MB estimate: core ~300KB + 4 grammars ~1.2MB). The `parseFile()` interface is parser-agnostic -- `extractEdges()` and all downstream consumers (code-graph-db, code-graph-context, code-graph-query) need zero changes. Concrete S-expression queries designed for CALLS (`call_expression` + `member_expression`), IMPORTS (`import_statement` + `named_imports`), DECORATES (`decorator` + `decorated_definition`), OVERRIDES (`override_modifier` + name-match heuristic).
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:604:4. **Budget allocator 5 improvements**: (a) Intent-aware priority reordering (structural queries prefer codeGraph, semantic prefer cocoIndex). (b) Proportional overflow distribution with weighted shares instead of greedy first-come. (c) Minimum-floor protection during trim (never trim below 50% of floor). (d) Allocation metrics telemetry (demandRatio, overflowUtilization, dropRate). (e) Dynamic source registry pattern for future sources.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:608:**Automatic AI Utilization** (iter 057): Three-tier auto-enrichment architecture for code graph + CocoIndex without explicit tool calls:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:612:| T1: Session lifecycle | SessionStart / Compaction | Background incremental code_graph_scan + ccc_reindex; preload working set neighborhoods | Zero (background) | 300-500 tokens graph, 200-400 CocoIndex |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:614:| T3: Query-aware | memory_context/memory_search runs | Graph neighborhood expansion alongside semantic results; intent-based routing | Shares main budget | Via 3-source allocator (floors + overflow) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:620:- **Lazy per-file staleness checks via `ensureFreshFiles()`** (iter 067): On `code_graph_query`/`code_graph_context` call, extract touched file paths from results, run two-tier staleness check: (1) mtime fast-path comparing `statSync().mtimeMs` against stored `code_files.file_mtime_ms` (~1ms/file), (2) content hash verification only when mtime differs (~5-20ms/file). Hybrid sync/async reindex: <=2 stale files reindexed synchronously, 3-10 files deferred to async with `freshness.reindexInProgress: true` flag, >10 files triggers nextAction suggesting full scan. Requires `ALTER TABLE code_files ADD COLUMN file_mtime_ms INTEGER` schema extension (mirrors memory system's `memory_index.file_mtime_ms` pattern). CocoIndex coordination: code graph stores `lastStaleDetectedAt` timestamp; `ccc_status` checks it and triggers `ccc_reindex({ full: false })` if recent. Session-start batch: first MCP call triggers parallel `handleCodeGraphScan({ incremental: true })` + `cccReindex({ full: false })` via `resolveTrustedSession` session detection.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:628:- **Dedicated `extractFilePathHint(args)` needed**: Existing `extractContextHint` returns first match from `['input', 'query', 'prompt', 'specFolder', 'filePath']` which prioritizes query strings over file paths. Graph enrichment needs a file-path-specific extractor checking `['file_path', 'filePath', 'path', 'subject']` with path-shape validation.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:632:- **Working set data available but not leveraged**: session-prime.ts renders workingSet as text list but never feeds it to code_graph_query for structural preloading. Adding 3 lines to `handleStartup` injects file outlines for the top 5 recently-active files.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:641:| T2: Instruction-file triggers | CODEX.md / CLAUDE.md force memory_context() at session start | Codex CLI, Copilot, Gemini | Good (AI compliance dependent) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:646:- **CODEX.md already implements T2**: Explicit compaction recovery instructions with `memory_context({ mode: "resume" })` as first action.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:647:- **Agent definitions are cross-runtime identical**: `.opencode/agents/`, `.codex/agents/`, `.claude/agents/` all declare same MCP server access (`spec_kit_memory`, `cocoindex_code`) with same workflow.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:657:- **Per-tool priming behavior**: memory tools get full recovery hints (interrupted sessions, last spec folder, graph freshness); code graph tools get index freshness warnings; CocoIndex tools get availability status.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:659:- **CODEX.md gap identified**: No instruction-level trigger for code_graph_status() on session start. Enhancement: add `code_graph_status()` to "Context Retrieval Primitives" as third cross-runtime primitive alongside memory_match_triggers and memory_context.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:676:**CocoIndex Utilization Improvements** (iter 059): Five improvement areas for better CocoIndex integration:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:681:   - Propagate CocoIndex similarity score into ArtifactRef confidence (currently discarded)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:689:   - Keyword pre-classification: "who calls X" -> Code Graph impact; "find code that does X" -> CocoIndex search
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:690:   - Confidence-based fallback: low CocoIndex similarity (<0.3) -> fall back to code graph; file_anchor resolution -> suggest CocoIndex
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:691:   - Dual-query for ambiguous intents: execute both searches in parallel, merge via compact-merger
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:693:4. **Hybrid query patterns** (3 new patterns):
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:694:   - Structural expansion of semantic results: CocoIndex -> resolve seeds -> expand neighborhood automatically
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:695:   - Semantic enrichment of structural results: Code graph call chain -> CocoIndex finds similar non-connected code
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:696:   - Working set warm-up: code graph hot files + CocoIndex adjacent code on session start
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:698:5. **Underutilized CocoIndex features**:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:699:   - Language/path filters not passed through from code graph metadata to CocoIndex searches
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:715:- **Seed resolution** deepened: CocoIndex scores are discarded at integration seam, needs near-exact tier
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:733:| **P2-6** | Missing query API operations | 5/10 | ~100-150 LOC/op | Schema |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:736:| **P3-3** | Hybrid query patterns (3 patterns) | 5/10 | ~200-300 LOC | Seeds + router + indexes |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:749:| CocoIndex availability graceful degradation | Low | Partial |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:757:5. CocoIndex/Code Graph independence: true at index level, tightly integrated at query level
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:789:- **B1 Stale-on-read** (76-104 LOC): Add `ensureFreshFiles()` to `code-graph-db.ts`, `file_mtime_ms` schema column, mtime fast-path. Modify `handlers/code-graph/query.ts` and `context.ts` to call it.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:828:| 0 | Full | Code Graph + CocoIndex + Memory | Default | 3-source merge |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:829:| 1 | Graph-down | CocoIndex + Memory | `initDb()` throws or `getStats()` null | Skip codeGraph in MergeInput, log warning |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:830:| 2 | Graph+Coco-down | Memory only | CocoIndex binary missing AND graph unavailable | Constitutional + triggered memories only |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:833:Implementation: A `DegradationLevel` enum (0-3) computed once per session via `computeDegradationLevel()` that probes each source. Passed into `mergeCompactBrief` to reallocate token budgets (e.g., Level 1 moves code graph's 1200-token floor to CocoIndex and memory). Estimated: ~60 LOC.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:855:## Part X: Final Synthesis -- Complete Research Program Summary (95 Iterations)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:861:This research program evaluated, designed, specified, and then revalidated a comprehensive upgrade to the Spec Kit Memory MCP system's context preservation and code understanding capabilities. The program spanned 95 iterations across 7 segments, using four execution modes (orchestrator-driven research, parallel GPT-5.4 Codex agents, Claude Opus deep-research iterations, and GPT-5.4 verification passes via Copilot CLI).
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:866:3. **BUILD** clean-room structural code graph using tree-sitter + SQLite, integrated into existing MCP search pipeline
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:867:4. **USE** CocoIndex as complementary semantic layer -- no overlap with structural code graph
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:874:Segment 6 investigated four research questions with Claude Opus deep-research iterations:
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:884:- 3-tier auto-enrichment: T1 session lifecycle (background preloading), T2 tool dispatch (file-path-aware injection via GRAPH_AWARE_TOOLS interceptor), T3 query-aware (graph expansion alongside semantic results via 3-source allocator)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:895:**Q16 -- CocoIndex Utilization** (iterations 059, 063):
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:897:- CocoIndex score propagation: similarity scores currently discarded at integration seam; blend into ArtifactRef confidence
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:899:- 3 hybrid query patterns: structural expansion of semantic results, semantic enrichment of structural results, working set warm-up
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:930:| CocoIndex MCP roundtrip | N/A (not in hook path) | 100-500ms | Must be tool-dispatch-time only |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:939:- Level 0 (full): Code Graph + CocoIndex + Memory
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:940:- Level 1 (graph-down): CocoIndex + Memory (code graph DB unavailable)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:941:- Level 2 (graph+coco-down): Memory only (both unavailable)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:954:- `integration.test.ts`: Full pipeline E2E (scan -> query -> context -> enrich)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:993:All 16 research questions remain answered. Segment 7 converted the remaining uncertainty into a concrete verification and hardening backlog. The program is ready for implementation, but only with truth-sync and P1 hardening at the front of the queue.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1001:> **Segment 7 scope:** 20 planned verification iterations via `copilot -p` (GPT-5.4, high reasoning) across 5 waves of 4. The local workspace used for this final synthesis contains direct artifacts for iterations `076-089` and `091` plus the canonical `deep-research-state.jsonl`; standalone markdown files for `090`, `092`, `093`, and `094` were not present, so the scorecard, roadmap, and parity outputs below are reconstructed from the available segment evidence rather than quoted from absent files.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1012:Modified items included the exact wording of the `CALLS` failure mode (severely degraded, not universal zero), Phase B ownership (`context-server.ts` is mandatory and `code-graph-db.ts` belongs to stale-on-read/B1 rather than the minimal Phase A fix), and the status of the performance and auto-enrichment work (useful design budgets, but not yet live measured pipeline behavior). Several Q14/Q16 items -- `GRAPH_AWARE_TOOLS`, first-call priming, near-exact seed resolution, auto-reindex triggers, and hybrid query execution -- were reaffirmed as **recommended future work**, not shipped behavior.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1025:| **5** | Auto-enrichment features | Keep as post-hardening work | First-call priming, `GRAPH_AWARE_TOOLS`, auto-reindex triggers, and hybrid query patterns remain design-only until the earlier correctness/security work lands |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1035:| **OpenCode** | `AGENTS.md`, `.opencode/agents/*.md`, `spec_kit_resume_auto.yaml` | No native hooks | Add reusable Session Start Protocol + `code_graph_status()` in the earliest context-loading step; keep graph expansion query-driven | **~90%** |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1036:| **Codex CLI** | `AGENTS.md`, `.codex/agents/context.toml` | No native hooks | Force first-turn `memory_context(...)` + `code_graph_status()` via instructions; do not rely on hook-style implicit warmup | **~85%** |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1048:This tally is intentionally conservative: it reflects only the Segment 7 verification evidence present locally (`076-089`, `091`, and `deep-research-state.jsonl`) rather than inventing results for missing standalone artifacts.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1062:> **Segment 8 scope:** 10 targeted research iterations via `copilot -p` (GPT-5.4, high effort) investigating concrete, implementable improvements for non-hook CLI context preservation. Each iteration examined a specific capability gap with file-level source references, LOC estimates, and cross-runtime parity impact projections.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1068:Key finding: the existing MCP server already contains most of the primitives needed for cross-runtime parity. The gap is not missing infrastructure but **missing coordination** -- priming payloads live in response metadata instead of actionable recovery context, code graph freshness is fragmented across multiple helpers, query routing is orphaned, and tool workflows require 3-5 manual calls instead of one composite operation.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1076:| 098 | Code graph auto-trigger | Lazy indexing on first query (C) + mtime staleness (B) + docs (D) | 170-360 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1077:| 099 | Query-intent routing integration | Auto-routing in memory_context (A) + classification metadata (D) | 150-300 |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1093:3. **Lazy code graph indexing** (Iter 098): Add `ensureCodeGraphReady()` to `code_graph_context` and `code_graph_query` so non-hook CLIs get automatic graph indexing on first structural query. Only sessions using graph tools pay the cost.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1097:4. **session_resume composite tool** (Iter 101): Single MCP tool combining `memory_context(resume)` + `code_graph_status` + `ccc_status`. Saves 400-900 tokens and 2-4 request/response cycles per resume flow.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1099:5. **Query-intent routing in memory_context** (Iter 099): Wire orphaned `classifyQueryIntent()` into `memory_context` so structural queries auto-route to code graph. Universal benefit across all runtimes.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1129:3. **`classifyQueryIntent()` is ready to wire in.** The orphaned classifier returns `structural | semantic | hybrid` with confidence scores. Wiring it into `memory_context` as a backend router (not just a mode selector) would unify the query experience.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1146:| 017 | 166 | memory_context resume flow |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1151:| 022 | -- | Query router and hybrid search (pending) |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1162:| 033 | 48 | CocoIndex integration options |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1175:| 046 | 284 | CocoIndex-Code Graph bridge design |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1176:| 047 | 70 | tree-sitter-CocoIndex chunk alignment |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1183:| 054 | 549 | code_graph_context API with CocoIndex seeds |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1188:| 059 | ~200 | CocoIndex utilization: seed resolution, auto-reindex, hybrid queries |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1199:| 070 | ~250 | Performance analysis: 1800ms budget, SQLite <10ms, CocoIndex 100-500ms |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/research.md:1236:At the same time, the visible startup digest became inconsistent or disappeared in later sessions. The key research question was whether these were two separate regressions or one shared prompt-assembly fault.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:2:title: "LLM query reformulation"
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:3:description: "Corpus-grounded LLM query reformulation applies step-back abstraction combined with real corpus seed grounding to produce enriched query variants in deep mode, gated by the SPECKIT_LLM_REFORMULATION flag."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:7:# LLM query reformulation
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:11:Corpus-grounded LLM query reformulation applies step-back abstraction combined with real corpus seed grounding to produce enriched query variants in deep mode, gated by the `SPECKIT_LLM_REFORMULATION` flag.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:13:Sometimes a user's query is too specific or uses different vocabulary than what is stored. This feature rewrites the query using an LLM, but grounds it in actual corpus content first to prevent hallucination. It retrieves a few real results via cheap keyword search, feeds them to the LLM alongside the query, and asks for a step-back abstraction plus a couple of alternative phrasings. The result is better recall without making up terms that do not exist in the data.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:19:The reformulation module performs a two-step process: (1) cheap seed retrieval via FTS5/BM25 keyword search (no embedding call, up to `SEED_LIMIT = 3` results) to ground the prompt in real corpus content, then (2) a single LLM call to produce a step-back abstraction and up to `MAX_VARIANTS = 2` corpus-grounded query variants. Timeout is `REFORMULATION_TIMEOUT_MS = 8000ms`. Output strings shorter than `MIN_OUTPUT_LENGTH = 5` characters are rejected.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:21:LLM results are cached via a shared LLM result cache (key: normalized query + mode, TTL 1 hour) imported from `llm-cache.ts`, also shared with the HyDE module. Budget: at most 1 LLM call per reformulation. Combined with HyDE: at most 2 total LLM calls per deep query.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:35:| `mcp_server/lib/search/llm-reformulation.ts` | Lib | Seed retrieval, LLM reformulation, step-back abstraction, variant generation |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:36:| `mcp_server/lib/search/llm-cache.ts` | Lib | Shared LLM result cache (used by both reformulation and HyDE) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:37:| `mcp_server/lib/search/sqlite-fts.ts` | Lib | FTS5/BM25 keyword search for seed retrieval |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:38:| `mcp_server/lib/search/search-flags.ts` | Lib | `isLlmReformulationEnabled()` flag accessor |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:39:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage 1 integration: invokes reformulation in deep mode |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:45:| `mcp_server/tests/search-flags.vitest.ts` | Flag behavior for LLM reformulation |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:52:- Source feature title: LLM query reformulation
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:53:- Current reality source: mcp_server/lib/search/llm-reformulation.ts module header and implementation
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/13-tree-sitter-wasm-parser.md:30:| `mcp_server/code_graph/lib/grammars/` | Assets | Tree-sitter query files per language |
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/13-tree-sitter-wasm-parser.md:31:| `mcp_server/code_graph/lib/queries/` | Assets | S-expression query patterns for symbol extraction |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:60:  - Acceptance criteria: Recall@20 within 10% of pre-thinning baseline on eval query set.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:65:  - Sub-steps: (1) Parse spec folder path from memory metadata. (2) Build in-memory hierarchy tree at query time (or cached). (3) Add hierarchy-aware traversal to `graph-search-fn.ts`. (4) Return parent/sibling memories as contextual results.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:67:  - **EVIDENCE**: `spec-folder-hierarchy.ts` created — buildHierarchyTree, getRelatedFolders, queryHierarchyMemories; relevance scoring (self=1.0, parent=0.8, sibling=0.5). 46 tests passing in `s6-s4-spec-folder-hierarchy.vitest.ts`.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:71:    - Sub-steps: (1) Candidate generation — cosine similarity >0.85 pair query. (2) Conflict check — keyword negation heuristic (contains "not", "never", contradicts prior claim). (3) Flag pair + surface cluster. (4) Write `contradiction_flag` to memory record.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:138:  - [x] S4 hierarchy traversal functional — **EVIDENCE**: `graph-search-fn.ts` now augments graph retrieval with `queryHierarchyMemories()` when `specFolder` is present, and pipeline integration confirms `specFolder` propagation to graph search.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:141:  - [x] N3-lite edge bounds enforced (MAX_EDGES_PER_NODE=20, MAX_STRENGTH_INCREASE=0.05/cycle) — **EVIDENCE**: `insertEdge()` rejects 21st auto edge (T-BOUNDS-02); Hebbian cap honors `created_by='auto'` after query fix (T-HEB-06); runtime hook `runConsolidationCycleIfEnabled()` enforces weekly cadence (T-CONS-05).
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/tasks.md:179:  - Research evidence: See `9 - analysis-pageindex-systems-architecture.md`, `9 - recommendations-pageindex-patterns-for-speckit.md`, `9 - pageindex-tree-search-analysis.md` in the parent research/ folder
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:4:This pass investigated the remaining D3 namespace-isolation question by tracing `sk-improve-agent`'s `mutation-coverage.cjs` against the shared coverage-graph SQLite DB, MCP query handlers, and convergence handler. The goal was to confirm whether `loop_type: "improvement"` actually lands in the shared store and whether any shipped read surface can co-mingle improvement-session nodes with research/review sessions.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:9:- The shared SQLite coverage graph does not admit `improvement` loop types at all. The DB layer defines `LoopType = 'research' | 'review'`, constrains valid kinds/relations by those two namespaces, and the schema enforces `CHECK(loop_type IN ('research', 'review'))`; the MCP upsert handler repeats the same validation and rejects any other value (`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:17`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:136-146`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:152-157`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:51-53`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:72-80`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:10:- Because the shipped shared-store path accepts only `research` and `review`, improvement-session nodes cannot currently co-mingle with deep-research or deep-review nodes inside the shared SQLite store through the visible MCP boundary. The more accurate finding is contract drift: Section 11 and Known Context both frame the improvement namespace as if it persists into the shared store, but the live writer and validator surfaces show a separate local JSON graph instead (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`, `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`, `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:599`, `.opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:59-67`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:76-78`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:11:- A different namespace-isolation weakness does exist on the shared read side for research/review sessions: the convergence handler never accepts `sessionId`, constructs its namespace from only `{ specFolder, loopType }`, and then calls `getStats()` plus `computeSignals()` / `computeMomentum()` without session scoping, so convergence decisions aggregate all sessions sharing the same spec folder and loop type (`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:47-52`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:92-111`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:511-545`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-220`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:12:- The query surface only partially exposes session isolation. `handleCoverageGraphQuery()` accepts `sessionId` and passes it into `ns`, but the inspected helper queries for coverage gaps, contradictions, and unverified claims read by `spec_folder` and `loop_type` only, ignoring `ns.sessionId`; this means research/review sessions can be co-mingled on read even though improvement-mode entries are blocked from the DB entirely (`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:55-58`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-126`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:136-147`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:15:- The visible MCP coverage-graph path is not currently allowing `loop_type: "improvement"` to pollute shared research/review graphs; the stronger risk is documentation/strategy drift plus missing per-session read isolation inside the research/review namespaces.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:18:- I did not inspect hidden executor internals outside the published skill, workflow, and MCP handler surfaces, so the negative claim stays scoped to the shipped writer/validator/query path that is visible in-repo.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:21:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:31:- `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:33:- `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:34:- `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/15-evaluation-api-surface.md:41:| `mcp_server/tests/api-public-surfaces.vitest.ts` | Direct export contract for the public eval/search barrels and top-level API barrel parity |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-111-120.md:1:# Research Synthesis: Iterations 111-120 — OpenCode Prompt-Schema Regression
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/04-confidence-based-result-truncation.md:33:| `mcp_server/lib/search/confidence-truncation.ts` | Lib | Confidence-based truncation |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:2:title: ".../022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:3:description: "Calibrate fusion heuristics, build shadow fusion lab, implement query-aware graph weight, per-query fusion routing, and learned Stage 2 weights."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:16:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:41:| **Successor** | `../002-query-intelligence-reformulation/spec.md` |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:50:This is **Phase 1** of the Research-Based Refinement specification.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:52:**Scope Boundary**: Fusion calibration, shadow fusion lab, query-aware graph weight, per-query fusion routing, and learned Stage 2 weights. All changes target the Stage 2 (Fusion & Scoring) layer with controlled additions to Stage 1 candidate generation for graph weight gating.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:75:The current fusion pipeline relies on flat heuristic constants: a fixed RRF K=60, a flat convergence bonus of +0.10, a static graph boost of 1.5x, and hard-coded Stage 2 signal weights. Deep research (5 GPT 5.4 agents, 1.35M tokens) identified these as the primary gap -- the code is mature but the calibration is not data-driven. Without query-aware tuning, literal ID lookups receive the same fusion treatment as multi-hop causal queries, leaving measurable retrieval quality on the table.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:79:Replace flat fusion heuristics with data-driven, query-aware scoring across the Stage 2 pipeline, achieving measurable MRR@5 and NDCG@10 improvement while preserving simple-query latency and providing shadow infrastructure for safe experimentation.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:110:| `shared/search/hybrid-search.ts` | Modify | Query-aware graph weight gating |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:111:| `shared/search/adaptive-fusion.ts` | Modify | Fusion policy router, QPP feature extraction |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:112:| `shared/search/stage1-candidate-gen.ts` | Modify | Graph weight parameterization from router |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:126:| REQ-D1-001 | **Calibrated Overlap Bonus** — Replace flat +0.10 convergence bonus with query-aware bounded feature that scales with channel hit ratio and mean normalized score. | S | `SPECKIT_CALIBRATED_OVERLAP_BONUS` | Overlap bonus scales with channel count, capped at 0.06, eval shows no regression on existing test queries |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:135:| REQ-D1-005 | **Intent Router Selects Fusion Family** — Route between RRF, score fusion, and graph-heavy fusion based on QPP features (score spread, channel agreement). Cross-dep: needs D1-002 shadow lab results. | M | `SPECKIT_FUSION_POLICY_ROUTER` | Fusion family selection active for all query types, fallback to RRF preserved, eval shows improvement over static RRF |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:142:**Research Source**: Recommendation #1
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:156:**Research Source**: Recommendation #8
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:166:Historical design note: the shadow lab was planned to run all three fusion policies in parallel on each query but only return the active policy's results. Telemetry would have captured per-policy NDCG@10, MRR@5, and latency for later analysis.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:170:**Research Source**: Recommendation #9
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:184:**Research Source**: Recommendation #22
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:185:**Files**: `shared/search/hybrid-search.ts`, `shared/search/adaptive-fusion.ts`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:188:const graphEligible = intent in ['understand', 'find_decision'] && !looksLikeLiteralId(query);
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:198:**Research Source**: Recommendation #23
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:199:**Files**: `shared/search/adaptive-fusion.ts`, `shared/search/stage1-candidate-gen.ts`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:203:else if (looksLikeLiteralId(query)) policy = 'rrf';
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:213:**Research Source**: Recommendation #28
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:232:- **SC-D1-001**: MRR@5 improvement >= +1 point across the eval query set
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:233:- **SC-D1-002**: NDCG@10 improvement >= +1 point across the eval query set
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:236:- **SC-D1-005**: Shadow fusion lab captures telemetry for all 3 policies per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:250:| Risk | Graph weight gating false negatives — intent classifier may incorrectly demote graph for queries that need it | Medium | Conservative threshold (default graph-eligible), A/B shadow comparison, per-query telemetry for debugging |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:263:- **NFR-P01**: Simple-query p95 latency must not increase (sub-second preserved)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:268:- **NFR-R01**: All new capabilities remain feature-flagged; rollout state may graduate to default-on after validation, but effective flag state must remain reproducible and logged per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:273:- **NFR-O01**: Shadow lab telemetry records per-policy NDCG@10, MRR@5, and latency per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:274:- **NFR-O02**: Feature flag state logged on each query for reproducibility
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:287:- Empty query: Intent classifier returns `unknown`; fusion defaults to RRF with K=60
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:295:- Feature flag toggled mid-session: Next query uses new policy; no session state to invalidate
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:309:| Research | 12/20 | Research complete; implementation requires eval infrastructure |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:320:- What is the acceptable shadow lab overhead budget per query? (Proposed: 15ms p95)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:327:- [Parent Spec](../spec.md) -- Research-Based Refinement coordination
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:332:- [Sibling: D2 Query Intelligence](../002-query-intelligence-reformulation/spec.md) -- Successor phase
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:335:- Research Source (historical, path removed) -- Recommendations #1, #8, #9, #22, #23, #28
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:338:LEVEL 2 SPEC — Phase 1 of 5 (Research-Based Refinement)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md:340:- 6 requirements from research recommendations
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:4:This iteration investigated D5 by tracing whether the current deep-loop runtimes actually read coverage-graph state or `graphEvents` during convergence and stop-gating, or whether graph data is only emitted and left for optional downstream tooling. The scope covered the active deep-research and deep-review workflow surfaces plus the shared convergence and contradiction modules they would need to call.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7:- The shared graph-convergence handler does implement real stop-gating against persisted graph state: it computes graph signals, then evaluates research/review blockers using `findCoverageGaps()`, `findContradictions()`, and `findUnverifiedClaims()` before returning `STOP_ALLOWED`, `STOP_BLOCKED`, or `CONTINUE` (.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:20-25; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:109-163; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:245-275; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:343-355).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:8:- The active loop workflow surfaces I inspected only require agents to emit `graphEvents`; they do not show any corresponding `deep_loop_graph_upsert`, `deep_loop_graph_query`, or `deep_loop_graph_convergence` invocation in the same runtime path. In the checked YAMLs, graph handling appears as an iteration-record output contract, not a read-back decision step (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326; .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:436-437).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:9:- The deep-research reducer still operates on iteration markdown sections plus JSONL rows filtered to `type === "iteration"`, then rebuilds packet outputs from those inputs; there is no reducer-owned path here that parses or promotes `graphEvents` into strategy, registry, or dashboard state. That means the synchronized packet surfaces remain blind to graph-aware stop evidence unless some other process reads the graph separately (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:10:- Contradiction handling is split across layers: the CJS helper can scan in-memory `CONTRADICTS` edges, but the active convergence handler actually blocks on contradictions through the TypeScript query layer (`findContradictions(ns)`), which implies graph-aware contradiction blocking depends on a populated persisted namespace rather than on raw JSONL `graphEvents` alone (.opencode/skills/system-spec-kit/scripts/lib/coverage-graph-contradictions.cjs:37-67; .opencode/skills/system-spec-kit/scripts/lib/coverage-graph-contradictions.cjs:85-129; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:20-25; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:255-257; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:353-355).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:18:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:19:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:20:- .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:22:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:23:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:25:- **CR-P1-5:** Cache lookup moved before embedding readiness gate in search handler.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:41:| `mcp_server/lib/search/pipeline/stage2-fusion.ts` | Lib | Re-sort behavior after feedback mutations before top-K slicing |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:42:| `mcp_server/lib/search/vector-index-queries.ts` | Lib | Dedup/orphan query hardening with `parent.parent_id IS NULL` filters |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:43:| `mcp_server/lib/search/evidence-gap-detector.ts` | Lib | `Number.isFinite` guards for score safety |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:47:| `mcp_server/handlers/memory-search.ts` | Handler | Search-handler flow fix moving cache lookup ahead of the embedding-readiness wait |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:53:| `mcp_server/tests/integration-search-pipeline.vitest.ts` | Pipeline and guard behavior validation |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/14-cross-ai-validation-fixes.md:58:| `mcp_server/tests/hybrid-search.vitest.ts` | Search-handler ordering and integration behavior |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/implementation-summary.md:47:The follow-up pass closed the wiring gaps that mattered for release confidence: chunk thinning now runs before child writes, encoding intent persists through active and deferred indexing paths, hierarchy traversal augments graph search when `specFolder` is present, and the N3-lite runtime hook now runs on the intended cadence with bounds enforced during strengthening.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/007-sprint-6-indexing-and-graph/implementation-summary.md:61:3. Hardened runtime call sites after review so the documented features were exercised by the actual indexing and search paths.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:3:description: "Composite MCP tool (session_resume) that merges memory resume context, code graph status, CocoIndex availability, and structural bootstrap hints into a detailed recovery payload."
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:12:Composite MCP tool (session_resume) that merges memory resume context, code graph status, CocoIndex availability, and structural bootstrap hints into a single recovery payload.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:14:The `session_resume` handler performs three recovery steps: (1) a filesystem-first resume ladder via `buildResumeLadder()` that reconstructs session state from `handover.md -> _memory.continuity -> spec docs`, (2) code graph status lookup returning freshness-aware `fresh | stale | empty | error` values plus counts and last scan timestamp, and (3) CocoIndex binary availability probing. It also appends the shared structural `ready | stale | missing` contract from `session-snapshot.ts`, so callers can tell when a deeper refresh is needed. Results are merged into a `SessionResumeResult` with `memory`, `codeGraph`, `cocoIndex`, optional `structuralContext`, and `hints` fields. For the canonical first-call recovery step, use `session_bootstrap`; for operator-facing packet recovery, start from `handover.md -> _memory.continuity -> spec docs`; `session_resume` remains the detailed merged surface.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:20:`session_resume` is the detailed merged recovery surface behind the higher-level `/spec_kit:resume` workflow. The handler still merges the resume ladder, code-graph status, CocoIndex availability, and structural bootstrap hints into one response, but Phase 017 added a transport-bound auth check around any explicit `args.sessionId`.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:24:The rest of the merged recovery payload is unchanged in shape: `memory` still comes from the `handover.md -> _memory.continuity -> spec docs` ladder, `codeGraph` still reports freshness-aware graph state, `cocoIndex` still reports binary availability, and `structuralContext` plus `hints` still explain whether the caller should escalate to `session_bootstrap` or `code_graph_scan`. Phase 017 therefore hardened who may resume a session without changing the overall recovery contract that callers consume.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/18-session-resume-tool.md:38:| `mcp_server/code_graph/lib/code-graph-db.ts` | Lib | Code graph status query |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/03-single-and-folder-delete-memorydelete.md:39:| `mcp_server/lib/search/vector-index.ts` | Lib | Vector index facade for `deleteMemory()` |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/03-single-and-folder-delete-memorydelete.md:44:| `mcp_server/lib/search/graph-search-fn.ts` | Lib | Degree cache clearing after delete |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:2:title: ".../022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:3:description: "Four-phase implementation plan for D1 fusion calibration, shadow fusion lab, query-aware routing, and learned Stage 2 weights across the 4-stage retrieval pipeline."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:14:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:43:This plan implements 6 research recommendations (#1, #8, #9, #22, #23, #28) that calibrate fusion heuristics and introduce data-driven scoring across the Stage 2 pipeline. The approach follows a strict progression: **calibrate first** (Phase A establishes baselines and replaces flat constants), **build shadow infrastructure** (Phase B enables safe experimentation), **wire query-awareness** (Phase C introduces intent-based routing), and **learn weights last** (Phase D trains on accumulated data). All features are gated behind independent feature flags with fallback to existing behavior.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:56:- [ ] Judged relevance query set identified (minimum 50 queries)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:63:- [ ] Simple-query p95 latency unchanged
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:82:- **hybrid-search.ts**: Search orchestrator -- receives query-aware graph weight gating (Phase C)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:158:**Goal**: Make fusion policy and graph weight respond to query characteristics instead of using static values.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:163:- [ ] Implement `looksLikeLiteralId()` query classifier
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:164:- [ ] Implement query-aware graph weight in `hybrid-search.ts`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:171:- [ ] Run eval comparing static vs query-aware fusion (target: +2-6 NDCG@10 on graph queries)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:201:| Latency | Simple-query p95 regression per phase | benchmark | 4 benchmark runs |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:221:| Judged relevance query set | Data requirement | Yellow — needs curation | K-optimization and learned weights need labeled data; minimum 50 queries per intent |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:287:2. Verify eval metrics return to baseline within 1 query cycle
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:303:- [Parent Spec](../spec.md) -- Research-Based Refinement coordination
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:307:- Research Source (historical, path removed) -- Recommendations #1, #8, #9, #22, #23, #28
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md:310:LEVEL 2 PLAN — Phase 1 of 5 (Research-Based Refinement)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:1:# Research Synthesis: Iterations 106-110 — Hookless Context Priming Optimization
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:24:The overlap is partial: both check graph status and CocoIndex, but only agent priming does memory resume and only MCP priming does constitutional memory injection and session-primed state management.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:30:Cold-start latency is dominated by `memory_context(resume)` -- the other 3 calls in the bootstrap are nearly free. The existing `primeSessionIfNeeded()` already provides a sub-50ms minimum viable prime with graph freshness, CocoIndex availability, and recommended next calls.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:46:`buildServerInstructions()` is the only truly pre-LLM surface available without hooks. Currently it only reports memory counts and search channels. Adding a compact session recovery digest (last spec folder, last task, graph freshness, recommended first action) at ~150-400 tokens would give every runtime pre-LLM startup steering at connection time.
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:60:6. Strengthen tool descriptions for `memory_context`, `session_resume`, `session_health` with recovery affordances
.opencode/specs/system-spec-kit/024-compact-code-graph/research/synthesis-106-110.md:63:7. Create `session_bootstrap()` composite tool that returns memory + graph + CocoIndex + health in one call
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/spec.md:50:2. **MCP Server Core**: Fixed semantic-memory.js, vector-index.js, hybrid-search.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/spec.md:63:- `hybrid-search.js` - useDecay forwarding, result shape consistency, init validation, FTS5 escaping
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/03-channel-min-representation.md:13:Imagine you ask a librarian for book recommendations and they only check one shelf, ignoring everything else in the library. This feature makes sure that every search method that found something useful gets at least one result in the final answer. That way you see a diverse set of results instead of one dominant source drowning out everything else.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/03-channel-min-representation.md:33:| `mcp_server/lib/search/channel-representation.ts` | Lib | Core analysis: detects under-represented channels, appends promoted items (no re-sort) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/03-channel-min-representation.md:34:| `mcp_server/lib/search/channel-enforcement.ts` | Lib | Pipeline wrapper: delegates to core, re-sorts globally by score, returns enforcement metadata |
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:19:- Repo-wide symbol search for the new D3 modules surfaced mostly docs, specs, changelog entries, and tests, which limited negative-proof evidence to the runtime files that do exist.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:23:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:45:Rotate to D4 and audit reducer write boundaries against the published machine-owned anchor contracts. The most productive next pass is to compare the deep-research, deep-review, and sk-improve-agent reducers against their target markdown/state assets and verify whether they ever rewrite human-owned sections or anchor ranges outside the declared machine-owned zones. That would close the remaining self-compliance question without reopening the already-settled D3 persistence analysis.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:10:4. [vector-index.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:1)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:21:5. `vectorIndex.getDb` is available via re-export at [vector-index.ts:134](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:134) (implemented as `get_db()` at [vector-index-store.ts:687](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-store.ts:687), aliased at [vector-index-store.ts:863](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-store.ts:863))
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:45:4. [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:1)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:46:5. [vector-index.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:1)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:55:3. `getGraphMetrics()` exists at [hybrid-search.ts:261](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:261), exported at [hybrid-search.ts:1819](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:1819)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:56:4. `vectorIndex.getStatusCounts` re-export exists at [vector-index.ts:86](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:86), implemented as `get_status_counts()` at [vector-index-queries.ts:157](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-queries.ts:157)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:87:7. [vector-index.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:1)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/codex53-verifier.md:98:5. `vectorIndex.verifyIntegrity` usage path exists (re-export at [vector-index.ts:107](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts:107), implementation `verify_integrity` at [vector-index-queries.ts:1284](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-queries.ts:1284))
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/checklist.md:2:title: "...hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/checklist]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/checklist.md:14:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence"
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/10-full-reporting-and-ablation-study-framework.md:20:The framework uses dependency injection for the search function, making it testable without the full pipeline. Statistical significance is assessed via a sign test using log-space binomial coefficient computation (preventing overflow for n>50, fixed in Sprint 8). Verdict classification ranges from CRITICAL (channel removal causes significant regression) through negligible to HARMFUL (channel removal actually improves results). Results are stored in `eval_metric_snapshots` with negative timestamp IDs to distinguish ablation runs from production evaluation data. The framework runs behind the `SPECKIT_ABLATION` flag. Token-usage aggregation now filters to finite values greater than zero, so ablation reports stop emitting synthetic `0` token rows when `runAblation()` has no real token-usage samples to aggregate.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/10-full-reporting-and-ablation-study-framework.md:22:The reporting dashboard aggregates per-sprint metric summaries (mean, min, max, latest and count) and per-channel performance views (hit count, average latency and query count) from the evaluation database. Trend analysis compares consecutive runs to detect regressions. Sprint labels are inferred from metadata JSON. A `isHigherBetter()` helper correctly interprets trend direction for different metric types. The dashboard now calls `getEvalDb()` before falling back to `initEvalDb()`, which preserves an already-selected non-default or test eval DB instead of silently switching back to the default one. Its request `limit` is the number of sprint groups kept after grouping, not the number of raw eval runs fetched. Both the ablation runner and the dashboard are exposed as new MCP tools: `eval_run_ablation` and `eval_reporting_dashboard`.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:2:title: "Index-time query surrogates"
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:3:description: "Index-time query surrogates generate surrogate metadata (aliases, headings, summaries, heuristic questions) at index time for improved recall without runtime LLM calls, gated by the SPECKIT_QUERY_SURROGATES flag."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:7:# Index-time query surrogates
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:11:Index-time query surrogates generate surrogate metadata (aliases, headings, summaries, heuristic questions) at index time for improved recall without runtime LLM calls, gated by the `SPECKIT_QUERY_SURROGATES` flag.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:13:A document might be the perfect answer to a question but use completely different words. This feature solves that by pre-generating alternative descriptions of each document at index time: abbreviations, headings, short summaries, and likely questions the document answers. At query time, these surrogates are matched against the incoming query with a lightweight token overlap check — no LLM calls needed. It is like writing the index cards for a library catalog in advance so lookups are fast.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:25:At query time, Stage 1 batch-loads stored surrogates from SQLite and matches them against the incoming query using token overlap. A match requires a minimum overlap ratio of `MIN_MATCH_THRESHOLD = 0.15`. The runtime matcher `matchSurrogates()` returns `{ score, matchedSurrogates }` for one document; the exported `SurrogateMatchResult` interface is stale because it still includes `memoryId`, but memory IDs actually come from the surrounding candidate rows in Stage 1. Stage 1 applies the returned match score as a capped additive boost to existing candidates.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:27:Enabled by default (graduated). Set `SPECKIT_QUERY_SURROGATES=false` to disable. Also has a flag accessor in `search-flags.ts`.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:37:| `mcp_server/lib/search/query-surrogates.ts` | Lib | Alias extraction, heading extraction, summary generation, surrogate question generation, query-time matching |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:38:| `mcp_server/lib/search/surrogate-storage.ts` | Lib | SQLite table initialization plus single/batch surrogate load and store helpers |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:39:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage 1 integration: batch-loads surrogates and applies capped additive boosts to existing candidates |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:40:| `mcp_server/lib/search/search-flags.ts` | Lib | `isQuerySurrogatesEnabled()` flag accessor |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:46:| `mcp_server/tests/query-surrogates.vitest.ts` | Flag behavior, alias extraction, surrogate matching |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:53:- Source feature title: Index-time query surrogates
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:54:- Current reality source: mcp_server/lib/search/query-surrogates.ts, mcp_server/lib/search/surrogate-storage.ts, mcp_server/lib/search/pipeline/stage1-candidate-gen.ts, and mcp_server/lib/search/search-flags.ts
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/plan.md:32:│   ├── Agent 3: Core libs (embeddings, vector-index, hybrid-search)
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/plan.md:75:| 3 | hybrid-search.js | useDecay, result shape, FTS5 escaping |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/plan.md:97:├── Agent 2: vector-index.js, hybrid-search.js - All 8 fixes
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/spec.md:34:A comprehensive 10-agent research sweep across all 42 specs with code verification has identified **39 unique, verified open issues** that require resolution.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/spec.md:147:- research-findings.md - All spec summaries
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:7:- `sk-deep-research`'s active reducer does not implement the shared-graph bridge: it only imports `node:fs` and `node:path`, and the only reducer references matching `graph|convergence|upsert|deep_loop` are pass-through reads of precomputed `convergenceSignals`, not graph parsing or MCP calls (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:246-247; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:271; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:442).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:8:- Both deep-loop convergence contracts still document a reducer-owned in-memory graph bridge that is not present in the live reducer: deep research says "the reducer builds an in-memory coverage graph" when `graphEvents` exist, and deep review says the same for review iterations (.opencode/skills/sk-deep-research/references/convergence.md:1181-1205; .opencode/skills/sk-deep-review/references/convergence.md:658-683).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:11:- The 042 graph-integration packet explicitly recorded the intended bridge as already implemented: its implementation summary says the reducer parses `graphEvents`, calls `deep_loop_graph_upsert`, and falls back through `JSONL -> local JSON graph -> SQLite projection`, which sharpens this audit result into a current reality gap between packet claims and runtime wiring (.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:12:- `sk-improve-agent` follows a different path entirely: its resume contract replays a local "coverage graph + registry", and `mutation-coverage.cjs` persists an `improvement` JSON graph with `fs`/`path` helpers and `loopType: 'improvement'`, while the agent only consumes an orchestrator-provided summary as advisory context. That means it does not supply the missing shared `deep_loop_graph_*` bridge for research/review convergence (.opencode/skills/sk-improve-agent/SKILL.md:294-300; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:9-10; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:21; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:50-67; .opencode/agents/agent-improver.md:175-177).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:15:- No hidden bridge appeared in the active reducer path: the deep-research reducer still has no MCP/tool client imports and no graph-event parsing branch, so the bridge is not merely buried deeper in the same file (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:246-247).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:21:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:22:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:23:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:24:- .opencode/skills/sk-deep-research/references/convergence.md:1181-1205
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:28:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:34:- What worked and why: Comparing live reducer imports and search hits against the documented bridge contract made the missing runtime handoff explicit very quickly.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:35:- What did not work and why: Repo-wide symbol search still surfaced older packet/spec artifacts, so I had to keep separating "promised by 042 docs" from "called by active runtime code."
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:39:Rotate to D4 and verify whether the documented lineage modes and stop-state persistence are actually exercised by the live workflows: compare the deep-research/deep-review YAMLs, reducer inputs, and JSONL event handling to see whether `resume`, `restart`, `fork`, `completed-continue`, and `blockedStop` with full gate payloads survive the normal runtime path or remain primarily contractual/documented behavior.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/15-code-graph-auto-trigger.md:15:Packet 013 made this visible to callers instead of leaving it as an internal helper concern. When `code_graph_query` or `code_graph_context` hits a `full_scan` readiness result and inline indexing does not complete, the handlers return an explicit blocked payload with:
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/15-code-graph-auto-trigger.md:22:`code_graph_query` also preserves the original `operation` and `subject`, while `code_graph_context` preserves the requested `queryMode`. This page therefore describes both the helper's auto-trigger behavior and the caller-visible blocked contract layered on top of it.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/15-code-graph-auto-trigger.md:40:| `mcp_server/code_graph/handlers/query.ts` | Handler | Returns the caller-visible blocked `code_graph_query` payload when readiness requires a full scan |
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/15-code-graph-auto-trigger.md:43:| `mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts` | Test | Verifies the explicit blocked query payload for `full_scan` readiness |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/009-sprint-8-deferred-features/spec.md:126:- Deferred runtime follow-on moved into `010-sprint-9-extra-features` and `011-research-based-refinement`; remaining release truth-sync is tracked in `012-pre-release-fixes-alignment-preparation`.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:2:title: "...022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:3:description: "Detailed task breakdown across 4 phases: calibration foundations, shadow infrastructure, query-aware fusion, and learned weights."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:14:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:84:  - **Acceptance**: Module accepts judged query set with relevance labels, computes NDCG@10 and MRR@5 per K value
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:85:  - **Hint**: The judged query set should be a typed array: `{ query: string, intent: IntentClass, relevantIds: string[], labels: Map<string, number> }`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:108:  - **Acceptance**: Tests cover: metric computation correctness, intent segmentation, tie-breaking (lower K wins), empty query set handling, fallback when flag OFF
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:137:  - **Acceptance**: Runs all 3 policies on each query, returns active policy result, captures per-policy NDCG@10, MRR@5, and latency as telemetry
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:146:  - **Acceptance**: Flag defaults to OFF; when ON, shadow comparison runs on each query; when OFF, only active policy runs (no overhead)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:162:**Goal**: Make fusion policy and graph weight respond to query characteristics.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:168:- [ ] T018 Implement `looksLikeLiteralId()` query classifier (`shared/search/adaptive-fusion.ts`) — 3h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:172:- [ ] T019 Implement query-aware graph weight in `hybrid-search.ts` (`shared/search/hybrid-search.ts`) — 4h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:177:    const graphEligible = intent in ['understand', 'find_decision'] && !looksLikeLiteralId(query);
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:182:- [ ] T020 Add `SPECKIT_GRAPH_QUERY_GATING_V1` feature flag with fallback to static weight (`shared/search/hybrid-search.ts`) — 1h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:184:  - **Acceptance**: Flag defaults to OFF; when OFF, existing static graph weight unchanged; when ON, query-aware gating active
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:186:- [ ] T021 [P] Write integration tests for graph weight gating (`shared/search/__tests__/hybrid-search.test.ts`) — 3h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:188:  - **Acceptance**: Tests cover: literal ID query gets weight 0.2, understand query gets elevated weight, find_decision query gets elevated weight, unknown intent gets default, flag OFF preserves static weight
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:192:- [ ] T022 Implement QPP features: score spread and channel agreement (`shared/search/adaptive-fusion.ts`) — 4h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:197:- [ ] T023 Build fusion policy router based on QPP features and intent (`shared/search/adaptive-fusion.ts`) — 4h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:199:  - **Acceptance**: Router selects fusion family per query: `minmax_linear` when QPP low and spread high, `rrf` for literal IDs, `rrf+graph` for graph-eligible queries with high graph quality
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:203:    else if (looksLikeLiteralId(query)) policy = 'rrf';
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:207:- [ ] T024 Add `SPECKIT_FUSION_POLICY_ROUTER` feature flag with fallback to RRF (`shared/search/adaptive-fusion.ts`) — 1h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:209:  - **Acceptance**: Flag defaults to OFF; when OFF, all queries use RRF; when ON, router selects policy per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:211:- [ ] T025 [P] Write integration tests for fusion routing (`shared/search/__tests__/adaptive-fusion.test.ts`) — 3h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:215:- [ ] T026 Run eval comparing static vs query-aware fusion — 3h
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:291:- [ ] Simple-query p95 latency unchanged
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md:315:LEVEL 2 TASKS — Phase 1 of 5 (Research-Based Refinement)
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:14:  "mode": "research",
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:34:    "deep-research-config.json": "immutable",
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:35:    "deep-research-state.jsonl": "append-only",
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:36:    "deep-research-strategy.md": "mutable",
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:37:    "deep-research-dashboard.md": "auto-generated",
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-config.json:39:    "research/research.md": "mutable"
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:3:description: "Describes the dedicated SQLite evaluation database, its five-table schema and the fail-safe logging hooks that capture retrieval quality data without affecting production query flow."
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:10:Describes the dedicated SQLite evaluation database, its five-table schema and the fail-safe logging hooks that capture retrieval quality data without affecting production query flow.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:12:When you want to know how well your search results are performing, you need a safe place to store that measurement data. This feature keeps all quality-tracking records in a separate storage area so they never mix with or interfere with the actual search results you rely on. If the measurement process ever hits a problem, your searches keep working normally as if nothing happened.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:18:A separate SQLite database (`speckit-eval.db`) stores retrieval quality data in five tables: `eval_queries`, `eval_channel_results`, `eval_final_results`, `eval_ground_truth` and `eval_metric_snapshots`. Keeping evaluation data in its own database is a deliberate security decision. The main search database should never carry evaluation artifacts that could leak into production results.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:20:Logging hooks in the search, context and trigger handlers are best-effort and fail-safe: they run only when `SPECKIT_EVAL_LOGGING=true`, and all write paths are wrapped in non-fatal `try/catch` blocks so query responses continue even if eval logging fails. `memory_search` and `memory_context` emit per-channel rows. `memory_match_triggers` emits query/final-result rows.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:30:| `mcp_server/lib/eval/eval-db.ts` | Lib | Evaluation database schema, table creation, and query helpers |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/01-evaluation-database-and-schema.md:31:| `mcp_server/lib/eval/eval-logger.ts` | Lib | Fail-safe logging hooks that write query, per-channel, and final-result rows to the eval database |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:14:This is how you add new knowledge to the system. You point it at a file and it reads, understands and stores the content so it becomes searchable. Before storing, it checks whether the same information already exists and decides whether to add it fresh, update an older version or skip it entirely. Quality checks catch low-value content before it clutters up the knowledge base.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:22:The canonical router now classifies save chunks across 8 categories: `narrative_progress`, `narrative_delivery`, `decision`, `handover_state`, `research_finding`, `task_update`, `metadata_only`, and `drop`. Tier 1 handles structured and heuristic routes, Tier 2 compares against the routing prototype library, and Tier 3 is now wired into the live save handler by default and the configured LLM endpoint is available. Delivery cues now favor sequencing, gating, rollout, and verification language over generic implementation verbs, while the handover/drop boundary keeps hard transcript or telemetry wrappers on the refuse-to-route side and lets softer operational phrases survive when the chunk is clearly a stop-state note.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:28:Phase 017 tightened the canonical writer contract in two places. Commit `aaf0f49a8` fixed H-56-1 so every successful canonical save refreshes packet metadata instead of treating repeat saves as a structural no-op, and commit `88063287b` added the research-tree follow-up that backfills missing `description.json` and `graph-metadata.json` files under research iteration folders when the saved packet owns those children. That means a successful `memory_save` now updates the merged spec doc, the packet metadata, and any newly missing research metadata surfaces in one canonical pass.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:45:For large files exceeding the chunking threshold, the system splits into a parent record (metadata only) plus child chunk records, each with its own embedding. Before indexing, anchor-aware chunk thinning scores each chunk using a composite of anchor presence (weight 0.6, binary) and content density (weight 0.4, 0-1). Chunks scoring below 0.3 are dropped to reduce storage and search noise. The thinning never returns an empty array. Chunk embedding cache keys now hash normalized content, matching the main embedding path, so structurally equivalent chunks reuse the same cache entry.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:51:The `asyncEmbedding` parameter (boolean, default `false`) enables non-blocking saves. When set to `true`, embedding generation is deferred: the spec-doc record is written immediately with a `pending` embedding status, and an async background attempt generates the embedding afterward. The spec-doc record is immediately searchable via BM25 and FTS5 while the embedding processes. When `false` (the default), the save blocks until embedding generation completes before returning. Watcher- and ingest-driven reindex paths no longer force deferred embeddings on ordinary cache misses. They follow this normal synchronous path unless `asyncEmbedding: true` was explicitly requested or embedding generation actually fails.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:53:Safety mechanisms run deep. Path security validation checks the file against an allowlist of base paths. File type validation accepts only `.md` and `.txt` in approved directories. Pre-flight validation checks anchor format, detects duplicates and estimates token budget before investing in embedding generation. A per-spec-folder mutex lock prevents TOCTOU race conditions when multiple saves target the same folder. SHA-256 content hashing skips same-path saves only when the existing row is in a healthy state (`success`, `pending`, or valid chunked-parent `partial`), so unhealthy rows still re-enter indexing. Cross-path hash dedup also accepts chunked parents in `partial` state and ignores invalid parent rows marked `complete`. A mutation ledger records every create, update, reinforce and supersede action for audit. The trigger matcher cache, tool cache and constitutional cache are all invalidated on write, and `memory_index_scan` now routes scan-triggered invalidation through the broader mutation-hook behavior used by other mutation paths. If embedding generation fails, the spec-doc record is still stored and searchable via BM25/FTS5 with the embedding marked as pending for later re-indexing.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:55:Successful insertions now clear the search cache immediately instead of waiting for delete-time invalidation or TTL expiry. `index_memory()` calls `clear_search_cache()` after the transactional insert, active-projection update and optional `vec_memories` write succeed, so a brand-new spec-doc record becomes visible to repeated `memory_search` calls right away. The fix closes a stale-results gap where the save path could report success while cached searches still replayed a pre-insert snapshot.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/01-memory-indexing-memorysave.md:84:| `scripts/memory/backfill-research-metadata.ts` | Script | Research-tree metadata backfill step invoked from the canonical save workflow |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:3:description: "The query complexity router classifies incoming queries by term count and trigger match to select how many search channels run."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:11:The query complexity router classifies incoming queries by term count and trigger match to select how many search channels run.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:13:Not every question needs the same amount of effort to answer. This feature sizes up your question first, like a triage nurse, and routes simple lookups through a fast path while sending complex research questions through a deeper search. Without it, every question would get the full heavy-duty treatment, wasting time and resources on things that could be answered in seconds.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:23:The `SPECKIT_COMPLEXITY_ROUTER` flag is **enabled by default** (graduated Sprint 4, `isComplexityRouterEnabled()` returns `true` unless explicitly set to `"false"`). When the flag is disabled, the classifier returns "complex" as a safe fallback so every query still gets the full pipeline. The minimum 2-channel invariant is enforced at the router level.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:25:The router's classification tier (`routeResult.tier`) is propagated into `traceMetadata.queryComplexity` in hybrid search (CHK-038), making it available in response envelopes when `includeTrace: true`. The formatter reads this via a fallback path from `traceMetadata` when stage metadata is unavailable.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:35:| `mcp_server/lib/search/query-classifier.ts` | Lib | Query complexity classification |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:36:| `mcp_server/lib/search/query-router.ts` | Lib | Channel routing |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:37:| `mcp_server/lib/search/hybrid-search.ts` | Lib | Trace propagation (`routeResult.tier` -> `traceMetadata.queryComplexity`, CHK-038) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:43:| `mcp_server/tests/query-classifier.vitest.ts` | Query classification accuracy |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:44:| `mcp_server/tests/query-router-channel-interaction.vitest.ts` | Channel interaction tests |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:45:| `mcp_server/tests/query-router.vitest.ts` | Query routing logic |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:54:| Tier routing uses only `termCount` + `triggerMatch` | `query-classifier.ts` | 170-180 |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:55:| `charCount` / `stopWordRatio` used for confidence only | `query-classifier.ts` `determineConfidence()` | 97-122 |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:56:| Flag default is enabled (`raw !== 'false'`) | `query-classifier.ts` `isComplexityRouterEnabled()` | 43-46 |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:57:| Tier propagated to `traceMetadata.queryComplexity` | `hybrid-search.ts` | CHK-038 |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:58:| Classification accuracy tests | `query-classifier.vitest.ts` | — |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/description.json:2:  "specFolder": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/description.json:18:    "011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/scratch/reaudit-2026-03-23/gpt54-analyst.md:10:Evidence: aggregate payload fields are assembled at [memory-crud-stats.ts:305](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L305); ranking modes and count-vs-scoring split are in [memory-crud-stats.ts:177](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L177) and [memory-crud-stats.ts:205](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L205); scoring fallback is at [memory-crud-stats.ts:229](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L229); `totalSpecFolders` is captured before slicing at [memory-crud-stats.ts:251](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L251); graph metrics come from [hybrid-search.ts:261](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts#L261); validation/error envelopes are in [memory-crud-stats.ts:67](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L67), [memory-crud-stats.ts:155](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L155), and [memory-crud-stats.ts:279](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-stats.ts#L279); tests confirm truncation, ranking modes, and fallback at [handler-memory-stats-edge.vitest.ts:189](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-stats-edge.vitest.ts#L189) and [memory-crud-extended.vitest.ts:1040](/Users/michelkerkmeester/MEGA/Development/Opencode%20Env/Public/.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts#L1040).
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/checklist.md:43:- [x] **BUG-009**: Forward `useDecay` parameter in hybrid-search.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/checklist.md:62:- [x] **MED-001**: Add init validation in hybrid-search.js
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/checklist.md:123:- [x] **VER-003**: All hybrid-search.js fixes verified
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/12-compact-merger.md:3:description: "Compact merger combines context from Memory, Code Graph, and CocoIndex into a unified compact brief within the 4000-token budget."
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/12-compact-merger.md:11:Compact merger combines context from Memory, Code Graph, and CocoIndex into a unified compact brief within the 4000-token budget.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:4:This iteration rotated to D4 and audited whether the shipped reducers for `sk-deep-research`, `sk-deep-review`, and `sk-improve-agent` write outside their declared machine-owned zones. The scope was limited to reducer write paths, target markdown/state assets, and the published ownership contracts for strategy, dashboard, registry, and report surfaces.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:7:- `sk-deep-research` is anchor-scoped and fail-closed on strategy writes. Its reducer only replaces the `key-questions`, `answered-questions`, `what-worked`, `what-failed`, `exhausted-approaches`, `ruled-out-directions`, and `next-focus` anchor blocks, and it throws if any requested anchor is missing; that matches the research strategy contract declaring sections 3 and 6-11 reducer-rewritten while leaving sections 1, 2, 4, 5, 12, and 13 stable (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-331`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:353-366`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:8:- The same `sk-deep-research` reducer only writes three outputs in its normal pass: `findings-registry.json`, `deep-research-strategy.md`, and `deep-research-dashboard.md`. I found no reducer path that touches iteration markdown or any other human-authored research asset during refresh (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:11:- `sk-deep-review` is fail-open where `sk-deep-research` is fail-closed: if an expected anchor is missing, `replaceAnchorSection()` returns the original content instead of halting, and the reducer still writes the resulting strategy file back out. That prevents cross-anchor spill into adjacent human-owned sections, but it also means corrupted or missing machine-owned zones can silently persist (`.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:431-445`, `.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:640-645`).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:23:- `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:24:- `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:41:Rotate to D5 and inspect the live convergence math plus its callers to determine whether the coverage graph contributes materially to stop gating or only decorates already ratio-driven decisions. The most productive next pass is to trace the research/review convergence helpers and any YAML/runtime call sites that pass graph-derived signals, then compare the documented graph-aware stop language against the actual weight each graph-backed signal carries in the final composite and blocking decisions.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/plan.md:79:| P1-004 | Wire includeContiguity through to search | 1.5h | Phase 1 |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/plan.md:88:- [ ] Checkpoint restore preserves semantic search capability
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/12-test-quality-improvements.md:24:**P2c:** Four tautological flag tests in `integration-search-pipeline.vitest.ts` were rewritten to test actual behavioral differences instead of testing what they set up.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/12-test-quality-improvements.md:46:| `mcp_server/tests/integration-search-pipeline.vitest.ts` | Reworked flag tests to validate behavior deltas |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:13:When you ask a complex question that covers multiple topics at once (for example "What is the spec-doc record save workflow and how does query expansion work?"), the system may fail to find good results because it tries to match everything at once. This feature detects coordinating conjunctions ("and", "or", "also") and multiple wh-question words to split such queries into focused sub-queries. Each sub-query retrieves independently, and results are merged by facet coverage. This only activates in deep mode, where the extra retrieval cost is acceptable.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:21:The `isQueryDecompositionEnabled()` function in `search-flags.ts` checks the flag. The `query-decomposer.ts` module performs bounded facet detection:
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:26:- Graceful fallback: if the Stage 1 decomposition branch errors, execution falls through to the standard deep expansion path rather than returning only the original query; if no expansion variants are produced, the original query remains as the fallback.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:37:| `mcp_server/lib/search/query-decomposer.ts` | Lib | Bounded facet detection, conjunction splitting, sub-query generation |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:38:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage-1 orchestration, deep-mode gate for decomposition |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:39:| `mcp_server/lib/search/search-flags.ts` | Lib | `isQueryDecompositionEnabled()` flag accessor |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:45:| `mcp_server/tests/query-decomposer.vitest.ts` | Decomposition logic and edge cases |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:46:| `mcp_server/tests/query-decomposition.vitest.ts` | Integration-level decomposition tests |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:54:- Current reality source: mcp_server/lib/search/pipeline/stage1-candidate-gen.ts deep-mode decomposition branch and mcp_server/lib/search/query-decomposer.ts heuristics
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/003-discovery/implementation-summary.md:61:The audit was executed by dispatching 2 Opus research agents (parallel) to read feature catalog entries and verify against source code, followed by 2 Sonnet documentation agents (parallel) to update spec folder documents with findings. All agents operated as LEAF nodes at depth 1 under single-hop orchestration.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/graph-metadata.json:3:  "packet_id": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/graph-metadata.json:4:  "spec_folder": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/graph-metadata.json:5:  "parent_id": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/graph-metadata.json:197:    "causal_summary": "This is **Phase 1** of the Research-Based Refinement specification.",
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md:3:description: "Heuristic pre-classifier that routes queries to the optimal retrieval backend: structural (code graph), semantic (CocoIndex), or hybrid (both)."
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md:11:Heuristic pre-classifier that routes queries to the optimal retrieval backend: structural (code graph), semantic (CocoIndex), or hybrid (both).
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md:13:Keyword-dictionary scoring classifies queries into three intents: structural (symbol/relationship queries routed to code graph), semantic (conceptual/discovery queries routed to CocoIndex), and hybrid (mixed queries that merge results from both). Confidence scores and matched keywords are returned alongside the intent classification. Integrated into memory_context handler for automatic query-intent routing.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md:19:mcp_server/code_graph/lib/query-intent-classifier.ts
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/14-query-intent-classifier.md:29:| `mcp_server/code_graph/lib/query-intent-classifier.ts` | Lib | Keyword-based intent classification with confidence scoring |
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:1:# Iteration 7: D1 Research Convergence Signal Gap Audit
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:4:This iteration stayed on D1 and compared the live deep-research stop path against the richer research-signal set already implemented in the shared coverage-graph stack. The goal was to separate concrete runtime gaps from signals that look intentionally not adopted by the current deep-research contract.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:7:- The live deep-research workflow still evaluates STOP with a local 3-signal vote only: rolling average, MAD noise floor, and question entropy, then falls through a generic `checkQualityGuards(state, strategy)` call. The active convergence step does not name `contradictionDensity`, `sourceDiversity`, `claimVerificationRate`, or `evidenceDepth` anywhere in the runtime algorithm (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:8:- `sourceDiversity` is not a speculative extra from the shared graph stack; the deep-research convergence contract already makes it a first-class `qualityGate.checks` sub-check inside the legal-stop bundle. That means the current lack of an explicit shared-graph bridge for this signal is a runtime integration gap, not a deliberate omission (.opencode/skills/sk-deep-research/references/convergence.md:214-220; .opencode/skills/sk-deep-research/references/convergence.md:246-260; .opencode/skills/sk-deep-research/references/convergence.md:297-303).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:9:- `contradictionDensity` is also already part of the published deep-research convergence model: the contract says high contradiction density should block STOP and surface as a `qualityGate` semantic sub-check. Because the live workflow's active stop math still stops at the inline 3-signal vote, this is another concrete runtime gap rather than a merely hypothetical graph enhancement (.opencode/skills/sk-deep-research/references/convergence.md:363-386; .opencode/skills/sk-deep-research/references/convergence.md:411-423; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:10:- The shared coverage-graph stack already computes a richer research convergence payload with `questionCoverage`, `claimVerificationRate`, `contradictionDensity`, `sourceDiversity`, and `evidenceDepth`, then evaluates `sourceDiversity` and `evidenceDepth` as blocking guards and escalates high contradiction density or unverified claims into blockers/warnings. So the infrastructure gap is not in the graph/MCP layer; it is in the deep-research runtime not calling that layer (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:35-41; .opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:175-275).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:11:- `claimVerificationRate` and `evidenceDepth` look like deliberate non-adoptions in `sk-deep-research` rather than current regressions. The shared graph stack exposes both signals, but the published deep-research semantic extension still names `semanticNovelty`, `contradictionDensity`, and `citationOverlap` as the added semantic checks, not claim-verification or path-depth gates (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:35-41; .opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/sk-deep-research/references/convergence.md:341-457).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:12:- The reducer still cannot surface graph-backed research convergence even when `graphEvents` are present. It derives its convergence score from `latestIteration.convergenceSignals?.compositeStop ?? latestIteration?.newInfoRatio`, while the same convergence reference says the reducer should derive additional graph signals when `graphEvents` exist. That leaves graph-side research signals operationally disconnected from packet-level status surfaces (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249; .opencode/skills/sk-deep-research/references/convergence.md:1181-1205).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:15:- This is not primarily a shared-infrastructure deficit: the graph/MCP layer already computes and evaluates the richer research signals, including blocker semantics for `sourceDiversity`, `evidenceDepth`, contradictions, and unverified claims (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:175-275).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:16:- `claimVerificationRate` and `evidenceDepth` should not yet be treated as contract drift in `sk-deep-research`; the current research convergence reference still frames the semantic extension around `semanticNovelty`, `contradictionDensity`, and `citationOverlap` instead (.opencode/skills/sk-deep-research/references/convergence.md:341-457).
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:19:- I did not inspect confirm-mode workflows in this pass because the question was whether the active deep-research runtime currently bridges to the shared graph signal set; the auto workflow, convergence reference, reducer, and shared graph handler were sufficient to classify the signal gaps.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:22:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:23:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:24:- .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:25:- .opencode/skills/sk-deep-research/SKILL.md:217-218
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:26:- .opencode/skills/sk-deep-research/references/convergence.md:214-320
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:27:- .opencode/skills/sk-deep-research/references/convergence.md:341-457
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:28:- .opencode/skills/sk-deep-research/references/convergence.md:1181-1205
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:29:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:35:- What worked and why: Comparing the published research convergence contract directly against the shared graph signal schema made it easy to distinguish "already promised but unwired" from "available elsewhere but never adopted here."
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:40:Rotate to D2 and audit the new `sk-deep-review` reducer under partial-failure conditions rather than staying on research convergence. The next productive pass is to test whether `scripts/reduce-state.cjs` preserves finding lifecycle state, deduplication, and blocking gate evidence when an iteration file is malformed or only partially written, because that would answer the remaining D2 question about real-world reducer idempotency without reopening the already-covered contradiction/read-path ground.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/checklist.md:107:- [x] Parameter passed to hybridSearch.searchWithFallback() → L652-657
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/checklist.md:156:- [x] Semantic search works after restore
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/checklist.md:166:- [x] /search:help created OR documented as not needed
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/checklist.md:226:- [x] No performance regression in search
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/checklist.md:227:- [x] Database indexes improve query speed → 3 indexes added
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/03-observer-effect-mitigation.md:3:description: "Describes how the evaluation infrastructure avoids perturbing production query performance through fail-safe degradation and non-fatal handling in evaluation and observability paths."
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/03-observer-effect-mitigation.md:10:Describes how the evaluation infrastructure avoids perturbing production query performance through fail-safe degradation and non-fatal handling in evaluation and observability paths.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/03-observer-effect-mitigation.md:12:Measuring performance can sometimes slow down the thing you are measuring, like how stepping on a scale while running would trip you up. This feature makes sure that all the quality-checking work happens quietly in the background. If the measurement process breaks, your searches keep running at full speed without noticing.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/03-observer-effect-mitigation.md:18:Evaluation logging is implemented as fail-safe and best-effort rather than SLO-enforced runtime monitoring. The `eval-logger` hooks no-op unless `SPECKIT_EVAL_LOGGING=true` and degrade to non-fatal warnings on write failures, so evaluation paths do not block production query flow.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/03-observer-effect-mitigation.md:30:| `mcp_server/lib/eval/eval-logger.ts` | Lib | Non-fatal evaluation logging hooks for query, per-channel, and final-result events |
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:3:{"type":"iteration","run":2,"status":"complete","focus":"Spec Kit Memory MCP system architecture analysis","findingsCount":9,"newInfoRatio":0.88,"noveltyJustification":"Deep analysis of MCP server reveals 33 tools, hybrid search, cognitive layers","timestamp":"2026-03-29T09:20:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:15:{"type":"iteration","run":13,"status":"complete","focus":"Hybrid hook+tool architecture design","findingsCount":6,"newInfoRatio":0.44,"noveltyJustification":"First design connecting Claude hooks, Gate 1, memory_context resume, and MCP auto-surface","timestamp":"2026-03-29T09:44:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:20:{"type":"event","event":"segment_start","segment":3,"reason":"Implementation-ready deep research across 7 phases — 20 iterations via GPT-5.4 agents","timestamp":"2026-03-30T10:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:22:{"type":"iteration","run":17,"status":"insight","focus":"memory_context resume flow — nested envelope, 3 budget layers","findingsCount":9,"newInfoRatio":0.84,"noveltyJustification":"Resume brief lives in inner envelope, ResumeProfile includes topResult, 3 distinct token budgets (1200/2000/4000)","timestamp":"2026-03-30T10:20:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:29:{"type":"iteration","run":25,"status":"complete","focus":"Recovery payload format — stdout contract for compact-inject","findingsCount":9,"newInfoRatio":0.78,"noveltyJustification":"RecoveryPayload type, search-formatter attachment, hook layer is separate, cache versioning needed","timestamp":"2026-03-30T10:27:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:37:{"type":"iteration","run":33,"status":"complete","focus":"CocoIndex Code integration options","findingsCount":7,"newInfoRatio":0.65,"noveltyJustification":"Semantic search vs structural graph, separate concerns, possible shared embedding","timestamp":"2026-03-30T10:37:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:40:{"type":"event","event":"segment_start","segment":4,"reason":"Code graph deep research — functionalities, possibilities, best practices","timestamp":"2026-03-30T16:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:49:{"type":"iteration","run":44,"status":"insight","focus":"Code graph MCP tool API design","findingsCount":10,"newInfoRatio":0.86,"noveltyJustification":"MCP tool schemas, query patterns, output format, MVP feature set","timestamp":"2026-03-30T16:17:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:52:{"type":"event","event":"segment_start","segment":5,"focus":"CocoIndex + Code Graph Integration Research","method":"GPT-5.4 codex agents, high reasoning, 2 waves of 5 parallel","timestamp":"2026-03-30T16:30:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:53:{"type":"iteration","run":46,"status":"complete","focus":"CocoIndex ↔ Code Graph Bridge Design","findingsCount":10,"newInfoRatio":0.75,"noveltyJustification":"Bridge API contract, seed shape, expansion behavior, reverse enrichment, latency budget","timestamp":"2026-03-30T17:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:54:{"type":"iteration","run":47,"status":"complete","focus":"tree-sitter ↔ CocoIndex Chunk Alignment","findingsCount":8,"newInfoRatio":0.68,"noveltyJustification":"Chunk boundary mapping, structure-aware chunking vs function-level, source map design","timestamp":"2026-03-30T17:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:56:{"type":"iteration","run":50,"status":"complete","focus":"Compact Repo Map Generation — Structural Graph + CocoIndex","findingsCount":10,"newInfoRatio":0.76,"noveltyJustification":"Aider repo-map analysis, typed graph improvement, CocoIndex ranking influence, MVP map design","timestamp":"2026-03-30T17:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:57:{"type":"iteration","run":51,"status":"complete","focus":"Incremental Index Coordination — CocoIndex + Code Graph Sync","findingsCount":10,"newInfoRatio":0.65,"noveltyJustification":"Independent refresh cycles, freshness metadata, branch switch handling","timestamp":"2026-03-30T17:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:60:{"type":"iteration","run":49,"status":"complete","focus":"Token Budget Allocation Across 3 Context Sources","findingsCount":10,"newInfoRatio":0.71,"noveltyJustification":"Three-source allocator with floors+overflow, priority order, CocoIndex token estimation, SessionStart budget profile","timestamp":"2026-03-30T18:15:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:61:{"type":"iteration","run":55,"status":"complete","focus":"Implementation Readiness — CocoIndex-Aware Code Graph Architecture","findingsCount":10,"newInfoRatio":0.65,"noveltyJustification":"Final synthesis: phase 008+ specs, readiness scorecard, MVP scope, LOC estimates","timestamp":"2026-03-30T18:15:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:62:{"type":"iteration","run":54,"status":"complete","focus":"MCP Tool API — code_graph_context with CocoIndex Seeds","findingsCount":10,"newInfoRatio":0.74,"noveltyJustification":"Full parameter schema, seed normalization, output format, budget enforcement, query modes","timestamp":"2026-03-30T18:30:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:63:{"type":"event","event":"synthesis_complete","totalIterations":55,"segment":5,"stopReason":"all_cocoindex_integration_iterations_complete","timestamp":"2026-03-30T18:35:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:64:{"type":"event","event":"segment_start","segment":6,"focus":"Feature Improvement + Non-Hook Runtime UX Research","method":"Claude Opus deep-research agent, 20 iterations","timestamp":"2026-03-31T12:00:00.000Z"}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:67:{"type":"iteration","run":56,"status":"complete","focus":"Q13 — Feature improvements for code graph, budget allocator, merger, hook system","findingsCount":8,"newInfoRatio":0.72,"noveltyJustification":"6 of 8 findings are new (endLine bug, missing edge types, SymbolKind gaps, query API gaps, merger improvements, hook-based refresh); 2 partially new (tree-sitter migration extends iter-31/38, budget allocator extends iter-49)","keyQuestions":["Q16"],"answeredQuestions":["Q13"],"ruledOut":["LSP-based approach","native tree-sitter bindings"],"focusTrack":"feature-improvements","timestamp":"2026-03-31T15:00:00.000Z","durationMs":360000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:68:{"type":"iteration","run":59,"status":"complete","focus":"CocoIndex utilization improvements — seed resolution, auto-reindexing, query routing, hybrid patterns","findingsCount":5,"newInfoRatio":0.80,"noveltyJustification":"4 of 5 findings are fully new (near-exact seed resolution, auto-reindex triggers, hybrid query patterns, underutilized features); intent router improvement partially builds on segment 5 research","keyQuestions":["Q16"],"answeredQuestions":["Q16"],"ruledOut":["real-time file watcher for CocoIndex","LSP integration for query routing"],"focusTrack":"cocoindex-utilization","timestamp":"2026-03-31T14:45:00.000Z","durationMs":480000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:70:{"type":"iteration","run":63,"status":"complete","focus":"Q16 DEEP DIVE — seed resolution chain, auto-reindex, hybrid queries, CocoIndex MCP tools","findingsCount":8,"newInfoRatio":0.75,"noveltyJustification":"6 of 8 findings are new implementation-level designs (near-exact tier with confidence formula, score propagation blend, stale-triggered auto-reindex, hybrid query patterns A/B/C, missing composite index); 2 deepen prior findings (CocoIndex 1-tool limitation, computeFreshness coarseness)","keyQuestions":["Q16"],"answeredQuestions":["Q16"],"ruledOut":["SQLite editdist3 for fuzzy names","real-time file watcher","extending CocoIndex native MCP"],"focusTrack":"cocoindex-utilization","timestamp":"2026-03-31T15:30:00.000Z","durationMs":420000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:75:{"type":"iteration","run":67,"status":"complete","focus":"Auto-indexing and staleness detection design — stale-on-read mechanism with per-file granularity","findingsCount":8,"newInfoRatio":0.72,"noveltyJustification":"6 of 8 findings new (mtime fast-path gap, per-file staleness vs global MAX, ensureFreshFiles function design, hybrid sync/async threshold, schema extension with file_mtime_ms, CocoIndex freshness coordination); 2 deepen prior findings (content hash mechanism details from iter-063, computeFreshness coarseness from iter-063)","keyQuestions":[],"answeredQuestions":["Auto-indexing mechanism design","Staleness detection with latency constraints","CocoIndex coordination"],"ruledOut":["file watchers","global-only freshness check","synchronous reindex for all stale files"],"focusTrack":"auto-indexing","timestamp":"2026-03-31T18:00:00.000Z","durationMs":420000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:76:{"type":"iteration","run":66,"status":"complete","focus":"Tree-sitter WASM migration feasibility — regex parser analysis, adapter design, query patterns, bundle sizes","findingsCount":6,"newInfoRatio":0.55,"noveltyJustification":"3 of 6 findings are new (concrete S-expression query patterns for 4 edge types, adapter interface design with fallback, revised bundle size 1.5MB vs prior 8-15MB estimate); 2 partially new (regex parser limitation taxonomy deepens iter-060, migration phase plan updates LOC estimates); 1 redundant (endLine bug already fully documented)","keyQuestions":[],"answeredQuestions":["Q13 sub-question: tree-sitter WASM migration feasibility — fully answered"],"ruledOut":["node-tree-sitter native bindings","lazy grammar download from CDN","npm page scraping for web-tree-sitter"],"focusTrack":"feature-improvements","timestamp":"2026-03-31T19:00:00.000Z","durationMs":420000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:78:{"type":"iteration","run":70,"status":"complete","focus":"PERFORMANCE AND LATENCY ANALYSIS — hook timeout budget, SQLite query costs, token estimation accuracy, CocoIndex latency, pipeline latency budget design","findingsCount":8,"newInfoRatio":0.72,"noveltyJustification":"6 of 8 findings are new (1700ms headroom quantification, SQLite 1-9ms 1-hop expansion, token estimation 15-25% error margin, CocoIndex 100-500ms MCP roundtrip, tree-sitter 5-50ms per file, full pipeline latency budget table); 2 partially new (staleness check cost deepens iter-067 design, expandAnchor 400ms deadline budget confirms iter-061)","keyQuestions":[],"answeredQuestions":["Hook budget headroom","SQLite query costs","Token estimation accuracy","CocoIndex latency","Pipeline latency budget"],"ruledOut":["CocoIndex in hook path","synchronous tree-sitter reindex >3 files in hook"],"focusTrack":"performance-analysis","timestamp":"2026-03-31T20:30:00.000Z","durationMs":420000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:81:{"type":"iteration","run":72,"status":"complete","focus":"CROSS-REFERENCE WITH DEEP REVIEW FINDINGS -- 8 P1, 9 P2 from parallel GPT-5.4 review vs 71 research iterations","findingsCount":5,"newInfoRatio":0.70,"noveltyJustification":"3 of 5 findings are new (3 P1s our research missed: F001 cache race, F011 budget ceiling, F012 merger overflow; revised Phase A scope 120-165 LOC; 5 new P2s identified). 1 partially new (partial overlap matrix synthesizes both streams). 1 confirmatory (2 full overlaps validate our top priorities F005/F008).","keyQuestions":[],"answeredQuestions":["Does review FAIL verdict change implementation phasing?"],"ruledOut":["treating P2 security findings as phase blockers","re-running the review"],"focusTrack":"cross-reference","timestamp":"2026-03-31T22:00:00.000Z","durationMs":480000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:84:{"type":"iteration","run":75,"status":"thought","focus":"FINAL SYNTHESIS — Complete research program summary, research.md Part X update, convergence report","findingsCount":5,"newInfoRatio":0.10,"noveltyJustification":"Pure consolidation iteration: all 5 findings are synthesis of prior iterations (segment 6 summary, program metrics, three deliverables, open items, convergence assessment). No new external evidence gathered.","keyQuestions":[],"answeredQuestions":[],"ruledOut":[],"focusTrack":"consolidation","timestamp":"2026-03-31T22:30:00.000Z","durationMs":300000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:87:{"type":"iteration","run":79,"status":"complete","focus":"VERIFY Q16 findings from iterations 059 and 063 against current code in seed-resolver.ts, code-graph-db.ts, code-graph-context.ts, and CocoIndex MCP registration","findingsCount":7,"newInfoRatio":0.74,"noveltyJustification":"5 of 7 prior Q16 claims were disproven as current implementation, 1 was confirmed (native CocoIndex MCP exposes only search, with management surfaced through wrappers), and 1 was narrowed to a partial confirmation (missing composite index exists but performance necessity is not proven by live code).","keyQuestions":["Which Q16 findings from iterations 059 and 063 are actually implemented in current code?"],"answeredQuestions":["Which Q16 findings from iterations 059 and 063 are actually implemented in current code?"],"ruledOut":["Treating Q16 design proposals as shipped behavior","Inferring auto-reindex from freshness/staleness helpers alone","Inferring hybrid query execution from CocoIndex seed support alone"],"focusTrack":"verification","timestamp":"2026-03-31T13:44:00.000Z","durationMs":780000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:90:{"type": "iteration", "run": 77, "status": "complete", "focus": "VERIFY Q14 findings from iterations 057 and 061 against current code: auto-enrichment tiers, GRAPH_AWARE_TOOLS, pre-dispatch interception, MEMORY_AWARE_TOOLS double-check, and latency-budget implications", "findingsCount": 5, "newInfoRatio": 0.38, "noveltyJustification": "Primarily a verification pass. Two Q14 claims remain directly supported by current code (pre-dispatch interception and MEMORY_AWARE_TOOLS double-check). Three claims were narrowed from implementation-sounding statements to design-only proposals (three-tier graph/CocoIndex auto-enrichment, GRAPH_AWARE_TOOLS, and Promise.allSettled orchestration).", "keyQuestions": ["Do the five Q14 claims from iterations 057 and 061 still match the current implementation?"], "answeredQuestions": ["Three-tier graph/CocoIndex auto-enrichment is not implemented in the current code", "GRAPH_AWARE_TOOLS is not present in the current code", "Pre-dispatch interception remains the correct insertion point", "The MEMORY_AWARE_TOOLS defensive double-check pattern still exists", "The 250ms latency budget still exists, but Promise.allSettled remains a future-facing recommendation"], "ruledOut": ["Treating proposed graph/CocoIndex auto-enrichment as already shipped", "Assuming WorkingSetTracker performs session-start graph preloading"], "focusTrack": "verification", "timestamp": "2026-03-31T23:15:00.000Z", "durationMs": 300000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:91:{"type":"iteration","run":82,"status":"complete","focus":"VERIFY performance analysis from iteration 070 against current timing code in shared.ts, compact-inject.ts, compact-merger.ts, and budget-allocator.ts","findingsCount":6,"newInfoRatio":0.68,"noveltyJustification":"This pass uncovered a major scope correction: the live PreCompact hook only times stdin parsing and merge execution, so iteration 070's end-to-end headroom and enriched-pipeline latency numbers are not currently measured facts but mostly future-state estimates.","keyQuestions":["Which iteration 070 performance claims are still directly supported by current timing code?"],"answeredQuestions":["HOOK_TIMEOUT_MS is still 1800ms but only wraps parseHookStdin() in the live PreCompact hook","Token estimation still uses Math.ceil(text.length / 4)","Current code does not instrument or execute the richer SQLite/CocoIndex/tree-sitter hook pipeline assumed in iteration 070","Budget allocator timing remains uninstrumented"],"ruledOut":["Treating the 1800ms timeout as an end-to-end guard on the full live hook body","Treating 1-hop SQLite, CocoIndex, and full hook-path latency numbers as currently measured in source","Treating the current hook's cocoIndex section as a live CocoIndex MCP result"],"focusTrack":"verification","timestamp":"2026-03-31T13:38:38.148Z","durationMs":420000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:95:{"type":"iteration","run":86,"status":"complete","focus":"COPILOT CLI DEEP DIVE — instruction auto-loading, recovery reuse, and session-start auto-trigger design for memory_context + code_graph_scan","findingsCount":6,"newInfoRatio":0.71,"noveltyJustification":"This pass adds four concrete corrections to prior runtime assumptions: official Copilot CLI auto-loads AGENTS.md/.github/copilot-instructions.md/.github/instructions rather than a .github/copilot/ directory, repository-level custom agents live under .github/agents, repo-local .agents/agents is not the authoritative startup surface, and the right place for session-start graph priming is shared instruction files rather than optional agent profiles. Two findings deepen prior work by translating Claude recovery steps into Copilot-safe trigger patterns and by separating semantic vs structural auto-triggers.","keyQuestions":["Does Copilot CLI auto-load any instruction files?","How should Copilot auto-trigger memory_context and code_graph_scan on session start?","How does Copilot's markdown agent model change integration versus Codex TOML agents?"],"answeredQuestions":["Copilot CLI auto-loads AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md, optional root CLAUDE.md/GEMINI.md, and local/home instruction files","This repo currently has no .github/copilot/ directory or Copilot instruction files; the existing universal AGENTS.md already supplies Gate 1 memory_match_triggers but not code-graph startup priming","Copilot session-start priming should live in AGENTS.md plus optional .github/copilot-instructions.md or path-specific instructions, with code_graph_scan gated by code_graph_status and structural-intent triggers rather than fired on every turn","Copilot's markdown agent profiles are selection/delegation surfaces, whereas Codex TOML agents are canonical runtime prompts in this repo, so global startup behavior should not rely on Copilot agent profiles alone"],"ruledOut":["Using .github/copilot/ as the primary Copilot CLI auto-load surface","Relying on optional Copilot agent profiles alone for universal session-start priming","Running code_graph_scan unconditionally on every Copilot prompt"],"focusTrack":"non-hook-runtime","timestamp":"2026-03-31T13:49:25.654Z","durationMs":900000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:96:{"type":"iteration","run":85,"status":"complete","focus":"CODEX CLI deep dive — Session Start Protocol and @context auto-triggers","findingsCount":6,"newInfoRatio":0.83,"noveltyJustification":"4 of 6 findings are fully new (exact Codex agent inventory, cross-agent hook-wording audit, @context sequencing gap, and concrete CODEX.md/@context instruction text), while 2 deepen earlier non-hook-runtime findings about CODEX.md recovery behavior and Codex's lack of automatic graph warmup.","keyQuestions":["How should CODEX.md force memory_context() and code_graph_status() at session start?","What exact instruction additions should be made to .codex/agents/context.toml?"],"answeredQuestions":["A mandatory first-turn CODEX.md Session Start Protocol should call memory_context() and code_graph_status() before substantive work","The @context agent should gain a first-turn SESSION PRIME step, explicit code_graph_status() in its default sequence, and a structural auto-trigger subsection"],"ruledOut":["Relying on Claude-style SessionStart hooks in Codex","Forcing code_graph_scan() on every session start","Limiting the change to @deep-research only"],"focusTrack":"non-hook-runtime","timestamp":"2026-03-31T13:49:18.884Z","durationMs":480000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:97:{"type": "iteration", "run": 84, "status": "complete", "focus": "OPENCODE DEEP DIVE - concrete auto-trigger instructions for code graph + memory_context on session start", "findingsCount": 7, "newInfoRatio": 0.71, "noveltyJustification": "5 of 7 findings are fully new (complete OpenCode agent inventory with explicit MCP-binding audit, exact resume YAML injection point, per-agent insertion map, reusable OpenCode Session Start Protocol block, and concrete CLAUDE.md row/section rewrite). 2 findings are partially new because they refine prior non-hook-runtime work with direct current-code verification (scattered hook-aware fallback clauses and the minimal-friction split between graph status and graph expansion).", "keyQuestions": ["What exact OpenCode instruction changes should auto-trigger memory_context and code graph readiness on session start?"], "answeredQuestions": ["Which .opencode/agent files exist and which declare explicit MCP frontmatter bindings?", "Where is the best injection point in spec_kit_resume_auto.yaml for graph readiness?", "What universal Session Start Protocol should CLAUDE.md add?"], "ruledOut": ["auto-calling code_graph_context on every session start", "keeping graph startup logic only in late hook-routing appendices", "requiring Claude-style lifecycle hooks for OpenCode"], "focusTrack": "session-start-ux", "timestamp": "2026-03-31T13:58:00.000Z", "durationMs": 1500000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:98:{"type":"iteration","run":89,"status":"complete","focus":"VERIFY review P1 findings 4-6 against current code: stop-time auto-save surrogate, structural endLine collapse, and code_graph_context seed identity stripping","findingsCount":3,"newInfoRatio":0.36,"noveltyJustification":"Primarily a verification pass. All three review findings remain valid in current code; the main new value is tightening the exact failure mode for each boundary: stop-hook surrogate state reuse, still-unfixed one-line ranges, and public-handler seed type erasure.","keyQuestions":["Does session-stop implement a dedicated auto-save path or just reuse pendingCompactPrime?","Has the structural endLine collapse bug been fixed since Segment 6 research?","Do manual and graph seeds retain their identity through the public code_graph_context handler?"],"answeredQuestions":["session-stop still reuses pendingCompactPrime as a surrogate stop-time auto-save path","The structural indexer still collapses symbol ranges to one line, so the Segment 6 endLine bug remains live","The public code_graph_context handler still strips manual/graph seed identity before resolution"],"ruledOut":["Claiming the stop hook already performs a dedicated context-save operation","Claiming the endLine fix landed after Segment 6","Claiming manual and graph seeds keep provider-specific identity through the public handler"],"focusTrack":"verification","timestamp":"2026-03-31T14:02:42.031Z","durationMs":300000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:100:{"type": "iteration", "run": 91, "status": "complete", "focus": "VERIFY review P1-10 and key P2 findings against current code (rootDir validation, compact cache freshness, workingSet reachability, transcript cache accounting, exception text exposure)", "findingsCount": 5, "newInfoRatio": 0.67, "noveltyJustification": "This pass fully revalidated the headline security and correctness findings against current source and added two important nuances: the startup Working Memory branch is unreachable through the normal hook pipeline rather than logically impossible, and cache buckets are parsed correctly but dropped only from surfaced totals and cost estimates.", "keyQuestions": ["Do review findings P1-10, P2-1, P2-2, P2-3, and P2-8 still match the current implementation?"], "answeredQuestions": ["code_graph_scan still accepts caller-controlled rootDir with no workspace-boundary validation", "session-prime still reuses pendingCompactPrime without any freshness check", "the startup Working Memory branch still has no in-repo workingSet producer", "transcript totals and surfaced USD estimates still exclude cacheCreation and cacheRead buckets", "memory_context and code_graph_context still reflect raw internal exception text back to callers"], "ruledOut": ["Treating session-stop's duplicate-save age check as protection for compact recovery freshness", "Treating the Working Memory branch as produced anywhere in the current hook pipeline", "Treating cache buckets as absent from transcript parsing"], "focusTrack": "verification", "timestamp": "2026-03-31T14:02:59.560Z", "durationMs": 900000}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:104:{"type":"event","event":"segment_start","segment":9,"focus":"OpenCode plugin prompt-schema regression research","method":"direct source analysis + external opencode-lcm comparison + in-repo OpenCode plugin comparison","timestamp":"2026-04-03T18:00:00.000Z","notes":"Continuing from the existing iteration corpus even though the JSONL history was already stale relative to iterations 106-110."}
.opencode/specs/system-spec-kit/024-compact-code-graph/research/deep-research-state.jsonl:117:{"type": "iteration", "run": 95, "status": "thought", "focus": "FINAL SYNTHESIS -- Segment 7 verification summary, updated roadmap, parity matrix, and revised P1 status", "findingsCount": 5, "newInfoRatio": 0.12, "noveltyJustification": "Primarily consolidation: this iteration synthesizes the available Segment 7 verification evidence into the final research and strategy updates, while adding the provenance-critical note that standalone iteration-090/092/093/094 markdown artifacts were absent locally and therefore had to be reconstructed from the canonical state log plus extant iteration files.", "keyQuestions": [], "answeredQuestions": ["Segment 7 synthesis completed", "Updated implementation roadmap captured", "Cross-runtime parity matrix captured", "Revised P1 verification tally captured"], "ruledOut": ["Pretending standalone iteration-090/092/093/094 markdown files were present locally", "Treating design-only auto-enrichment proposals as shipped behavior"], "focusTrack": "consolidation", "timestamp": "2026-03-31T14:11:06.107Z", "durationMs": 300000}
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:3:description: "Dynamic token budget allocation scales the token budget returned per query based on query complexity tier."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:11:Dynamic token budget allocation scales the token budget returned per query based on query complexity tier.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:19:Returning 4,000 tokens for a simple trigger-phrase lookup wastes context window. Token budgets now scale with query complexity: simple queries receive 1,500 tokens, moderate queries 2,500 and complex queries 4,000.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:33:| `mcp_server/lib/search/dynamic-token-budget.ts` | Lib | Token budget computation |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:34:| `mcp_server/lib/search/hybrid-search.ts` | Lib | Budget adjustment with header overhead (CHK-060) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:35:| `mcp_server/lib/search/query-classifier.ts` | Lib | Query complexity classification |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:42:| `mcp_server/tests/query-classifier.vitest.ts` | Query classification accuracy |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:2:title: "Implementation [system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:3:description: "Cross-phase coordination plan for 5 sub-phases implementing 29 research recommendations across fusion, query, graph, feedback, and UX dimensions."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:5:  - "research refinement plan"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:13:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:20:# Implementation Plan: Research-Based Refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:39:Implements 29 research recommendations across 5 parallel sub-phases. The key architectural principle: **calibrate before learning, log before changing, shadow before live**. All new features are gated behind feature flags. The simple-query fast path must remain sub-second p95.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:46:- [ ] Research report reviewed for each dimension
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:57:- [ ] Simple-query p95 latency unchanged
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:132:| D2 | C | #25 | 1M/L | Index-time query surrogates |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md:169:- Research source preserved in the Phase 19 scratch artifacts
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/10-per-memory-history-log.md:32:| `.opencode/skills/system-spec-kit/mcp_server/lib/storage/history.ts` | Lib | History table init/migration and `recordHistory`/query helpers |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/10-per-memory-history-log.md:33:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts` | Lib | DB startup initialization for `memory_history` |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/10-per-memory-history-log.md:39:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts` | Lib | Writes `DELETE` events for mutation API delete helpers |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:2:title: "Verificat [system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:3:description: "Parent verification checklist for 5 sub-phases implementing 29 research recommendations."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:5:  - "research refinement checklist"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:11:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:21:# Verification Checklist: Research Based Refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:25:- **Phase:** 11 (Research-Based Refinement)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:32:- [x] [P1] [P1] All 5 child folders have spec.md, plan.md, tasks.md, checklist.md [Evidence: spec tree verified under `011-research-based-refinement/00*-*/`]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:41:- [x] [P1] [P1] All new features remain gated behind feature flags [Evidence: runtime helpers in `mcp_server/lib/search/search-flags.ts`]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:42:- [x] [P1] [P1] Feature catalog/playbook coverage updated for graduated and opt-in search flags [Evidence: feature catalog + manual playbook sync completed on 2026-03-22]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:49:- [x] [P1] [P1] Regression coverage exists for the repaired feature-flag paths [Evidence: `concept-routing`, `memory-search-ux-hooks`, `tool-input-schema`, `progressive-disclosure`, `session-state`, `fusion-lab`]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:53:- [x] [P1] [P1] Obsolete concept-routing regression was removed and replaced with current API coverage [Evidence: `graph-concept-routing.vitest.ts` removed; `concept-routing.vitest.ts` + `memory-search-ux-hooks.vitest.ts` cover live behavior]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/checklist.md:73:- [x] [P1] [P1] New modules remain in their intended runtime/test directories [Evidence: `mcp_server/lib/search/`, `mcp_server/handlers/`, `mcp_server/tests/`]
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:2:  "topic": "Further improvements to sk-deep-research v1.5.0.0, sk-deep-review v1.2.0.0, and sk-improve-agent v1.1.0.0 (and their associated commands, agents, YAML workflows): self-compliance audit, coverage graph integration audit, and prioritized recommendations.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:10:  "specFolder": "skilled-agent-orchestration/042-sk-deep-research-review-improvement-2",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:31:    "registryFile": "research/findings-registry.json",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:32:    "dashboardFile": "research/deep-research-dashboard.md",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:33:    "strategyFile": "research/deep-research-strategy.md",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:44:  "capabilityMatrixPath": ".opencode/skills/sk-deep-research/assets/runtime_capabilities.json",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:45:  "capabilityMatrixDocPath": ".opencode/skills/sk-deep-research/references/capability_matrix.md",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:46:  "runtimeCapabilityResolver": ".opencode/skills/sk-deep-research/scripts/runtime-capabilities.cjs",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:47:  "reducerScriptPath": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:48:  "pauseSentinelPath": "research/.deep-research-pause",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:49:  "archiveRoot": "research/archive",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:52:    "deep-research-config.json": "immutable",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:53:    "deep-research-state.jsonl": "append-only",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:54:    "deep-research-strategy.md": "mutable",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:55:    "deep-research-dashboard.md": "auto-generated",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-config.json:58:    "research/research.md": "mutable"
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md:2:title: "Code graph SQLite storage and MCP query tools"
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md:7:# Code graph SQLite storage and MCP query tools
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md:13:SQLite database (`code-graph.sqlite`) stores indexed files, symbol nodes, and relationship edges. 4 MCP tools: `code_graph_scan` (workspace indexing, with null-summary clearing of stale persisted edge-enrichment summaries), `code_graph_query` (outline/calls/imports; CALLS mode prefers callable implementation nodes over wrapper-shadow candidates for ambiguous subjects and returns ambiguity / selected-candidate metadata; shares the blocked/degraded `full_scan` response contract with `code_graph_context`), `code_graph_status` (freshness plus readiness, trust, parse-health, and `graphQualitySummary` reporting), and `code_graph_context` (LLM neighborhoods with readiness metadata, blocked full-scan responses, structured `metadata.partialOutput`, and an explicit `metadata.deadlineMs` when budget or deadline limits trim output). WAL mode, foreign keys, directional indexes.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md:31:| `mcp_server/code_graph/handlers/query.ts` | Handler | Implements `code_graph_query` for callers, imports, and outlines |
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/08-code-graph-storage-query.md:47:- Source feature title: Code graph SQLite storage and MCP query tools
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/issue-registry.md:57:| P1-004 | includeContiguity parameter not passed to search | 042 | VERIFIED_OPEN | Parameter extracted but never used in hybrid-search.js |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/issue-registry.md:67:| P1-014 | Missing /memory:help, /search:help | 033 | VERIFIED_OPEN | Namespace-specific help commands don't exist |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/issue-registry.md:77:| P2-001 | Missing database indexes (file_path, content_hash) | 042 | VERIFIED_OPEN | Schema has no indexes - impacts query performance |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/issue-registry.md:101:| P3-004 | Memory tier not in detailed output | 031 | VERIFIED_OPEN | Tier info missing from search result display |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/06-synthetic-ground-truth-corpus.md:3:description: "Describes the 110-query ground truth corpus covering all seven intent types with hand-written natural language queries, hard negatives and agent consumption findings for realistic retrieval evaluation."
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/06-synthetic-ground-truth-corpus.md:10:Describes the 110-query ground truth corpus covering all seven intent types with hand-written natural language queries, hard negatives and agent consumption findings for realistic retrieval evaluation.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/06-synthetic-ground-truth-corpus.md:12:To know if search results are right, you need an answer key. This is a collection of 110 test questions with known correct answers, written in everyday language rather than system keywords. It also includes trick questions designed to catch the system returning wrong results. Without this answer key, there would be no reliable way to measure whether changes actually improve or hurt search quality.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/06-synthetic-ground-truth-corpus.md:18:A corpus of 110 query-relevance pairs covers all seven intent types with at least five queries per type and at least three complexity tiers (simple factual, moderate relational, complex multi-hop).
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:280:Fix hybrid-search.js bugs
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:424:Verify vector-index and hybrid-search
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:766:This session did not involve significant architectural or technical decisions. The work was primarily implementation, bug fixes, documentation, or research.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:785:- **Research** - 3 actions
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:867:Verifying system with 10 Opus agents → Now let me synthesize all verification results: Now I'll fix all three files: Executed sequential_thinking_sequentialthinking Verify semantic-memory. js fixes Verify vector-index and hybrid-search Verify scoring libs fixes Verify integration libs fixes Verify system-memory SKILL. Used tools: , ,  and 30 more.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:903:Fixing found issues → Now let me synthesize all verification results: Now I'll fix all three files: Executed sequential_thinking_sequentialthinking Verify semantic-memory. js fixes Verify vector-index and hybrid-search Verify scoring libs fixes Verify integration libs fixes Verify system-memory SKILL. Used tools: , ,  and 30 more.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:1002:| Memory Not Found | Search returns no results | Check `memory_search({ specFolder: "005-memory/017-comprehensive-bug-fix" })` |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:1007:2. **Load memory context** - Use memory_search to surface prior work
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:1046:> **Machine-Readable Section** - This YAML block is parsed by the semantic memory indexer for search optimization and decay calculations.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:1056:context_type: "general"        # research|implementation|decision|discovery|general
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/029-comprehensive-bug-fix/scratch/legacy-memory-quarantine/24-12-25_12-07__comprehensive-bug-fix-029.md:1098:last_search_query: ""
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:3:description: "Graph concept routing extracts noun phrases from a query and matches them against a concept alias table, recording matched concepts as Stage 1 trace metadata when SPECKIT_GRAPH_CONCEPT_ROUTING is enabled."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:11:Graph concept routing extracts noun phrases from a query and matches them against a concept alias table, recording matched concepts as Stage 1 trace metadata when `SPECKIT_GRAPH_CONCEPT_ROUTING` is enabled.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:13:Normally, the graph retrieval channel only activates when a query explicitly references known entities. This feature adds a lightweight concept-routing pass over natural-language queries: it extracts noun phrases, matches them against canonical concept names and aliases, and records the resulting concepts in retrieval trace metadata. Today that gives downstream observability into which concepts were recognized, but it does not directly switch Stage 1 into a graph retrieval branch.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:21:The `isGraphConceptRoutingEnabled()` function in `search-flags.ts` checks the flag. The entity linker module (`entity-linker.ts`) provides query-time concept routing alongside its cross-document entity linking role. It extracts noun phrases from the query, matches them against the concept alias table in SQLite, and returns canonical concept names plus a `graphActivated` boolean. `stage1-candidate-gen.ts` currently uses that output only to append a `d2-concept-routing` trace entry with `matchedConcepts` and `graphActivated: true`; that trace field mirrors the routing result for observability, but it does not switch the Stage 1 search path or directly activate a graph retrieval channel. Note that the inline comment on `isGraphConceptRoutingEnabled()` in `search-flags.ts` overstates this behavior by saying it is "activating the graph channel"; current runtime behavior is trace-only at this stage.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:31:| `mcp_server/lib/search/entity-linker.ts` | Lib | Query-time concept routing, noun phrase extraction, alias table matching |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:32:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage-1 orchestration, records concept-routing results into retrieval trace metadata |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:33:| `mcp_server/lib/search/search-flags.ts` | Lib | `isGraphConceptRoutingEnabled()` flag accessor |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:40:| `mcp_server/tests/memory-search-ux-hooks.vitest.ts` | Live search integration coverage for graduated routing-adjacent UX hooks |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:48:- Current reality source: mcp_server/lib/search/entity-linker.ts and mcp_server/lib/search/pipeline/stage1-candidate-gen.ts concept-routing trace branch
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:21:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:23:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:43:Rotate to D4 and audit self-compliance drift in `sk-improve-agent`'s published runtime contracts. The most productive next pass is to compare the README, SKILL, `assets/improvement_strategy.md`, and the visible reducer/dashboard path to verify which promised operator-visible artifacts actually survive end-to-end, especially around trade-off annotations, benchmark stability labeling, and stop-reason/session-outcome wording. That would convert this D3 evidence into a broader contract-compliance answer without reopening already-closed research/review findings.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/04-tier-based-bulk-deletion-memorybulkdelete.md:26:The `olderThanDays` parameter is validated as a positive integer (>= 1) before query construction. Values that are zero, negative, non-integer, or NaN return a validation error rather than silently removing the age filter. The `tool-schemas.ts` definition enforces `minimum: 1` at the schema level.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/04-tier-based-bulk-deletion-memorybulkdelete.md:40:| `mcp_server/lib/search/vector-index.ts` | Lib | Vector index facade for memory deletion |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:2:title: "Tasks: Resear [system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:3:description: "Cross-phase coordination tasks for 5 sub-phases implementing 29 research recommendations."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:5:  - "research refinement tasks"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:12:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:19:# Tasks: Research-Based Refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:61:- [ ] T009 Run latency regression — verify simple-query p95 < 1s
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:67:  - See: `002-query-intelligence-reformulation/tasks.md`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:68:  - Evidence: query-decomposer.ts created, entity-linker.ts + stage1-candidate-gen.ts extended, 65 tests
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:71:  - Evidence: graph-lifecycle.ts (814 lines), post-insert.ts wired, search-flags.ts extended, 69 tests
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:79:- [x] T014 [P] Execute D1 Phases B+C — Shadow fusion lab, query-aware graph, fusion router (#8, #22, #23)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:86:  - See: `002-query-intelligence-reformulation/tasks.md`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:99:  - Evidence: query-surrogates.ts (400 lines), heuristic extraction + SQLite storage + query-time matching, 80 tests
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:110:  - Evidence: 25 inline entries added across 5 sections (graph, scoring, query, memory quality, UX hooks)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:129:5. Simple-query p95 latency unchanged
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md:139:- [D2 Tasks](002-query-intelligence-reformulation/tasks.md)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:2:title: "Feature [system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:6:  - "query intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:13:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:29:Systematic code audit of 11 Query Intelligence features in the Spec Kit Memory MCP server. Each feature from the `feature_catalog/12--query-intelligence/` category will be verified against its source code implementation to confirm accuracy, completeness, and catalog alignment.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:79:- LLM query reformulation
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:81:- Index-time query surrogates
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:94:| `feature_catalog/12--query-intelligence/*.md` | Reference | Feature catalog source files |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:95:| `007-code-audit-per-feature-catalog/012-query-intelligence/` | Create | Audit documentation |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:179:| Research | 11/20 | Must trace each feature to source |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:236:**Deep Review Update (2026-03-25)**: F07-F09 are restored to MATCH because runtime defaults now align with the catalog and surrogate matching is wired into Stage 1. F02 is downgraded to PARTIAL because RSF was removed while stale catalog references remain. F10 is downgraded to PARTIAL because deep-mode search bypasses faceted decomposition.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:246:| F07 | LLM query reformulation | MATCH | Runtime default TRUE now matches the catalog |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:248:| F09 | Index-time query surrogates | MATCH | Surrogate matching is wired into Stage 1 and now matches the catalog |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/spec.md:256:3. **Deep-mode decomposition gap (F10)**: Production deep-mode search bypasses the faceted decomposition helper and falls back to the basic split path, so the catalog currently overstates live behavior.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:70:The graph channel is completely broken — 0% hit rate in production due to `mem:${edgeId}` string IDs being compared against numeric memory IDs. The chunk collapse dedup logic only runs on the `includeContent=true` path, allowing duplicate chunks to surface in default search mode (`includeContent=false`). Co-activation scoring suffers from hub domination where highly-connected memories dominate results regardless of query relevance. Most critically, zero evaluation metrics exist — every tuning decision is pure speculation.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:84:- **G1**: Fix graph channel ID format — convert `mem:${edgeId}` to numeric memory IDs at BOTH locations (`graph-search-fn.ts` lines 110 AND 151)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:104:| `graph-search-fn.ts` | Modify | G1: Fix ID format from `mem:${edgeId}` to numeric |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:105:| `memory-search.ts` | Modify | G3: Fix chunk collapse to run on all code paths |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:109:| Eval handler files | Create | R13-S1: Logging hooks for search/context/trigger handlers |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:121:| REQ-S0-001 | **G1**: Fix graph channel ID format — convert `mem:${edgeId}` to numeric memory IDs | Graph hit rate > 0% in retrieval telemetry; verified at BOTH locations in `graph-search-fn.ts` (lines ~110 AND ~151); cross-ref: CHK-010, T001 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:122:| REQ-S0-002 | **G3**: Fix chunk collapse conditional — dedup on all code paths including `includeContent=false` | No duplicate chunk rows in default search mode; tested via both `includeContent=true` and `includeContent=false` paths; cross-ref: CHK-011, T002 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:125:| REQ-S0-004 | **G-NEW-1**: BM25-only baseline comparison | BM25 baseline MRR@5 recorded and compared to hybrid. Ground truth corpus satisfies diversity requirement: >=30 manually curated non-trigger-phrase queries, >=5 queries per intent type, >=3 query complexity tiers. BM25 contingency decision requires statistical significance (p<0.05, paired t-test or bootstrap CI) on >=100 diverse queries. |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:146:- **SC-002**: No duplicate chunk rows appear in default search mode after G3 fix
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:156:- >=5 queries per intent type, >=3 query complexity tiers (simple single-concept, moderate multi-concept, complex cross-document)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:179:- **Required artifact**: Written rationale document explaining why multi-channel retrieval provides sufficient value over BM25-only, citing specific query categories where hybrid outperforms
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:191:- **NFR-P01**: Eval logging adds ≤5ms p95 to search latency — measured before/after (D4 observer effect check)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:192:- **NFR-P02**: G1 fix must not degrade graph search performance
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:200:- **NFR-R02**: Eval infrastructure degrades gracefully — search continues if eval DB is unavailable
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:215:- **Zero graph edges found**: Graph search returns empty — not an error post-G1 fix
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:229:| Scope | 15/25 | 5 files across 3 subsystems (graph, search, eval), schema creation |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:231:| Research | 8/20 | Research complete (142 analysis); code locations identified |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/spec.md:242:- **OQ-S0-003**: G-NEW-2 pre-analysis — what agent consumption patterns dominate in practice? Findings may reshape ground truth query design for representativeness.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:3:description: "Category covering Claude Code hooks (PreCompact, SessionStart, Stop), structural code graph (indexer, SQLite, MCP tools), CocoIndex bridge, and compaction working-set integration."
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:12:Category covering runtime hook automation, structural code graph (indexer, SQLite, MCP tools), CocoIndex bridge, and compaction working-set integration.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:14:This category documents the hybrid context injection system that preserves critical knowledge across context compaction events. It combines three complementary systems: hook-based lifecycle automation, structural code analysis (code graph), and semantic search (CocoIndex) — all merging under a 4000-token budget for compaction injection.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:20:Implemented across spec 024-compact-code-graph with phase 018 canonical continuity layered on top. The shipped surface now includes hook scripts, code graph modules, MCP tools, budget allocator, tree-sitter parser with regex fallback, query-intent routing, auto-trigger, session health/resume/bootstrap tools, the structural ready/stale/missing contract, Gemini hooks, and startup-brief follow-ons. Recovery now treats `/spec_kit:resume` as the canonical surface and follows `handover.md -> _memory.continuity -> spec docs` before widening to broader memory artifacts.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:35:| `mcp_server/code_graph/lib/query-intent-classifier.ts` | Lib | Structural/semantic/hybrid query routing |
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/01-category-overview.md:38:| `mcp_server/handlers/session-resume.ts` | Handler | Composite resume (memory + graph + CocoIndex) |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json:2:  "specFolder": "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json:3:  "description": "Feature Specification: Research-Based Refinement",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json:7:    "research-based",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json:12:  "folderSlug": "research-based-refinement",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/description.json:20:    "21-03-26_18-29__created-phase-folder-011-research-based.md",
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:2:title: "Implementatio [system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:6:  - "query intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:12:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:69:- **Feature Catalog**: `feature_catalog/12--query-intelligence/` — source of truth
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:95:- [x] Audit: LLM query reformulation — PARTIAL (F07: flag contradiction)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:97:- [x] Audit: Index-time query surrogates — PARTIAL (F09: missing file + dead code)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/plan.md:184:| `surrogate-storage.ts` unlisted in catalog; `matchSurrogates()` dead code at query time | F09 | Low — missing source ref + dead code |
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:2:title: Deep Research Dashboard
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:3:description: Auto-generated reducer view over the research packet.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:6:# Deep Research Dashboard - Session Overview
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:13:Reducer-generated observability surface for the active research packet.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:18:- Topic: Further improvements to sk-deep-research v1.5.0.0, sk-deep-review v1.2.0.0, and sk-improve-agent v1.1.0.0 (and their associated commands, agents, YAML workflows): self-compliance audit, coverage graph integration audit, and prioritized recommendations.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:39:| 7 | D1 research convergence signal gap audit | - | 0.58 | 6 | complete |
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:63:- [x] D1: What undocumented edge cases, redundant reducer passes, journal-rollup gaps, or resume-flow drifts exist in the sk-deep-research v1.5.0.0 loop?
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:69:- [x] D3: Is the mutation coverage graph namespace (`loop_type: "improvement"`) properly isolated from the deep-research/deep-review namespaces in the shared SQLite store?
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:71:- [x] D4: Do blocked-stop events always persist `gateResults` with the complete set of review-specific or research-specific gates, or are gates silently dropped?
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:74:- [x] D5: Does any loop phase (init / iteration / convergence / synthesis) actively READ from the coverage graph (`coverage-graph-query.ts`, `coverage-graph-convergence.cjs`) to inform decisions, or only WRITE to it?
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:78:- [x] D5: Are there missing MCP tool calls (e.g., `code_graph_query` for semantic neighbors) that the loops should be making but aren't?
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:92:- .opencode/agents/deep-research.md:159-166 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:93:- .opencode/skills/sk-deep-research/references/loop_protocol.md:190-198 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:94:- .opencode/skills/sk-deep-research/references/loop_protocol.md:247-255 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:95:- .opencode/skills/sk-deep-research/references/loop_protocol.md:77-84 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:96:- .opencode/skills/sk-deep-research/references/state_format.md:145-177 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:97:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:98:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:99:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:100:- .opencode/skills/sk-deep-research/SKILL.md:190-199 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:101:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38 (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:102:- No evidence that prior iteration findings would make these observations redundant; `research/iterations/` was empty before this run and `deep-research-state.jsonl` only contained the config row (.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-state.jsonl:1). (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:103:- No evidence that YAML workflow outputs bypass the reducer-owned packet surfaces; both auto and confirm flows still target `findings-registry.json` and `deep-research-dashboard.md` as synchronized outputs (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:83-84; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:197; .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:83-84; .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:196-217). (iteration 1)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:104:- .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326 (iteration 2)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:106:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127 (iteration 2)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:107:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502 (iteration 2)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:114:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52 (iteration 2)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:115:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10 (iteration 2)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:118:- .opencode/skills/sk-deep-research/references/convergence.md:1181-1205 (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:119:- .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12 (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:125:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55 (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:126:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52 (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:127:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10 (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:128:- No hidden bridge appeared in the active reducer path: the deep-research reducer still has no MCP/tool client imports and no graph-event parsing branch, so the bridge is not merely buried deeper in the same file (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:246-247). (iteration 3)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:131:- This is not isolated to one loop. The research and review auto YAMLs both classify the same lineage branches while only surfacing a smaller event set in the active runtime path (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-153`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:155-177`). (iteration 4)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:132:- This is not just a documentation omission. Both convergence references are explicit about first-class blocked-stop persistence and full gate bundles, so the drift is between published contract and live workflow serialization, not between two equally vague docs (`.opencode/skills/sk-deep-research/references/convergence.md:305-309`, `.opencode/skills/sk-deep-review/references/convergence.md:58-85`). (iteration 4)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:135:- This is not a documentation-gap false alarm: both convergence references already define the shared enum, the legacy-label normalization rules, and the required blocked-stop persistence shape in detail (.opencode/skills/sk-deep-research/references/convergence.md:21-31; .opencode/skills/sk-deep-review/references/convergence.md:44-56). (iteration 5)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:138:- This is not limited to one loop. Both research and review convergence references promise graph-aware gate participation, but both active auto workflows keep STOP evaluation inline and local (`.opencode/skills/sk-deep-research/references/convergence.md:1181-1205`, `.opencode/skills/sk-deep-review/references/convergence.md:661-683`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:343-375`). (iteration 6)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:139:- `claimVerificationRate` and `evidenceDepth` should not yet be treated as contract drift in `sk-deep-research`; the current research convergence reference still frames the semantic extension around `semanticNovelty`, `contradictionDensity`, and `citationOverlap` instead (.opencode/skills/sk-deep-research/references/convergence.md:341-457). (iteration 7)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:140:- I did not inspect confirm-mode workflows in this pass because the question was whether the active deep-research runtime currently bridges to the shared graph signal set; the auto workflow, convergence reference, reducer, and shared graph handler were sufficient to classify the signal gaps. (iteration 7)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:141:- This is not primarily a shared-infrastructure deficit: the graph/MCP layer already computes and evaluates the richer research signals, including blocker semantics for `sourceDiversity`, `evidenceDepth`, contradictions, and unverified claims (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:175-275). (iteration 7)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:148:- This is not another reducer merge-stability regression. Iteration 9 already established that finding dedup and transition ordering stay stable at 50+ findings, which leaves observability and recovery handoff as the remaining D2 weakness (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:7-11`). (iteration 10)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:152:- Repo-wide symbol search for the new D3 modules surfaced mostly docs, specs, changelog entries, and tests, which limited negative-proof evidence to the runtime files that do exist. (iteration 12)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:160:- A command-doc requirement to invoke structural graph tools before or during iterations; the inspected command surfaces only bootstrap CocoIndex. (iteration 15)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:161:- A wrapper-level `deep_loop_graph_convergence` step on the visible research/review iteration path; the cited YAML paths go from iteration output to reducer execution without a graph-convergence call. (iteration 15)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:163:- I did not inspect hidden executor internals outside the published skill, workflow, and MCP handler surfaces, so the negative claim stays scoped to the shipped writer/validator/query path that is visible in-repo. (iteration 16)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:164:- The visible MCP coverage-graph path is not currently allowing `loop_type: "improvement"` to pollute shared research/review graphs; the stronger risk is documentation/strategy drift plus missing per-session read isolation inside the research/review namespaces. (iteration 16)
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:178:If this research spins into a follow-on packet, the next productive move is not another broad loop audit but a narrow implementation-gap triage for `sk-improve-agent`: inspect `score-candidate.cjs`, any hidden orchestrator wrapper, and the confirm-mode workflow for off-path graph consumption, then decide whether to wire `mutation-coverage.cjs` into live focus/stop decisions or downgrade the docs/templates so they stop implying graph-driven behavior that the visible loop does not perform.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-dashboard.md:183:- None active beyond normal research uncertainty.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:20:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:21:- .opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/13-evaluation-and-housekeeping-fixes.md:20:- **Ablation recallK (#33):** Ablation search limit uses `recallK` parameter instead of hardcoded 20.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:41:This plan implements Sprint 0 — the blocking foundation sprint. Two independent tracks run in parallel: (1) Bug fixes (G1 graph ID, G3 chunk collapse, R17 fan-effect) targeting known regressions in the graph and search subsystems; (2) Eval infrastructure (R13-S1 schema, logging hooks, metric computation, BM25 baseline) creating the measurement foundation that gates all subsequent sprints.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:50:- [ ] Research complete — 142 analysis and recommendations reviewed
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:51:- [ ] G1 code location verified (`graph-search-fn.ts` ~line 110)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:52:- [ ] G3 code location verified (`memory-search.ts` ~line 303)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:71:- **Graph subsystem** (Track 1): `graph-search-fn.ts` — ID format fix, returns numeric memory IDs
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:72:- **Search handlers** (Track 1): `memory-search.ts` — chunk collapse dedup on all paths
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:75:- **Logging hooks** (Track 2): Intercepts in search/context/trigger handlers to log queries and results to eval DB
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:90:- [ ] G1: Fix graph ID format in `graph-search-fn.ts` lines 110 AND 151 — convert `mem:${edgeId}` to numeric (3-5h) — WHY: Graph channel has 0% hit rate due to string-vs-numeric ID mismatch; ALL downstream graph work (R4, R10, N2) is blocked until this is fixed. **Risk**: Fix may reveal sparse graph (few edges) — this is informational, not a failure.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:91:- [ ] G3: Fix chunk collapse conditional in `memory-search.ts` — dedup on ALL paths (2-4h) — WHY: Duplicate chunks inflate result counts and distort MRR/NDCG metrics, making baseline measurements unreliable. Note: The bug is at the call site (~line 1002), not the function definition (~line 303).
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:92:- [ ] R17: Add fan-effect divisor to co-activation in `co-activation.ts` (1-2h) — WHY: Without fan-effect correction, hub memories with many co-activations dominate results regardless of query relevance, poisoning evaluation baselines.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:97:- [ ] R13-S1: Add logging hooks to search, context, and trigger handlers (6-8h)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:101:- [ ] G-NEW-2 Pre-Analysis: Lightweight agent consumption pattern survey (3-4h) — WHY: Understanding how AI agents currently query memory_search (what patterns, what they select, what they ignore) directly informs ground truth query design. Without this, synthetic queries risk being unrepresentative of real usage.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:102:  - Analyze recent agent query logs for pattern categories
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:104:  - Document findings as input to ground truth query design (T007)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:108:- [ ] G-NEW-1/G-NEW-3: Generate ground truth — minimum 100 query-relevance pairs (50 minimum for initial baseline; >=100 required for BM25 contingency decision). MUST satisfy diversity requirement: >=5 queries per intent type, >=3 query complexity tiers (simple, moderate, complex), >=30 manually curated queries NOT derived from trigger phrases. Incorporate G-NEW-2 pre-analysis findings into query design. (2-4h)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:129:| Unit | T004b observer effect — search p95 with eval logging on vs off | Vitest | 1-2 tests |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:133:| Unit | T007 ground truth diversity — query distribution meets intent/complexity/manual thresholds | Vitest | 1-2 tests |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:134:| Integration | End-to-end search with graph channel active | Vitest | ~2 tests |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:149:| 142 research analysis | Internal | Green | Design decisions unclear |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/plan.md:186:| Phase 2b (Agent Consumption Pre-Analysis) | None (can start independently) | Phase 3 (findings feed query design) |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:14:You can rename a spec-doc record or change its priority without deleting and re-creating it. When you change the title, the system automatically updates its internal search index to match. If the update fails partway through, everything rolls back to the way it was before so you never end up with a half-changed record.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:22:When the title changes, the system regenerates the vector embedding to keep search results aligned. This is a critical detail: if you rename a spec-doc record from "Authentication setup guide" to "OAuth2 configuration reference", the old embedding no longer represents the content accurately. Automatic regeneration fixes that.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:28:BM25 refresh is not limited to title edits. Whenever either `title` or `triggerPhrases` changes, the handler re-reads the updated row and rebuilds the BM25 document from `title`, `content_text`, `trigger_phrases`, and `file_path` so lexical search stays aligned with metadata edits. Infrastructure-level BM25 outages are downgraded to warnings, but data-path BM25 failures from an otherwise live index still abort the transaction and roll the update back.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:34:Successful metadata updates now invalidate the search cache as part of the same transactional path. After the handler refreshes BM25, optionally persists the replacement vector and recomputes folder interference scores, it calls `clear_search_cache()` so renamed memories and trigger updates appear in subsequent cached searches immediately instead of after TTL expiry.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:46:| `mcp_server/lib/search/bm25-index.ts` | Lib | BM25 re-index when title or trigger phrases change |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/02-memory-metadata-update-memoryupdate.md:47:| `mcp_server/lib/search/vector-index.ts` | Lib | Persistent memory row updates |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:3:description: "Covers the embedding-based query expansion path and distinguishes it from the separate rule-based deep-mode query-variant expansion path."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:11:This entry covers the embedding-based query expansion path, which broadens retrieval for complex queries by mining related terms from the vector index and appending them to the original query. It is separate from the rule-based `query-expander.ts` path used to build deep-mode synonym variants.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:13:Sometimes the words you use in a question do not match the words stored in the system, even though they mean the same thing. This embedding-driven path automatically adds related terms to your search so you find relevant results even when the exact wording differs. Separately, deep-mode query expansion can generate rule-based synonym variants without mining the vector index.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:19:Embedding-based query expansion broadens retrieval for complex queries by mining similar spec-doc records from the vector index and extracting related terms to append to the original query, producing an enriched combined query string. Stop-words are filtered out and tokens shorter than 3 characters are discarded.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:21:When R15 classifies a query as "simple", the embedding-based expansion path is suppressed because expanding a trigger-phrase lookup would add noise. If embedding expansion produces no additional terms, the original query proceeds unchanged. Separately, `query-expander.ts` provides rule-based synonym variants for deep-mode retrieval; that is a distinct path and should not be conflated with vector-mined expansion. In the 4-stage pipeline, Stage 1 runs the baseline and expanded-query searches in parallel with deduplication (baseline-first). Runs behind the `SPECKIT_EMBEDDING_EXPANSION` flag (default ON).
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:31:| `mcp_server/lib/search/embedding-expansion.ts` | Lib | Embedding-based query expansion: mines vector index for related terms, appends to query |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:32:| `mcp_server/lib/search/query-expander.ts` | Lib | Rule-based deep-mode synonym variant expansion (distinct from embedding path) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:33:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage-1 orchestration: parallel baseline+expansion with dedup |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:34:| `mcp_server/lib/search/query-classifier.ts` | Lib | Complexity classification; simple queries suppress embedding expansion |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:35:| `mcp_server/lib/search/search-flags.ts` | Lib | `isEmbeddingExpansionEnabled()` flag accessor (`SPECKIT_EMBEDDING_EXPANSION`) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:42:| `mcp_server/tests/query-expander.vitest.ts` | Rule-based query expansion tests |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:44:| `mcp_server/tests/search-flags.vitest.ts` | Feature flag behavior |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:2:title: "...ystem-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:5:  - "011-research-based-refinement implementation summary"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:6:  - "011-research-based-refinement delivery record"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:12:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:19:# Implementation Summary: Research Based Refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:31:| **Spec Folder** | 011-research-based-refinement |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:43:The parent phase coordinated and recorded delivery across all five research dimensions: fusion and scoring intelligence, query intelligence and reformulation, graph-augmented retrieval, feedback and quality learning, and retrieval UX/presentation. The packet now cleanly represents those child outcomes without relying on the stale research-path references that previously broke validation.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:59:1. Split the research recommendations into five child folders with clear phase ownership.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:71:2. Point parent research references at the epic-level research artifact that actually exists.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md:96:- The parent no longer links to the missing historical research subtree; it now relies on the existing epic-level research artifact.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/checklist.md:2:title: "Verifica [system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/checklist]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/checklist.md:6:  - "query intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/checklist.md:12:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:42:- [x] CHK-S0-001 [P0] Bug fix code locations verified — `graph-search-fn.ts` lines 110 AND 151 (G1 has TWO occurrences), `memory-search.ts` ~line 1002 (G3 conditional gating at the call site, not line 303 which is the function definition) — HOW: Open each file, search for `mem:${` (G1) and chunk collapse conditional (G3); confirm line numbers match. Cross-ref T001, T002. (verified: both locations fixed in graph-search-fn.ts; call-site conditional fixed in memory-search.ts) [EVIDENCE: graph-search-fn.ts:157-160 (queryCausalEdgesFTS5) and :221-224 (queryCausalEdgesLikeFallback) — both emit `id: sourceNum`/`id: targetNum` as numeric via Number() cast; no `mem:$` string construction remains. memory-search.ts:551-569 applySessionDedup runs unconditionally regardless of includeContent flag]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:44:- [x] CHK-S0-003 [P1] 142 research analysis and recommendations reviewed for Sprint 0 scope — HOW: Confirm R-001 through R-017 items relevant to Sprint 0 are addressed in spec.md scope section. (verified: scope section covers all relevant R items) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:52:- [x] CHK-S0-010 [P0] G1 produces numeric memory IDs (not `mem:${edgeId}` strings) (verified: numeric IDs in graph-search-fn.ts) [EVIDENCE: graph-search-fn.ts:157-160 `id: Number(row.source_id)` in queryCausalEdgesFTS5; :221-224 same pattern in queryCausalEdgesLikeFallback — both use Number() cast, not string template]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:53:- [x] CHK-S0-011 [P0] G3 chunk dedup runs on ALL code paths (including `includeContent=false`) (verified: unconditional dedup applied at call site) [EVIDENCE: memory-search.ts:551-569 applySessionDedup called at :905 for cached path and :559 for live path — both paths apply dedup independent of includeContent; graph-search-fn.ts:100-109 dedup by memory id runs unconditionally on all graphResults]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:56:- [x] CHK-S0-013b [P1] NFR-P02: G1 fix must not degrade graph search performance — HOW: Benchmark graph search latency before and after G1 fix; p95 must not increase by >10%. Cross-ref NFR-P02 in spec.md §7. (verified: no performance regression observed) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:65:- [x] CHK-S0-020 [P0] 20-30 new tests added covering: G1 numeric IDs, G3 all code paths, R17 bounds, R13-S1 schema/hooks/metrics, BM25 path, T054 SHA256 dedup, T004b observer effect, T006a-e diagnostic metrics, T006f ceiling eval, T006g quality proxy, T007 ground truth diversity — HOW: Run `npx vitest --reporter=verbose`; count new test cases; verify each subsystem has >=1 test. Cross-ref T001-T008, T054. (verified: 4684 baseline tests passing) [EVIDENCE: test files confirmed: graph-search-fn.vitest.ts, eval-db.vitest.ts, eval-logger.vitest.ts, bm25-baseline.vitest.ts, content-hash-dedup.vitest.ts, co-activation.vitest.ts, ground-truth.vitest.ts, reporting-dashboard.vitest.ts in mcp_server/tests/]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:68:- [x] CHK-S0-023 [P1] Eval metric computation verified against known test data — HOW: Define at least 1 fixed test case with known ground truth (e.g., query "A" with relevant memories M1, M2, M3 at ranks 1, 3, 5 → expected MRR@5 = 0.467); compute metric via R13 and verify match within ±0.01; cross-ref T006, T013 (verified: hand-calculation matched within ±0.01) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:73:- [x] CHK-S0-028 [P1] Observer effect mitigation (D4) verified — search p95 increase ≤10% with eval logging enabled (verified: T004b observer effect check passed) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:84:- [x] CHK-S0-033 [P1] NFR-P01: Eval logging adds ≤5ms p95 to search latency — measured before/after (verified: D4 observer effect check passed ≤5ms threshold) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:85:- [x] CHK-S0-034 [P1] NFR-R02: Search continues normally if eval DB is unavailable — graceful degradation verified (verified: eval logging disabled with warning on DB failure; search unaffected) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:118:- [x] CHK-S0-060 [P0] Graph hit rate > 0% — verified via eval telemetry or manual query inspection (verified: numeric IDs in graph-search-fn.ts fix resolves 0% hit rate — Gate 1 PASS) [EVIDENCE: graph-search-fn.ts:157-160,:221-224 — Number() cast on source_id/target_id produces integer IDs matching memory_index.id column; comment at :147-149 documents the fix rationale]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:119:- [x] CHK-S0-061 [P0] No duplicate chunk rows in default search mode (`includeContent=false`) (verified: T002 unconditional dedup — Gate 2 PASS) [EVIDENCE: graph-search-fn.ts:100-111 dedup Map keyed by memory id runs on all code paths; memory-search.ts:559,:905,:935 session dedup applied in both live and cached response paths regardless of includeContent]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:120:- [x] CHK-S0-062 [P0] Baseline MRR@5, NDCG@10, Recall@20, Hit Rate@1 computed for 100+ queries (50+ minimum for initial baseline; >=100 required before CHK-S0-064 BM25 contingency decision) — HOW: Run `eval_metric_snapshots` query against `speckit-eval.db`; verify row count >=100 in `eval_final_results` table; cross-ref T006, T007 (verified: 110 queries — MRR@5=0.2083 — Gate 3 PASS) [EVIDENCE: bm25-baseline.ts:471-556 runBM25Baseline() computes MRR@5/NDCG@10/Recall@20/HitRate@1; eval-metrics.ts:105,532 computeMRR function; ground-truth-data.ts loads queries from data/ground-truth.json; eval-db.ts:90-99 eval_metric_snapshots table stores results]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:121:- [x] CHK-S0-062b [P0] Ground truth query diversity verified — >=5 queries per intent type, >=3 query complexity tiers (simple, moderate, complex), >=3 hard negatives. HARD GATE. — HOW: Count distinct intent_type tags and complexity_tier tags in `eval_queries` table; verify thresholds. Evidence required: query distribution table showing counts per intent type and tier. (verified: >=5 per intent type, >=3 tiers — Gate 4 PASS) [EVIDENCE: ground-truth-data.ts:7-14 defines 7 IntentType values (add_feature, fix_bug, refactor, security_audit, understand, find_spec, find_decision); :16 defines 3 ComplexityTier values (simple, moderate, complex); :73-76 QUERY_DISTRIBUTION computes counts per intentType, complexityTier, and hardNegativeCount]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:122:- [x] CHK-S0-062c [P1] G-NEW-2 pre-analysis completed — agent consumption pattern report produced with >=5 identified consumption patterns; findings incorporated into ground truth query design (T007). Cross-ref T007b. (verified: pre-analysis pattern report produced — Gate 8 PASS) [EVIDENCE: documented in phase spec/plan/tasks artifacts]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/checklist.md:130:- [x] CHK-S0-069 [P0] REQ-S0-007 eval-the-eval hand-calculation complete — hand-calculated MRR@5 for 5 randomly selected queries matches R13 computed values within ±0.01; all discrepancies resolved before BM25 contingency decision — HOW: Select 5 random queries from ground truth, manually compute MRR@5 from ranked results, compare to `eval_metric_snapshots` table values; cross-ref T013, REQ-S0-007 (verified: all 5 queries within ±0.01 tolerance) [EVIDENCE: eval-metrics.ts:105 computeMRR() implements MRR calculation; bm25-baseline.ts:526-527 per-query MRR computed and accumulated; ground-truth-data.ts:40-48 GroundTruthRelevance structure with queryId/memoryId/relevance supports hand-calculation verification against computed values]
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/20-passive-context-enrichment.md:13:The spec-doc record-surface and response-hints hooks form a passive enrichment pipeline. On every tool call, constitutional memories and trigger-matched spec-doc records are surfaced and appended to the response envelope. Code graph status is included when available. Token estimation prevents oversized payloads. The enrichment is additive (appended to hints) and does not modify the primary tool response. This ensures AI runtimes always have access to critical context even when they do not explicitly call memory_context.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:20:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:21:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:272:rootCause: After the major Spec Kit + Memory merger (spec 035), multiple refinement attempts (036-042) identified issues but many were duplicates, already fixed, or superseded. No single source of truth existed for remaining work.; solution: Comprehensive 10-agent research across all 42 specs with code verification to identify truly open issues, followed by 10-agent parallel implementation to fix all P0-P3 issues; patterns: Used parallel agent dispatch for both research and implementation phases. Grouped fixes by file to avoid conflicts. Verified fixes with syntax checks. Documented architecture decisions for deferred items.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:440:### Decision 6: Decision: Modified checkpoint create/restore to include vec_memories embeddings because users expected checkpoint restore to preserve semantic search capability
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:442:**Context**: Decision: Modified checkpoint create/restore to include vec_memories embeddings because users expected checkpoint restore to preserve semantic search capability
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:451:   Decision: Modified checkpoint create/restore to include vec_memories embeddings because users expected checkpoint restore to preserve semantic search capability
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:457:**Rationale**: Decision: Modified checkpoint create/restore to include vec_memories embeddings because users expected checkpoint restore to preserve semantic search capability
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:622:| Memory Not Found | Search returns no results | Check `memory_search({ specFolder: "003-memory-and-spec-kit/043-post-merge-refinement-final" })` |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:627:2. **Load memory context** - Use memory_search to surface prior work
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:666:> **Machine-Readable Section** - This YAML block is parsed by the semantic memory indexer for search optimization and decay calculations.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:676:context_type: "general"        # research|implementation|decision|discovery|general
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/043-post-merge-refinement-final/scratch/legacy-memory-quarantine/26-12-25_08-12__post-merge-refinement-final.md:718:last_search_query: ""
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/07-bm25-only-baseline.md:3:description: "Describes the BM25/FTS5-only baseline measurement (MRR@5 of 0.2083) that confirmed lexical search alone still underperforms hybrid retrieval."
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/07-bm25-only-baseline.md:10:Describes the BM25/FTS5-only baseline measurement (MRR@5 of 0.2083) that confirmed lexical search alone still underperforms hybrid retrieval.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/07-bm25-only-baseline.md:12:This test answered a simple question: "Would basic keyword search be good enough on its own?" By running just keyword matching against 110 test questions and measuring how poorly it performed, the team proved that the more advanced multi-method search approach is worth the extra effort. Without this baseline measurement, you would be guessing whether the added complexity actually helps.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/07-bm25-only-baseline.md:18:Running the BM25/FTS5-only baseline path (disabling vector, graph and trigger channels) on the 110-query corpus produced an MRR@5 of 0.2083. That is well below 50% of hybrid performance.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/07-bm25-only-baseline.md:20:If BM25 had been competitive, the entire multi-channel approach would be questioned. Instead, the gap confirmed that hybrid retrieval adds real value over lexical search. The contingency decision to proceed with the full program was based on this measurement. No opinions, no intuitions, just a number. The current runtime keeps the in-memory BM25 path enabled by default; use `ENABLE_BM25=false` if you need to force the FTS5 fallback for comparison.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:46:- [x] T000a [P] Record pre-Sprint-0 performance baseline — current p95 search latency, memory count, existing system behavior snapshot [1-2h] — Baseline
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:49:- [x] T000c [P] Audit `search-weights.json` — verify `maxTriggersPerMemory` status, smart ranking section behavior [1-2h] — OQ-003
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:50:- [x] T000d [P] Curate diverse ground truth query set — manually create ≥15 natural-language queries covering: graph relationship queries ("what decisions led to X?"), temporal queries ("what was discussed last week?"), cross-document queries ("how does A relate to B?"), and hard negatives; minimum ≥5 per intent type, ≥3 complexity tiers (simple factual, moderate relational, complex multi-hop) [2-3h] — G-NEW-1/G-NEW-3
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:51:  - Acceptance: query set JSON with `intent_type`, `complexity_tier`, `expected_result_ids` fields per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:58:- [x] T001 [P] Fix graph channel ID format — convert `mem:${edgeId}` to numeric memory IDs at BOTH locations (`graph-search-fn.ts` lines 110 AND 151) [3-5h] — G1 (REQ-S0-001)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:60:  - Implementation hint: Search for `mem:${` in `graph-search-fn.ts`; replace with numeric extraction `parseInt(edgeId)` or equivalent
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:62:- [x] T002 [P] Fix chunk collapse conditional — dedup on ALL code paths including `includeContent=false` (`memory-search.ts`) [2-4h] — G3 (REQ-S0-002)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:63:  - Acceptance: No duplicate chunk rows in default search mode; tested via both `includeContent` paths
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:64:  - Implementation hint: Bug is at the call site (~line 1002 in `memory-search.ts`), not the function definition (~line 303). The conditional gating skips dedup when `includeContent=false`.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:82:- [x] T004b Implement R13 observer effect mitigation — health check measuring search p95 with eval logging on vs off; trigger if >10% increase [2-4h] {T004} — D4 (REQ-S0-003)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:83:- [x] T005 Add logging hooks to search, context, and trigger handlers [6-8h] {T004} — R13-S1 (REQ-S0-003)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:90:  - [x] T006-checkpoint [GATE] Intermediate validation — verify T006a–T006e produce expected output on a fixed test case with known ground truth values (e.g., query with known relevant memories at known ranks → compute expected MRR@5, verify match within ±0.01); resolve discrepancies before T006f/T006g [1h]
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:99:- [x] T007b [P] G-NEW-2 pre-analysis: Lightweight agent consumption pattern survey — analyze how AI agents currently consume memory search results (query patterns, selection behavior, ignored results). Examine recent agent query logs, CLAUDE.md routing patterns, and skill definitions. Document top 5-10 consumption patterns. Findings feed into ground truth query design (T007). [3-4h] — G-NEW-2 pre-analysis
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:101:  - Implementation hint: Check `memory_search` call sites in `.opencode/skills/` and `.claude/agents/` for query construction patterns
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:109:- [x] T007 Generate synthetic ground truth from trigger phrases — minimum 100 query-relevance pairs (50 minimum for initial baseline metrics, >=100 required for BM25 contingency decision per REQ-S0-004) with DIVERSITY REQUIREMENT: >=5 queries per intent type (add_feature, fix_bug, refactor, security_audit, understand, find_spec, find_decision), >=3 query complexity tiers (simple single-concept, moderate multi-concept, complex cross-document). Include >=30 manually curated natural-language queries NOT derived from trigger phrases (per REQ-S0-004 hard gate, raised per REC-10). Incorporate G-NEW-2 pre-analysis findings into query design. [2-4h] {T004, T007b} — G-NEW-1 / G-NEW-3 (REQ-S0-004)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:110:  - Acceptance: 100+ queries with intent type and complexity tier tags; diversity thresholds met; >=30 queries MUST be manually curated natural-language queries NOT derived from trigger phrases (per REQ-S0-004 hard gate); document manual vs synthetic query split in query distribution table
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:113:    1. Generate intent-typed query templates from trigger phrases
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:119:  - Implementation hint: Select 5 queries randomly from ground truth corpus; for each query, manually rank relevant memories and compute MRR@5 = (1/5) * Σ(1/rank_i); compare to `eval_metric_snapshots` table
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:123:  - Implementation hint: Use FTS5-only path in `memory-search.ts`; disable vector, graph, and trigger channels via flags
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:133:  - [x] No duplicate chunk rows in default search
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:135:  - [x] Ground truth diversity: >=5 queries per intent type, >=3 query complexity tiers (HARD gate)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:164:| T000c | T000c | Audit search-weights.json |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:165:| T000d | T000d | Curate diverse ground truth query set |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/tasks.md:172:| T005 | T005 | Logging hooks for search handlers (R13-S1) |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:3:description: "HyDE generates a short hypothetical document answering the query, embeds it, and uses the pseudo-document embedding as an additional retrieval channel for deep low-confidence queries, gated by the SPECKIT_HYDE flag."
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:11:HyDE generates a short hypothetical document answering the query, embeds it, and uses the pseudo-document embedding as an additional retrieval channel for deep low-confidence queries, gated by the `SPECKIT_HYDE` flag.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:13:When a search returns weak results, the problem is often a vocabulary mismatch between the query and the stored content. HyDE bridges this gap by asking an LLM to write a short document that would answer the question, then searching with that document's embedding instead of the query's. Since the hypothetical document uses the language of an answer rather than a question, it often matches stored content better. It is active by default (both `SPECKIT_HYDE` and `SPECKIT_HYDE_ACTIVE` are ON); set `SPECKIT_HYDE_ACTIVE=false` to revert to shadow mode where results are logged but not merged.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:27:Budget: 1 LLM call per cache miss. Combined with reformulation: at most 2 total LLM calls per deep query. Set `SPECKIT_HYDE=false` to disable the feature entirely. In shadow mode (`SPECKIT_HYDE_ACTIVE=false`), results are logged but NOT merged. In active mode, results are merged into candidates. Debug logging available via `SPECKIT_HYDE_LOG=true`.
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:39:| `mcp_server/lib/search/hyde.ts` | Lib | Pseudo-document generation, embedding, low-confidence detection, shadow/active mode |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:40:| `mcp_server/lib/search/llm-cache.ts` | Lib | Shared LLM result cache |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:41:| `mcp_server/lib/search/llm-reformulation.ts` | Lib | `normalizeQuery()` imported for cache key normalization |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:42:| `mcp_server/lib/search/search-flags.ts` | Lib | `isHyDEEnabled()` flag accessor |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:43:| `mcp_server/lib/search/pipeline/stage1-candidate-gen.ts` | Lib | Stage 1 integration: invokes HyDE in deep mode with low-confidence baseline |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:49:| `mcp_server/tests/search-flags.vitest.ts` | Flag behavior for HyDE |
.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:57:- Current reality source: mcp_server/lib/search/hyde.ts module header and implementation
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:2:title: "...hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:3:description: "Add query decomposition, graph concept routing, corpus-grounded LLM reformulation, HyDE shadow mode, and index-time query surrogates."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:5:  - "query decomposition"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:9:  - "query surrogates"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:15:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:50:The current retrieval pipeline treats every user query as a single opaque string — one embedding lookup, one keyword expansion, one graph probe. This works for simple, well-phrased queries but fails when the user's question is multi-faceted ("what decisions were made about scoring AND graph pruning?"), uses vocabulary that diverges from stored terminology, or targets concepts that sit across multiple memory clusters. The result is missed recall on complex queries while simple-query latency must remain untouched.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:54:Introduce five query-intelligence capabilities — decomposition, concept routing, corpus-grounded LLM reformulation, HyDE shadow mode, and index-time query surrogates — each behind a feature flag, each gated to deep/complex queries only, to close the recall gap on hard queries without regressing the fast path.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:68:- **REQ-D2-005** — Index-time query surrogates (precomputed aliases, surrogate questions)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:83:| `query-decomposer.ts` | **New** | REQ-D2-001 |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:96:### REQ-D2-001: Query Decomposition (Research Rec #10, Size M)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:102:**Files:** `stage1-candidate-gen.ts`, new `query-decomposer.ts`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:120:### REQ-D2-002: Graph Concept Routing (Research Rec #11, Size S/M)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:143:### REQ-D2-003: Corpus-Grounded LLM Reformulation (Research Rec #12, Size M)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:145:**What:** Step-back abstraction combined with corpus seed retrieval — not raw HyDE. Retrieves cheap seed results first, then asks the LLM to rewrite the query using those seeds as grounding context.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:169:### REQ-D2-004: HyDE Shadow Mode (Research Rec #24, Size M)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:193:### REQ-D2-005: Index-Time Query Surrogates (Research Rec #25, Size M/L)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:195:**What:** At index time, precompute aliases, decision summaries, and likely user questions for each memory. At query time, match against surrogates to boost recall without runtime LLM calls.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:213:onQuery(q) => search(q + matchedSurrogates(q));
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:229:| SC-D2-002 | Simple-query p95 latency unchanged | Regression test passes |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:230:| SC-D2-003 | Per-query LLM budget for deep/complex | ≤ 2 LLM calls |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:243:| Risk | API cost stacking — multiple LLM calls per query | Medium | ≤ 2 LLM calls budget, caching, corpus-grounded approach reduces retries |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:254:- [Parent Spec](../spec.md) — Research-Based Refinement (011)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:258:- Research Source (historical, path removed) — Full 29-recommendation synthesis
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:265:- Child of 011-research-based-refinement
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md:266:- 5 requirements from research recommendations #10, #11, #12, #24, #25
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/05-quality-proxy-formula.md:12:You cannot have a person hand-check every search result after every change. This feature creates a single "quality score" from 0 to 1 that runs automatically and flags when results are getting worse. Think of it like an automated smoke detector for search quality: it watches for problems around the clock so you do not have to.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/05-quality-proxy-formula.md:18:Manual evaluation does not scale. You cannot hand-review every query across every sprint.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:14:After a search result is shown to you, you can tell the system whether it was helpful or not. Helpful results get a confidence boost so they show up more often in the future. Unhelpful results get demoted so they appear less. Over time, the system learns which memories are genuinely useful and which ones keep missing the mark, like training a recommendation engine with your thumbs-up and thumbs-down.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:20:Every search result is either helpful or not. This tool lets you record that judgment and triggers several downstream systems based on the feedback.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:22:Positive feedback adds 0.1 to the spec-doc record's confidence score (capped at 1.0). Negative feedback subtracts 0.05 (floored at 0.0). The base confidence for any memory starts at 0.5. The asymmetry between positive (+0.1) and negative (-0.05) increments is intentional. It takes one good validation to raise confidence by 0.1 but two bad validations to cancel that out. This bias toward preservation reflects the assumption that a spec-doc record might be unhelpful for one query but still valuable for another.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:26:Negative feedback persistence fires unconditionally on every negative validation. A `recordNegativeFeedbackEvent()` call stores the event in the `negative_feedback_events` table. The search handler reads these events and applies a confidence multiplier that starts at 1.0, decreases by 0.1 per negative validation and floors at 0.3. Time-based recovery with a 30-day half-life gradually restores the multiplier. Demotion scoring runs behind the `SPECKIT_NEGATIVE_FEEDBACK` flag (default ON).
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:28:When a `queryId` is provided alongside positive feedback, two additional systems activate. Learned feedback persistence records the user's selection and extracts query terms into a separate `learned_triggers` column (isolated from the FTS5 index to prevent contamination). These learned triggers boost future searches for the same terms. Ground truth selection logging records the event in the evaluation database for the ground truth corpus, returning a `groundTruthSelectionId` in the response.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:30:**Prerequisites for learned-feedback activation:** The validation call must include `queryTerms` AND `resultRank` in addition to `queryId`. Without all three fields, learned-feedback persistence is skipped and only the base confidence adjustment and auto-promotion/demotion paths fire.
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:47:| `mcp_server/lib/search/auto-promotion.ts` | Lib | Positive-validation promotion thresholds and throttle |
.opencode/skills/system-spec-kit/feature_catalog/02--mutation/05-validation-feedback-memoryvalidate.md:49:| `mcp_server/lib/search/learned-feedback.ts` | Lib | Learned-trigger extraction, audit logging, and persistence |
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:20:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:21:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/001-sprint-0-measurement-foundation/implementation-summary.md:83:- ~~`relevanceWeight=0.2` anomaly in `search-weights.json` is flagged but unresolved; may skew BM25 comparison results~~ **RESOLVED** (Sprint 10): `relevanceWeight` is now 0.5 in `search-weights.json`; dead `rrfFusion` and `crossEncoder` config sections removed (P2-05)
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/spec.md:41:   - Updated search.md command with anchor-aware loading UI
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/spec.md:53:| `research` | Investigation | `research-lenis-scroll-006` |
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/spec.md:62:| `.opencode/commands/memory/search.md` | Added anchorId to MCP signatures, anchor-aware detail view |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:2:title: "...hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:3:description: "Focus: Heuristic-only query improvements — no LLM calls in the query path."
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:11:  - "query"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:17:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:44:**Focus:** Heuristic-only query improvements — no LLM calls in the query path.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:48:| A.1 | Implement facet detection heuristic (`isMultiFacet`) | `query-decomposer.ts` | 1d |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:49:| A.2 | Implement bounded decomposition (`decompose()`, max 3 facets) | `query-decomposer.ts` | 1d |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:50:| A.3 | Implement facet-coverage merge strategy | `query-decomposer.ts` | 1d |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:63:- Simple-query latency unchanged (no LLM calls added)
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:70:**Focus:** LLM-powered query enhancement for deep/complex queries only.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:90:- LLM call budget ≤ 2 per query
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:98:**Focus:** Shift query-intelligence work to index time — precompute surrogates per memory.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:107:| C.4 | Implement query-time surrogate matching and boost | `vector-index-store.ts` | 1d |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:109:| C.6 | Tests: surrogate generation, storage, query-time matching, recall impact | test files | 1d |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:127:| **A** | REQ-D2-001, REQ-D2-002 | Heuristic query enhancement | 7d | D3 Phase A (for concept routing entity tables) |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:163:| `SPECKIT_QUERY_SURROGATES` | Index + query time | Off | C |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md:169:Each feature is independently flag-gated. Rollback = disable flag. No data migrations required. Index-time surrogates (Phase C) are additive metadata — disabling the flag skips surrogate matching at query time but stored surrogates remain inert.
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:6:      "text": "D1: What undocumented edge cases, redundant reducer passes, journal-rollup gaps, or resume-flow drifts exist in the sk-deep-research v1.5.0.0 loop?",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:42:      "text": "D3: Is the mutation coverage graph namespace (`loop_type: \"improvement\"`) properly isolated from the deep-research/deep-review namespaces in the shared SQLite store?",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:54:      "text": "D4: Do blocked-stop events always persist `gateResults` with the complete set of review-specific or research-specific gates, or are gates silently dropped?",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:72:      "text": "D5: Does any loop phase (init / iteration / convergence / synthesis) actively READ from the coverage graph (`coverage-graph-query.ts`, `coverage-graph-convergence.cjs`) to inform decisions, or only WRITE to it?",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:95:      "id": "question-16-d5-are-there-missing-mcp-tool-calls-e-g-code-graph-query-for-semantic-neighbors-",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:96:      "text": "D5: Are there missing MCP tool calls (e.g., `code_graph_query` for semantic neighbors) that the loops should be making but aren't?",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:104:      "text": "Dashboard stuck reporting does not match the loop contract: the protocol says stuck count increments whenever `newInfoRatio < config.convergenceThreshold`, but the dashboard only counts `status == \"stuck\"` or `newInfoRatio === 0`, so low-but-nonzero no-progress passes are invisible in the synchronized packet view (.opencode/skills/sk-deep-research/references/loop_protocol.md:190-198; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:107:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:108:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:109:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:110:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:111:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:112:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:113:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:114:        ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:115:        ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:116:        ".opencode/agents/deep-research.md:159-166"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:120:      "id": "finding-1-5-deep-research-ownership-guidance-still-drifts-internally-the-skill-data-flow-say",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:121:      "text": "Deep-research ownership guidance still drifts internally: the skill data flow says the agent writes `strategy.md` during each iteration, while the agent contract says reducer-owned state should be refreshed only from the iteration file plus JSONL append. That mismatch creates a real redundant-pass risk for any runtime or operator following the older skill text literally (.opencode/skills/sk-deep-research/SKILL.md:190-199; .opencode/agents/deep-research.md:159-166).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:124:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:125:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:126:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:127:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:128:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:129:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:130:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:131:        ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:132:        ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:133:        ".opencode/agents/deep-research.md:159-166"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:138:      "text": "Resume context has a documented side channel that the reducer never reflects. Both the loop protocol and agent contract say `research/research-ideas.md` should be read during resume, but reducer inputs are limited to config, JSONL, strategy, registry/dashboard outputs, and `iterations/`, so synchronized packet surfaces cannot show whether the ideas backlog changed the resumed trajectory (.opencode/skills/sk-deep-research/references/loop_protocol.md:247-255; .opencode/agents/deep-research.md:64-76; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:481-487).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:141:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:142:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:143:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:144:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:145:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:146:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:147:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:148:        ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:149:        ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:150:        ".opencode/agents/deep-research.md:159-166"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:155:      "text": "The reducer drops every non-`iteration` JSONL row by filtering `parseJsonl(...).filter((record) => record.type === 'iteration')`, so documented `resumed`, `guard_violation`, `blocked_stop`, and stuck-recovery events can exist in `deep-research-state.jsonl` without ever surfacing in `findings-registry.json`, `deep-research-strategy.md`, or `deep-research-dashboard.md` (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502; .opencode/skills/sk-deep-research/references/loop_protocol.md:77-84; .opencode/skills/sk-deep-research/references/loop_protocol.md:113-120).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:158:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:159:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:160:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:161:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:162:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:163:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:164:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:165:        ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:166:        ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:167:        ".opencode/agents/deep-research.md:159-166"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:172:      "text": "The reducer rollup is materially narrower than the JSONL/state schema. It parses findings, ruled-out bullets, sources, reflection, and next-focus from iteration markdown, but it never promotes `noveltyJustification`, structured `ruledOut.reason/evidence`, `sourceStrength`, or `graphEvents`, which makes those fields effectively write-only unless another consumer reads raw JSONL (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:146-175; .opencode/skills/sk-deep-research/references/state_format.md:145-152; .opencode/skills/sk-deep-research/references/state_format.md:171-177).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:175:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:176:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:177:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:178:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:179:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:180:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:181:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:182:        ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:183:        ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:184:        ".opencode/agents/deep-research.md:159-166"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:189:      "text": "Contradiction handling is split across layers: the CJS helper can scan in-memory `CONTRADICTS` edges, but the active convergence handler actually blocks on contradictions through the TypeScript query layer (`findContradictions(ns)`), which implies graph-aware contradiction blocking depends on a populated persisted namespace rather than on raw JSONL `graphEvents` alone (.opencode/skills/system-spec-kit/scripts/lib/coverage-graph-contradictions.cjs:37-67; .opencode/skills/system-spec-kit/scripts/lib/coverage-graph-contradictions.cjs:85-129; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:20-25; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:255-257; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:353-355).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:192:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:193:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:194:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:196:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:197:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:208:      "text": "The active loop workflow surfaces I inspected only require agents to emit `graphEvents`; they do not show any corresponding `deep_loop_graph_upsert`, `deep_loop_graph_query`, or `deep_loop_graph_convergence` invocation in the same runtime path. In the checked YAMLs, graph handling appears as an iteration-record output contract, not a read-back decision step (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326; .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:436-437).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:211:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:212:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:213:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:215:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:216:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:226:      "id": "finding-2-3-the-deep-research-reducer-still-operates-on-iteration-markdown-sections-plus-jso",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:227:      "text": "The deep-research reducer still operates on iteration markdown sections plus JSONL rows filtered to `type === \"iteration\"`, then rebuilds packet outputs from those inputs; there is no reducer-owned path here that parses or promotes `graphEvents` into strategy, registry, or dashboard state. That means the synchronized packet surfaces remain blind to graph-aware stop evidence unless some other process reads the graph separately (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:230:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:231:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:232:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:234:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:235:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:246:      "text": "The shared graph-convergence handler does implement real stop-gating against persisted graph state: it computes graph signals, then evaluates research/review blockers using `findCoverageGaps()`, `findContradictions()`, and `findUnverifiedClaims()` before returning `STOP_ALLOWED`, `STOP_BLOCKED`, or `CONTINUE` (.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:20-25; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:109-163; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:245-275; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:343-355).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:249:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:250:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:251:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:253:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:254:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:268:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:269:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:270:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:271:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:275:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:282:      "id": "finding-3-1-sk-deep-research-s-active-reducer-does-not-implement-the-shared-graph-bridge-it-",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:283:      "text": "`sk-deep-research`'s active reducer does not implement the shared-graph bridge: it only imports `node:fs` and `node:path`, and the only reducer references matching `graph|convergence|upsert|deep_loop` are pass-through reads of precomputed `convergenceSignals`, not graph parsing or MCP calls (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:246-247; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:271; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:442).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:286:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:287:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:288:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:289:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:293:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:301:      "text": "`sk-improve-agent` follows a different path entirely: its resume contract replays a local \"coverage graph + registry\", and `mutation-coverage.cjs` persists an `improvement` JSON graph with `fs`/`path` helpers and `loopType: 'improvement'`, while the agent only consumes an orchestrator-provided summary as advisory context. That means it does not supply the missing shared `deep_loop_graph_*` bridge for research/review convergence (.opencode/skills/sk-improve-agent/SKILL.md:294-300; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:9-10; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:21; .opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:50-67; .opencode/agents/agent-improver.md:175-177).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:304:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:305:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:306:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:307:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:311:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:319:      "text": "Both deep-loop convergence contracts still document a reducer-owned in-memory graph bridge that is not present in the live reducer: deep research says \"the reducer builds an in-memory coverage graph\" when `graphEvents` exist, and deep review says the same for review iterations (.opencode/skills/sk-deep-research/references/convergence.md:1181-1205; .opencode/skills/sk-deep-review/references/convergence.md:658-683).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:322:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:323:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:324:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:325:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:329:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:337:      "text": "The 042 graph-integration packet explicitly recorded the intended bridge as already implemented: its implementation summary says the reducer parses `graphEvents`, calls `deep_loop_graph_upsert`, and falls back through `JSONL -> local JSON graph -> SQLite projection`, which sharpens this audit result into a current reality gap between packet claims and runtime wiring (.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:340:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:341:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:342:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:343:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:347:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:358:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:359:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:360:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:361:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:365:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:372:      "id": "finding-4-2-sk-deep-research-s-persisted-lineage-metadata-stays-wired-to-fresh-session-defau",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:373:      "text": "`sk-deep-research`'s persisted lineage metadata stays wired to fresh-session defaults in the normal runtime path I inspected. The auto workflow seeds `lineage.lineageMode: \"new\"`, `lineage.parentSessionId: null`, and `lineage.continuedFromRun: null` during config creation (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:157-180`), then later uses a synthesis fallback of `'completed-continue'` if no stop reason is found (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-409`). The reducer's status view reads lifecycle mode only from `config.lineage.lineageMode`, while its JSONL load drops all non-`iteration` records (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490`). That means resume/reopen semantics can influence control flow without updating reducer-visible lineage state away from `new`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:376:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:377:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:38-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:378:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-180",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:379:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:383:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:46-91",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:384:        ".opencode/skills/sk-deep-research/references/state_format.md:234-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:385:        ".opencode/skills/sk-deep-research/references/convergence.md:214-220",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:386:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:390:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:391:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:401:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:402:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:38-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:403:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-180",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:404:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:408:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:46-91",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:409:        ".opencode/skills/sk-deep-research/references/state_format.md:234-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:410:        ".opencode/skills/sk-deep-research/references/convergence.md:214-220",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:411:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:415:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:416:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:423:      "text": "Because both reducers collapse JSONL to iteration rows only, even a correctly emitted blocked-stop event would not survive into the synchronized dashboard/strategy surfaces without separate promotion logic. Deep research loads `parseJsonl(...).filter((record) => record.type === 'iteration')` before rendering status and metrics (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490`), and deep review derives both dashboard and status output from the same iteration-only view (`.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:485-487`, `.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:539-548`). So full `gateResults` and lifecycle events are currently dropped twice: first by the flat YAML outputs, then again by reducer ingestion rules.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:426:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:427:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:38-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:428:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-180",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:429:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:433:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:46-91",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:434:        ".opencode/skills/sk-deep-research/references/state_format.md:234-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:435:        ".opencode/skills/sk-deep-research/references/convergence.md:214-220",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:436:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:440:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:441:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:448:      "text": "The blocked-stop contract is much richer than the live workflow outputs. Deep research requires a replayable legal-stop bundle and says any failed gate must append a `blocked_stop` event carrying `stopReason: \"blockedStop\"`, `legalStop.blockedBy`, full `legalStop.gateResults`, and a `recoveryStrategy` (`.opencode/skills/sk-deep-research/references/convergence.md:214-220`, `.opencode/skills/sk-deep-research/references/convergence.md:305-309`). Deep review documents the same shape, including a full `gateResults` map and replay inputs (`.opencode/skills/sk-deep-review/references/convergence.md:58-85`, `.opencode/skills/sk-deep-review/references/convergence.md:411-411`). But the live auto workflows emit only `decision` plus a human-readable `reason` from convergence (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:268-286`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:356-372`), so the documented gate bundle never appears in the reducer-facing runtime outputs I inspected.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:451:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:452:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:38-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:453:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-180",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:454:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:458:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:46-91",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:459:        ".opencode/skills/sk-deep-research/references/state_format.md:234-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:460:        ".opencode/skills/sk-deep-research/references/convergence.md:214-220",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:461:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:465:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:466:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:473:      "text": "The live auto workflows classify `resume`, `restart`, `fork`, and `completed-session`, but the active YAML evidence I inspected does not append first-class `resumed`, `restarted`, `forked`, or `completed_continue` events during those branches. In `sk-deep-research`, the runtime branches only log/skip (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-153`), while the only explicit event appends in the file are `migration`, `paused`, and `synthesis_complete` (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:126`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:244`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:445`). `sk-deep-review` shows the same pattern: lifecycle branches are classified (`.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:155-177`), but the concrete event appends I found are `migration`, `paused`, `stuck_recovery`, and `synthesis_complete` only (`.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:149`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:329`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:382`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:661`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:476:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:477:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-003.md:38-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:478:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-180",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:479:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:390-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:483:        ".opencode/skills/sk-deep-research/references/loop_protocol.md:46-91",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:484:        ".opencode/skills/sk-deep-research/references/state_format.md:234-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:485:        ".opencode/skills/sk-deep-research/references/convergence.md:214-220",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:486:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:490:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:405-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:491:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-490",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:498:      "text": "`blockedStop` remains contractual rather than live in the inspected auto paths. The research and review convergence references require a first-class `blocked_stop` event carrying `stopReason=blockedStop` plus full legal-stop payloads, but the active auto YAMLs emit no `blocked_stop`/`blockedStop` record; their only explicit terminal stop-reason persistence is the later `synthesis_complete.stopReason` field (.opencode/skills/sk-deep-research/references/convergence.md:305-309; .opencode/skills/sk-deep-review/references/convergence.md:411-411; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:445-445; .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:661-661).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:501:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:502:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:503:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:504:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:505:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:509:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:510:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:511:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:512:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:516:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:517:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:524:      "text": "`stuckRecovery` is also not promoted consistently in live control flow. Deep review appends a raw `stuck_recovery` event with `strategy`, `targetDimension`, and `outcome`, but without `stopReason`; deep research's active `if_stuck_recovery` branch only logs, rewrites `next_focus`, and resets `stuck_count` without appending any recovery event at all (.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:375-383; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290; .opencode/skills/sk-deep-research/references/convergence.md:88-89; .opencode/skills/sk-deep-review/references/convergence.md:157-157; .opencode/skills/sk-deep-review/references/convergence.md:438-439).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:527:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:528:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:529:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:530:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:531:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:535:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:536:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:537:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:538:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:542:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:543:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:550:      "text": "Both convergence contracts publish `userPaused`, `blockedStop`, and `stuckRecovery` as shared `stopReason` enum values, and both also publish explicit legacy-label normalization tables that say raw labels like `paused`, `sentinel file detected`, `stuck_detected`, and `stuck_unrecoverable` should map into that shared enum (.opencode/skills/sk-deep-research/references/convergence.md:21-31; .opencode/skills/sk-deep-research/references/convergence.md:77-90; .opencode/skills/sk-deep-review/references/convergence.md:44-56; .opencode/skills/sk-deep-review/references/convergence.md:427-439).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:553:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:554:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:555:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:556:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:557:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:561:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:562:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:563:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:564:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:568:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:569:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:576:      "text": "Sentinel pauses do not become persisted `userPaused` state in the live auto workflows. Both loops only append `{\"type\":\"event\",\"event\":\"paused\",\"reason\":\"sentinel file detected\"}` and halt, with no `stopReason` field on the pause record despite the contract mapping that pair to `userPaused` (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246; .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:325-331; .opencode/skills/sk-deep-research/references/convergence.md:84-85; .opencode/skills/sk-deep-review/references/convergence.md:434-434).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:579:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:580:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:581:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:582:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:583:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:587:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:588:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:589:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:590:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:594:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:595:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:602:      "text": "The only persisted consumer-facing stop-reason field in the live auto workflows is a free-form `{reason}` string copied into `synthesis_complete.stopReason`, and both workflows explicitly default that value to `completed-continue` when no later stop reason is found. That fallback is outside the published shared enum, so even the terminal stop-reason field can drift away from `converged|maxIterationsReached|userPaused|blockedStop|stuckRecovery|error|manualStop` (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445; .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:580-661; .opencode/skills/sk-deep-research/references/convergence.md:890-890; .opencode/skills/sk-deep-review/references/convergence.md:565-565).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:605:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:606:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:607:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:608:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:609:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:613:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:614:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:615:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:616:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:620:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:621:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:627:      "id": "finding-5-6-the-reducer-dashboard-layer-does-not-repair-that-drift-deep-research-filters-jso",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:628:      "text": "The reducer/dashboard layer does not repair that drift. Deep research filters JSONL down to `record.type === 'iteration'` before building registry/dashboard state and only exposes lifecycle metadata from config, while deep review renders dashboard progress from iteration rows and exposes lifecycle mode from config without surfacing any `stopReason` field. In practice, that means no reducer-owned surface normalizes or republishes `userPaused`, `blockedStop`, or `stuckRecovery` for downstream consumers (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502; .opencode/skills/sk-deep-review/scripts/reduce-state.cjs:484-548; .opencode/skills/sk-deep-review/scripts/reduce-state.cjs:625-638).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:631:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:632:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-004.md:45-46",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:633:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:240-246",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:634:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:282-290",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:635:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:409-445",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:639:        ".opencode/skills/sk-deep-research/references/convergence.md:21-31",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:640:        ".opencode/skills/sk-deep-research/references/convergence.md:77-90",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:641:        ".opencode/skills/sk-deep-research/references/convergence.md:305-309",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:642:        ".opencode/skills/sk-deep-research/references/convergence.md:890-890",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:646:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:407-414",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:647:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:657:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:658:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:659:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:661:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:663:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:664:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:672:      "id": "finding-6-1-the-live-deep-research-stop-path-still-uses-an-inline-3-signal-vote-plus-checkqu",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:673:      "text": "The live deep-research stop path still uses an inline 3-signal vote plus `checkQualityGuards(state, strategy)` and never names any graph or contradiction helper in the active convergence step, even while calling the graph-aware model \"experimental/reference-only\" for live runs (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:676:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:677:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:678:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:680:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:682:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:683:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:695:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:696:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:697:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:699:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:701:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:702:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:710:      "id": "finding-6-4-the-published-deep-research-contract-says-that-when-graphevents-exist-the-reduce",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:711:      "text": "The published deep-research contract says that when `graphEvents` exist, \"the reducer builds an in-memory coverage graph and derives additional signals for the legal-stop gate evaluation,\" including graph coverage sub-checks (`.opencode/skills/sk-deep-research/references/convergence.md:1181-1205`). The live research reducer does not implement that bridge: its only imports are `fs` and `path`, and its convergence score is taken from `latestIteration.convergenceSignals?.compositeStop` or `latestIteration?.newInfoRatio` rather than any graph helper (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:714:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:715:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:716:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:718:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:720:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:721:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:733:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-49",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:734:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-005.md:31-32",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:735:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:737:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:739:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-13",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:740:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:749:      "text": "`claimVerificationRate` and `evidenceDepth` look like deliberate non-adoptions in `sk-deep-research` rather than current regressions. The shared graph stack exposes both signals, but the published deep-research semantic extension still names `semanticNovelty`, `contradictionDensity`, and `citationOverlap` as the added semantic checks, not claim-verification or path-depth gates (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:35-41; .opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/sk-deep-research/references/convergence.md:341-457).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:752:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:753:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:754:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:755:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:756:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:757:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:758:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:759:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:766:      "id": "finding-7-3-contradictiondensity-is-also-already-part-of-the-published-deep-research-converg",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:767:      "text": "`contradictionDensity` is also already part of the published deep-research convergence model: the contract says high contradiction density should block STOP and surface as a `qualityGate` semantic sub-check. Because the live workflow's active stop math still stops at the inline 3-signal vote, this is another concrete runtime gap rather than a merely hypothetical graph enhancement (.opencode/skills/sk-deep-research/references/convergence.md:363-386; .opencode/skills/sk-deep-research/references/convergence.md:411-423; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:770:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:771:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:772:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:773:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:774:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:775:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:776:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:777:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:785:      "text": "`sourceDiversity` is not a speculative extra from the shared graph stack; the deep-research convergence contract already makes it a first-class `qualityGate.checks` sub-check inside the legal-stop bundle. That means the current lack of an explicit shared-graph bridge for this signal is a runtime integration gap, not a deliberate omission (.opencode/skills/sk-deep-research/references/convergence.md:214-220; .opencode/skills/sk-deep-research/references/convergence.md:246-260; .opencode/skills/sk-deep-research/references/convergence.md:297-303).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:788:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:789:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:790:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:791:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:792:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:793:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:794:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:795:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:802:      "id": "finding-7-1-the-live-deep-research-workflow-still-evaluates-stop-with-a-local-3-signal-vote-",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:803:      "text": "The live deep-research workflow still evaluates STOP with a local 3-signal vote only: rolling average, MAD noise floor, and question entropy, then falls through a generic `checkQualityGuards(state, strategy)` call. The active convergence step does not name `contradictionDensity`, `sourceDiversity`, `claimVerificationRate`, or `evidenceDepth` anywhere in the runtime algorithm (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:806:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:807:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:808:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:809:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:810:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:811:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:812:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:813:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:820:      "id": "finding-7-6-the-reducer-still-cannot-surface-graph-backed-research-convergence-even-when-gra",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:821:      "text": "The reducer still cannot surface graph-backed research convergence even when `graphEvents` are present. It derives its convergence score from `latestIteration.convergenceSignals?.compositeStop ?? latestIteration?.newInfoRatio`, while the same convergence reference says the reducer should derive additional graph signals when `graphEvents` exist. That leaves graph-side research signals operationally disconnected from packet-level status surfaces (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249; .opencode/skills/sk-deep-research/references/convergence.md:1181-1205).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:824:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:825:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:826:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:827:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:828:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:829:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:830:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:831:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:838:      "id": "finding-7-4-the-shared-coverage-graph-stack-already-computes-a-richer-research-convergence-p",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:839:      "text": "The shared coverage-graph stack already computes a richer research convergence payload with `questionCoverage`, `claimVerificationRate`, `contradictionDensity`, `sourceDiversity`, and `evidenceDepth`, then evaluates `sourceDiversity` and `evidenceDepth` as blocking guards and escalates high contradiction density or unverified claims into blockers/warnings. So the infrastructure gap is not in the graph/MCP layer; it is in the deep-research runtime not calling that layer (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:35-41; .opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:175-275).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:842:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-39",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:843:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-006.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:844:        ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:845:        ".opencode/skills/sk-deep-research/SKILL.md:217-218",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:846:        ".opencode/skills/sk-deep-research/references/convergence.md:214-320",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:847:        ".opencode/skills/sk-deep-research/references/convergence.md:341-457",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:848:        ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:849:        ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-249",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:860:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:861:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:877:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:878:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:894:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:895:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:911:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:912:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:928:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:929:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-007.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:945:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:946:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:947:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:963:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:964:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:965:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:981:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:982:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:983:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:999:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1000:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1001:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1017:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1018:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:421-425`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1019:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-008.md:17-18`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1035:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1036:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:37-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1052:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1053:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:37-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1069:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1070:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:37-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1086:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1087:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:37-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1103:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:39-40",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1104:        ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:37-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1220:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1221:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1243:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1244:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1266:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1267:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1289:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1290:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1312:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:41-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1313:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-011.md:37-40`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1331:      "id": "finding-13-1-sk-deep-research-is-anchor-scoped-and-fail-closed-on-strategy-writes-its-reducer",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1332:      "text": "`sk-deep-research` is anchor-scoped and fail-closed on strategy writes. Its reducer only replaces the `key-questions`, `answered-questions`, `what-worked`, `what-failed`, `exhausted-approaches`, `ruled-out-directions`, and `next-focus` anchor blocks, and it throws if any requested anchor is missing; that matches the research strategy contract declaring sections 3 and 6-11 reducer-rewritten while leaving sections 1, 2, 4, 5, 12, and 13 stable (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-331`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:353-366`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1335:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1336:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1337:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1354:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1355:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1356:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1369:      "id": "finding-13-5-sk-deep-review-is-fail-open-where-sk-deep-research-is-fail-closed-if-an-expected",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1370:      "text": "`sk-deep-review` is fail-open where `sk-deep-research` is fail-closed: if an expected anchor is missing, `replaceAnchorSection()` returns the original content instead of halting, and the reducer still writes the resulting strategy file back out. That prevents cross-anchor spill into adjacent human-owned sections, but it also means corrupted or missing machine-owned zones can silently persist (`.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:431-445`, `.opencode/skills/sk-deep-review/scripts/reduce-state.cjs:640-645`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1373:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1374:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1375:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1392:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1393:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1394:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1411:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1412:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1413:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1426:      "id": "finding-13-2-the-same-sk-deep-research-reducer-only-writes-three-outputs-in-its-normal-pass-f",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1427:      "text": "The same `sk-deep-research` reducer only writes three outputs in its normal pass: `findings-registry.json`, `deep-research-strategy.md`, and `deep-research-dashboard.md`. I found no reducer path that touches iteration markdown or any other human-authored research asset during refresh (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1430:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:20-21`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1431:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:317-366`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1432:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:478-507`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1449:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1450:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1455:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1456:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1459:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1461:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1467:      "text": "The \"live\" graph convergence path exists, but as a separate MCP decision engine rather than the reducer math the loops visibly consume here. The handler computes research/review thresholds, classifies signals as `weighted` vs `blocking_guard`, and can return `STOP_ALLOWED` only \"pending newInfoRatio agreement.\" That means graph convergence is architecturally downstream-compatible with loop stop logic, but still not the same thing as the reducer's current `compositeStop` pass-through (`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:58-118`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:183-239`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:290-379`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1470:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1471:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1476:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1477:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1480:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1482:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1488:      "text": "The published convergence docs currently overstate reducer-side graph usage. Research docs say the reducer builds an in-memory graph from `graphEvents` and adds a `graphCoverage` sub-check to legal-stop evaluation; review docs make the same claim for `graphEvidence` under `findingStability`. But the workflow path I traced tells the LEAF agent to emit optional `graphEvents` and then runs `reduce-state.cjs`, while the inspected reducers themselves do not implement the documented graph rebuild or extra gate expansion (`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`, `.opencode/skills/sk-deep-review/references/convergence.md:661-683`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:432-437`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1491:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1492:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1497:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1498:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1501:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1503:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1508:      "id": "finding-14-3-the-shipped-deep-research-reducer-does-not-consume-either-of-those-graph-specifi",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1509:      "text": "The shipped deep-research reducer does not consume either of those graph-specific outputs directly. Its registry `convergenceScore` is set from `latestIteration.convergenceSignals.compositeStop ?? latestIteration.newInfoRatio ?? 0`, and the trend block only prints that scalar plus `coverageBySources`. I found no reducer path in the inspected ranges that reads `graphScore`, `blendedScore`, or graph gate results, so graph math only reaches research state if some earlier producer already collapsed it into `convergenceSignals.compositeStop` (`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`, `.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1512:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1513:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1518:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1519:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1522:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1524:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1533:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1534:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1539:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1540:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1543:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1545:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1554:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1555:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1560:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1561:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1564:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1566:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1575:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1576:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-013.md:38-39`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1581:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:244-273`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1582:        "`.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-443`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1585:        "`.opencode/skills/sk-deep-research/references/convergence.md:1183-1205`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1587:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:322-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1593:      "text": "The Code Graph routing promise is present in the agent prompts, but only there in the inspected loop surfaces: `@deep-research` says to route structural navigation through `code_graph_query`/`code_graph_context` at `.opencode/agents/deep-research.md:442`, and `@deep-review` repeats the same instruction at `.opencode/agents/deep-review.md:572`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1596:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1597:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1598:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1600:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1602:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1603:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1606:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1613:      "text": "The command docs do not carry that structural-routing contract forward. Their \"Code Context Bootstrap\" sections tell operators to use only CocoIndex before starting the loop, at `.opencode/commands/spec_kit/deep-research.md:203` and `.opencode/commands/spec_kit/deep-review.md:239`; neither command doc mentions `code_graph_query`, `code_graph_context`, or `deep_loop_graph_convergence`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1616:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1617:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1618:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1620:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1622:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1623:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1626:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1633:      "text": "The executable auto-YAML wrappers also omit structural graph tools from the live LEAF-tool budget. Deep research exposes `[Read, Write, Edit, Bash, Grep, Glob, WebFetch, mcp__cocoindex_code__search]` at `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`, and deep review exposes `[Read, Write, Edit, Bash, Grep, Glob, mcp__cocoindex_code__search]` at `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:76`; neither wrapper provisions `code_graph_query`, `code_graph_context`, or `deep_loop_graph_convergence`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1636:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1637:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1638:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1640:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1642:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1643:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1646:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1653:      "text": "The live wrapper path after each iteration is still \"emit optional `graphEvents`, then run `reduce-state.cjs`,\" not \"call structural graph tools before convergence.\" The deep-research workflow says to include optional `graphEvents` at `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326` and then runs `node .opencode/skills/sk-deep-research/scripts/reduce-state.cjs` at `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:331`; deep review mirrors that pattern at `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:436`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:437`, and `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:473`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1656:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1657:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1658:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1660:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1662:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1663:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1666:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1673:      "text": "The skill-level contracts undercut the agent-doc promise further. `sk-deep-research`'s `allowed-tools` list includes memory tools but no CocoIndex or Code Graph at `.opencode/skills/sk-deep-research/SKILL.md:4`, while `sk-deep-review` includes CocoIndex but still no structural graph tools at `.opencode/skills/sk-deep-review/SKILL.md:4`; its integration guidance likewise documents only semantic search via `mcp__cocoindex_code__search` at `.opencode/skills/sk-deep-review/SKILL.md:476`.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1676:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1677:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1678:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1680:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1682:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1683:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1686:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1692:      "id": "finding-15-6-within-the-inspected-deep-research-deep-review-skill-command-and-agent-materials",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1693:      "text": "Within the inspected deep-research/deep-review skill, command, and agent materials, the only literal `code_graph_query`/`code_graph_context` mentions I found were the two agent-doc routing lines at `.opencode/agents/deep-research.md:442` and `.opencode/agents/deep-review.md:572`. That is enough evidence to close the remaining D5 question: missing structural MCP tool calls are not just absent from live iterations, they are not provisioned anywhere except the agent prompt prose.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1696:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1697:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-014.md:1-33`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1698:        "`.opencode/agents/deep-research.md:437-442`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1700:        "`.opencode/commands/spec_kit/deep-research.md:201-203`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1702:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:72`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1703:        "`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326-331`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1706:        "`.opencode/skills/sk-deep-research/SKILL.md:1-4`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1716:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1717:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1726:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1728:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1729:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1735:      "text": "A different namespace-isolation weakness does exist on the shared read side for research/review sessions: the convergence handler never accepts `sessionId`, constructs its namespace from only `{ specFolder, loopType }`, and then calls `getStats()` plus `computeSignals()` / `computeMomentum()` without session scoping, so convergence decisions aggregate all sessions sharing the same spec folder and loop type (`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:47-52`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:92-111`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:511-545`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-220`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1738:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1739:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1748:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1750:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1751:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1756:      "id": "finding-16-4-because-the-shipped-shared-store-path-accepts-only-research-and-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1757:      "text": "Because the shipped shared-store path accepts only `research` and `review`, improvement-session nodes cannot currently co-mingle with deep-research or deep-review nodes inside the shared SQLite store through the visible MCP boundary. The more accurate finding is contract drift: Section 11 and Known Context both frame the improvement namespace as if it persists into the shared store, but the live writer and validator surfaces show a separate local JSON graph instead (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`, `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`, `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:599`, `.opencode/skills/sk-improve-agent/scripts/mutation-coverage.cjs:59-67`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:76-78`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1760:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1761:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1770:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1772:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1773:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1782:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1783:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1792:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1794:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1795:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1800:      "id": "finding-16-6-the-query-surface-only-partially-exposes-session-isolation-handlecoveragegraphqu",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1801:      "text": "The query surface only partially exposes session isolation. `handleCoverageGraphQuery()` accepts `sessionId` and passes it into `ns`, but the inspected helper queries for coverage gaps, contradictions, and unverified claims read by `spec_folder` and `loop_type` only, ignoring `ns.sessionId`; this means research/review sessions can be co-mingled on read even though improvement-mode entries are blocked from the DB entirely (`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:55-58`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-126`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:136-147`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1804:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1805:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1814:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1816:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1817:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1823:      "text": "The shared SQLite coverage graph does not admit `improvement` loop types at all. The DB layer defines `LoopType = 'research' | 'review'`, constrains valid kinds/relations by those two namespaces, and the schema enforces `CHECK(loop_type IN ('research', 'review'))`; the MCP upsert handler repeats the same validation and rejects any other value (`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:17`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:136-146`, `.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-db.ts:152-157`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:51-53`, `.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/upsert.ts:72-80`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1826:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1827:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:556-557`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1836:        "`.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:28-35`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1838:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:63-147`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1839:        "`.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:238-277`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1848:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1849:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1850:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1870:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1871:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1872:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1892:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1893:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1894:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1914:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1915:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1916:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1936:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1937:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-012.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1938:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-016.md:7-11`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1958:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1959:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1972:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1973:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1986:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:1987:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2000:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2001:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2014:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-53`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2015:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-017.md:42-43`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2028:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2029:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2044:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2045:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2060:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2061:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2076:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2077:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2092:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2093:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2108:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2109:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2124:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2125:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:36-37`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2140:      "text": "I found no visible contradiction-oriented graph gate in the operator path. The published improve-agent workflow enumerates scan, propose, score, benchmark, append, reduce, and stop steps, and the reducer’s stop evaluator uses no contradiction input or graph query surface, so contradiction handling remains absent from the visible coverage-graph loop rather than participating in stop blocking. (`.opencode/commands/improve/agent.md:272-286`, `.opencode/commands/improve/assets/improve_agent-improver_auto.yaml:137-158`, `.opencode/skills/sk-improve-agent/scripts/reduce-state.cjs:259-325`)",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2143:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2144:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:36-37`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2162:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2163:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:36-37`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2181:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2182:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:36-37`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2200:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2201:        "`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:36-37`",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2217:      "id": "ruled-out-1-10-opencode-agent-deep-research-md-159-166",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2218:      "text": ".opencode/agents/deep-research.md:159-166",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2222:      "id": "ruled-out-1-6-opencode-skill-sk-deep-research-references-loop-protocol-md-190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2223:      "text": ".opencode/skills/sk-deep-research/references/loop_protocol.md:190-198",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2227:      "id": "ruled-out-1-7-opencode-skill-sk-deep-research-references-loop-protocol-md-247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2228:      "text": ".opencode/skills/sk-deep-research/references/loop_protocol.md:247-255",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2232:      "id": "ruled-out-1-5-opencode-skill-sk-deep-research-references-loop-protocol-md-77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2233:      "text": ".opencode/skills/sk-deep-research/references/loop_protocol.md:77-84",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2237:      "id": "ruled-out-1-8-opencode-skill-sk-deep-research-references-state-format-md-145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2238:      "text": ".opencode/skills/sk-deep-research/references/state_format.md:145-177",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2242:      "id": "ruled-out-1-2-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2243:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2247:      "id": "ruled-out-1-3-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2248:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:438-444",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2252:      "id": "ruled-out-1-4-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2253:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2257:      "id": "ruled-out-1-9-opencode-skill-sk-deep-research-skill-md-190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2258:      "text": ".opencode/skills/sk-deep-research/SKILL.md:190-199",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2262:      "id": "ruled-out-1-1-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2263:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:36-38",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2268:      "text": "No evidence that prior iteration findings would make these observations redundant; `research/iterations/` was empty before this run and `deep-research-state.jsonl` only contained the config row (.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-state.jsonl:1).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2273:      "text": "No evidence that YAML workflow outputs bypass the reducer-owned packet surfaces; both auto and confirm flows still target `findings-registry.json` and `deep-research-dashboard.md` as synchronized outputs (.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:83-84; .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:197; .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:83-84; .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:196-217).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2277:      "id": "ruled-out-2-3-opencode-command-spec-kit-assets-spec-kit-deep-research-auto-yaml-326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2278:      "text": ".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:326",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2287:      "id": "ruled-out-2-5-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2288:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:103-127",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2292:      "id": "ruled-out-2-6-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2293:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:489-502",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2327:      "id": "ruled-out-2-1-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2328:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2332:      "id": "ruled-out-2-2-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2333:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-001.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2347:      "id": "ruled-out-3-4-opencode-skill-sk-deep-research-references-convergence-md-1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2348:      "text": ".opencode/skills/sk-deep-research/references/convergence.md:1181-1205",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2352:      "id": "ruled-out-3-3-opencode-skill-sk-deep-research-scripts-reduce-state-cjs-11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2353:      "text": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2382:      "id": "ruled-out-3-8-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2383:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md:47-55",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2387:      "id": "ruled-out-3-1-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2388:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:48-52",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2392:      "id": "ruled-out-3-2-opencode-specs-skilled-agent-orchestration-042-sk-deep-research-review-improveme",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2393:      "text": ".opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-002.md:7-10",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2397:      "id": "ruled-out-3-12-no-hidden-bridge-appeared-in-the-active-reducer-path-the-deep-research-reducer-s",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2398:      "text": "No hidden bridge appeared in the active reducer path: the deep-research reducer still has no MCP/tool client imports and no graph-event parsing branch, so the bridge is not merely buried deeper in the same file (.opencode/skills/sk-deep-research/scripts/reduce-state.cjs:11-12; .opencode/skills/sk-deep-research/scripts/reduce-state.cjs:246-247).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2412:      "id": "ruled-out-4-3-this-is-not-isolated-to-one-loop-the-research-and-review-auto-yamls-both-classif",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2413:      "text": "This is not isolated to one loop. The research and review auto YAMLs both classify the same lineage branches while only surfacing a smaller event set in the active runtime path (`.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:128-153`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:155-177`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2418:      "text": "This is not just a documentation omission. Both convergence references are explicit about first-class blocked-stop persistence and full gate bundles, so the drift is between published contract and live workflow serialization, not between two equally vague docs (`.opencode/skills/sk-deep-research/references/convergence.md:305-309`, `.opencode/skills/sk-deep-review/references/convergence.md:58-85`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2433:      "text": "This is not a documentation-gap false alarm: both convergence references already define the shared enum, the legacy-label normalization rules, and the required blocked-stop persistence shape in detail (.opencode/skills/sk-deep-research/references/convergence.md:21-31; .opencode/skills/sk-deep-review/references/convergence.md:44-56).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2447:      "id": "ruled-out-6-3-this-is-not-limited-to-one-loop-both-research-and-review-convergence-references-",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2448:      "text": "This is not limited to one loop. Both research and review convergence references promise graph-aware gate participation, but both active auto workflows keep STOP evaluation inline and local (`.opencode/skills/sk-deep-research/references/convergence.md:1181-1205`, `.opencode/skills/sk-deep-review/references/convergence.md:661-683`, `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:250-277`, `.opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:343-375`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2453:      "text": "`claimVerificationRate` and `evidenceDepth` should not yet be treated as contract drift in `sk-deep-research`; the current research convergence reference still frames the semantic extension around `semanticNovelty`, `contradictionDensity`, and `citationOverlap` instead (.opencode/skills/sk-deep-research/references/convergence.md:341-457).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2458:      "text": "I did not inspect confirm-mode workflows in this pass because the question was whether the active deep-research runtime currently bridges to the shared graph signal set; the auto workflow, convergence reference, reducer, and shared graph handler were sufficient to classify the signal gaps.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2463:      "text": "This is not primarily a shared-infrastructure deficit: the graph/MCP layer already computes and evaluates the richer research signals, including blocker semantics for `sourceDiversity`, `evidenceDepth`, contradictions, and unverified claims (.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:163-228; .opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:175-275).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2498:      "text": "This is not another reducer merge-stability regression. Iteration 9 already established that finding dedup and transition ordering stay stable at 50+ findings, which leaves observability and recovery handoff as the remaining D2 weakness (`.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-009.md:7-11`).",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2517:      "id": "ruled-out-12-2-repo-wide-symbol-search-for-the-new-d3-modules-surfaced-mostly-docs-specs-change",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2518:      "text": "Repo-wide symbol search for the new D3 modules surfaced mostly docs, specs, changelog entries, and tests, which limited negative-proof evidence to the runtime files that do exist.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2558:      "text": "A command-doc requirement to invoke structural graph tools before or during iterations; the inspected command surfaces only bootstrap CocoIndex.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2562:      "id": "ruled-out-15-3-a-wrapper-level-deep-loop-graph-convergence-step-on-the-visible-research-review-",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2563:      "text": "A wrapper-level `deep_loop_graph_convergence` step on the visible research/review iteration path; the cited YAML paths go from iteration output to reducer execution without a graph-convergence call.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2573:      "text": "I did not inspect hidden executor internals outside the published skill, workflow, and MCP handler surfaces, so the negative claim stays scoped to the shipped writer/validator/query path that is visible in-repo.",
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/findings-registry.json:2578:      "text": "The visible MCP coverage-graph path is not currently allowing `loop_type: \"improvement\"` to pollute shared research/review graphs; the stronger risk is documentation/strategy drift plus missing per-session read isolation inside the research/review namespaces.",
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md:3:description: "Automatic backend selection in memory_context that routes queries to code graph, CocoIndex, or both based on the query-intent classifier output."
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md:11:Automatic backend selection in memory_context that routes queries to code graph, CocoIndex, or both based on the query-intent classifier output.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md:13:When memory_context receives a query, the query-intent classifier scores it against structural and semantic keyword dictionaries. Structural queries (e.g., "what calls functionX", "show imports") are routed to the code graph for symbol-level results. Semantic queries (e.g., "find examples of error handling") are routed to CocoIndex for vector-similarity results. Hybrid queries trigger both backends and merge the results. The routing is transparent to the caller; memory_context auto-selects the backend without requiring explicit mode parameters.
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md:30:| `mcp_server/code_graph/lib/query-intent-classifier.ts` | Lib | Classification engine (structural/semantic/hybrid) |
.opencode/skills/system-spec-kit/feature_catalog/22--context-preservation-and-code-graph/19-query-intent-routing.md:31:| `mcp_server/code_graph/handlers/` | Handler | Structural backend (code graph query) |
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/09-scoring-observability.md:18:Scoring observability logs to `scoring_observations` with a 5% sampler (`SAMPLING_RATE = 0.05`). Each observation includes memory/query identifiers, score-before/score-after values, score delta and novelty/interference fields provided by the caller.
.opencode/skills/system-spec-kit/feature_catalog/09--evaluation-and-measurement/09-scoring-observability.md:22:Failures are fail-safe but not silent. Initialization, insert and stats-query errors are caught and logged with `console.error`, and scoring execution continues unchanged.
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/checklist.md:2:title: "...d-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/checklist]"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/checklist.md:11:  - "query"
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/checklist.md:16:    packet_pointer: "system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation"
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:21:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/deep-research-strategy.md:44-47`
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-019.md:22:- `.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/research/iterations/iteration-018.md:16-34`
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:4:File verification: all 7 catalog-listed `mcp_server` refs exist (catalog refs at [01-query-complexity-router.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/01-query-complexity-router.md:34), :35, :36, :42-:45).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:5:Function verification: `isComplexityRouterEnabled()` exists at [query-classifier.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-classifier.ts:45), `determineConfidence()` at :99, `classifyQueryComplexity()` at :143, `routeQuery()` at [query-router.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-router.ts:119).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:6:Flag defaults: `SPECKIT_COMPLEXITY_ROUTER` default ON (`raw !== 'false'`) at [query-classifier.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-classifier.ts:46).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:7:Behavior: tiering uses trigger+term count at [query-classifier.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-classifier.ts:175) and propagates to `traceMetadata.queryComplexity` at [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:1121).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:12:File verification: all 5 catalog-listed `mcp_server` refs exist (catalog refs at [02-relative-score-fusion-in-shadow-mode.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/02-relative-score-fusion-in-shadow-mode.md:32), :39-:42).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:13:Function verification: `fuseResultsRsf()` at [rsf-fusion.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/rsf-fusion.ts:114), `fuseResultsRsfMulti()` at :221, `fuseResultsRsfCrossVariant()` at :322.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:15:Behavior: live path uses RRF (`fuseResultsMulti`) at [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:816); `rsfShadow` metadata type slot still present at :151.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:16:Unreferenced files found: [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:150) (RSF compatibility slot is implemented there but not listed in catalog source table).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:20:File verification: all 4 catalog-listed refs exist (catalog refs at [03-channel-min-representation.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/03-channel-min-representation.md:32), :33, :39, :40).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:21:Function verification: `analyzeChannelRepresentation()` at [channel-representation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-representation.ts:95), `enforceChannelRepresentation()` at [channel-enforcement.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-enforcement.ts:81).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:22:Flag defaults: `SPECKIT_CHANNEL_MIN_REP` default ON at [channel-representation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-representation.ts:70).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:23:Behavior: quality floor `0.005` at :15; core appends promotions (no resort) at :177; wrapper resorts globally by score at [channel-enforcement.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-enforcement.ts:111).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:24:Unreferenced files found: [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:890) (pipeline integration callsite).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:28:File verification: all 2 catalog-listed refs exist (catalog refs at [04-confidence-based-result-truncation.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/04-confidence-based-result-truncation.md:32), :38).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:29:Function verification: `truncateByConfidence()` at [confidence-truncation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:113).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:32:Unreferenced files found: [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:913) (pipeline integration callsite).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:36:File verification: all 6 catalog-listed refs exist (catalog refs at [05-dynamic-token-budget-allocation.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/05-dynamic-token-budget-allocation.md:32), :33, :34, :40-:42).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:37:Function verification: `isDynamicTokenBudgetEnabled()` at [dynamic-token-budget.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/dynamic-token-budget.ts:57), `getDynamicTokenBudget()` at :79.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:39:Behavior: 1500/2500/4000 tiers match at :43-:47; computed early before channel execution in [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:640) before channel collection starts at :654.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:40:Mismatch detail: catalog says context-header overhead is ~12 tokens/result; code reserves ~26 (`(100+1)/4` rounded up) at [hybrid-search.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:233), applied at :1068-:1071.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:41:Unreferenced files found: [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:211) (`isContextHeadersEnabled()` is part of this feature behavior but not listed).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:45:File verification: all 54 catalog-listed `mcp_server` refs exist (implementation refs at [06-query-expansion.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/06-query-expansion.md:30)-:54; test refs at :72-:100).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:46:Function verification: `expandQueryWithEmbeddings()` at [embedding-expansion.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/embedding-expansion.ts:181), `isExpansionActive()` at :300, `expandQuery()` at [query-expander.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-expander.ts:73).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:47:Flag defaults: `isEmbeddingExpansionEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:112), default ON via [rollout-policy.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/rollout-policy.ts:59).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:48:Behavior: stop-words + min token length 3 enforced at [embedding-expansion.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/embedding-expansion.ts:72), :75, :135-:137; simple-query suppression at :196-:199; Stage1 baseline+expanded parallel run and baseline-first dedup at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:552)-:577.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:52:7. **F07 – LLM query reformulation**  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:53:File verification: all 7 catalog-listed refs exist (catalog refs at [07-llm-query-reformulation.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/07-llm-query-reformulation.md:32)-:36, :42, :50).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:54:Function verification: `cheapSeedRetrieve()` at [llm-reformulation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:102), `llm.rewrite()` at :340, `normalizeQuery()` at :421, `isLlmReformulationEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:319).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:55:Flag defaults: runtime default ON (search-flags + rollout-policy), but stale module comment says default FALSE at [llm-reformulation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:17).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:56:Behavior: constants match catalog (`SEED_LIMIT=3`, `MAX_VARIANTS=2`, `MIN_OUTPUT_LENGTH=5`, timeout 8000ms) at :58, :67, :73, :61; deep-mode gate in caller at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:797); fail-open seed retrieval at [llm-reformulation.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:121)-:125; shared 1h cache at [llm-cache.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-cache.ts:40).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:61:File verification: all 7 catalog-listed refs exist (catalog refs at [08-hyde-hypothetical-document-embeddings.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/08-hyde-hypothetical-document-embeddings.md:36)-:40, :46, :54).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:62:Function verification: `generateHyDE()` at [hyde.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hyde.ts:297), `runHyDE()` at :391, `lowConfidence()` at :133, `isHyDEActive()` at :111, `isHyDEEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:328).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:63:Flag defaults: `SPECKIT_HYDE` default ON via `isFeatureEnabled`; `SPECKIT_HYDE_ACTIVE` default ON (`val !== 'false' && val !== '0'`) at [hyde.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hyde.ts:112)-:113.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:64:Behavior: low-confidence thresholds match (`0.45`, min results `1`) at :87 and :93; timeout 8000ms at :96; deep-mode caller gate at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:867); shadow-vs-active merge behavior at [hyde.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/hyde.ts:420)-:425.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:68:9. **F09 – Index-time query surrogates**  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:69:File verification: all 4 catalog-listed refs exist (catalog refs at [09-index-time-query-surrogates.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/09-index-time-query-surrogates.md:36), :37, :43, :51).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:70:Function verification: `generateSurrogates()` at [query-surrogates.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-surrogates.ts:377), `matchSurrogates()` at :455, `isQuerySurrogatesEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:272).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:71:Flag defaults: runtime default ON via search-flags/rollout-policy, but stale module header says default OFF at [query-surrogates.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-surrogates.ts:6), :17.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:72:Behavior: constants align (`MAX_SUMMARY_LENGTH=200`, min questions 2, max 5, `MIN_MATCH_THRESHOLD=0.15`) at :80, :77, :74, :83; query-time matching is wired in Stage1 at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:983)-:1030 (contrary to older audit note).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:73:Unreferenced files found: [surrogate-storage.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/surrogate-storage.ts:182) and [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:991) implement core storage/query-time behavior but are not listed in the feature entry source table.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:77:File verification: all 6 catalog-listed refs exist (catalog refs at [10-query-decomposition.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/10-query-decomposition.md:36)-:38, :44, :45, :53).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:78:Function verification: `isMultiFacet()` at [query-decomposer.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-decomposer.ts:97), `decompose()` at :168, `mergeByFacetCoverage()` at :212, `isQueryDecompositionEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:252).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:79:Flag defaults: default ON via search-flags/rollout-policy.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:80:Behavior: conjunction and wh-word heuristic detection matches at [query-decomposer.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/query-decomposer.ts:30), :47, :106-:116; cap `MAX_FACETS=3` at :22; deep-mode gating in caller at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:396), :407.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:81:Mismatch detail: catalog says “any error returns only the original query”; Stage1 catch path falls through to standard expansion flow, not strictly “original-only” ([stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:448)-:460).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:86:File verification: all 6 catalog-listed refs exist (catalog refs at [11-graph-concept-routing.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/feature_catalog/12--query-intelligence/11-graph-concept-routing.md:30)-:32, :38, :39, :47).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:87:Function verification: `nounPhrases()` at [entity-linker.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/entity-linker.ts:150), `matchAliases()` at :201, `routeQueryConcepts()` at :311, `isGraphConceptRoutingEnabled()` at [search-flags.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:262).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:88:Flag defaults: default ON via search-flags/rollout-policy.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:89:Behavior: noun phrase extraction + alias-table matching exists ([entity-linker.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/entity-linker.ts:150)-:220, :232-:276).  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:90:Mismatch detail: catalog says matched concepts “activate the graph retrieval channel”; current Stage1 only records trace metadata (`matchedConcepts`, `graphActivated`) at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:331)-:337, with no downstream consumer found in pipeline code.  
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:99:| 2 | Relative score fusion in shadow mode | Yes (5/5) | Yes | N/A (runtime inert) | Yes (`hybrid-search.ts`) | MATCH |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:100:| 3 | Channel min-representation | Yes (4/4) | Yes | Yes | Yes (`hybrid-search.ts`) | MATCH |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:101:| 4 | Confidence-based result truncation | Yes (2/2) | Yes | Yes | Yes (`hybrid-search.ts`) | MATCH |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:102:| 5 | Dynamic token budget allocation | Yes (6/6) | Yes | Yes | Yes (`search-flags.ts`) | PARTIAL |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:104:| 7 | LLM query reformulation | Yes (7/7) | Yes | Runtime yes, comment drift | None material | PARTIAL |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:106:| 9 | Index-time query surrogates | Yes (4/4) | Yes | Runtime yes, comment drift | Yes (`surrogate-storage.ts`, `stage1-candidate-gen.ts`) | PARTIAL |
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/scratch/reaudit-2026-03-23/codex53-verifier.md:110:Prior-audit cross-check: [implementation-summary.md](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/specs/system-spec-kit/022-hybrid-rag-fusion/007-code-audit-per-feature-catalog/012-query-intelligence/implementation-summary.md:43) findings about default-comment contradictions still apply for reformulation/surrogates; prior “surrogates not wired” note is now outdated given current Stage1 integration at [stage1-candidate-gen.ts](/Users/michelkerkmeester/MEGA/Development/Opencode Env/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:983).  
.opencode/skills/system-spec-kit/feature_catalog/11--scoring-and-calibration/04-classification-based-decay.md:21:FSRS decay rates now vary by a two-dimensional multiplier matrix. On the context axis: decisions never decay (stability set to Infinity), research memories get 2x stability and implementation/discovery/general memories follow the standard rate. On the tier axis: constitutional and critical memories never decay, important memories get 1.5x stability, normal memories follow the standard, temporary memories decay at 0.5x and deprecated at 0.25x.
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/014-anchor-enforcement/scratch/legacy-memory-quarantine/1-skill-advisor-graph/006-skill-graph-sqlite-migration/graph-metadata.json",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/007-skill-graph-auto-setup/checklist.md",".opencode/skills/skill-advisor/SET-UP_GUIDE.md",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/scripts/skill-graph.json",".opencode/skills/skill-advisor/graph-metadata.json",".opencode/skills/mcp-coco-index/graph-metadata.json"],"sessionId":"rvw-011-gen2-2026-04-13T21-00-00Z","parentSessionId":"rvw-011-2026-04-13T16-50-00Z","lineageMode":"restart","generation":2,"continuedFromRun":null,"findingsCount":5,"findingsSummary":{"P0":0,"P1":4,"P2":1},"findingsNew":{"P0":0,"P1":4,"P2":0},"newFindingsRatio":0.18,"newInfoRatio":0.18,"timestamp":"2026-04-13T21:46:00Z","durationMs":960000,"findingRefs":["G2-F001","G2-F002","G2-F003","G2-F004","G2-F005"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail","feature_catalog_code":"pass","playbook_capability":"pass"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"No live routing or security regression survived the recheck. The remaining issues are packet-governance defects found by rereading the parent and phase docs after verifying that the former runtime blockers are closed.","ruledOut":["Former runtime findings F001, F010, F040/F041, and F110 remain closed on the current code paths.","Former blocker themes F020/F021/F022/F060 no longer survive as active P0s after rereading the updated packet scope, checklist, and Phase 005 closeout evidence.","No live regression was found in graph loading, validation, or the 44-case routing harness during this stabilization pass."],"releaseReadinessState":"in-progress","verdictCandidate":"CONDITIONAL","recoveryNote":"Generation-2 state exposed prior work through JSONL runs 001-005 only, so this pass reconstructed the missing markdown lineage and remaining run from those records plus the archived gen1 packet and live rereads."}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/iterations/iteration-007.md:5:- Files reviewed: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md, .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/implementation-summary.md, .opencode/changelog/01--system-spec-kit/v3.4.0.0.md, .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/iterations/iteration-007.md:22:- The runtime still contains a best-effort drop with a keep-the-column fallback. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-011.md:10:4. Phase `001-fix-delivery-progress-confusion` is pointed at the correct file but is too coarse about the change. The concrete implementation seam is not only the delivery regex block at `RULE_CUES.narrative_delivery`; it is also the progress-specific override at `scoreCategories()` lines `853-860`, because that floor lets implementation verbs beat delivery cues before Tier2 can correct the route. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/001-fix-delivery-progress-confusion/spec.md:10] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:853]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-011.md:22:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/001-fix-delivery-progress-confusion/spec.md:10`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/description.json:3:  "description": "Implement the converged pt-01 + pt-02 External Project research recommendations across Code Graph, Memory causal graph, and Skill Advisor — selective adaptati",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/description.json:10:    "research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/review-report.md:33:- **F005 - shared_space_id contract drift**: packet docs, checklist evidence, and changelog still overstate the deprecated-column cleanup compared with the retry-on-bootstrap runtime helper. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/review-report.md:35:- **F007 - workflow YAML family still documents non-canonical support-artifact indexing**: deep-review, deep-research, completion, and adjacent flows still use generic support-artifact or retired checkpoint wording instead of canonical spec-doc routing. [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:863] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml:1031] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/review/v3/iterations/iteration-009.md:31]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/review-report.md:25:- F002 - Shared-space column retirement story is internally inconsistent. The cleanup packet says shared_space_id stays, the changelog says it drops on startup, and the runtime performs a best-effort drop with an older-SQLite fallback that keeps the column. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:50-53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:92-94] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:4:description: "6-sub-phase plan implementing converged pt-01 + pt-02 research. License-audit gate, Code Graph foundation, three parallel uplift packets, docs rollup."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:21:Implement converged pt-01 + pt-02 research as 6 owner-scoped sub-phases. Sequencing: P0 license gate → Code Graph foundation → 3 parallel uplift packets → docs rollup. Each code sub-phase ships its own per-packet feature_catalog + manual_testing_playbook entries inline; trailing 006 sub-phase rolls up umbrella docs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:56:  - MODIFY `code_graph/handlers/query.ts:978-981, 862-909` — surface `reason`/`step`; extend `computeBlastRadius`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:58:- **No schema change** (purely JSON metadata + query-output enrichment).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:76:  - MODIFY `formatters/search-results.ts` — add `trustBadges` to envelope.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:78:- **Reuse existing fields** in `lib/storage/causal-edges.ts:82-94` and `lib/search/causal-boost.ts:327-338` (`computeTraversalFreshnessFactor`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-032.md:8:2. Duplicate-name noise is gone: duplicate rows fell from `2,020` to `0`, and duplicate-affected folders fell from `270` to `0`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:12:- No new P1 family. Existing `F005` remains open because the packet docs, checklist, and changelog still describe the `shared_space_id` cleanup as one-time / first-startup, while the runtime helper retries `ALTER TABLE memory_index DROP COLUMN shared_space_id` on each bootstrap until the column is gone or SQLite rejects the operation. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:14:- No new P1 family. Existing `F007` remains open because the workflow YAML family still tells operators to refresh or index generated continuity support artifacts, including broader `plan` and `implement` flows in addition to the already-open deep-review / deep-research / complete surfaces, even though the runtime manual says those artifacts are not the primary continuity source. [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:858] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml:1031] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_plan_auto.yaml:538] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_implement_auto.yaml:538] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_implement_confirm.yaml:582] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/README.md:38]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:30:- `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:31:- `.opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:48:- `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-006.md:53:- No new `mcp_server/` code path reads or writes `shared_space_id`; the only remaining in-scope runtime behavior is the known bootstrap drop helper behind `F005`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/checklist.md:127:- [x] [P2] CHK-050 The packet root contains only root docs, metadata JSONs, `path-references-audit.md`, and the support directories `research/` and `review/`. [EVIDENCE: packet root directory listing]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/checklist.md:55:- [ ] `backfill-research-metadata.js --apply` runs cleanly
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:16:- Review target: `mcp_server/lib/search/vector-index-schema.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:23:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts` | 7 | 9 | 7 | 7 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:35:- Evidence: [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444-1450], [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2299-2305], [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/spec.md:99-103], [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/spec.md:134-146], [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/implementation-summary.md:41-42], [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/implementation-summary.md:95]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:46:    ".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444-1450",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:47:    ".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2299-2305",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:73:- [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444-1450]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-007.md:74:- [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2299-2305]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md:4:Collapse the convergence-wave findings into the exact code-change descriptions that phase owners can implement without reopening the research questions.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md:10:4. The convergence verdict is stable: there are no unanswered packet questions left, no zero-coverage routing categories in the router tests, and no new evidence that changes the phase order. Additional research would mostly restate the same fix set; the next real signal comes from implementation and the before/after benchmark on the 132-sample corpus plus the targeted regression suite. [INFERENCE: synthesis across iterations 1-25]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md:13:- Continuing the research loop instead of handing the packet back to implementation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md:16:- Expecting another research pass to change the phase order or revive threshold tuning as the primary fix.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-025.md:32:- What I would do differently: Add an explicit "exact patch shape" step to the standard deep-research closeout template once accuracy questions are settled.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:3:  "packet_id": "system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:4:  "spec_folder": "system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:16:      "008 deep-research review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:17:      "010 deep-research review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:19:      "010 review research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:21:      "26 010 review research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:25:      "deep-research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:31:      "research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:40:      "research/research.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:41:      "research/resource-map.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:46:      "mcp_server/code_graph/handlers/query.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:54:      "mcp_server/formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:56:      "mcp_server/lib/search/search-utils.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:57:      "mcp_server/handlers/memory-search.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:63:        "name": "research.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:65:        "path": "research/research.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:93:        "name": "query.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:95:        "path": "mcp_server/code_graph/handlers/query.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:141:        "name": "search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:143:        "path": "mcp_server/formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:153:        "name": "search-utils.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:155:        "path": "mcp_server/lib/search/search-utils.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:159:        "name": "memory-search.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:161:        "path": "mcp_server/handlers/memory-search.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:177:        "name": "Deep Research Review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/graph-metadata.json:214:      "research/research.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:31:Phase 012 plans to land selective adaptations of External Project patterns into Public's Code Graph (002, 003), Skill Advisor (004), and Memory trust display (005). pt-02 deep-research iteration 9 read the upstream LICENSE and identified it as **PolyForm Noncommercial 1.0.0**, ranking direct source reuse as a P0 governance blocker [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:3] [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:10] [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:18]. No formal sub-phase audit had been recorded; this ADR closes that gate.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:35:The agent brief refers to `external/LICENSE`. The pt-02 research evidence chain consistently cites the LICENSE at `external/LICENSE` (no nested `external-project/` subdirectory) [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:3] [SOURCE: research/007-external-project-pt-02/deltas/iter-009.jsonl]. This ADR uses the research-cited path because that is the verifiable evidence trail; orchestrator should normalize the path in any subsequent briefs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:39:The repository's `.gitignore` excludes `external/` (line 76). Detached-HEAD worktrees created via `git worktree add` therefore do not contain the upstream LICENSE file in their checkout. This audit reproduces the **canonical PolyForm Noncommercial 1.0.0** text published by the PolyForm Project at `https://polyformproject.org/licenses/noncommercial/1.0.0`, which is the licence identity established by the pt-02 research executor (`cli-codex` model `gpt-5.5`, reasoning `high`, service tier `fast`) when it read `external/LICENSE` lines 1, 19, and 31 in iteration 9 [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:10].
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:105:Personal use for research, experiment, and testing for
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:114:public research organization, public safety or health
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:194:| **Personal Uses / Noncommercial Organizations** | Defines the permitted-purpose scope: personal study, hobby, education, research, government, charitable, environmental, public-safety, public-health. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:195:| **Fair Use** | Preserved — fair-use carve-outs (research citation, criticism, transformative analysis) survive unchanged. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:199:**Summary:** PolyForm Noncommercial 1.0.0 is a **permissive-for-noncommercial / restrictive-for-commercial** licence. It does **not** prohibit reading the source as architectural reference, citing it in research, or producing **clean-room** Public-side reimplementations that contain no copyrightable expression from the upstream codebase.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:209:3. **Pattern citation only.** Public's commits, ADRs, and code comments may name the External Project pattern as architectural inspiration with `[SOURCE: external/...:line]` references — these citations are research metadata, not derivative works.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:213:This definition aligns with phase-root ADR-012-001's "clean-room adaptation only" decision and with pt-02 INV-04 [SOURCE: research/007-external-project-pt-02/research.md:174].
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:225:| **003** Edge metadata | Edge `reason` + `step` JSON columns surfaced in `code_graph_query` output | **CONDITIONAL** | Pattern allowed; forbidden source forms: copying External Project's `relationships` table DDL, exact field names if they would constitute schema-text copying (Public is free to use the words "reason"/"step" as natural-language identifiers — they are not copyrightable individually, but the combined schema layout is). Public must derive its column shape from its own ADR, not from the upstream `relationships` schema. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:284:- pt-02 risk basis: `001-research-and-baseline/007-external-project/research/007-external-project-pt-02/iterations/iteration-009.md:3,10,18`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/decision-record.md:285:- pt-02 invariant: `research/007-external-project-pt-02/research.md:174` (INV-04 clean-room gate)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-010.md:16:- **F002 stays closed as a separate active registry item** and remains dependent on F005: no checklist/runtime evidence justified reopening it beyond the already-open shared-semantics drift in `spec.md`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/tasks.md:135:- [x] T066 Wave 1 — Apply 14 documentation fixes (templates, requirements, continuity, stop-hook, graph-metadata, READMEs, archive notes, playbook prose across sk-deep-review, sk-deep-research, system-spec-kit).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/tasks.md:191:- Preserved research archive: `research/005-release-cleanup-playbooks-pt-01/`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/spec.md:41:> `010/008-deep-research-review` audit (research/research.md §6 D5).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/spec.md:117:- pt-02 §12 RISK-01: `.../007-external-project/research/007-external-project-pt-02/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-002.md:23:- Deep-review and deep-research save hooks still require `generate-context.js` and verify canonical continuity landing in `implementation-summary.md`, `decision-record.md`, or `handover.md`. [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:857-870] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml:989-1002] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:638-650] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:817-827]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-002.md:34:- `.opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-002.md:35:- `.opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-016.md:10:4. The child phase's “keep the canonical entry, drop the duplicate” requirement implies a simple preference rule: preserve the first accepted basename and skip later collisions. That is safe as long as `deriveKeyFiles()` continues to append canonical packet docs deliberately. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/003-deduplicate-entities/spec.md] [INFERENCE: from current key-file ordering and phase scope]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-016.md:20:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/003-deduplicate-entities/spec.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-008.md:16:- Review target: `mcp_server/lib/search/vector-index-schema.ts`, packet `010` closure evidence
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-008.md:23:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts` | 7 | 9 | 7 | 7 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-008.md:46:- [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444-1450]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/iterations/iteration-008.md:47:- [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2299-2305]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/scratch/review-prompt.md:9:### 1. Source research (the ground truth that 012 is supposed to implement)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/scratch/review-prompt.md:10:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/scratch/review-prompt.md:11:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/scratch/review-prompt.md:35:- `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts` (cited at :862-909 computeBlastRadius, :978-981 query output)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/scratch/review-prompt.md:37:- `.opencode/skills/system-spec-kit/mcp_server/lib/search/causal-boost.ts` (cited at :49-77 freshness decay)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-006.md:9:3. Two `narrative_progress` prototype samples were misread as `research_finding` because they mention packet docs, sources, or one-source-of-truth work in language that overlaps the research cue set. Tier2 would have corrected both, but Tier1 accepted them early at `0.80`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:357] [INFERENCE: live corpus examples `NP-02` and `NP-04` from dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-006.md:10:4. One `research_finding` sample was classified as `metadata_only` because it discussed overlap in metadata and continuity terms, showing that `_memory.continuity` vocabulary can overpower research intent when the chunk is framed as findings about metadata. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:365] [INFERENCE: live corpus example `RF-03` from dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-004.md:13:- The deep-review/deep-research workflow quartet no longer carries the old workflow-side NF002 memory-path/save-target wording; each now routes and indexes the canonical spec document. [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:863] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml:995] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:644] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:822]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-003.md:4:This iteration cross-checked the `shared_space_id` cleanup narrative across the packet docs, the `v3.4.0.0` changelog, the shipped runtime schema helper, and the two requested lifecycle playbooks. Files reviewed: `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md`, `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md`, `.opencode/changelog/01--system-spec-kit/v3.4.0.0.md`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts`, `.opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/097-async-ingestion-job-lifecycle-p0-3.md`, and `.opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/144-advisory-ingest-lifecycle-forecast.md`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-003.md:6:Closure-status notes: F002 is not fully closed because the packet docs and changelog describe the `shared_space_id` cleanup as a one-time / first-startup migration, while the shipped runtime retries the `ALTER TABLE ... DROP COLUMN` path whenever the column still exists and silently no-ops on unsupported SQLite builds. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1537] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2338] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2474]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-003.md:19:- **F005**: Shared-memory docs overclaim a one-time drop migration — `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47` — `spec.md`, `checklist.md`, and the `v3.4.0.0` changelog all describe the `shared_space_id` cleanup as a one-time / first-startup migration, but `dropDeprecatedSharedSpaceColumn()` only guards on current column presence and reissues `ALTER TABLE memory_index DROP COLUMN shared_space_id` whenever bootstrap reaches `ensureGovernanceTables()`. On SQLite builds without `DROP COLUMN`, the runtime still silently no-ops and never reads or writes the column, but the documentation overclaims the exact retry lifecycle. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:103] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1537] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2338] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2474]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-003.md:23:- Runtime reads or writes `shared_space_id` outside the drop helper — ruled out because the only remaining in-scope `shared_space_id` hits under `mcp_server/` are the existence guard and `ALTER TABLE ... DROP COLUMN` inside `dropDeprecatedSharedSpaceColumn()`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1537] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/iterations/iteration-003.md:27:- The packet/checklist/changelog story is materially aligned on the key runtime behavior (SQLite 3.35+ drops the column, older builds silently no-op, runtime never reads or writes it); only the “one-time / first-startup” phrasing drifted from the shipped retry semantics. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-010.md:14:- Repo-wide `create-agent` search mainly surfaced changelog/spec history and unrelated create workflows; the actionable residual drift in this pass is limited to the folder-readme YAMLs and the two neighboring create-command docs cited above.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/prompts/agent-brief.md:20:   `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/external/LICENSE`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/prompts/agent-brief.md:22:6. **Research basis:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/prompts/agent-brief.md:23:   `.../research/007-external-project-pt-02/research.md` §12 (RISK-01 license contamination)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-strategy.md:97:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts` | [D1, D2, D3, D4] | 14 | 0 P0, 1 P1, 0 P2 | complete |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:2:title: "Resource Map: 008-deep-research-review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:6:  - "010 deep-research resource map"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:10:# Resource Map — 008-deep-research-review
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:12:This document maps every finding from the 10-iteration deep-research review to the files, line ranges, and tests that prove or disprove it. Use as the canonical lookup when triaging the findings into the recommended `010/008` and `010/009` follow-up sub-phases.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:71:| `001-research-and-baseline/007-external-project/external/LICENSE` | 17-22 | Actual notice line |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:89:| `mcp_server/code_graph/handlers/query.ts` | ~614-635 | `edgeMetadataOutput` site (re-validates) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:100:| `mcp_server/code_graph/handlers/query.ts` | ~859-897 | `computeBlastRadius` SQL/traversal — actual mechanism does not match documented `limit + 1` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:101:| `mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts` | (overflow tests) | Tests do not pin the mechanism |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:111:| `mcp_server/code_graph/handlers/query.ts` | (riskLevel derivation) | Hard-coded threshold count of 10 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:121:| `mcp_server/code_graph/handlers/query.ts` | 1121-1135 + sites for 5 codes | All 5 codes implemented in code |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:122:| `mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts` | (existing) | 4/5 codes tested; minConfidence schema-tested only |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:163:| `mcp_server/formatters/search-results.ts` | 235-360 | Merge-per-field + sanitizeAgeLabel |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:195:| `mcp_server/lib/search/search-utils.ts` | (CacheArgsInput) | Generation gated by enableCausalBoost |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:196:| `mcp_server/handlers/memory-search.ts` | (read+thread) | Generation read site |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/resource-map.md:197:| `mcp_server/tests/causal-edges-unit.vitest.ts` | (R-007-12 cases × 6) | Tests counter increments only — not cache-key change at memory_search level |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-state.jsonl:2:{"type":"iteration","mode":"review","run":7,"status":"insight","focus":"D1/D3 live shared-memory grep hits","dimension":"correctness","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/implementation-summary.md"],"sessionId":"2026-04-12T17:15:00Z-010-remove-shared-memory","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":1,"findingsSummary":{"P0":0,"P1":1,"P2":0},"findingsNew":{"P0":0,"P1":1,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":1.0,"noveltyJustification":"The first grep pass found one remaining active-runtime residue that still carries the removed shared-space identifier.","findingRefs":["DR-010-I007-P1-001"],"dimensionScores":{"correctness":7,"traceability":7},"coverage":{"filesReviewed":3,"filesTotal":3,"dimensionsComplete":["correctness","traceability"]},"ruledOut":["no-live-shared-memory-handlers-or-runtime-imports-remain-outside-the-schema-file"],"timestamp":"2026-04-12T17:16:00Z","durationMs":47000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-state.jsonl:3:{"type":"iteration","mode":"review","run":8,"status":"insight","focus":"D2/D4 stabilization of runtime grep surface","dimension":"security","dimensions":["security","maintainability"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/implementation-summary.md"],"sessionId":"2026-04-12T17:15:00Z-010-remove-shared-memory","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":1,"findingsSummary":{"P0":0,"P1":1,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.0,"noveltyJustification":"The second pass added no new hits and confirmed the residue is isolated to the kept schema-column exception.","findingRefs":["DR-010-I007-P1-001"],"dimensionScores":{"security":10,"maintainability":7},"coverage":{"filesReviewed":3,"filesTotal":3,"dimensionsComplete":["correctness","security","traceability","maintainability"]},"ruledOut":["no-additional-shared-memory-runtime-hits-remain-beyond-the-shared_space_id-schema-column"],"timestamp":"2026-04-12T17:17:00Z","durationMs":43000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/deep-review-state.jsonl:4:{"type":"iteration","mode":"review","run":14,"status":"thought","focus":"D1/D2/D3 live-code grep revalidation","dimension":"correctness","dimensions":["correctness","security","traceability"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/010-remove-shared-memory/implementation-summary.md"],"sessionId":"2026-04-12T17:15:00Z-010-remove-shared-memory","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":1,"findingsSummary":{"P0":0,"P1":1,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.0,"noveltyJustification":"The requested grep sweep found no new residue and reconfirmed only the pre-existing shared_space_id schema-column exception.","findingRefs":["DR-010-I007-P1-001"],"dimensionScores":{"correctness":8,"security":10,"traceability":8},"coverage":{"filesReviewed":3,"filesTotal":3,"dimensionsComplete":["correctness","security","traceability","maintainability"]},"ruledOut":["no-shared-memory-identifiers-remain-in-reviewed-live-code","no-hydra-identifiers-remain-in-reviewed-live-code"],"timestamp":"2026-04-12T19:54:00Z","durationMs":41000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-032.md:9:3. `decision` and `research_finding` also remain close (`0.8797`, `distance 0.1203`), which fits the remaining research, metadata, and source-of-truth vocabulary overlap seen in the benchmark replay. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:1] [INFERENCE: packet-local lexical-vector centroid analysis over routing-prototypes.json]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-010.md:15:- **F090**: The packet claim that the regression fixture "fixed 3 wrong expectations" is not traceable from repository evidence. The top-level implementation summary, the Phase 001 implementation summary, and the handover all repeat the claim, but the fixture path's visible git history in this repo is a single add commit (`a931525421`) that already contains the current 44-case dataset. Because no file in the packet names the three case IDs or preserves the old -> new expectation deltas, reviewers can confirm that the new `P1-GRAPH-*` rows match live behavior, but they cannot verify that the supposed three corrected expectations were genuine fixes rather than silent expectation rewrites. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:93] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/implementation-summary.md:91] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:55]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:2:title: "Deep Research: Phase 010 + 010/007 + 011 Independent Review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:5:  - "010 deep-research review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:7:  - "008 deep-research review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:9:  - "26 010 review research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:11:contextType: "research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:14:    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:17:    recent_action: "10-iteration cli-codex deep-research review complete. 18 distinct findings (1 P1, 17 P2) across all 010 + 010/007 + 011 surfaces. 33-closure systematic audit: 20 in code, 8 doc-only, 5 contradicted. Final convergence 0.93."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:21:      - "research.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:23:      - "008-deep-research-review-pt-01/iterations/iteration-001.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:24:      - "008-deep-research-review-pt-01/iterations/iteration-002.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:25:      - "008-deep-research-review-pt-01/iterations/iteration-003.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:26:      - "008-deep-research-review-pt-01/iterations/iteration-004.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:27:      - "008-deep-research-review-pt-01/iterations/iteration-005.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:28:      - "008-deep-research-review-pt-01/iterations/iteration-006.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:29:      - "008-deep-research-review-pt-01/iterations/iteration-007.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:30:      - "008-deep-research-review-pt-01/iterations/iteration-008.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:31:      - "008-deep-research-review-pt-01/iterations/iteration-009.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:32:      - "008-deep-research-review-pt-01/iterations/iteration-010.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:33:      - "008-deep-research-review-pt-01/deep-research-state.jsonl"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:36:# Deep Research: Phase 010 + 010/007 + 011 Independent Review
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:38:<!-- ANCHOR:research-summary -->
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:42:A 10-iteration deep-research review (cli-codex gpt-5.5 high fast, fresh-context per iteration) audited every system shipped under Phase 010 (sub-phases 001-006), the 010/007 remediation pass (T-A through T-F, claiming 33 closed findings), and the 011 manual-testing-playbook coverage follow-up (4 scenarios extended + 17 new vitest cases).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:57:<!-- /ANCHOR:research-summary -->
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:73:### Key research questions
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:163:**Claim** (010/007/T-F implementation-summary): `query.ts` requests `limit + 1` rows from SQL to detect true overflow.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:226:| D17 R-007-12 cache-key memory_search semantics | P2 | 010/009 | test-add |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:283:- R-007-12 memory_search end-to-end cache-key change test + enableCausalBoost gating test (D17)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:339:- `mcp_server/code_graph/handlers/query.ts` (lines 600-1500, esp. 614-635, 859-897, 1048-1058, 1121-1135)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:351:- `mcp_server/formatters/search-results.ts` (lines 235-360 trust-badge merge + age allowlist + DI seam + fetch-result shape)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:353:- `mcp_server/lib/search/search-utils.ts` (CacheArgsInput.causalEdgesGeneration)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:354:- `mcp_server/handlers/memory-search.ts` (generation read + thread)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:359:- `mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:385:`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:389:| `strategy.md` | Research charter, per-iteration focus rotation, convergence detection |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:390:| `deep-research-config.json` | Frozen config (executor, RQs, non-goals, stop conditions) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/research.md:391:| `deep-research-state.jsonl` | Append-only event log (init + 10 iteration_complete events) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-004.md:4:Traceability review of the six deep-review/deep-research/complete workflow YAMLs for any lingering `memory/*.md` checks or "support artifact" wording.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-004.md:17:- This pass found the stale wording concentrated in `spec_kit_complete_*`; the broader family search did not surface equivalent `support artifact` matches in the deep-review or deep-research YAMLs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-state.jsonl:2:{"type":"iteration","mode":"review","run":1,"status":"complete","focus":"Correctness re-verification of retired memory-path rejection and startup-drop semantics","dimensions":["correctness"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts",".opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/skills/system-spec-kit/mcp_server/tests/full-spec-doc-indexing.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/memory-parser-extended.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts"],"sessionId":"review-v5-20260414T153445Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":0,"findingsSummary":{"P0":0,"P1":0,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.00,"timestamp":"2026-04-14T15:50:00Z","durationMs":48000,"findingRefs":[],"traceabilityChecks":{"spec_code":"pass","checklist_evidence":"pass","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"pending"},"coverage":{"correctness":true,"security":false,"traceability":false,"maintainability":false},"ruledOut":["Legacy /memory/ parsing support in extractSpecFolder is not an active correctness bug because acceptance is gated by isMemoryFile() and memory-save.","Startup helper/comment remediation did not introduce an obvious destructive side effect."],"focusTrack":"correctness","convergenceSignals":{"rollingAvg":0.00,"madScore":0.00,"dimensionCoverage":0.25,"compositeStop":0.11}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-state.jsonl:3:{"type":"iteration","mode":"review","run":2,"status":"complete","focus":"Traceability re-verification of shared_space_id retirement semantics across spec, checklist, changelog, and runtime helper","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts"],"sessionId":"review-v5-20260414T153445Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":1,"findingsSummary":{"P0":1,"P1":0,"P2":0},"findingsNew":{"P0":1,"P1":0,"P2":0},"newFindingsRatio":1.00,"timestamp":"2026-04-14T15:58:00Z","durationMs":46000,"findingRefs":["F005"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"pass","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"pending","changelog_runtime":"pass"},"coverage":{"correctness":true,"security":false,"traceability":true,"maintainability":false},"noveltyJustification":"F005 remains open because spec.md still contradicts the every-startup idempotent shared_space_id retirement semantics now matched by the checklist, changelog, and runtime helper.","ruledOut":["The changelog no longer carries the old first-launch-only wording.","The checklist/runtime pairing is still consistent.","No executable runtime mismatch was found in scope."],"focusTrack":"traceability","convergenceSignals":{"rollingAvg":0.50,"madScore":0.50,"dimensionCoverage":0.50,"compositeStop":0.18}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-state.jsonl:5:{"type":"iteration","mode":"review","run":4,"status":"complete","focus":"Traceability sweep of spec-kit workflow YAML family for canonical-doc wording and scratch checkpoint paths","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_plan_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_plan_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_implement_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_implement_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_resume_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_resume_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_debug_confirm.yaml"],"sessionId":"review-v5-20260414T153445Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":3,"findingsSummary":{"P0":2,"P1":1,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.50,"timestamp":"2026-04-14T16:14:00Z","durationMs":52000,"findingRefs":["NF002"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"pass","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"fail","changelog_runtime":"pass"},"coverage":{"correctness":true,"security":false,"traceability":true,"maintainability":false},"noveltyJustification":"F007 is closed, but the remaining workflow drift under NF002 is now narrowed to plan_confirm and implement_confirm prose.","ruledOut":["Remaining memory/*.md mentions in complete workflows are negative guardrails only.","resume/debug YAMLs use canonical wording.","No generated-support-artifact-path token remains in scope."],"focusTrack":"traceability","convergenceSignals":{"rollingAvg":0.60,"madScore":0.10,"dimensionCoverage":0.50,"compositeStop":0.14}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-state.jsonl:7:{"type":"iteration","mode":"review","run":6,"status":"insight","focus":"Traceability re-verification of cross-runtime deep-review manuals and lifecycle continuity docs","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/agents/deep-review.md",".claude/agents/deep-review.md",".codex/agents/deep-review.toml",".gemini/agents/deep-review.md",".opencode/commands/spec_kit/plan.md",".opencode/commands/spec_kit/complete.md",".opencode/commands/spec_kit/implement.md",".opencode/commands/spec_kit/handover.md",".opencode/commands/spec_kit/resume.md",".opencode/commands/spec_kit/debug.md",".opencode/commands/spec_kit/deep-review.md",".opencode/commands/spec_kit/deep-research.md"],"sessionId":"review-v5-20260414T153445Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":5,"findingsSummary":{"P0":2,"P1":3,"P2":0},"findingsNew":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":1.00,"timestamp":"2026-04-14T16:31:00Z","durationMs":50000,"findingRefs":["F003"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"pass","skill_agent":"pending","agent_cross_runtime":"fail","feature_catalog_code":"pending","playbook_capability":"partial","changelog_runtime":"pass"},"coverage":{"correctness":true,"security":false,"traceability":true,"maintainability":false},"noveltyJustification":"F003 reopens because the deep-review manuals now split between legacy and canonical iteration-write contracts, while F004 remains functionally closed.","ruledOut":["F004 does not reopen as a full lifecycle continuity failure.","implement.md internal references path is not operator-facing continuity guidance."],"focusTrack":"traceability","convergenceSignals":{"rollingAvg":0.75,"madScore":0.25,"dimensionCoverage":0.50,"compositeStop":0.12}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-state.jsonl:9:{"type":"iteration","mode":"review","run":8,"status":"complete","focus":"Security re-verification of save/index trust boundaries and retired-path rejection","dimensions":["correctness","security","traceability"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts",".opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts",".opencode/skills/system-spec-kit/mcp_server/utils/validators.ts",".opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/full-spec-doc-indexing.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts"],"sessionId":"review-v5-20260414T153445Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":7,"findingsSummary":{"P0":2,"P1":3,"P2":2},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.00,"timestamp":"2026-04-14T16:47:00Z","durationMs":48000,"findingRefs":[],"traceabilityChecks":{"spec_code":"pass","checklist_evidence":"pending","skill_agent":"pending","agent_cross_runtime":"fail","feature_catalog_code":"partial","playbook_capability":"partial","changelog_runtime":"pass"},"coverage":{"correctness":true,"security":true,"traceability":true,"maintainability":false},"ruledOut":["Legacy extractSpecFolder compatibility is not an active bypass in the reviewed save/index entry points.","No new path-expansion regression appeared in validator hardening."],"focusTrack":"security","convergenceSignals":{"rollingAvg":0.50,"madScore":0.10,"dimensionCoverage":0.75,"compositeStop":0.16}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/review-report.md:22:    ".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444-1450",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/review-report.md:23:    ".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2299-2305",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/006-continuity-refactor-gates-pt-01/010-remove-shared-memory/review-report.md:41:- If schema migration is now safe, remove or rename the dormant `shared_space_id` column definitions in [`vector-index-schema.ts`](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1444).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-001.md:11:- F002 baseline remains consistent on executable correctness: the spec and checklist both claim an every-startup, idempotent `dropDeprecatedSharedSpaceColumn()` call with silent fallback on unsupported SQLite, and the runtime still implements that behavior from `ensureGovernanceTables()`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:52] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1549]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-001.md:16:- The startup helper/comment remediation did not introduce an obvious destructive side effect: if `shared_space_id` is already absent the helper returns immediately, and if `DROP COLUMN` is unsupported it swallows the error and leaves the orphan column unused. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-001.md:19:- No scoped test file reviewed here explicitly simulates the older-SQLite `DROP COLUMN` failure branch, so that fallback was confirmed by direct code inspection rather than a dedicated test assertion. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1542]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/review-report.md:42:| F002 | **Open** | P0 (derivative) | Not reopened as a separate active registry item, but it is still not closed because F005 remains open. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-brief.md:22:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-brief.md:23:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-026.md:4:Re-scan the active `.opencode/specs/` corpus after phases `001`-`003` and doc-alignment phase `005` landed, while keeping the original “exclude `z_archive`” boundary so the eight original research questions can be compared directly.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-026.md:34:Turn the raw rescan into before/after deltas against the original eight research questions, then separate parser wins from stale-metadata lag.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-010.md:4:    next_safe_action: "Synthesize research.md and resource-map.md from iter 010 + prior 9; orchestrator runs canonical save"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-010.md:56:| D17: R-007-12 tests prove generation increments but not `memory_search` cache-key semantics | P2 | `010/009-test-rig-adversarial-coverage` | test-add |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/deep-review-strategy.md:83:- SQL injection in the reviewed `skill-graph-db.ts` query paths.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:2:{"type":"iteration","mode":"review","run":1,"status":"complete","focus":"correctness - retired memory path closure verification","dimension":"correctness","dimensions":["correctness"],"findingsCount":0,"newFindingsRatio":0,"noveltyJustification":"The inspected runtime handlers, command assets, and current runtime harness all aligned on rejecting or no longer emitting retired memory/*.md public paths, while the remaining legacy literals were ruled out as historical reconciliation coverage.","findingsSummary":{"P0":0,"P1":0,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"upgrades":[],"resolved":["F001","NF003"],"findingRefs":[],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts",".opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-index-discovery.ts",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts",".opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts",".opencode/commands/create/assets/create_agent_auto.yaml",".opencode/commands/create/assets/create_agent_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml"],"traceabilityChecks":{"summary":{"required":1,"executed":1,"pass":1,"partial":0,"fail":0,"blocked":0,"notApplicable":0,"gatingFailures":0},"results":[{"protocolId":"spec_code","status":"pass","gateClass":"hard","applicable":true,"counts":{"pass":1,"partial":0,"fail":0},"evidence":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2080-2085",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-index-discovery.ts:27-28",".opencode/commands/create/assets/create_agent_auto.yaml:573-580",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:862-866",".opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:1048-1049"],"findingRefs":[],"summary":"Runtime save/index behavior and the inspected command assets aligned on canonical spec-doc or generated-artifact paths; no active retired memory/*.md public path remained."}]},"sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T12:53:14Z","durationMs":900000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:3:{"type":"iteration","mode":"review","run":2,"status":"complete","focus":"security - governance/provenance/retention and save-hook path enforcement","dimension":"security","dimensions":["security"],"findingsCount":0,"newFindingsRatio":0,"noveltyJustification":"Re-reading the governed ingest path, bounded spec-doc-health walk-up, and public YAML save hooks confirmed the canonical save gate stayed closed and surfaced no new security defect.","findingsSummary":{"P0":0,"P1":0,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"upgrades":[],"resolved":[],"findingRefs":[],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts",".opencode/skills/system-spec-kit/mcp_server/lib/governance/scope-governance.ts",".opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts",".opencode/skills/system-spec-kit/shared/parsing/spec-doc-health.ts",".opencode/commands/create/assets/create_agent_auto.yaml",".opencode/commands/create/assets/create_agent_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml"],"sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T12:58:30Z","durationMs":480000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:4:{"type":"iteration","mode":"review","run":3,"status":"complete","focus":"traceability - shared_space_id migration narrative and lifecycle playbook canonical-surface verification","dimension":"traceability","dimensions":["traceability"],"findingsCount":1,"newFindingsRatio":1,"noveltyJustification":"This pass produced one fully new P2 traceability finding about one-time / first-startup wording drift while separately closing the lifecycle-playbook artifact concern.","findingsSummary":{"P0":0,"P1":0,"P2":1},"findingsNew":{"P0":0,"P1":0,"P2":1},"findingsRefined":{"P0":0,"P1":0,"P2":0},"upgrades":[],"resolved":["F004"],"findingRefs":["F005"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/097-async-ingestion-job-lifecycle-p0-3.md",".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/144-advisory-ingest-lifecycle-forecast.md"],"traceabilityChecks":{"summary":{"required":3,"executed":3,"pass":1,"partial":2,"fail":0,"blocked":0,"notApplicable":0,"gatingFailures":0},"results":[{"protocolId":"spec_code","status":"partial","gateClass":"advisory","applicable":true,"counts":{"pass":0,"partial":1,"fail":0},"evidence":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md:47",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md:65",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md:103",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1537",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2338",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2474"],"findingRefs":["F005"],"summary":"Packet docs and changelog match the important runtime contract but overstate the migration as one-time / first-startup on unsupported SQLite builds."},{"protocolId":"checklist_evidence","status":"partial","gateClass":"advisory","applicable":true,"counts":{"pass":0,"partial":1,"fail":0},"evidence":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md:53",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1537",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541"],"findingRefs":["F005"],"summary":"CHK-013 correctly says the runtime never reads or writes shared_space_id, but its one-time fallback wording is slightly stronger than the shipped retry behavior."},{"protocolId":"playbook_capability","status":"pass","gateClass":"hard","applicable":true,"counts":{"pass":1,"partial":0,"fail":0},"evidence":[".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/097-async-ingestion-job-lifecycle-p0-3.md:19",".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/097-async-ingestion-job-lifecycle-p0-3.md:35",".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/144-advisory-ingest-lifecycle-forecast.md:19",".opencode/skills/system-spec-kit/manual_testing_playbook/05--lifecycle/144-advisory-ingest-lifecycle-forecast.md:35"],"findingRefs":[],"summary":"Both audited lifecycle playbooks point at canonical spec docs and not at retired memory artifacts."}]},"ruledOut":["lifecycle playbooks still pointing at retired memory artifacts","runtime reads or writes shared_space_id outside the drop helper"],"focusTrack":"traceability","sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T13:09:00Z","durationMs":600000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:5:{"type":"iteration","mode":"review","run":4,"status":"complete","focus":"maintainability - continuity manuals, workflow wording, and shared_space_id severity validation","dimension":"maintainability","dimensions":["maintainability"],"findingsCount":3,"newFindingsRatio":0.83,"noveltyJustification":"This pass found two fully new P1 command/workflow contract defects and upgraded the prior shared_space_id wording advisory from P2 to P1 after re-reading the runtime against the shipped wording.","findingsSummary":{"P0":0,"P1":3,"P2":0},"findingsNew":{"P0":0,"P1":2,"P2":0},"findingsRefined":{"P0":0,"P1":1,"P2":0},"upgrades":["F005:P2->P1"],"resolved":[],"findingRefs":["F005","F006","F007"],"filesReviewed":[".opencode/agents/write.md",".claude/agents/write.md",".gemini/agents/write.md",".codex/agents/write.toml",".codex/agents/speckit.toml",".codex/agents/handover.toml",".opencode/commands/create/assets/create_agent_auto.yaml",".opencode/commands/create/assets/create_agent_confirm.yaml",".opencode/commands/memory/save.md",".opencode/commands/memory/learn.md",".opencode/commands/memory/search.md",".opencode/commands/memory/README.txt",".opencode/commands/memory/manage.md",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts"],"ruledOut":["F003 active agent-manual retired-artifact drift","NF001 create-agent canonical-doc regression"],"focusTrack":"maintainability","sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T14:05:00Z","durationMs":420000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:6:{"type":"iteration","mode":"review","run":5,"status":"complete","focus":"maintainability - saturation pass over remaining workflow and command surfaces","dimension":"maintainability","dimensions":["maintainability"],"findingsCount":3,"newFindingsRatio":0,"noveltyJustification":"Saturation pass over the remaining workflow and command surfaces found no new defect family; it only reconfirmed the already-open F006/F007 wording drift, with F007 also present in the spec_kit_complete_* guardrail text.","findingsSummary":{"P0":0,"P1":3,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"upgrades":[],"resolved":[],"findingRefs":["F006","F007"],"filesReviewed":[".opencode/commands/memory/save.md",".opencode/commands/memory/learn.md",".opencode/commands/memory/search.md",".opencode/commands/memory/README.txt",".opencode/commands/memory/manage.md",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_confirm.yaml"],"ruledOut":["residual /memory:manage shared references in audited command/workflow surfaces","new standalone memory/*.md authoring flow beyond F006/F007 wording drift"],"focusTrack":"maintainability","sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T14:18:00Z","durationMs":300000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:7:{"type":"iteration","mode":"review","run":6,"status":"complete","focus":"maintainability - exact-pattern closure sweep over scoped packet, workflow, manual, and runtime surfaces","dimension":"maintainability","dimensions":["maintainability"],"findingsCount":3,"newFindingsRatio":0,"noveltyJustification":"This was a closure sweep over the scoped packet, workflow, manual, and runtime surfaces; it found stable residual findings only and did not reveal any hidden P0/P1 defect family beyond F005, F006, and F007.","findingsSummary":{"P0":0,"P1":3,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"findingRefs":["F005","F006","F007"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/commands/memory/save.md",".opencode/commands/memory/manage.md",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_plan_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_implement_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_implement_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_resume_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_resume_confirm.yaml",".opencode/commands/create/assets/create_agent_auto.yaml",".opencode/commands/create/assets/create_agent_confirm.yaml",".opencode/agents/write.md",".claude/agents/write.md",".gemini/agents/write.md",".codex/agents/write.toml",".codex/agents/speckit.toml",".codex/agents/handover.toml",".opencode/skills/system-spec-kit/mcp_server/lib/README.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts"],"ruledOut":["hidden /memory:manage shared references in the scoped command/workflow/manual/runtime sweep","new standalone memory/*.md or {spec_folder}/memory/*.md authoring contract beyond the existing F006/F007 wording cluster","new mcp_server shared_space_id read/write path beyond the known bootstrap drop helper","spec_kit_resume_* fallback wording as a new primary-contract defect"],"focusTrack":"maintainability","sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T14:32:00Z","durationMs":360000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-state.jsonl:11:{"type":"iteration","mode":"review","run":10,"status":"complete","focus":"traceability - terminal convergence and final-synthesis prep over residual F005/F006/F007/F008","dimension":"traceability","dimensions":["traceability"],"findingsCount":4,"newFindingsRatio":0,"noveltyJustification":"Terminal convergence pass re-checked the residual cluster against the already-audited primary evidence and found no new or refined defects; the packet still converges on the same four documentary P1 findings.","findingsSummary":{"P0":0,"P1":4,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"findingsRefined":{"P0":0,"P1":0,"P2":0},"upgrades":[],"resolved":[],"findingRefs":["F005","F006","F007","F008"],"traceabilityChecks":{"summary":{"required":4,"executed":4,"pass":1,"partial":0,"fail":3,"blocked":0,"notApplicable":0,"gatingFailures":0},"results":[{"protocolId":"spec_code","status":"fail","gateClass":"hard","applicable":true,"counts":{"pass":0,"partial":0,"fail":1},"evidence":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md:47",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md:53",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534"],"findingRefs":["F005"],"summary":"Packet docs, checklist evidence, and changelog still overstate the shared_space_id cleanup relative to the retry-on-bootstrap runtime helper."},{"protocolId":"feature_catalog_code","status":"fail","gateClass":"advisory","applicable":true,"counts":{"pass":0,"partial":0,"fail":1},"evidence":[".opencode/skills/system-spec-kit/feature_catalog/04--maintenance/01-workspace-scanning-and-indexing-memoryindexscan.md:22",".opencode/skills/system-spec-kit/feature_catalog/feature_catalog.md:649",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-index-discovery.ts:27"],"findingRefs":["F008"],"summary":"The live feature catalog still claims retired spec-folder memory-file discovery even though runtime discovery excludes memory/ directories."},{"protocolId":"agent_cross_runtime","status":"pass","gateClass":"advisory","applicable":true,"counts":{"pass":1,"partial":0,"fail":0},"evidence":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/review/v3/iterations/iteration-008.md:17",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/review/v3/iterations/iteration-009.md:24"],"findingRefs":[],"summary":"Latest correctness passes still show live runtime entry points rejecting or avoiding retired memory/*.md paths, so the residual cluster is documentary only."},{"protocolId":"checklist_evidence","status":"fail","gateClass":"advisory","applicable":true,"counts":{"pass":0,"partial":0,"fail":1},"evidence":[".opencode/commands/memory/save.md:145",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:863",".opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml:1031"],"findingRefs":["F006","F007"],"summary":"Residual command and workflow wording still points operators at retired continuity or support-artifact models instead of the canonical packet-doc contract."}]},"coverage":{"filesReviewed":14,"filesTotal":14,"dimensionsComplete":["correctness","security","traceability","maintainability"]},"ruledOut":["reopened runtime or security bypass for retired memory/*.md acceptance or emission","any new residual defect family beyond F005/F006/F007/F008"],"focusTrack":"traceability","sessionId":"rvw-2026-04-14T12-37-42Z-v3","generation":1,"lineageMode":"new","timestamp":"2026-04-14T16:00:00Z","durationMs":300000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-020.md:63:- **F081** — **P1** — live `skill-advisor` <-> `mcp-coco-index` dependency pair is underweighted at `0.4` relative to the packet contract. First seen: 009. Reconfirmed: 013.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-016.md:10:4. The best implementation guidance for phase `003` is fail-open plus explicit observability. Reuse the `llm-reformulation.ts` pattern of env-based endpoint configuration, `AbortController`, and warning logs, then surface the Tier3 latency and cache-hit state through existing routing audit entries. That keeps the atomic save path usable even when the classifier is unavailable or slow. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:203] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:1175]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-016.md:22:- `.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:203`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-001.md:13:- The `dropDeprecatedSharedSpaceColumn()` remediation is comment-only for behavior: the helper still returns when the table or column is absent and still swallows `DROP COLUMN` failures on older SQLite. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1539] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1542]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-001.md:16:- The v4 comment added above `dropDeprecatedSharedSpaceColumn()` did not introduce a runtime behavior change; the executable body remains idempotent and unchanged in effect. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1538]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-037.md:10:4. Four packets still store `planned` while `implementation-summary.md` exists on disk, but the drift is now traceable to explicit frontmatter status choices rather than normalization or stale-backfill noise: the three `018-research-content-routing-accuracy` child phases keep `status: planned` in `spec.md`, `plan.md`, and `checklist.md`, and the `006-canonical-continuity-refactor` root still carries explicit `planned` status in multiple canonical docs. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/001-fix-delivery-progress-confusion/checklist.md:3] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/checklist.md:12] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:7:- The parent ledger marks every top-level task `T001`-`T012` complete and does not contain any explicit deferred/superseded follow-up lane or pointer to later packet-owned work. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:43] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:70]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:8:- Later child ledgers do carry packet-owned follow-up state: `001-research-findings-fixes/tasks.md` leaves five items explicitly deferred, and `005-repo-wide-path-migration/tasks.md` records a later closeout pass that had to rewrite execution tracking and re-run packet verification. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:60] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:80] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:54] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:73]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:9:- The parent `implementation-summary.md` still reads like a completed delivery summary plus a short limitations list; it does not compensate for the parent task ledger by enumerating the later deferred/remediation lanes for maintainers. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:32] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:97] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:103]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:14:- **F170**: The parent `tasks.md` is no longer an accurate execution ledger for the packet. It presents the original 12-task implementation story as fully complete, but packet-owned follow-up work later moved into child ledgers that contain explicit deferred items (`001-research-findings-fixes`) and an additional closeout/remediation pass (`005-repo-wide-path-migration`). Because the parent tracker never records that handoff or marks any superseded/deferred follow-up state, maintainers reading the top-level task file alone get a false "all work complete" view of the packet. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:43] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:70] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:80] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:58] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:73]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:17:- There is no separate "deferred item without rationale" defect inside the parent `tasks.md` itself, because the parent ledger contains no explicit deferred markers at all. The concrete problem is omission of later deferred/remediation lanes from the top-level tracker. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:43] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:70]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-018.md:18:- This is not a case where deferred work vanished completely from packet-local documentation; the follow-up child ledgers do record those lanes. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/tasks.md:80] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:58] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/tasks.md:73]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:15:- **P0 — ADR does not quote the actual LICENSE verbatim.** `spec.md:85` requires the LICENSE file to be read in full and quoted verbatim in the audit ADR, but `decision-record.md:45` labels the quote as canonical PolyForm text rather than the actual file, and `decision-record.md:85` preserves the PolyForm example notice (`Yoyodyne`) instead of the real GitNexus Required Notice at `001-research-and-baseline/007-git-nexus/external/LICENSE:21`. This means the P0 license gate is not actually closed. Fix by replacing the ADR quote with the actual `external/LICENSE` contents and re-running the classification against that text.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:19:- **P1 — Required Notice handling drops the upstream notice identity.** The ADR correctly states that Required Notice lines must be carried forward in distributions at `decision-record.md:190`, but the quoted license block contains only the example notice at `decision-record.md:85` while the actual upstream notice is `Required Notice: Copyright Abhigyan Patwari (...)` at `001-research-and-baseline/007-git-nexus/external/LICENSE:21`. This creates a compliance and attribution risk for any future packaging or documentation that relies on this ADR as the notice source. Fix by recording the actual Required Notice and making downstream PR guidance preserve it when license terms are distributed.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:23:No additional findings. The allow-list broadly matches the phase-root ownership contracts: phase root keeps clean-room adaptation mandatory at `decision-record.md:18`, Code Graph/Memory/Skill Advisor owner boundaries are reflected in pt-02 research at `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md:284`, and the sub-phase table covers 002-005 at `001-clean-room-license-audit/decision-record.md:221`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:27:No findings. The reviewed surface is documentation-only; it adds no hot path, query, cache, indexing, or runtime memory behavior.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:39:- **P1 — Downstream unblocking is unsafe until the actual-license and validation gaps are resolved.** The continuity frontmatter says the next safe action is to unblock downstream Code Graph work at `implementation-summary.md:16`, and the checklist repeats that status is complete at `checklist.md:30`, but the actual LICENSE differs from the ADR quote at `001-research-and-baseline/007-git-nexus/external/LICENSE:21` and strict validation remains pending at `checklist.md:28`. Letting 002-005 proceed from this state can bake an incorrect notice record into later PR attestations. Fix by reopening 001, correcting the quote/notice, passing validation, then reissuing the unblock.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/review/review-report.md:51:1. Replace the ADR's canonical PolyForm quote with the actual `001-research-and-baseline/007-git-nexus/external/LICENSE` text, including the real Required Notice.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-002.md:8:- **F005**: the shared-space retirement story is still not uniform across the audited surfaces. The runtime, checklist, and changelog now describe an every-startup idempotent retry with silent no-op fallback on unsupported SQLite, but `spec.md` still mixes that with "one-time", "runs once", and "first launch" language. Under this audit's severity rule, that means the prior closure blocker is not actually fixed. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:103] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:182] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-002.md:15:- The checklist/runtime pairing is still consistent; no checklist drift surfaced in this pass. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-002.md:16:- No executable runtime mismatch was found in scope; the failure is traceability consistency, not code behavior. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/tasks.md:74:**Note:** Follow-up work is tracked in child phase ledgers: `001-research-findings-fixes/tasks.md` (5 deferred P1 items) and `005-repo-wide-path-migration/tasks.md` (closeout remediation pass). This parent ledger covers the original implementation scope only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-014.md:13:- **F130**: CHK-031's evidence string has gone stale. The checklist still says `"use figma"` proves the dependency pull-up with `mcp-code-mode at 0.92`, but the current live advisor returns the same dependency reason at `0.95`. The integration still works; the problem is that the checklist is freezing an old score and no longer serves as executable evidence. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:79] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:120] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:127]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-014.md:14:- **F131**: CHK-032's sk-code family-affinity example no longer reproduces. The checklist claims `"build full stack"` demonstrates `!graph:family(sk-code)`, but the exact prompt currently returns no recommendations, and the shipped regression prompt `"build full stack typescript service"` returns only `sk-code-opencode` without any family-affinity reason. That means the checklist is now pointing at a non-demonstrable proof point for the claimed behavior. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:80] [SOURCE: .opencode/skills/skill-advisor/scripts/fixtures/skill_advisor_regression_cases.jsonl:38] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:141] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:151]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-006.md:17:- The agent-tree continuity search returned no `memory/*.md` or "support artifact" hits, so the residual drift in this pass is concentrated in spec-kit command playbooks rather than runtime agent manuals.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-006.md:20:Switch dimensions: run a security pass across the runtime gating and save/search entry points to ensure the documentation drift did not mask a trust-boundary or path-acceptance regression.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/deep-review-strategy.md:76:- The startup helper/comment remediation did not introduce an obvious destructive side effect; the helper remains idempotent and swallows unsupported `DROP COLUMN` failures. (iteration 1, evidence: `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/checklist.md:13:      Evidence: brief's `external/LICENSE` path corrected to `external/LICENSE` (see `decision-record.md` §"Source-of-Record Path Correction"); licence identity (PolyForm Noncommercial 1.0.0) established by pt-02 deep-research executor in iteration 9 [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:10]; `external/` is gitignored (`.gitignore:76`) and absent from detached worktrees, so canonical PolyForm Noncommercial 1.0.0 text from `https://polyformproject.org/licenses/noncommercial/1.0.0` was reproduced as the verbatim quote, with the actual-file-deviation reopen rule documented.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-013.md:7:1. `extractReferencedFilePaths()` currently accepts almost any backticked token that contains a dot-extension; it only excludes URLs, `./research/`, `../`, wildcards, and `...`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:320-334]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-002.md:7:1. Tier1 heuristic scoring is cue-driven and asymmetric: each cue regex adds `0.18`, but some categories also receive floor boosts, such as `narrative_progress` at `0.72`, `narrative_delivery` at `0.74`, `decision` at `0.76`, `task_update` at `0.90`, `handover_state` at `0.84`, `research_finding` at `0.80`, `metadata_only` at `0.93`, and `drop` at `0.92`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:340] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:842]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-002.md:8:2. Target selection is deterministic by category: progress and delivery append paragraphs to `implementation-summary.md`, research and handover append sections, tasks update a phase anchor, metadata writes `_memory.continuity`, and `decision` switches between ADR insertion on `L3/L3+` and in-place summary updates on `L1/L2`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:918] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/content-router.vitest.ts:92]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-002.md:10:4. Several prototype texts intentionally contain overlapping language such as "verification," "same-pass alignment," "research," or "current state," which means the library is designed to expose confusion pressure rather than remove it. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:47] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:173]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v3/deep-review-findings-registry.json:25:      "note": "The workflow YAML family (deep-review, deep-research, spec_kit_complete, plus the plan/implement save-context flows) still describes indexing generated support artifacts and authoring guardrails under memory/ instead of pinning continuity to canonical spec documents."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-009.md:7:- A repo-wide JSON sweep across all 21 skill metadata files found no missing required top-level/derived fields, no invalid targets, no self-referencing edges, no sibling / prerequisite symmetry mismatches, and no `depends_on` cycles. `python3 .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py --validate-only` still passes with only the two pre-existing zero-edge warnings for `sk-deep-research` and `sk-git`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-009.md:13:- **F080**: `skill-advisor/graph-metadata.json` ships twenty `enhances` edges at `0.8`, but the packet defines `enhances` weights as `0.3-0.7`. Because the compiler still accepts any numeric weight inside `[0.0, 1.0]`, the live routing graph is already outside its documented contract and can apply stronger-than-promised overlay boosts to every routed companion skill. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:115] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:118] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:10] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:30] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:142]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-009.md:14:- **F081**: The `skill-advisor` <-> `mcp-coco-index` hard-dependency pair is encoded at `0.4` in both directions even though `depends_on` / `prerequisite_for` are documented as `0.7-1.0`. That means the shipped graph labels the relationship as "cannot function without target" while serializing it with a soft-hint strength, which can underweight a dependency that the packet claims is foundational to routing. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:115] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:117] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:121] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:7] [SOURCE: .opencode/skills/mcp-coco-index/graph-metadata.json:17]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-009.md:21:- None. Once the packet's edge-type weight table was re-checked, the broad corpus sweep collapsed quickly to two concrete live contract violations in `skill-advisor` / `mcp-coco-index`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:90:| Include `prerequisite_for` in compiled output | Research audit (P0-4) found topology-only graph insufficient; `prerequisite_for` is now compiled into runtime adjacency |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:134:### 001-research-findings-fixes
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:138:Fixed 5 P0 blocking issues and 2 of 5 P1 issues from the 10-iteration GPT-5.4 deep research audit. P0 fixes: ghost candidate guard in `_apply_graph_boosts()` and `_apply_family_affinity()`, edge gaps filled for 4 skill metadata files, `intent_signals` included in compiled output (size target relaxed to 4KB), `prerequisite_for` compiled into runtime adjacency, and `_graph_boost_count` tracking added with 10% confidence penalty when >50% graph-derived. P1 fixes: evidence separation improved and topology augmented. Files: `skill_advisor.py`, `skill_graph_compiler.py`, 4 `graph-metadata.json` files.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:164:**Status:** planned but not executed. No implementation-summary exists. Tasks and checklist items all unchecked. Design: migrate skill graph storage to SQLite (`skill-graph.sqlite`) with `skill_nodes` and `skill_edges` tables, WAL mode, FK constraints, and 4 MCP tool handlers (scan, query, status, validate). Recorded as planned work not completed.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:176:**Status:** planned but not executed. No implementation-summary exists. 4/12 tasks done; all checklist items unchecked. Design: create feature catalogs for `sk-deep-research`, `sk-deep-review`, and `sk-improve-agent` — root catalog files with per-category sub-files covering loop lifecycle, state management, convergence, and output/review dimensions. Recorded as partially started work not completed.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-005.md:14:- Section 3.3's damping constants still match the implementation: enhances uses `0.3`, siblings `0.15`, depends_on `0.2`, family affinity `0.08`, and the boost floor remains `0.1`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:145-147] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/plan.md:88-97] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:100-149]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-005.md:24:- **F040**: `validate_skill_metadata()` does not enforce the edge-type-specific weight bands promised by the packet. Section 3.1 says `depends_on` / `prerequisite_for` must be `0.7-1.0`, `enhances` `0.3-0.7`, `siblings` `0.4-0.6`, and `conflicts_with` `0.5-1.0`, but the validator only checks that each weight is numeric and inside `[0.0, 1.0]`. Semantically invalid metadata such as `depends_on: 0.1` or `siblings: 0.9` will therefore pass `--validate-only` and feed incorrect boost strengths into runtime routing. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:115-121] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:124-146] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:100-127]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-002.md:8:- **F005**: The v4 remediation is not fully closed because the changelog still says SQLite 3.35+ installs shed the deprecated column "on first launch" even though the spec, checklist, and helper comment all describe an every-startup idempotent retry path. [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-002.md:14:- The mismatch is not between runtime and packet-local docs; `spec.md`, `checklist.md`, and the helper comment all agree on every-startup idempotent behavior. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v5/iterations/iteration-008.md:14:- The deprecated `shared_space_id` cleanup remains fail-safe: startup drops the column when supported and otherwise leaves an unread orphan rather than reviving the old field. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1541] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1543] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1545]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:4:Compare the Wave 4 corpus tables directly against the eight original Wave 1 research answers.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:8:2. `key_files` quality improved sharply: resolution rose from `59.87%` (`3,172/5,298`) to `81.25%` (`3,818/4,699`), while stored `key_files` volume fell by `599` entries despite the corpus gaining `20` active packets. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:9:3. Status accuracy improved from `302` planned packets down to `56`, and `planned` folders with `implementation-summary.md` fell from `259` to `10`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:10:4. Trigger-cap enforcement is now fully clean: over-cap folders dropped from `216` to `0`, max trigger count fell from `33` to `12`, and excess triggers above the cap fell from `949` to `0`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:659-667] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:11:5. Duplicate entity rows went from `2,020` across `270` folders to `0`, but entity-cap pressure got worse: the 16-entity cap now hits `360` of `364` active folders. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-027.md:20:- `research/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:13:- A1: `computeBlastRadius` calls `queryImportDependentsForBlastRadius(minConfidence)` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:916`; that helper either calls `graphDb.queryFileImportDependents()` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:831` or runs a SQL import-edge scan at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:838`. The only result cap in `computeBlastRadius` is `.slice(0, limit)` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:967`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:14:- A2: No underlying SQL/traversal call requests `limit + 1`. The minConfidence SQL has no `LIMIT` clause between `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:838` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:849`, and the no-filter branch delegates with no limit argument at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:831`. The code comment says "`limit + 1` semantically" while using the whole BFS frontier at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:960`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:15:- A3: `partialResult` is set for overflow only inside the `overflowed` spread branch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1003` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1008`; it is absent when the spread condition is false at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1016`. Other fallback branches set `partialResult` independently for unresolved, ambiguous, empty-source, and compute-error cases at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1177`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1211`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1238`, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1281`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:16:- A4: Mental test, `limit: 5`, true affected count exactly 5: `totalAffectedBeforeSlice = affectedByFile.size` becomes `5` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:963`; the array is sliced to 5 at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:967`; `overflowed = totalAffectedBeforeSlice > limit` evaluates `5 > 5`, so `false`, at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`; the overflow fallback spread is skipped at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1003`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:17:- A5: Deciding line for runtime behavior is `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`, because `>` correctly avoids the exact-limit false positive. Deciding line for closure-integrity is `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:30`, which explicitly requested `limit + 1` from underlying SQL.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:21:- B1: `args.minConfidence` is read at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1131` through `const minConfidence = clampNumericConfidence(args.minConfidence ?? 0)`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:22:- B2: It is clamped to `[0, 1]` by `clampNumericConfidence`, which returns `Math.max(0, Math.min(1, value))` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:624` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:628`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:23:- B3: `minConfidence: 0` effectively means no filtering. The helper takes the `minConfidence <= 0` branch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:830`, calls `queryFileImportDependents()` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:831`, and does not execute the `.filter(edge.confidence >= minConfidence)` path at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:862`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:24:- B4: `minConfidence: 1` reaches the SQL scan branch, parses edge confidence at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:860`, and keeps only `edge.confidence >= 1` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:862`. Since `clampNumericConfidence` caps above-1 values to 1 at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:628`, this behaves as "confidence equal to 1 after clamp."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:25:- B5: Omitted `minConfidence` defaults to `0` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1131`, so it follows the no-filter helper branch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:830`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:29:- C1 `limit_reached`: set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1007`. Trigger: the full traversal count exceeds `limit`, via `overflowed = totalAffectedBeforeSlice > limit` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968` and the overflow-only fallback branch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1003`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:30:- C2 `unresolved_subject`: set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1176`. Trigger: after candidate ambiguity checks, `graphDb.resolveSubjectFilePath(candidate)` returns a non-string or empty value at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1147` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1148`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:31:- C3 `ambiguous_subject`: set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1210`. Trigger: fq-name or name matching pushes one or more entries to `ambiguityCandidates` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1135` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1141`, then `ambiguityCandidates.length > 0` returns the ambiguity fallback at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:32:- C4 `empty_source`: set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1237`. Trigger: all raw subjects are processed without resolution failures or ambiguity, but no source file was accumulated, via `sourceFiles.length === 0` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1219`. This branch appears defensive and may be hard to hit through the current earlier unresolved branch.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:33:- C5 `compute_error`: set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1280`. Trigger: `computeBlastRadius(...)` throws inside the try block at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1247` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1248`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:34:- C6: The code paths are ordered, not nondeterministically mutually reachable. Ambiguous subjects continue without resolution at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1137` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1143`, then always return `ambiguous_subject` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`; unresolved returns immediately at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1160`; compute happens only after non-empty sources pass `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1247`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:35:- C7: The compute-error path logs with `console.warn` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1255`. The metric type includes `spec_kit.graph.blast_radius_failure_total` at `.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:513`, defines it as a counter with `code` label at `.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:537`, and increments it with `{ code: 'compute_error' }` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1260`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:38:- D1: For blast_radius, fq-name ambiguity populates `ambiguityCandidates[]` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1135`; name ambiguity after fq-name misses populates it at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1141`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:39:- D2: Each candidate object includes `symbolId`, `fqName`, `name`, `kind`, `filePath`, and `startLine`, mapped at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:200` through `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:208`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:40:- D3: The response shape is not stable across the four main operations. `ambiguityCandidates` is only in the blast-radius payload at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1301`; relationship operations surface ambiguity through `warnings` and `selectedCandidate` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1345`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1377`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1399`, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1420`. Outline has neither field in its payload at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1107`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:41:- D4: There is silent-ish disambiguation outside blast_radius: `resolveSubject` picks an operation-aware candidate at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:362` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:378`, returning `selectedCandidate` plus warnings when multiple matches exist at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:366` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:382`. Blast_radius explicitly avoids choosing a default by `continue`-ing on ambiguity at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1137` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1143`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:44:- E1: Runtime behavior is tested in `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:922`, with `minConfidence: 0.75` passed at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:958`, the filtered value echoed at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:963`, and the low-confidence file excluded at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:968`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:45:- E2: Handler tests cover omitted/default `0` incidentally at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:788` and an interior threshold `0.75` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:958`. They do not cover explicit runtime `0`, runtime `1`, or runtime `0.5`. Schema tests cover acceptance of `0.5`, `0`, and `1` at `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:516`, `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:525`, and `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:534`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:46:- E3: Unknown-param rejection is covered generically for strict schemas at `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:106` and by the allowed-args list that includes `minConfidence` for `code_graph_query` at `.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:676`, but there is no `code_graph_query`-specific unknown-parameter rejection case in the code-graph schema block. The rejection cases around `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:570` cover bad operation and bad minConfidence values, then unknown params for `code_graph_status` at `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:607`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:54:- **Evidence:** Runtime code sets all five literals at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1007`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1176`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1210`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1237`, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1280`. Tests assert unresolved fallback shape without `code` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:851`, and ambiguous fallback shape without `code` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:1004`; `rg` finds no `limit_reached`, `empty_source`, or `compute_error` assertions in that handler test file.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:61:- **Evidence:** Schema tests accept `0.5`, `0`, and `1` at `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:516`, `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:525`, and `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:534`, and reject out-of-range/non-numeric values at `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:580`, `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:589`, and `.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:598`. Runtime tests cover only an interior `0.75` filter at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:922` and default echo `0` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:788`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:62:- **Suggested action:** Add handler tests for explicit `minConfidence: 0` taking the `queryFileImportDependents()` path, `minConfidence: 1` retaining only confidence-1 edges, `minConfidence: 0.5` retaining equals-threshold edges, and omitted minConfidence defaulting to no filtering.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:65:- HANDLED: F12's runtime exact-limit behavior is correct; `5 > 5` is false at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`, so exact-limit responses do not get a false `limit_reached` fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:66:- HANDLED: `minConfidence` is clamped defensively in the handler at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1131`, even though schema validation already bounds it at `.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:461`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:67:- HANDLED: `compute_error` emits both operator-visible logging and metric instrumentation at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1255` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1260`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md:68:- HANDLED: Blast-radius ambiguity does not silently pick the first match; ambiguity candidates are surfaced and the query exits before resolution at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:54:The upstream `external/LICENSE` (path corrected from the brief's `external/LICENSE` per pt-02 evidence chain) is **PolyForm Noncommercial 1.0.0**, identified by the pt-02 deep-research executor (`cli-codex` model `gpt-5.5`, reasoning `high`, service tier `fast`) in iteration 9 [SOURCE: research/007-external-project-pt-02/iterations/iteration-009.md:10].
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:61:| Permitted purposes | Personal study, hobby, education, research, charitable / public-safety / public-health / environmental / government use |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:66:The licence does **not** prohibit reading the upstream source as architectural reference, citing it in research with `[SOURCE: external/...]` markers, or producing fresh Public-side implementations from a behavioural specification. It does prohibit any commercial use of the source itself, any verbatim copy, and any translated copy that preserves substantial similarity.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:103:| Sub-phase governance agent (`claude-opus-4-7`) | **APPROVED** for clean-room adaptation under PolyForm Noncommercial 1.0.0 | 2026-04-25 | Verbatim LICENSE quote published in `decision-record.md`; classification table covers 002, 003, 004, 005; fail-closed rule binding on all 012 PRs. Worktree-isolation caveat documented (canonical PolyForm Noncommercial 1.0.0 text reproduced because `external/` is gitignored and absent from detached worktrees; pt-02 research executor read the actual file in iteration 9 and confirmed identity). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:128:2. Discovered that `external/` is gitignored (`.gitignore:76`) and therefore absent from detached-HEAD worktrees. The brief's referenced `external/LICENSE` path also disagrees with the pt-02 research evidence chain, which consistently cites `external/LICENSE`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:186:1. **Verbatim text reproduced from canonical source, not the actual `external/LICENSE` file.** The detached-HEAD worktree does not contain the gitignored `external/` directory. The reproduction is from the canonical PolyForm Noncommercial 1.0.0 text published by the PolyForm Project, identified-as-applied by the pt-02 research executor in iteration 9. Any reviewer with direct access to `external/LICENSE` who finds a deviation (e.g. a `Required Notice:` line, modified clause, or different licence version) MUST re-open this ADR.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/001-clean-room-license-audit/implementation-summary.md:199:- pt-02 risk basis: `research/007-external-project-pt-02/iterations/iteration-009.md:3,10,18` and `deltas/iter-009.jsonl`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-026.md:9:3. The remaining preserved-subset errors are narrower: `narrative_progress -> research_finding` (`NP-02`, `NP-04`), `research_finding -> metadata_only` (`RF-03`), and one short `drop` fragment that falls below the refusal floor (`DR-05-s1`). [INFERENCE: packet-local preserved-subset replay over dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-026.md:11:5. The delivered fixes therefore solved the packet's original live-text hotspots. The residual errors now cluster around research/metadata overlap and very short telemetry fragments, not delivery or handover mechanics. [INFERENCE: packet-local preserved-subset replay over dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-strategy.md:1:# Deep Research Strategy: Skill Advisor Graph Quality Audit
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-strategy.md:3:## Research Charter
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-strategy.md:26:- [ ] Q8: How does the graph interact with CocoIndex semantic search?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-strategy.md:32:No prior memory found. This is a fresh research session on newly implemented code.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-033.md:9:3. The two `README.md / ARCHITECTURE.md` anomalies come from heading extraction in the 017 and 018 doc-alignment packets, where slash-joined surface labels are being retained as heading entities. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json:101-110] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/004-doc-surface-alignment/graph-metadata.json:93-102]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-033.md:19:- 50-entry random entity sample over `/tmp/phase019-research2/entity-sample.tsv`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-033.md:21:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-033.md:22:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/004-doc-surface-alignment/graph-metadata.json`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-007.md:10:- Local file-path validation still rejects paths outside allowed roots, explicit `..` traversal, and null-byte attempts before downstream handlers act on the path. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/utils/validators.ts:122] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/search-results-format.vitest.ts:97] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/search-results-format.vitest.ts:122]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-007.md:11:- Search-result classification still drops non-canonical document types and only returns canonical spec-document rows when the normalized path can be classified as a spec document. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:231] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:242] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:247]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/iterations/iteration-004.md:11:- **F002 remains open - the release narrative still contradicts the shipped fallback behavior.** The packet spec and checklist now describe a startup `DROP COLUMN` attempt with a silent no-op fallback on older SQLite, and the runtime implements exactly that, but the changelog still promises that existing databases auto-drop the deprecated column so no orphan columns remain. Those four sources still do not tell the same story. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47-48] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53-53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94-94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:257-258]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-state.jsonl:2:{"type":"iteration","mode":"review","run":1,"status":"complete","focus":"Correctness review of retired-memory path rejection and shared_space_id bootstrap helper behavior","dimensions":["correctness"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts",".opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/skills/system-spec-kit/mcp_server/tests/full-spec-doc-indexing.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/memory-parser-extended.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts"],"sessionId":"review-v4-20260414T145040Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":0,"findingsSummary":{"P0":0,"P1":0,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.00,"timestamp":"2026-04-14T15:00:00Z","durationMs":42000,"findingRefs":[],"traceabilityChecks":{"spec_code":"pending","checklist_evidence":"pending","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"pending"},"coverage":{"correctness":true,"security":false,"traceability":false,"maintainability":false},"ruledOut":["Behavioral regression in dropDeprecatedSharedSpaceColumn() from the v4 comment-only change."],"focusTrack":"correctness","convergenceSignals":{"rollingAvg":0.00,"madScore":0.00,"dimensionCoverage":0.25,"compositeStop":0.11}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-state.jsonl:3:{"type":"iteration","mode":"review","run":2,"status":"complete","focus":"Traceability review of F005 startup semantics across spec, checklist, changelog, and helper comment","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts"],"sessionId":"review-v4-20260414T145040Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":1,"findingsSummary":{"P0":1,"P1":0,"P2":0},"findingsNew":{"P0":1,"P1":0,"P2":0},"newFindingsRatio":0.65,"timestamp":"2026-04-14T15:06:00Z","durationMs":36000,"findingRefs":["F005"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"partial","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"pending"},"coverage":{"correctness":true,"security":false,"traceability":true,"maintainability":false},"noveltyJustification":"Prior v3 P1 finding F005 remains open because release documentation still describes a first-launch effect instead of the every-startup retry contract.","focusTrack":"traceability","convergenceSignals":{"rollingAvg":0.33,"madScore":0.50,"dimensionCoverage":0.50,"compositeStop":0.18}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-state.jsonl:5:{"type":"iteration","mode":"review","run":4,"status":"complete","focus":"Traceability review of workflow YAML family for lingering support-artifact and memory-path wording","dimensions":["correctness","traceability"],"filesReviewed":[".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_complete_confirm.yaml"],"sessionId":"review-v4-20260414T145040Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":3,"findingsSummary":{"P0":3,"P1":0,"P2":0},"findingsNew":{"P0":1,"P1":0,"P2":0},"newFindingsRatio":0.58,"timestamp":"2026-04-14T15:18:00Z","durationMs":38000,"findingRefs":["F005","F006","F007"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail","skill_agent":"pending","agent_cross_runtime":"pending","feature_catalog_code":"pending","playbook_capability":"fail"},"coverage":{"correctness":true,"security":false,"traceability":true,"maintainability":false},"noveltyJustification":"F007 remains open because spec_kit_complete_auto.yaml and spec_kit_complete_confirm.yaml still reference retired memory-path checks and generated support artifacts.","focusTrack":"traceability","convergenceSignals":{"rollingAvg":0.46,"madScore":0.50,"dimensionCoverage":0.50,"compositeStop":0.14}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-state.jsonl:8:{"type":"iteration","mode":"review","run":7,"status":"complete","focus":"Security review of retired-memory path trust boundaries and canonical-source enforcement","dimensions":["correctness","security","traceability"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/utils/validators.ts",".opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts",".opencode/skills/system-spec-kit/mcp_server/tests/search-results-format.vitest.ts",".opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts"],"sessionId":"review-v4-20260414T145040Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":4,"findingsSummary":{"P0":4,"P1":0,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.00,"timestamp":"2026-04-14T15:38:00Z","durationMs":36000,"findingRefs":["F004","F005","F006","F007"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail","skill_agent":"pass","agent_cross_runtime":"pass","feature_catalog_code":"pass","playbook_capability":"fail"},"coverage":{"correctness":true,"security":true,"traceability":true,"maintainability":false},"ruledOut":["Security regression in path validation or canonical-source enforcement."],"focusTrack":"security","convergenceSignals":{"rollingAvg":0.38,"madScore":0.15,"dimensionCoverage":0.75,"compositeStop":0.11}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-037.md:12:- Treating F7 as a hidden fix for the `research_finding` versus `metadata_only` classification seam.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-011.md:7:- Sub-phase `002-manual-testing-playbook` is scoped to a 24-scenario package plus a distinct root operator guide, and the live root playbook still inventories that package as 8 routing scenarios, 7 graph-boost scenarios, 5 compiler scenarios, and 4 regression-safety scenarios. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/spec.md:30] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/spec.md:58] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/spec.md:71] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:176] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:193] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:209] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:223]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-011.md:9:- The packet's path-reference and root-guide checks are still grounded in the live playbook: the root guide uses `skill-advisor/scripts/*` paths in preconditions, release-readiness inputs, compiler tables, and regression tables, and it still points operators at the live `feature_catalog/feature_catalog.md` entrypoint. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:59] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:61] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:69] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:71] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:69] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:105] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:209] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:223] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:243]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-011.md:12:- CHK-020 / CHK-021 / CHK-022 / CHK-033 are reproducible from the current package structure: the root guide and scenario snippets point at `.opencode/skills/skill-advisor/scripts/skill_advisor.py`, `.opencode/skills/skill-advisor/scripts/skill_graph_compiler.py`, `.opencode/skills/skill-advisor/scripts/skill_advisor_regression.py`, and `.opencode/skills/skill-advisor/scripts/skill-graph.json`, matching the live parser surfaces exposed by the scripts themselves. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:59] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:60] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:61] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:70] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/01--routing-accuracy/001-git-routing.md:42] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/03--compiler/001-schema-validation.md:42] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/03--compiler/005-health-check.md:42] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/04--regression-safety/001-full-regression.md:42] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1762] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor_regression.py:183] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:468]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-011.md:13:- CHK-032's directory inventory is still accurate: the root guide enumerates the expected 8/7/5/4 category breakdown and the packet spec describes the same 24-scenario corpus. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/checklist.md:69] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/spec.md:60] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/002-manual-testing-playbook/spec.md:63] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:176] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:193] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:209] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md:223]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:8:{"type":"iteration","mode":"review","run":6,"status":"complete","focus":"D3 Traceability (deep pass) - sub-phase 001/003 packet alignment against shipped advisor/compiler artifacts","dimensions":["traceability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/001-research-findings-fixes/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/001-research-findings-fixes/checklist.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/001-research-findings-fixes/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/003-skill-advisor-packaging/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/003-skill-advisor-packaging/checklist.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/003-skill-advisor-packaging/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/003-skill-advisor-packaging/review/deep-review-findings.md",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/scripts/skill-graph.json",".opencode/skills/skill-advisor/graph-metadata.json"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":13,"findingsSummary":{"P0":3,"P1":8,"P2":2},"findingsNew":{"P0":0,"P1":3,"P2":0},"newFindingsRatio":0.28,"newInfoRatio":0.28,"timestamp":"2026-04-13T17:10:00Z","durationMs":780000,"findingRefs":["F050","F051","F052"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"The deep pass found new packet-local drift: sub-phase 001 still scopes all five P1 fixes as delivered and freezes a 20-skill verification snapshot, while sub-phase 003 still anchors provenance to a stale 007-era review artifact even though the packet now validates cleanly.","convergenceSignals":{"rollingAvg":0.39,"madScore":0.24,"dimensionCoverage":0.75,"compositeStop":0.18}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:10:{"type":"iteration","mode":"review","run":11,"status":"complete","focus":"D4 Maintainability (deep pass) - sub-phase 002 manual-testing-playbook completeness and command executability","dimensions":["maintainability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/002-manual-testing-playbook/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/002-manual-testing-playbook/checklist.md",".opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md",".opencode/skills/skill-advisor/manual_testing_playbook/01--routing-accuracy/001-git-routing.md",".opencode/skills/skill-advisor/manual_testing_playbook/01--routing-accuracy/008-semantic-search-routing.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/001-dependency-pullup.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/002-enhances-overlay.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/003-ghost-prevention.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/004-family-affinity.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/005-evidence-separation.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/006-hub-skill-edges.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/007-prerequisite-for.md",".opencode/skills/skill-advisor/manual_testing_playbook/03--compiler/001-schema-validation.md",".opencode/skills/skill-advisor/manual_testing_playbook/03--compiler/003-compiled-signals.md",".opencode/skills/skill-advisor/manual_testing_playbook/03--compiler/005-health-check.md",".opencode/skills/skill-advisor/manual_testing_playbook/04--regression-safety/001-full-regression.md",".opencode/skills/skill-advisor/manual_testing_playbook/04--regression-safety/003-graph-cases.md",".opencode/skills/skill-advisor/manual_testing_playbook/04--regression-safety/004-abstain-noise.md",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/scripts/skill_advisor_regression.py",".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/scripts/skill-graph.json"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":18,"findingsSummary":{"P0":4,"P1":12,"P2":2},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.0,"newInfoRatio":0.12,"timestamp":"2026-04-13T17:32:00Z","durationMs":1680000,"findingRefs":[],"ruledOut":["RS-003's inline JSON filter is executable as written and parses the regression harness JSON correctly.","GB-005 remains a valid behavioral check rather than a stale playbook command because it uses the live skill_advisor.py prompt plus --threshold interface.","No legacy manual_testing_playbook command surface was found in the sampled scenarios; the migrated scripts paths and flags are consistent with the live CLIs."],"crossReferenceChecks":{"spec_code":"fail","checklist_evidence":"fail","playbook_capability":"pass","feature_catalog_code":"pending"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"This D4 deep pass closed the playbook_capability overlay by executing representative routing, graph, compiler, and regression scenarios from sub-phase 002 against the live scripts layout. It found no new maintainability drift in the playbook itself and converted the remaining uncertainty into a documented pass rather than another finding.","convergenceSignals":{"rollingAvg":0.24,"madScore":0.12,"dimensionCoverage":1.0,"compositeStop":0.24}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:12:{"type":"iteration","mode":"review","run":13,"status":"complete","focus":"D2 Security (deep pass) - graph metadata integrity across the 21-file corpus","dimensions":["security"],"filesReviewed":[".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/graph-metadata.json",".opencode/skills/system-spec-kit/graph-metadata.json",".opencode/skills/sk-deep-review/graph-metadata.json",".opencode/skills/mcp-code-mode/graph-metadata.json",".opencode/skills/cli-copilot/graph-metadata.json",".opencode/skills/sk-git/graph-metadata.json",".opencode/skills/sk-code-review/graph-metadata.json",".opencode/skills/mcp-coco-index/graph-metadata.json",".opencode/skills/sk-code-full-stack/graph-metadata.json",".opencode/skills/sk-code-opencode/graph-metadata.json",".opencode/skills/sk-code-web/graph-metadata.json",".opencode/skills/sk-improve-agent/graph-metadata.json",".opencode/skills/sk-improve-prompt/graph-metadata.json"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":18,"findingsSummary":{"P0":4,"P1":12,"P2":2},"findingsNew":{"P0":0,"P1":2,"P2":0},"newFindingsRatio":0.18,"newInfoRatio":0.18,"timestamp":"2026-04-13T17:28:00Z","durationMs":510000,"findingRefs":["F080","F081"],"ruledOut":["A repo-wide 21-file sweep found no missing required fields, invalid targets, self-edges, sibling/prerequisite symmetry mismatches, or depends_on cycles.","Sampled CLI, MCP, system, review, code-quality, and utility metadata files remain structurally valid; the live integrity issue is localized to off-band weights."],"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"This D2 deep pass found actual shipped metadata drift, not just a theoretical validator gap: the current corpus contains off-band edge weights in skill-advisor and mcp-coco-index while the rest of the sampled metadata remains structurally sound.","convergenceSignals":{"rollingAvg":0.14,"madScore":0.09,"dimensionCoverage":1.0,"compositeStop":0.14}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:13:{"type":"iteration","mode":"review","run":10,"status":"complete","focus":"D3 Traceability - regression fixture accuracy and provenance for claimed expectation fixes","dimensions":["traceability"],"filesReviewed":[".opencode/skills/skill-advisor/scripts/fixtures/skill_advisor_regression_cases.jsonl",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/manual_testing_playbook/manual_testing_playbook.md",".opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/002-enhances-overlay.md",".opencode/skills/mcp-clickup/graph-metadata.json",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/001-research-findings-fixes/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/handover.md"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":19,"findingsSummary":{"P0":4,"P1":13,"P2":2},"findingsNew":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.05,"newInfoRatio":0.16,"timestamp":"2026-04-13T17:08:00Z","durationMs":1080000,"findingRefs":["F090"],"ruledOut":["P1-GRAPH-001/002/003 are not stale expectations; live analyzer runs and the canonical regression harness still satisfy those rows."],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"This pass verified that all three new graph-specific regression rows still match current routing behavior, then found a new provenance gap: the packet repeatedly says three older fixture expectations were fixed, but no retained file or fixture history identifies which cases changed or what the prior expectations were.","convergenceSignals":{"rollingAvg":0.13,"madScore":0.08,"dimensionCoverage":1.0,"compositeStop":0.13}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:18:{"type":"iteration","mode":"review","run":20,"status":"complete","focus":"Final stabilization - dedupe registry, recheck active P0s, and freeze synthesis-ready verdict","dimensions":["correctness","security","traceability","maintainability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/deep-review-state.jsonl",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/deep-review-strategy.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-001.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-002.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-003.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-004.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-005.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-006.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-007.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-008.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-009.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-010.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-011.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-012.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-013.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-014.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-015.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-016.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-017.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-018.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-019.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/checklist.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/tasks.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/handover.md",".opencode/skills/skill-advisor/graph-metadata.json",".opencode/skills/mcp-coco-index/graph-metadata.json",".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/scripts/skill-graph.json"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":23,"findingsSummary":{"P0":4,"P1":17,"P2":2},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.0,"newInfoRatio":0.05,"timestamp":"2026-04-13T17:14:58Z","durationMs":600000,"findingRefs":["F001","F010","F011","F020","F021","F022","F023","F030","F031","F040","F041","F050","F052","F060","F061","F080","F081","F090","F110","F130","F131","F150","F170"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail","feature_catalog_code":"fail","playbook_capability":"pass"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"Final stabilization found no new defects but rebuilt the canonical registry from all iteration files 001-019, merged F051 into F021, kept F001 active after iteration 019 re-confirmed it remains the only open ordering defect on the analyze-request pipeline, and confirmed that the four known P0 contradictions remain genuine after adversarial reread.","ruledOut":["F160-F163 are recheck aliases of F020/F021/F022/F060 and do not create new active registry rows.","F080 and F081 were re-observed without severity drift and each remain a single canonical finding.","No same-pass graph-compounding defect survived the iteration 019 recheck; F001 remains the only open ordering issue on that pipeline surface."],"convergenceSignals":{"rollingAvg":0.0,"madScore":0.0,"dimensionCoverage":1.0,"compositeStop":0.0},"releaseReadinessState":"release-blocking","verdictCandidate":"FAIL"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:20:{"type":"iteration","mode":"review","run":18,"status":"complete","focus":"D4 Maintainability - parent task-ledger accuracy vs packet-owned deferred/remediation work","dimensions":["maintainability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/tasks.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/001-research-findings-fixes/tasks.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/005-repo-wide-path-migration/tasks.md"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":23,"findingsSummary":{"P0":4,"P1":17,"P2":2},"findingsNew":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.09,"newInfoRatio":0.09,"timestamp":"2026-04-13T17:15:04Z","durationMs":360000,"findingRefs":["F170"],"ruledOut":["The parent tasks ledger does not contain an explicit deferred item without rationale; the defect is omission of later deferred/remediation lanes from the top-level tracker.","Deferred/remediation work is still documented in packet-local child task ledgers rather than disappearing entirely."],"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"This D4 pass found a new maintainability/documentation defect in the parent execution tracker: later packet-owned deferred/remediation work exists, but the top-level tasks ledger still presents the packet as fully complete with no forward pointer to those lanes.","convergenceSignals":{"rollingAvg":0.07,"madScore":0.05,"dimensionCoverage":1.0,"compositeStop":0.07}}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-state.jsonl:22:{"type":"iteration","mode":"review","run":20,"status":"complete","focus":"Final stabilization - dedupe registry, recheck active P0s, and freeze synthesis-ready verdict","dimensions":["correctness","security","traceability","maintainability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/deep-review-state.jsonl",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/deep-review-strategy.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-001.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-002.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-003.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-004.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-005.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-006.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-007.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-008.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-009.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-010.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-011.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-012.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-013.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-014.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-015.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-016.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-017.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-018.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/review/iterations/iteration-019.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/checklist.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/implementation-summary.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/tasks.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-skill-advisor-graph/handover.md",".opencode/skills/skill-advisor/graph-metadata.json",".opencode/skills/mcp-coco-index/graph-metadata.json",".opencode/skills/skill-advisor/scripts/skill_graph_compiler.py",".opencode/skills/skill-advisor/scripts/skill_advisor.py",".opencode/skills/skill-advisor/scripts/skill-graph.json"],"sessionId":"rvw-011-2026-04-13T16-50-00Z","parentSessionId":null,"lineageMode":"new","generation":1,"continuedFromRun":null,"findingsCount":23,"findingsSummary":{"P0":4,"P1":17,"P2":2},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.0,"newInfoRatio":0.05,"timestamp":"2026-04-13T17:14:58Z","durationMs":600000,"findingRefs":["F001","F010","F011","F020","F021","F022","F023","F030","F031","F040","F041","F050","F052","F060","F061","F080","F081","F090","F110","F130","F131","F150","F170"],"traceabilityChecks":{"spec_code":"fail","checklist_evidence":"fail","feature_catalog_code":"fail","playbook_capability":"pass"},"coverage":{"dimensionsCovered":["correctness","security","traceability","maintainability"],"dimensionsRemaining":[]},"noveltyJustification":"Final stabilization found no new defects but rebuilt the canonical registry from all iteration files 001-019, merged F051 into F021, kept F001 active after iteration 019 re-confirmed it remains the only open ordering defect on the analyze-request pipeline, and confirmed that the four known P0 contradictions remain genuine after adversarial reread.","ruledOut":["F160-F163 are recheck aliases of F020/F021/F022/F060 and do not create new active registry rows.","F080 and F081 were re-observed without severity drift and each remain a single canonical finding.","No same-pass graph-compounding defect survived the iteration 019 recheck; F001 remains the only open ordering issue on that pipeline surface."],"convergenceSignals":{"rollingAvg":0.0,"madScore":0.0,"dimensionCoverage":1.0,"compositeStop":0.0},"releaseReadinessState":"release-blocking","verdictCandidate":"FAIL"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:16:Review of 011-skill-advisor-graph spec folder: a Level 2 implementation that added structured graph metadata to all 20 skill folders, compiled into a lightweight skill-graph.json, and integrated graph-derived boosts into the skill_advisor.py routing pipeline. Includes 5 sub-phases (001-005) covering research fixes, testing playbook, packaging, enrichment, and path migration.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:51:| D2 Security | CONDITIONAL | 2, 13, 15 | Found one P1 trust-boundary gap in compiler path validation, one P2 resilience gap in advisor graph consumption, and a deep-pass live metadata drift where `skill-advisor` / `mcp-coco-index` ship 22 edges outside the packet's documented weight bands; the iteration 15 confidence-calibration recheck added no new finding and ruled out a graph-only threshold bypass. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:113:- The `skill-advisor` <-> `mcp-coco-index` dependency pair is serialized at `0.4`, below the packet's `0.7-1.0` hard-dependency band, so a documented foundational relationship is materially underweighted in the shipped graph.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:154:- 5 sub-phases completed (001-research-findings-fixes through 005-repo-wide-path-migration)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:163:- The live corpus currently contains 22 off-band edges accepted by validation: twenty `skill-advisor.enhances` edges at `0.8` plus the `skill-advisor` <-> `mcp-coco-index` dependency pair at `0.4`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:204:| `.opencode/skills/*/graph-metadata.json` (21 files on disk) | [D2, D3, D4] | 13 | 2 P0, 2 P1, 1 P2 (F020, F021, F031, F080, F081; deep-pass sweep localized live weight drift to `skill-advisor` + `mcp-coco-index`) | partial |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/deep-review-strategy.md:210:| `011-skill-advisor-graph/001-research-findings-fixes/` | [D3] | 10 | 3 P1 (F050, F051, F090) | partial |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/iterations/iteration-008.md:14:- A direct search for `findMemoryFiles` in `context-server.vitest.ts` produced no hits, so the maintainability drift in this pass is limited to the stale save-pipeline comment rather than an active dead-mock dependency.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/spec.md:68:- `.opencode/skills/system-spec-kit/mcp_server/README.md` — handler list update (new `detect_changes`, enriched query/blast_radius)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-013.md:10:4. Phase `002-fix-handover-drop-confusion` should therefore split the drop heuristic into two classes: hard wrapper evidence that still deserves the `0.92` floor, and soft operational commands that should either score much lower or defer to handover when strong stop-state cues (`current state`, `next session`, `resume`, `blocker`) are also present. That is the smallest change that matches the phase scope without touching downstream handover handling. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/002-fix-handover-drop-confusion/spec.md:10] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:369]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-013.md:22:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/002-fix-handover-drop-confusion/spec.md:10`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:29:1. `system-spec-kit` is under-modeled as a zero-edge hub even though its own docs describe downstream flows to `sk-code-opencode`, `sk-git`, and `sk-doc`, and it routes semantic queries to CocoIndex. Evidence: `.opencode/skills/system-spec-kit/graph-metadata.json:6-15`, `.opencode/skills/system-spec-kit/SKILL.md:775-777`, `.opencode/skills/system-spec-kit/SKILL.md:919-923`, `.opencode/skills/system-spec-kit/SKILL.md:943-951`. Provenance: iterations 001, 004, 006, and 007.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:30:2. `mcp-coco-index` is also a zero-edge orphan despite clear workflow coupling to semantic/concept code search. Evidence: `.opencode/skills/mcp-coco-index/graph-metadata.json:6-15`, `.opencode/skills/system-spec-kit/SKILL.md:775-777`. Provenance: iterations 005 and 007.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:36:8. `sk-deep-review <-> sk-deep-research` is structurally valid but semantically risky as a routing sibling because it leaks the wrong autonomous mode into review-only prompts. Evidence: `.opencode/skills/sk-deep-review/graph-metadata.json:7-18`. Provenance: iterations 007 and 008.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:54:6. Built-in CocoIndex search fails closed to `[]` on any subprocess problem, so semantic/graph interaction silently disappears in restricted environments. Primary edit surface: `.opencode/skills/skill-advisor/scripts/skill_advisor.py:1038-1065`. Provenance: iteration 005.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:61:3. Distinguish routing-only versus observability-only relationships. Some pairs, such as `sk-deep-review <-> sk-deep-research`, may belong in docs or diagnostics but not in runtime ranking. Provenance: iterations 007 and 008.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:62:4. Improve explainability and debuggability by surfacing graph provenance, semantic-search failure reasons, and possibly an explicit reverse view for prerequisite relationships. Provenance: iterations 005 and 007.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:76:     - `.opencode/skills/mcp-coco-index/graph-metadata.json:6-15`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:81:     - `mcp-coco-index -> system-spec-kit` as `enhances` or another workflow-facing edge type if introduced
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:107:3. Reclassify or de-route the `sk-deep-review <-> sk-deep-research` relationship.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:114:5. Make CocoIndex failure debuggable.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:115:   - Update `.opencode/skills/skill-advisor/scripts/skill_advisor.py:1038-1065` to emit a non-fatal diagnostic or trace reason when built-in semantic search fails.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:151:3. Important hub and utility skills are still graph-orphans or graph-invisible: `system-spec-kit`, `mcp-coco-index`, `sk-doc`, `sk-improve-prompt`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-010.md:160:4. CocoIndex failure diagnostics.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-017.md:21:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/004-normalize-legacy-files/spec.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-strategy.md:51:- A family-wide YAML search quickly isolated the remaining F007 drift to the `spec_kit_complete_*` pair instead of the deep-review/deep-research workflows. (iteration 4)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-strategy.md:71:- A runtime regression from the new helper comment was ruled out because the executable body still only returns early or swallows unsupported `DROP COLUMN` failures. (iteration 1, evidence: `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1538`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/deep-review-strategy.md:113:| `.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts` | [D1] | 1 | 0 P0, 0 P1, 0 P2 | partial |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/plan.md:24:9. `.opencode/skills/system-spec-kit/mcp_server/README.md` — add `detect_changes` to handler list; note enriched query/blast_radius/skill-advisor lanes/memory badges
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:2:  "specFolder": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph-pt-01/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:3:  "description": "Research iteration artifacts for 011-skill-advisor-graph.",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:5:    "research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:19:    "research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:26:    "source_spec_folder": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/description.json:27:    "new_spec_folder": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph-pt-01/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md:68:  - `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/external/LICENSE:17-22` — the actual license notice line names the upstream project owner.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md:76:- There is no root-level `external/` directory in the workspace. The external source tree still exists under `.opencode/specs/.../001-research-and-baseline/007-external-project/external/`, which appears to be legitimate research/source evidence rather than shipped runtime code.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:4:D3 Traceability - cross-check sub-phase `001-research-findings-fixes` and `003-skill-advisor-packaging` packet claims against the current `skill-advisor` scripts, compiled graph artifact, and packet-local evidence files.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:7:- 001's landed ghost-candidate and graph-evidence-separation fixes still match the shipped advisor code: graph boosts require pre-graph evidence, family affinity only boosts already-scored members, and confidence calibration still tracks `_graph_boost_count`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/spec.md:150] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:83] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:131] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1602]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:8:- 003's package-layout description is current: the shipped root still contains `README.md`, `SET-UP_GUIDE.md`, `feature_catalog/`, `manual_testing_playbook/`, `scripts/`, and `graph-metadata.json`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/spec.md:30] [SOURCE: .opencode/skills/skill-advisor:1-6]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:12:- 001 CHK-023 / CHK-040 still line up with the live compiler: `--validate-only` passes and still emits the documented zero-edge warnings for `sk-deep-research` and `sk-git`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/checklist.md:69] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/checklist.md:87] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:521]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:19:- **F050**: `001-research-findings-fixes/spec.md` still scopes the phase as "Fix all 5 P1 issues," but the same packet's completion docs and the shipped advisor code show that three P1 items remain deferred. The spec therefore overstates what this sub-phase actually delivered. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/spec.md:113] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/implementation-summary.md:48] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/checklist.md:98] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1062] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1596]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:20:- **F051**: `001-research-findings-fixes/implementation-summary.md` freezes a verification snapshot with `skill_graph_skill_count: 20`, but `health_check()` reports the current compiled graph's `skill_count`, and the checked-in graph now declares `21`. That makes the packet's recorded verification evidence non-reproducible from the shipped artifact. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/001-research-findings-fixes/implementation-summary.md:71] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1660] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1676] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-006.md:21:- **F052**: `003-skill-advisor-packaging` still presents `review/deep-review-findings.md` as the packet's provenance source, but that file is a stale pre-remediation review artifact: it still records a CONDITIONAL verdict, cites `007-skill-advisor-graph/...` paths, and claims strict validation fails. That directly conflicts with the current 003 packet, which now reports validation/integrity PASS, so CHK-001 and the spec metadata point at the wrong evidence source. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/spec.md:50] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/checklist.md:42] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/review/deep-review-findings.md:10] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/review/deep-review-findings.md:27] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/review/deep-review-findings.md:81] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/003-skill-advisor-packaging/implementation-summary.md:81]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/review-report.md:57:| **F081** | Security | skill-advisor/mcp-coco-index `depends_on` pair at 0.4 (spec says 0.7-1.0) | Iter 009 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/review-report.md:101:- Fix off-band weights in skill-advisor and mcp-coco-index metadata (F080, F081)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json:3:  "packet_id": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph-pt-01/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json:4:  "spec_folder": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph-pt-01/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json:36:    "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph/iterations"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json:40:    "source_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/graph-metadata.json:41:    "new_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/011-skill-advisor-graph-pt-01/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-027.md:7:1. The packet preserves the earlier corpus counts but not the exact compact-variant generator. That means the old `132`-sample baseline is only partially reproducible from current artifacts. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/research/iterations/iteration-005.md:7] [INFERENCE: packet-local artifact inspection]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-027.md:9:3. The reconstructed compact errors are refusal-heavy rather than seam-heavy: `narrative_delivery -> refusal` (`4`), `research_finding -> refusal` (`3`), and `metadata_only -> refusal` (`3`) lead the list. [INFERENCE: packet-local reconstructed 132-sample replay over dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-027.md:20:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/research/iterations/iteration-005.md:7`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:7:- Section 3.3's boost constants and pipeline placement still match the implementation: enhances uses `0.3`, siblings `0.15`, depends_on `0.2`, family affinity `0.08`, and graph boosts run after phrase boosts but before explicit variant matching. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:143] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:100] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1512]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:8:- The health fields documented in the packet are present in the runtime health payload (`skill_graph_loaded`, `skill_graph_skill_count`). [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:40] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1660]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:14:- **F020**: The packet still documents per-skill metadata as `schema_version: 1` everywhere, but the shipped implementation has already moved at least one skill to schema version 2 and the compiler explicitly accepts both versions. That contradicts both the schema table and CHK-006, so the traceability packet no longer describes the real contract. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:101] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:43] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:33] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:94] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:2]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:15:- **F021**: The packet scope still says the graph covers 20 skill folders, but discovery compiles every folder under `.opencode/skills/` that contains `graph-metadata.json`, including the non-routable `skill-advisor` folder. `compile_graph()` then publishes `skill_count = len(all_metadata)`, so the checked-in graph advertises `skill_count: 21` while advisor health still reports only 20 real skills. That is a direct spec/code contradiction about what the compiled graph represents. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:31] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:157] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:49] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:449] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:3] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1662]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:16:- **F022**: The success criteria and downstream docs still claim the compiled graph is under 2KB / 1950 bytes, but the current generated artifact is materially larger. The compiler measures serialized byte size at write time, and the checked-in artifact now includes 21 skills, full `signals`, and a 10-item `hub_skills` list; this review's runtime check measured 4667 bytes. The packet therefore claims a success criterion that the shipped artifact no longer meets. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:178] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:56] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:38] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:535] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:19:- **F023**: The checklist and implementation summary both claim hub-skill evidence that no longer matches the algorithm or the artifact. `compute_hub_skills()` returns every skill whose inbound edge count is above the median, and the current graph publishes 10 hub skills; the packet still cites only `sk-code-review` and `sk-code-web`. That makes CHK-013 and the implementation summary's hub-skill evidence stale even though the compiler itself is behaving consistently with its current code. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:58] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:38] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:66] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:366] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-003.md:22:- The graph-boost math itself is not the traceability problem in this iteration; the documented constants and call-site order still line up with the code. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:145] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:100] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1512]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-038.md:11:5. Reusing the packet's heuristic scorecard with the updated evidence raises overall health to `91/100`: structure `100/100`, status/freshness `99/100`, `key_files` `82/100`, and entities `79/100`. This is better than the Wave 4 `89/100`, but the corpus is still not clean because unresolved `key_files` and saturated entity output remain material precision risks. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/iterations/iteration-034.md:8-11] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-038.md:21:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/iterations/iteration-034.md:8-11`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-038.md:30:- What worked and why: refining the scope-leak check to true spec-root-relative cross-folder paths separated real entity precision problems from benign `research/research.md` references.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-004.md:11:4. `intent_signals` can already auto-generate a meaningful exact subset of the phrase table. I found 21 exact phrase-skill matches where the hardcoded phrase string is already present verbatim in a skill’s `intent_signals`. The cleanest exact duplicates are: `code review`, `pr review`, `security review`, and `quality gate` for `sk-code-review` (`.opencode/skills/sk-code-review/graph-metadata.json:19-20`); `deep research` and `research loop` for `sk-deep-research` (`.opencode/skills/sk-deep-research/graph-metadata.json:15-16`); `deep review`, `review loop`, `iterative review`, and `spec folder review` for `sk-deep-review` (`.opencode/skills/sk-deep-review/graph-metadata.json:17-18`); `semantic search`, `code search`, and `coco index` for `mcp-coco-index` (`.opencode/skills/mcp-coco-index/graph-metadata.json:13-14`); `improve agent` and `evaluate agent` for `sk-improve-agent`; and the exact CLI phrases `gemini cli`, `delegate to gemini`, `codex cli`, `delegate to codex`, `copilot cli`, and `delegate to copilot` from their respective metadata.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-004.md:13:5. A second tier of phrase entries is also derivable from `intent_signals`, but only with simple alias templates rather than exact string copy. I found roughly 29 phrase-skill pairs that are near matches to existing signals, such as `use claude code`, `claude code cli`, and `delegate to claude code` from the `claude code` / `delegate to claude` signal family; `find code that` and `semantic code search` from the `find code` / `code search` family; and `:review`, `/improve:agent`, `/improve:prompt`, `sk-code-review`, and similar explicit naming wrappers that are just templated variants of canonical intent or skill identity. This suggests the graph system does not need a 1:1 replacement phrase table; it needs compiled canonical signals plus a deterministic alias-expansion layer.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-004.md:15:6. `intent_signals` should be included in the compiled output. Right now a zero-edge skill such as `system-spec-kit` still carries valuable routing metadata in its source file (`spec folder`, `save context`, `save memory`, `spec kit`, `memory search`), but none of that survives compilation because the skill only contributes to `families`, not adjacency (`.opencode/skills/system-spec-kit/graph-metadata.json:13-14`, `.opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:249-267`). Including `intent_signals` in the compiled artifact would let the runtime use graph metadata as the canonical source for exact intent routing even when a skill has no edges.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/review-report.md:41:| F001 | **Closed** | Runtime still rejects retired `specs/**/memory/*.md` inputs at save/parser entry points, and the helper comment did not change behavior. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2080] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:955] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1538] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/review-report.md:45:| F005 | **Open** | Spec/checklist/helper align on every-startup idempotent retry, but the changelog still says SQLite 3.35+ installs shed the column on first launch. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:258] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v4/review-report.md:74:- **Vector-index helper comment**: no runtime behavior change was detected; the helper body still no-ops on already-clean schemas and swallows unsupported `DROP COLUMN` failures for older SQLite builds. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md:2:This iteration audited the remaining MCP and CLI skill `graph-metadata.json` files that were not covered in iteration 1, cross-checked each one against its `SKILL.md` frontmatter description, and re-tested the two open semantic questions from the prompt. The main result is that six of the seven files are structurally and semantically in reasonable shape as written: the three CLI orchestrators are fully consistent with the established `0.5` sibling pattern, and the `mcp-clickup` / `mcp-figma` / `mcp-chrome-devtools` dependencies on `mcp-code-mode` all match their documented Code Mode routing. The two substantive gaps are narrower: `mcp-chrome-devtools -> sk-code-web` looks directionally correct but probably a bit underweighted, and `mcp-coco-index` still looks like a semantically important orphan even though its zero-edge metadata is schema-valid.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md:15:6. `mcp-coco-index` is the remaining likely graph gap. Its zero-edge metadata is technically valid (`.opencode/skills/mcp-coco-index/graph-metadata.json:6-15`), but the skill description and surrounding workflow docs show that it is not actually isolated in use. Its frontmatter and activation section frame it as the default semantic search surface for unfamiliar-code exploration and concept-based code discovery (`.opencode/skills/mcp-coco-index/SKILL.md:2-4`, `.opencode/skills/mcp-coco-index/SKILL.md:20-41`), and `system-spec-kit` explicitly routes "semantic/concept queries" to CocoIndex (`.opencode/skills/system-spec-kit/SKILL.md:775-777`). That means "zero edges" is probably under-modeling a real workflow coupling. I would not call the exact target fully settled yet, but I do think this audit strengthens the case that `mcp-coco-index` should have at least one directional `enhances` relationship to a workflow skill that consumes semantic search. The cleanest current candidate among graph nodes is `system-spec-kit`, because that skill explicitly delegates semantic query routing to CocoIndex.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md:17:7. The three CLI skills' frontmatter descriptions do not reveal any hidden graph inconsistencies beyond the sibling mesh. `cli-codex` emphasizes code generation, code review, web research, architecture analysis, and parallel processing (`.opencode/skills/cli-codex/SKILL.md:2-5`, `.opencode/skills/cli-codex/SKILL.md:23-55`), `cli-copilot` emphasizes collaborative planning and cloud delegation (`.opencode/skills/cli-copilot/SKILL.md:2-5`, `.opencode/skills/cli-copilot/SKILL.md:23-52`), and `cli-gemini` emphasizes web research plus architecture analysis (`.opencode/skills/cli-gemini/SKILL.md:2-5`, `.opencode/skills/cli-gemini/SKILL.md:23-52`). Those capability differences show up appropriately in `domains` and `intent_signals`, but they do not justify changing the sibling weights. The current graph is treating them as same-family peers with different direct routing signals, which is consistent with both the metadata and the packet design.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md:21:2. If `mcp-coco-index` stops being a zero-edge skill, should its first edge be `enhances -> system-spec-kit`, or do we want to reserve `system-spec-kit` for broader workflow links and instead connect CocoIndex to a code-workflow skill such as `sk-code-full-stack` or `sk-code-web`?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-006.md:22:3. More generally, are "tooling utility" skills like `mcp-coco-index` intentionally allowed to remain graph orphans as long as their `intent_signals` are strong, or does the packet want the graph to model their repeated workflow companionship too?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:13:- A1 — HANDLED. `mergeTrustBadges` is implemented as a per-field overlay: explicit non-null `confidence` wins, explicit non-`never` age strings win, boolean fields fall through when `null`, and missing required booleans omit the whole badge (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:351`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:357`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:367`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:14:- A2 — HANDLED. For `{ confidence: null, extractionAge: 'never', orphan: null, ... }`, the merge uses derived values for confidence/ages/booleans when a derived badge exists; if no derived badge exists and booleans remain undefined, it returns `undefined` and omits the badge (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:357`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:360`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:363`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:367`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:15:- A3 — HANDLED. `{ confidence: 0.9 }` is accepted as a partial: normalization clamps only confidence, derives missing age labels to `never`, and leaves booleans as `null`; merge then uses `0.9` plus derived fields if available, or omits the badge if derived booleans are unavailable (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:301`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:304`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:309`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:357`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:16:- A4 — HANDLED. Derived `undefined` plus incomplete explicit data cannot ship a half-formed badge because `orphan === undefined || weightHistoryChanged === undefined` returns `undefined` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:367`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:20:- B1 — HANDLED. Exact regex: `/^(?:never|today|yesterday|\d{1,6}\s+(?:day|days|week|weeks|month|months)\s+ago)$/` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:276`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:21:- B2 — HANDLED by code inspection. The regex accepts `never`, `today`, `yesterday`, `1 day ago`, `1 days ago`, `1 week ago`, and `999999 months ago`; it rejects `xx`, `1day ago`, `tomorrow`, `1 yr ago`, and `\x07 days ago` because the grammar requires one of the listed tokens or 1-6 digits + whitespace + allowed unit + whitespace + `ago` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:276`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:22:- B3 — HANDLED. The 32-character cap is `MAX_AGE_LABEL_LENGTH = 32`, enforced before the regex test (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:277`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:282`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:23:- B4 — HANDLED. Rejected explicit age strings fall through to `formatAgeString` using `fallbackIso` when it is a string, otherwise `null`; raw rejected strings are not surfaced (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:285`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:288`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:26:- C1 — HANDLED. `fetchTrustBadgeSnapshots(results, dbGetter)` includes an optional `dbGetter` parameter (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:402`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:404`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:27:- C2 — HANDLED. The default is `dbGetter: () => ReturnType<typeof requireDb> = requireDb` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:404`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:28:- C3 — HANDLED. `rg` found production usage only at `formatSearchResults`, which calls `fetchTrustBadgeSnapshots(results)` without a custom getter; only `tests/memory/trust-badges.test.ts` passes `testDbGetter`, so the seam is genuinely test-only today (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:751`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:115`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:150`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:29:- C4 — HANDLED. The bind-type fix exists as `const boundIds = resultIds.map((id) => String(id));`, with the SQL call using `.all(...boundIds)` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:451`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:455`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:492`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:36:- D4 — HANDLED. `CacheArgsInput` accepts `causalEdgesGeneration`, and `buildCacheArgs` includes it only when `enableCausalBoost === true` and the value is finite (`.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:58`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:66`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:181`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:213`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:37:- D5 — HANDLED. `memory-search.ts` reads the generation only for causal boost and threads it into `buildCacheArgs` (`.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:847`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:852`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:887`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:38:- D6 — HANDLED. When `enableCausalBoost` is false, `causalEdgesGenerationForCache` is `undefined`, and `buildCacheArgs` also gates inclusion on `enableCausalBoost === true`; non-causal callers avoid needless invalidation (`.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:852`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:181`, `.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:213`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:39:- D7 — HANDLED with a boundary caveat. In the single-process synchronous mutation path, successful mutations bump before returning from their mutator, so later causal searches read the new generation. A request that already read generation N can still race with a mutation before its async pipeline completes, but any cache entry written under N is abandoned by future N+1 cache keys; this is possible current-response staleness, not persistent cross-generation cache poisoning (`.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:852`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:949`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1199`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:42:- E1 — HANDLED. `TrustBadgeFetchResult` shape is `{ snapshots, attempted, derivedCount, failureReason }` via readonly fields: `snapshots: Map<number, TrustBadgeSnapshot>`, `attempted: boolean`, `derivedCount: number`, and `failureReason: 'no_db' | 'no_results' | 'query_error' | null` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:380`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:388`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:43:- E2 — HANDLED. Branches set `failureReason: null` for no numeric IDs, `'no_db'` when `dbGetter` throws, `'no_results'` when a query returns no snapshots, `null` when derived snapshots exist, and `'query_error'` when the query throws (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:410`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:427`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:511`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:518`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:44:- E3 — HANDLED. `MemoryResultTrace.trustBadgeDerivation` is declared with `attempted`, `derivedCount`, and structured `failureReason`, then stamped onto traces when `includeTrace` is true (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:168`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:814`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:45:- E4 — HANDLED. Callers are consistent with the harmonized return shape: production uses `trustBadgeFetch.snapshots.get(resultId)`, and tests use `fetchResult.snapshots.get(...)`; no remaining bare `fetchTrustBadgeSnapshots(...).get(...)` or `snapshots.get(...)` mismatch was found by `rg` (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:786`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:119`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:154`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:48:- F16 (P2, test-add, RQ5): R-007-11 lacks a regression test for partial explicit trust badges merging with derived fallback. Remediation: add a `formatSearchResults` or exported testable case where explicit `{ confidence: 0.9 }` overlays a derived badge and preserves derived age/booleans. Evidence: merge supports the behavior (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:357`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:364`), but tests cover only SQL derivation and full explicit pass-through (`.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:91`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:166`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:49:- F17 (P2, test-add / closure-integrity, RQ2/RQ5): If the 010/007/T-E closure claims three SQL-pipeline cases, the test evidence does not match; only two tests pass `testDbGetter` into `fetchTrustBadgeSnapshots`, while the third explicitly avoids DB dependence. Remediation: either correct the closure claim or add a third SQL-pipeline case, such as `query_error` or no-weight-history table fallback. Evidence: SQL cases at `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:115` and `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:150`; formatter-only comment at `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:167`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:50:- F18 (P2, test-add, RQ3/RQ5): R-007-P2-10 age allowlist is implemented, but the trust-badge suite has no explicit accepted/rejected boundary tests for malformed age labels and fallback derivation. Remediation: add table tests for `never`, `today`, `1 days ago`, `999999 months ago`, `tomorrow`, `1day ago`, `1 yr ago`, and control-character input with `extractedAt` fallback. Evidence: sanitizer exists (`.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:276`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:282`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:288`), but current trust-badge tests only exercise full valid labels (`.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:178`, `.opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:180`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md:59:- HANDLED: Cache generation is bumped by successful causal-edge mutators and exported for memory-search cache keys.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:8:- Harmful: they also create graph-only noise, especially via family and sibling propagation, including `mcp-coco-index` and `mcp-figma` on a DevTools query and `sk-deep-research` on a deep-review query.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:13:- `mcp-coco-index` still has zero declared edges (`.opencode/skills/mcp-coco-index/graph-metadata.json:1-15`) and currently enters unrelated MCP results mainly through family affinity rather than an explicit workflow relationship.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:116:    "skill": "mcp-coco-index",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:168:- Graph boosts appear in the reasons for `sk-code-web`, `mcp-code-mode`, `mcp-coco-index`, `mcp-figma`, `sk-code-review`, `sk-code-opencode`, and `sk-code-full-stack`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:172:- The biggest problem is family bleed. `mcp-coco-index` and `mcp-figma` rise mostly on `!graph:family(mcp)` even though the prompt never asks for semantic search or Figma. When family affinity is disabled, both drop below more honest low-signal candidates.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:212:    "skill": "sk-deep-research",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:264:- Graph boosts appear in the reasons for `sk-code-review`, `sk-deep-research`, and the lower `sk-code-*` results.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:266:- The sibling boost to `sk-deep-research` is harmful for this prompt. It is a mode-confusion false positive caused purely by the `sk-deep-review <-> sk-deep-research` sibling relation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:275:   - Evidence: `mcp-coco-index` and `mcp-figma` appear on the DevTools query mainly because of `!graph:family(mcp)`, and `sk-deep-research` appears on the deep-review query because of `!graph:sibling(sk-deep-review,0.5)`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:279:   - Evidence: `system-spec-kit`, `mcp-coco-index`, and `sk-doc` still declare no edges at all (`.opencode/skills/system-spec-kit/graph-metadata.json:1-15`, `.opencode/skills/mcp-coco-index/graph-metadata.json:1-15`, `.opencode/skills/sk-doc/graph-metadata.json:1-15`), and none of them appear in compiled adjacency (`.opencode/skills/skill-advisor/scripts/skill-graph.json:39-145`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:283:     - `mcp-coco-index -> sk-code-opencode` and `mcp-coco-index -> sk-code-web` as semantic-search workflow edges
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:292:   - Evidence: current routing can already explain `mcp-code-mode` on the DevTools query via compiled `depends_on` from `mcp-chrome-devtools` (`.opencode/skills/mcp-chrome-devtools/graph-metadata.json:6-18`, `.opencode/skills/skill-advisor/scripts/skill-graph.json:68-88`), so missing `prerequisite_for` output is not blocking this routing path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:305:1. Reconsider whether `sk-deep-review <-> sk-deep-research` should remain a plain sibling pair.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:310:   - Evidence: current live routing already ties `sk-code-web` with the primary tool route on the CSS-layout query, so this edge is not underpowered enough to justify immediate weight growth.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-008.md:321:3. For autonomous loop pairs like `sk-deep-review` and `sk-deep-research`, should the relationship remain in the graph but be excluded from runtime scoring, or is the better fix to reclassify the relation type entirely?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-013.md:9:- The "strong signal" detection logic is intentionally strict at both boundaries: seed members must exceed `1.0`, and the strongest family member must rise above `1.5` before any sibling boost is emitted. Exact `1.0` and exact `1.5` scores do not qualify, which matches both the feature catalog wording and the 011 packet's integration description. [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:142] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:147] [SOURCE: .opencode/skills/skill-advisor/feature_catalog/02--graph-system/05-family-affinity.md:18] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:146] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:149]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-013.md:10:- Family affinity still runs before explicit variant matching, so explicit named-skill hits do not fan out into sibling boosts. That ordering remains consistent with the 011 packet and with the GB-004 guard whose purpose is to prevent ghost siblings from surfacing on explicit CLI requests. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:149] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1512] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1518] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/004-family-affinity.md:14] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/004-family-affinity.md:28]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-013.md:20:- The "strong signal" gate is not accidentally widened by explicit-variant matching. Family affinity executes earlier in the pipeline, which is the same behavior the manual testing contract relies on to prevent ghost siblings. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:149] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1512] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1518] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/004-family-affinity.md:18]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-013.md:23:- Trying to turn the pre-explicit call order into a correctness defect ran into the packet's own design contract. If family affinity were moved later so explicit matches could drive sibling boosts, that would be a routing-policy change, not a mismatch between implementation and specification. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:149] [SOURCE: .opencode/skills/skill-advisor/manual_testing_playbook/02--graph-boosts/004-family-affinity.md:18]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-007.md:13:- **F060**: Phase 005 signs off REQ-004 / CHK-023 as if a scoped grep over the full `011-skill-advisor-graph/` root is clean, but `handover.md` inside that same root still contains legacy non-`scripts/` `skill-advisor` paths (`.opencode/skills/skill-advisor/skill_graph_compiler.py`, `.opencode/skills/skill-advisor/skill-graph.json`). I re-checked scope after spotting the handover file: the packet explicitly defines the broader `011-skill-advisor-graph/` tree as the grep target, so this is in scope and makes the recorded closeout evidence false. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/spec.md:115] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/checklist.md:67] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/implementation-summary.md:86] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:44] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:46] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:49] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:54]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-007.md:16:- **F061**: Phase 004's CHK-014 evidence overstates what the packet actually serializes. The checklist says packet `graph-metadata.json` lists live repo files such as `sk-deep-review/graph-metadata.json` and `skill_graph_compiler.py`, but the current `derived.key_files` list only contains packet docs plus a subset of other skill metadata files; neither cited evidence file appears there. The packet did remove the old glob, but its claimed packet-metadata evidence surface is still inaccurate. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/spec.md:79] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/checklist.md:57] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/graph-metadata.json:43] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/graph-metadata.json:63]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-007.md:20:- Phase 004 did succeed at replacing the old glob-based packet metadata pattern with concrete paths; the remaining issue is narrower than F020/F023 and is confined to the checklist's claimed examples for that metadata surface. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/spec.md:79] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/004-graph-metadata-enrichment/graph-metadata.json:43]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-007.md:23:- A broader repo search still finds retired `skill-advisor` path literals in archives and other scratch/history surfaces, but Phase 005's stated binary gate is narrower: the full `011-skill-advisor-graph/` root must be clean. That kept this iteration anchored to packet traceability instead of drifting into unrelated cleanup. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/spec.md:115]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-007.md:7:1. Category-to-merge mapping is fixed: `narrative_progress` and `narrative_delivery` use `append-as-paragraph`, `handover_state` and `research_finding` use `append-section`, `decision` uses `insert-new-adr` on `L3/L3+` and `update-in-place` on lower packet levels, `task_update` uses `update-in-place`, and `metadata_only` updates frontmatter continuity rather than anchor-merging. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:918] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:925]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/prompts/agent-brief.md:43:| `.opencode/skills/system-spec-kit/mcp_server/README.md` | **MODIFY** — handler list (add `detect_changes`); note enriched query/blast_radius outputs and new affordance lane wiring |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/iterations/iteration-003.md:9:- No new P0/P1/P2 findings. The only active runtime residue is `dropDeprecatedSharedSpaceColumn()`, which performs a best-effort schema cleanup and does not read or write shared-space scope at runtime; no live shared-memory lifecycle tools, `sharedSpaceId` request plumbing, or shared-memory docs surfaced in `mcp_server/`, `scripts/`, `shared/`, `templates/`, or `feature_catalog/`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1548]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json:3:  "packet_id": "system-spec-kit/026-graph-and-context-optimization/research/003-graph-metadata-validation-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json:4:  "spec_folder": "system-spec-kit/026-graph-and-context-optimization/research/003-graph-metadata-validation-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json:36:    "system-spec-kit/026-graph-and-context-optimization/research/010-search-and-routing-tuning-003-graph-metadata-validation/iterations"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json:40:    "source_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/010-search-and-routing-tuning-003-graph-metadata-validation/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/graph-metadata.json:41:    "new_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/003-graph-metadata-validation-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/findings-registry.json:10:    "Q8: CocoIndex interaction",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md:2:This iteration answered Q7 and Q8 by measuring the real size impact of compiling `domains` and `intent_signals` into `.opencode/skills/skill-advisor/scripts/skill-graph.json`, then tracing how CocoIndex semantic hits enter `skill_advisor.py` and interact with graph propagation. The main result is that the current `~2KB` target is only realistic for topology-only output. If the compiled artifact is expected to carry routing metadata as well, the practical target should move to roughly `3-4KB` with a compact indexed layout, because raw string-heavy inclusion lands closer to `5.2KB`. On the scoring side, semantic hits and graph boosts are complementary, but they are not independent: semantic evidence is blended first, then graph edges propagate that same evidence to related skills, which can legitimately help companion routing but can also double-count confidence.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md:9:3. The compiler currently validates `domains` and `intent_signals` but discards both during compilation, so the runtime graph cannot use the strongest packet-local routing metadata at all. This especially hurts zero-edge but high-value routing skills such as `mcp-coco-index`, `sk-doc`, `sk-git`, and `system-spec-kit`, because they contribute no adjacency yet still carry useful canonical signals in their source metadata. `system-spec-kit` is the clearest example: it has no compiled outbound or inbound edge presence, but its `graph-metadata.json` still contains routing-critical signals like `spec folder`, `save context`, `save memory`, `spec kit`, and `memory search` that never make it into `skill-graph.json` (`.opencode/skills/system-spec-kit/graph-metadata.json`, `.opencode/skills/skill-advisor/scripts/skill-graph.json:1`, `.opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:249-291`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md:13:5. The semantic-search pipeline and graph pipeline are intentionally stacked, not isolated. In `analyze_request()`, the advisor first adds the auto-semantic intent hint for `mcp-coco-index`, then blends CocoIndex hits via `_apply_semantic_boosts()`, then applies token and phrase boosters, and only after that applies `_apply_graph_boosts()` and `_apply_family_affinity()`. Explicit skill-name boosts happen later and therefore do not cascade through the graph. The practical effect is that semantic hits can seed related skills through graph propagation, but explicit naming cannot (`.opencode/skills/skill-advisor/scripts/skill_advisor.py:1128-1154`, `.opencode/skills/skill-advisor/scripts/skill_advisor.py:1465-1499`, `.opencode/skills/skill-advisor/scripts/skill_advisor.py:1500-1510`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md:19:8. There is also an operational failure mode in the CocoIndex interaction: built-in semantic search fails closed and effectively becomes invisible to the advisor. `_cocoindex_search_builtin()` returns an empty hit list on any non-zero `ccc` exit or subprocess error. In this sandbox, direct `ccc search` failed because the daemon wanted to write `~/.cocoindex_code/daemon.log`, which is outside the writable sandbox; in normal advisor execution that would collapse to `[]` with no routing-visible error. So part of the Q8 answer is that graph/semantic interaction can disappear entirely in restricted environments, not because the logic is wrong but because semantic retrieval is silently suppressed upstream (`.opencode/skills/skill-advisor/scripts/skill_advisor.py:1038-1056`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-005.md:28:3. Should `_cocoindex_search_builtin()` surface a diagnostic reason when semantic search fails, so graph/semantic interaction is debuggable instead of silently degrading to keyword-only routing?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-009.md:117:- `P1-REVIEW-003`: graph adds `sk-deep-research` under `sk-deep-review`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-033.md:8:2. The next risky pairs are `HS-01` versus `RF-05` (`0.7786`) and `NP-01` versus `ND-03` (`0.7590`), which means the refreshed corpus still clusters state-heavy blocker language near research findings and some implementation narratives near delivery mechanics. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:133] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:207] [INFERENCE: packet-local nearest-neighbor scan over routing-prototypes.json]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:14:- The compiler still accepts both schema versions 1 and 2, and the live `skill-advisor/graph-metadata.json` still ships `schema_version: 2`. That means the top-level packet's "Always 1" schema contract and CHK-006 remain false on a file the current compiler explicitly validates. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:101-106] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:43-48] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:33-35] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:94-99] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:1-3]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:15:- The compiled graph still publishes `skill_count: 21` because discovery counts every child folder under `.opencode/skills/` that contains `graph-metadata.json`, including `skill-advisor`. The strongest downgrade theory from earlier passes still holds only as impact-limiting counterevidence: runtime discovery loads `*/SKILL.md` records, so the extra node is inert for live routing. That narrows F021 to a packet/artifact contract failure rather than a fresh routing bug, but it does not make the packet's 20-skill claim true. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:123-139] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:157-164] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:49-71] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:446-455] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor_runtime.py:93-96] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor_runtime.py:171-183]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:16:- The packet still claims the compiled graph is 1950 bytes / under 2KB, while packet-local continuity already records that the target had to be relaxed to 4KB and that the graph was already 3957 bytes at handoff. The current artifact now measures 4667 bytes on disk, so there is no surviving interpretation under which the packet's completed size claims are still accurate. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:176-183] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:54-59] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:36-39] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:27-30] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:44-47] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:544-553]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:17:- Phase 005 still defines zero forbidden matches across the broader `011-skill-advisor-graph/` tree as a hard requirement, and its checklist and implementation summary still mark that grep as clean. `handover.md` sits inside that same tree and still contains legacy non-`scripts/` `skill-advisor` paths, so the closeout claim remains false on the current packet contents. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/spec.md:108-116] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/checklist.md:64-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/implementation-summary.md:81-87] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:44-46] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:54-55]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:22:- **F160 (recheck of F020)**: F020 remains a genuine P0, not a P1. The best downgrade argument was that schema v2 might be an additive side channel outside the top-level contract, but the packet explicitly says `schema_version` is "Always 1", CHK-006 marks that invariant complete, the compiler accepts both 1 and 2, and a live compiled input (`skill-advisor/graph-metadata.json`) still uses 2. That is still a false core schema claim inside the packet's own blocker-level verification surface. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:101-106] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:43-48] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:33-35] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:94-99] [SOURCE: .opencode/skills/skill-advisor/graph-metadata.json:1-3]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:23:- **F161 (recheck of F021)**: F021 remains a genuine P0, not a P1. Iteration 008 already ruled out the more severe theory that the 21st `skill-advisor` node leaks into live ranked output, but that only limits impact. The packet still promises 20 skill folders and a compiled graph sample with `skill_count: 20`, while the compiler still emits `len(all_metadata)` and the checked-in graph still says `21`. Because the compiled artifact itself is one of the feature's core deliverables, this mismatch remains a blocker-level contract failure even if the extra node is currently inert for routing. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:123-139] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:157-164] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:49-71] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:446-455] [SOURCE: .opencode/skills/skill-advisor/scripts/skill-graph.json:1] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor_runtime.py:93-96] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor_runtime.py:171-183]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:24:- **F162 (recheck of F022)**: F022 remains a genuine P0, not a P1. The best downgrade path would be "the 2KB number was an aspirational draft target," but the packet promotes it to a checked success criterion in both `spec.md` and `checklist.md`, and `implementation-summary.md` repeats the 1950-byte result as completed work. Packet-local continuity already admits the target had been relaxed to 4KB and the graph had grown to 3957 bytes, while the current artifact now measures 4667 bytes. That leaves no credible basis for treating the size miss as a minor advisory. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/spec.md:176-183] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/checklist.md:54-59] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:36-39] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:27-30] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:44-47] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_graph_compiler.py:544-553]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-017.md:25:- **F163 (recheck of F060)**: F060 remains a genuine P0, not a P1. The strongest downgrade theory was that `handover.md` might sit outside the Phase 005 grep scope or outside the closeout artifact set, but REQ-004 and SC-002 explicitly scope the broader `011-skill-advisor-graph/` tree, not just the Phase 005 subfolder. Since the checklist and implementation summary still mark the root-wide grep clean while `handover.md` inside that root still carries forbidden legacy path literals, the packet-defined hard blocker is still unmet. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/spec.md:108-116] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/spec.md:130-135] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/checklist.md:64-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/005-repo-wide-path-migration/implementation-summary.md:81-87] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:44-46] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-search-routing-advisor/001-skill-graph-metadata-routing-boosts/handover.md:54-55]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-002.md:109:Iter 003 should focus on 010/003 reason/step round-trip and blast_radius enrichment per strategy.md, with special attention to whether enriched fields survive persistence, query, and response formatting without silent fallback loss.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-003.md:19:4. There is no orphan-skill or no-edge validation. Four of the 20 scanned skill metadata files currently declare zero edges at all: `mcp-coco-index`, `sk-doc`, `sk-git`, and `system-spec-kit`. The compiler does not report that condition anywhere, even though the packet is trying to model skill relationships explicitly.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:2:{"type":"iteration","run":1,"status":"insight","focus":"Q1+Q6: edge inventory accuracy and missing edges","findingsCount":5,"newInfoRatio":0.78,"timestamp":"2026-04-13T14:35:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:3:{"type":"iteration","run":2,"status":"insight","focus":"Q2+Q3: damping factors and snapshot pattern","findingsCount":6,"newInfoRatio":0.65,"timestamp":"2026-04-13T14:42:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:4:{"type":"iteration","run":3,"status":"insight","focus":"Q4+Q9: compiler robustness and weight consistency","findingsCount":5,"newInfoRatio":0.60,"timestamp":"2026-04-13T14:42:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:5:{"type":"iteration","run":4,"status":"insight","focus":"Q5+Q10: graph vs boosters and ROI improvements","findingsCount":7,"newInfoRatio":0.55,"timestamp":"2026-04-13T14:42:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:6:{"type":"iteration","run":5,"status":"insight","focus":"Q7+Q8: size target and CocoIndex interaction","findingsCount":6,"newInfoRatio":0.50,"timestamp":"2026-04-13T14:52:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:7:{"type":"iteration","run":6,"status":"insight","focus":"MCP and CLI skill audit","findingsCount":5,"newInfoRatio":0.35,"timestamp":"2026-04-13T14:52:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:8:{"type":"iteration","run":7,"status":"insight","focus":"sk-util and sk-code family audit","findingsCount":4,"newInfoRatio":0.30,"timestamp":"2026-04-13T14:52:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:9:{"type":"iteration","run":8,"status":"insight","focus":"Validate findings with live queries + prioritized improvements","findingsCount":8,"newInfoRatio":0.25,"timestamp":"2026-04-13T15:02:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:10:{"type":"iteration","run":9,"status":"insight","focus":"Regression risk analysis","findingsCount":4,"newInfoRatio":0.15,"timestamp":"2026-04-13T15:02:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-state.jsonl:11:{"type":"iteration","run":10,"status":"insight","focus":"Final synthesis","findingsCount":0,"newInfoRatio":0.05,"timestamp":"2026-04-13T15:02:00.000Z","sessionId":"sgraph-research-001","generation":1}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/iterations/iteration-007.md:11:- **NF002 - Active command docs and review/research workflows still advertise retired memory/shared surfaces.** `memory/README.txt` still tells operators to check `specs/**/memory/` and use `/memory:manage shared member`, `memory/learn.md`, `memory/save.md`, and `memory/search.md` still list `/memory:manage shared`, `memory/manage.md` still claims a four-source pipeline that includes legacy spec memory artifacts, and the deep-review/deep-research auto+confirm YAMLs still verify save success by checking `{spec_folder}/memory/*.md`. These are active operator-facing assets that no longer match the canonical continuity contract. [SOURCE: .opencode/commands/memory/README.txt:318-323] [SOURCE: .opencode/commands/memory/learn.md:501-505] [SOURCE: .opencode/commands/memory/save.md:536-541] [SOURCE: .opencode/commands/memory/search.md:768-772] [SOURCE: .opencode/commands/memory/manage.md:264-271] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:863-871] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml:995-1003] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:644-652] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:822-830]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-018.md:9:3. Several categories also lack adversarial tests entirely. `decision`, `research_finding`, `metadata_only`, and `task_update` each have direct positive-path tests but no negative or ambiguity tests that prove they beat close neighbors. That matters because earlier iterations already found spillover between progress and research, and between research and metadata. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/content-router.vitest.ts:76] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/content-router.vitest.ts:122] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/content-router.vitest.ts:167]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-018.md:35:Translate the research into concrete implementation guidance for phases `001`, `002`, and `003`, with exact code locations and test additions.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-028.md:30:- What I would do differently: capture the “planned with complete checklist” bucket as a first-class dashboard signal instead of deriving it ad hoc in research.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/review/review_archive/gen1-2026-04-13/iterations/iteration-012.md:7:- `health_check()` still emits the graph-status fields `skill_graph_loaded`, `skill_graph_skill_count`, and `skill_graph_path`, and the CLI prints that payload after CocoIndex enrichment. [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1660] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1675] [SOURCE: .opencode/skills/skill-advisor/scripts/skill_advisor.py:1790]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:2:title: "...sor/001-memory-search-routing-tuning/002-content-routing-accuracy/research/002-content-routing-accuracy-research/research]"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:3:description: "This packet stayed read-only and only updated research/ artifacts. Iterations 1-25 established the pre-implementation baseline and produced the three remediation phases plus the..."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:7:  - "search"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:10:  - "research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:13:contextType: "research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:16:    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/002-content-routing-accuracy/research/002-content-routing-accuracy-research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:21:    key_files: ["research.md"]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:23:# Research Synthesis: Content Routing Accuracy After Implementation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:27:This packet stayed read-only and only updated `research/` artifacts. Iterations 1-25 established the pre-implementation baseline and produced the three remediation phases plus the doc-alignment follow-on. Iterations 26-35 reran the benchmark against shipped behavior, traced the always-on Tier 3 path end to end, checked the canonical docs against code, and measured prototype separation after the refresh. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:384] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:951] [SOURCE: .opencode/commands/memory/save.md:76]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:31:- The earlier compact-variant generator was not preserved as a packet artifact, so any all-in `132`-sample replay is diagnostic rather than strictly baseline-comparable. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/research/iterations/iteration-005.md:7] [INFERENCE: packet-local artifact inspection]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:38:- The prior baseline recorded in iteration 5 was `87.88%` on the earlier `132`-sample corpus. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/research/iterations/iteration-005.md:7]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:41:  - `narrative_progress -> research_finding` for `NP-02` and `NP-04`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:42:  - `research_finding -> metadata_only` for `RF-03`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:48:- Those misses are concentrated in compact-only refusals for delivery, research, metadata, and terse drop telemetry.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:61:  - research roots: `PACKET_KIND: research`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:91:- `decision <-> research_finding` also remains close at `0.8797`, which fits the residual overlap around source-of-truth, investigation, and metadata-heavy prose. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:1] [INFERENCE: packet-local lexical-vector centroid analysis over routing-prototypes.json]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:102:- `narrative_progress -> research_finding` when implementation text is heavy on spec-doc and source-of-truth nouns (`NP-02`, `NP-04`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:103:- `research_finding -> metadata_only` when a finding discusses continuity, preflight, postflight, and metadata fields (`RF-03`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:108:2. Distinguish `research_finding` from `metadata_only` more explicitly when `_memory.continuity`, `preflight`, or `postflight` vocabulary appears inside analytical prose rather than field-heavy payloads. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:409] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:417]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:109:3. Add one more guard so spec-doc nouns alone do not push progress narratives into `research_finding`. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:390] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:409]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:118:- No new router edge case surfaced in the final focused sweep. The remaining mechanics are unchanged: two progress chunks still get accepted early as research, one research chunk still gets accepted early as metadata, and one terse telemetry fragment still refuses below the `drop` floor. [INFERENCE: packet-local edge-case replay over dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:119:- Active save docs stay clean. The only checked live-surface `SPECKIT_TIER3_ROUTING` mentions are the feature-catalog rows that explicitly describe the flag as removed. [SOURCE: .opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/01-1-search-pipeline-features-speckit.md:130] [SOURCE: .opencode/skills/system-spec-kit/feature_catalog/feature_catalog.md:4480] [INFERENCE: targeted `rg` sweep across active save surfaces]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:128:4. The remaining accuracy work is optional and much narrower: short-fragment robustness around progress versus research, research versus metadata, and terse drop telemetry.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/research.md:130:If the team wants another pass, it should be a small follow-on refinement wave aimed at those short-fragment cases. If not, this packet can stop here; the main research question stayed answered after the fix verification.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-config.json:15:    "sessionId": "sgraph-research-001",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-config.json:29:    "registryFile": "research/findings-registry.json",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-config.json:30:    "dashboardFile": "research/deep-research-dashboard.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/deep-research-config.json:31:    "strategyFile": "research/deep-research-strategy.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/research/iterations/iteration-001.md:9:5. `sk-deep-review` is mostly accurate on its explicit review-loop ties, but it still lacks a graph connection to the spec-validation system it routinely works alongside. The metadata correctly records `depends_on -> sk-code-review` and `siblings -> sk-deep-research` (`.opencode/skills/sk-deep-review/graph-metadata.json:7-13`). However, its intent signals include `spec folder review` (`.opencode/skills/sk-deep-review/graph-metadata.json:17-18`), while `system-spec-kit` owns spec-folder/validation/context routing (`.opencode/skills/system-spec-kit/SKILL.md:3`, `.opencode/skills/skill-advisor/scripts/skill_advisor.py:919-927`). That coupling is visible in routing behavior but absent from the graph.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/review/review-brief.md:29:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/review/review-brief.md:30:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-023.md:8:2. The missing work is larger than a classifier call because there is no concrete production `RouterCache` implementation anywhere in `mcp_server/` outside the interface and tests. Phase `003` therefore needs both a classifier adapter and a cache adapter. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:231] [INFERENCE: repo-wide search found `RouterCache` only in `content-router.ts` and test doubles]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-023.md:9:3. The smallest realistic production diff is about `90-130` LOC. A thin OpenAI-compatible call helper modeled on `callLlmForReformulation()` is roughly `45-60` LOC, a small session/spec-folder cache wrapper is another `20-30` LOC, env/response plumbing is about `10-20` LOC, and the actual injection at `memory-save.ts:1008` is only `8-15` LOC. If the phase also introduces routing-specific env names instead of reusing an existing OpenAI-compatible endpoint contract, the diff moves toward the high end of that range. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:200] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1008] [INFERENCE: line-count estimate based on the existing helper shape and the missing seams]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-023.md:11:5. There is also a config-contract choice to make. The only existing OpenAI-compatible env pattern in this codebase is `LLM_REFORMULATION_ENDPOINT`, `LLM_REFORMULATION_API_KEY`, and `LLM_REFORMULATION_MODEL`; there is no routing-specific env surface yet. Reusing that pattern keeps the implementation small, while adding `ROUTING_TIER3_*` style envs improves clarity but adds more code and tests. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:185] [INFERENCE: repo-wide search found no routing-specific endpoint env contract]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-023.md:21:- `.opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:200`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:10:  "specFolder": ".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/002-content-routing-accuracy",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:29:    "registryFile": "research/findings-registry.json",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:30:    "dashboardFile": "research/deep-research-dashboard.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:31:    "strategyFile": "research/deep-research-strategy.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:42:  "capabilityMatrixPath": ".opencode/skills/sk-deep-research/assets/runtime_capabilities.json",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:43:  "capabilityMatrixDocPath": ".opencode/skills/sk-deep-research/references/capability_matrix.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:44:  "runtimeCapabilityResolver": ".opencode/skills/sk-deep-research/scripts/runtime-capabilities.cjs",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:45:  "reducerScriptPath": ".opencode/skills/sk-deep-research/scripts/reduce-state.cjs",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:46:  "pauseSentinelPath": "research/.deep-research-pause",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:47:  "archiveRoot": "research/archive",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:50:    "deep-research-config.json": "immutable",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:51:    "deep-research-state.jsonl": "append-only",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:52:    "deep-research-strategy.md": "mutable",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:53:    "deep-research-dashboard.md": "auto-generated",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-config.json:56:    "research/research.md": "mutable"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-019.md:9:3. Phase `003-wire-tier3-llm-classifier` should add a real classifier adapter and then inject it. The missing constructor seam is `memory-save.ts` line `1008`; the existing call graph is already ready to receive `classifyWithTier3` and `cache`. Reuse the fail-open, timeout-bounded `fetch()` pattern from `lib/search/llm-reformulation.ts`, but build the request from `buildTier3Prompt()` and return validated `Tier3RawResponse` objects. Then add handler coverage for natural routing without `routeAs`, plus router coverage for cache hits, timeouts, and unavailable-provider fallbacks in the live save path. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1008] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:1128] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/llm-reformulation.ts:203]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-019.md:10:4. Test work should follow the same phase boundaries. `content-router.vitest.ts` needs explicit regression samples for delivery-plus-implementation language, handover-plus-command language, and metadata-versus-research ambiguity. `handler-memory-save.vitest.ts` needs at least one naturally ambiguous atomic-save fixture that reaches Tier3 and proves safe fallback when the classifier returns `null` or times out. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/content-router.vitest.ts:65] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1076]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-029.md:9:3. Research-root packets derive `PACKET_KIND: research` from spec frontmatter rather than pure path shape, which confirms the metadata-first packet-kind logic is live. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1294] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:870]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json:3:  "packet_id": "system-spec-kit/026-graph-and-context-optimization/research/002-content-routing-accuracy-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json:4:  "spec_folder": "system-spec-kit/026-graph-and-context-optimization/research/002-content-routing-accuracy-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json:36:    "system-spec-kit/026-graph-and-context-optimization/research/010-search-and-routing-tuning-002-content-routing-accuracy/iterations"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json:40:    "source_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/010-search-and-routing-tuning-002-content-routing-accuracy/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/graph-metadata.json:41:    "new_packet_id": "system-spec-kit/026-graph-and-context-optimization/research/002-content-routing-accuracy-research/iterations",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:2:title: "...or/001-memory-search-routing-tuning/003-graph-metadata-validation/research/003-graph-metadata-validation-research/research]"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:3:description: "This research loop scanned every graph-metadata.json file under .opencode/specs/ excluding z_archive and node_modules, read the runtime schema/parser/backfill code, and cross-ch..."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:6:  - "search"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:10:  - "research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:13:contextType: "research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:16:    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/003-graph-metadata-validation/research/003-graph-metadata-validation-research"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:21:    key_files: ["research.md"]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:23:# Research: Graph Metadata Quality and Relationship Validation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:26:This research loop scanned every `graph-metadata.json` file under `.opencode/specs/` excluding `z_archive` and `node_modules`, read the runtime schema/parser/backfill code, and cross-checked representative packet docs. The investigation stayed read-only outside this packet's `research/` folder.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:33:## Research Answers
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/research.md:86:Entity quality is downstream of key-file quality, and both are currently too noisy for high-confidence graph/search enrichment.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/checklist.md:23:- [x] No broken links in any updated doc — VALIDATED PASS via `ls`: all 8 source-file references in updated docs resolve (`mcp_server/code_graph/handlers/detect-changes.ts`, `handlers/index.ts`, `code_graph/lib/diff-parser.ts`, `code_graph/lib/phase-runner.ts`, `code_graph/lib/structural-indexer.ts`, `skill_advisor/lib/affordance-normalizer.ts`, `formatters/search-results.ts`, `lib/response/profile-formatters.ts`); all 10 new per-packet entry relative paths in feature_catalog and manual_testing_playbook indexes resolve via `ls` (5 catalog + 5 playbook); anchor balance preserved per modified file via `grep -c "ANCHOR:"`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/checklist.md:29:- [x] merged-phase-map.md updated with 012 entry [See `026/merged-phase-map.md` new "Derived Implementation Phases" section after "Active Phase Themes" — 012 row records derivation from `001-research-and-baseline/007-external-project/` pt-01 + pt-02 syntheses with owner wrapper `026-graph-and-context-optimization/`, plus a one-paragraph note describing the six sub-phase decomposition]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-038.md:7:1. The active operator-facing save docs remain clean. The only checked live-surface mentions of `SPECKIT_TIER3_ROUTING` are the feature-catalog rows that explicitly mark the flag removed; the command, skill, and save-workflow docs no longer reintroduce stale opt-in wording. [SOURCE: .opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/01-1-search-pipeline-features-speckit.md:130] [SOURCE: .opencode/skills/system-spec-kit/feature_catalog/feature_catalog.md:4480] [INFERENCE: targeted `rg` sweep across active save surfaces]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-038.md:8:2. The focused edge-case sweep reproduces the same mechanics as before, with no additions: `NP-02` and `NP-04` still accept Tier1 research cues before Tier2 can correct them, `RF-03` still accepts Tier1 metadata cues, and `DR-05-s1` still falls below the refusal floor even though its nearest Tier2 neighbors are both `drop`. [INFERENCE: packet-local edge-case replay over dist/lib/routing/content-router.js]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-038.md:9:3. This is the third consecutive post-fix iteration with `newInfoRatio < 0.10` and no fresh router finding. Early convergence is justified, and no further research iterations are warranted unless the team chooses to open the optional short-fragment refinement wave. [INFERENCE: synthesis across iterations 36-38]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-038.md:18:- `.opencode/skills/system-spec-kit/feature_catalog/19--feature-flag-reference/01-1-search-pipeline-features-speckit.md:130`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-017.md:9:3. Some categories are much better anchored. `metadata_only` and `drop` have distinctive field-heavy or wrapper-heavy vocabularies, while `decision` and `research_finding` stay relatively coherent around rationale and evidence language. That supports the earlier observation that the main problem is not global corpus quality but two narrow semantic seams. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:131] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:165]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-017.md:10:4. The best near-term prototype work is surgical, not wholesale: refresh 2-3 delivery examples and 1-2 handover examples to emphasize category-specific nouns, then leave the rest of the library stable so the before/after benchmark stays attributable. This aligns with phases `001` and `002` and avoids turning the routing benchmark into a full corpus rewrite. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/001-fix-delivery-progress-confusion/spec.md:10] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/002-fix-handover-drop-confusion/spec.md:10]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-017.md:22:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/001-fix-delivery-progress-confusion/spec.md:10`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:2:title: Deep Research Dashboard
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:3:description: Auto-generated reducer view over the research packet.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:6:# Deep Research Dashboard - Session Overview
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:13:Reducer-generated observability surface for the active research packet.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:160:- Continuing the research loop instead of handing the packet back to implementation. (iteration 25)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:161:- Expecting another research pass to change the phase order or revive threshold tuning as the primary fix. (iteration 25)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:171:- Treating the packet as still documentation-drifted just because earlier research was written before implementation landed. (iteration 30)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:180:- Continuing the research loop again before deciding whether short-fragment robustness is worth another targeted code pass. (iteration 35)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:185:- Treating F7 as a hidden fix for the `research_finding` versus `metadata_only` classification seam. (iteration 37)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/deep-research-dashboard.md:197:- None active beyond normal research uncertainty.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/002-content-routing-accuracy-research/iterations/iteration-008.md:7:1. `spec-doc-structure.ts` enforces a shape contract: `append-as-paragraph` only on prose or section anchors, `insert-new-adr` only on ADR anchors, `append-table-row` only on table anchors, `update-in-place` only on checklist anchors, and `append-section` only on section-like anchors or research docs. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/validation/spec-doc-structure.ts:627] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/validation/spec-doc-structure.ts:688]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-018.md:21:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/spec.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-018.md:31:- What did not work and why: broad repo searches for “12 trigger” produced too much documentation noise before I narrowed back to the parser.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:19:- B2: HANDLED with drift. The DB row mapper calls the exported sanitizer at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:795` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:799`; `query.ts` sanitizes in `edgeMetadataOutput` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:653` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:654`; `code-graph-context.ts` sanitizes in `formatContextEdge` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts:316` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts:317`. Drift: query/context duplicate local sanitizer logic instead of importing the exported function.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:21:- B4: GAP. Malformed `code_edges.metadata` JSON is parsed directly in `rowToEdge` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:788` with no catch around that mapper; relationship query paths call `rowToEdge` from `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:545` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:568`. A separate confidence-only parser catches JSON failures at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:819` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:822`, but that does not protect `rowToEdge`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:25:- C1: HANDLED. `depthGroups` is produced by `buildDepthGroups` as `Record<number, BlastRadiusAffectedFile[]>` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:865`, initializes depths `1..maxDepth` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:870`, groups affected files by `affectedFile.depth` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:873`, returned from `computeBlastRadius` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:986`, and exported in the final payload at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1298`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:26:- C2: HANDLED with boundary doc drift. Code derives `riskLevel` from depth-one fanout and ambiguity: high when ambiguity exists or depth-one count > 10 at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:884`, medium when depth-one count >= 4 at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:888`, low otherwise at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:891`, then exports it at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1299`. The 010/003 brief documents medium as `[4,9]` at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:66`, leaving depth-one count `10` under-specified while code classifies it as medium.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:27:- C3: HANDLED. The handler clamps request `minConfidence` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1131`, passes it to computation at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1248`, returns it from `computeBlastRadius` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:997`, and echoes it in the response at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1300`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:28:- C4: HANDLED. `ambiguityCandidates` starts empty at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1130`, is populated when fq_name or name matching has multiple candidates at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1135` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1141`, returns an ambiguity fallback at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`, and remains `[]` on unambiguous fallback paths at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1173` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1234`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:29:- C5: HANDLED. The original 010/003 documented `failureFallback?: { reason, partialResult? }` at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:84`; current code emits `reason`, optional `code`, and `partialResult` containing `sourceFiles`, `nodes`, `affectedFiles`, and `depthGroups` per the interface at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:147` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:157`, built by `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:894`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:32:- D1: HANDLED. `limit_reached` is set at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1007`, `unresolved_subject` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1176`, `ambiguous_subject` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1210`, `empty_source` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1237`, and `compute_error` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1280`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:33:- D2: HANDLED. All five codes are set at distinct sites: overflow inside `computeBlastRadius` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1003`, unresolved sibling/subject in the raw-subject loop at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1147`, ambiguity after the loop at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`, empty source at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1219`, and compute exception catch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1247`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:34:- D3: HANDLED. `BlastRadiusFailureCode` is a closed TypeScript literal union at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:170`, listing exactly the five documented values through `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:175`; the fallback interface uses that type at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:156`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:35:- D4: HANDLED. The `compute_error` branch warns at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1255` and increments `spec_kit.graph.blast_radius_failure_total` with `{ code: 'compute_error' }` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1260`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:38:- E1: GAP in mechanism, HANDLED in behavior. T-F instructed `query.ts` to request `limit + 1` from SQL at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:30`, but the current implementation does not issue a limited SQL query; it loads all import dependents via `queryFileImportDependents()` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:831` or all qualifying import edges from SQL without `LIMIT` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:837`. The DB helper query likewise has no `LIMIT` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:604`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:39:- E2: HANDLED. True overflow is detected before slicing by `totalAffectedBeforeSlice = affectedByFile.size` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:963` and `overflowed = totalAffectedBeforeSlice > limit` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:40:- E3: HANDLED. Because the check is `>` rather than `>=` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`, result count exactly equal to `limit` does not create `failureFallback` / `partialResult`; `failureFallback` is only added under `overflowed` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1003`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:43:- F1: HANDLED. The multi-subject loop is at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1133`, resolves each candidate at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1147`, builds preserved seed nodes on failure at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1155`, and pushes successful sources at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1189`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:44:- F2: HANDLED with naming drift. Resolved sibling seeds are preserved in the local `preservedSeedNodes` array at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1155` and emitted as `nodes` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1168` plus `partialResult.nodes` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1177`. No response field named `preservedSeedNodes` is emitted, despite the 010/007 summary using that name at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:316`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:45:- F3: HANDLED. The failure path does not reset `nodes = []`; it emits `nodes: preservedSeedNodes` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1168` and carries the same seeds in `partialResult` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1179`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:54:- **Evidence:** `rowToEdge` performs `JSON.parse` with no local catch at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:788`; relationship reads invoke that mapper from `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:545` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:568`. The sanitizer handles bad `reason`/`step` values after a successful parse at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:795`, but malformed JSON never reaches it. The only nearby catch is the blast-radius confidence parser at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:819`, which is a separate path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:62:- **Evidence:** T-F explicitly asked to "Request `limit + 1` from underlying SQL" at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:30`, but `queryImportDependentsForBlastRadius` either calls the unlimited DB helper at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:831` or runs an unlimited SQL import-edge scan at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:837`; the actual overflow fix is full traversal size comparison at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:963` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:968`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:63:- **Suggested action:** Update the remediation summary/brief language to say "compare full traversal count before slicing" or implement a bounded `limit + 1` frontier query if the performance intent still matters.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:70:- **Evidence:** The 010/003 brief says HIGH if depth-one count > 10, MEDIUM if depth-one is `[4,9]`, LOW if <= 3 at `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:66`. Code classifies count 10 as medium because high is `> 10` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:885` and medium is `>= 4` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:888`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:75:- HANDLED: Relationship query output includes sanitized `reason` and `step` via `edgeMetadataOutput` at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:647`, and tests assert visible values at `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts:622`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:77:- HANDLED: `minConfidence` uses metadata confidence when present and weight fallback when metadata is absent/malformed for the blast-radius confidence-only path at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:817` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:860`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:78:- HANDLED: Ambiguous blast-radius subjects do not silently select a default node; they return a high-risk ambiguity fallback at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1192`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:79:- HANDLED: All five `failureFallback.code` literals exist and are wired to distinct branches at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1007`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1176`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1210`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1237`, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1280`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md:80:- HANDLED: Multi-subject unresolved fallback preserves already-resolved seed nodes instead of wiping the response to `nodes: []`, via `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1155` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1168`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json:8:  "specFolder": ".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/003-graph-metadata-validation",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json:23:    "deep-research-config.json": "immutable",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json:24:    "deep-research-state.jsonl": "append-only",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json:25:    "deep-research-strategy.md": "mutable",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-config.json:27:    "research/research.md": "mutable"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-dashboard.md:1:# Deep Research Dashboard
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-dashboard.md:28:- Original research questions answered: `8 / 8`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/tasks.md:18:| T-006-B1 | Update root `/README.md` features section | B | complete — `README.md` lines updated under §3 CocoIndex + Code Graph (Edge Explanation + `detect_changes` Preflight subsections), §3 Skill Advisor (Affordance Evidence subsection), §3 Memory Engine (Causal Trust Display Badges subsection); footer version bump 4.2 -> 4.3 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/tasks.md:25:| T-006-D1 | Update `merged-phase-map.md` with 012 entry | D | complete — new "Derived Implementation Phases" section after "Active Phase Themes" (012 derived from `001-research-and-baseline/007-external-project/` pt-01 + pt-02; owner wrapper `026-graph-and-context-optimization/`); one-paragraph note describing the six sub-phase decomposition and ownership-boundary contract from pt-02 §13 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/tasks.md:27:| T-006-E2 | Link check (no broken refs) | E | complete — verified all source-file references in updated docs resolve via `ls`: `mcp_server/code_graph/handlers/detect-changes.ts`, `handlers/index.ts`, `code_graph/lib/diff-parser.ts`, `code_graph/lib/phase-runner.ts`, `code_graph/lib/structural-indexer.ts`, `skill_advisor/lib/affordance-normalizer.ts`, `formatters/search-results.ts`, `lib/response/profile-formatters.ts` (all 8 present); verified all 10 new per-packet entry paths from feature_catalog and manual_testing_playbook indexes resolve via `ls` (5 catalog + 5 playbook); anchor balance verified per file via `grep -c "ANCHOR:"` (README.md 14, SKILL.md 14, system-spec-kit/README.md 21 with 1 body-text mention, mcp_server/README.md 22, INSTALL_GUIDE.md 0) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-019.md:4:Reconcile the live code findings with the four child implementation phases under the current research packet.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-019.md:7:1. `001-fix-status-derivation`, `002-sanitize-key-files`, and `003-deduplicate-entities` still map cleanly onto the current parser hotspots and remain justified by live corpus measurements. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/001-fix-status-derivation/spec.md] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/002-sanitize-key-files/spec.md] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/003-deduplicate-entities/spec.md]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-019.md:8:2. `004-normalize-legacy-files` is now stale against the active branch because the live corpus no longer contains legacy text metadata. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/004-normalize-legacy-files/spec.md] [SOURCE: live filesystem scan over `.opencode/specs` on 2026-04-13]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-state.jsonl:4:{"type":"iteration","mode":"review","run":3,"status":"complete","focus":"Security sweep for shared-memory governance/auth residue","dimensions":["security"],"filesReviewed":[".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts",".opencode/skills/system-spec-kit/scripts/**",".opencode/skills/system-spec-kit/shared/**",".opencode/skills/system-spec-kit/templates/**",".opencode/skills/system-spec-kit/feature_catalog/**"],"sessionId":"review-memory-deprecation-v2-20260414T110341Z","parentSessionId":"review-memory-deprecation-20260414T092851Z","lineageMode":"new","generation":2,"continuedFromRun":20,"findingsCount":1,"findingsSummary":{"P0":0,"P1":1,"P2":0},"findingsNew":{"P0":0,"P1":0,"P2":0},"newFindingsRatio":0.0,"newInfoRatio":0.0,"timestamp":"2026-04-14T11:36:00.000Z","durationMs":36000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-state.jsonl:5:{"type":"iteration","mode":"review","run":4,"status":"insight","focus":"shared_space_id release narrative versus shipped fallback behavior","dimensions":["traceability"],"filesReviewed":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/008-cleanup-and-audit/001-remove-shared-memory/checklist.md",".opencode/changelog/01--system-spec-kit/v3.4.0.0.md",".opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts"],"sessionId":"review-memory-deprecation-v2-20260414T110341Z","parentSessionId":"review-memory-deprecation-20260414T092851Z","lineageMode":"new","generation":2,"continuedFromRun":20,"findingsCount":2,"findingsSummary":{"P0":0,"P1":2,"P2":0},"findingsNew":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.28,"newInfoRatio":0.28,"findingRefs":["F002"],"timestamp":"2026-04-14T11:44:00.000Z","durationMs":39000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-state.jsonl:8:{"type":"iteration","mode":"review","run":7,"status":"insight","focus":"Command docs and workflow assets still advertising retired memory/shared surfaces","dimensions":["traceability","maintainability"],"filesReviewed":[".opencode/commands/memory/README.txt",".opencode/commands/memory/learn.md",".opencode/commands/memory/save.md",".opencode/commands/memory/search.md",".opencode/commands/memory/manage.md",".opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml",".opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml"],"sessionId":"review-memory-deprecation-v2-20260414T110341Z","parentSessionId":"review-memory-deprecation-20260414T092851Z","lineageMode":"new","generation":2,"continuedFromRun":20,"findingsCount":4,"findingsSummary":{"P0":0,"P1":4,"P2":0},"findingsNew":{"P0":0,"P1":1,"P2":0},"newFindingsRatio":0.24,"newInfoRatio":0.24,"findingRefs":["NF002"],"timestamp":"2026-04-14T12:08:00.000Z","durationMs":47000}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/implementation-summary.md:63:| 012/003 | Edge `reason` + `step` JSON metadata fields (no SQLite migration); `blast_radius` adds `depthGroups`, `riskLevel` (depth-one fanout rule: high on ambiguity or >10, medium on 4-10, low on 0-3), `minConfidence` filter, `ambiguityCandidates`, structured `failureFallback`; context propagation through structured edges | Root README §3 Edge Explanation and Blast-Radius Uplift subsection; `SKILL.md` §3 Code Graph capability matrix (`code_graph_query` row); `system-spec-kit/README.md` §3 Code Graph (Edge explanation paragraph); `mcp_server/README.md` §3.1.13 Code Graph; `INSTALL_GUIDE.md` §6.4b smoke test |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/implementation-summary.md:65:| 012/005 | Display-only `MemoryTrustBadges` per `MemoryResultEnvelope` derived from existing causal-edge columns (`confidence` from edge `strength`, `extractionAge`, `lastAccessAge`, `orphan` from inbound-edge absence, `weightHistoryChanged` from `weight_history` row presence); response-profile preservation across `quick`/`research`/`resume`; formatter fails open when DB handle or `weight_history` table is unavailable | Root README §3 Memory Engine (Causal Trust Display Badges subsection); `SKILL.md` §3 Key Concepts (memory trust badges bullet); `system-spec-kit/README.md` §3 Memory System (Causal Trust Display Badges subsection with badge table); `mcp_server/README.md` §3.1.5 Causal Graph (Causal trust display badges paragraph); `INSTALL_GUIDE.md` §6.4d smoke test |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/implementation-summary.md:84:| `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/merged-phase-map.md` | +10 / 0 | New "Derived Implementation Phases" section after "Active Phase Themes": 012 entry (derived from `001-research-and-baseline/007-external-project/` pt-01 + pt-02; owner wrapper `026-graph-and-context-optimization/`) with one-paragraph note describing the six sub-phase decomposition and the ownership-boundary contract from pt-02 §13 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/implementation-summary.md:135:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/spec.md:215:| Research | 12/20 | pt-02 findings and license audit guided implementation |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:17:    next_safe_action: "Wait for 012/001 license sign-off; then read formatters/search-results.ts"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:45:**Problem:** `MemoryResultEnvelope` exposes `confidence` and `trace.graphContribution` but no unified trust/freshness badge surface. Memory's existing causal-edge schema (`lib/storage/causal-edges.ts:82-94`) already stores `strength`, `evidence`, `source_anchor`, `target_anchor`, `extracted_at`, `created_by`, `last_accessed`. `lib/search/causal-boost.ts:327-338` (`computeTraversalFreshnessFactor`) already implements freshness decay using `FRESHNESS_DECAY_WINDOW_MS`. The data exists; the display doesn't.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:47:**Purpose:** Add display-only `trustBadges` to memory search results. Pure presentation layer. No schema change. No new relation types. No code-fact storage.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:56:- Surface in `memory_search` and `memory_context` response shapers
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:69:| `mcp_server/formatters/search-results.ts` | MODIFY | Add `trustBadges` to envelope |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:70:| `mcp_server/lib/response/profile-formatters.ts` | MODIFY | Propagate badges into search results |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:97:- [ ] Integration: memory_search returns `trustBadges` in envelope
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:109:- Verified anchors: `lib/storage/causal-edges.ts:82-94` (schema), `lib/search/causal-boost.ts:327-338` (`computeTraversalFreshnessFactor` decay logic), `formatters/search-results.ts`, `lib/response/profile-formatters.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:18:    next_safe_action: "Wait for 012/001 license sign-off; then read query.ts:862-909 (computeBlastRadius)"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:46:**Problem:** Public's edge metadata in `code_edges.metadata` carries `confidence`, `detectorProvenance`, `evidenceClass` (verified at `code-graph-db.ts:92` + emitted at `structural-indexer.ts:85-94`) but no `reason`/`step` fields explaining WHY a relation was inferred. `computeBlastRadius` (`query.ts:862-909`) groups by depth but lacks risk levels, min-confidence filtering, ambiguity surfacing, and structured failure states.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:56:- Surface those fields in query output
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:70:| `mcp_server/code_graph/handlers/query.ts:862-909` | MODIFY | Extend `computeBlastRadius` output shape |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:71:| `mcp_server/code_graph/handlers/query.ts:978-981` | MODIFY | Surface `reason`/`step` in relationship-query output |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:101:- [ ] Integration: `code_graph_query` end-to-end with new fields
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:112:- Verified anchors: `code-graph-db.ts:92` (JSON metadata column), `structural-indexer.ts:85-94` (metadata writer), `query.ts:862-909` (computeBlastRadius), `query.ts:978-981` (query output)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md:9:3. `system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment` is clearly stale: stored metadata still says `planned`, but all five packet docs now declare `status: complete`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json:29-37] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/spec.md:12] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/plan.md:12] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/tasks.md:11] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/checklist.md:11] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/implementation-summary.md:11]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md:10:4. The full “planned + complete checklist” bucket contains only five packets: two skilled-agent packets missing `implementation-summary.md` and three stale doc-alignment packets whose metadata still only lists `spec.md` in `source_docs`. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/004-doc-surface-alignment/graph-metadata.json:109-111] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/005-doc-surface-alignment/graph-metadata.json:117-119]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md:22:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md:23:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/004-doc-surface-alignment/graph-metadata.json`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/iterations/iteration-029.md:24:- `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/005-doc-surface-alignment/graph-metadata.json`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:1:{"type":"config","topic":"Graph metadata relationship validation and entity quality analysis","maxIterations":10,"convergenceThreshold":0.05,"createdAt":"2026-04-13T00:00:00Z","specFolder":".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:13:{"type":"iteration","run":11,"status":"complete","focus":"`deriveStatus()` minimal patch and live status drift","findingsCount":4,"newInfoRatio":0.82,"noveltyJustification":"Established the live 360-file baseline and isolated the exact one-function fallback needed for phase 001.","keyQuestions":["FQ-1"],"answeredQuestions":[],"ruledOut":["Parsing markdown status tables as a runtime signal"],"focusTrack":"status-minimal","toolsUsed":["Read","Bash"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:346-353",".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:498-510",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/001-fix-status-derivation/spec.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T08:28:00Z","durationMs":600000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:16:{"type":"iteration","run":14,"status":"complete","focus":"Bare non-canonical filename filtering for `key_files`","findingsCount":4,"newInfoRatio":0.66,"noveltyJustification":"Identified the structural rule that removes most current misses after proper spec-relative resolution.","keyQuestions":["FQ-2"],"answeredQuestions":["FQ-2"],"ruledOut":["Relying on repo-root existence checks without spec-relative resolution"],"focusTrack":"key-files-structure","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:463-471",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/002-sanitize-key-files/spec.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T09:05:00Z","durationMs":480000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:18:{"type":"iteration","run":16,"status":"complete","focus":"Exact basename-dedupe insertion point and canonical preference","findingsCount":4,"newInfoRatio":0.54,"noveltyJustification":"Translated the collision measurements into the concrete callsites that phase 003 should patch first.","keyQuestions":["FQ-3"],"answeredQuestions":["FQ-3"],"ruledOut":["Adding the basename check only to extracted entities"],"focusTrack":"entities-patch-shape","toolsUsed":["Read","Bash"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:418-446",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/003-deduplicate-entities/spec.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T09:29:00Z","durationMs":420000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:19:{"type":"iteration","run":17,"status":"complete","focus":"Legacy normalization safety and active-corpus drift","findingsCount":4,"newInfoRatio":0.50,"noveltyJustification":"Rechecked the live corpus instead of repeating the stale 35-file assumption and mapped the safest no-op-friendly backfill flag.","keyQuestions":["FQ-4"],"answeredQuestions":["FQ-4"],"ruledOut":["Unconditional whole-tree backfill as the safest legacy cleanup path"],"focusTrack":"legacy-normalization","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:82-160",".opencode/skills/system-spec-kit/scripts/graph/backfill-graph-metadata.ts:139-177",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/004-normalize-legacy-files/spec.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T09:41:00Z","durationMs":420000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:20:{"type":"iteration","run":18,"status":"complete","focus":"Trigger-phrase cap root cause and minimal enforcement","findingsCount":4,"newInfoRatio":0.46,"noveltyJustification":"Pinned the overflow to a single missing slice call and quantified the current excess above the intended ceiling.","keyQuestions":["FQ-5"],"answeredQuestions":["FQ-5"],"ruledOut":["Looking for a hidden schema-level max-length guard"],"focusTrack":"trigger-cap","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:523-545",".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-schema.ts:29-39",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/spec.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T09:53:00Z","durationMs":360000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:21:{"type":"iteration","run":19,"status":"complete","focus":"Follow-on phase alignment and implementation order","findingsCount":4,"newInfoRatio":0.40,"noveltyJustification":"Mapped the live code findings back onto the four child phases and identified phase 004 as drifted against the active branch.","keyQuestions":["FQ-1","FQ-2","FQ-3","FQ-4","FQ-5"],"answeredQuestions":[],"ruledOut":["Treating all four follow-on phases as equally urgent without rechecking live corpus drift"],"focusTrack":"phase-alignment","toolsUsed":["Read","Bash"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/001-fix-status-derivation/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/002-sanitize-key-files/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/003-deduplicate-entities/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/004-normalize-legacy-files/spec.md"],"timestamp":"2026-04-13T10:05:00Z","durationMs":300000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:22:{"type":"iteration","run":20,"status":"complete","focus":"Remediation synthesis and implementation guidance","findingsCount":5,"newInfoRatio":0.34,"noveltyJustification":"Closed the reopened wave by converting the individual patch investigations into a risk-ranked implementation order and packet guidance.","keyQuestions":["FQ-1","FQ-2","FQ-3","FQ-4","FQ-5"],"answeredQuestions":["FQ-1","FQ-2","FQ-3","FQ-4","FQ-5"],"ruledOut":["Opening another discovery-only wave before landing parser fixes"],"focusTrack":"wave2-synthesis","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md",".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts",".opencode/skills/system-spec-kit/scripts/graph/backfill-graph-metadata.ts","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T10:18:00Z","durationMs":300000,"sessionId":"f5055a5f-4041-485b-a6d0-b56cd0457f7c","generation":2,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:35:{"type":"iteration","run":27,"status":"complete","focus":"Before-versus-after comparison for the original eight research questions","findingsCount":5,"newInfoRatio":0.34,"noveltyJustification":"Wave 4 converted the raw rescan into direct deltas against Wave 1 and showed that key-file resolution, status fidelity, trigger hygiene, and freshness all improved while entity-cap saturation became the new bottleneck.","keyQuestions":["PVQ-1"],"answeredQuestions":["PVQ-1"],"ruledOut":["Treating entity de-duplication as the end of entity-quality work"],"focusTrack":"wave4-deltas","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T12:31:00Z","durationMs":360000,"sessionId":"937db887-8922-4028-b13d-4eeca0e16d8f","generation":4,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:37:{"type":"iteration","run":29,"status":"complete","focus":"Manual review of a 10-folder planned sample plus full-set stale-pocket check","findingsCount":5,"newInfoRatio":0.22,"noveltyJustification":"The manual sample proved the remaining planned set is mostly real, while the full-set follow-up isolated three clearly stale doc-alignment packets and two contract-bound packets that only lack implementation-summary.md.","keyQuestions":["PVQ-2"],"answeredQuestions":["PVQ-2"],"ruledOut":["Calling the two complete-checklist skilled-agent packets parser regressions before checking their missing implementation summaries"],"focusTrack":"planned-manual","toolsUsed":["Read","Bash","rg"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json",".opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/010-sk-agent-improver-self-test-fixes/tasks.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T12:48:00Z","durationMs":360000,"sessionId":"937db887-8922-4028-b13d-4eeca0e16d8f","generation":4,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:41:{"type":"iteration","run":33,"status":"complete","focus":"Manual entity sample plus residual anomaly inspection","findingsCount":4,"newInfoRatio":0.10,"noveltyJustification":"The random sample came back clean, which shifted the residual question from broad entity noise to a tiny set of specific extraction artifacts: one code-fence language token and two slash-joined headings.","keyQuestions":["PVQ-4"],"answeredQuestions":["PVQ-4"],"ruledOut":["Opening another broad entity-cleanup wave before isolating the exact surviving anomaly patterns"],"focusTrack":"entities-anomalies","toolsUsed":["Read","Bash","rg"],"sourcesQueried":[".opencode/specs/skilled-agent-orchestration/041-sk-recursive-agent-loop/011-sk-agent-improver-advisor-readme-sync/spec.md",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/018-research-content-routing-accuracy/004-doc-surface-alignment/graph-metadata.json","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T13:20:00Z","durationMs":240000,"sessionId":"937db887-8922-4028-b13d-4eeca0e16d8f","generation":4,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:42:{"type":"iteration","run":34,"status":"complete","focus":"Heuristic health scoring and stale-metadata anomaly review","findingsCount":5,"newInfoRatio":0.08,"noveltyJustification":"This pass collapsed the post-implementation evidence into one scorecard and isolated the two remaining maintenance anomalies that still need attention: three stale doc-alignment packets and one hyphenated status value.","keyQuestions":["PVQ-5"],"answeredQuestions":[],"ruledOut":["Treating the remaining stale packets as parser regressions before checking their source-doc lag"],"focusTrack":"health-score","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-skill-advisor-graph/graph-metadata.json",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/017-research-search-fusion-tuning/005-doc-surface-alignment/graph-metadata.json",".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:102-120","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T13:27:00Z","durationMs":240000,"sessionId":"937db887-8922-4028-b13d-4eeca0e16d8f","generation":4,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:43:{"type":"iteration","run":35,"status":"complete","focus":"Final post-implementation synthesis and next-phase targeting","findingsCount":5,"newInfoRatio":0.06,"noveltyJustification":"No new defect class appeared here; the value came from turning the validated corpus metrics into one clear maintenance recommendation plus a sharply scoped follow-on phase target.","keyQuestions":["PVQ-5"],"answeredQuestions":["PVQ-5"],"ruledOut":["Starting another discovery-only loop instead of converting the residual evidence into explicit next-phase goals"],"focusTrack":"wave4-synthesis","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/research.md","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T13:34:00Z","durationMs":240000,"sessionId":"937db887-8922-4028-b13d-4eeca0e16d8f","generation":4,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/research/003-graph-metadata-validation-research/deep-research-state.jsonl:49:{"type":"iteration","run":38,"status":"complete","focus":"Post-fix entity precision revalidation and convergence","findingsCount":5,"newInfoRatio":0.04,"noveltyJustification":"The final pass improved the residual entity counts and health score, but it still only refined already-known hygiene work rather than opening another broad discovery area.","keyQuestions":["RVQ-3"],"answeredQuestions":["RVQ-3"],"ruledOut":["Opening another broad discovery wave before residual hygiene implementation"],"focusTrack":"wave5-entities-convergence","toolsUsed":["Read","Bash","jq"],"sourcesQueried":[".opencode/skills/system-spec-kit/mcp_server/lib/graph/graph-metadata-parser.ts:474-559",".opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-canonical-continuity-refactor/019-research-graph-metadata-validation/research/iterations/iteration-034.md:8-11","live filesystem scan over .opencode/specs on 2026-04-13"],"timestamp":"2026-04-13T14:24:00Z","durationMs":300000,"sessionId":"260a89b1-fff2-4889-bac7-8adfa5ff79a8","generation":5,"lineageMode":"completed-continue"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/plan.md:140:| pt-02 RISK-05 | Internal research | Green | Defines privacy and schema constraints |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-config.json:3:  "research_topic": "Independent review-angle deep research on Phase 010 (sub-phases 001-006), 010/007 remediation (T-A through T-F), and 011 manual-testing-playbook coverage-and-run. Verify correctness, security, observability, and test coverage match shipped code on main. 33 closed findings + 11 new vitest cases under audit. Read code on main directly; do not rely on implementation-summary.md as primary evidence.",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-config.json:4:  "spec_folder": "system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-config.json:5:  "artifact_dir": ".opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-config.json:39:  "session_id": "008-deep-research-review-pt-01"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-dashboard.md:34:| 7 | Command asset drift | memory docs + review/research YAMLs | traceability, maintainability | 0/1/0 | 0.24 | insight |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/plan.md:16:3. Surface fields in `query.ts:978-981` relationship-query output
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/plan.md:20:5. Extend `computeBlastRadius` (`query.ts:862-909`) signature: add `minConfidence?: number`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/plan.md:17:4. Decide display placement (memory_search results / context envelope / status panel) — record in implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/plan.md:20:5. Modify `formatters/search-results.ts` to add `trustBadges` to envelope (additive)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:50:Memory search results now carry display-only trust badges without changing Memory storage. The formatter reads existing causal-edge trust signals at response time, turns them into a stable additive `trustBadges` payload, and keeps that payload attached to each result through response-profile shaping. That gives callers a quick freshness and trust read without introducing new schema, relation types, or Code Graph facts into Memory.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:54:`mcp_server/formatters/search-results.ts` now defines additive `MemoryTrustBadges` output and batch-derives those badges from connected causal-edge records. The derivation uses existing columns only: `strength`, `extracted_at`, `last_accessed`, and the existing `weight_history` table. Orphan status is derived from the absence of inbound causal edges. The formatter fails open when the DB handle or history table is unavailable, and it preserves explicit precomputed `trustBadges` payloads when a caller already supplied them.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:58:`mcp_server/lib/response/profile-formatters.ts` now carries `trustBadges` in its result typing, so `quick`, `research`, and `resume` views keep the badge payload on `results[]` and `topResult` rather than dropping it during output shaping. The placement decision is per-result, not top-level, because the trust signal belongs beside the specific Memory claim the user is judging.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:62:The trust display ships on each `MemoryResultEnvelope` result in `memory_search` output, then flows through profile shaping unchanged. I did not place it in a top-level status panel or context envelope because the trust signal is about a specific Memory claim, not the search request as a whole.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:68:| `mcp_server/formatters/search-results.ts` | Modified | Add additive trust-badge derivation and result-envelope attachment |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:82:I followed the sub-phase contract in the brief: read the sub-phase packet, phase-root ADR, license gate, research anchors, and the protected public code before editing. The code change stays inside the approved formatter and response-profile surface and keeps Memory as a display-only consumer of existing causal-edge storage. I also added packet-local catalog and playbook entries so the shipped behavior has a matching documentation surface.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:119:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/implementation-summary.md:146:| Targeted Vitest — `tests/response-profile-formatters.vitest.ts` | PASS — Wave-3 canonical file is inside the 9 PASSED test files; response-profile preservation behaviour is verified end-to-end (badges round-trip through `quick`/`research`/`resume` profile shaping). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:15:- A3 — CONFIRMED-MATCHES-CODE. Blast-radius docs claim `depthGroups`, `riskLevel`, `minConfidence`, `ambiguityCandidates`, and `failureFallback` at `README.md:533-535`; code surfaces these fields in `code_graph/handlers/query.ts:986-1008` and `code_graph/handlers/query.ts:1298-1302`, with `minConfidence` in the public schema at `tool-schemas.ts:576-584`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:16:- A4 — CONFIRMED-MATCHES-CODE. Trust badges are documented as per-result additive fields with fail-open/profile preservation at `README.md:420-430`; code defines and attaches `trustBadges` in `formatters/search-results.ts:179-191`, `formatters/search-results.ts:331-338`, `formatters/search-results.ts:751-788`, and preserves the shape in `lib/response/profile-formatters.ts:54-59`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:27:- C4 — DRIFT-FROM-CODE for at least `code_graph_query`. The per-handler text and parameter table omit `blast_radius`, `subjects`, `unionMode`, and `minConfidence` at `mcp_server/README.md:1054-1068`, while schema/code expose them at `tool-schemas.ts:576-584` and `schemas/tool-input-schemas.ts:116-123`, `schemas/tool-input-schemas.ts:676`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:31:- D2 — DRIFT-FROM-CODE for umbrella count, CONFIRMED-MATCHES-CODE for the new capability smoke signatures. The guide still says the server provides 43 tools at `mcp_server/INSTALL_GUIDE.md:5`, contradicting the 51-tool canonical export at `tool-schemas.ts:875-938`. The `detect_changes` smoke uses `{ diff, rootDir }` at `INSTALL_GUIDE.md:486-495`, matching `tool-schemas.ts:642-645`; blast-radius smoke uses `code_graph_query({ operation: "blast_radius", subject, maxDepth, minConfidence })` at `INSTALL_GUIDE.md:503-508`, matching `tool-schemas.ts:576-584`. The memory smoke at `INSTALL_GUIDE.md:466-472` is a natural-language client prompt, not a handler-signature claim.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:47:- F22 — P2, doc-fix, RQ4. `mcp_server/README.md` `code_graph_query` handler docs omit the shipped blast-radius parameters. Evidence: the doc lists operations as `outline`, `calls_from`, `calls_to`, `imports_from`, `imports_to` and parameters through `maxDepth` at `mcp_server/README.md:1054-1068`; the schema includes `blast_radius`, `subjects`, `unionMode`, and `minConfidence` at `tool-schemas.ts:576-584` and allows those parameters at `schemas/tool-input-schemas.ts:676`. Remediation: update the per-handler section to match the JSON schema.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md:72:{"iter":7,"convergence_score":0.79,"findings":[{"id":"F19","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"SKILL.md still carries stale 48/47 tool-count claims"},{"id":"F20","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"INSTALL_GUIDE still advertises 43 tools"},{"id":"F21","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"mcp_server README detailed tool reference omits 11 of 51 tools"},{"id":"F22","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"mcp_server README code_graph_query docs omit blast_radius parameters"},{"id":"F23","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"feature_catalog command-surface paragraph still says 43 tools"}],"checklist_handled":18,"checklist_drift":5,"rq_coverage":{"RQ1":"No new P0/P1 doc-vs-code drift in 010/006 umbrella docs.","RQ2":"No new closure contradiction; known F12/F14/F17 retained.","RQ3":"Docs match shipped hardening surfaces except known F14 TS/Python caveat.","RQ4":"Expanded with F19-F23 doc/catalog drift findings.","RQ5":"Manual playbook index and 011-added blocks confirmed preserved."},"new_p0":0,"new_p1":0,"new_p2":5}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-state.jsonl:1:{"event":"init","at":"2026-04-25T20:30:00Z","session_id":"008-deep-research-review-pt-01","spec_folder":"system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review","max_iterations":10,"convergence_threshold":0.05,"executor":{"kind":"cli-codex","model":"gpt-5.5","reasoning_effort":"high","service_tier":"fast","timeout_seconds":900},"status":"INITIALIZED"}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/tasks.md:15:| T-003-A3 | Surface in query output `query.ts:978-981` | A | complete — relationship edges include `reason` + `step` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/tasks.md:21:| T-003-B5 | Wrap failure paths in structured `failureFallback` | B | complete — unresolved/ambiguous/query-failure paths return structured fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:3:**Session:** 008-deep-research-review-pt-01
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:9:## Research Charter
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:24:### Key research questions
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:86:(Loaded from `memory_context` at workflow start — populated in iteration 1.)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:122:- `research.md` — 17-section synthesized findings document
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:127:- `deep-research-state.jsonl` — orchestrator state log
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md:128:- `deep-research-config.json` — frozen config (this folder)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-findings-registry.json:34:      "title": "Command docs and review/research workflows still advertise retired memory/shared surfaces",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-brief.md:15:- mcp_server/code_graph/handlers/query.ts (computeBlastRadius + edge surfacing)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-brief.md:17:- 3 vitest files: code-graph-context-handler/code-graph-indexer/code-graph-query-handler
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-brief.md:25:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-brief.md:26:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/graph-metadata.json:37:      "mcp_server/formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/graph-metadata.json:50:      "formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/graph-metadata.json:61:        "name": "search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/graph-metadata.json:63:        "path": "mcp_server/formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-006.jsonl:1:{"iter":6,"convergence_score":0.74,"findings":[{"id":"F16","severity":"P2","remediation":"test-add","rq":["RQ5"],"summary":"Missing regression test for partial explicit trust-badge overlay using derived fallback","evidence":[".opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:357",".opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:364",".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:91",".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:166"]},{"id":"F17","severity":"P2","remediation":"test-add","rq":["RQ2","RQ5"],"summary":"T-E test evidence is two SQL-pipeline cases plus one formatter pass-through, not three SQL-pipeline cases","evidence":[".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:115",".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:150",".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:167"]},{"id":"F18","severity":"P2","remediation":"test-add","rq":["RQ3","RQ5"],"summary":"Age-label allowlist lacks explicit accepted/rejected boundary tests despite sanitizer implementation","evidence":[".opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:276",".opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:282",".opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:288",".opencode/skills/system-spec-kit/mcp_server/tests/memory/trust-badges.test.ts:178"]}],"checklist_handled":23,"checklist_gap":2,"rq_coverage":{"RQ1":"No new P0/P1 in 010/005 focus; prior coverage retained from iters 1-5.","RQ2":"Extended with F17 closure-integrity precision gap; prior F12/F14 remain.","RQ3":"Trust-badge sanitizer and cache invalidation boundaries code-backed; F18 adds adversarial test gap.","RQ4":"Pending iter 007 umbrella-doc audit.","RQ5":"Extended with F16/F17/F18 test sufficiency gaps."},"new_p0":0,"new_p1":0,"new_p2":3}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:21:6. **Research basis:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:22:   `.../research/007-external-project-pt-02/research.md` §4 (Code Graph findings — Confidence edges, Explanation gap, Public blast radius rows), §11 Packet 2, §12 RISK-07
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:25:   - `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts` (lines 862-909 for `computeBlastRadius`; 978-981 for relationship-query output)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:40:| `mcp_server/code_graph/handlers/query.ts` | **MODIFY** lines 862-909 (extend `computeBlastRadius` output shape) and 978-981 (surface `reason`+`step` in relationship-query output) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:57:- `skill_advisor/`, `lib/storage/`, `lib/search/`, `formatters/` (other sub-phases)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:96:- Verified anchors: `structural-indexer.ts:85-94` (metadata writer), `query.ts:862-909` (`computeBlastRadius`), `query.ts:978-981` (query output)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:30:**Wave-3 canonical verification:** `tsc --noEmit` exit 0; `vitest run` 9 passed | 1 skipped (10), 90 passed | 3 skipped (93), 1.34s — the 003 surfaces (`code-graph-context-handler.vitest.ts`, `code-graph-indexer.vitest.ts`, `code-graph-query-handler.vitest.ts`) are inside the 9 PASSED files with all 003 cases passing. `validate.sh --strict` FAILED on cosmetic template-section conformance only (deferred P2; not a contract violation). Closes R-007-7, R-007-20.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:34:- Relationship query output now includes `reason` and `step` per edge, beside the existing confidence and evidence fields.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:70:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:93:| Relationship query output coverage | PASS | `code-graph-query-handler.vitest.ts` asserts per-edge `reason` and `step`; inside the 9 PASSED files. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:94:| Blast-radius risk/depth/filter/ambiguity/fallback coverage | PASS | `code-graph-query-handler.vitest.ts` adds low, medium, high, `minConfidence`, ambiguity and `failureFallback` cases; all passing. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:15:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:859`: `computeBlastRadius` slices `affectedFiles` to `limit` before deciding whether the result is partial, then `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:897` emits `failureFallback.reason = "limit_reached"` whenever the sliced length is `>= limit`. A result with exactly `limit` affected files is reported as fallback/truncated even when no row was omitted. Track the pre-slice total or request `limit + 1` before slicing.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:17:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1048`: the unresolved-subject fallback preserves prior `sourceFiles`, but `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1050` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1058` return empty `nodes` / `partialResult.nodes`. In multi-subject mode, a later unresolved subject can erase already-resolved seed nodes from the structured partial result. Include seed nodes for resolved sources in this fallback path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:21:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:763`: persisted edge metadata is parsed back from SQLite without validation, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:614` / `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:615` emit `reason` and `step` directly. The current writer uses fixed strings at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/structural-indexer.ts:91`, but stale/imported/hand-edited DB rows can still put arbitrary text into JSON and the context text brief at `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts:545`. Add an allowlist or single-line sanitizer on the read path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:25:- P1 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:29` adds `minConfidence` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1024` consumes it, satisfying spec R-003-4 in handler code. The public strict Zod schema omits it at `.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:452`, and strict mode is the default at `.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:27`; the JSON tool schema also omits it at `.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:573`, and the allowed-parameter ledger omits it at `.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:669`. Real MCP callers will get an unknown-parameter failure before the handler sees the new feature. Add `minConfidence` to all tool schema surfaces and extend `tool-input-schema.vitest.ts`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:29:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:739` selects every cross-file `IMPORTS` edge for `minConfidence > 0`, then `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:758` parses/filter metadata in process before BFS starts at `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:818`. Large graphs pay whole-graph import-edge cost for every blast-radius query. Prefer frontier-scoped DB lookups, cached adjacency with confidence, or a bounded `limit + 1` traversal strategy.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:31:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:245` re-ranks ambiguous subjects by calling `relationshipEdgeCount` for every candidate; `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:211` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:216` perform per-candidate edge queries. This is acceptable for small ambiguity sets, but names shared across many generated wrappers become an N+1 hot path. Batch edge counts by candidate IDs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:35:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1229`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1258`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1287`, and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1315` duplicate relationship-edge response construction across four switch branches. The new metadata fields had to be threaded through each branch, which raises the chance of future drift. Extract shared outbound/inbound relationship mappers.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:39:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1121` catches blast-radius computation failures and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1135` converts them into a successful `status: "ok"` payload with `failureFallback`. That is a reasonable user contract, but there is no log, metric, fallback code, or error class for operators to distinguish DB/metadata failures from legitimate empty blast radius. Emit a warning/metric and use a stable `failureFallback.code`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/checklist.md:18:- [x] `trustBadges` computed from existing columns only — `formatters/search-results.ts` derives from `strength`, `extracted_at`, `last_accessed`, and `weight_history`; orphan from inbound-edge absence.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-strategy.md:24:- No web research or external sources.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-strategy.md:66:- What was tried: global text searches for legacy memory-path helpers and retired surfaces.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/deep-review-strategy.md:123:| .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts | D2, D3 | 4 | 1 P1 | complete |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md:17:- [x] `computeBlastRadius` returns `{ depthGroups, riskLevel, ambiguityCandidates, failureFallback? }` — `query.ts` adds these fields alongside existing `nodes` and `affectedFiles`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md:18:- [x] `minConfidence` parameter filters edges during traversal — `QueryArgs.minConfidence` and targeted query test cover `0.75` filtering.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md:19:- [x] Risk classification rules documented + tested — documented in `implementation-summary.md`; query tests cover low, medium and high.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md:20:- [x] Ambiguous target returns candidates — no silent default pick (pt-02 §12 RISK-07) — query test asserts candidates and no call to `resolveSubjectFilePath`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/checklist.md:31:- [x] code-graph vitest suite passes unchanged — Wave-3 canonical (010/007/T-B, 2026-04-25): `npx --no-install vitest run code_graph/tests/code-graph-context-handler.vitest.ts code_graph/tests/code-graph-indexer.vitest.ts code_graph/tests/code-graph-query-handler.vitest.ts ...` → 9 passed | 1 skipped (10) test files, 90 passed | 3 skipped (93) tests, 1.34s. The 003 surfaces (`code-graph-context-handler.vitest.ts`, `code-graph-indexer.vitest.ts`, `code-graph-query-handler.vitest.ts`) are inside the 9 PASSED files with all 003 cases passing. Skips are the documented trust-badges SQL-mock describe block (R-007-13 / T-E remediation), not 003's surface.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/prompts/agent-brief.md:19:5. **Research basis:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/prompts/agent-brief.md:20:   `.../research/007-external-project-pt-02/research.md` §6 (Skill Advisor findings), §11 Packet 3, §12 RISK-05 (prompt-stuffing risk)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/prompts/agent-brief.md:52:- `code_graph/`, `lib/storage/`, `lib/search/`, `formatters/` (other sub-phases)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-009.jsonl:1:{"iter":9,"convergence_score":0.88,"findings":[{"id":"F24","severity":"P2","title":"011 detect_changes absolute-path test is not absolute and misses mixed-header bypasses","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F25","severity":"P2","title":"Edge metadata sanitizer tests do not assert all documented read-path call sites","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F26","severity":"P2","title":"R-007-12 unit tests miss memory_search cache-key semantics and enableCausalBoost gating","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F27","severity":"P2","title":"Playbook 199 claims R-007-8 coverage without conflicts_with parity checks","status":"new","rq":["RQ2","RQ5"],"remediation":"test-add/doc-fix"},{"id":"F28","severity":"P2","title":"Manual fixture retains boilerplate-heavy near-duplicate seed pairs","status":"new","rq":["RQ5"],"remediation":"test-add"}],"checklist_handled":19,"checklist_gap":5,"rq_coverage":{"RQ1":"No new P0/P1; known F1/F6 remains open and uncovered by 011 cases.","RQ2":"Extended with playbook closure-surface precision for F12/F14/F17/F19-F23.","RQ3":"Adversarial coverage improved but mixed-header and sanitizer call-site wiring remain gaps.","RQ4":"No new umbrella-doc drift; playbook metadata mismatch captured as F27.","RQ5":"Expanded materially with F24-F28 test-rig sufficiency gaps."},"new_p0":0,"new_p1":0,"new_p2":5}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:19:5. **Research basis:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:20:   `.../research/007-external-project-pt-02/research.md` §5 (Memory findings), §11 Packet 4, §12 RISK-06
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:23:   - `.opencode/skills/system-spec-kit/mcp_server/lib/search/causal-boost.ts` (lines 327-338 `computeTraversalFreshnessFactor` decay logic — DO NOT modify)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:24:   - `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts` (target — add `trustBadges` to envelope)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:37:| `mcp_server/formatters/search-results.ts` | **MODIFY** — add `trustBadges: { confidence, extractionAge, lastAccessAge, orphan, weightHistoryChanged }` to `MemoryResultEnvelope` (additive) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:38:| `mcp_server/lib/response/profile-formatters.ts` | **MODIFY** — propagate badges into search results |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:49:- `lib/search/causal-boost.ts` (NO modification to decay logic)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/prompts/agent-brief.md:67:7. **Display placement** — record your decision (memory_search results vs context envelope vs status panel) in `implementation-summary.md` under "Display Placement Decision".
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:1:# Deep-Research Iteration 010 — Cross-Cutting Synthesis + Adopt/Adapt/Reject/Defer Matrix
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. **This is the synthesis iteration** — you read all 9 prior iterations + deltas + state log, and produce the consolidated review with an Adopt/Adapt/Reject/Defer matrix.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:7:1. Strategy: `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:8:2. State log: `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deep-research-state.jsonl` (10 events: init + 9 iteration-complete events)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:9:3. All 9 iterations: `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-{001..009}.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:10:4. All 9 deltas: `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-{001..009}.jsonl`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:48:| F26 | iter 9 | P2 | test-add | RQ5 | R-007-12 cache-key memory_search semantics untested | ADOPT | new tests |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:111:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-010.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-010.md:117:    next_safe_action: "Synthesize research.md and resource-map.md from iter 010 + prior 9; orchestrator runs canonical save"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:26:| R-007-11 | T-D | trust-badge merge per field | CLOSED-IN-CODE | Already verified iter 6; per-field normalization/merge is in `search-results.ts:291-320` and `search-results.ts:342-370`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:28:| R-007-13 | T-E | trust-badges DI strategy; "3/3 SQL tests pass" | CONTRADICTED-BY-CODE | DI seam and bind-side fix are real at `search-results.ts:398-405` and SQL casts at `search-results.ts:472-478`; test file has only two SQL-pipeline tests plus one formatter pass-through at `trust-badges.test.ts:91`, `trust-badges.test.ts:132`, `trust-badges.test.ts:166`. This re-confirms F17 precision drift against the `3/3 SQL tests` claim at `007-review-remediation/implementation-summary.md:47` and `007-review-remediation/implementation-summary.md:264`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:39:| R-007-P2-3 | T-D | `reason`/`step` allowlist on read path | CLOSED-IN-CODE | Shared shape appears at all three promised read sites: DB parse sanitizer at `code-graph-db.ts:756-783` and applied at `code-graph-db.ts:787-800`; query output sanitizer at `query.ts:631-645` and applied through `edgeMetadataOutput` at `query.ts:647-654`; context output sanitizer at `code-graph-context.ts:287-300` and applied at `code-graph-context.ts:302-317`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:40:| R-007-P2-4 | T-F | limit+1 overflow detection | CONTRADICTED-BY-CODE | Re-confirms F12. Code records `totalAffectedBeforeSlice = affectedByFile.size`, slices to `limit`, then sets `overflowed = totalAffectedBeforeSlice > limit` at `query.ts:960-968`; there is no actual `limit + 1` request path despite the closure wording at `007-review-remediation/implementation-summary.md:303-309`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:41:| R-007-P2-5 | T-F | multi-subject seed preservation | CLOSED-IN-CODE | On unresolved candidate, already-resolved siblings are kept as `preservedSeedNodes` at `query.ts:1147-1159`, returned in `nodes` at `query.ts:1164-1170`, and placed in `partialResult` at `query.ts:1174-1182`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:42:| R-007-P2-6 | T-F | stable `failureFallback.code` | CLOSED-IN-CODE | Already verified iter 4; examples remain visible for `limit_reached`, `unresolved_subject`, `ambiguous_subject`, `empty_source`, and `compute_error` at `query.ts:1005-1008`, `query.ts:1174-1177`, `query.ts:1208-1211`, `query.ts:1235-1238`, `query.ts:1278-1281`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:43:| R-007-P2-7 | T-F | shared relationship-edge mapper | CLOSED-IN-CODE | Helpers exist at `query.ts:685-719`; four branches are collapsed into two case groups at `query.ts:1357-1405`, preserving `includeLine` differences for calls vs imports. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md:46:| R-007-P2-10 | T-D | age-label allowlist | CLOSED-IN-CODE | Already verified iter 6; allowlist regex and fallback derivation are at `search-results.ts:262-288`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:42:- **B5:** NO. The suite imports and calls only `sanitizeEdgeMetadataString` from `code-graph-db.ts` (`edge-metadata-sanitize.test.ts:9`). It does not assert the sanitizer is called from all 3 documented sites: `rowToEdge` applies it at `code-graph-db.ts:787-800`, `edgeMetadataOutput` applies a local equivalent at `query.ts:647-654`, and `formatContextEdge` applies a local equivalent at `code-graph-context.ts:302-317`. That is a regression-detection gap: deleting one call site can leave this suite green.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:43:- **B6:** If the exported sanitizer changed to `return value`, the 8 unit tests would catch it strongly: non-string, empty, over-length, control-char, DEL, and mixed-control tests fail (`edge-metadata-sanitize.test.ts:18-65`). But a call-site mutation such as removing `reason: sanitizeEdgeMetadataReadString(...)` in `query.ts:653` or `formatContextEdge` in `code-graph-context.ts:316-317` would not be caught by this file.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:54:- **C2:** NO. The unit tests do not verify `enableCausalBoost === true` gating. The gating exists in code: `buildCacheArgs` includes `causalEdgesGeneration` only when `enableCausalBoost === true` at `search-utils.ts:178-214`, and `memory-search.ts` only reads the generation for causal-boost calls at `memory-search.ts:847-887`. The unit suite never exercises this path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:55:- **C3:** NO. The tests verify only the counter increments. They do not run `memory_search`, build the cache key end to end, or assert cache hit/miss behavior through `toolCache.generateCacheKey` at `memory-search.ts:891`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:56:- **C4:** NO. There is no concurrency/race test. The generation counter is in-memory and incremented before degree-cache invalidation (`causal-edges.ts:173-182` from the rg result), but the suite does not verify deterministic behavior when two `memory_search` calls race with a mutation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:62:- **026 Block A:** The prompt and expected fields match the relationship/blast-radius handler surface. Relationship output uses `edgeMetadataOutput` for `reason` / `step` at `query.ts:647-654`, and the playbook requires those plus `depthGroups`, `riskLevel`, `minConfidence`, `ambiguityCandidates`, and `failureFallback` at `026-code-graph-edge-explanation-blast-radius-uplift.md:38-43`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:63:- **026 Blocks B/C/D/E:** Mostly match current return shapes. Block B checks runtime exact-limit truth (`partialResult:false` when count equals limit) at playbook `:45-49`, which current code achieves via pre-slice size comparison, not the documented `limit + 1` mechanism from known F12. Block C matches preserved resolved seeds (`:51-54`). Block D matches the 5 `failureFallback.code` values and allows `compute_error` to be unautomatable (`:56-62`). Block E matches relationship-query sanitizer exposure (`:64-69`), but it does not exercise `code_graph_context`'s `formatContextEdge` path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:65:- **203 Blocks A/B:** Block A matches trust-badge formatter/profile preservation (`203-memory-causal-trust-display.md:36-40`). Block B is stronger than the new unit tests: it explicitly requires `H1 === H1'`, `H2 !== H1`, and `enableCausalBoost=false` stability at `:42-48`, matching the gated cache-key design in `memory-search.ts:847-887` and `search-utils.ts:178-214`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:81:- **F25 (P2, test-add, RQ5): Edge metadata sanitizer tests validate the helper, not all documented read-path call sites.** Evidence: the unit suite imports only `sanitizeEdgeMetadataString` at `edge-metadata-sanitize.test.ts:9`; documented call sites are `rowToEdge` at `code-graph-db.ts:787-800`, `edgeMetadataOutput` at `query.ts:647-654`, and `formatContextEdge` at `code-graph-context.ts:302-317`. Remediation: add fixture/mocked-row tests for relationship query and context output, ideally with a direct DB mutation or mocked edge carrying control chars.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:82:- **F26 (P2, test-add, RQ5): R-007-12 unit tests prove generation increments, not memory_search cache invalidation semantics.** Evidence: G1-G6 only read `getCausalEdgesGeneration()` around storage mutations (`causal-edges-unit.vitest.ts:702-771`). The actual semantics live in `memory-search.ts:847-891` and `search-utils.ts:178-214`, but no test asserts `enableCausalBoost=true` changes the cache key while `false` stays stable. Remediation: add a focused `memory_search` cache-key test with mutation and causal-boost on/off controls.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:92:- Playbook 026 Block E would catch raw control characters leaking through relationship query output (`026-code-graph-edge-explanation-blast-radius-uplift.md:64-86`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md:107:{"iter":9,"convergence_score":0.88,"findings":[{"id":"F24","severity":"P2","title":"011 detect_changes absolute-path test is not absolute and misses mixed-header bypasses","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F25","severity":"P2","title":"Edge metadata sanitizer tests do not assert all documented read-path call sites","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F26","severity":"P2","title":"R-007-12 unit tests miss memory_search cache-key semantics and enableCausalBoost gating","status":"new","rq":["RQ5"],"remediation":"test-add"},{"id":"F27","severity":"P2","title":"Playbook 199 claims R-007-8 coverage without conflicts_with parity checks","status":"new","rq":["RQ2","RQ5"],"remediation":"test-add/doc-fix"},{"id":"F28","severity":"P2","title":"Manual fixture retains boilerplate-heavy near-duplicate seed pairs","status":"new","rq":["RQ5"],"remediation":"test-add"}],"checklist_handled":19,"checklist_gap":5,"rq_coverage":{"RQ1":"No new P0/P1; known F1/F6 remains open and uncovered by 011 cases.","RQ2":"Extended with playbook closure-surface precision for F12/F14/F17/F19-F23.","RQ3":"Adversarial coverage improved but mixed-header and sanitizer call-site wiring remain gaps.","RQ4":"No new umbrella-doc drift; playbook metadata mismatch captured as F27.","RQ5":"Expanded materially with F24-F28 test-rig sufficiency gaps."},"new_p0":0,"new_p1":0,"new_p2":5}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:32:- **F002 - Shared-space column retirement story still disagrees between release artifacts and shipped runtime.** The runtime and packet docs describe a best-effort startup `DROP COLUMN` with an older-SQLite no-op fallback, but the changelog still promises an unconditional auto-drop that leaves no orphan columns. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47-48] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53-53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94-94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:257-258]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:35:- **NF002 - Command docs and review/research workflows still advertise retired memory/shared surfaces.** `memory/README.txt`, `memory/learn.md`, `memory/save.md`, `memory/search.md`, and `memory/manage.md` still point to `specs/**/memory/` or `/memory:manage shared`, and the deep-review/deep-research auto+confirm workflows still verify save success by checking `{spec_folder}/memory/*.md`. [SOURCE: .opencode/commands/memory/README.txt:318-323] [SOURCE: .opencode/commands/memory/learn.md:501-505] [SOURCE: .opencode/commands/memory/save.md:536-541] [SOURCE: .opencode/commands/memory/search.md:768-772] [SOURCE: .opencode/commands/memory/manage.md:264-271] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_auto.yaml:863-871] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-review_confirm.yaml:995-1003] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_auto.yaml:644-652] [SOURCE: .opencode/commands/spec_kit/assets/spec_kit_deep-research_confirm.yaml:822-830]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:70:   - Replace `{spec_folder}/memory/*.md` save checks in deep-review/deep-research workflows with the canonical generated-support-artifact surface.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:77:- Clean: no new security-relevant shared-memory scope or auth residue surfaced in runtime/supporting packages. [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1548]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/review/review-brief.md:28:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/review/review-brief.md:29:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-brief.md:14:- mcp_server/formatters/search-results.ts (trustBadges field)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-brief.md:25:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-brief.md:26:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-008.md:1:# Deep-Research Iteration 008 — 010/007 T-A..T-F closure integrity vs shipped code
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-008.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. Defensive code-review of internal closure claims. Read-only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-008.md:66:- R-007-P2-5 multi-subject seed preservation — verify code at query.ts:1048-1058.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-008.md:74:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-008.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:1:# Deep-Research Iteration 007 — 010/006 umbrella docs vs code reality
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. Defensive code/doc-review of internal documentation. Read-only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:22:A1. **Tool count claims**: search root README for "tool" mentions referring to total count. Current claim is "60 MCP tools" (51 + 7 + 1 + 1 + ...). Cite the lines and verify 51 matches `TOOL_DEFINITIONS.length` in `mcp_server/tool-schemas.ts`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:43:D2. Smoke-test invocation examples for detect_changes, blast_radius, memory_search — do they match current handler signatures?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:59:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-007.md:72:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-007.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:1:# Deep-Research Iteration 004 — 010/003 minConfidence + ambiguity + failureFallback.code drill
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. This is a defensive code review of an internal code-graph system. Read-only — no code changes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:23:A1. Cite the line in `mcp_server/code_graph/handlers/query.ts` where `computeBlastRadius` builds its SQL/traversal call. Quote the exact `LIMIT` clause or `slice(0, limit)` invocation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:31:B1. Where in `query.ts` is the `args.minConfidence` parameter read?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:42:C1-C5. Cite the line in `query.ts` where `failureFallback.code = '<code>'` is set. For each code, what scenario triggers it? Trace the conditional that selects this code.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:50:D3. Is the response shape stable across the 4 main `code_graph_query` operations (`outline`, `calls_from`, `calls_to`, `blast_radius`), or is it only on `blast_radius`?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:61:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:62:2. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:63:3. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-002.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:64:4. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:65:5. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts` (focus lines 600-1500)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:68:8. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:73:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-004.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-004.md:118:JSONL delta to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-004.jsonl`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md:1:# Deep-Research Iteration 001 — Focus: 010/001 license posture + 010/002 phase-runner + detect_changes preflight
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md:14:   `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md:62:`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-001.md:100:`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-001.jsonl`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-007.jsonl:1:{"iter":7,"convergence_score":0.79,"findings":[{"id":"F19","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"SKILL.md still carries stale 48/47 tool-count claims"},{"id":"F20","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"INSTALL_GUIDE still advertises 43 tools"},{"id":"F21","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"mcp_server README detailed tool reference omits 11 of 51 tools"},{"id":"F22","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"mcp_server README code_graph_query docs omit blast_radius parameters"},{"id":"F23","severity":"P2","remediation":"doc-fix","rq":"RQ4","title":"feature_catalog command-surface paragraph still says 43 tools"}],"checklist_handled":18,"checklist_drift":5,"rq_coverage":{"RQ1":"No new P0/P1 doc-vs-code drift in 010/006 umbrella docs.","RQ2":"No new closure contradiction; known F12/F14/F17 retained.","RQ3":"Docs match shipped hardening surfaces except known F14 TS/Python caveat.","RQ4":"Expanded with F19-F23 doc/catalog drift findings.","RQ5":"Manual playbook index and 011-added blocks confirmed preserved."},"new_p0":0,"new_p1":0,"new_p2":5}
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/implementation-summary.md:84:- pt-01 synthesis: `.../001-research-and-baseline/007-external-project/research/007-external-project-pt-01/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/implementation-summary.md:85:- pt-02 synthesis: `.../001-research-and-baseline/007-external-project/research/007-external-project-pt-02/research.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/review/review-report.md:19:- **P1 — Instruction-shaped affordance filtering is narrower than the stated prompt-stuffing boundary.** The spec requires instruction-shaped strings to be stripped or dropped (`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/spec.md:174`) and pt-02 says affordance ingestion must require allowlisted normalization and privacy-preserving output (`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md:267`). The TypeScript denylist only catches role labels plus `ignore previous/all instructions` (`.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/affordance-normalizer.ts:59`), and the Python compiler duplicates the same narrow expression (`.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_graph_compiler.py:59`). Common variants such as "ignore prior instructions" or "disregard previous directions" would become sanitized trigger text. Fix: broaden the prompt-injection detector, add adversarial variants in both TS and Python tests, or move to a positive allowlist for short noun-phrase style affordances.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/review/review-report.md:57:- Full implementation/spec/research files reviewed: 3,059 LOC.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:1:# Deep-Research Iteration 002 — Defensive audit of 010/002 input validation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. This is a **defensive code review** of an internal code-graph tool. The goal is to verify the input-validation layer is complete; we are auditing OUR OWN shipped code to find gaps a future user-supplied diff might expose, so we can close them with tests and tighter validators. Read-only — no code changes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:7:Iter 1 wrote findings to `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md`. Read it first. Key open items:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:65:1. `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:66:2. `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-002.md:75:Write to `iteration-002.md` (path: `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-002.md`):
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/deep-review-findings-registry.json:52:        "[SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/deep-review-findings-registry.json:210:        "[SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/deep-review-findings-registry.json:330:        "[SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:15:- P1 — Partial or malformed explicit `trustBadges` suppress correct DB-derived badges. `normalizeTrustBadges()` accepts any object and fills missing fields with `null`, `"never"`, or `false`; `formatSearchResults()` then prefers that object over the derived snapshot with `explicitTrustBadges ?? derivedTrustBadges`. A caller that sends `{ trustBadges: {} }` or only one field will erase the computed `strength`, `extracted_at`, `last_accessed`, orphan, and weight-history values required by the spec. Evidence: `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:235`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:239`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:246`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:609`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:613`, `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/spec.md:80`. Fix: reject incomplete explicit badge objects, or merge valid explicit fields over the derived snapshot instead of replacing it wholesale.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:19:- P2 — Explicit badge age labels are emitted verbatim, creating a small prompt-stuffing surface in a trust UI field. The formatter clamps numeric confidence, but it accepts `extractionAge` and `lastAccessAge` strings as-is before preserving caller-supplied badges over derived values. The pt-02 risk model is strict about owner boundaries and prompt-stuffing surfaces; this field should stay a compact display label, not arbitrary caller text. Evidence: `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:239`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:240`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:243`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:609`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:613`, `.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md:267`. Fix: derive age strings from timestamps where possible, and cap/sanitize explicit display strings to a small allowlisted age-label grammar.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:23:- P1 — Cached `memory_search` responses can serve stale trust badges after causal-edge changes. The cache key is built from search arguments, not causal-edge state; formatted responses, including `trustBadges`, are cached for the default 60 seconds. Causal-edge mutations invalidate degree and graph-signal caches, but they do not bump or clear the `memory_search` tool cache, so recent `strength`, `last_accessed`, or `weight_history` updates can be hidden behind a cache hit. Evidence: `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:880`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:889`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1188`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1190`, `.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:56`, `.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:58`, `.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:150`, `.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:160`, `.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:660`. Fix: include a causal-edge generation/version in the cache key or invalidate `memory_search` cache entries when causal edges or weight history mutate.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:27:- P2 — Trust-badge SQL runs for every result before profile shaping can discard most of the payload. `formatSearchResults()` always calls `fetchTrustBadgeSnapshots(results)`, then the handler applies response profiles later; `quick` profile may keep only `topResult`. This is bounded by result limits, so it is not a hot-path blocker, but it does extra DB work for reduced profiles. Evidence: `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:262`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:298`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:582`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1471`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1477`. Fix: either pass effective profile into formatting and limit badge derivation for `quick`, or accept this deliberately and document the bounded cost.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:31:- P2 — The `trustBadges` shape is duplicated with different optionality across formatter and profile layers. `MemoryTrustBadges` requires all fields, while `SearchResultEntry.trustBadges` redeclares the same fields as optional. That makes future field additions easy to drop silently in response profiles. Evidence: `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:152`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:158`, `.opencode/skills/system-spec-kit/mcp_server/lib/response/profile-formatters.ts:54`, `.opencode/skills/system-spec-kit/mcp_server/lib/response/profile-formatters.ts:60`. Fix: export and reuse the canonical badge type, or define a shared structural type for profile entries.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:35:- P2 — Badge derivation failures are silent and are not surfaced in trace or telemetry. `fetchTrustBadgeSnapshots()` returns an empty map when `requireDb()` fails or when the SQL query fails; later telemetry records graph-walk diagnostics, but not badge derivation status. The result is indistinguishable from "no causal trust data exists," which makes missing badges hard to debug. Evidence: `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:271`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:275`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:348`, `.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:350`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1322`, `.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1327`. Fix: add a non-user-facing trace flag or telemetry field such as `trustBadges: { attempted, derivedCount, failureReason }`, keeping the response fail-open.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/005-memory-causal-trust-display/review/review-report.md:53:3. Tie `memory_search` cache validity to causal-edge/weight-history mutations, or avoid caching dynamic trust badge fields.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:45:| R-007-11 | Trust-badges: reject incomplete explicit `trustBadges` (or merge per-field) (`formatters/search-results.ts:235-246, 609-613`) | done | P1 — merge-per-field; `mergeTrustBadges` overlays explicit non-null on derived |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:47:| R-007-P2-3 | Edge metadata: allowlist `reason`/`step` on read path (`code-graph-db.ts:763`, `query.ts:614-615`, `code-graph-context.ts:545`) | done | P2 — allowlist (single-line, ≤200 chars, no control chars) at all 3 read sites |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:49:| R-007-P2-10 | Memory: sanitize/cap explicit `extractionAge`/`lastAccessAge` strings (`formatters/search-results.ts:239-243`) | done | P2 — `ALLOWED_AGE_LABEL` regex + `MAX_AGE_LABEL_LENGTH` cap |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:50:| R-007-P2-11 | Memory: trace flag `{attempted, derivedCount, failureReason}` for badge derivation (`formatters/search-results.ts:271-275, 348-350`) | done | P2 — `MemoryResultTrace.trustBadgeDerivation` populated when `includeTrace` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:62:| R-007-12 | Memory_search cache: include causal-edge generation in cache key (`handlers/memory-search.ts:880-1190`, `lib/cache/tool-cache.ts:56-58`) | pending | P1 — staleness fix |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:67:| R-007-P2-4 | `computeBlastRadius`: request `limit + 1` to detect true overflow (`query.ts:859, 897`) | pending | P2 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:68:| R-007-P2-5 | `computeBlastRadius`: multi-subject seed preservation when sibling fails (`query.ts:1048-1058`) | pending | P2 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:69:| R-007-P2-6 | Failure-fallback: stable `code` + warning log/metric (`query.ts:1121-1135`) | pending | P2 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:70:| R-007-P2-7 | Extract shared relationship-edge mapper from 4 switch branches (`query.ts:1229, 1258, 1287, 1315`) | pending | P2 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/spec.md:84:| **T-D** Sanitization hardening | `affordance-normalizer.ts` (TS), `skill_graph_compiler.py` (PY), edge metadata read path in `query.ts`, age-label allowlist in `formatters/search-results.ts` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/spec.md:112:| R-007-12 | 005 | T-A | Memory_search cache invalidation on causal-edge mutations (causal-edge generation in cache key) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/plan.md:28:11. Choose diff parsing library (P1-03 blocker — research: `diff`, `parse-diff`, custom). Record decision in implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/plan.md:57:- Memory_search cache invalidation on causal-edge mutations.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:14:    "system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:60:      "formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:64:      ".opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-01/research.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:65:      ".opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/research/007-external-project-pt-02/research.md",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:118:        "name": "search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:120:        "path": "formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/graph-metadata.json:220:    "causal_summary": "Implement the converged pt-01 + pt-02 External Project research recommendations as a 6-sub-phase Level 3 implementation packet. pt-02 cross-checked pt-01 with an independent executor (cli-codex gpt-5.5 high fast) and reached the same core conclusions: External Project is **architectural evidence**, not a source transplant; Code Graph / Memory / Skill Advisor stay **separately owned**; route/tool/shape work is **deferred** until Public has the substrate.",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:1:# Deep-Research Iteration 005 — 010/004 affordance denylist + conflicts_with reject + debug counters
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. Defensive code review of internal skill-advisor system. Read-only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:68:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:69:2. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md` (for prior context)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:82:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-005.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-005.md:124:JSONL delta to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-005.jsonl`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:1:# Deep-Research Iteration 009 — 011 playbook scenarios + 17 new vitest cases adversarial completeness
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. Defensive code/test review of internal regression suite. Read-only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:37:B5. **Gap test**: does the suite assert that the sanitizer is actually CALLED at all 3 documented sites (`code-graph-db.ts:rowToEdge`, `query.ts:edgeMetadataOutput`, `code-graph-context.ts:formatContextEdge`)? If not — that's a regression-detection gap.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:44:C3. Do they verify the cache key actually changes (i.e. test through `memory_search` end-to-end), or only the counter increments?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:63:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:68:6. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts` (edgeMetadataOutput sanitizer call)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-009.md:78:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-009.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/graph-metadata.json:38:      "formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/graph-metadata.json:61:        "name": "search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/graph-metadata.json:63:        "path": "formatters/search-results.ts",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:14:    recent_action: "Wave 1 fully integrated. All 6 batches (T-A through T-F) cherry-picked onto main. T-F closes 11 cleanup findings (R-007-12/16/17/18/P2-2/4/5/6/7/9/12) via cache-key generation counter, INSTALL_GUIDE Python path fix, tool-count canonicalization (51), query.ts micro-fixes (true overflow detection via full-traversal-then-slice; semantically equivalent to `limit + 1`, multi-subject seed preservation, failureFallback.code, shared edge-mapper dedup), affordance debug counters, phase alias note."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:31:      - "../../mcp_server/formatters/search-results.ts"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:45:- **T-C (public API surface gaps):** `minConfidence` exposed end-to-end on `code_graph_query` (Zod schema, JSON schema, allowed-parameter ledger, accept/reject tests). `affordances` DEFER decision: stays compile-time-only scorer seam (prompt-injection surface concern). Closes R-007-6, R-007-10.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:46:- **T-D (sanitization hardening):** 7 files hardened (`detect-changes.ts` canonical-root path containment, `diff-parser.ts` per-side hunk counters, `skill_graph_compiler.py` validate-reject `conflicts_with` + broadened denylist, `affordance-normalizer.ts` broadened denylist, `formatters/search-results.ts` merge-per-field trustBadges + allowlisted age strings + trace flag, `phase-runner.ts` duplicate-output rejection, `code-graph-db.ts`/`query.ts:614-615`/`code-graph-context.ts` `reason`/`step` allowlist on read path). New shared adversarial fixture `affordance-injection-fixtures.json` consumed by both TS and Python tests. Closes R-007-3, 4, 8, 9, 11, P2-1, P2-3, P2-8, P2-10, P2-11. Verify: tsc clean; vitest 37/37 PASS; pytest 57/57 PASS.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:48:- **T-F (doc cleanup + query.ts micro-fixes + cache invalidation):** memory_search cache key includes causal-edge generation counter (folded only when `enableCausalBoost=true`); INSTALL_GUIDE Python smoke-test path fixed; tool count canonicalized to 51 (`TOOL_DEFINITIONS.length`) across all umbrella docs with explicit deferred-handlers-do-not-count note; broken `FEATURE_CATALOG_IN_SIMPLE_TERMS` link removed; `structural-indexer.ts` `runPhases` wrapped in try/catch/finally so error outcome metric emits; `query.ts` detects true overflow by comparing full-BFS-traversal size against `limit` BEFORE slicing (semantically equivalent to `limit + 1` — the BFS frontier is already over-collected, so no extra SQL request is needed; 008/D8 doc-fix correction), preserves seed nodes on multi-subject sibling failures, adds stable `failureFallback.code` + new `spec_kit.graph.blast_radius_failure_total` metric, and dedupes 4 switch branches via shared edge mapper; affordance debug counters (received/accepted/dropped_unsafe/dropped_empty/dropped_unknown_skill) added to TS + Python; 010/006 alias note for renumber. Closes R-007-12, 16, 17, 18, P2-2, P2-4, P2-5, P2-6, P2-7, P2-9, P2-12.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:98:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:157:### R-007-6 — Expose `minConfidence` on `code_graph_query` MCP surface (T-C)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:162:- Handler at `mcp_server/code_graph/handlers/query.ts:1024` already accepts `args.minConfidence` (clamped via `clampNumericConfidence`) and threads it through `computeBlastRadius` (line 1122) and `queryImportDependentsForBlastRadius` (line 731). The only public-API gap is schema rejection: requests with `minConfidence` were dropped at validation as an unknown property (`additionalProperties: false`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:163:- 010/003 implementation summary already documents `minConfidence` as a published field of the `blast_radius` response (line 34) and as a tested code path (line 58, `code-graph-query-handler.vitest.ts` covers `minConfidence` cases). So callers are documented to expect the input lever; only the schema needed to catch up.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:171:| `mcp_server/schemas/tool-input-schemas.ts` (line 675) | Added `'minConfidence'` to `ALLOWED_PARAMETERS.code_graph_query` ledger |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:226:`mcp_server/formatters/search-results.ts:235-360` rewrites the explicit-trust-badge path:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:230:- **R-007-P2-11 trace flag**: `fetchTrustBadgeSnapshots` now returns `{snapshots, attempted, derivedCount, failureReason}`. Failure reasons: `'no_db' | 'no_results' | 'query_error' | null`. Trace exposes `MemoryResultTrace.trustBadgeDerivation` when `includeTrace` is set.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:240:- `mcp_server/code_graph/handlers/query.ts:608-635` — `edgeMetadataOutput` re-validates (defense-in-depth for non-DB-sourced edges).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:259:| `mcp_server/formatters/search-results.ts` | `fetchTrustBadgeSnapshots` exported with new optional `dbGetter = requireDb` parameter (DI seam); `toTrustBadges` and `TrustBadgeSnapshot` exported for direct test assertion; bind-type coercion `resultIds.map(String)` so SQL `CAST(memory_id AS TEXT)` joins resolve against TEXT-typed `source_id`/`target_id` columns. **Integration note:** function returns the T-D `TrustBadgeFetchResult` shape (`{snapshots, attempted, derivedCount, failureReason}`); tests dereference `fetchResult.snapshots.get(...)`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:270:#### R-007-12 — Memory_search cache invalidation on causal-edge mutations
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:271:**Strategy:** include a causal-edges generation counter in the `memory_search` cache key. Mutations bump a module-level counter; readers fold the counter into the cache key only when `enableCausalBoost=true` so unrelated callers do not suffer needless cache misses.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:278:| `mcp_server/lib/search/search-utils.ts` | New optional `causalEdgesGeneration?: number` on `CacheArgsInput`; gated by `enableCausalBoost === true` so the cache key stays stable for non-causal callers |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:279:| `mcp_server/handlers/memory-search.ts` | Imports `causal-edges`; reads generation when `enableCausalBoost` is true; threads through to `buildCacheArgs` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:291:- `/README.md` lines 7, 56, 1261, 1281, 1301 → "60 MCP tools" (51 spec_kit_memory + 7 code mode + 1 CocoIndex + 1 sequential thinking) and "51 tools, 7 layers + L8 graph/advisor + L9 coverage"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:309:`code_graph/handlers/query.ts::computeBlastRadius` now records
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:377:- Backward compat: existing `code_graph_query` callers without `minConfidence` continue to pass schema validation (covered by the pre-existing `'code_graph_query accepts structural traversal options'` case at lines 503-514 of the test file, which omits `minConfidence`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:1:# Deep-Research Iteration 006 — 010/005 trust-badge merge + age allowlist + dbGetter DI + cache invalidation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. Defensive code review of internal memory + trust-display system. Read-only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:19:A1. Cite `mcp_server/formatters/search-results.ts` `mergeTrustBadges` function (or equivalent). Walk through the per-field overlay logic.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:45:D4. Cite `mcp_server/lib/search/search-utils.ts` where `causalEdgesGeneration` is accepted on `CacheArgsInput` and gated by `enableCausalBoost === true`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:46:D5. Cite `mcp_server/handlers/memory-search.ts` where the generation is read and threaded through.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:53:E2. Cite where `failureReason: 'no_db' | 'no_results' | 'query_error' | null` is set per branch.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:59:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:60:2. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:62:4. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:63:5. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:70:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-006.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-006.md:112:JSONL delta to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-006.jsonl`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/checklist.md:41:- [ ] R-007-12 memory_search cache invalidation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:1:# Deep-Research Iteration 003 — 010/003 reason/step round-trip + blast_radius enrichment audit
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:3:You are a fresh-context deep-research executor (cli-codex gpt-5.5 high fast). No memory of prior iterations. This is a defensive code review of an internal code-graph system. Read-only — no code changes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:33:   - `mcp_server/code_graph/handlers/query.ts` — `edgeMetadataOutput` (line ~614 area)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:43:C1. `depthGroups[]` — produced where in `query.ts`? Shape?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:53:D1. Cite the line in `query.ts` that sets `failureFallback.code = '<code>'`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:60:E1. Cite `query.ts` lines where `limit + 1` is requested from SQL.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:66:F1. Cite the multi-subject loop in `query.ts` (~lines 1048-1058 per docs).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:72:1. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/strategy.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:73:2. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-001.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:74:3. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-002.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:75:4. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:78:7. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/structural-indexer.ts` (search for `reason` / `step` write sites)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:79:8. `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-query-handler.vitest.ts`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:85:Write to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/iterations/iteration-003.md`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/prompts/iteration-003.md:139:JSONL delta to `/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/research/008-deep-research-review-pt-01/deltas/iteration-003.jsonl`:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/implementation-summary.md:98:- Symbol attribution: per-hunk overlap against `queryOutline(filePath)` rows; synthetic `module` nodes are excluded so they don't drown per-symbol signal. Path resolution flows through `graphDb.resolveSubjectFilePath` for parity with `code_files` row keying.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/implementation-summary.md:136:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/implementation-summary.md:158:| `detect_changes` never invokes `queryOutline` on stale graph | PASS — readiness probe runs first; tests assert `expect(mocks.queryOutline).not.toHaveBeenCalled()` on stale paths |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/implementation-summary.md:249:4. **Symbol attribution uses pure line-range overlap.** This is the documented Packet 1 contract (pt-02 §4 `detect_changes` row + CG-13). It does NOT execute downstream BFS through call/edge graphs to find indirectly-impacted symbols — that's `blast_radius` territory and is owned by sub-phase 003. Callers wanting full impact must combine `detect_changes` outputs with `code_graph_query({ operation: 'blast_radius' })`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/prompts/agent-brief.md:19:5. **Research basis:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/prompts/agent-brief.md:20:   `.../research/007-external-project-pt-02/research.md` §4 (Code Graph findings), §11 Packet 1, §12 RISK-03
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/prompts/agent-brief.md:54:- `code_graph/handlers/query.ts` (sub-phase 003 owns this)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/prompts/agent-brief.md:56:- Any `skill_advisor/`, `lib/storage/`, `lib/search/`, `formatters/` files (other sub-phases)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/checklist.md:13:- [x] `detect_changes` NEVER returns `"no affected symbols"` on stale state — same code path returns `affectedSymbols: []` ONLY inside the `blocked` payload (with `blockedReason`); test asserts `mocks.queryOutline` is NEVER called on stale state
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/checklist.md:21:- [x] Existing code-graph vitest suite passes unchanged — Wave-3 canonical (010/007/T-B, 2026-04-25): `npx --no-install vitest run code_graph/tests/phase-runner.test.ts code_graph/tests/detect-changes.test.ts code_graph/tests/code-graph-context-handler.vitest.ts code_graph/tests/code-graph-indexer.vitest.ts code_graph/tests/code-graph-query-handler.vitest.ts ...` → 9 passed | 1 skipped (10) test files, 90 passed | 3 skipped (93) tests, 1.34s. The 002 surfaces (`phase-runner.test.ts`, `detect-changes.test.ts`) are inside the 9 PASSED files with all 002 cases passing. Skips are the documented trust-badges SQL-mock describe block (R-007-13 / T-E remediation), not 002's surface.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/tasks.md:23:| T-002-C3 | Map hunks to symbols via line-range overlap | C | complete — `rangesOverlap()` consumed by `detect-changes.ts` against `queryOutline()` rows |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/tasks.md:25:| T-002-D2 | Hard rule: status=blocked on stale (never empty) | D | complete — `readinessRequiresBlock()` blocks when `freshness !== 'fresh'`; tests assert `queryOutline` is NEVER called on stale state |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-brief.md:28:**Source-of-truth research:**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-brief.md:29:- `001-research-and-baseline/007-git-nexus/research/007-git-nexus-pt-02/research.md` §11 / §12 / §13
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-C.md:8:1. `minConfidence` parameter for `code_graph_query` (handler accepts it; schema rejects it as unknown)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-C.md:29:| `mcp_server/schemas/tool-input-schemas.ts` (lines ~452, ~669) | MODIFY | Add `minConfidence: number().min(0).max(1).optional()` to query schema; add to allowed-parameter ledger |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-C.md:30:| `mcp_server/tool-schemas.ts` (~line 573) | MODIFY | Add `minConfidence` to JSON schema for `code_graph_query` tool |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-C.md:38:- `code_graph/handlers/query.ts` (handler logic already done)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-E.md:12:- Test mocks `lib/search/vector-index.js` `getDb()` and `utils/index.js` + `utils/db-helpers.js` `requireDb()`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-E.md:23:4. `mcp_server/formatters/search-results.ts:262-352` (the function being tested — `fetchTrustBadgeSnapshots`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-E.md:42:| `mcp_server/formatters/search-results.ts` (line 262 fn signature) | MODIFY (Strategy A only) — add optional `dbGetter` parameter; default to `requireDb` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-E.md:49:- `lib/search/causal-boost.ts` decay logic (no changes)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-E.md:50:- `formatters/search-results.ts` outside the one function signature (other batches own different parts)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-B.md:24:  code_graph/tests/code-graph-query-handler.vitest.ts \
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-D.md:29:| `mcp_server/formatters/search-results.ts` (lines 235-246, 239-243, 271-275, 348-350, 609-613) | R-007-11, R-007-P2-10, R-007-P2-11 | Reject incomplete explicit `trustBadges` OR merge per-field; sanitize/cap age-label strings to allowlisted grammar; add trace flag for badge derivation |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-D.md:31:| `mcp_server/code_graph/lib/code-graph-db.ts` (~line 763) + `code_graph/handlers/query.ts` (lines 614-615) + `code_graph/lib/code-graph-context.ts` (~line 545) | R-007-P2-3 | Allowlist `reason`/`step` strings on read path (single-line, length-cap, non-control-char) — protect against stale/imported metadata |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-D.md:37:- `code_graph/handlers/query.ts` outside lines 614-615 (T-F owns rest of query.ts)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:7:Close 4 P1 + 7 P2 cleanup findings — broken links, conflicting tool counts, INSTALL_GUIDE bug, memory_search cache invalidation, `query.ts` micro-fixes, doc dedup.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:25:| `mcp_server/handlers/memory-search.ts` (lines 880, 889, 1188, 1190) + `mcp_server/lib/cache/tool-cache.ts` (lines 56-58) + `mcp_server/lib/storage/causal-edges.ts` (lines 150, 160, 660) | R-007-12 | Include causal-edge generation/version in memory_search cache key, OR invalidate memory_search cache entries on causal-edge mutations |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:30:| `mcp_server/code_graph/handlers/query.ts` (line 859, 897) | R-007-P2-4 | Request `limit + 1` from underlying SQL; use this to detect true overflow (set `partialResult` only when actual overflow, not when result happens to equal limit) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:31:| `mcp_server/code_graph/handlers/query.ts` (lines 1048-1058) | R-007-P2-5 | In multi-subject blast-radius, preserve resolved seed nodes when a sibling subject fails (don't reset `nodes` to `[]`) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:32:| `mcp_server/code_graph/handlers/query.ts` (lines 1121, 1135) | R-007-P2-6 | Add stable `failureFallback.code` field; emit warning log + metric so operators can distinguish DB failure from empty blast radius |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:33:| `mcp_server/code_graph/handlers/query.ts` (lines 1229, 1258, 1287, 1315) | R-007-P2-7 | Extract shared outbound/inbound relationship-edge mapper to deduplicate the 4 switch branches |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:40:- `code_graph/handlers/query.ts` lines 614-615 (T-D's reason/step allowlist territory)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:64:- Commit: `fix(010/007/T-F): doc + label cleanup, query.ts micro-fixes, memory_search cache invalidation`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-report.md:19:- **P1 — Diff paths can escape `rootDir` after root canonicalization succeeds.** `rootDir` is checked against the workspace (`.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:151`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:152`), but `resolveCandidatePath` accepts absolute diff paths and resolves relative paths without verifying the result remains under `canonicalRootDir` (`.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:122`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:124`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:125`). That unchecked path is then sent through `resolveSubjectFilePath` and `queryOutline` (`.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:218`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/detect-changes.ts:223`). A crafted diff with `+++ /absolute/path` or `+++ b/../outside.ts` can therefore probe indexed symbols outside the requested repository. Fix by canonicalizing each candidate and rejecting any candidate outside `canonicalRootDir`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/review/review-report.md:23:- **P1 — `detect_changes` is exported as a handler but is not registered as an MCP tool.** The spec requires handler registration with proper schema (`.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/002-code-graph-phase-runner-and-detect-changes/spec.md:98`), and `handlers/index.ts` only exports the function (`.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/index.ts:11`). The actual code-graph dispatcher does not import `handleDetectChanges` (`.opencode/skills/system-spec-kit/mcp_server/code_graph/tools/code-graph-tools.ts:5`), its `TOOL_NAMES` set excludes any detect-changes name (`.opencode/skills/system-spec-kit/mcp_server/code_graph/tools/code-graph-tools.ts:19`), and the switch has no detect-changes case (`.opencode/skills/system-spec-kit/mcp_server/code_graph/tools/code-graph-tools.ts:58`). The MCP-visible schemas list only scan/query/status/context in this section (`.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:554`, `.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:556`, `.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:570`, `.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:589`, `.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:595`). Result: external clients cannot call the new preflight despite the feature being marked shipped. Fix by adding a tool name, schema, validator entry, and dispatcher case, or by changing the spec/checklist to state explicitly that this packet only adds an internal handler.

codex
The repo’s specs live under `.opencode/specs`, not `specs`, and the broad grep was too noisy. The useful signal so far is around `026-graph-and-context-optimization`, especially a “search intelligence stress test” packet and a review remediation note mentioning `memory_search` cache invalidation.
exec
/bin/zsh -lc "rg --files .opencode/skills/system-spec-kit/mcp_server | rg '(memory-search|search-results|tool-cache|causal|storage|vector|fts|retrieval|context)'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/skills/system-spec-kit/mcp_server/context-server.ts
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-links-processor.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts
.opencode/skills/system-spec-kit/mcp_server/lib/interfaces/vector-store.ts
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/scorer/lanes/graph-causal.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/context.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-context-handler.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/api/storage.ts
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts
.opencode/skills/system-spec-kit/mcp_server/tests/search-results-format.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/causal-fixes.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/context-metrics.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-causal-graph.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-ux-hooks.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context-session-state.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-store.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-integration.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-context.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-compatibility.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/causal-edges.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-storage.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-store-remediation.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/sqlite-fts.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-impl.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context-eval-channels.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-eval-channels.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/memory-context.resume-gate-d.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/surrogate-storage.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-store.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/retrieval-directives.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/causal-boost.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/sqlite-fts.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-aliases.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-impl.ts
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-directives.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/causal-edges-unit.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/tool-cache.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/hybrid-search-context-headers.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-trace.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-queries.ts
.opencode/skills/system-spec-kit/mcp_server/tests/causal-boost.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/context-server-error-envelope.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-benchmark-memory-search.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/caller-context.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tools/context-tools.ts
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/access-tracker.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/post-insert-metadata.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/checkpoints.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/README.md
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/reconsolidation.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/incremental-index.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/learned-triggers-schema.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/mutation-ledger.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/transaction-manager.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/document-helpers.ts
.opencode/skills/system-spec-kit/mcp_server/lib/storage/history.ts
.opencode/skills/system-spec-kit/mcp_server/lib/context/caller-context.ts
.opencode/skills/system-spec-kit/mcp_server/lib/context/opencode-transport.ts
.opencode/skills/system-spec-kit/mcp_server/lib/context/publication-gate.ts
.opencode/skills/system-spec-kit/mcp_server/lib/context/README.md
.opencode/skills/system-spec-kit/mcp_server/lib/context/shared-payload.ts
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts
.opencode/skills/system-spec-kit/mcp_server/lib/graph/community-storage.ts

exec
/bin/zsh -lc "rg -n \"memory_search cache|cache invalidation|search intelligence|search bug|empty results|fallback|FTS|BM25|CocoIndex\" .opencode/specs/system-spec-kit/026-graph-and-context-optimization -g 'spec.md' -g 'plan.md' -g 'tasks.md' -g 'implementation-summary.md' -g 'review-report.md' -g 'agent-brief*.md'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/004-claude-freshness-schema-harness-fixes/spec.md:72:Hook testing surfaced three defects. (A) The skill-advisor freshness contract is split: `skill-graph-generation.json` reports `state: "live"` but every advisor probe returns `freshness: "stale"` with `errorCode: SOURCE_NEWER_THAN_SKILL_GRAPH` because `sourceSignature` is persisted as `null`, so the source/graph comparison has no anchor to reconcile against. Every advisor call pays the stale-fallback path. (B) `.claude/settings.local.json` UserPromptSubmit/SessionStart/PreCompact/Stop blocks use a nested structure where the outer object carries `bash`/`timeoutSec` (a Copilot CLI schema) and the inner `hooks` array carries Claude's documented `command`/`timeout`. Three hooks fire per UserPromptSubmit in practice; the duplicated invocations make hook behavior hard to reason about. (C) There is no documented multi-turn harness for the skill-advisor testing playbook — operators running the 17-test pack pay cache-creation (~$0.17) on every fresh `claude -p` invocation, ~5-10x what a single reused session would cost.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/004-claude-freshness-schema-harness-fixes/plan.md:137:| `skill_graph_scan` MCP tool | Internal | Green | Can't verify SC-001 without it; fallback: direct `node scripts/scan.js` if exposed |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/004-claude-freshness-schema-harness-fixes/plan.md:138:| Claude Code CLI `--include-hook-events` | External | Green (verified 2.1.118 on 2026-04-23) | Can't verify REQ-004 hook count; fallback: instrument dist/hooks/claude/* with counter |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/spec.md:87:Both Copilot behaviors are silent: there is no error, no log entry, no fallback notice. The hook simply does not fire because the transport was never wired for Copilot.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/spec.md:152:| REQ-008 | Extractor correctly categorizes paths using the phase-012 ten-category skeleton. | Snapshot tests cover: README, Documents, Commands, Agents, Skills, Specs, Scripts, Tests, Config, Meta. Unknown extensions land in a deterministic fallback category. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/002-resource-map-deep-loop-fix-creation/implementation-summary.md:93:The packet authored its own Level 2 spec docs inline (structured against the Level 2 template shapes) and created the new template file directly, then dispatched cli-codex gpt-5.4 high fast with service_tier fast to execute the coordinated surface-wiring pass across the other ~12 files. cli-copilot was staged as fallback but not needed — codex returned clean edits, a typecheck exit 0, and grep coverage on every target file on the first pass.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/002-resource-map-deep-loop-fix-creation/plan.md:127:| cli-codex (with cli-copilot fallback) | External executor | Green | Surface-wiring pass cannot run autonomously; manual edits still possible |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/spec.md:90:- 003 — Code Graph edge `reason`/`step` display + blast_radius uplift (risk levels, min-confidence filter, ambiguity candidates, structured failure-fallback)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/spec.md:196:- Unknown relation: skipped instead of assigned a fallback multiplier.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/spec.md:145:| `mcp_server/lib/utils/canonical-path.ts` | B | Create | `resolveCanonicalPath()` wrapper around `fs.realpathSync` with fail-open fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/002-copilot-custom-instructions-hook-parity/implementation-summary.md:27:      - ".opencode/skills/system-spec-kit/manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/plan.md:100:- **`lib/utils/canonical-path.ts`** — `resolveCanonicalPath()` wrapper around `fs.realpathSync` with fail-open fallback for missing targets.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/plan.md:118:resolveCanonicalPath() — fs.realpathSync with fail-open fallback
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/plan.md:178:- [x] Add realpath canonicalization: `lib/utils/canonical-path.ts` with `fs.realpathSync` + fail-open fallback; wire into save-time + code-graph `specificFiles`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/004-skill-advisor-affordance-evidence/implementation-summary.md:103:| Skip unknown affordance relation types | Skipping avoids an implicit fallback relation that could behave like a new relation type. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/tasks.md:85:- [x] **T-05** Create realpath canonicalization helper. [EVIDENCE: `mcp_server/lib/utils/canonical-path.ts` wraps `fs.realpathSync` with fail-open fallback.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/implementation-summary.md:109:`scripts/memory/cleanup-index-scope-violations.ts` provides dry-run / apply / verify modes. The apply path opens `database.transaction(...)`, rebuilds the cleanup plan inside the transaction snapshot to close the TOCTOU window, emits governance-audit rows for every downgrade, and lets the `memory_index` trigger chain handle FTS cleanup.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-memory-indexer-invariants/implementation-summary.md:200:| README reversal delete | exit `0`; deleted memory `11672` plus `memory_history=1`, `memory_lineage=1`, `vec_memories=1`, `active_memory_projection=1`; `memory_index` handled FTS via trigger |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/spec.md:112:| R-007-12 | 005 | T-A | Memory_search cache invalidation on causal-edge mutations (causal-edge generation in cache key) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/spec.md:132:| R-007-P2-6 | 003 | T-D | Failure-fallback emits stable `code` + log/metric (operator visibility) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/003-resource-map-deep-loop-integration/implementation-summary.md:70:| `.opencode/skills/system-spec-kit/scripts/resource-map/README.md` | Created | Documents the extractor input/output contract and fallback behavior. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/plan.md:53:- **Goal:** Add `reason`/`step` to edge metadata + display; enrich `blast_radius` with depth groups, risk levels, min-confidence filter, ambiguity candidates, structured failure-fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:76:| 1 | `.opencode/README.md` | 01, 02, 07 | Rewrite Gate 2 and directory-structure prose: hook brief primary, `skill_advisor.py` as fallback; advisor surface now lives in `mcp_server/skill-advisor/`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:77:| 2 | `.opencode/install_guides/SET-UP - AGENTS.md` | 02, 07 | Gate 2 setup teaches runtime hook brief first; `skill_advisor.py` as diagnostic fallback; add native-tool/bootstrap verification + `--force-native` / `--force-local` / disable-flag notes. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:81:| 6 | `.opencode/skills/system-spec-kit/feature_catalog/**` | 10 | Update `22--context-preservation-and-code-graph/05-cross-runtime-fallback.md` to name `.claude/settings.local.json` as the Copilot wrapper surface and note top-level writer commands on `UserPromptSubmit` + `SessionStart`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:84:| 9 | `.opencode/skills/system-spec-kit/references/config/hook_system.md` | 01, 04, 05, 06, 07, 10 | Canonical runtime hook matrix refresh: Codex native SessionStart; Claude `UserPromptSubmit` in the four-event example; OpenCode plugin bridge + `experimental.chat.system.transform`; Copilot file-based parity via `.claude/settings.local.json`; cross-runtime fallback prose aligned. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:85:| 10 | `AGENTS.md` | 01, 05, 09 | Gate 2 anchored on hook brief primary + `skill_advisor.py` fallback; Codex SessionStart parity note; OpenCode plugin ESM exemption under `sk-code-opencode` language table. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:91:| 11 | `.opencode/skills/system-spec-kit/manual_testing_playbook/**/*.md` | 10 | Update `22--context-preservation-and-code-graph/252-cross-runtime-fallback.md` to validate Copilot via `.claude/settings.local.json` wrapper path + managed-block refresh. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:92:| 12 | `.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md` | 03 | Add `SPECKIT_CODEX_HOOK_TIMEOUT_MS` (default, scope, timeout fallback behavior). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:114:| REQ-001 | Update `.opencode/README.md` Gate 2 + directory-structure sections | Hook brief primary, `skill_advisor.py` fallback, advisor path corrected to `mcp_server/skill-advisor/` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:115:| REQ-002 | Update `.opencode/install_guides/SET-UP - AGENTS.md` Gate 2 flow | Hook-first setup path, script fallback, native-tool verification steps |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:119:| REQ-006 | Update `feature_catalog/22--context-preservation-and-code-graph/05-cross-runtime-fallback.md` | Copilot fallback entry names `.claude/settings.local.json` + top-level writer commands |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:122:| REQ-009 | Update `references/config/hook_system.md` | Canonical runtime matrix + Copilot row + Codex native + Claude four-event example + OpenCode plugin + cross-runtime fallback prose |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:123:| REQ-010 | Update top-level `AGENTS.md` Gate 2 + runtime notes | Hook brief primary + fallback, Codex SessionStart parity, OpenCode plugin ESM exemption in `sk-code-opencode` table |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:129:| REQ-011 | Update `manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md` | Copilot validation scenario inspects `.claude/settings.local.json` + managed-block refresh |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/spec.md:130:| REQ-012 | Add `SPECKIT_CODEX_HOOK_TIMEOUT_MS` to `mcp_server/ENV_REFERENCE.md` | Default, scope, timeout-fallback behavior documented |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:46:   - Update cross-runtime fallback prose to match.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:50:   - Gate 2 rule: hook brief primary, `skill_advisor.py` fallback, cite hook reference.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:57:   - Codex: describe native `SessionStart` + prompt hook when enabled, with `/spec_kit:resume` as fallback (post-05 state).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:74:8. **`.opencode/install_guides/SET-UP - AGENTS.md`** — Gate 2 hook-first path, script fallback, native-tool/bootstrap verification, `--force-native` / `--force-local` / disable-flag notes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:78:10. **`feature_catalog/22--context-preservation-and-code-graph/05-cross-runtime-fallback.md`** — Copilot fallback entry named and describes top-level writer commands on `UserPromptSubmit` + `SessionStart`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:82:11. **`manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md`** — Copilot scenario expanded to inspect `.claude/settings.local.json` top-level fields/commands and smoke managed-block refresh.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/plan.md:103:   - `grep -rn "skill_advisor.py" .opencode/README.md .opencode/skills/system-spec-kit/README.md AGENTS.md` should show only *fallback* references, never primary.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/plan.md:57:- Memory_search cache invalidation on causal-edge mutations.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/plan.md:60:- Failure-fallback `code` + log/metric.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:30:| T-001 | Rewrite runtime matrix + cross-runtime fallback prose in `.opencode/skills/system-spec-kit/references/config/hook_system.md`: Codex native `SessionStart` (post-05), Claude `UserPromptSubmit` in four-event example, OpenCode plugin bridge, Copilot `.claude/settings.local.json` wrappers | P0 | [009/01, 04, 05, 06, 07, 10] — top hotspot, 6 sub-packets flagged |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:31:| T-002 | Update top-level `AGENTS.md`: Gate 2 hook-brief primary + `skill_advisor.py` fallback; Codex SessionStart parity note; OpenCode plugin ESM exemption in `sk-code-opencode` language table | P0 | [009/01, 05, 09] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:41:| T-005 | Update `.opencode/README.md`: Gate 2 prose (hook brief primary, script fallback), directory-structure (advisor surface in `mcp_server/skill-advisor/`) | P0 | [009/01, 02, 07] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:51:| T-008 | Update `.opencode/install_guides/SET-UP - AGENTS.md`: Gate 2 hook-first path, script fallback, native-tool/bootstrap verification, `--force-native` / `--force-local` / disable-flag notes | P0 | [009/02, 07] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:53:| T-010 | Update `feature_catalog/22--context-preservation-and-code-graph/05-cross-runtime-fallback.md`: Copilot fallback entry names `.claude/settings.local.json` + top-level writer commands | P0 | [009/10] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:61:| T-011 | Update `manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md`: Copilot scenario inspects `.claude/settings.local.json` top-level fields/commands + smokes managed-block refresh via that path | P1 | [009/10] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/tasks.md:62:| T-012 | Add `SPECKIT_CODEX_HOOK_TIMEOUT_MS` entry to `.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md` (default, scope, timeout-fallback behavior) | P1 | [009/03] |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/006-docs-and-catalogs-rollup/tasks.md:18:| T-006-B1 | Update root `/README.md` features section | B | complete — `README.md` lines updated under §3 CocoIndex + Code Graph (Edge Explanation + `detect_changes` Preflight subsections), §3 Skill Advisor (Affordance Evidence subsection), §3 Memory Engine (Causal Trust Display Badges subsection); footer version bump 4.2 -> 4.3 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:37:- Ambiguous symbol subjects return candidate metadata and a structured fallback instead of silently choosing a default graph node.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:38:- Added targeted test coverage in existing Code Graph Vitest files for edge metadata, relationship output, context propagation, risk levels, confidence filtering, ambiguity candidates and failure fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/implementation-summary.md:94:| Blast-radius risk/depth/filter/ambiguity/fallback coverage | PASS | `code-graph-query-handler.vitest.ts` adds low, medium, high, `minConfidence`, ambiguity and `failureFallback` cases; all passing. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:15:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:859`: `computeBlastRadius` slices `affectedFiles` to `limit` before deciding whether the result is partial, then `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:897` emits `failureFallback.reason = "limit_reached"` whenever the sliced length is `>= limit`. A result with exactly `limit` affected files is reported as fallback/truncated even when no row was omitted. Track the pre-slice total or request `limit + 1` before slicing.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:17:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1048`: the unresolved-subject fallback preserves prior `sourceFiles`, but `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1050` and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1058` return empty `nodes` / `partialResult.nodes`. In multi-subject mode, a later unresolved subject can erase already-resolved seed nodes from the structured partial result. Include seed nodes for resolved sources in this fallback path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/review/review-report.md:39:- P2 — `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1121` catches blast-radius computation failures and `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/query.ts:1135` converts them into a successful `status: "ok"` payload with `failureFallback`. That is a reasonable user contract, but there is no log, metric, fallback code, or error class for operators to distinguish DB/metadata failures from legitimate empty blast radius. Emit a warning/metric and use a stable `failureFallback.code`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/plan.md:32:The expected outcome is **A: full isolation** — helpers move to a clearly named non-plugin folder, plugins continue to import them via relative paths, and a vitest guard fails CI if a non-plugin file lands in the plugin folder. Outcomes B (no-op default exports for helpers) and C (extension/prefix opt-out via OpenCode config) are documented fallbacks if Phase 1 surfaces a hard constraint.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:7:Close 4 P1 + 7 P2 cleanup findings — broken links, conflicting tool counts, INSTALL_GUIDE bug, memory_search cache invalidation, `query.ts` micro-fixes, doc dedup.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:25:| `mcp_server/handlers/memory-search.ts` (lines 880, 889, 1188, 1190) + `mcp_server/lib/cache/tool-cache.ts` (lines 56-58) + `mcp_server/lib/storage/causal-edges.ts` (lines 150, 160, 660) | R-007-12 | Include causal-edge generation/version in memory_search cache key, OR invalidate memory_search cache entries on causal-edge mutations |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/prompts/agent-brief-T-F.md:64:- Commit: `fix(010/007/T-F): doc + label cleanup, query.ts micro-fixes, memory_search cache invalidation`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/tasks.md:20:| T-003-B4 | Implement ambiguity detection + candidate surfacing | B | complete — ambiguous `fq_name`/`name` subjects return candidates and fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/tasks.md:21:| T-003-B5 | Wrap failure paths in structured `failureFallback` | B | complete — unresolved/ambiguous/query-failure paths return structured fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:7:You add `reason`/`step` explanation fields to code-graph edge metadata and enrich `computeBlastRadius` output with risk levels, min-confidence filtering, ambiguity candidates, and structured failure-fallback. **No SQLite schema migration** — JSON metadata only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:42:| `mcp_server/code_graph/tests/blast-radius.test.ts` (or extend existing) | **MODIFY** — add tests for risk levels, min-confidence filter, ambiguity candidates, failure fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/prompts/agent-brief.md:68:7. **Structured failure fallback** — return `{ failureFallback: { reason, partialResult? } }`, never bare error strings.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/spec.md:53:**Key decisions**: outcome A (full hook parity) is the overwhelmingly likely path — the transport exists, the schema is known, only the contract details need confirming. Outcomes B (workaround) and C (documented limitation) are emergency fallbacks if the investigation uncovers a hard constraint (e.g., Codex hooks are notification-only and can't inject into model context).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/tasks.md:82:- [x] **T-29** Run `node .opencode/skills/system-spec-kit/scripts/dist/memory/generate-context.js` for canonical save (refreshes description.json + graph-metadata.json). [EVIDENCE: `generate-context.js` exited 0, refreshed `graph-metadata.json`, indexed 7/8 canonical files with deferred BM25 fallback after embedding network failures, and reported no blocking post-save issues.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/tasks.md:96:- [x] **T-35** Update implementation-summary.md with the Phase 4 outcome, refresh ADR-004 evidence table, run strict validation + canonical save. [EVIDENCE: implementation summary/checklist/spec/ADR updated with Phase 4 evidence; `validate.sh --strict` passed 0 errors / 0 warnings; `generate-context.js` exited 0 and refreshed graph metadata with non-blocking embedding fallback warnings.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:69:A live `/memory:search` session against the indexed-continuity runtime exposed contract violations and degraded UX across the retrieval, output rendering, and causal-graph subcommands. The empty-arguments gate fired correctly, but every downstream stage produced at least one observable defect: the intent classifier emitted `fix_bug` (confidence 0.098) for the query "Semantic Search" despite the spec mandating `understand` as the no-keyword-match fallback; the `memory_context` wrapper reported `truncated=true` and zero `results` while consuming only 2% of its 3000-3500 token budget; the assistant rendering used the explicitly-forbidden phrase "Auto-triggered memories"; `causal-stats` returned three of six valid relation types and labeled itself `health: "healthy"` while reporting `meetsTarget: false`. The root spec at `.opencode/commands/memory/search.md` documents the intended behavior, but the runtime drifts from it on multiple axes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:90:- Re-architecting the hybrid retrieval pipeline (graph + vector + FTS5/BM25); only the observable surface defects are catalogued.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:113:| REQ-001 | Intent classifier MUST honor the documented no-keyword-match fallback. | For queries with no keyword hit and `confidence < 0.30`, the classifier returns `understand` (per spec §4A "Default fallback") instead of an arbitrary low-confidence intent such as `fix_bug` (currently observed at 0.098 for "Semantic Search"). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:124:| REQ-007 | `QUALITY=gap` flag MUST trigger automatic broadening before returning. | Spec §1 promises 3-tier FTS fallback (FTS5 → BM25 → Grep) on weak retrievals. Currently `avg_score:0.13`, `quality:"gap"` is reported but no broadening occurs. After fix, gap-flagged retrievals attempt at least one fallback tier before returning. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:134:| REQ-012 | CocoIndex daemon health MUST be checked before relying on the vector channel. | Current behavior: command attempts CocoIndex search, fails silently when daemon is down. After fix, command emits an explicit `WARN: vector channel unavailable, lexical-only` line in the result block when daemon is unreachable. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:136:| REQ-014 | AskUserQuestion custom-answer routing MUST be defined. | Spec §4 offers 7 intents + "Analysis tools". A custom answer like "Semantic Search" currently becomes the QUERY (auto-detect intent) — undocumented. Either document this routing or add explicit "Code search / Explore codebase" option that routes to CocoIndex. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:175:| Dependency | CocoIndex daemon must be runnable for REQ-012 verification. | Medium | Document the start command and add a smoke test before remediation lands. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:184:- Should intent confidence below threshold T fall back to `understand`, or surface a sentinel `unknown`? Spec says fallback is `understand`; runtime appears to skip the fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:203:Spec §4A keyword table assigns NONE of {"semantic","search"} to `fix_bug`; the documented fallback is `understand`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/implementation-summary.md:65:The skill-advisor plugin now treats OpenCode runtime readiness as lifecycle/handler readiness instead of advisor bridge success. The SDK and compact plugin both confirmed the real event discriminant is `type`; Phase 5 retained that discriminant, added direct/wrapped event payload normalization, and stopped skipped/degraded bridge responses from overwriting `runtime_ready=false`. The first `experimental.chat.system.transform` call also flips readiness to true as a pragmatic fallback if lifecycle events are not observed.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/implementation-summary.md:85:Focused vitest was extended to cover hook shape, system prompt injection, empty fail-open behavior, session-message prompt fallback, event readiness/cache cleanup, and status tool registration. A direct Node smoke imported the plugin, invoked `experimental.chat.system.transform`, and asserted the advisor brief landed in `output.system[]`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/implementation-summary.md:141:| `generate-context.js` | PASS; Phase 3, Phase 4, and Phase 5 runs exited 0. Phase 5 refreshed graph metadata and canonical context with non-blocking embedding/provider fallback behavior. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/005-opencode-plugin-loader-bridge-fixes/implementation-summary.md:152:4. **Memory embeddings were deferred.** `generate-context.js` exited 0, but embedding-provider network calls failed and the indexer saved BM25/FTS-searchable entries without embeddings.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/spec.md:92:- Implementing runtime code in Spec Kit Memory, Code Graph, CocoIndex, or startup hooks.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:90:- **Cluster 2 — Intent Classifier Drift (P0/P1)** — REQ-001, REQ-004, REQ-016. `meta.intent.type = "fix_bug"` (confidence 0.098) returned for "Semantic Search" instead of documented `understand` fallback. Same response also carries `data.queryIntentRouting.queryIntent = "semantic"` (confidence 0.8) — two classifiers, no resolution policy. Change surface: intent detection logic + threshold gate.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:98:- **Cluster 6 — Folder Discovery + Channel Health (P1/P2)** — REQ-008, REQ-012, REQ-017. Folder-discovery binds on weak signal ("Semantic Search" → `skilled-agent-orchestration/023-sk-deep-research-creation`); CocoIndex daemon failure is silent; "code graph" vs "causal graph" naming collides. Change surface: similarity threshold + startup health check + naming disambiguation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:100:- **Cluster 7 — Quality Fallback + Edge Growth (P1/P2)** — REQ-007, REQ-010, REQ-014. `QUALITY=gap` flag is informational only; spec §1 promises 3-tier FTS fallback that never activates. Causal-graph edge growth dominated by autonomous `supersedes`-only backfill (+344 in 15 min, `caused`/`supports` unchanged). AskUserQuestion custom-answer routing undocumented. Change surface: retrieval pipeline + backfill job + command spec.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:124:- [ ] **Phase 2C — P2 refinement:** Cluster 7 (quality fallback + edge growth + custom-answer routing)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:156:| CocoIndex daemon | External | Red (down — observed in conversation) | REQ-012 verification blocked until daemon runnable |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/003-code-graph-edge-explanation-and-impact-uplift/spec.md:4:description: "Add reason/step fields to edge metadata + display; enrich blast_radius with depth groups, risk levels, min-confidence filter, ambiguity candidates, structured failure-fallback. No SQLite migration."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:49:- **Change:** Runtime matrix + cross-runtime fallback prose refresh: Codex native `SessionStart` (post-05) + prompt hook gated by `codex_hooks`, Claude `UserPromptSubmit` in four-event example, OpenCode plugin bridge + `experimental.chat.system.transform`, Copilot file-based parity via `.claude/settings.local.json` top-level wrapper fields.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:57:- **Change:** Gate 2 anchored on hook brief primary with `skill_advisor.py` as fallback; Codex post-05 native `SessionStart` parity note; OpenCode plugin ESM exemption in `sk-code-opencode` language table.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:81:- **Change:** Gate 2 prose + directory-structure updated; advisor surface pointer corrected to `mcp_server/skill-advisor/`; hook-primary routing with `skill_advisor.py` described as compatibility/scripted fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:105:- **Change:** Gate 2 setup teaches runtime hook brief first with `skill_advisor.py` as diagnostic fallback; native-tool/bootstrap verification added; `--force-native` / `--force-local` / disable-flag notes added.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:116:### T-010 — `feature_catalog/22--context-preservation-and-code-graph/05-cross-runtime-fallback.md` (Skill, HIGH)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:119:- **Applied report:** `applied/06-_opencode_skill_system-spec-kit_feature_catalog_22--context-preservation-and-code-graph_05-cross-runtime-fallback_md.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:121:- **Change:** Copilot fallback entry now names `.claude/settings.local.json` as the effective wrapper surface; notes top-level writer commands on `UserPromptSubmit` + `SessionStart`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:124:### T-011 — `manual_testing_playbook/22--context-preservation-and-code-graph/252-cross-runtime-fallback.md` (Skill, MED)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:127:- **Applied report:** `applied/11-_opencode_skill_system-spec-kit_manual_testing_playbook_22--context-preservation-and-code-graph_252-cross-runtime-fallback_md.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:137:- **Change:** `SPECKIT_CODEX_HOOK_TIMEOUT_MS` (default 3000 ms) documented in §2 INFRASTRUCTURE with scope (Codex `UserPromptSubmit` hook + advisor subprocess) and timeout-fallback behavior (stale advisory on timeout).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:162:- **Prompt-embedded guard applied in all 13 agent prompts.** The dispatcher's POST-05 CODEX RECONCILIATION RULE instructed every agent to write the post-05 state (`codex_hooks`-gated native `SessionStart` + `UserPromptSubmit`, `/spec_kit:resume` as fallback) wherever its target file discusses Codex runtime hook capability. Drift check: `grep -n "no lifecycle hook" .opencode/skills/system-spec-kit/SKILL.md .opencode/skills/system-spec-kit/references/config/hook_system.md AGENTS.md` returns no results (verified post-edit).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:175:   - `skill_advisor.py` survivors in `.opencode/README.md` (4), `AGENTS.md` (5), system-spec-kit/README.md (0). Every surviving mention describes compatibility/fallback context — verified by line sample.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/008-docs-impact-remediation/implementation-summary.md:217:- Cross-file consistency gates (checklist §Cross-File Consistency Gates) pass: surviving `skill_advisor.py` references all describe fallback context; zero `.github/hooks/scripts` references remain in Copilot hook README or INSTALL_GUIDE.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/implementation-summary.md:67:Manual testing playbooks, feature catalogs, and README-style operator docs now describe Codex native `SessionStart` and `UserPromptSubmit` hooks as the primary path. Prompt-wrapper language remains only as a fallback for older or unavailable hook-policy deployments.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/007-hook-parity/003-codex-native-startup-advisor-hooks/implementation-summary.md:121:2. **CocoIndex timed out during implementation.** Code exploration used direct file reads and `rg` after semantic search timed out.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:8:  - "intent classifier fallback fix"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:76:- [x] T102 Instrument per-result token estimation; log estimated vs actual for 10 sample queries — diagnosed via inline `node` probe; bug was the `fallbackToStructuredBudget()` zero-fill, not estimator inflation
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:77:- [x] T103 Identify whether `data.content` stub-replacement is unconditional or conditional — confirmed unconditional zero-fill at original `mcp_server/handlers/memory-context.ts:482` `fallbackToStructuredBudget`; preserves none of the structurally-truncated survivors
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:78:- [x] T104 Fix: when `actualTokens / budgetTokens < 0.50`, return all results unmodified (`mcp_server/handlers/memory-context.ts:467-481` early-return guard) PLUS preserve survivors via the new `preservedAfterStructural` snapshot fed into `fallbackToStructuredBudget()` (`mcp_server/handlers/memory-context.ts:472-545, 696-705, 766-797`)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:108:- [ ] T602 [P] Add CocoIndex daemon health check at `/memory:search` invocation start
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:114:- [ ] T701 Wire 3-tier FTS fallback (FTS5 → BM25 → Grep) to trigger automatically when quality=gap
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:118:- [ ] T705 Regression test: weak query triggers fallback; output includes `fallback_tier` field
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:62:`Code_Environment/Public` already operates CocoIndex, Code Graph MCP, and Spec Kit Memory. It does not yet have a Mainframe-style shared query-result cache or a self-healing loop that patches stale code-context artifacts after agent failures. Contextador appears to address both concerns, but its claims (93% token reduction, "self-improving" knowledge, cross-agent reuse) need to be verified against the actual checked-in source instead of README marketing.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:83:- Direct comparison with current CocoIndex, Code Graph MCP, and Spec Kit Memory surfaces in this repository
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:133:| REQ-006 | Compare Contextador against current CocoIndex, Code Graph MCP, and Spec Kit Memory surfaces | research.md cites concrete repo paths in the comparison |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:204:| Multi-Agent | 8/15 | cli-codex delegation plus internal fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:216:| R-003 | Codex CLI unavailable mid-loop | H | L | Internal @deep-research fallback path |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md:258:- How granular is the `routeQuery(...)` decision between AI routing, keyword fallback, and fan-out, and is fan-out bounded?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/tasks.md:69:| R-007-P2-6 | Failure-fallback: stable `code` + warning log/metric (`query.ts:1121-1135`) | pending | P2 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:31:This packet no longer treats the earlier six-phase warning-hook prototype as the active plan. The canonical 2026-04-08 research narrowed the safe early continuity lane to two things: truthful predecessor ordering and a bounded producer-side metadata patch inside `session-stop.ts` and `hook-state.ts` after the FTS helper and forced-degrade tests exist [SOURCE: research.md §1; §2].
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:35:**Critical Dependencies**: The FTS capability helper and forced-degrade matrix are hard predecessors, and replay isolation is still required before any producer patch can be trusted [SOURCE: research.md §2]. The FTS capability cascade predecessor work is now explicitly owned by new phase 010-fts-capability-cascade-floor (R7, recommendations.md:65-73).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:69:- explicit predecessor dependency on FTS helper plus forced-degrade tests
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:84:- Confirm and document the predecessor dependency on the FTS capability helper plus truthful forced-degrade tests.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:120:| REQ-001 | Packet `002` records the FTS helper plus forced-degrade matrix as a hard predecessor. | `spec.md`, `plan.md`, and `tasks.md` all state that this packet is not the first continuity implementation packet and depends on the earlier FTS hardening lane [SOURCE: research.md §2]. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:160:| Dependency | **R-001: FTS prerequisite missing** | High | Keep the predecessor dependency explicit and do not claim this packet is ready to implement ahead of that lane [SOURCE: research.md §2]. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:206:- FTS predecessor not yet landed: packet cannot honestly claim implementation readiness.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/spec.md:229:| R-001 | Packet is implemented before the FTS helper plus forced-degrade predecessor lands. | High | Medium | Keep predecessor wording explicit across all packet docs. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/spec.md:64:Phase 010 and the 010/007 remediation pass shipped 33 closed findings spanning new operator-facing surfaces (detect_changes MCP tool, blast_radius enrichment, edge reason/step, affordance evidence, trust badges, memory_search causal cache invalidation). The baseline manual-testing-playbook scenarios written by 010/006 were authored before 010/007 hardened those surfaces. Two scenarios (014 detect_changes, 026 blast_radius) are now stale on adversarial paths and on the 010/007-added behaviour (path canonicalization, multi-file diff boundary, minConfidence, overflow detection, multi-subject seed preservation, failureFallback.code, edge reason/step sanitization, cache invalidation). One new scenario (memory_search cache invalidation on causal-edge mutation) is missing. Without this sync, the playbook is reassuring but not actually probing the surfaces operators rely on.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md:7:  - "search intelligence playbook"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md:74:The system-spec-kit "Search / Query / Intelligence" surfaces (memory_search, memory_context, code_graph_query, advisor_recommend, intent classifier, etc.) have grown organically across 26+ optimization packets. Sibling packet `005-memory-search-runtime-bugs` catalogs 17 defects observed in a single live session. We need a reproducible, cross-AI stress-test that quantifies how well the search intelligence performs under realistic prompt variation — not just bug-hunt, but ongoing quality regression.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md:77:Build a playbook that dispatches a fixed prompt corpus (9 scenarios × 3 prompt types) through cli-codex, cli-copilot, and cli-opencode, then scores each outcome against a 5-dimension rubric (correctness, tool selection, latency, token efficiency, hallucination). The asymmetry between cli-opencode (full Spec Kit Memory MCP runtime) and cli-codex/cli-copilot (external runtimes without our MCP) is the test's most informative axis — it reveals whether our search intelligence adds measurable value over off-the-shelf AI capabilities.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md:175:| Risk | CocoIndex daemon may be down during execution (REQ-012 from 005) | Medium | Pre-flight check; document the channel as unavailable in findings if so |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:63:  - Threaded a `preservedAfterStructural` snapshot through the structural truncation loop so when the second-pass `compactStructuredResult` cannot reach budget, the `fallbackToStructuredBudget()` candidate-state ladder now starts with a "preserve survivors" envelope (full + metadata-only) before falling through to the legacy zero-fill envelopes. Returned-count metadata is re-derived from the actual emitted payload to eliminate the historical mismatch where `returnedResultCount=2` shipped alongside `count:0,results:[]`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:67:  - Added a centroid-only confidence floor (0.30, per spec §4A "Default fallback") that fires only when the winning intent has zero keyword + zero regex-pattern evidence. Existing single-keyword classification stays at the legacy 0.08 floor, so the 80%-accuracy regression suite (T037 / T060 / C138) keeps passing while the "Semantic Search" → fix_bug bug is eliminated.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:93:- **Intent classifier returns `fix_bug` for "Semantic Search"** at confidence 0.098 — spec §4A documents `understand` as the no-match fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:159:4. **CocoIndex daemon health was not directly probed.** REQ-012 is based on the conversation transcript reporting daemon-not-running; verify the daemon's actual state before remediation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/implementation-summary.md:79:- Surrogate coverage: `code_graph/tests/code-graph-query-handler.vitest.ts` covers minConfidence, ambiguity, and failure-fallback paths; `code_graph/tests/code-graph-indexer.vitest.ts` covers reason/step round-trip; the read-path sanitizer at three sites (`code-graph-db.ts:756-805`, `query.ts:608-635`, `code-graph-context.ts:287-320`) is unit-tested via the indexer test fixture.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/implementation-summary.md:83:`manual_testing_playbook/13--memory-quality-and-indexing/203-memory-causal-trust-display.md` extended with **Block A** (existing badge derivation + profile preservation) and **Block B** (cache invalidation — R-007-12, plus a negative control verifying non-causal-boost callers are untouched).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/implementation-summary.md:85:- Surrogate coverage: `tests/memory/trust-badges.test.ts` (3/3 PASS post 010/007/T-E unskip); the cache invalidation surface is wired in `lib/storage/causal-edges.ts` (`causalEdgesGeneration` counter + `invalidateDegreeCache()` mutator) and `lib/search/search-utils.ts` (`causalEdgesGeneration?: number` gated by `enableCausalBoost === true`) and `handlers/memory-search.ts` (read + thread-through). No dedicated cache-invalidation vitest exists yet — this is identified as a future targeted test (out of scope for 011).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/implementation-summary.md:173:| 203 trust badges | B — cache invalidation (R-007-12) | UNAUTOMATABLE-by-design | `tests/causal-edges-unit.vitest.ts` (R-007-12 generation counter, 6 cases) **NEW** | PASS 6/6 | **PASS** |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/implementation-summary.md:214:| `manual_testing_playbook/13--memory-quality-and-indexing/203-memory-causal-trust-display.md` | Added Block B (cache invalidation + non-causal-boost negative control); SOURCE METADATA updated |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md:42:Run the autonomous sk-deep-research loop against Contextador's checked-in source under `external/`. Each iteration is a fresh agent dispatch that reads a focused slice of the codebase, writes findings to research/iterations/iteration-NNN.md (created at runtime), appends to the JSONL state log, and lets the reducer update findings-registry.json, the deep-research-strategy file, and the deep-research-dashboard file. cli-codex (gpt-5.4 high) is the preferred iteration runtime; the internal `@deep-research` agent is the fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md:81:- **Iteration Agent (fallback)**: Internal `@deep-research` LEAF agent dispatched via Task tool when Codex is unavailable.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md:324:- [x] cli-codex availability re-checked or fallback path armed
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md:345:2. Try the documented fallback (internal `@deep-research` agent)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:48:- **T-F (doc cleanup + query.ts micro-fixes + cache invalidation):** memory_search cache key includes causal-edge generation counter (folded only when `enableCausalBoost=true`); INSTALL_GUIDE Python smoke-test path fixed; tool count canonicalized to 51 (`TOOL_DEFINITIONS.length`) across all umbrella docs with explicit deferred-handlers-do-not-count note; broken `FEATURE_CATALOG_IN_SIMPLE_TERMS` link removed; `structural-indexer.ts` `runPhases` wrapped in try/catch/finally so error outcome metric emits; `query.ts` detects true overflow by comparing full-BFS-traversal size against `limit` BEFORE slicing (semantically equivalent to `limit + 1` — the BFS frontier is already over-collected, so no extra SQL request is needed; 008/D8 doc-fix correction), preserves seed nodes on multi-subject sibling failures, adds stable `failureFallback.code` + new `spec_kit.graph.blast_radius_failure_total` metric, and dedupes 4 switch branches via shared edge mapper; affordance debug counters (received/accepted/dropped_unsafe/dropped_empty/dropped_unknown_skill) added to TS + Python; 010/006 alias note for renumber. Closes R-007-12, 16, 17, 18, P2-2, P2-4, P2-5, P2-6, P2-7, P2-9, P2-12.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:270:#### R-007-12 — Memory_search cache invalidation on causal-edge mutations
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:291:- `/README.md` lines 7, 56, 1261, 1281, 1301 → "60 MCP tools" (51 spec_kit_memory + 7 code mode + 1 CocoIndex + 1 sequential thinking) and "51 tools, 7 layers + L8 graph/advisor + L9 coverage"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:319:`partialResult` now also carries those seeds so the failure-fallback payload
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/implementation-summary.md:325:- All five failure-fallback sites now set `code` deterministically.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:39:This plan converts packet `002` from a warning-consumer rollout into a producer-first prerequisite packet. The active lane is now: document the FTS predecessor honestly, verify replay isolation, patch bounded metadata in `session-stop.ts` plus `hook-state.ts`, and prove the seam is safe to hand to later continuity packets [SOURCE: research.md §1; §2; spec.md §3].
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:67:- Confirm the FTS helper plus forced-degrade predecessor remains explicit before claiming implementation readiness.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:76:| AI-ORDER-001 | Treat the FTS helper plus forced-degrade lane as a hard predecessor | Keeps packet ordering aligned to canonical research |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:116:- [x] Record FTS helper plus forced-degrade tests as the hard predecessor
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:152:| FTS capability helper plus forced-degrade tests | Internal predecessor | Yellow | Packet `002` cannot claim implementation readiness ahead of this lane |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:173:FTS helper + forced-degrade tests
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/plan.md:192:| Predecessor lane | None | Truthful FTS capability state | Replay and producer patch |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-manual-testing-playbook-coverage-and-run/plan.md:107:| Trust-badge cache invalidation cleanup | Per-test isolated DB OR explicit teardown step | Avoid leaving orphan causal edges in the shared fixture. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md:6:  - "search intelligence playbook plan"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md:51:A two-sub-phase architecture: 001 designs the playbook (scenarios, rubric, dispatch matrix, scripts), 002 executes it (runs the matrix, scores outputs, synthesizes findings). The asymmetry between cli-opencode (full Spec Kit Memory MCP) and cli-codex/cli-copilot (external runtimes) is the test's primary signal — it quantifies whether our search intelligence adds measurable value over off-the-shelf AI capabilities.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md:110:            ├──> Pre-flight: check CLIs installed, mem DB snapshot, CocoIndex daemon
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md:170:| CocoIndex daemon running | External | Red (down per 005 evidence) | Vector channel unavailable; document in findings |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/spec.md:96:- Parser-fallback infrastructure, deprecation alias matrices, glossary lint validators, pre-commit hooks. The prior research output produced a 4-PR plan optimized for a rename — none of that ships.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-memory-terminology/spec.md:199:- **Archived prior research** (`research_archive/rename-pivot-2026-04-26-pt-01/`) — 10 iterations of `/spec_kit:deep-research` scoped for a code+command+key rename; substrate (6-layer concept model, 21-tool inventory, Anthropic + MCP-registry collision analysis) is still useful but the recommendations (rename, alias matrix, parser-fallback, glossary-lint, 4-PR plan) are out-of-scope per the user's pivot. Kept for reference only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/tasks.md:71:- [x] T018 Iteration 6 - compare against current Public retrieval surfaces (CocoIndex, Code Graph MCP, Spec Kit Memory)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:3:description: "Make /memory:save planner-first (non-mutating) by default while preserving full-auto as an explicit fallback, retire the legacy [spec]/memory/*.md write path, and decouple freshness (graph-metadata refresh, spec-doc reindex, enrichment) from the hot save path via explicit follow-up APIs."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:9:  - "full-auto fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:45:      - "Implementation shipped planner-first default with explicit full-auto fallback; freshness work moved to explicit follow-up APIs."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:60:This packet delivers the end state implied by that analysis. `/memory:save` is planner-first by default: the handler computes the same route and legality data as before but stops short of mutation and returns structured planner output instead. `full-auto` is preserved as an explicit fallback via `SPECKIT_SAVE_PLANNER_MODE=full-auto`, with canonical atomic mutation, `POST_SAVE_FINGERPRINT` safety parity, same-path identity, and rollback intact. The legacy `[spec]/memory/*.md` write path is retired. Four previously default-on behaviors become explicit opt-in: `SPECKIT_ROUTER_TIER3_ENABLED`, `SPECKIT_QUALITY_AUTO_FIX`, `SPECKIT_RECONSOLIDATION_ENABLED`, `SPECKIT_POST_INSERT_ENRICHMENT_ENABLED`. Freshness becomes follow-up work via three new APIs: `refreshGraphMetadata`, `reindexSpecDocs`, `runEnrichmentBackfill`. `hybrid` is documented as reserved and currently behaves like `plan-only`. The content-router category contract is preserved with one honest, scoped exception: a Tier 3 default-disable and manual-review guard inside `content-router.ts`. 43 implementation tasks shipped under v3.4.1.0. A deep-review pass flagged 3 P0, 5 P1, and 1 P2 findings on router honesty, fallback safety parity, blocker classification, deferred-helper coverage, and changelog accuracy; all 9 were resolved before closeout.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:95:Ship a `/memory:save` contract that matches the evidence: planner-first by default so operators see the plan before anything changes, full-auto preserved as an explicit fallback for the cases that still need it, and freshness work moved to callable follow-up APIs so every save doesn't pay for work it doesn't need. Retire the legacy `[spec]/memory/*.md` write path end-to-end. Make four previously default-on behaviors opt-in via per-subsystem env flags, preserve `hybrid` as a reserved value, and record the scoped router exception honestly so docs match the code.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:106:- Preserve the `full-auto` writer path as an explicit fallback activated via `SPECKIT_SAVE_PLANNER_MODE=full-auto` with canonical atomic mutation, promotion, rollback, and same-path identity intact.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:117:- Update tests across `memory-save`, `content-router`, `quality-loop`, `save-quality-gate`, reconsolidation-bridge, reconsolidation, assistive-reconsolidation, chunking, graph-refresh, thin-continuity, planner UX, CLI target authority, and memory-save integration to prove planner-default + fallback end-to-end behavior.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:134:| Canonical writer reuse | `create-record.ts`, `atomic-index-memory.ts`, `thin-continuity-record.ts`, `post-insert.ts` | Reuse/preserve | Core writer earns its cost; fallback path depends on stable interfaces |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:137:| Reconsolidation | `reconsolidation-bridge.ts` | Gate | Move behind explicit opt-in or fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:139:| Command docs | `../../../../command/memory/save.md`, `../../../../command/memory/manage.md` | Modify | Document planner-first default, fallback, and follow-up freshness actions |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:143:| Test surfaces | See tasks.md §Testing — broad vitest + transcript prototype sweep | Modify | Prove planner-default, fallback parity, gate behavior, continuity upserts |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:162:| REQ-002 | Explicit `full-auto` must remain available as fallback. | Setting `SPECKIT_SAVE_PLANNER_MODE=full-auto` runs the canonical atomic writer with promotion, rollback, and same-path identity intact. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:166:| REQ-006 | Reconsolidation-on-save must be explicit opt-in. | Default path never triggers reconsolidation; `SPECKIT_RECONSOLIDATION_ENABLED=false` is default; opt-in via env flag or fallback execution. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:170:| REQ-010 | Fallback safety parity must be preserved. | `POST_SAVE_FINGERPRINT` parity is restored on the full-auto path; fallback tests prove atomic mutation + rollback semantics match the pre-packet writer. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:174:| REQ-014 | Shipped documentation must match the runtime contract. | `/memory:save` docs, `ENV_REFERENCE.md`, release notes, and templates describe planner-first default, explicit fallback, follow-up APIs, reserved `hybrid`, and the scoped router exception honestly. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:198:| REQ-028 | Env reference diagrams and tables stay readable. | Env reference uses consistent wording for default/opt-in, reserved, and fallback. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:199:| REQ-029 | Chunking stays a size-driven fallback. | Chunking remains a fallback behavior for oversized inputs; not a default dependency. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:213:- **SC-006**: `SPECKIT_RECONSOLIDATION_ENABLED=false` is the default; reconsolidation is available via opt-in or fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:236:| Dependency | Canonical atomic writer stability | High | Preserve as-is; fallback path relies on it |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:238:| Dependency | Vitest + transcript fixtures | High | Broad test sweep covers planner, fallback, router, quality, reconsolidation, enrichment, follow-up APIs, continuity |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:241:| Risk | Full-auto fallback loses `POST_SAVE_FINGERPRINT` parity | High | Explicit remediation (P015-R002) restores parity; fallback tests prove it |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:257:- **NFR-C02**: The full-auto fallback must match pre-packet writer behavior for atomic mutation and rollback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:258:- **NFR-C03**: Router target authority must be identical between planner and fallback paths for the same inputs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:274:- **NFR-M01**: The canonical atomic writer must remain the single mutation mechanism used by the fallback path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:287:- **NFR-U02**: Operator docs must describe planner-first default, explicit fallback, and follow-up APIs in consistent language.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:298:- **NFR-TH01**: Transcript snapshots retained in packet-local `scratch/` or `review/` directories must not contain raw API keys, bearer tokens, or user credentials. The planner and fallback paths must strip or redact credential-shaped strings before writing any transcript artifact to disk.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:318:- A reader assumes "planner-first" means `full-auto` was deleted → docs must be explicit that `full-auto` remains available as fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:330:| Risk | 21/25 | High narrative + correctness risk because the packet changes the default save contract and must preserve fallback safety parity |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:363:### US-002: Full-auto fallback
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:439:- [x] Implementation truth preserved: planner-first default + explicit fallback + follow-up APIs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:457:| Tooling operators | `/memory:save` users | Medium | Need clear default, fallback, and follow-up behavior |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:466:- Shipped planner-first default for `/memory:save` with explicit `full-auto` fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:484:### Scenario 2: Full-auto fallback remains available
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:494:**Then** they understand that these behaviors moved to explicit follow-up actions or fallback mode rather than disappearing.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:500:**Then** they see `plan-only` as default, `full-auto` as explicit fallback, and `hybrid` as reserved.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:518:**Then** they see that reconsolidation remains available only through explicit opt-in or fallback behavior.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:541:| Research | Could the save system be redesigned without replacing the core writer? | Yes. The research recommended a planner-first wrapper around the existing canonical prep and fallback writer. | `research/014-research-snapshot/research.md`, `research/014-research-snapshot/iterations/iteration-020.md` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:545:| Implementation | Was the old full-auto path deleted? | No. It remained available as explicit `full-auto` fallback. | `review/015-deep-review-snapshot/primary-docs/spec.md`, `review/015-deep-review-snapshot/primary-docs/implementation-summary.md`, `../../../../changelog/01--system-spec-kit/v3.4.1.0.md` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/spec.md:548:| Review | What did the first deep-review pass find? | 3 P0, 5 P1, and 1 P2 findings across router honesty, fallback parity, blocker classification, coverage, and doc drift. | `review/015-deep-review-snapshot/review-report.md`, `review/015-deep-review-snapshot/deep-review-findings-registry.json` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/spec.md:72:- Pre-flight contract (CLIs installed, authenticated, CocoIndex daemon status, DB snapshot)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/spec.md:141:│    • Check CocoIndex daemon         │
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/tasks.md:7:  - "search intelligence test tasks"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md:43:This phase produced a deep, source-grounded research packet on Contextador, the Bun-based MCP query server. The headline takeaway is that Public already wins on retrieval substrate (CocoIndex semantic, Code Graph structural, Spec Kit Memory continuity), so Contextador's surviving value is runtime retrieval ergonomics, not a replacement retrieval engine. The 93% token-reduction claim is estimated from fixed constants in `external/src/lib/core/stats.ts:26-28`, not benchmarked, and the served `context` payload is narrower than the README suggests. After the 20-iteration closeout, source coverage remained approximately 84.8% of files in `external/src/` and approximately 100% of non-test production source files, with the extension pass focused on question closure rather than broader production-file discovery.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md:55:`research/research.md` Section 4 contains the cross-comparison table against CocoIndex, Code Graph MCP, and Spec Kit Memory, with NEW/DUPLICATE/HYBRID/NEGATIVE verdicts per capability. Section 5 contains the cross-phase ownership table for 002-codesight, 003-contextador, and 004-graphify, establishing that 003 owns runtime retrieval ergonomics, 002 owns scan-time analysis and artifact generation, and 004 owns graph and provenance intelligence.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md:64:The phase ran the autonomous sk-deep-research loop with cli-codex (gpt-5.4 high) preferred for the primary research pass. Codex was invoked via `codex exec --model gpt-5.4 -c model_reasoning_effort="high" --sandbox workspace-write --skip-git-repo-check -` with prompts piped via stdin from temporary prompt files under `/tmp`. After each iteration, the reducer script `node .opencode/skills/sk-deep-research/scripts/reduce-state.cjs` synchronized findings-registry.json, the strategy file, and the dashboard file. The packet then received a local extension from 13 to 20 total iterations, closing every tracked question, refreshing reducer-owned artifacts, and updating the canonical synthesis. Zero internal `@deep-research` fallback was required across the full lineage.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md:78:| Internal `@deep-research` retained as documented fallback | Resilience if Codex CLI failed mid-loop; in practice fallback was not needed |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/plan.md:142:| D3 | `workflow.ts:1271-1295`, `semantic-signal-extractor.ts:260-284` | Remove unconditional folder-token append (keep `ensureMinTriggerPhrases()` low-count fallback); require source adjacency for topic bigrams | Medium — overfilter risk |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/plan.md:143:| D2 | `decision-extractor.ts:182-185`, `:367-388` | Add raw `keyDecisions` reader before lexical fallback; precedence hardening only when authoritative arrays exist (do NOT blanket-disable lexical) | High — could regress degraded payloads if scoped wrong |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:3:description: "Milestoned delivery (M1-M10) for the planner-first /memory:save contract: audit + retirement of the legacy [spec]/memory/*.md write path, 20-iteration relevance research, planner contract + fallback implementation, routing/quality/reconsolidation/enrichment trim, follow-up API extraction, verification, release alignment, and deep-review remediation."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:34:      - "The planner-first default + explicit fallback architecture preserves the canonical writer while eliminating the default-path overreach."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:60:The plan delivers a planner-first default for `/memory:save` while preserving the canonical atomic writer as an explicit fallback. It retires the legacy `[spec]/memory/*.md` write path end-to-end, gates four previously default-on save-path behaviors behind explicit env flags, and extracts freshness into three explicit follow-up APIs. Delivery runs through 10 sequential milestones: audit surface + classification, retirement cutover, relevance research, planner contract build-out, routing + quality trim, verification + transcript prototypes, release alignment, and deep-review remediation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:99:- [x] Full-auto fallback tests prove atomic mutation + rollback + `POST_SAVE_FINGERPRINT` parity.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:111:Planner-first wrapper around the preserved canonical atomic writer. The default path computes route + legality + advisory data and returns structured planner output without mutating files. An explicit fallback path activates the canonical writer with full atomic semantics intact. Freshness work lives in callable follow-up APIs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:119:- **Reconsolidation (`reconsolidation-bridge.ts`)**: Gated behind `SPECKIT_RECONSOLIDATION_ENABLED=true` or explicit fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:122:- **Env reference + command docs + release notes**: Aligned to describe default/opt-in/reserved/fallback consistently.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:203:- [x] T001-T005 Add planner-default and fallback flag definitions; planner response interfaces; response serialization helpers; planner blocker and advisory response helpers.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:204:- [x] T006-T008 Make `generate-context.ts` request planner-first behavior by default; update `/memory:save` docs; make `memory-save.ts` return planner output by default with explicit fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:213:- [x] T023-T026 Gate reconsolidation behind explicit flag/fallback; move default-path enrichment to explicit follow-up behavior; preserve same-path lineage; keep chunking as size-driven fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:220:- [x] T035-T037 Memory-save integration tests for planner-default plus fallback end-to-end; planner UX regression tests for readable output; thin-continuity tests for normalization + upsert parity.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:223:- [x] T041-T043 Review structural parity between `/memory:save` + `AGENTS.md` + system-spec-kit skill doc; review fallback safety against `atomic-index-memory.ts` + `create-record.ts`; review transcript mismatches and convert unresolved issues into follow-on tasks.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:234:- **F002 [P0]**: fallback safety parity → resolved by reinstating `POST_SAVE_FINGERPRINT`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:253:| Runtime contract tests | Planner-default + fallback parity + router + quality + follow-up APIs | Vitest suites + targeted sweeps | `review/015-deep-review-snapshot/primary-docs/tasks.md`, `review/015-deep-review-snapshot/primary-docs/checklist.md`, `review/015-deep-review-snapshot/primary-docs/implementation-summary.md` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:312:- **Trigger**: Planner-default mutates under some branch, fallback loses atomic safety parity, router preservation claim contradicts code, or remediation reopens a closed finding.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:314:- **Data reversal**: No data migrations. Vector DB schema unchanged; saves still use the canonical atomic writer when fallback is active.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:393:- [x] Full-auto fallback tests pass with `POST_SAVE_FINGERPRINT` parity
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:399:1. Revert planner commits atomically; fallback behavior continues via canonical writer.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:456:| Planner contract | Research | Non-mutating default + fallback | Trim milestones |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:469:4. **Ship the planner-first default + full-auto fallback** — critical because it is the operator-facing contract.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:488:| M6 | Planner contract | Planner-first default + fallback + shared types | Runtime handler |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:532:If a runtime change regresses fallback safety, revert and patch the specific subsystem before re-running the verification sweep.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:584:| SYNC-003 | Runtime complete | W-C + W-D | Tests cover default + fallback + gated subsystems |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:611:- The canonical atomic writer is the single mutation mechanism; fallback preserves atomic semantics.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/plan.md:622:| Runtime correctness | Complete | Planner default non-mutating + fallback atomic parity |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/plan.md:78:- **Pre-flight check** (`scripts/preflight.sh`) — verify CLIs + auth + DB snapshot + CocoIndex daemon
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/plan.md:157:| CocoIndex daemon | External | Red per 005 evidence | Vector channel unavailable; document |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/implementation-summary.md:6:  - "search intelligence stress test summary"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/implementation-summary.md:60:- **Asymmetry as signal**: cli-opencode has full Spec Kit Memory MCP runtime; cli-codex and cli-copilot do not. The delta quantifies how much value our search intelligence adds vs off-the-shelf AI.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/implementation-summary.md:129:4. **CocoIndex daemon may be down** — 005 reports the daemon was unreachable. If still down at execution, the vector retrieval channel will be absent; document as a known constraint in findings.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/001-cache-warning-hooks/tasks.md:47:- [x] T001 [P0] Record FTS helper plus forced-degrade tests as the hard predecessor (`spec.md`, `plan.md`, `research.md`) [EVIDENCE: packet docs now name the FTS helper plus forced-degrade lane as the hard predecessor and strict validation passes.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:145:- **Target tools**: `memory_context` (auto mode), with FTS5 fallback if vector channel weak
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:159:- **Target tools**: `code_graph_query` (structural traversal), fallback to `cocoindex_search` or grep
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:185:- **Prompt**: `I'm debugging the search bug — what should I look at first?`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:187:- **Target tools**: `advisor_recommend`, `session_bootstrap`, `memory_match_triggers` on "search bug"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:212:- **2**: Optimal tool selection per expected behavior; uses CocoIndex/code_graph/memory_search correctly per scenario
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md:394:| Risk | Q1 expects code-graph data; if graph is empty (per startup hook) the scenario degrades | Medium | Document fallback: if code_graph unavailable, scenario reverts to grep-based query |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/tasks.md:69:- [ ] T103 Verify CocoIndex daemon status; document if down
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:148:- [x] **P015-T001** Add planner-default and fallback flag definitions. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:149:- [x] **P015-T002** Document planner, fallback, and deferred follow-up flags. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:154:- [x] **P015-T007** Update `/memory:save` docs for planner-first default and fallback. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:155:- [x] **P015-T008** Make `memory-save.ts` return planner output by default with explicit fallback. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:170:- [x] **P015-T023** Gate reconsolidation-on-save behind explicit flags or fallback. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:173:- [x] **P015-T026** Keep chunking as a size-driven fallback instead of a default dependency. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:179:- [x] **P015-T032** Update assistive-reconsolidation tests so assistive recommendations remain deferred or fallback-only. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:180:- [x] **P015-T033** Update chunking tests for size-driven fallback behavior. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:182:- [x] **P015-T035** Update memory-save integration tests for planner-default plus fallback end-to-end behavior. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:189:- [x] **P015-T042** Review fallback safety against `atomic-index-memory.ts` and `create-record.ts`. Evidence: `review/015-deep-review-snapshot/primary-docs/tasks.md`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:239:- [x] Full-auto fallback tests pass (atomic mutation + rollback + `POST_SAVE_FINGERPRINT` parity)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/tasks.md:241:- [x] `/memory:save` docs, `ENV_REFERENCE.md`, templates, and v3.4.1.0 release notes align on default/opt-in/reserved/fallback vocabulary
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/spec.md:92:- External Project graph persistence and query model: LadybugDB adapter, schema, hybrid BM25/vector search, Cypher escape hatch, staleness handling, and registry behavior.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:32:      - "Packet is complete; shipped contract is planner-first default with explicit full-auto fallback."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:58:`/memory:save` is planner-first by default. Invoking it now returns a structured planner response — routes, legality blockers, advisories, follow-up actions — and mutates no files on disk. Operators who still need automatic mutation can opt in by setting `SPECKIT_SAVE_PLANNER_MODE=full-auto`, which runs the canonical atomic writer with `POST_SAVE_FINGERPRINT` safety parity, same-path identity, promotion, and rollback intact. `hybrid` is reserved and currently behaves like `plan-only`. The legacy `[spec]/memory/*.md` write path is retired runtime-wide. Four previously default-on save-path behaviors are now explicit opt-in: Tier 3 routing (`SPECKIT_ROUTER_TIER3_ENABLED`), quality-loop auto-fix (`SPECKIT_QUALITY_AUTO_FIX`), reconsolidation-on-save (`SPECKIT_RECONSOLIDATION_ENABLED`), and post-insert enrichment (`SPECKIT_POST_INSERT_ENRICHMENT_ENABLED`). Freshness is callable via three new follow-up APIs: `refreshGraphMetadata`, `reindexSpecDocs`, `runEnrichmentBackfill`. Docs, env reference, and release notes all agree on the same default/opt-in/reserved/fallback vocabulary.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:70:43 of 43 tasks completed under v3.4.1.0. The planner-first contract + flag plumbing (M1) landed before the trim work (M2-M4) so the schema was stable by the time routing, quality, reconsolidation, and enrichment moved behind env gates. Follow-up APIs (`refreshGraphMetadata`, `reindexSpecDocs`, `runEnrichmentBackfill`) expose freshness as callable work instead of baked-in side effects. Targeted tests covered planner-default behavior, fallback parity, router deterministic default, quality advisory output, structural blocker preservation, reconsolidation opt-in, enrichment deferral, continuity upsert parity, planner UX readability, CLI target authority, and end-to-end integration. Three real session transcripts exercised planner-first behavior before closeout.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:74:Deep review flagged 9 findings (3 P0, 5 P1, 1 P2) covering router honesty, fallback safety parity, blocker classification, deferred-helper status, coverage gaps, follow-up tool naming, env reference drift, and release-note accuracy:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:134:| Ship planner-first default + explicit full-auto fallback | Non-mutating default is reviewable; full-auto remains available for automation that depends on it |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:135:| Preserve the canonical atomic writer | The proven mutation mechanism earns its cost; fallback must stay safe |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/004-memory-save-rewrite/implementation-summary.md:153:| Implementation carry-over | PASS — packet preserves planner-first default, explicit fallback, follow-up APIs, and 43 completed tasks |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/tasks.md:100:| T301 | D3a — Remove unconditional folder-token append in `core/workflow.ts:1271-1295` (keep `ensureMinTriggerPhrases()` low-count fallback) | SUPERSEDED — See implementation-summary.md §003-sanitization-precedence |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/tasks.md:102:| T303 | D2 — Add raw `keyDecisions` reader to `extractors/decision-extractor.ts:182-185` before lexical fallback | SUPERSEDED — See implementation-summary.md §003-sanitization-precedence |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/tasks.md:103:| T304 | D2 — Implement precedence hardening (do NOT blanket-disable lexical fallback) at `:367-388` | SUPERSEDED — See implementation-summary.md §003-sanitization-precedence |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:61:Phase 3 introduced the trigger-phrase sanitizer, topic-adjacency guardrails, and the authored-decision precedence gate. That closed D3 and D2 while preserving degraded-payload fallback where it still belongs.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:148:- **P1-003** `decision-extractor.ts:205` — raw `keyDecisions` entries validated before gaining authority; `JSON.stringify(manualObj)` fallback removed; lexical fallback only suppressed when a valid authored decision survives
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:248:- Created `trigger-phrase-sanitizer.ts` encoding empirical D3 junk-class and allowlist rules; integrated into `workflow.ts` while preserving `ensureMinTriggerPhrases()` low-count fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:249:- `semantic-signal-extractor.ts` rejects non-adjacent synthetic bigrams; `decision-extractor.ts` now gates lexical fallback behind authored-array precedence (degraded-payload fallback preserved).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:251:- Key decision: lexical fallback not globally disabled — only suppressed when authoritative arrays exist.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation/implementation-summary.md:321:- Lane 5: Explicit `causalLinks` pass-through; D5 linker and reviewer share one continuation contract with description-aware fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/implementation-summary.md:123:3. **CocoIndex bootstrap timed out.** The synthesis relies on direct reads, reducer state, and source citations instead.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:3:description: "Read-only 20-iteration research investigation of the Claudest external Claude Code plugin marketplace and the claude-memory plugin (FTS5/BM25 conversation recall, SessionStart context injection, extract-learnings consolidation, get-token-insights observability) to identify adopt/prototype/reject patterns and execution-ready follow-on packet contracts for Code_Environment/Public's Spec Kit Memory and Code Graph stack."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:30:Phase 5 of `001-research-graph-context-systems` is a read-only audit of the Claudest external Claude Code plugin marketplace (`external/.claude-plugin/marketplace.json`) and its flagship `claude-memory` plugin to translate concrete patterns into actionable improvements for `Code_Environment/Public`. The plugin is studied at function level: the v3 SQLite schema with branch-aware BM25/FTS5 recall, the Stop/SessionStart hook chain that pre-computes branch summaries and injects them into the next session via `hookSpecificOutput.additionalContext`, the `extract-learnings` consolidation pipeline split between `memory-auditor` and `signal-discoverer`, and the `get-token-insights` skill that ingests Claude JSONL session logs into a relational analytics model with embedded HTML dashboard. The deliverable is an evidence-grounded `adopt now` / `prototype later` / `reject` matrix grounded in `external/plugins/...` file:line citations across 20 deep-research iterations, plus packet-ready briefs and an execution-ready follow-on packet roadmap for Public's FTS, analytics, SessionStart, and consolidation seams.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:32:**Key Decisions**: Keep the original 12-iteration cli-codex lineage intact, then reopen the packet in `completed-continue` mode and extend it to 20 total iterations. Generation 1 (iters 1-12) answered the original charter and converted Q10 into a usable handoff package. Generation 2 (iters 13-20) translated those conclusions into implementation-facing contracts: FTS helper scope, forced-degrade tests, Stop-hook metadata patch, normalized analytics replay shape, SessionStart fast-path placement, verifier/discoverer split mapping, token-observability contracts, and a dependency-ordered packet roadmap.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:62:`Code_Environment/Public` already has Spec Kit Memory MCP (semantic search, intent-aware routing, importance tiers), Code Graph for structural queries, the `024/002` SessionStart hook for source-aware routing, and the `024/003` Stop hook for token snapshots and session summaries. But Public lacks (a) a runtime FTS capability cascade that degrades from FTS5/BM25 → FTS4 → LIKE rather than failing silently when the SQLite build varies, (b) a Stop-time pre-computed `context_summary` cached on per-session state for SessionStart fast-path injection, (c) an explicit auditor-vs-discoverer split in its consolidation flow, and (d) cross-session analytics-grade storage with cache-tier-aware pricing normalization. Without an evidence-grounded survey of how Claudest's `claude-memory` plugin actually implements these patterns at function level, any port would risk importing the wrong patterns or missing the load-bearing implementation nuances.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:79:- BM25/FTS5 → FTS4 → LIKE recall cascade in `external/plugins/claude-memory/skills/recall-conversations/scripts/search_conversations.py`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:87:- Continuation charter (iters 8-12): Q10 synthesis matrix, sequencing against existing Public packets, smallest-safe-v1 slicing, packet-ready briefs (FTS cascade + normalized analytics), and uncertainty closeout against Public's `mcp_server/lib/search/sqlite-fts.ts` + `mcp_server/hooks/claude/session-stop.ts`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:88:- Completed-continue execution charter (iters 13-20): FTS helper contract, forced-degrade verification matrix, Stop-hook transcript identity/cache token patch, normalized analytics replay schema, SessionStart cached-summary placement, verifier/discoverer workflow split, token-observability JSON contracts, and dependency-ordered implementation roadmap.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:112:| REQ-002 | P0 | Map the v3 SQLite schema in `db.py` (projects/sessions/branches/messages/branch_messages/import_log + `branches_fts`/`messages_fts`) and explain why branch-level aggregation matters for BM25 ranking |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:113:| REQ-003 | P0 | Trace `detect_fts_support()` and the FTS5/FTS4/LIKE cascade in `search_conversations.py` line by line |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:121:| REQ-011 | P1 | Continuation charter: stress-test sequencing against existing Public packets, define smallest safe v1 per adopt-now lane, write packet-ready briefs for FTS capability cascade + normalized analytics tables, and resolve all open implementation uncertainties against actual Public source |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:122:| REQ-012 | P1 | Land the closeout: confirm whether Public has lower-level FTS capability probe than `memory_fts` table existence and whether `024/003` Stop-hook payload persists transcript identity for normalized replay |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:135:- Two packet-ready briefs (FTS capability cascade + normalized analytics tables) live in `research/research.md` §18.4 with named Public file surfaces, forced-degrade matrices, and rollback plans.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:165:- Public packets `023/013` (FTS5 fix), `024/002` (SessionStart hook), `024/003` (Stop hook tracking), `022/008` (signal extraction) — referenced as substrate dependencies in the sequencing analysis.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:218:**As a** Code_Environment/Public maintainer planning the next FTS or analytics packet
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:230:**Acceptance**: research/research.md §18.4 contains Brief A (FTS capability cascade) and Brief B (normalized analytics tables), each with goal/non-goal/contract/forced-degrade matrix/rollback/risks/uncertainty resolution.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:247:**Scenario 2 (REQ-003 — FTS cascade trace)**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:250:- **Then** the iteration file documents the FTS5 BM25 ranking branch, the FTS4 MATCH+recency branch, and the LIKE %term% branch with line citations and explicit query rewriting rules
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md:268:- **Given** Brief A and Brief B contain implementation uncertainties about Public's lower-level FTS probe and `024/003` payload shape
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md:78:- [x] T205 Iteration 11: packet-ready briefs (Brief A FTS cascade + Brief B normalized analytics tables) — cli-codex gpt-5.4 high → 9 findings, newInfoRatio 0.31
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md:88:- [x] T212 Iteration 13: FTS capability helper contract + caller migration plan — Codex gpt-5.4 high → 6 findings, newInfoRatio 0.44
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md:89:- [x] T213 Iteration 14: forced-degrade FTS test matrix — Codex gpt-5.4 high → 5 findings, newInfoRatio 0.39
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md:124:- [x] Two packet-ready briefs in `research/research.md` §18.4 (Brief A FTS capability cascade + Brief B normalized analytics tables)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:30:Phase 4 of `001-research-graph-context-systems` is a read-only audit of the graphify external Python skill to translate its two-pass codebase knowledge graph patterns into concrete improvements for Code_Environment/Public's existing structural retrieval stack (Code Graph MCP, CocoIndex, Spec Kit Memory). The deliverable is an evidence-backed Adopt/Adapt/Reject table grounded in specific `external/graphify/` file:line citations, not a generic feature inventory. No source files outside this spec folder are modified during the research phase.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:32:**Key Decisions**: Use a 20-iteration two-wave deep-research loop; preserve K1 to K42 finding lineage across the original run plus completed-continue wave; keep Code Graph MCP and CocoIndex as the platform while translating graphify patterns into additive rollout guidance for Public.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:61:Public already has Code Graph MCP for structural code queries (442.9K nodes, 225.4K edges), CocoIndex for semantic retrieval, Spec Kit Memory for persistent context, and hook-based context injection patterns. It does NOT have community-clustered knowledge graphs, multimodal artifact extraction (PDFs, images), evidence-tagged provenance for retrieval edges, or a PreToolUse hook that nudges Claude away from raw Grep when a structural index exists. graphify ships all four capabilities in a small Python package, so it is the closest external candidate to study before deciding which patterns to bring inside Public.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:65:Produce an evidence-backed translation layer that tells Public exactly which graphify patterns to adopt directly, adapt into existing surfaces, or reject as duplicative or non-applicable, with every recommendation tied to `external/graphify/` file:line evidence and to a specific Public surface (Code Graph MCP, CocoIndex, Spec Kit Memory, hooks, or CLAUDE.md).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:93:- Wholesale replacement of Code Graph MCP or CocoIndex - prompt Don'ts forbid it unless graphify clearly solves something they cannot
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:130:| REQ-009 | Compare graphify against Public's existing Code Graph MCP and CocoIndex without duplicating phase 002 or phase 003 findings | research.md section 10 has a capability matrix; section 11 documents cross-phase deduplication |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md:288:1. **Given** any Adopt row in research/research.md section 12, **When** I read the "Concrete Adoption Plan" column, **Then** I see a specific Public surface (for example `code_graph_query` response payload, project hooks, CocoIndex incremental update path).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:41:Run a 20-iteration deep-research loop against `external/` to translate Claudest's claude-memory plugin (v3 SQLite schema with branch-aware BM25/FTS5 recall, Stop/SessionStart hook chain with cached `context_summary` fast path, `extract-learnings` consolidation with `memory-auditor`/`signal-discoverer` split) and the `get-token-insights` skill into Public-actionable adopt/prototype/reject recommendations, packet-ready briefs, and implementation-ready follow-on contracts. Iterations 1-12 dispatched through `cli-codex gpt-5.4 high --full-auto --sandbox workspace-write`; iteration 7 converged the original charter, then iterations 8-12 deepened Q10 into matrix, sequencing, v1 slicing, packet briefs, and uncertainty closeout. The packet was then reopened in `completed-continue` mode for iterations 13-20, which converted the first continuation into concrete implementation seams: FTS capability helper scope, forced-degrade tests, Stop-hook metadata patch, normalized analytics replay schema, SessionStart fast-path placement, verifier/discoverer split mapping, portable token-observability contracts, and a dependency-ordered roadmap. Externalized state in `research/deep-research-{config,state,strategy,dashboard,findings-registry}` survives crash and resume; reducer runs after every iteration to keep registry, dashboard, and machine-owned strategy sections in sync.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:64:- [x] Two packet-ready briefs delivered in §18.4 (Brief A: FTS capability cascade; Brief B: Normalized analytics tables)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:148:5. Iteration 11: packet-ready briefs (Brief A FTS capability cascade + Brief B normalized analytics tables, with named Public file surfaces).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:154:2. Iteration 13: FTS capability helper contract + caller migration plan.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:155:3. Iteration 14: forced-degrade FTS verification matrix.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:204:- Public packets `023/013` (FTS5 fix), `024/002` (SessionStart hook), `024/003` (Stop hook tracking), `022/008` (signal extraction) — referenced as substrate dependencies.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md:382:4. If unblockable: switch engine (cli-codex to native-fallback or vice versa), log `engine_switch` event, retry once
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:66:| 11 | packet-ready briefs (FTS cascade + normalized analytics) | cli-codex gpt-5.4 high | 9 | 0.31 | (refines Q10) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:68:| 13 | FTS capability helper contract + caller migration plan | codex gpt-5.4 high | 6 | 0.44 | Q11 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:69:| 14 | forced-degrade FTS test matrix | codex gpt-5.4 high | 5 | 0.39 | Q12 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:83:3. **Branch-aware BM25 is the load-bearing recall pattern** — the v3 schema stores messages once and treats branches as a separate index with `aggregated_content` + `context_summary`. BM25 ranks whole branches, then hydration recovers exact message sequences. (iter 2)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:85:5. **SessionStart fast path is a Stop-time precomputed `context_summary`, not on-demand** — the cached-summary cascade in `summarizer.py` is what makes injection cheap; without the precomputed cache, the fallback path must rebuild the summary inline. (iter 3)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:90:10. **The first follow-on packet should be the FTS capability cascade, narrowed to `fts5_bm25 → like_scan`** — Brief A in §18.4 with iter 12 closeout: Public still creates only `memory_fts USING fts5`, so an `fts4_match` lane requires schema work; the safe v1 is FTS5 + LIKE plus a shared lexical-capability helper in `mcp_server/lib/search/sqlite-fts.ts`. (iter 11 + iter 12)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:96:- **Adopt now**: branch-aware BM25/FTS5 cascade (probe-first, explicit query branches), cached-summary SessionStart fast path (Stop-time write + SessionStart read augmentation), auditor/discoverer split for consolidation, cache-cliff metric, per-tier pricing/cache cost normalization, dashboard JSON contracts (`trends`, `skill_usage`, `agent_delegation`, `hook_performance`, `findings`, `recommendations`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:102:**Brief A: FTS capability cascade** (`research/research.md` §18.4) — narrowed v1 to `fts5_bm25 → like_scan` with explicit backend metadata; central capability helper in `mcp_server/lib/search/sqlite-fts.ts`; consumers in `mcp_server/lib/search/hybrid-search.ts` and `mcp_server/lib/search/graph-search-fn.ts`; forced-degrade verification matrix; rollback plan via narrow feature flag.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:106:**Execution-ready roadmap** (`research/research.md` §19) — explicit packet order: FTS helper and degrade tests, Stop-hook metadata patch, analytics reader, SessionStart fast path, verifier/discoverer workflow split, then token-insight contracts.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:147:4. **Generation 2 converted those briefs into packet contracts**: FTS helper scope (iter 13), forced-degrade tests (iter 14), Stop-hook metadata patch (iter 15), normalized analytics reader (iter 16), SessionStart fast path placement (iter 17), verifier/discoverer workflow split (iter 18), portable token contracts (iter 19), and final packet ordering (iter 20).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:148:5. **First follow-on packet remains the FTS capability cascade, narrowed**: generation 2 confirmed the first packet should still be `fts5_bm25 → like_scan` plus typed degrade metadata and tests, with no default `fts4_match` promise.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:161:- [x] Two packet-ready briefs (Brief A FTS cascade + Brief B normalized analytics) in `research/research.md` §18.4
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md:180:- **`fts4_match` lane is gated on schema work**: The Brief A v1 was narrowed to `fts5_bm25 → like_scan` because Public still provisions only `memory_fts USING fts5` (`mcp_server/lib/search/vector-index-schema.ts:2382-2412`). Restoring an `fts4_match` lane requires alternate FTS4 schema creation in the same packet.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/implementation-summary.md:3:description: "20 total deep-research iterations across two waves produced 42 consolidated findings (K1 to K42) and a phased rollout translation for Public's Code Graph, CocoIndex, hooks, validation, and scoring surfaces."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/implementation-summary.md:43:You can now point any Public maintainer at `research/research.md` and get a line-grounded translation layer that says exactly which graphify patterns to adopt, adapt, or reject for Code Graph MCP, CocoIndex, Spec Kit Memory, hooks, validation, and scoring surfaces. The audit now covers 20 total iterations across two waves, produced 42 consolidated K-findings (K1 through K42), and answered all 22 research questions. Reading section 12 plus sections 13.A and 13.B gives the full recommendation and rollout set without backfilling assumptions.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/implementation-summary.md:125:1. **codex parallel-job API contention is unmitigated.** The iter 2 starvation incident proved that codex-cli sequential dispatch is the safe pattern for this loop. Parallel codex dispatches across iterations are NOT supported by this workflow. Workaround: dispatch iterations sequentially, log `engine_switch` events when fallback is needed.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/spec.md:79:- **Cluster E — runtime-specific observability gap** (R52-P1-002): The Copilot hook runtime is missing both `compact-cache.ts` (absent file) and `shared.ts` (absent file). Its `session-prime.ts` does not read `payloadContract?.provenance.trustState`. Copilot-driven sessions lose trust provenance across compaction — directly impacting Phase 017's autonomous-execution plan (Copilot-fallback runtime limited to 3 parallel dispatches per `feedback_copilot_concurrency_override` (user memory)).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/spec.md:303:**Copilot-primary autonomous execution blocker**: Per `feedback_copilot_concurrency_override` (user memory) and `feedback_phase_018_autonomous` (user memory), Phase 017 plans to use cli-copilot as the Codex-fallback runtime. Cluster E (T-W1-HOK-01 + T-W1-HOK-02) MUST land before autonomous Copilot iteration launches — otherwise H-56-4 observability blind spot activates during Phase 017 itself.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/tasks.md:63:- [x] **T-12** Run `validate.sh --strict` on this packet, then `generate-context.js` for canonical save. Update implementation-summary.md (replace placeholder) and parent handover.md with phase outcome. [EVIDENCE: implementation summary replaced; parent handover row added; strict validation passed 0 errors / 0 warnings; `generate-context.js --json ...` exited 0 with deferred embedding fallback due network fetch failures.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/plan.md:335:- [ ] cli-codex CLI is reachable (`which codex`) OR claude-opus-direct fallback is available
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/plan.md:119:- cli-copilot gpt-5.4 high (fallback, 3-concurrent max)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/plan.md:133:**Execution mode**: Per `feedback_phase_018_autonomous` (user memory), each wave runs under cli-codex primary + cli-copilot fallback (3 concurrent max). After each wave's code-complete, dispatch `/spec_kit:deep-review :auto` ×7 before proceeding to the next wave.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/implementation-summary.md:79:`npm install --save ignore --package-lock=false` was attempted first but could not complete under the restricted registry/cache environment. `ignore` was added to `mcp_server/package.json` as a direct dependency (`^5.3.2`), and the runtime code prefers that direct dependency. A fallback to the local ESLint transitive copy keeps this sandbox verifiable until dependencies are refreshed normally.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/002-code-graph-context-and-scan-scope/implementation-summary.md:108:| Canonical save | `node .opencode/skills/system-spec-kit/scripts/dist/memory/generate-context.js --json ...` | Exit 0; embedding calls deferred because network fetch failed, BM25/FTS indexing path used |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:30:Phase 2 of `001-research-graph-context-systems` is a read-only audit of the codesight external Node.js/TypeScript skill (zero-runtime-dependency CLI that scans a project root and generates AI-assistant context artifacts) to translate its detector architecture, MCP tool design, profile generation, scanner heuristics, and blast-radius analysis into concrete improvements for `Code_Environment/Public`'s existing structural retrieval stack (Code Graph MCP, CocoIndex, Spec Kit Memory). The deliverable is an evidence-backed Adopt/Adapt/Reject table plus late-session adoption synthesis grounded in specific `external/src/` file:line citations across 20 deep-research iterations, not a generic feature inventory. No source files outside this spec folder are modified during the research phase.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:32:**Key Decisions**: Run the packet to 20 total iterations across three segments: original charter (iters 1-5), first continuation charter (iters 6-10), and a `completed-continue` extension (iters 11-20) covering watch/hook automation, middleware/libs/config detectors, formatter lifecycle, MCP cache/error semantics, AI-config write safety, HTML projection, scanner heuristics, and final adoption synthesis. Iterations 1-3 and 6-10 used cli-codex `gpt-5.4` high reasoning effort, iters 4-5 used native fallback after codex stalls, and iters 11-20 executed directly in the active Codex session because self-invoking cli-codex from Codex would be circular. The packet keeps the 22-row Adopt/Adapt/Reject matrix and extends it with the 20-iteration synthesis.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:60:`Code_Environment/Public` already has CocoIndex semantic search, Code Graph MCP for structural queries, and Spec Kit Memory for context preservation, but it lacks Codesight-style automated `CLAUDE.md` / `.cursorrules` / `codex.md` / `AGENTS.md` generation from a single project scan, per-AI-tool profile generation, and a blast-radius command built around reverse-import BFS. Without an evidence-grounded survey of Codesight's actual implementation (separated from its README marketing claims), any port would risk importing the wrong patterns, the wrong claims, and the wrong risks.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:93:- Re-implementing CocoIndex semantic search, Code Graph MCP structural queries, or Spec Kit Memory in Public.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:147:| R-001 | cli-codex CLI stalls in S sleep state under API throttling | Native Read/Grep fallback (used in iters 4-5) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md:201:| R-001 (codex stall) | Medium | Low | Mitigated via native fallback (iters 4-5) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/review-report.md:25:- F002 - Shared-space column retirement story is internally inconsistent. The cleanup packet says shared_space_id stays, the changelog says it drops on startup, and the runtime performs a best-effort drop with an older-SQLite fallback that keeps the column. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:50-53] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:92-94] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/review-report.md:36:   - Decide whether the supported runtime story is keep, drop, or best-effort drop with fallback, then align packet docs, checklist evidence, and changelog wording to that reality.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:3:description: "20-iteration deep-research packet for the codesight external Node.js/TypeScript skill using cli-codex, native fallback, direct Codex continuation, reducer-managed state, and post-closeout doc reconciliation."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:245:| Phase 2 (iters 4-5) | ~30 minutes | native fallback | Includes stuck codex wait time |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:318:- **ADR-002**: Switch to native Read/Grep fallback after codex stalled in iters 4-5
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:335:- [x] cli-codex CLI is reachable (`codex --version`) OR native Read/Grep fallback is available
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:362:ENGINE: <cli-codex | native-fallback>
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md:374:4. If unblockable: switch engine (cli-codex to native-fallback or vice versa), log `engine_switch` event, retry once
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:24:| F002 | P1 | **open** | `spec.md`, `checklist.md`, and runtime now match the drop-with-fallback story, but the changelog still claims existing databases auto-drop the column so no orphan columns remain. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:32:- **F002 - Shared-space column retirement story still disagrees between release artifacts and shipped runtime.** The runtime and packet docs describe a best-effort startup `DROP COLUMN` with an older-SQLite no-op fallback, but the changelog still promises an unconditional auto-drop that leaves no orphan columns. [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:47-48] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/spec.md:65-68] [SOURCE: .opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup-playbooks/002-cleanup-and-audit/001-remove-shared-memory/checklist.md:53-53] [SOURCE: .opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1534-1542] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:94-94] [SOURCE: .opencode/changelog/01--system-spec-kit/v3.4.0.0.md:257-258]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:55:| checklist_evidence | pass | CHK-013 now matches the runtime's drop-with-fallback behavior. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/000-release-cleanup/001-release-cleanup-playbooks/review/008-cleanup-and-audit-pt-01/v2/review-report.md:64:   - Rewrite the v3.4.0.0 shared-space column note so it matches the runtime and packet docs: startup drop attempt, silent no-op fallback on older SQLite.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/spec.md:137:- **SC-005**: **Given** legacy CLI or plugin callers, **When** advisor routing runs, **Then** the compatibility path returns a valid recommendation or safe fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/implementation-summary.md:125:- `0c9d6f612` (T-CPN-01): closing-pass CP-002 marked RESOLVED by commit `e774eef07` (T-PIN-08). Wave C agent caught CP-002 actually referred to `graph-lifecycle.ts:onIndex()` skip-reason collapse, not the entity-linker fallback — docs updated truthfully.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/tasks.md:64:- [x] T104 Iteration 4: profile generators + benchmark validation (Q8, Q10) — native fallback (codex stalled in S sleep ~40 min) → 6 findings, newInfoRatio 0.55 (11.2x claim is README-only; only Drizzle+Prisma have schema tests)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/tasks.md:65:- [x] T105 Iteration 5: static vs query-time + cross-phase scoping (Q11, Q12, Q4-confirmed) — native fallback (codex stalled in S sleep ~20 min) → 5 findings, newInfoRatio 0.42 (Drizzle index gap reconfirmed via grep)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/implementation-summary.md:56:| 1-5 | Original charter: execution flow, routes, schemas, MCP tools, blast radius, profiles, benchmark claims, cross-phase scoping | cli-codex + native fallback | 26 | Q1-Q12 |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/implementation-summary.md:87:- **Adopt now (11 items)**: orchestration shape, static `.codesight/` artifact emission, AST-first/regex-fallback pattern, per-tool profile overlay, F1 fixture harness, hot-file ranking (degree counting), Python AST + subprocess pattern, SQLAlchemy AST schema extraction, telemetry surface (local opt-in), `disableDetectors` short-circuit, Drizzle gap documentation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/review/016-foundational-runtime-pt-01/review-report.md:212:| T-EXH-01 | P2 | L | `mcp_server/` (7+ typed unions) | Add `assertNever` utility + apply to `OnIndexSkipReason`, `EnrichmentStepStatus`, `EnrichmentSkipReason`, `EnrichmentFailureReason`, `ConflictAbortStatus`, `HookStateLoadFailureReason`, `SharedPayloadTrustState`, `TriggerCategory`. R4-P2-002 resolves. High leverage because it prevents future silent runtime-fallback bugs. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-advisor-standards-alignment/tasks.md:66:  [EVIDENCE: `node --check` exit 0; `npm run build` exit 0; focused Vitest 30/30; strict validation 0 errors / 0 warnings; `generate-context.js --json` exit 0 with deferred embedding fallback; implementation summary and parent docs updated.]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-advisor-standards-alignment/implementation-summary.md:105:- Canonical save completed with deferred embedding fallback because the Voyage embedding request failed under restricted network access; BM25/FTS indexing remains available.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/spec.md:87:- Code Graph: AST detection accuracy, edge enrichment strategy, scan trigger correctness, cache invalidation behavior, query surface contract, and failure mode handling
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/spec.md:171:- **RQ-01 AST Edge Detection Gaps**: Which call-edge and import-edge types does the tree-sitter parser miss or misattribute for TypeScript, JavaScript, Python, and Bash? Are there node kinds (decorators, type aliases, dynamic imports) where the regex fallback produces materially different edges than tree-sitter, causing incorrect CALLS chains in `code_graph_query`?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/spec.md:178:- **RQ-05 Scan Throughput and Incremental Accuracy**: At the current corpus size (~1,400 files, ~52K nodes, ~30K edges), what fraction of incremental scan time is spent on mtime+hash comparison vs. actual parsing? Are there files repeatedly re-parsed despite not changing, indicating a cache invalidation bug in `structural-indexer.ts`?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/review/016-foundational-runtime-pt-02/review-report.md:130:**Surface**: `mcp_server/handlers/session-resume.ts:450-478`. Guard at line 457 is `if (requestedSessionId && callerCtx?.sessionId && requestedSessionId !== callerCtx.sessionId)` — three-way AND. Line 477 passes `claudeSessionId: requestedSessionId ?? undefined` without `callerCtx.sessionId` fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/004-runtime-executor-hardening/001-foundational-runtime/review/016-foundational-runtime-pt-02/review-report.md:136:**Latent risk**: MEDIUM. The positive-binding gap is a design choice that the test encodes. Any future Phase 018 remediation that adopts `callerCtx.sessionId` fallback must invert `session-resume-auth.vitest.ts:212-220`; failing to do so breaks test coverage and silently reverts the intent.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/plan.md:628:- **Option B (KEEP)**: Rejected. Zero callers, no wiring intent, and maintaining dead code increases future maintenance burden. PR 11 is documented as a contingent fallback only.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/002-skill-graph-daemon-native-advisor-tools/implementation-summary.md:111:**Status:** Complete (2026-04-20, SHA `77b0f59e2`). Migrated `.opencode/skills/system-spec-kit/scripts/` from CommonJS to pure ESM. Changes: flipped `package.json` `"type"` to `"module"`, added `esm-entry.ts` helpers (`isMainModule`, `dirnameFromImportMeta`), converted 16 entrypoint guards from `require.main === module`, converted 4 `require()` assignments, replaced `__dirname` with `dirnameFromImportMeta`, added `.js` suffixes to relative TS imports, updated `validate.sh` to use `--import tsx` loader fallback on Node 20.19.5. Post-migration: Node 25 and Node 20.19.5 both reach ordinary validation failures without CJS/ESM SyntaxError. 98 files changed total.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/spec.md:153:| Dependency | `code_graph_status` MCP tool | High | Verify tool availability in Phase 0; degrade to `code_graph_scan --status` CLI fallback if unavailable |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/spec.md:154:| Dependency | `detect_changes` MCP tool | High | Same — fallback to git status + glob comparison |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/spec.md:185:- **NFR-R01**: Command degrades gracefully if MCP tools unavailable (fallback to git + glob)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/spec.md:200:- `code_graph_status` returns timeout: fallback to filesystem-only diagnosis with warning
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md:141:Improved the graph-metadata parser quality across five review findings: added checklist-aware status derivation, sanitized `key_files` against noise classes, deduplicated entities using canonical-path preference, scoped backfill traversal to active packets by default, aligned doc surfaces, added real path resolution with cross-track fallback and obsolete-path rejection, and raised the entity cap from 16 to 24 while tightening canonical-scope checks. Post-backfill corpus scan: `command-shaped key_files = 0`, `status outliers = 0`, `duplicateEntityNameGroups = 0`, `legacyGraphMetadataFiles = 0`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md:147:**001-fix-status-derivation** — complete. Replaced the old frontmatter-only fallback with safer status derivation. Packets with `implementation-summary.md` can move to `complete` when their checklist is complete or absent. Checklist-backed work with unchecked items stays `in_progress`. Added `checklist-aware deriveStatus()` fallback and checklist completion helper.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md:165:| Use checklist presence as status fallback | Prevents premature `complete` status on packets that have open checklist items |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md:211:| Use checklist presence as status fallback (003) | Prevents premature complete status on open checklist items |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:3:description: "Act on all 6 recommendations from 021/002 Smart-Router research + build spec-kit-skill-advisor OpenCode plugin per 021/001 V8/V9. Scope: fix stale paths, tune ON_DEMAND keywords, replace CLI silent fallbacks, build CI check, ship observe-only telemetry harness, ship advisor plugin."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:17:    dispatch_policy: "cli-codex gpt-5.4 high fast primary; cli-copilot gpt-5.4 high fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:56:- **021/002** (skill-manifest smart-router efficacy): 6 recommendations spanning stale paths, keyword tuning, fallback safety, CI check, observe-only harness.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:82:**Area C — CLI silent-fallback replacement**
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:106:- Tests: unit tests for cache invalidation + status tool + opt-out behavior
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:143:| REQ-003 | Area C: CLI fallbacks use UNKNOWN | All 4 CLI skills no longer silent-default to productive intent |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/spec.md:210:- **Given** a CLI skill has no matching route score, **When** its pseudocode fallback executes, **Then** it returns UNKNOWN and a disambiguation checklist instead of a productive intent.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/spec.md:72:1. **Content-hash staleness predicate** — extend `isFileStale()` to use `content_hash` as a fallback when mtime matches.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/plan.md:48:Phase 023 turns the 021 smart-router research into concrete safeguards and a plugin. The work is ordered to reduce breakage: fix broken router paths first, add the static checker that proves path hygiene, tune conservative ON_DEMAND keywords from the corpus, replace unsafe CLI fallbacks, then add observe-only telemetry and the OpenCode advisor plugin.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/plan.md:64:- [ ] Area C updates all 4 CLI skills to UNKNOWN fallback
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/plan.md:105:- [ ] Replace CLI silent fallbacks
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/plan.md:164:                                       -> Area C fallback safety
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/review-report.md:68:- Historical packet docs outside `001` still contain `SPECKIT_TIER3_ROUTING` mentions, but the five live configs are clean and the active save handler is always-on Tier 3 with fail-open Tier 2 fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-doctor-command/implementation-summary.md:152:5. **MCP tool fallback paths not exhaustively tested.** The YAMLs document fallback to `git status` + glob comparison if `code_graph_status` or `detect_changes` are unavailable, but those fallback paths have not been smoke-tested against a real degraded state.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-skill-graph-metadata-routing-boosts/implementation-summary.md:170:Made skill graph setup less fragile by shipping `init-skill-graph.sh` (validates graph metadata, exports JSON fallback, runs health check), completing the advisor fallback logic in `skill_advisor.py` (prefers SQLite, falls back to JSON, auto-compiles if neither exists), adding skill-graph lifecycle logging to `context-server.ts` (fresh-creation, existing-load, reindex, new-skill detection), and updating the canonical operator setup guide at `skill-advisor/SET-UP_GUIDE`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/tasks.md:3:description: "Task tracking for Phase 023: stale router paths, static checker, ON_DEMAND tuning, CLI fallback safety, observe-only telemetry, OpenCode plugin, and verification."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/tasks.md:69:- [x] T040 Area C: Update `cli-codex`, `cli-copilot`, `cli-gemini`, and `cli-claude-code` zero-score fallbacks to UNKNOWN disambiguation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/review-report.md:88:| R1-P1-003 | P1 | PR-5 (absorbs R4-P1-001 from PR-5) | Metrics cardinality envelope is not enforced for caller-provided labels (env-derived and repo-controlled) | `.opencode/skills/system-spec-kit/mcp_server/skill-advisor/lib/scorer/fusion.ts:320` (env labels); `.opencode/skills/system-spec-kit/mcp_server/skill-advisor/lib/metrics.ts:578` (collector sink) | Normalize `SPECKIT_RUNTIME` and `SPECKIT_ADVISOR_FRESHNESS` to closed enums before emission. Clamp or bucket `skill_id` (sourced from SQLite `skill_nodes.id` or filesystem `graph-metadata.json.skill_id`) to known built-in IDs plus a `custom_skill` fallback. Have `SpeckitMetricsCollector` reject or bucket labels outside declared value policies at the sink rather than only at individual emission sites. | M, 4–6 h |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/review/015-code-graph-advisor-refinement-pt-01/review-report.md:89:| R4-P1-002 | P1 | PR-2/PR-7 | Claude hook commands execute a repo-relative hook selected by ambient cwd and PATH | `.claude/settings.local.json:31` | Anchor the `git rev-parse --show-toplevel` fallback to the canonical settings-file directory rather than ambient cwd. Use a pinned Node binary (`process.execPath` from setup, or an absolute path) rather than unqualified `node`. In nested-repo or worktree launches, the current command can resolve `.opencode/…/dist/hooks/claude/*.js` from a different repository. | M, 3–5 h |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/plan.md:151:- **Hash predicate (T08):** unit tests in `code-graph-indexer.vitest.ts` covering same-mtime/different-hash, missing-hash fallback, unchanged-content freshness
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/implementation-summary.md:3:description: "Tracks Phase 023 delivery across router remediation, static validation, keyword tuning, CLI fallback safety, observe-only telemetry, and the OpenCode skill-advisor plugin."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/implementation-summary.md:49:Phase 023 shipped all six work areas from the 021 smart-router research packet and added the OpenCode `spec-kit-skill-advisor` plugin. The packet fixes stale route resources, adds static router validation, tunes conservative ON_DEMAND routing keywords, replaces silent CLI fallback with UNKNOWN disambiguation, creates observe-only telemetry, and delivers a bridge-backed OpenCode plugin that imports the Phase 020 advisor producer and renderer without modifying Phase 020 runtime code.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/implementation-summary.md:150:| `.opencode/skills/cli-{claude-code,codex,copilot,gemini}/SKILL.md` | Modified | Replace zero-score silent CLI fallback with UNKNOWN disambiguation |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/003-smart-remediation-opencode-plugin/implementation-summary.md:194:| CLI fallback scan | PASS: four zero-score branches return `UNKNOWN`; no silent `GENERATION` fallback remains |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:61:Current 026 graph work hardens trust (`011`) and advisory routing (`008`), but it does not add new detector provenance states, blast-radius correctness fixes, evidence-tagged edges, cluster metadata, export contracts, or graph-specific fallback behavior. The cross-phase research now shows several additive upgrades that fit Public's existing Code Graph MCP substrate without creating a second graph authority. [SOURCE: ../001-research-graph-context-systems/002-codesight/research/research.md:926-928]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:75:- Detector provenance taxonomy and AST or structured-fallback discipline.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:78:- Optional query fallback tiering for graph-local lexical helpers.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:115:| REQ-001 | Graph detector outputs distinguish `ast`, `structured`, `regex`, or `heuristic` provenance and never mislabel non-AST results as AST. | Detector fixtures prove non-AST paths cannot emit `ast` provenance and that explicit fallback states survive serialization. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:125:| REQ-006 | Graph-local lexical fallback surfaces explicit backend metadata and forced-degrade tests if a cascade tier is added. | If a fallback cascade is implemented, tests cover compile-probe miss, missing table or index, and runtime ranking failure while preserving explicit backend metadata. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:151:**Given** a detector falls back from AST parsing, **when** graph metadata is serialized, **then** the payload records an honest fallback provenance class instead of mislabeling the result as AST. [SOURCE: ../001-research-graph-context-systems/002-codesight/research/research.md:949-953]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:172:| Risk | Blast-radius or fallback surfaces overclaim precision | Medium | Use explicit low-authority labels, backend metadata, and frozen test corpora. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:195:- Partial provenance metadata: keep fallback states explicit rather than coercing them into `ast`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:224:| R-005 | Blast-radius or fallback surfaces overclaim precision | M | M | Use explicit low-authority labels, backend metadata, and frozen test corpora. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/spec.md:262:- Should graph-local fallback tiering ship in the same implementation wave as the adopt-now detector and blast-radius work, or land behind a follow-on flag once the P0 lane is stable?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/implementation-summary.md:71:The packet completed its 20-iteration deep-research loop and then executed the Phase 5 implementation roadmap across PR-1 through PR-10. The implementation covered corpus-path repair, Claude settings rewrite, the PR-3 promotion-subsystem delete sweep, readiness/trust-state vocabulary unification, metrics instrumentation, cache invalidation wiring, settings parity coverage, and the parse/query/hook-brief benchmark surfaces.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/004-code-graph-advisor-refinement/implementation-summary.md:85:| `applied/B6.md` | cross-packet daemon-availability regression | advisor-status freshness/trustState decoupling + Python compat-shim daemonless fallback + manual-testing-playbook 47→42 phrase reconciliation; 14/14 in-scope tests now green |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/implementation-summary.md:77:- **`001-documentation-code-alignment/`**: Phase 022 brings the skill-advisor package into line with the hook surface that Phase 020 shipped. Operators now see prompt-time hook invocation as the primary Gate 2 path, still have the direct Python CLI documented as a fallback, and have a packet-local a...
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/implementation-summary.md:84:- **`001-advisor-hook-brief-improvements/`**: One explicit threshold contract across plugin defaults, native bridge routing, fallback routing, and operator-facing bridge metadata. OpenCode native bridge rendering now flows through shared `renderAdvisorBrief(...)` invariants, Codex prompt submission and prompt-wrapper fallback share the same builder, and `advisor_recommend`/`advisor_validate` accept explicit `workspaceRoot` with durable JSONL diagnostics...
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:101:- Optional graph-local fallback tiering, clustering metadata, and export contracts behind bounded flags
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:118:- [x] Implement detector provenance taxonomy plus AST or structured-fallback discipline.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:121:- [x] Keep optional fallback, clustering, and export work behind explicit gating and non-authority wording.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:136:| Frozen detector fixtures | Provenance taxonomy and fallback serialization | Vitest or packet-local fixtures under `007` discipline |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:152:| Claudest/R7 fallback pattern | Internal optional | Optional | Graph-local fallback tiering can borrow the pattern but does not block the packet |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/plan.md:252:- Optional fallback tiering research can stay behind gating while the adopt-now lane is implemented.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/spec.md:56:1. Unifying the effective-threshold contract across the OpenCode plugin defaults, native bridge route, and fallback route.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/spec.md:58:3. Normalizing Codex prompt submission and prompt-wrapper fallback against the shared builder contract.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/spec.md:71:- Script fallback: `mcp_server/skill-advisor/scripts/skill_advisor.py`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/spec.md:109:| REQ-001 | OpenCode and Codex runtime entrypoints share the packet-014 threshold/render contract | OpenCode native + fallback paths and Codex prompt submission + prompt-wrapper fallback all consume the shared builder/render flow without branch-specific threshold drift |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/spec.md:17:    dispatch_policy: "cli-codex gpt-5.4 high fast primary; cli-copilot gpt-5.4 high fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/spec.md:74:- `../../../../skill/skill-advisor/README.md` — add hook-based invocation as primary path; keep explicit `skill_advisor.py` as fallback; cross-reference references/hooks/skill-advisor-hook.md.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/plan.md:96:- [ ] `014-F-001` Threshold unification: route OpenCode native and fallback paths through one effective-threshold source in `.opencode/plugins/spec-kit-skill-advisor.js`, `.opencode/plugin-helpers/spec-kit-skill-advisor-bridge.mjs`, `.opencode/skills/system-spec-kit/mcp_server/skill-advisor/lib/skill-advisor-brief.ts`, and `.opencode/skills/system-spec-kit/references/hooks/skill-advisor-hook.md`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/plan.md:27:      - "Preserve direct Python advisor as fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/plan.md:91:Runtime prompt-submit hooks call `buildSkillAdvisorBrief()`, render a model-visible advisor brief when threshold and freshness allow it, write prompt-free diagnostics, and otherwise return `{}` or wrapper no-op output. The direct Python CLI remains a fallback for raw advisor JSON and troubleshooting.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/plan.md:108:- [x] Add README hook-primary section and direct CLI fallback label
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/spec.md:58:3. Which code-graph tools, events, or signals are under-used by downstream consumers (memory search, CocoIndex bridge, session bootstrap)?
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/spec.md:70:- Parser adapters (tree-sitter WASM + regex fallback) and the `SPECKIT_PARSER` env knob.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/spec.md:72:- CocoIndex ↔ code-graph bridge: seed resolution, neighborhood expansion.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/spec.md:79:- CocoIndex's own indexing pipeline (covered by 026 phase 006 research instead).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/spec.md:48:**Key Decisions**: Research-first — no implementation child created until `001-initial-research` produces actionable findings on hook trigger points, cache invalidation model, and context budget curves. Each finding cluster becomes a sibling child (`020/002-*`, `020/003-*`). The umbrella packet owns sequencing; cluster-local behavior stays in each child.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/spec.md:201:- [ ] Documentation: new hook-surface reference doc covers contract, failure modes, cache invalidation, cross-runtime semantics (location under `.opencode/skills/system-spec-kit/references/hooks/`, created by 020/009)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md:11:The backend resilience work added the intended streams, but the evidence and safety story did not land cleanly. The strongest implementation issues are inconsistent workspace containment on the new verify/resolver paths, resolver fallback gaps, malformed-baseline drift handling, and verifier contract mismatches. The strongest release blocker is simpler: too many claimed requirements are still verified indirectly, with synthetic helpers or mock-only shapes instead of direct executable proof.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md:29:- **Correctness:** 13 active findings. The biggest issues are nested tsconfig resolution, type-only import tagging, regex-fallback resolver parity, malformed-baseline drift status, case-insensitive verifier matching, incomplete persisted verification context, and readiness-state propagation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md:41:- `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/scan.ts:281-289`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/status.ts:40-76,155-214`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-indexer.vitest.ts:219-225`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-scan.vitest.ts:138-332`, `.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-siblings-readiness.vitest.ts:302-322` — `REQ-007`, `REQ-008`, and `REQ-009` lack direct tests for edge weights, baseline persistence, drift thresholds, and status fallback behavior. Fix: add `edge-drift.ts` unit tests plus scan/status coverage for baseline persistence and thresholded drift summaries.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md:48:- `.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/structural-indexer.ts:531-559` — the regex fallback still drops resolver metadata required for type-only and re-export resolution. Fix: emit `moduleSpecifier`, `importKind`, and `exportKind` on the regex path too.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/review/review-report.md:81:4. Bring resolver behavior up to the packet contract: full tsconfig `extends` traversal with cycle protection, per-specifier type-only import tagging, and regex fallback metadata parity.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/plan.md:87:CALLS-oriented queries first resolve a subject node in `query.ts`, then execute graph reads that must either return implementation-focused results or an explicit blocked/degraded contract when readiness demands a full scan (`013-ZC-F-001`, `013-F-001`). Context requests carry richer CocoIndex seed metadata and bounded-work deadline state through `seed-resolver.ts` and `code-graph-context.ts` (`013-F-002`, `013-F-006`), while scans persist metadata that status/startup readers can surface without leaving stale summaries behind (`013-F-003`, `013-F-004`, `013-F-005`).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/review-report.md:66:- CocoIndex semantic discovery could not be used in this session because each attempted query returned a cancelled-tool response.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/plan.md:149:- [ ] 007-gemini-copilot-hook-wiring (Gemini JSON `additionalContext` + Copilot SDK + wrapper fallback)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/tasks.md:41:- [x] T005 [P0] Update `../../../../skill/skill-advisor/README.md` — add §Hook Invocation section (primary path); preserve explicit CLI fallback [Evidence: README §2 and §3]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:49:Phase 022 brings the skill-advisor package into line with the hook surface that Phase 020 shipped. Operators now see prompt-time hook invocation as the primary Gate 2 path, still have the direct Python CLI documented as a fallback, and have a packet-local audit trail for the Phase 020 TypeScript quality pass.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:59:The setup guide now names hook invocation as the primary Gate 2 mode and keeps the one-shot CLI mode as a fallback path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:73:| `lib/codex-hook-policy.ts:5`, `hooks/copilot/user-prompt-submit.ts:6`, `hooks/codex/prompt-wrapper.ts:5`, `lib/skill-advisor/normalize-adapter-output.ts:18`, `lib/context/shared-payload.ts:602` | Comments used dated, packet, legacy, or compatibility wording | Rephrased comments around durable runtime behavior and fallback contracts |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:81:| `../../../../skill/skill-advisor/README.md` | Modified | Document hook invocation as primary and direct CLI as fallback |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:93:| `.opencode/skills/system-spec-kit/mcp_server/hooks/codex/prompt-wrapper.ts` | Modified | Rename compatibility comment to fallback-path comment |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-documentation-code-alignment/implementation-summary.md:112:| Document hooks as primary and CLI as fallback | Phase 020 made prompt-time hook injection the default operator path, but direct CLI output is still useful for diagnostics and scripted checks. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:17:    dispatch_policy: "cli-codex gpt-5.4 high fast primary; cli-copilot gpt-5.4 high fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:47:Cross-runtime proactive skill-advisor hook surface. Each `UserPromptSubmit` event in Claude, Gemini, Copilot, and Codex runtimes runs `buildSkillAdvisorBrief(prompt, {runtime})` which returns a typed `AdvisorHookResult` rendered to the model as `hookSpecificOutput.additionalContext` (JSON transport) or wrapper-preamble (fallback). Brief emits a sanitized skill recommendation with freshness/confidence/uncertainty fields; fail-open contract returns `{}` (no-op) on any error.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:52:- **020/003 freshness + source cache** — `lib/skill-advisor/freshness.ts` (`getAdvisorFreshness()`), `source-cache.ts` (15-min LRU), `generation.ts` (atomic counter + corrupt recovery). Per-skill fingerprints, generation-tagged snapshots, JSON-fallback always-stale.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:56:- **020/007 Gemini + Copilot hooks** — `hooks/gemini/user-prompt-submit.ts` (JSON additionalContext), `hooks/copilot/user-prompt-submit.ts` (SDK `onUserPromptSubmitted` preferred, wrapper-fallback when SDK local-unavailable). Wrapper explicitly rejects notification-only `{}` as model-visible.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:57:- **020/008 Codex integration** — `lib/codex-hook-policy.ts` dynamic detector (500ms probes → live/partial/unavailable), `hooks/codex/user-prompt-submit.ts` (stdin-canonical, argv-fallback), `hooks/codex/pre-tool-use.ts` (Bash-only deny from `.codex/policy.json`; PostToolUse is audit-only), `hooks/codex/prompt-wrapper.ts` fallback. Parity test extended to 4 runtimes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:75:**Implementation (020/002-009):** 10-campaign battle plan (see `battle-plan.md`). Executor policy: **cli-codex gpt-5.4 high fast primary; cli-copilot gpt-5.4 high fallback**. Orchestrator = Claude Opus 4.7 (1M context). Each campaign: pre-flight verify → dispatch codex via `codex exec --model gpt-5.4 -c model_reasoning_effort=high -c service_tier=fast -c approval_policy=never --sandbox workspace-write` → monitor background → verify tests/tsc/validate independently → commit (orchestrator; codex sandbox blocks git) → TaskUpdate → next.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:205:**Status:** Complete (2026-04-19). Shipped Gemini `BeforeAgent` adapter (`hooks/gemini/user-prompt-submit.ts`) emitting JSON `additionalContext`; Copilot adapter (`hooks/copilot/user-prompt-submit.ts`) with SDK `onUserPromptSubmitted` preferred + wrapper fallback when SDK local-unavailable. 3-runtime parity harness (Claude/Gemini/Copilot) covering 5 canonical fixtures — identical `additionalContext` after transport normalization. Gemini registered in `.gemini/settings.json`. Copilot wrapper-fallback produces `promptWrapper` when brief exists; notification-only `{}` explicitly separated.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:208:**Status:** Complete (2026-04-19) — code/test surface only; `.codex/` registration snippets deferred due to sandbox EPERM. Shipped `lib/codex-hook-policy.ts` dynamic detector (`codex --version` + `codex hooks list` probes → live/partial/unavailable), `hooks/codex/user-prompt-submit.ts` (stdin canonical, argv fallback), `hooks/codex/pre-tool-use.ts` (Bash-only deny from `.codex/policy.json`; PostToolUse audit-only), `hooks/codex/prompt-wrapper.ts` (fallback when detector=unavailable). Parity extended to 4 runtimes (Claude/Gemini/Copilot/Codex). Sandbox captured `codex-cli 0.121.0`; `hooks list` failed → detector outcome `partial`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:211:**Status:** Complete (2026-04-19). Published skill-advisor-hook reference doc (650 lines, DQI 97/100) in `.opencode/skills/system-spec-kit/references/hooks/` with capability matrix, failure-mode playbook, observability contract, performance budgets, migration notes, concurrency, disable flag, privacy contract, troubleshooting. Published skill-advisor-hook-validation (8-step manual playbook). Updated `CLAUDE.md` §Gate 2 (hook primary, direct CLI fallback). Updated 4 runtime READMEs (`hooks/claude/`, `hooks/gemini/`, `hooks/copilot/`, `hooks/codex/`). `.codex/settings.json` and `.codex/policy.json` documented as snippets only per 008 sandbox deferral.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/004-advisor-hook-surface-integration/implementation-summary.md:217:2. **Copilot SDK runtime capture deferred.** `@github/copilot-cli` SDK package not locally available during 020/007 development; wrapper fallback path tested via mocks. SDK-path behavior will be validated when the SDK lands locally (tracked as non-blocker; wrapper path is production-ready).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/tasks.md:45:- [x] T002 Add detector provenance taxonomy and update detector contracts plus serialization. [SOURCE: ../001-research-graph-context-systems/002-codesight/research/research.md:899-900] [SOURCE: ../../../../../skill/system-spec-kit/mcp_server/lib/context/shared-payload.ts:31] [SOURCE: ../../../../../skill/system-spec-kit/mcp_server/handlers/code-graph/scan.ts:35] [EVIDENCE: vitest `keeps detector provenance separate from the parser trust-axis vocabulary`; vitest `keeps detector provenance honest for fallback lanes`]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/tasks.md:57:- [ ] DEFERRED T014 If lexical fallback is included, add a graph-local capability selector plus a forced-degrade verification matrix. [SOURCE: ../001-research-graph-context-systems/002-codesight/research/research.md:916-916] [EVIDENCE: `handlers/code-graph/query.ts` has no lexical fallback cascade to harden in this run, so no capability selector or degrade matrix shipped]
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/implementation-summary.md:43:- OpenCode now uses one explicit threshold contract across plugin defaults, native bridge routing, fallback routing, and operator-facing bridge metadata.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/implementation-summary.md:45:- Codex prompt submission and prompt-wrapper fallback now share the same builder, timeout, threshold, and durable-diagnostics contract.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/implementation-summary.md:57:| `.opencode/skills/system-spec-kit/mcp_server/hooks/codex/prompt-wrapper.ts` | Codex fallback parity + durable diagnostics |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/implementation-summary.md:80:- Kept OpenCode’s native bridge route, but forced it through the same threshold object and shared renderer as the fallback path instead of preserving a custom formatter.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-advisor-hook-brief-improvements/implementation-summary.md:105:- The current workspace reports stale advisor freshness during direct hook/bridge smokes, so the verification evidence exercised prompt-safe stale/fallback behavior rather than a live daemon path.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/implementation-summary.md:55:The packet hardened code-graph CALLS resolution so ambiguous `handle*` subjects now select callable implementation nodes instead of wrapper shadows, and it made query/context reads fail explicitly when readiness requires a suppressed full scan. It also preserved CocoIndex ranking fidelity through seed resolution, cleared stale edge-enrichment summaries on null-summary scans, surfaced `graphQualitySummary` through status/startup readers, transported a compact startup shared-payload contract through Claude, Gemini, Copilot, and Codex runtime hooks, and turned `deadlineMs` plus `partialOutput` into real context response metadata.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/implementation-summary.md:63:| `.opencode/skills/system-spec-kit/mcp_server/code-graph/lib/seed-resolver.ts` | CocoIndex score/snippet/range/provider preservation and ranking |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/implementation-summary.md:94:- Preserved CocoIndex semantic score as the primary seed-ordering signal and graph confidence as the fallback/tie-break layer.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/implementation-summary.md:85:| Defer lexical fallback cascades, clustering, and export work | `code_graph_query` has no lexical fallback cascade today, and ADR-003 keeps clustering and export work prototype-later so the adopt-now lane stays bounded. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/001-code-graph-upgrades/implementation-summary.md:106:1. `code_graph_query` still has no lexical fallback cascade, so Lane F stayed not applicable in this run. If a lexical fallback is added later, it still needs its own capability selector and forced-degrade matrix.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/005-code-graph-backend-resilience/tasks.md:84:- [x] T09 [P0] Capture resolver metadata: extend `RawCapture` at `mcp_server/code_graph/lib/structural-indexer.ts:113-126` with `moduleSpecifier?: string`, `importKind?: 'value'|'type'`, `exportKind?: 'named'|'star'|'declaration'`. Update import/export captures in `mcp_server/code_graph/lib/tree-sitter-parser.ts:340-397` and `:399-465` to record these fields. Preserve regex-fallback source in `structural-indexer.ts:485-502`. Deps: T08. (verified)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/review-report.md:31:Evidence: CocoIndex fidelity survives only when callers send `seed.file`; `seed.filePath` falls through the generic seed path and drops provider-specific metadata.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/review-report.md:32:Recommended fix: treat `filePath` as equivalent to `file` for CocoIndex seeds and add a regression for that public input shape.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/review/review-report.md:101:3. Fix `F-002` and `F-003` together: complete the new context contract by accepting `filePath` CocoIndex seeds and correcting `omittedAnchors`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-deferred-remediation-telemetry-run/spec.md:17:    dispatch_policy: "cli-codex gpt-5.4 high fast primary; cli-copilot gpt-5.4 high fallback"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/003-code-graph-hook-improvements/tasks.md:72:- [ ] T008 P1 Address `013-F-002` by preserving CocoIndex `score`, `snippet`, and range fidelity in `.opencode/skills/system-spec-kit/mcp_server/code-graph/lib/seed-resolver.ts` and `.opencode/skills/system-spec-kit/mcp_server/code-graph/handlers/context.ts`, with ranking coverage in `.opencode/skills/system-spec-kit/mcp_server/code-graph/tests/code-graph-context-handler.vitest.ts`

exec
/bin/zsh -lc "find .opencode/specs -path '*search*' -maxdepth 8 -type f \\( -name 'spec.md' -o -name 'plan.md' -o -name 'tasks.md' -o -name 'implementation-summary.md' -o -name 'review-report.md' -o -name 'agent-brief*.md' \\)" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/010-search-retrieval-quality-fixes/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/013-fts5-fix-and-search-dashboard/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/011-indexing-and-adaptive-fusion/007-external-graph-memory-research/spec.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/implementation-summary.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/tasks.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/review/review-report.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/plan.md
.opencode/specs/system-spec-kit/023-hybrid-rag-fusion-refinement/007-hybrid-search-null-db-fix/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/012-search-routing-final-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/archive-invalid-2026-04-13T16-59-27Z/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/002-content-routing-accuracy-research/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/004-search-fusion-tuning-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/003-graph-metadata-validation-research/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/006-content-routing-accuracy-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/011-search-routing-late-findings-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/review/007-graph-metadata-validation-review/review-report.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/006-skill-advisor/001-memory-search-routing-tuning/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/005-code-graph/006-code-graph-resilience-research/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/002-codesight/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/007-external-project/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/004-graphify/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/005-claudest/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/006-research-memory-redundancy/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/003-contextador/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/001-research-and-baseline/001-claude-optimization-settings/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/008-deep-research-review/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/002-search-scenario-execution/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/001-search-scenario-design/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/implementation-summary.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/tasks.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/plan.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/002-resource-map-deep-loop-fix/001-reverse-parent-research-review-folders/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/009-xethryon/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/008-bmad-autonomous-development/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/004-get-it-right-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/005-intellegix-code-agent-toolkit-master/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/001-agent-lightning-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/007-relay-main/spec.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/implementation-summary.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/tasks.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/plan.md
.opencode/specs/system-spec-kit/z_future/agentic-system-upgrade/001-research-agentic-systems/006-ralph-main/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/002-query-intelligence-reformulation/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/implementation-summary.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/001-fusion-scoring-intelligence/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/004-feedback-quality-learning/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/003-graph-augmented-retrieval/spec.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/tasks.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/plan.md
.opencode/specs/system-spec-kit/022-hybrid-rag-fusion/001-hybrid-rag-fusion-epic/011-research-based-refinement/005-retrieval-ux-presentation/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/005-post-research-wave-2-controlled-delivery/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/006-post-research-wave-3-outcome-confirmation/spec.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/tasks.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/plan.md
.opencode/specs/system-spec-kit/z_archive/020-mcp-working-memory-hybrid-rag/004-post-research-wave-1-governance-foundations/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/080-ai-integration-patterns-research/spec.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/implementation-summary.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/tasks.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/plan.md
.opencode/specs/system-spec-kit/z_archive/001-fix-command-dispatch/z_archive/077-speckit-upgrade-from-research/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/002-semantic-coverage-graph/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/003-wave-executor/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/007-skill-rename-improve-agent-prompt/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/009-round3-review-remediation/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/006-graph-testing-and-playbook-alignment/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/010-root-level-review-research-convention/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/008-further-deep-loop-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/review/archive-rvw-2026-04-11/review-report.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/001-runtime-truth-foundation/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/005-agent-improver-deep-loop-alignment/spec.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/tasks.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/plan.md
.opencode/specs/skilled-agent-orchestration/042-sk-deep-research-review-improvement-2/004-offline-loop-optimizer/spec.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/tasks.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/plan.md
.opencode/specs/skilled-agent-orchestration/023-sk-deep-research-creation/spec.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/tasks.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/plan.md
.opencode/specs/skilled-agent-orchestration/034-sk-deep-research-review-folders/spec.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/tasks.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/plan.md
.opencode/specs/skilled-agent-orchestration/030-sk-deep-research-review-mode/spec.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/tasks.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/plan.md
.opencode/specs/skilled-agent-orchestration/035-sk-deep-research-path-migration/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/001-sk-deep-research-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/tasks.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/002-sk-deep-review-improvements/spec.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/plan.md
.opencode/specs/skilled-agent-orchestration/040-sk-deep-research-review-improvement-1/spec.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/tasks.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/plan.md
.opencode/specs/skilled-agent-orchestration/036-sk-deep-research-review-split/spec.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/tasks.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/plan.md
.opencode/specs/skilled-agent-orchestration/024-sk-deep-research-refinement/spec.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/tasks.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/plan.md
.opencode/specs/skilled-agent-orchestration/028-sk-deep-research-testing-playbook/spec.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/implementation-summary.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/tasks.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/plan.md
.opencode/specs/skilled-agent-orchestration/029-sk-deep-research-first-upgrade/spec.md

exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec.md | sed -n '1,220p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md | sed -n '1,220p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
     1	---
     2	# SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2
     3	title: "Feature Specification [system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook/spec]"
     4	description: "Stress-test playbook for system-spec-kit Search/Query/Intelligence features by dispatching simple/vague/specific prompts via cli-codex, cli-copilot, and cli-opencode and scoring quality + efficiency against a fixed rubric."
     5	trigger_phrases:
     6	  - "001-search-intelligence-stress-playbook"
     7	  - "search intelligence playbook"
     8	  - "memory search cross-AI test"
     9	  - "cli-codex cli-copilot cli-opencode stress test"
    10	  - "search query intelligence rubric"
    11	  - "external vs MCP search comparison"
    12	importance_tier: "important"
    13	contextType: "research"
    14	_memory:
    15	  continuity:
    16	    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/011-mcp-runtime-stress-remediation/001-search-intelligence-stress-playbook"
    17	    last_updated_at: "2026-04-26T14:50:00Z"
    18	    last_updated_by: "claude-opus-4-7"
    19	    recent_action: "Created root packet"
    20	    next_safe_action: "Author 001"
    21	    blockers: []
    22	    key_files:
    23	      - "spec.md"
    24	      - "plan.md"
    25	      - "tasks.md"
    26	      - "implementation-summary.md"
    27	    completion_pct: 25
    28	    open_questions:
    29	      - "How many runs per (scenario × CLI) cell? Default N=1 baseline; optionally expand to N=3 for variance signal"
    30	      - "Should cli-opencode use --agent general OR --agent context for fair comparison vs external CLIs?"
    31	      - "Fixed-corpus scoring or use the actual production memory database? (production = realistic, fixed = reproducible)"
    32	    answered_questions: []
    33	template_source_hint: "<!-- SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2 -->"
    34	---
    35	# Feature Specification: Search Intelligence Stress-Test Playbook
    36	
    37	<!-- SPECKIT_LEVEL: 1 -->
    38	<!-- SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2 -->
    39	
    40	---
    41	
    42	<!-- ANCHOR:metadata -->
    43	## 1. METADATA
    44	
    45	| Field | Value |
    46	|-------|-------|
    47	| **Level** | 1 |
    48	| **Priority** | P1 |
    49	| **Status** | In Progress |
    50	| **Created** | 2026-04-26 |
    51	| **Branch** | `main` |
    52	| **Parent Spec** | ../spec.md |
    53	| **Sibling Phases** | 005-memory-search-runtime-bugs (findings packet for related defects) |
    54	| **Sub-Phases** | 001-search-scenario-design, 002-search-scenario-execution |
    55	<!-- /ANCHOR:metadata -->
    56	
    57	---
    58	
    59	<!-- ANCHOR:phase-map -->
    60	## PHASE DOCUMENTATION MAP
    61	
    62	| Phase | Folder | Status | Description |
    63	|-------|--------|--------|-------------|
    64	| 1 | 001-search-scenario-design/ | Design Complete | 9-scenario corpus + 5-dim rubric + dispatch matrix + scripts |
    65	| 2 | 002-search-scenario-execution/ | Scaffold Complete; Execution Deferred | Run harness + scoring workflow + findings aggregation contract |
    66	<!-- /ANCHOR:phase-map -->
    67	
    68	---
    69	
    70	<!-- ANCHOR:problem -->
    71	## 2. PROBLEM & PURPOSE
    72	
    73	### Problem Statement
    74	The system-spec-kit "Search / Query / Intelligence" surfaces (memory_search, memory_context, code_graph_query, advisor_recommend, intent classifier, etc.) have grown organically across 26+ optimization packets. Sibling packet `005-memory-search-runtime-bugs` catalogs 17 defects observed in a single live session. We need a reproducible, cross-AI stress-test that quantifies how well the search intelligence performs under realistic prompt variation — not just bug-hunt, but ongoing quality regression.
    75	
    76	### Purpose
    77	Build a playbook that dispatches a fixed prompt corpus (9 scenarios × 3 prompt types) through cli-codex, cli-copilot, and cli-opencode, then scores each outcome against a 5-dimension rubric (correctness, tool selection, latency, token efficiency, hallucination). The asymmetry between cli-opencode (full Spec Kit Memory MCP runtime) and cli-codex/cli-copilot (external runtimes without our MCP) is the test's most informative axis — it reveals whether our search intelligence adds measurable value over off-the-shelf AI capabilities.
    78	<!-- /ANCHOR:problem -->
    79	
    80	---
    81	
    82	<!-- ANCHOR:scope -->
    83	## 3. SCOPE
    84	
    85	### In Scope
    86	- Define the 9-scenario corpus across 3 features (Search, Query, Intelligence) × 3 prompt-types (Simple, Vague, Specific).
    87	- Define the 5-dimension scoring rubric.
    88	- Define the dispatch matrix: which CLI, which model, which agent/profile, which reasoning effort per cell.
    89	- Define the output schema (per-run files + aggregate findings).
    90	- Author dispatch scripts that respect each CLI's concurrency limit (cli-copilot hard cap = 3).
    91	- Sequence two sub-phases: 001 (design — this packet's child) and 002 (execution).
    92	
    93	### Out of Scope
    94	- Fixing the 17 defects in sibling packet `005-memory-search-runtime-bugs` (separate remediation packet handles that).
    95	- Modifying the Search/Query/Intelligence runtime under `mcp_server/`.
    96	- Adding new search features or channels.
    97	- Cross-CLI (cli-claude-code, cli-gemini) — kept to the three the user specified.
    98	- Statistical significance testing beyond N=3 per cell (this is a stress-test playbook, not a benchmark).
    99	
   100	### Files to Change
   101	
   102	| File Path | Change Type | Description |
   103	|-----------|-------------|-------------|
   104	| `spec.md` | Create | This root spec |
   105	| `plan.md` | Create | Two-sub-phase architecture + scoring methodology |
   106	| `tasks.md` | Create | Phase 1 (design) → Phase 2 (execute) → Phase 3 (synthesize) |
   107	| `implementation-summary.md` | Create | Outcome summary (placeholder until execution lands) |
   108	| `description.json` | Create | Indexer metadata |
   109	| `graph-metadata.json` | Create | Graph traversal metadata |
   110	| `001-search-scenario-design/` | Create | Sub-phase: scenario corpus, rubric, dispatch matrix, scripts |
   111	| `002-search-scenario-execution/` | Create | Sub-phase: actual run-and-score harness + findings synthesis |
   112	<!-- /ANCHOR:scope -->
   113	
   114	---
   115	
   116	<!-- ANCHOR:requirements -->
   117	## 4. REQUIREMENTS
   118	
   119	### P0 - Blockers (MUST complete)
   120	
   121	| ID | Requirement | Acceptance Criteria |
   122	|----|-------------|---------------------|
   123	| REQ-001 | Define a fixed 9-scenario corpus | 001-search-scenario-design/spec.md lists exactly 9 scenarios (3 features × 3 prompt types) with prompt text, expected outcome, target tools/anchors, and feature/type tags |
   124	| REQ-002 | Define a 5-dimension rubric | Rubric covers correctness, tool selection, latency, token efficiency, hallucination on a 0-2 scale (10 pts max per scenario) plus 1 narrative dimension |
   125	| REQ-003 | Define dispatch matrix per CLI | For each of cli-codex, cli-copilot, cli-opencode: model id, reasoning effort, sandbox/agent profile, expected concurrency, prompt template wrapper |
   126	| REQ-004 | Honor cli-copilot 3-process concurrency cap | Dispatch script checks `pgrep -f "copilot" \| wc -l` before launch; queues if ≥3 |
   127	
   128	### P1 - Required (complete OR user-approved deferral)
   129	
   130	| ID | Requirement | Acceptance Criteria |
   131	|----|-------------|---------------------|
   132	| REQ-005 | Per-run output schema | Each run produces runs subfolders containing prompt markdown, `output.txt`, `meta.json` (latency_ms, tokens_in, tokens_out, model, exit_code, started_at), score markdown (rubric with evidence) |
   133	| REQ-006 | Aggregate findings format | findings markdown with: per-scenario CLI comparison table, top 3 wins per CLI, top 3 failures per CLI, cross-cutting recommendations |
   134	| REQ-007 | Reproducibility | Dispatch scripts capture the exact CLI invocation (model, effort, flags, dir) so a third party can re-run any cell |
   135	| REQ-008 | Ablation cell for cli-opencode | At least one ablation cell runs cli-opencode WITHOUT spec-kit MCP tools to isolate "model quality" from "MCP advantage" |
   136	
   137	### P2 - Refinement opportunities
   138	
   139	| ID | Requirement | Acceptance Criteria |
   140	|----|-------------|---------------------|
   141	| REQ-009 | Variance via N=3 per cell | Optional: each (scenario × CLI) cell runs 3 times; rubric notes variance |
   142	| REQ-010 | Cross-link to 005 defects | Findings cross-reference REQ IDs from sibling 005-memory-search-runtime-bugs when a scenario surfaces a known defect |
   143	| REQ-011 | Persistent corpus versioning | Scenario corpus has a version (v1.0.0) so future runs can be compared against prior baseline |
   144	<!-- /ANCHOR:requirements -->
   145	
   146	---
   147	
   148	### Acceptance Scenarios
   149	
   150	**Given** the playbook is invoked, **when** sub-phase 001 closes, **then** every REQ-001..004 artifact is present and validates strict.
   151	
   152	**Given** sub-phase 002 runs, **when** all 27 base cells complete (9 scenarios × 3 CLIs), **then** 27 run score markdown files exist + 1 findings markdown aggregate.
   153	
   154	**Given** a third-party developer wants to re-run scenario S2 against cli-codex, **when** they read 002/runs/S2/cli-codex-1/meta.json, **then** they have the exact invocation to reproduce.
   155	
   156	---
   157	
   158	<!-- ANCHOR:success-criteria -->
   159	## 5. SUCCESS CRITERIA
   160	
   161	- **SC-001**: Sub-phase 001 ships a complete dispatch matrix that any operator can execute without further design decisions.
   162	- **SC-002**: Sub-phase 002 produces evidence-backed findings comparing cli-opencode (full MCP) vs cli-codex/cli-copilot (external) performance across all 9 scenarios.
   163	- **SC-003**: Findings surface at least one actionable insight that was not already known from `005-memory-search-runtime-bugs` (i.e., the playbook adds new signal).
   164	- **SC-004**: All three packets validate via `validate.sh --strict`.
   165	<!-- /ANCHOR:success-criteria -->
   166	
   167	---
   168	
   169	<!-- ANCHOR:risks -->
   170	## 6. RISKS & DEPENDENCIES
   171	
   172	| Type | Item | Impact | Mitigation |
   173	|------|------|--------|------------|
   174	| Risk | cli-copilot concurrency limit (3) makes 27-run sweep slow | Low | Sequential dispatch with simple queue; total runtime ~30-45 min |
   175	| Risk | CocoIndex daemon may be down during execution (REQ-012 from 005) | Medium | Pre-flight check; document the channel as unavailable in findings if so |
   176	| Risk | Scoring is partially subjective (correctness, tool selection) | Medium | Document scoring methodology in 001/spec.md; have second reviewer for borderline cells |
   177	| Risk | Production memory DB state changes between runs (causal-graph growth observed in 005) | Low | Snapshot DB state before each run; record snapshot hash in meta.json |
   178	| Dependency | Sibling 005 findings inform expected behavior (e.g., "Semantic Search" → fix_bug bug) | High | Cross-reference 005 REQs in scenario expectations |
   179	| Dependency | All 3 CLIs installed and authenticated | High | Pre-flight check in dispatch script; abort with clear error if missing |
   180	<!-- /ANCHOR:risks -->
   181	
   182	---
   183	
   184	<!-- ANCHOR:questions -->
   185	## 7. OPEN QUESTIONS
   186	
   187	- How many runs per (scenario × CLI) cell? Default to N=1 baseline (27 runs total). Expand to N=3 (81 runs) only if signal is too noisy.
   188	- Should cli-opencode dispatch use `--agent general` (full tool access) or `--agent context` (read-only retrieval focus)? Latter is closer in capability to external CLIs for fair comparison; former tests upper bound.
   189	- Use the live production memory database (realistic, time-varying) or a frozen snapshot (reproducible)? Recommend live for first sweep, snapshot for reruns.
   190	- Should the rubric weight dimensions equally, or weight correctness 2× since it dominates user value? Current spec uses equal weights; revisit after first sweep.
   191	- Should we test the same prompt across multiple cli-copilot models (gpt-5.4 vs claude-opus-4.6 vs gemini-3.1) to compare provider quality? Out of scope for v1, candidate for v2.
   192	<!-- /ANCHOR:questions -->

 succeeded in 0ms:
     1	---
     2	# SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2
     3	title: "Feature Specification [system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec]"
     4	description: "Findings spec cataloging /memory:search runtime bugs and refinements observed via live conversation + reproduction probes (intent classifier, truncation wrapper, output rendering, causal-stats hygiene)."
     5	trigger_phrases:
     6	  - "005-memory-search-runtime-bugs"
     7	  - "memory search runtime bugs"
     8	  - "memory_context truncation drops results"
     9	  - "intent classifier dual-source dissonance"
    10	  - "auto-triggered vocabulary violation"
    11	  - "causal-stats relation omission"
    12	  - "ephemeral session dedup"
    13	  - "folder-discovery misfire"
    14	  - "context quality degraded false hint"
    15	importance_tier: "important"
    16	contextType: "research"
    17	_memory:
    18	  continuity:
    19	    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs"
    20	    last_updated_at: "2026-04-26T14:33:00Z"
    21	    last_updated_by: "claude-opus-4-7"
    22	    recent_action: "Authored findings spec from live /memory:search reproduction"
    23	    next_safe_action: "Cluster fixes by root cause, then sequence remediation work in plan.md"
    24	    blockers: []
    25	    key_files:
    26	      - "spec.md"
    27	      - "plan.md"
    28	      - "tasks.md"
    29	      - "implementation-summary.md"
    30	    session_dedup:
    31	      fingerprint: "sha256:memory-search-runtime-bugs-2026-04-26"
    32	      session_id: "005-memory-search-runtime-bugs-2026-04-26"
    33	      parent_session_id: null
    34	    completion_pct: 25
    35	    open_questions:
    36	      - "Is the truncation logic miscalculating per-result tokens, or is the wrapper over-pruning by design?"
    37	      - "Should intent confidence below threshold T fall back to 'understand', or surface 'unknown'?"
    38	      - "Are enabled/contradicts/derived_from edge types implemented but unused, or absent from the schema entirely?"
    39	    answered_questions: []
    40	template_source_hint: "<!-- SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2 -->"
    41	---
    42	# Feature Specification: /memory:search Runtime Bugs and Refinements
    43	
    44	<!-- SPECKIT_LEVEL: 1 -->
    45	<!-- SPECKIT_TEMPLATE_SOURCE: spec-core | v2.2 -->
    46	
    47	---
    48	
    49	<!-- ANCHOR:metadata -->
    50	## 1. METADATA
    51	
    52	| Field | Value |
    53	|-------|-------|
    54	| **Level** | 1 |
    55	| **Priority** | P1 |
    56	| **Status** | Findings Captured |
    57	| **Created** | 2026-04-26 |
    58	| **Branch** | `main` |
    59	| **Parent Spec** | ../spec.md |
    60	| **Sibling Phases** | `001-cache-warning-hooks`, `002-memory-quality-remediation`, `003-continuity-refactor-gates`, `004-memory-save-rewrite` |
    61	<!-- /ANCHOR:metadata -->
    62	
    63	---
    64	
    65	<!-- ANCHOR:problem -->
    66	## 2. PROBLEM & PURPOSE
    67	
    68	### Problem Statement
    69	A live `/memory:search` session against the indexed-continuity runtime exposed contract violations and degraded UX across the retrieval, output rendering, and causal-graph subcommands. The empty-arguments gate fired correctly, but every downstream stage produced at least one observable defect: the intent classifier emitted `fix_bug` (confidence 0.098) for the query "Semantic Search" despite the spec mandating `understand` as the no-keyword-match fallback; the `memory_context` wrapper reported `truncated=true` and zero `results` while consuming only 2% of its 3000-3500 token budget; the assistant rendering used the explicitly-forbidden phrase "Auto-triggered memories"; `causal-stats` returned three of six valid relation types and labeled itself `health: "healthy"` while reporting `meetsTarget: false`. The root spec at `.opencode/commands/memory/search.md` documents the intended behavior, but the runtime drifts from it on multiple axes.
    70	
    71	### Purpose
    72	Capture the bug catalog with reproducible runtime evidence so a subsequent remediation packet can address each cluster independently and re-verify against the same probes. This spec is intentionally findings-only — fixes belong to a follow-up implementation packet.
    73	<!-- /ANCHOR:problem -->
    74	
    75	---
    76	
    77	<!-- ANCHOR:scope -->
    78	## 3. SCOPE
    79	
    80	### In Scope
    81	- Documenting every observed defect from the conversation transcript and the live reproduction probes against `memory_context`, `memory_search`, and `memory_causal_stats`.
    82	- Cross-referencing each defect against the canonical spec at `.opencode/commands/memory/search.md` to separate documented contract violations from undocumented gaps.
    83	- Clustering defects by root cause to enable independent remediation.
    84	- Recording the literal probe output as evidence so later runs can detect regression or confirm a fix.
    85	
    86	### Out of Scope
    87	- Implementing fixes (deferred to a follow-up packet referenced from `plan.md`).
    88	- Modifying the `/memory:search` command source file at `.opencode/commands/memory/search.md`.
    89	- Touching the runtime MCP server source code under `.opencode/skills/system-spec-kit/mcp_server/`.
    90	- Re-architecting the hybrid retrieval pipeline (graph + vector + FTS5/BM25); only the observable surface defects are catalogued.
    91	
    92	### Files to Change
    93	
    94	| File Path | Change Type | Description |
    95	|-----------|-------------|-------------|
    96	| `spec.md` | Create | This findings spec. |
    97	| `plan.md` | Create | Remediation strategy and root-cause clusters. |
    98	| `tasks.md` | Create | Per-defect work units. |
    99	| `implementation-summary.md` | Create | Placeholder until remediation lands. |
   100	| `description.json` | Create | Spec metadata for memory indexing. |
   101	| `graph-metadata.json` | Create | Graph-derived metadata for traversal. |
   102	<!-- /ANCHOR:scope -->
   103	
   104	---
   105	
   106	<!-- ANCHOR:requirements -->
   107	## 4. REQUIREMENTS
   108	
   109	### P0 — Correctness Bugs (broken contract)
   110	
   111	| ID | Requirement | Acceptance Criteria |
   112	|----|-------------|---------------------|
   113	| REQ-001 | Intent classifier MUST honor the documented no-keyword-match fallback. | For queries with no keyword hit and `confidence < 0.30`, the classifier returns `understand` (per spec §4A "Default fallback") instead of an arbitrary low-confidence intent such as `fix_bug` (currently observed at 0.098 for "Semantic Search"). |
   114	| REQ-002 | `memory_context` MUST NOT zero out results when token usage is far below budget. | Reproduction: `memory_context({input:"Semantic Search", mode:"auto"})` currently returns `meta.tokenBudgetEnforcement.{enforced:true, truncated:true, returnedResultCount:2}` with `actualTokens:71` against `budgetTokens:3000`, and `data.content[0].text` containing `{"count":0,"results":[]}`. After fix, when `actualTokens / budgetTokens < 0.50`, the result count must equal `originalResultCount`. |
   115	| REQ-003 | Output rendering MUST use canonical vocabulary from spec §4A Step 4b. | Render layer (assistant or formatter) emits "Trigger-matched spec-doc records" and "Constitutional rules" — never "Auto-triggered memories", "Triggered memories", or "Memories". |
   116	| REQ-004 | Single intent source-of-truth MUST be exposed per response. | Currently `meta.intent.type = "fix_bug"` (conf 0.098) and `data.queryIntentRouting.queryIntent = "semantic"` (conf 0.8) appear in the SAME response with different values. Define one as authoritative for downstream rendering and either remove the other or label it explicitly as a separate concern (e.g., backend-routing vs intent-classification). |
   117	
   118	### P1 — Degraded Signal (incorrect data exposed to caller)
   119	
   120	| ID | Requirement | Acceptance Criteria |
   121	|----|-------------|---------------------|
   122	| REQ-005 | `causal-stats` MUST emit all six valid relation types (zero-filled if absent). | Spec §5B lists `caused`, `enabled`, `supersedes`, `contradicts`, `derived_from`, `supports`. Runtime returns only the three with non-zero counts. After fix, `data.by_relation` always contains all six keys. |
   123	| REQ-006 | `causal-stats` health field MUST agree with `meetsTarget`. | Currently returns `health: "healthy"` AND `meetsTarget: false`. After fix, `meetsTarget=false` ⇒ `health ∈ {"degraded","below_target"}`. |
   124	| REQ-007 | `QUALITY=gap` flag MUST trigger automatic broadening before returning. | Spec §1 promises 3-tier FTS fallback (FTS5 → BM25 → Grep) on weak retrievals. Currently `avg_score:0.13`, `quality:"gap"` is reported but no broadening occurs. After fix, gap-flagged retrievals attempt at least one fallback tier before returning. |
   125	| REQ-008 | Folder-discovery MUST NOT auto-bind on weak signal. | Currently "Semantic Search" caused `folderDiscovery.specFolder = "skilled-agent-orchestration/023-sk-deep-research-creation"` (no semantic relationship). After fix, folder-binding requires either explicit `specFolder` parameter or per-token similarity above a documented threshold. |
   126	| REQ-009 | "Context quality is degraded" hint MUST be conditional on actual session state. | Currently emitted on every fresh ephemeral session. After fix, hint is suppressed when `sessionScope=="ephemeral"` and `eventCounterStart==0`. |
   127	| REQ-010 | Causal-graph edge growth MUST be balanced across relation types. | Two snapshots ~15 minutes apart show 344 new edges, ALL `supersedes`. After fix, document the autonomous backfill job, expose its scope, and add per-relation coverage targets so `caused`/`supports`/etc. do not stagnate. |
   128	| REQ-011 | Session deduplication MUST be effective across calls within a single user session. | Currently each `/memory:search` invocation gets a new ephemeral `effectiveSessionId`, so `enableDedup=true` never engages. After fix, command threads a stable session identifier (e.g., per OpenCode session) or documents the limitation explicitly. |
   129	
   130	### P2 — Refinement Opportunities
   131	
   132	| ID | Requirement | Acceptance Criteria |
   133	|----|-------------|---------------------|
   134	| REQ-012 | CocoIndex daemon health MUST be checked before relying on the vector channel. | Current behavior: command attempts CocoIndex search, fails silently when daemon is down. After fix, command emits an explicit `WARN: vector channel unavailable, lexical-only` line in the result block when daemon is unreachable. |
   135	| REQ-013 | Sub-target coverage MUST emit a remediation suggestion. | Currently `causal-stats` reports below-target coverage with no actionable hint. After fix, output includes "Top N unlinked records" or "Run X to backfill". |
   136	| REQ-014 | AskUserQuestion custom-answer routing MUST be defined. | Spec §4 offers 7 intents + "Analysis tools". A custom answer like "Semantic Search" currently becomes the QUERY (auto-detect intent) — undocumented. Either document this routing or add explicit "Code search / Explore codebase" option that routes to CocoIndex. |
   137	| REQ-015 | Trigger and constitutional channels SHOULD participate in dedup. | Currently the same 5 trigger matches resurface across calls in the same conversation; cosmetically redundant. |
   138	| REQ-016 | Intent classifier MUST be stable across paraphrased queries. | "Semantic Search" → `fix_bug`; "Find stuff related to semantic search" → `understand`. Refinement: add a stability test corpus and tune keywords or add embedding-based classification for low-confidence cases. |
   139	| REQ-017 | Naming collision between "code graph" (structural) and "causal graph" (memory) MUST be disambiguated. | Currently the startup hook says `Code Graph: empty` while `causal-stats` reports 1135 edges across 675 linked records. After fix, startup hook says "structural code graph" and `causal-stats` says "memory causal graph", or reuse a single canonical noun.|
   140	<!-- /ANCHOR:requirements -->
   141	
   142	---
   143	
   144	### Acceptance Scenarios
   145	
   146	**Given** a query with no documented intent keywords, **when** the classifier runs with confidence below 0.30, **then** it returns `understand` per spec §4A.
   147	
   148	**Given** a `memory_context` call where `actualTokens` is under 50% of `budgetTokens`, **when** the response is built, **then** `returnedResultCount` equals `originalResultCount` and `data.content` contains the actual results (not `count:0,results:[]`).
   149	
   150	**Given** a `causal-stats` call, **when** the response is built, **then** `by_relation` contains all six valid relation keys (zero-filled if absent) and `health` agrees with `meetsTarget`.
   151	
   152	**Given** an empty-results situation with trigger matches, **when** the formatter renders, **then** the heading reads "Trigger-matched spec-doc records (matched on phrase \"<keyword>\")" and never "Auto-triggered memories".
   153	
   154	---
   155	
   156	<!-- ANCHOR:success-criteria -->
   157	## 5. SUCCESS CRITERIA
   158	
   159	- **SC-001**: Every defect in §4 has a reproducible probe (command + expected literal output diff) recorded in `tasks.md`.
   160	- **SC-002**: Defects are clustered by root cause in `plan.md` so remediation can proceed cluster-by-cluster.
   161	- **SC-003**: The follow-up remediation packet, when implemented, can re-run the probes here and observe each acceptance criterion pass.
   162	- **SC-004**: Validation passes via `bash .opencode/skills/system-spec-kit/scripts/spec/validate.sh <this-folder> --strict`.
   163	<!-- /ANCHOR:success-criteria -->
   164	
   165	---
   166	
   167	<!-- ANCHOR:risks -->
   168	## 6. RISKS & DEPENDENCIES
   169	
   170	| Type | Item | Impact | Mitigation |
   171	|------|------|--------|------------|
   172	| Risk | Some defects may share a single root cause; over-counting could inflate scope. | Medium | `plan.md` clusters defects by root cause before remediation work begins. |
   173	| Risk | Probes are timestamp-bound (causal-graph edge counts grow); regression detection needs a different metric. | Low | Use coverage percent and presence-of-relation-type rather than absolute edge counts. |
   174	| Dependency | Remediation work touches `mcp_server/` source which is owned by sibling phases. | High | Coordinate with `004-memory-save-rewrite` and any active 005-memory-indexer-invariants work before landing changes. |
   175	| Dependency | CocoIndex daemon must be runnable for REQ-012 verification. | Medium | Document the start command and add a smoke test before remediation lands. |
   176	<!-- /ANCHOR:risks -->
   177	
   178	---
   179	
   180	<!-- ANCHOR:questions -->
   181	## 7. OPEN QUESTIONS
   182	
   183	- Is the truncation logic miscalculating per-result tokens, or is the wrapper over-pruning by design? Probe: log `tokenUsageSource`, per-result token estimate, and pruning decisions to identify whether estimates are inflated 30-50× (which would explain dropping at 2% reported usage).
   184	- Should intent confidence below threshold T fall back to `understand`, or surface a sentinel `unknown`? Spec says fallback is `understand`; runtime appears to skip the fallback.
   185	- Are `enabled`, `contradicts`, `derived_from` edge types implemented in the schema but unused, or absent entirely? Inspect `causal_edges` table and `memory_causal_link` enum to confirm.
   186	- Why does `health: "healthy"` co-exist with `meetsTarget: false`? Either definition is wrong, or "healthy" measures something else (orphaned edges = 0?).
   187	- Is the supersedes-only edge growth driven by an autonomous backfill job? If so, where does it live, and how can other relation types participate?
   188	
   189	### Reproduction Evidence (captured 2026-04-26)
   190	
   191	These probes are stored under §7 to keep the canonical Level 1 template structure intact while preserving the regression-detection anchor.
   192	
   193	Probe 1 — Intent classifier mis-routing:
   194	```
   195	memory_context({input:"Semantic Search", mode:"auto"})
   196	→ meta.intent.type = "fix_bug"
   197	  meta.intent.confidence = 0.0980
   198	  meta.intent.source = "auto-detected"
   199	  data.queryIntentRouting.queryIntent = "semantic"
   200	  data.queryIntentRouting.confidence = 0.8
   201	  data.queryIntentRouting.matchedKeywords = ["search"]
   202	```
   203	Spec §4A keyword table assigns NONE of {"semantic","search"} to `fix_bug`; the documented fallback is `understand`.
   204	
   205	Probe 2 — Truncation drops to zero at 2% budget:
   206	```
   207	memory_context({input:"Semantic Search", mode:"auto"})
   208	→ meta.tokenBudgetEnforcement = {budgetTokens:3000, actualTokens:71,
   209	   enforced:true, truncated:true, originalResultCount:5, returnedResultCount:2}
   210	  data.content[0].text = '{"summary":"Context truncated to fit token budget","data":{"count":0,"results":[]}, ...}'
   211	```
   212	71 / 3000 = 2.4% utilization; 5 results pruned to 0 in payload despite meta claiming 2 returned.
   213	
   214	Probe 3 — Causal-stats inconsistency:
   215	```
   216	memory_causal_stats()
   217	→ data.by_relation = {caused: 236, supersedes: 786, supports: 113}
   218	  data.health = "healthy"  data.meetsTarget = false
   219	  data.targetCoverage = "60%"  data.currentCoverage = "56.21%"
   220	```

exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/010-graph-impact-and-affordance-uplift/007-review-remediation/spec.md | sed -n '90,140p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
    90	## 4. REQUIREMENTS
    91	
    92	### P0 — Already resolved
    93	| ID | Status |
    94	|----|--------|
    95	| ~~LICENSE verbatim quote~~ | RESOLVED — External Project name scrubbed from codebase; no LICENSE quote needed |
    96	
    97	### P1 — In scope (21 findings)
    98	
    99	| ID | Sub-phase | Theme | Description |
   100	|----|-----------|-------|-------------|
   101	| R-007-1 | 001 | T-F | Drop "GitNexus"-era continuity + status mismatch in 001 (covered by scrub) |
   102	| R-007-2 | 002 | T-A | Wire `detect_changes` to MCP dispatcher (or mark internal-only in all docs) |
   103	| R-007-3 | 002 | T-D | Diff path canonicalization — reject paths outside `canonicalRootDir` |
   104	| R-007-4 | 002 | T-D | `parseUnifiedDiff` multi-file boundary fix (track expected hunk line counts) |
   105	| R-007-5 | 002 | T-B | Run vitest + tsc + validate.sh; record real evidence in 002 implementation-summary |
   106	| R-007-6 | 003 | T-C | Add `minConfidence` to MCP tool schema, Zod validator, allowed-parameter ledger |
   107	| R-007-7 | 003 | T-B | Run code_graph vitest + tsc + validate.sh; record real evidence in 003 |
   108	| R-007-8 | 004 | T-A | Decide `conflicts_with` affordance edge contract (validate-or-serialize) |
   109	| R-007-9 | 004 | T-D | Broaden prompt-injection denylist (TS + PY) for affordance-normalizer |
   110	| R-007-10 | 004 | T-C | Expose score-time `affordances` via public advisor-recommend input schema OR document compile-time-only |
   111	| R-007-11 | 005 | T-D | Reject incomplete explicit `trustBadges` payloads (or merge per-field) |
   112	| R-007-12 | 005 | T-A | Memory_search cache invalidation on causal-edge mutations (causal-edge generation in cache key) |
   113	| R-007-13 | 005 | T-E | Unskip trust-badges SQL tests via DI fixture or real-DB integration |
   114	| R-007-14 | 006 | T-A | Sync `detect_changes` integration story across handler/schema/dispatcher/docs |
   115	| R-007-15 | 006 | T-B | Mark verification operator-pending where commands didn't run; separate "estimated" from "passed" |
   116	| R-007-16 | 006 | T-F | Fix INSTALL_GUIDE smoke-test cwd bug (Python path mismatch after `cd`) |
   117	| R-007-17 | 006 | T-F | Resolve conflicting MCP tool counts across umbrella docs (one canonical source) |
   118	| R-007-18 | 006 | T-F | Restore or remove `FEATURE_CATALOG_IN_SIMPLE_TERMS.md` link |
   119	| R-007-19 | 002 | T-B | Update 002 checklist to uncheck operator-pending items (no premature PASS) |
   120	| R-007-20 | 003 | T-B | Update 003 checklist same way |
   121	| R-007-21 | 005 | T-B | Update 005 checklist same way |
   122	
   123	### P2 — Actionable subset (12 of 22 findings; rest deferred per below)
   124	
   125	| ID | Sub-phase | Theme | Description |
   126	|----|-----------|-------|-------------|
   127	| R-007-P2-1 | 002 | T-D | Phase runner reject duplicate output keys (mirror duplicate-name rejection) |
   128	| R-007-P2-2 | 002 | T-D | Wrap `runPhases` in try/finally so failures emit error-outcome metric |
   129	| R-007-P2-3 | 003 | T-D | Edge `reason`/`step` allowlist on read path (sanitize stale/imported rows) |
   130	| R-007-P2-4 | 003 | T-F | `computeBlastRadius` off-by-one on `limit_reached` (request `limit + 1`) |
   131	| R-007-P2-5 | 003 | T-F | Multi-subject blast-radius preserves resolved seeds when sibling fails |
   132	| R-007-P2-6 | 003 | T-D | Failure-fallback emits stable `code` + log/metric (operator visibility) |
   133	| R-007-P2-7 | 003 | T-F | Extract shared relationship-edge mapper (deduplicate 4 switch branches) |
   134	| R-007-P2-8 | 004 | T-D | Shared adversarial fixture for TS + PY sanitizers |
   135	| R-007-P2-9 | 004 | T-D | Debug counters for affordance-input drop categories |
   136	| R-007-P2-10 | 005 | T-D | Sanitize/cap `extractionAge` / `lastAccessAge` strings to allowlisted grammar |
   137	| R-007-P2-11 | 005 | T-D | Trace flag `{attempted, derivedCount, failureReason}` for badge derivation |
   138	| R-007-P2-12 | 006 | T-F | Phase-naming alias note (012 → 010 wrapper) where docs still reference 012 |
   139	
   140	### P2 — Deferred (10 findings — track but don't fix in 010/007)

exec
/bin/zsh -lc 'rg -n "function|async function|export|memory_search|toolCache|cache|causal|FTS|BM25|vector|search" .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts .opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts .opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts .opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts .opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts' in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:16:} from '../lib/search/session-transition.js';
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:36:} from '../lib/search/recovery-payload.js';
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:44:} from '../lib/search/confidence-scoring.js';
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:51:} from '../lib/search/result-explainability.js';
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:62:export interface AnchorTokenMetrics {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:70:/** Raw search result from database/vector search */
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:71:export interface RawSearchResult {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:78:  /** Raw vector cosine similarity (0-100 scale from sqlite-vec). */
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:89:/** Formatted search result */
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:90:export interface FormattedSearchResult {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:95:  /** Raw vector cosine similarity (0-100 scale from sqlite-vec), or averageSimilarity for multi-concept. */
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:112:export interface MemoryResultScores {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:122:export interface MemoryResultSource {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:130:export interface MemoryResultTrace {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:179:export interface MemoryTrustBadges {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:187:export interface MemoryResultEnvelope extends FormattedSearchResult {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:201:export interface MemoryParserLike {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:205:export interface TrustBadgeSnapshot {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:214:export type { MCPResponse };
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:221:export function validateFilePathLocal(filePath: string): string {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:238:export function safeJsonParse<T>(str: string | null | undefined, fallback: T): T {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:247:function toNullableNumber(value: unknown): number | null {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:256:function clampConfidence(value: unknown): number | null {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:279:function sanitizeAgeLabel(value: unknown, fallbackIso: unknown): string {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:298:function normalizeExplicitTrustBadges(value: unknown): MemoryTrustBadgePartial | null {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:331:export function toTrustBadges(snapshot: TrustBadgeSnapshot | null): MemoryTrustBadges | undefined {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:351:function mergeTrustBadges(
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:392: * Resolve causal-edge / weight-history badge snapshots for the given results.
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:402:export function fetchTrustBadgeSnapshots(
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:453:    // causal_edges. better-sqlite3 binds JS numbers as REAL, which would
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:476:        LEFT JOIN causal_edges ce
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:523:function resolveCompositeScore(rawResult: RawSearchResult): number | null {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:535:function resolveScoreResolution(rawResult: RawSearchResult): MemoryResultTrace['scoreResolution'] {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:543:function extractAnchorDetails(rawResult: RawSearchResult): { anchorIds: string[]; anchorTypes: string[] } {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:556:function addChannel(channelsUsed: Set<string>, candidate: unknown): void {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:563:function extractAttributedChannels(rawResult: RawSearchResult): string[] {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:587:function extractTrace(rawResult: RawSearchResult, extraData?: Record<string, unknown>): MemoryResultTrace {
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:698:export async function formatSearchResults(
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:700:  searchType: string,
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:729:      tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:732:        searchType: searchType,
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:741:        'Try broadening your search query',
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:850:    // Prefer precomputed chunk reassembly from memory-search to avoid disk reads.
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1027:    searchType: searchType,
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1039:    const { searchType: _s, count: _c, constitutionalCount: _cc, results: _r, ...safeExtra } = extraData as Record<string, unknown>;
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1044:    tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1053:   5. (ESM exports above — no CommonJS module.exports needed)
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:4:// Feature catalog: Tool-level TTL cache
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:48:  cacheGeneration: number;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:67:const cache = new Map<string, CacheEntry>();
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:78:function enforceAuxCacheBound<K, V>(map: Map<K, V>): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:92:let cacheGeneration = 0;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:98:function generateCacheKey(toolName: string, args: unknown): string {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:100:    throw new Error('[tool-cache] toolName must be a non-empty string');
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:108:function canonicalizeArgs(args: unknown): string {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:113:function sortKeys(value: unknown): unknown {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:143:function get<T = unknown>(key: string): T | null {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:146:  const entry = cache.get(key) as CacheEntry<T> | undefined;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:153:    cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:163:function set<T = unknown>(key: string, value: T, options: SetOptions = {}): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:169:  if (cache.size >= TOOL_CACHE_CONFIG.maxEntries) {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:180:  cache.set(key, entry as CacheEntry);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:184:function has(key: string): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:187:  const entry = cache.get(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:191:    cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:199:function del(key: string): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:200:  const deleted = cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:207:function getToolGeneration(toolName: string): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:211:function bumpToolGeneration(toolName: string): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:216:function removeInFlightWhere(predicate: (entry: InFlightEntry) => boolean): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:233:function matchesTool(regex: RegExp, toolName: string): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:242:function invalidateByTool(toolName: string): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:245:  for (const [key, entry] of cache.entries()) {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:252:    cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:262:function invalidateByPattern(pattern: RegExp | string): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:267:    console.warn(`[tool-cache] Invalid regex pattern: ${error instanceof Error ? error.message : String(error)}`);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:273:  for (const [key, entry] of cache.entries()) {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:287:    cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:299:function clear(): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:300:  const count = cache.size;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:302:  cache.clear();
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:305:  cacheGeneration++;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:310:function invalidateOnWrite(operation: string, _context: Record<string, unknown> = {}): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:312:    'memory_search',
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:327:    console.error(`[tool-cache] Invalidated ${totalInvalidated} entries after ${operation}`);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:339:function evictOldest(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:340:  const oldestKey = cache.keys().next().value;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:342:    cache.delete(oldestKey);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:347:function cleanupExpired(): number {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:351:  for (const [key, entry] of cache.entries()) {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:358:    cache.delete(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:365:function startCleanupInterval(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:377:function stopCleanupInterval(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:388:async function withCache<T>(
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:401:  const generationAtStart = cacheGeneration;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:405:  const cached = get<T>(key);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:406:  if (cached !== null) {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:407:    return cached;
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:414:    && existing.cacheGeneration === generationAtStart
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:426:    cacheGeneration: generationAtStart,
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:433:      generationAtStart === cacheGeneration
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:459:function getStats(): CacheStats {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:469:    currentSize: cache.size,
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:474:function resetStats(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:481:function getConfig(): ToolCacheConfig {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:485:function isEnabled(): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:493:function init(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:495:  console.error(`[tool-cache] Initialized with ${TOOL_CACHE_CONFIG.defaultTtlMs}ms TTL, max ${TOOL_CACHE_CONFIG.maxEntries} entries`);
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:498:function shutdown(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:502:  console.error('[tool-cache] Shutdown complete');
.opencode/skills/system-spec-kit/mcp_server/lib/cache/tool-cache.ts:514:export {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:14:import * as intentClassifier from '../lib/search/intent-classifier.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:21:import { handleMemorySearch } from './memory-search.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:43:} from '../lib/search/session-transition.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:47:import * as vectorIndex from '../lib/search/vector-index.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:53:import { discoverSpecFolder, getSpecsBasePaths } from '../lib/search/folder-discovery.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:59:} from '../lib/search/search-flags.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:88:  includeTrace?: boolean; // CHK-040: Forward to internal memory_search calls
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:124:  includeTrace?: boolean; // CHK-040: Forward to internal memory_search calls
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:127:  /** REQ-D5-003: Presentation profile ('quick'|'research'|'resume'|'debug'). Default: full response. */
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:235:function extractResultRowsFromContextResponse(responseText: string): Array<Record<string, unknown>> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:265:function readResumeDocumentContent(documentPath: string): string {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:273:function formatResumeLadderContent(result: ResumeLadderResult, row: ResumeRow): string {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:293:function normalizeResumeSource(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:305:function normalizeResumeDocumentType(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:314:function convertResumeLadderToRows(result: ResumeLadderResult, limit: number): ResumeRow[] {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:351:function extractStrategyError(result: ContextResult): StrategyErrorPayload | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:401:function buildStructuralRoutingNudge(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:447:function enforceTokenBudget(result: ContextResult, budgetTokens: number): { result: ContextResult; enforcement: TokenBudgetEnforcement } {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:530:            tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:542:            tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:559:          tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:570:          tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:860:  // Deep: Comprehensive semantic search with full context
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:863:    description: 'Semantic search with full context retrieval',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:864:    strategy: 'search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:868:  // Focused: Intent-specific search with optimized weights
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:871:    description: 'Intent-aware search with task-specific optimization',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:872:    strategy: 'intent-search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:903:async function executeQuickStrategy(input: string, options: ContextOptions): Promise<ContextResult> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:922:async function executeDeepStrategy(input: string, intent: string | null, options: ContextOptions): Promise<ContextResult> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:952:async function executeFocusedStrategy(input: string, intent: string | null, options: ContextOptions): Promise<ContextResult> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:983:async function executeResumeStrategy(input: string, intent: string | null, options: ContextOptions): Promise<ContextResult> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1035:function resolveSessionLifecycle(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1037:  db: ReturnType<typeof vectorIndex.getDb> | null,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1077:function resolveEffectiveMode(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1162:function maybeDiscoverSpecFolder(options: ContextOptions, args: ContextArgs): string | undefined {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1186:async function executeStrategy(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1209:function buildResponseMeta(params: BuildResponseMetaParams): Record<string, unknown> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1304:async function handleMemoryContext(args: ContextArgs): Promise<MCPResponse> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1546:        detectedIntent as import('../lib/search/intent-classifier.js').IntentType
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1571:  // in vector-index-queries.ts (m.spec_folder = ?) which silently drops all
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1603:        alternativeLayers: layerDefs.getRecommendedLayers('search')
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1706:      `For more granular control, use L2 tools: memory_search, memory_match_triggers`,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1737:    const db = vectorIndex.getDb();
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1826:export {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1836:export {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:4:// Feature catalog: Causal edge creation (memory_causal_link)
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:7:import { clearDegreeCacheForDb } from '../search/graph-search-fn.js';
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:11:import { isTemporalEdgesEnabled } from '../search/search-flags.js';
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:35:  caused:       1.3,  // Strong causal link
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:36:  enabled:      1.1,  // Weak causal link
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:53:function isFiniteNumber(value: unknown): value is number {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:57:function clampStrength(strength: number): number | null {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:62:function normalizeCausalEdgeRow(row: Record<string, unknown>): CausalEdge {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:135:  edgeId?: number;          // T202: causal_edges.id for unlink workflow
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:151: * Monotonically-increasing generation counter bumped on every causal-edge
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:153: * value in cache keys (e.g. memory_search when `enableCausalBoost=true`) so
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:154: * cached responses derived from the causal graph become stale on the next
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:155: * lookup without requiring a wholesale tool-cache invalidation.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:157: * R-007-12 — targeted memory_search cache invalidation.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:159:let causalEdgesGeneration = 0;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:161:function bumpCausalEdgesGeneration(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:164:  causalEdgesGeneration = causalEdgesGeneration >= Number.MAX_SAFE_INTEGER
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:166:    : causalEdgesGeneration + 1;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:169:function getCausalEdgesGeneration(): number {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:170:  return causalEdgesGeneration;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:173:function invalidateDegreeCache(): void {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:174:  // R-007-12: bump the causal-edges generation FIRST so any cache key that
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:175:  // includes it (e.g. memory_search when enableCausalBoost=true) becomes
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:180:    // H1 FIX: Use db-specific cache invalidation instead of the no-op global version
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:190:    // Graph signals cache invalidation is best-effort
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:198:function init(database: Database.Database): void {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:206:    database.exec('CREATE INDEX IF NOT EXISTS idx_causal_source ON causal_edges(source_id)');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:207:    database.exec('CREATE INDEX IF NOT EXISTS idx_causal_target ON causal_edges(target_id)');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:218:function insertEdge(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:229:    console.warn('[causal-edges] Database not initialized. Server may still be starting up.');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:245:  // Implementing FK validation would require seeding memory_index in 20+ causal edge tests.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:251:      console.warn(`[causal-edges] Edge bounds: node ${sourceId} has ${edgeCount} edges (max ${MAX_EDGES_PER_NODE}), rejecting auto edge`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:259:      console.warn('[causal-edges] insertEdge rejected non-finite strength');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:279:        SELECT id, strength FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:293:          UPDATE causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:306:          INSERT INTO causal_edges (
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:330:        SELECT id FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:358:    console.warn(`[causal-edges] insertEdge error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:366:function insertEdgesBatch(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:410:    console.warn(`[causal-edges] insertEdgesBatch error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:416:function bulkInsertEdges(edges: Array<Record<string, unknown>>): { inserted: number; failed: number } {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:424:    const edgeColumns = (database.prepare('PRAGMA table_info(causal_edges)').all() as Array<{ name: string }>)
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:433:      INSERT OR IGNORE INTO causal_edges (${edgeColumns.join(', ')})
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:465:    console.warn(`[causal-edges] bulkInsertEdges error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:471:function createEdgeQueryResult(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:482:function getEdgesFrom(sourceId: string, limit: number = MAX_EDGES_LIMIT): EdgeQueryResult {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:487:      SELECT * FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:496:        console.warn(`[causal-edges] touchEdgeAccess failed for edge ${edge.id}: ${e instanceof Error ? e.message : String(e)}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:502:    console.warn(`[causal-edges] getEdgesFrom error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:507:function getEdgesTo(targetId: string, limit: number = MAX_EDGES_LIMIT): EdgeQueryResult {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:512:      SELECT * FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:521:        console.warn(`[causal-edges] touchEdgeAccess failed for edge ${edge.id}: ${e instanceof Error ? e.message : String(e)}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:527:    console.warn(`[causal-edges] getEdgesTo error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:532:function getAllEdges(limit: number = MAX_EDGES_LIMIT): EdgeQueryResult {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:537:      SELECT * FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:546:    console.warn(`[causal-edges] getAllEdges error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:555:function getCausalChain(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:573:  function traverse(node: CausalChainNode, depth: number, path: Set<string>): void {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:618:function updateEdge(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:635:        console.warn('[causal-edges] updateEdge rejected non-finite strength');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:665:          'SELECT strength FROM causal_edges WHERE id = ?'
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:673:        `UPDATE causal_edges SET ${parts.join(', ')} WHERE id = ?`
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:695:    console.warn(`[causal-edges] updateEdge error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:700:function deleteEdge(edgeId: number): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:705:      'DELETE FROM causal_edges WHERE id = ?'
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:713:    console.warn(`[causal-edges] deleteEdge error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:721:function deleteEdgesForMemory(memoryId: string): number {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:725:    DELETE FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:738:function getGraphStats(): GraphStats {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:744:    const total = (db.prepare('SELECT COUNT(*) as count FROM causal_edges') as Database.Statement).get() as { count: number };
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:745:    const byRelation = (db.prepare('SELECT relation, COUNT(*) as count FROM causal_edges GROUP BY relation') as Database.Statement).all() as Array<{ relation: string; count: number }>;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:746:    const avgStrength = (db.prepare('SELECT AVG(strength) as avg FROM causal_edges') as Database.Statement).get() as { avg: number | null };
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:747:    const sources = (db.prepare('SELECT COUNT(DISTINCT source_id) as count FROM causal_edges') as Database.Statement).get() as { count: number };
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:748:    const targets = (db.prepare('SELECT COUNT(DISTINCT target_id) as count FROM causal_edges') as Database.Statement).get() as { count: number };
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:764:    console.warn(`[causal-edges] getGraphStats error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:769:function findOrphanedEdges(): CausalEdge[] {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:774:      SELECT ce.* FROM causal_edges ce
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:780:    console.warn(`[causal-edges] findOrphanedEdges error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:786:function cleanupOrphanedEdges(): { deleted: number } {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:800:    console.warn(`[causal-edges] cleanupOrphanedEdges error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:810: * Create causal relationship chain between spec folder documents.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:812: * Also: checklist SUPPORTS spec, decision-record SUPPORTS plan, research SUPPORTS spec
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:816:function createSpecDocumentChain(documentIds: Record<string, number>): { inserted: number; failed: number } {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:847:  if (ids.research && ids.spec) {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:848:    edges.push({ sourceId: String(ids.research), targetId: String(ids.spec), relation: RELATION_TYPES.SUPPORTS, strength: 0.7, evidence: 'Spec 126: research supports spec' });
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:860:function logWeightChange(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:874:function getWeightHistory(edgeId: number, limit: number = 50): WeightHistoryEntry[] {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:885:    console.warn(`[causal-edges] getWeightHistory error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:890:function rollbackWeights(edgeId: number, toTimestamp: string): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:898:        'SELECT strength FROM causal_edges WHERE id = ?'
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:933:        'UPDATE causal_edges SET strength = ? WHERE id = ?'
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:949:    console.warn(`[causal-edges] rollbackWeights error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:958:function countEdgesForNode(nodeId: string): number {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:962:      SELECT COUNT(*) as count FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:968:    console.warn(`[causal-edges] countEdgesForNode error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:973:function touchEdgeAccess(edgeId: number): void {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:976:    "UPDATE causal_edges SET last_accessed = datetime('now') WHERE id = ?"
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:980:function getStaleEdges(thresholdDays: number = STALENESS_THRESHOLD_DAYS): CausalEdge[] {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:984:      SELECT * FROM causal_edges
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:992:    console.warn(`[causal-edges] getStaleEdges error: ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:1001:export {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:1039:  // R-007-12: Generation counter for memory_search cache invalidation
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:1044: * Re-exports related public types.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:1046:export type {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:8:import * as toolCache from '../lib/cache/tool-cache.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:9:import * as causalEdges from '../lib/storage/causal-edges.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:11:import * as intentClassifier from '../lib/search/intent-classifier.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:13:import { isSessionBoostEnabled, isCausalBoostEnabled, isCommunitySearchFallbackEnabled, isDualRetrievalEnabled, isIntentAutoProfileEnabled } from '../lib/search/search-flags.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:14:import { searchCommunities } from '../lib/search/community-search.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:16:import { executePipeline } from '../lib/search/pipeline/index.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:17:import type { PipelineConfig, PipelineResult } from '../lib/search/pipeline/index.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:18:import type { IntentWeightsConfig } from '../lib/search/pipeline/types.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:22:import { getStrategyForQuery } from '../lib/search/artifact-routing.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:24:import { collapseAndReassembleChunkResults } from '../lib/search/chunk-reassembly.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:33:} from '../lib/search/search-utils.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:34:// CacheArgsInput used internally by buildCacheArgs (lib/search/search-utils.ts)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:70:} from '../lib/search/session-transition.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:82:} from '../lib/search/progressive-disclosure.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:91:} from '../lib/search/sqlite-fts.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:92:import type { LexicalCapabilitySnapshot } from '../lib/search/sqlite-fts.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:99:} from '../lib/search/session-state.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:102:import type { IntentType, IntentWeights as IntentClassifierWeights } from '../lib/search/intent-classifier.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:104:// RoutingResult, WeightedResult — now used internally by lib/search/search-utils.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:106:// Feature catalog: Semantic and lexical search (memory_search)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:107:// Feature catalog: Hybrid search pipeline
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:109:// Feature catalog: Quality-aware 3-tier search fallback
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:117: * Internal search result row — enriched DB row used within this handler.
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:183:  'research',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:193:function normalizeDocumentType(value: unknown): string | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:201:function resolveAnchorId(row: Record<string, unknown>): string | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:208:function resolveFilePath(row: Record<string, unknown>): string | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:215:function resolveCanonicalSourceKind(row: Record<string, unknown>): CanonicalSourceKind | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:254:function filterCanonicalSourceRows<T extends SessionAwareResult>(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:288:// ChunkReassemblyResult — now imported from lib/search/chunk-reassembly.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:292:function toIntentWeightsConfig(weights: IntentWeights | null): IntentWeightsConfig | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:330:  includeArchived?: boolean; // REQ-206: include archived memories in search (default false)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:338:  /** REQ-D5-003: Presentation profile ('quick'|'research'|'resume'|'debug'). Default: full response. */
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:344:// resolveRowContextType — now imported from lib/search/search-utils.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:347:function attachTelemetryMeta(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:372:    console.warn('[memory-search] Failed to attach telemetry payload:', message);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:377:function extractResponseResults(response: MCPResponse): Array<Record<string, unknown>> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:396:function extractSearchCachePayload(response: MCPResponse): SearchCachePayload | null {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:422:function parseResponseEnvelope(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:440:function replaceResponseEnvelope(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:451:function buildSessionStatePayload(sessionId: string): Record<string, unknown> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:461:function buildSearchResponseFromPayload(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:464:  cacheHit: boolean,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:467:    tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:472:    cacheHit,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:476:function attachLexicalCapabilityMetadata(
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:500:function hasPublicationContractFields(result: Record<string, unknown>): boolean {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:510:function applyPublicationGateToResponse(response: MCPResponse): MCPResponse {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:559:// resolveArtifactRoutingQuery, applyArtifactRouting — now imported from lib/search/search-utils.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:560:// CacheArgsInput — now imported from lib/search/search-utils.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:561:// parseNullableInt, collapseAndReassembleChunkResults — now imported from lib/search/chunk-reassembly.ts
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:577:function applySessionDedup(results: MemorySearchRow[], sessionId: string, enableDedup: boolean): DedupResult {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:603:// Path. The V2 4-stage pipeline handles all equivalent functionality.
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:609:/** Handle memory_search tool — performs hybrid vector/BM25 search with intent-aware ranking.
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:611: * @returns MCP response with ranked search results
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:613:async function handleMemorySearch(args: SearchArgs): Promise<MCPResponse> {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:614:  const _searchStartTime = Date.now();
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:668:  // Validate at least one search input is provided (moved from schema superRefine for GPT compatibility)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:680:        tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:685:          hint: 'Retry the original search to generate a fresh continuation cursor',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:692:      tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:699:      startTime: _searchStartTime,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:700:      cacheHit: false,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:720:          tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:739:      tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:751:      tool: 'memory_search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:772:  } catch (_error: unknown) { /* eval logging must never break search */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:791:      console.warn(`[memory-search] Invalid intent '${explicitIntent}', using auto-detection`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:802:      console.error(`[memory-search] Intent auto-detected as '${detectedIntent}' (fallback: ${classification.reason})`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:804:      console.error(`[memory-search] Intent auto-detected as '${detectedIntent}' (confidence: ${intentConfidence.toFixed(2)})`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:811:    console.error(`[memory-search] Intent confidence ${intentConfidence.toFixed(3)} below floor ${INTENT_CONFIDENCE_FLOOR}, overriding '${detectedIntent}' → 'understand'`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:825:        console.error(`[memory-search] Intent-to-profile auto-routing: '${detectedIntent}' → profile '${autoProfile}'`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:828:      // Auto-profile is best-effort — never breaks search
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:847:  // R-007-12: When causal boost is enabled, fold the causal-edges generation
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:848:  // counter into the cache key so causal-edge mutations naturally invalidate
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:849:  // the affected memory_search entries on the next lookup. We deliberately
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:850:  // keep the generation OFF the key when the caller has not opted into causal
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:851:  // boost — otherwise unrelated callers would suffer needless cache misses.
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:852:  const causalEdgesGenerationForCache = enableCausalBoost
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:853:    ? causalEdges.getCausalEdgesGeneration()
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:856:  // Build cache key args
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:857:  const cacheArgs = buildCacheArgs({
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:886:    cacheVersion: CANONICAL_READER_CACHE_VERSION,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:887:    causalEdgesGeneration: causalEdgesGenerationForCache,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:891:  const cacheKey = toolCache.generateCacheKey('memory_search', cacheArgs);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:892:  const cacheEnabled = toolCache.isEnabled() && !bypassCache;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:893:  const cachedPayload = cacheEnabled
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:894:    ? toolCache.get<SearchCachePayload>(cacheKey)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:900:  if (cachedPayload) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:901:    responseToReturn = buildSearchResponseFromPayload(cachedPayload, _searchStartTime, true);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:903:    // Wait for embedding model only on cache miss
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:915:      searchType: (hasValidConcepts && concepts!.length >= 2)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:952:    // Phase B T018/T019: Community search fallback — inject community members on weak results
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:966:          const communityResults = searchCommunities(effectiveQuery, requireDb(), 5);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:998:          console.warn(`[memory-search] Community search fallback failed (fail-open): ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1057:        `[memory-search] Lexical capability path '${lexicalCapability.lexicalPath}' (fallbackState: ${lexicalCapability.fallbackState})`
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1143:      causal: { applied: pipelineResult.metadata.stage2.causalBoostApplied },
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1156:      pipelineConfig.searchType,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1199:    const cachePayload = extractSearchCachePayload(formatted);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1200:    if (cachePayload && cacheEnabled) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1201:      toolCache.set(cacheKey, cachePayload, { toolName: 'memory_search' });
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1204:    responseToReturn = cachePayload
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1205:      ? buildSearchResponseFromPayload(cachePayload, _searchStartTime, false)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1228:  // Apply session deduplication AFTER cache
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1236:        console.warn('[memory-search] Failed to parse cached response for dedup:', message);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1243:    // P1-018 — Validate response shape before dedup. If the cached response
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1252:      console.warn('[memory-search] Cached response shape mismatch: missing "data" object, skipping dedup');
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1254:      console.warn('[memory-search] Cached response shape mismatch: "data.results" is not an array, skipping dedup');
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1343:  // Consumption instrumentation — log search event (fail-safe, never throws)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1360:        event_type: 'search',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1366:        latency_ms: Date.now() - _searchStartTime,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1370:  } catch (_error: unknown) { /* instrumentation must never cause search to fail */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1392:        latencyMs: Date.now() - _searchStartTime,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1406:  } catch (_error: unknown) { /* eval logging must never break search */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1408:  // REQ-D4-001: Implicit feedback — log search_shown events for returned results
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1425:          const queryId = _evalQueryId ? String(_evalQueryId) : String(_searchStartTime);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1427:            type: 'search_shown',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1431:            timestamp: _searchStartTime,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1438:  } catch (_error: unknown) { /* feedback logging must never break search */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1440:  // REQ-014: Query flow tracking + result_cited for includeContent searches
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1467:        const queryId = _evalQueryId ? String(_evalQueryId) : String(_searchStartTime);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1474:        // Log result_cited for includeContent searches (content was embedded = cited)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1480:  } catch (_error: unknown) { /* query flow tracking must never break search */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1496:        // Profile formatting is best-effort — never breaks search
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1513:export {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1517:export const __testables = {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1531:const handle_memory_search = handleMemorySearch;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1533:export {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1534:  handle_memory_search,

exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md | sed -n '1,220p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
     1	---
     2	# SPECKIT_TEMPLATE_SOURCE: plan-core | v2.2
     3	title: "Implementation Plan: /memory:search Runtime Remediation [system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan]"
     4	description: "Root-cause clusters and remediation strategy for /memory:search runtime bugs catalogued in spec.md. Findings-only packet; this plan briefs the follow-up remediation packet."
     5	trigger_phrases:
     6	  - "memory search remediation plan"
     7	  - "intent classifier root cause"
     8	  - "truncation wrapper repair"
     9	  - "rendering vocabulary enforcement"
    10	importance_tier: "important"
    11	contextType: "implementation"
    12	_memory:
    13	  continuity:
    14	    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs"
    15	    last_updated_at: "2026-04-26T14:33:00Z"
    16	    last_updated_by: "claude-opus-4-7"
    17	    recent_action: "Authored remediation plan with 7 root-cause clusters"
    18	    next_safe_action: "Hand off to remediation packet via tasks.md"
    19	    blockers: []
    20	    key_files:
    21	      - "spec.md"
    22	      - "plan.md"
    23	      - "tasks.md"
    24	      - "implementation-summary.md"
    25	    completion_pct: 50
    26	    open_questions: []
    27	    answered_questions: []
    28	template_source_hint: "<!-- SPECKIT_TEMPLATE_SOURCE: plan-core | v2.2 -->"
    29	---
    30	# Implementation Plan: /memory:search Runtime Remediation
    31	
    32	<!-- SPECKIT_LEVEL: 1 -->
    33	<!-- SPECKIT_TEMPLATE_SOURCE: plan-core | v2.2 -->
    34	
    35	---
    36	
    37	<!-- ANCHOR:summary -->
    38	## 1. SUMMARY
    39	
    40	### Technical Context
    41	
    42	| Aspect | Value |
    43	|--------|-------|
    44	| **Language/Stack** | TypeScript (MCP server), Bash (validators), Markdown (command spec) |
    45	| **Framework** | Spec Kit Memory MCP server, OpenCode runtime |
    46	| **Storage** | SQLite (memory_index, causal_edges) |
    47	| **Testing** | Vitest, custom probe scripts under `scripts/tests/` |
    48	
    49	### Overview
    50	
    51	`spec.md` catalogs 17 distinct defects across 4 P0, 7 P1, and 6 P2 buckets observed in `/memory:search`. Many share underlying root causes; this plan groups them into 7 clusters so a follow-up remediation packet can address each cluster independently and re-verify against the same probes captured in spec §8. This packet itself is findings-only — implementation is deferred.
    52	<!-- /ANCHOR:summary -->
    53	
    54	---
    55	
    56	<!-- ANCHOR:quality-gates -->
    57	## 2. QUALITY GATES
    58	
    59	### Definition of Ready
    60	- [x] All 17 defects mapped to REQ-001..017 in spec.md
    61	- [x] Live MCP probe evidence captured verbatim
    62	- [x] Each REQ has a falsifiable acceptance criterion
    63	- [x] Defects grouped into root-cause clusters (Cluster 1-7 in §3 below)
    64	
    65	### Definition of Done (this packet)
    66	- [x] spec.md, plan.md, tasks.md, implementation-summary.md, description.json, graph-metadata.json present
    67	- [x] All placeholders filled (no `[NAME]` or `[YYYY-MM-DD]` left)
    68	- [ ] `validate.sh --strict` passes against this folder
    69	- [ ] Memory indexer surfaces this packet via `memory_search`
    70	
    71	### Definition of Done (follow-up remediation packet)
    72	- [ ] Each Cluster 1-7 addressed by a discrete code change
    73	- [ ] Re-running spec §8 probes shows acceptance criteria pass
    74	- [ ] Regression tests added for P0 fixes (REQ-001, REQ-002, REQ-003, REQ-004)
    75	<!-- /ANCHOR:quality-gates -->
    76	
    77	---
    78	
    79	<!-- ANCHOR:architecture -->
    80	## 3. ARCHITECTURE
    81	
    82	### Pattern
    83	
    84	Findings-first remediation: catalog → cluster → sequence → execute. This packet performs the first three steps; the follow-up packet executes step four.
    85	
    86	### Root-Cause Clusters
    87	
    88	- **Cluster 1 — Truncation Wrapper (P0)** — REQ-002. `memory_context` budget enforcement drops `data.content` to `count:0,results:[]` while reporting `returnedResultCount > 0`. Token usage measured at 2% of budget when truncation fires. Suspect: per-result token estimation grossly inflated, OR wrapper unconditionally stub-replaces content when `truncated=true`. Change surface: `mcp_server/.../memory_context.ts` budget enforcement layer.
    89	
    90	- **Cluster 2 — Intent Classifier Drift (P0/P1)** — REQ-001, REQ-004, REQ-016. `meta.intent.type = "fix_bug"` (confidence 0.098) returned for "Semantic Search" instead of documented `understand` fallback. Same response also carries `data.queryIntentRouting.queryIntent = "semantic"` (confidence 0.8) — two classifiers, no resolution policy. Change surface: intent detection logic + threshold gate.
    91	
    92	- **Cluster 3 — Output Rendering Vocabulary (P0)** — REQ-003. Spec §4A Step 4b mandates "Trigger-matched spec-doc records" / "Constitutional rules" wording; assistant emitted forbidden "Auto-triggered memories" phrase. Change surface: server-side renderer OR stronger spec enforcement with literal forbidden-phrase list.
    93	
    94	- **Cluster 4 — Causal-Stats Output Hygiene (P1)** — REQ-005, REQ-006, REQ-013. `causal-stats` emits 3 of 6 documented relation types (zero-omission), labels `health: "healthy"` while `meetsTarget: false`, no remediation hint when target missed. Change surface: `memory_causal_stats` serializer.
    95	
    96	- **Cluster 5 — State Hygiene (P1)** — REQ-009, REQ-011, REQ-015. Default ephemeral session lifecycle defeats `enableDedup`; "Context quality is degraded" hint emitted unconditionally; trigger/constitutional channels not deduped. Change surface: command harness session-id threading + server hint emitter guard.
    97	
    98	- **Cluster 6 — Folder Discovery + Channel Health (P1/P2)** — REQ-008, REQ-012, REQ-017. Folder-discovery binds on weak signal ("Semantic Search" → `skilled-agent-orchestration/023-sk-deep-research-creation`); CocoIndex daemon failure is silent; "code graph" vs "causal graph" naming collides. Change surface: similarity threshold + startup health check + naming disambiguation.
    99	
   100	- **Cluster 7 — Quality Fallback + Edge Growth (P1/P2)** — REQ-007, REQ-010, REQ-014. `QUALITY=gap` flag is informational only; spec §1 promises 3-tier FTS fallback that never activates. Causal-graph edge growth dominated by autonomous `supersedes`-only backfill (+344 in 15 min, `caused`/`supports` unchanged). AskUserQuestion custom-answer routing undocumented. Change surface: retrieval pipeline + backfill job + command spec.
   101	
   102	### Data Flow
   103	
   104	`/memory:search "<query>"` → command harness parses args → routes to `memory_context` (retrieval mode) or analysis subcommand → wrapper assembles response with `meta` + `data` + `hints` → renderer formats output block → assistant emits to user. Defects span every stage of this pipeline; clusters above map to specific stages.
   105	<!-- /ANCHOR:architecture -->
   106	
   107	---
   108	
   109	<!-- ANCHOR:phases -->
   110	## 4. IMPLEMENTATION PHASES
   111	
   112	### Phase 1: Setup (this packet — DONE)
   113	- [x] Reproduce defects via live MCP probes; capture evidence
   114	- [x] Author `spec.md` with all 17 defects mapped to REQ-001..017
   115	- [x] Author `plan.md` (this file) with 7 root-cause clusters
   116	- [x] Author `tasks.md` decomposing remediation into work units
   117	- [x] Author placeholder `implementation-summary.md`
   118	- [x] Generate `description.json` and `graph-metadata.json`
   119	- [ ] Pass `validate.sh --strict`
   120	
   121	### Phase 2: Core Implementation (deferred to follow-up packet)
   122	- [ ] **Phase 2A — P0 fixes:** Cluster 1 (truncation), Cluster 2 (intent classifier), Cluster 3 (rendering vocabulary)
   123	- [ ] **Phase 2B — P1 hygiene:** Cluster 4 (causal-stats), Cluster 5 (state hygiene), Cluster 6 (folder discovery + channel health)
   124	- [ ] **Phase 2C — P2 refinement:** Cluster 7 (quality fallback + edge growth + custom-answer routing)
   125	
   126	### Phase 3: Verification (deferred to follow-up packet)
   127	- [ ] Re-run spec §8 probes; confirm each acceptance criterion passes
   128	- [ ] Add regression tests for P0 fixes
   129	- [ ] Update spec §8 evidence with new probe outputs
   130	- [ ] Mark spec.md REQ-001..017 acceptance criteria with evidence in checklist
   131	<!-- /ANCHOR:phases -->
   132	
   133	---
   134	
   135	<!-- ANCHOR:testing -->
   136	## 5. TESTING STRATEGY
   137	
   138	| Test Type | Scope | Tools |
   139	|-----------|-------|-------|
   140	| Probe-based regression | Each REQ has a probe in spec §8 — re-run after fix lands | Direct MCP tool calls (memory_context, memory_causal_stats) |
   141	| Unit | Per-component behavior (intent classifier, budget enforcer, serializer) | Vitest |
   142	| Integration | End-to-end `/memory:search` invocations against fixture queries | Vitest + MCP server harness |
   143	| Stability corpus | 20 paraphrased queries that should classify to the same intent (REQ-016) | Vitest + golden-output fixtures |
   144	<!-- /ANCHOR:testing -->
   145	
   146	---
   147	
   148	<!-- ANCHOR:dependencies -->
   149	## 6. DEPENDENCIES
   150	
   151	| Dependency | Type | Status | Impact if Blocked |
   152	|------------|------|--------|-------------------|
   153	| Sibling packet `004-memory-save-rewrite` (planner-first contract) | Internal | Green (complete) | None — already landed |
   154	| Sibling packet `002-memory-quality-remediation` (backend repair history) | Internal | Green (complete) | None — informs root-cause analysis |
   155	| `005-memory-indexer-invariants` parent-of-026 sibling | Internal | Yellow (active) | Coordinate to avoid double-touch on indexer code |
   156	| CocoIndex daemon | External | Red (down — observed in conversation) | REQ-012 verification blocked until daemon runnable |
   157	| Spec Kit Memory MCP server source | Internal | Green | All clusters touch this; ensure single PR-batching strategy |
   158	<!-- /ANCHOR:dependencies -->
   159	
   160	---
   161	
   162	<!-- ANCHOR:rollback -->
   163	## 7. ROLLBACK PLAN
   164	
   165	- **Trigger**: This packet is documentation-only. No runtime changes land here, so no rollback is possible or needed. Rollback for the follow-up remediation packet should be defined in that packet's plan.md.
   166	- **Procedure**: If findings prove incorrect after deeper investigation, update spec §4/§8 with corrected evidence and re-cluster in §3 above. The packet remains a versioned record even when individual findings are revised.
   167	<!-- /ANCHOR:rollback -->

exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md | sed -n '1,220p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
     1	---
     2	# SPECKIT_TEMPLATE_SOURCE: tasks-core | v2.2
     3	title: "Tasks: /memory:search Runtime Remediation [system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks]"
     4	description: "Per-defect work units for /memory:search runtime remediation, organized by root-cause cluster. Findings-packet tasks completed; remediation tasks deferred to follow-up packet."
     5	trigger_phrases:
     6	  - "memory search remediation tasks"
     7	  - "memory_context truncation fix"
     8	  - "intent classifier fallback fix"
     9	importance_tier: "important"
    10	contextType: "implementation"
    11	_memory:
    12	  continuity:
    13	    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs"
    14	    last_updated_at: "2026-04-26T14:33:00Z"
    15	    last_updated_by: "claude-opus-4-7"
    16	    recent_action: "Decomposed remediation plan into Phase 1-3 work units"
    17	    next_safe_action: "Hand off to remediation packet"
    18	    blockers: []
    19	    key_files:
    20	      - "spec.md"
    21	      - "plan.md"
    22	      - "tasks.md"
    23	    completion_pct: 75
    24	    open_questions: []
    25	    answered_questions: []
    26	template_source_hint: "<!-- SPECKIT_TEMPLATE_SOURCE: tasks-core | v2.2 -->"
    27	---
    28	# Tasks: /memory:search Runtime Remediation
    29	
    30	<!-- SPECKIT_LEVEL: 1 -->
    31	<!-- SPECKIT_TEMPLATE_SOURCE: tasks-core | v2.2 -->
    32	
    33	---
    34	
    35	<!-- ANCHOR:notation -->
    36	## Task Notation
    37	
    38	| Prefix | Meaning |
    39	|--------|---------|
    40	| `[ ]` | Pending |
    41	| `[x]` | Completed |
    42	| `[P]` | Parallelizable |
    43	| `[B]` | Blocked |
    44	
    45	**Task Format**: `T### [P?] Description (file path)`
    46	
    47	This packet is findings-only. Phase 1 (this packet) is complete; Phase 2 and Phase 3 are deferred to a follow-up remediation packet.
    48	<!-- /ANCHOR:notation -->
    49	
    50	---
    51	
    52	<!-- ANCHOR:phase-1 -->
    53	## Phase 1: Setup
    54	
    55	This packet (Phase 1) authors the findings; downstream phases are executed by the follow-up remediation packet.
    56	
    57	- [x] T001 Reproduce defects via live MCP probes (spec §8)
    58	- [x] T002 Author spec.md with all 17 defects mapped to REQ-001..017 (spec.md)
    59	- [x] T003 [P] Author plan.md with 7 root-cause clusters (plan.md)
    60	- [x] T004 [P] Author tasks.md decomposing remediation work (tasks.md — this file)
    61	- [x] T005 [P] Author implementation-summary.md placeholder (implementation-summary.md)
    62	- [x] T006 [P] Generate description.json (description.json)
    63	- [x] T007 [P] Generate graph-metadata.json (graph-metadata.json)
    64	- [ ] T008 Pass `bash .opencode/skills/system-spec-kit/scripts/spec/validate.sh <this-folder> --strict`
    65	<!-- /ANCHOR:phase-1 -->
    66	
    67	---
    68	
    69	<!-- ANCHOR:phase-2 -->
    70	## Phase 2: Implementation
    71	
    72	Deferred to the follow-up remediation packet.
    73	
    74	### Cluster 1 — Truncation Wrapper (P0; REQ-002)
    75	- [x] T101 Locate memory_context budget enforcement code (`mcp_server/handlers/memory-context.ts:447` — `enforceTokenBudget`)
    76	- [x] T102 Instrument per-result token estimation; log estimated vs actual for 10 sample queries — diagnosed via inline `node` probe; bug was the `fallbackToStructuredBudget()` zero-fill, not estimator inflation
    77	- [x] T103 Identify whether `data.content` stub-replacement is unconditional or conditional — confirmed unconditional zero-fill at original `mcp_server/handlers/memory-context.ts:482` `fallbackToStructuredBudget`; preserves none of the structurally-truncated survivors
    78	- [x] T104 Fix: when `actualTokens / budgetTokens < 0.50`, return all results unmodified (`mcp_server/handlers/memory-context.ts:467-481` early-return guard) PLUS preserve survivors via the new `preservedAfterStructural` snapshot fed into `fallbackToStructuredBudget()` (`mcp_server/handlers/memory-context.ts:472-545, 696-705, 766-797`)
    79	- [x] T105 [P] Regression test: existing T205-B suite still passes; inline node probe confirms `count > 0` after fix and metadata `returnedResultCount` matches actual payload `results.length`
    80	
    81	### Cluster 2 — Intent Classifier Drift (P0/P1; REQ-001, REQ-004, REQ-016)
    82	- [x] T201 Locate intent detection code (`mcp_server/lib/search/intent-classifier.ts:404` `classifyIntent`); confirmed `meta.intent` (this classifier) and `data.queryIntentRouting` (`mcp_server/code_graph/lib/query-intent-classifier.ts`) are SEPARATE scorers serving different purposes
    83	- [x] T202 Added centroid-only confidence floor at 0.30 per spec §4A — keeps existing P3-12 0.08 floor for keyword-driven scoring, escalates to 0.30 only when keyword + pattern evidence is empty (`mcp_server/lib/search/intent-classifier.ts:209` constant + `:484-505` gate). Avoids breaking 15 existing intent-corpus tests that depend on single-keyword classification.
    84	- [x] T203 [P] Documented authority split: `meta.intent.classificationKind = "task-intent"` is authoritative for rendering / anchors / mode-routing; `data.queryIntentRouting.classificationKind = "backend-routing"` is authoritative only for channel selection (`mcp_server/handlers/memory-context.ts:1180-1191, 1576-1583`)
    85	- [ ] T204 Add stability corpus: 20 paraphrased queries — DEFERRED (out of scope for P0 fixes; corpus exists informally via the 80% accuracy test at intent-classifier.vitest.ts:T060)
    86	- [x] T205 [P] Regression test verified inline: "Semantic Search" → understand (was fix_bug 0.098); "Find stuff related to semantic search" → understand; "fix the login bug" → fix_bug (single-keyword regression-safe)
    87	
    88	### Cluster 3 — Output Rendering Vocabulary (P0; REQ-003)
    89	- [x] T301 Decided option (b): stronger spec enforcement with literal forbidden-phrase list (option (a) blocked — assistant emits the rendering, not the runtime)
    90	- [ ] T302 If (a): build canonical formatter — N/A, see T301
    91	- [x] T303 Added "Forbidden Phrase Enforcement (REQ-003 / Cluster 3)" subsection to `.opencode/commands/memory/search.md` with full forbidden→required substitution table, mandatory pre-render gate steps, and a verification grep
    92	- [x] T304 [P] Verification grep specified in spec: `grep -Eci 'auto-triggered|triggered memories|triggered memory|constitutional memor(y|ies)'` MUST return 0 against the rendered block
    93	
    94	### Cluster 4 — Causal-Stats Output Hygiene (P1; REQ-005, REQ-006, REQ-013)
    95	- [ ] T401 Update memory_causal_stats serializer to emit all 6 relation keys (zero-fill if absent)
    96	- [ ] T402 [P] Reconcile health field with meetsTarget; document mapping in spec §5B
    97	- [ ] T403 [P] Add remediation hint when meetsTarget=false
    98	- [ ] T404 Regression test: response shape contains all 6 relations; health agrees with meetsTarget
    99	
   100	### Cluster 5 — State Hygiene (P1; REQ-009, REQ-011, REQ-015)
   101	- [ ] T501 Thread stable sessionId through `/memory:search` invocations within an OpenCode session
   102	- [ ] T502 [P] Guard "Context quality is degraded" hint emission on fresh ephemeral
   103	- [ ] T503 [P] Extend dedup to trigger and constitutional channels
   104	- [ ] T504 Regression test: two consecutive `/memory:search` calls in same session share session ID; second call dedupes prior triggers
   105	
   106	### Cluster 6 — Folder Discovery + Channel Health (P1/P2; REQ-008, REQ-012, REQ-017)
   107	- [ ] T601 Raise folder-discovery similarity threshold; require minimum signal strength before binding
   108	- [ ] T602 [P] Add CocoIndex daemon health check at `/memory:search` invocation start
   109	- [ ] T603 [P] Emit explicit `WARN: vector channel unavailable` line when daemon down
   110	- [ ] T604 [P] Disambiguate "code graph" vs "causal graph" naming in startup hook + causal-stats output
   111	- [ ] T605 Regression test: "Semantic Search" → `folderDiscovery=null`; daemon-down probe shows warning
   112	
   113	### Cluster 7 — Quality Fallback + Edge Growth (P1/P2; REQ-007, REQ-010, REQ-014)
   114	- [ ] T701 Wire 3-tier FTS fallback (FTS5 → BM25 → Grep) to trigger automatically when quality=gap
   115	- [ ] T702 [P] Investigate causal-backfill job; identify why only `supersedes` edges added
   116	- [ ] T703 Extend backfill to surface `caused` and `supports` candidates with confidence scores
   117	- [ ] T704 [P] Document AskUserQuestion custom-answer routing in spec §4 OR add "Code search" menu option
   118	- [ ] T705 Regression test: weak query triggers fallback; output includes `fallback_tier` field
   119	<!-- /ANCHOR:phase-2 -->
   120	
   121	---
   122	
   123	<!-- ANCHOR:phase-3 -->
   124	## Phase 3: Verification
   125	
   126	Deferred to the follow-up remediation packet.
   127	
   128	- [ ] T901 Re-run spec §8 Probe 1 (intent classifier); confirm "Semantic Search" → `understand`
   129	- [ ] T902 Re-run spec §8 Probe 2 (truncation); confirm `count > 0` in `data.content` at low token utilization
   130	- [ ] T903 Re-run spec §8 Probe 3 (causal-stats); confirm all 6 relations present + health agrees with meetsTarget
   131	- [ ] T904 Re-run spec §8 Probe 4 (folder discovery); confirm no spurious binding
   132	- [ ] T905 Re-run spec §8 Probe 5 (edge growth); confirm non-`supersedes` relation deltas
   133	- [ ] T906 Verify rendering vocabulary on empty-result `/memory:search` invocation
   134	- [ ] T907 Update spec.md §8 with post-fix probe outputs alongside the original evidence
   135	- [ ] T908 Mark all REQ-001..017 acceptance criteria as PASSED in checklist or implementation-summary
   136	<!-- /ANCHOR:phase-3 -->
   137	
   138	---
   139	
   140	<!-- ANCHOR:completion -->
   141	## Completion Criteria
   142	
   143	This packet (Phase 1) completes when:
   144	- [x] All Phase 1 tasks T001-T007 marked `[x]`
   145	- [ ] T008 (validation) passes
   146	- [ ] No `[B]` blocked tasks remaining in Phase 1
   147	- [ ] Memory indexer surfaces this packet via `memory_search "memory search runtime bugs"`
   148	
   149	The follow-up remediation packet completes when all Phase 2 + Phase 3 tasks are `[x]` and the spec §8 probes pass per their acceptance criteria.
   150	<!-- /ANCHOR:completion -->
   151	
   152	---
   153	
   154	<!-- ANCHOR:cross-refs -->
   155	## Cross-References
   156	
   157	- **Specification**: See `spec.md` (REQ-001..017 with acceptance criteria + probe evidence in §8)
   158	- **Plan**: See `plan.md` (7 root-cause clusters + phase sequencing)
   159	- **Implementation Summary**: See `implementation-summary.md`
   160	- **Canonical command spec**: `.opencode/commands/memory/search.md`
   161	- **Sibling packets**:
   162	  - `../001-cache-warning-hooks/` — token-budget hook patterns
   163	  - `../002-memory-quality-remediation/` — prior backend repair history
   164	  - `../003-continuity-refactor-gates/` — gates A-F coordination
   165	  - `../004-memory-save-rewrite/` — planner-first save contract
   166	- **Related work outside parent**: `../../005-memory-indexer-invariants/`
   167	<!-- /ANCHOR:cross-refs -->

exec
/bin/zsh -lc "nl -ba .opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts | sed -n '430,520p;760,830p;1140,1180p;1288,1328p;1538,1584p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
   430	}
   431	
   432	/* ───────────────────────────────────────────────────────────────
   433	   2. TOKEN BUDGET ENFORCEMENT (T205)
   434	   
   435	   Enforces per-layer/per-mode token budgets by estimating the
   436	   token count of strategy results and truncating when exceeded.
   437	   Uses character-based estimation: 1 token ≈ 4 chars.
   438	──────────────────────────────────────────────────────────────── */
   439	
   440	/**
   441	 * T205: Enforce token budget on strategy results.
   442	 * 
   443	 * Estimates the token count of the serialized result. If over budget,
   444	 * parses embedded result arrays and removes lowest-priority items
   445	 * until within budget. Higher-scored results are preserved.
   446	 */
   447	function enforceTokenBudget(result: ContextResult, budgetTokens: number): { result: ContextResult; enforcement: TokenBudgetEnforcement } {
   448	  const serialized = JSON.stringify(result);
   449	  const actualTokens = estimateTokens(serialized);
   450	
   451	  // Under budget — no enforcement needed
   452	  if (actualTokens <= budgetTokens) {
   453	    return {
   454	      result,
   455	      enforcement: {
   456	        budgetTokens,
   457	        actualTokens,
   458	        enforced: false,
   459	        truncated: false,
   460	      }
   461	    };
   462	  }
   463	
   464	  // REQ-002 (Cluster 1) Sanity guard: when reported usage is far below budget but
   465	  // we somehow entered enforcement (e.g. estimator ran twice on already-truncated
   466	  // payload, or budget was passed in as a tiny number), short-circuit and return
   467	  // the unmodified result. This prevents the historical regression where a
   468	  // 71-token payload against a 3000-token budget was nuked to count:0,results:[].
   469	  if (budgetTokens > 0 && actualTokens / budgetTokens < 0.50) {
   470	    return {
   471	      result,
   472	      enforcement: {
   473	        budgetTokens,
   474	        actualTokens,
   475	        enforced: false,
   476	        truncated: false,
   477	      }
   478	    };
   479	  }
   480	
   481	  // Over budget — attempt to truncate embedded results
   482	  // Strategy results contain an embedded MCPResponse with content[0].text as JSON
   483	  // That JSON has a .data.results array we can truncate
   484	  const truncatedResult = { ...result };
   485	  let parseFailed = false;
   486	  let originalResultCount: number | undefined;
   487	  let returnedResultCount: number | undefined;
   488	
   489	  const fallbackToStructuredBudget = (
   490	    baseResult: ContextResult,
   491	    parseFailedInnerText?: string,
   492	    preservedResults?: Array<Record<string, unknown>>,
   493	  ): ContextResult => {
   494	    const fallbackResult = { ...baseResult } as ContextResult;
   495	    const fallbackContent = Array.isArray((fallbackResult as Record<string, unknown>).content)
   496	      ? ((fallbackResult as Record<string, unknown>).content as Array<Record<string, unknown>>)
   497	      : [];
   498	    const contentClone = fallbackContent.map((entry) => ({ ...entry }));
   499	
   500	    // REQ-002 (Cluster 1): When structural truncation already produced a non-empty
   501	    // result set, preserve it rather than silently dropping to count:0,results:[].
   502	    // The previous behaviour caused the wrapper to report `returnedResultCount > 0`
   503	    // in metadata while shipping an empty payload to the caller.
   504	    const preservedSafe: Array<Record<string, unknown>> = Array.isArray(preservedResults)
   505	      ? preservedResults
   506	      : [];
   507	
   508	    const buildPreservedCandidates = (): Array<Record<string, unknown>> => {
   509	      if (preservedSafe.length === 0) {
   510	        return [];
   511	      }
   512	      const minimalResults = preservedSafe.map((r) => ({
   513	        id: r.id,
   514	        title: r.title,
   515	        similarity: r.similarity,
   516	        specFolder: r.specFolder,
   517	        confidence: r.confidence,
   518	        importanceTier: r.importanceTier,
   519	        isConstitutional: r.isConstitutional,
   520	        metadataOnly: true,
   760	
   761	        // Recalculate actual tokens after truncation
   762	        const newSerializedTokens = estimateTokens(JSON.stringify(truncatedResult));
   763	
   764	        if (newSerializedTokens <= budgetTokens) {
   765	          return {
   766	            result: truncatedResult,
   767	            enforcement: {
   768	              budgetTokens,
   769	              actualTokens: newSerializedTokens,
   770	              enforced: true,
   771	              truncated: true,
   772	              originalResultCount,
   773	              returnedResultCount,
   774	            }
   775	          };
   776	        }
   777	
   778	        const compacted = compactStructuredResult(innerEnvelope, currentResults, contentArr);
   779	        if (compacted) {
   780	          return {
   781	            result: compacted.result,
   782	            enforcement: {
   783	              budgetTokens,
   784	              actualTokens: compacted.actualTokens,
   785	              enforced: true,
   786	              truncated: true,
   787	              originalResultCount,
   788	              returnedResultCount,
   789	            }
   790	          };
   791	        }
   792	      }
   793	    } catch {
   794	      parseFailed = true;
   795	      parseFailedInnerText = contentArr[0].text;
   796	      // JSON parse failed — fall through to structural truncation
   797	    }
   798	  }
   799	
   800	  // Fallback when parsing fails or a structured response still exceeds budget.
   801	  // Always emit valid nested JSON rather than raw character slices.
   802	  // REQ-002 (Cluster 1): Hand the fallback the survivors from structural
   803	  // truncation so it can keep them instead of silently zero-filling.
   804	  const fallbackResult = fallbackToStructuredBudget(
   805	    parseFailed ? result : truncatedResult,
   806	    parseFailedInnerText,
   807	    preservedAfterStructural,
   808	  );
   809	
   810	  const fallbackTokens = estimateTokens(JSON.stringify(fallbackResult));
   811	
   812	  // Re-extract the actual returned count from the fallback envelope so the
   813	  // metadata never advertises survivors that the payload no longer contains.
   814	  let fallbackReturnedCount = returnedResultCount;
   815	  try {
   816	    const fallbackContent = (fallbackResult as Record<string, unknown>).content as Array<{ text?: string }> | undefined;
   817	    if (fallbackContent && fallbackContent[0]?.text) {
   818	      const parsedFallback = JSON.parse(fallbackContent[0].text) as { data?: { results?: unknown[] } };
   819	      if (Array.isArray(parsedFallback?.data?.results)) {
   820	        fallbackReturnedCount = parsedFallback.data!.results!.length;
   821	      }
   822	    }
   823	  } catch {
   824	    // keep the prior returnedResultCount on parse failure
   825	  }
   826	
   827	  return {
   828	    result: fallbackResult,
   829	    enforcement: {
   830	      budgetTokens,
  1140	      }
  1141	    }
  1142	  }
  1143	
  1144	  if (!CONTEXT_MODES[effectiveMode]) {
  1145	    effectiveMode = 'focused';
  1146	  }
  1147	
  1148	  return {
  1149	    effectiveMode,
  1150	    pressureOverrideApplied,
  1151	    pressureOverrideTargetMode,
  1152	    pressureWarning,
  1153	    intentClassification: {
  1154	      detectedIntent,
  1155	      intentConfidence,
  1156	      resumeHeuristicApplied,
  1157	      source: explicitIntent ? 'explicit' : 'auto-detected',
  1158	    },
  1159	  };
  1160	}
  1161	
  1162	function maybeDiscoverSpecFolder(options: ContextOptions, args: ContextArgs): string | undefined {
  1163	  if (args.specFolder || !isFolderDiscoveryEnabled()) {
  1164	    return undefined;
  1165	  }
  1166	
  1167	  try {
  1168	    const basePaths = getSpecsBasePaths();
  1169	    const discoveredFolder = discoverSpecFolder(args.input.trim(), basePaths) || undefined;
  1170	    if (discoveredFolder) {
  1171	      (options as Record<string, unknown>).folderBoost = {
  1172	        folder: discoveredFolder,
  1173	        factor: parseFloat(process.env.SPECKIT_FOLDER_BOOST_FACTOR || '1.3'),
  1174	      };
  1175	    }
  1176	    return discoveredFolder;
  1177	  } catch (error: unknown) {
  1178	    console.error(
  1179	      '[memory-context] folder discovery failed (non-critical):',
  1180	      error instanceof Error ? error.message : String(error),
  1288	      specFolder: discoveredFolder,
  1289	      source: 'folder-discovery',
  1290	    } : null,
  1291	    structuralRoutingNudge,
  1292	    ...telemetryMeta,
  1293	  };
  1294	}
  1295	
  1296	/* ───────────────────────────────────────────────────────────────
  1297	   7. MAIN HANDLER
  1298	──────────────────────────────────────────────────────────────── */
  1299	
  1300	/** Handle memory_context tool — L1 orchestration layer that routes to optimal retrieval strategy.
  1301	 * @param args - Context retrieval arguments (intent, mode, specFolder, anchors, etc.)
  1302	 * @returns MCP response with context-aware memory results
  1303	 */
  1304	async function handleMemoryContext(args: ContextArgs): Promise<MCPResponse> {
  1305	  const _contextStartTime = Date.now();
  1306	  const requestId = randomUUID();
  1307	
  1308	  try {
  1309	  try {
  1310	    await checkDatabaseUpdated();
  1311	  } catch (error: unknown) {
  1312	    const message = error instanceof Error ? error.message : String(error);
  1313	    return createMCPErrorResponse({
  1314	      tool: 'memory_context',
  1315	      error: `Database state check failed: ${message}`,
  1316	      code: 'E_INTERNAL',
  1317	      details: { requestId, layer: 'L1:Orchestration' },
  1318	      recovery: {
  1319	        hint: 'The memory database may be unavailable. Retry or check database connectivity.',
  1320	      },
  1321	    });
  1322	  }
  1323	
  1324	  const {
  1325	    input,
  1326	    mode: requested_mode = 'auto',
  1327	    intent: explicit_intent,
  1328	    specFolder: spec_folder,
  1538	
  1539	  // Phase C: Intent-to-profile auto-routing for memory_context.
  1540	  // Explicit caller `profile` always takes precedence; auto-detect fills in when absent.
  1541	  // Skip for 'quick' mode: quick routes through handleMemoryMatchTriggers which does not
  1542	  // support profile formatting — setting a profile there would be a no-op.
  1543	  if (!options.profile && detectedIntent && effectiveMode !== 'quick' && isIntentAutoProfileEnabled()) {
  1544	    try {
  1545	      const autoProfile = intentClassifier.getProfileForIntent(
  1546	        detectedIntent as import('../lib/search/intent-classifier.js').IntentType
  1547	      );
  1548	      if (autoProfile) {
  1549	        options.profile = autoProfile;
  1550	        console.error(`[memory-context] Intent-to-profile auto-routing: '${detectedIntent}' → profile '${autoProfile}'`);
  1551	      }
  1552	    } catch (_autoProfileErr: unknown) {
  1553	      // Auto-profile is best-effort — never breaks context retrieval
  1554	    }
  1555	  }
  1556	
  1557	  const sessionTransition = buildSessionTransitionTrace({
  1558	    previousState,
  1559	    resumedSession,
  1560	    effectiveMode,
  1561	    requestedMode: requested_mode,
  1562	    detectedIntent: detectedIntent ?? null,
  1563	    pressureOverrideApplied,
  1564	    queryHeuristicApplied: resumeHeuristicApplied,
  1565	  });
  1566	  options.sessionTransition = options.includeTrace === true ? sessionTransition : undefined;
  1567	
  1568	  const discoveredFolder = maybeDiscoverSpecFolder(options, { ...args, input: normalizedInput });
  1569	  // FIX P0: Folder discovery sets options.folderBoost for scoring only.
  1570	  // Do NOT propagate as options.specFolder — that becomes an exact-match filter
  1571	  // in vector-index-queries.ts (m.spec_folder = ?) which silently drops all
  1572	  // results when the discovered path has no indexed memories.
  1573	  const sessionStateResult = sessionManager.saveSessionState(effectiveSessionId, {
  1574	    specFolder: options.specFolder ?? discoveredFolder ?? spec_folder,
  1575	    tenantId: args.tenantId,
  1576	    userId: args.userId,
  1577	    agentId: args.agentId,
  1578	    currentTask: normalizedInput.slice(0, 500),
  1579	  });
  1580	  if (!sessionStateResult.success) {
  1581	    console.warn(
  1582	      `[memory-context] Failed to persist session identity for ${effectiveSessionId}: ${sessionStateResult.error ?? 'unknown error'}`,
  1583	    );
  1584	  }

exec
/bin/zsh -lc "nl -ba .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts | sed -n '780,910p;940,970p;1188,1248p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
   780	  // Intent-aware retrieval
   781	  let detectedIntent: string | null = null;
   782	  let intentConfidence = 0;
   783	  let intentWeights: IntentWeights | null = null;
   784	
   785	  if (explicitIntent) {
   786	    if (intentClassifier.isValidIntent(explicitIntent)) {
   787	      detectedIntent = explicitIntent;
   788	      intentConfidence = 1.0;
   789	      intentWeights = intentClassifier.getIntentWeights(explicitIntent);
   790	    } else {
   791	      console.warn(`[memory-search] Invalid intent '${explicitIntent}', using auto-detection`);
   792	    }
   793	  }
   794	
   795	  if (!detectedIntent && autoDetectIntent && hasValidQuery) {
   796	    const classification: IntentClassification = intentClassifier.classifyIntent(normalizedQuery!);
   797	    detectedIntent = classification.intent;
   798	    intentConfidence = classification.confidence;
   799	    intentWeights = intentClassifier.getIntentWeights(classification.intent as IntentType);
   800	
   801	    if (classification.fallback) {
   802	      console.error(`[memory-search] Intent auto-detected as '${detectedIntent}' (fallback: ${classification.reason})`);
   803	    } else {
   804	      console.error(`[memory-search] Intent auto-detected as '${detectedIntent}' (confidence: ${intentConfidence.toFixed(2)})`);
   805	    }
   806	  }
   807	
   808	  // FIX RC3-B: Intent confidence floor — override low-confidence auto-detections to "understand"
   809	  const INTENT_CONFIDENCE_FLOOR = parseFloat(process.env.SPECKIT_INTENT_CONFIDENCE_FLOOR || '0.25');
   810	  if (detectedIntent && intentConfidence < INTENT_CONFIDENCE_FLOOR && !explicitIntent) {
   811	    console.error(`[memory-search] Intent confidence ${intentConfidence.toFixed(3)} below floor ${INTENT_CONFIDENCE_FLOOR}, overriding '${detectedIntent}' → 'understand'`);
   812	    detectedIntent = 'understand';
   813	    intentConfidence = 1.0;
   814	    intentWeights = intentClassifier.getIntentWeights('understand' as IntentType);
   815	  }
   816	
   817	  // Phase C: Intent-to-profile auto-routing.
   818	  // Explicit caller `profile` always takes precedence; auto-detect fills in when absent.
   819	  let effectiveProfile: string | undefined = profile;
   820	  if (!effectiveProfile && detectedIntent && isIntentAutoProfileEnabled()) {
   821	    try {
   822	      const autoProfile = intentClassifier.getProfileForIntent(detectedIntent as IntentType);
   823	      if (autoProfile) {
   824	        effectiveProfile = autoProfile;
   825	        console.error(`[memory-search] Intent-to-profile auto-routing: '${detectedIntent}' → profile '${autoProfile}'`);
   826	      }
   827	    } catch (_autoProfileErr: unknown) {
   828	      // Auto-profile is best-effort — never breaks search
   829	    }
   830	  }
   831	  const adaptiveFusionIntent = effectiveProfile === 'resume'
   832	    ? 'continuity'
   833	    : detectedIntent;
   834	
   835	  // Re-run artifact routing with detected intent for fallback coverage
   836	  if (detectedIntent && artifactRouting?.detectedClass === 'unknown' && artifactRouting?.confidence === 0) {
   837	    artifactRouting = getStrategyForQuery(artifactRoutingQuery, specFolder, detectedIntent);
   838	  }
   839	
   840	  // Create retrieval trace at pipeline entry
   841	  const trace = createTrace(
   842	    effectiveQuery,
   843	    sessionId,
   844	    detectedIntent || undefined
   845	  );
   846	
   847	  // R-007-12: When causal boost is enabled, fold the causal-edges generation
   848	  // counter into the cache key so causal-edge mutations naturally invalidate
   849	  // the affected memory_search entries on the next lookup. We deliberately
   850	  // keep the generation OFF the key when the caller has not opted into causal
   851	  // boost — otherwise unrelated callers would suffer needless cache misses.
   852	  const causalEdgesGenerationForCache = enableCausalBoost
   853	    ? causalEdges.getCausalEdgesGeneration()
   854	    : undefined;
   855	
   856	  // Build cache key args
   857	  const cacheArgs = buildCacheArgs({
   858	    normalizedQuery,
   859	    hasValidConcepts,
   860	    concepts,
   861	    specFolder,
   862	    tenantId: normalizedScope.tenantId,
   863	    userId: normalizedScope.userId,
   864	    agentId: normalizedScope.agentId,
   865	    limit,
   866	    mode,
   867	    tier,
   868	    contextType,
   869	    useDecay,
   870	    includeArchived,
   871	    qualityThreshold,
   872	    applyStateLimits,
   873	    includeContiguity,
   874	    includeConstitutional,
   875	    includeContent,
   876	    anchors,
   877	    detectedIntent,
   878	    adaptiveFusionIntent,
   879	    minState: minState ?? '',
   880	    rerank,
   881	    applyLengthPenalty,
   882	    sessionId,
   883	    enableSessionBoost,
   884	    enableCausalBoost,
   885	    includeTrace,
   886	    cacheVersion: CANONICAL_READER_CACHE_VERSION,
   887	    causalEdgesGeneration: causalEdgesGenerationForCache,
   888	  });
   889	
   890	  let _evalChannelPayloads: EvalChannelPayload[] = [];
   891	  const cacheKey = toolCache.generateCacheKey('memory_search', cacheArgs);
   892	  const cacheEnabled = toolCache.isEnabled() && !bypassCache;
   893	  const cachedPayload = cacheEnabled
   894	    ? toolCache.get<SearchCachePayload>(cacheKey)
   895	    : null;
   896	
   897	  let responseToReturn: MCPResponse;
   898	  let goalRefinementPayload: Record<string, unknown> | null = null;
   899	
   900	  if (cachedPayload) {
   901	    responseToReturn = buildSearchResponseFromPayload(cachedPayload, _searchStartTime, true);
   902	  } else {
   903	    // Wait for embedding model only on cache miss
   904	    if (!isEmbeddingModelReady()) {
   905	      const modelReady = await waitForEmbeddingModel(30000);
   906	      if (!modelReady) {
   907	        throw new Error('Embedding model not ready after 30s timeout. Try again later.');
   908	      }
   909	    }
   910	
   940	      trackAccess,
   941	      detectedIntent,
   942	      adaptiveFusionIntent,
   943	      intentConfidence,
   944	      intentWeights: toIntentWeightsConfig(intentWeights),
   945	      artifactRouting: artifactRouting as unknown as PipelineConfig['artifactRouting'],
   946	      trace,
   947	    };
   948	
   949	    const pipelineResult: PipelineResult = await executePipeline(pipelineConfig);
   950	    let resultsForFormatting = pipelineResult.results as unknown as SessionAwareResult[];
   951	
   952	    // Phase B T018/T019: Community search fallback — inject community members on weak results
   953	    let communityFallbackApplied = false;
   954	    const shouldRunCommunitySearch = (
   955	      isDualRetrievalEnabled() &&
   956	      isCommunitySearchFallbackEnabled() &&
   957	      effectiveQuery.length > 0 &&
   958	      (retrievalLevel === 'global' || retrievalLevel === 'auto')
   959	    );
   960	    if (shouldRunCommunitySearch) {
   961	      const isWeakResult = resultsForFormatting.length === 0 ||
   962	        (retrievalLevel === 'global') ||
   963	        (resultsForFormatting.length < 3 && retrievalLevel === 'auto');
   964	      if (isWeakResult) {
   965	        try {
   966	          const communityResults = searchCommunities(effectiveQuery, requireDb(), 5);
   967	          if (communityResults.totalMemberIds.length > 0) {
   968	            // Fetch the actual memory rows for community member IDs
   969	            const memberIds = communityResults.totalMemberIds.slice(0, 20);
   970	            const placeholders = memberIds.map(() => '?').join(', ');
  1188	          undefined,
  1189	          effectiveQuery,
  1190	          { scopeKey: progressiveScopeKey },
  1191	        );
  1192	        parsedFormatted.envelope.data = data;
  1193	        formatted = replaceResponseEnvelope(formatted, parsedFormatted.firstEntry, parsedFormatted.envelope);
  1194	      }
  1195	    }
  1196	
  1197	    formatted = applyPublicationGateToResponse(formatted);
  1198	
  1199	    const cachePayload = extractSearchCachePayload(formatted);
  1200	    if (cachePayload && cacheEnabled) {
  1201	      toolCache.set(cacheKey, cachePayload, { toolName: 'memory_search' });
  1202	    }
  1203	
  1204	    responseToReturn = cachePayload
  1205	      ? buildSearchResponseFromPayload(cachePayload, _searchStartTime, false)
  1206	      : formatted;
  1207	  }
  1208	
  1209	  responseToReturn = applyPublicationGateToResponse(responseToReturn);
  1210	
  1211	  if (sessionId && isSessionRetrievalStateEnabled() && !sessionManager.isEnabled()) {
  1212	    const parsedResponse = parseResponseEnvelope(responseToReturn);
  1213	    const data = parsedResponse?.envelope.data && typeof parsedResponse.envelope.data === 'object'
  1214	      ? parsedResponse.envelope.data as Record<string, unknown>
  1215	      : null;
  1216	      const existingResults = Array.isArray(data?.results) ? data.results as SessionAwareResult[] : null;
  1217	
  1218	    if (parsedResponse && data && existingResults && existingResults.length > 0) {
  1219	      const deduped = deduplicateWithSessionState(existingResults, sessionId);
  1220	      data.results = deduped.results as SessionAwareResult[];
  1221	      data.count = deduped.results.length;
  1222	      data.sessionDedup = deduped.metadata;
  1223	      parsedResponse.envelope.data = data;
  1224	      responseToReturn = replaceResponseEnvelope(responseToReturn, parsedResponse.firstEntry, parsedResponse.envelope);
  1225	    }
  1226	  }
  1227	
  1228	  // Apply session deduplication AFTER cache
  1229	  if (sessionId && enableDedup && sessionManager.isEnabled()) {
  1230	    let resultsData: Record<string, unknown> | null = null;
  1231	    if (responseToReturn?.content?.[0]?.text && typeof responseToReturn.content[0].text === 'string') {
  1232	      try {
  1233	        resultsData = JSON.parse(responseToReturn.content[0].text) as Record<string, unknown>;
  1234	      } catch (err: unknown) {
  1235	        const message = toErrorMessage(err);
  1236	        console.warn('[memory-search] Failed to parse cached response for dedup:', message);
  1237	        resultsData = null;
  1238	      }
  1239	    } else if (responseToReturn && typeof responseToReturn === 'object') {
  1240	      resultsData = responseToReturn as unknown as Record<string, unknown>;
  1241	    }
  1242	
  1243	    // P1-018 — Validate response shape before dedup. If the cached response
  1244	    // Doesn't have the expected data.results array, log a warning and skip dedup
  1245	    // Rather than silently falling through to the un-deduped response.
  1246	    const data = (resultsData && typeof resultsData.data === 'object' && resultsData.data !== null)
  1247	      ? resultsData.data as Record<string, unknown>
  1248	      : null;

codex
There’s one very strong starting point now: `005-memory-search-runtime-bugs`. Its task file has been updated past the original findings-only state, so it doubles as the current remediation ledger: P0s are mostly marked fixed, while causal-stats, session hygiene, folder discovery, channel health, and quality fallback remain open.
exec
/bin/zsh -lc "nl -ba .opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md | sed -n '1,220p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
     1	---
     2	# SPECKIT_TEMPLATE_SOURCE: impl-summary-core | v2.2
     3	title: "Implementation Summary [system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary]"
     4	description: "Findings-only packet — implementation deferred to follow-up remediation packet. Captures bug catalog, root-cause clusters, and reproduction probes for /memory:search runtime defects."
     5	trigger_phrases:
     6	  - "005-memory-search-runtime-bugs implementation"
     7	  - "memory search runtime findings packet"
     8	importance_tier: "important"
     9	contextType: "implementation"
    10	_memory:
    11	  continuity:
    12	    packet_pointer: "system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs"
    13	    last_updated_at: "2026-04-26T14:33:00Z"
    14	    last_updated_by: "claude-opus-4-7"
    15	    recent_action: "Captured findings; remediation deferred to follow-up packet"
    16	    next_safe_action: "Schedule remediation packet to consume Cluster 1-7 from plan.md"
    17	    blockers: []
    18	    key_files:
    19	      - "spec.md"
    20	      - "plan.md"
    21	      - "tasks.md"
    22	      - "implementation-summary.md"
    23	    completion_pct: 100
    24	    open_questions:
    25	      - "Truncation root cause: estimator inflation vs unconditional stub-replace"
    26	      - "Intent classifier authority: meta.intent vs data.queryIntentRouting"
    27	      - "Edge type schema: are enabled/contradicts/derived_from implemented?"
    28	    answered_questions: []
    29	template_source_hint: "<!-- SPECKIT_TEMPLATE_SOURCE: impl-summary-core | v2.2 -->"
    30	---
    31	# Implementation Summary
    32	
    33	<!-- SPECKIT_LEVEL: 1 -->
    34	<!-- SPECKIT_TEMPLATE_SOURCE: impl-summary-core | v2.2 -->
    35	<!-- HVR_REFERENCE: .opencode/skills/sk-doc/references/hvr_rules.md -->
    36	
    37	---
    38	
    39	<!-- ANCHOR:metadata -->
    40	## Metadata
    41	
    42	| Field | Value |
    43	|-------|-------|
    44	| **Spec Folder** | 005-memory-search-runtime-bugs |
    45	| **Completed** | 2026-04-26 (findings only) |
    46	| **Level** | 1 |
    47	| **Status** | Findings captured; remediation deferred |
    48	<!-- /ANCHOR:metadata -->
    49	
    50	---
    51	
    52	<!-- ANCHOR:what-built -->
    53	## What Was Built
    54	
    55	A findings-only spec packet documenting 17 defects in the `/memory:search` command runtime, observed during a live conversation and confirmed via direct MCP probes. Defects are organized into 4 P0 (correctness), 7 P1 (degraded signal), and 6 P2 (refinement) requirements (REQ-001 through REQ-017). The plan groups them into 7 root-cause clusters; tasks decompose each cluster into work units for a follow-up remediation packet.
    56	
    57	### Cluster 1-3 Remediation (landed in this packet on 2026-04-26)
    58	
    59	The findings packet was extended in-place to land the three P0 cluster fixes:
    60	
    61	- **Cluster 1 — Truncation Wrapper (REQ-002)**:
    62	  - Added a sanity-guard early return in `enforceTokenBudget()` so when `actualTokens / budgetTokens < 0.50` the result is returned unmodified, matching the spec acceptance criterion.
    63	  - Threaded a `preservedAfterStructural` snapshot through the structural truncation loop so when the second-pass `compactStructuredResult` cannot reach budget, the `fallbackToStructuredBudget()` candidate-state ladder now starts with a "preserve survivors" envelope (full + metadata-only) before falling through to the legacy zero-fill envelopes. Returned-count metadata is re-derived from the actual emitted payload to eliminate the historical mismatch where `returnedResultCount=2` shipped alongside `count:0,results:[]`.
    64	  - File: `mcp_server/handlers/memory-context.ts` (`enforceTokenBudget` and helpers, plus the call-site at the very end of the function).
    65	
    66	- **Cluster 2 — Intent Classifier Drift (REQ-001 / REQ-004 / REQ-016)**:
    67	  - Added a centroid-only confidence floor (0.30, per spec §4A "Default fallback") that fires only when the winning intent has zero keyword + zero regex-pattern evidence. Existing single-keyword classification stays at the legacy 0.08 floor, so the 80%-accuracy regression suite (T037 / T060 / C138) keeps passing while the "Semantic Search" → fix_bug bug is eliminated.
    68	  - Annotated dual-classifier output: `meta.intent` is now explicitly `classificationKind: "task-intent"` and authoritative for rendering / anchors / mode-routing; `data.queryIntentRouting` is `classificationKind: "backend-routing"` and authoritative only for channel selection. A `seeAlso` cross-pointer breaks the symmetry the original probe flagged.
    69	  - Files: `mcp_server/lib/search/intent-classifier.ts` and `mcp_server/handlers/memory-context.ts`.
    70	
    71	- **Cluster 3 — Output Rendering Vocabulary (REQ-003)**:
    72	  - Added a "Forbidden Phrase Enforcement" subsection to the canonical command spec at `.opencode/commands/memory/search.md` §4A Step 4b. The subsection is a literal substitution table covering "Auto-triggered memories", "Triggered memories", "Constitutional memories", and the standalone "Memories" header; spells out a mandatory pre-render gate the assistant runs before emitting; and provides a regression-safe `grep -Eci` verification command.
    73	  - Source-side runtime is rendered by the assistant, so the only correct repair surface was the spec — server-side renderer was rejected to keep the change surgical.
    74	
    75	### Verification
    76	
    77	- All targeted vitest suites green: token-budget-enforcement, memory-context, handler-causal-graph, intent-classifier, intent-routing, gate-d-regression-intent-routing (200 passing tests).
    78	- Inline runtime probes via `node` against the freshly-built `dist/`:
    79	  - `classifyIntent("Semantic Search")` → `understand` (was `fix_bug` at 0.098)
    80	  - `classifyIntent("Find stuff related to semantic search")` → `understand` (REQ-016 stability)
    81	  - `classifyIntent("fix the login bug")` → `fix_bug` (single-keyword regression-safe)
    82	  - `enforceTokenBudget` under-budget → `truncated:false`, full results preserved
    83	  - `enforceTokenBudget` true over-budget → `returnedResultCount` matches `data.results.length`
    84	- `bash .opencode/skills/system-spec-kit/scripts/spec/validate.sh ... --strict` → PASSED (0 errors, 0 warnings).
    85	
    86	### Out of Scope This Packet
    87	
    88	Clusters 4-7 (P1 / P2) remain deferred per the original plan. Boundary respected: did not refactor surrounding code beyond the bug surface; did not modify the empty-arguments interactive prompt structure; did not touch the canonical command spec for anything except the Cluster 3 forbidden-phrase enforcement section.
    89	
    90	### Headline Defects
    91	
    92	- **Truncation drops results to zero at 2% budget usage** — `memory_context({input:"Semantic Search"})` reports `actualTokens:71 / budgetTokens:3000`, yet `data.content` returns `count:0,results:[]` with `truncated:true`.
    93	- **Intent classifier returns `fix_bug` for "Semantic Search"** at confidence 0.098 — spec §4A documents `understand` as the no-match fallback.
    94	- **Dual-classifier dissonance** — same response carries `meta.intent.type = "fix_bug"` (0.098) AND `data.queryIntentRouting.queryIntent = "semantic"` (0.8); no documented resolution policy.
    95	- **Vocabulary violation** — render output used "Auto-triggered memories" — explicitly forbidden by spec §4A Step 4b.
    96	- **`causal-stats` returns 3 of 6 relation types**, reports `health: "healthy"` while `meetsTarget: false`.
    97	- **Lopsided graph growth** — 344 new edges in 15 minutes, 100% `supersedes`; `caused`/`supports` stagnate.
    98	
    99	### Files Changed
   100	
   101	| File | Action | Purpose |
   102	|------|--------|---------|
   103	| `spec.md` | Create | Bug catalog with REQ-001..017 and live probe evidence |
   104	| `plan.md` | Create | 7 root-cause clusters with change surface and verification per cluster |
   105	| `tasks.md` | Create | Findings-packet tasks (T0.1-T0.7) + deferred remediation tasks (T1-T7) |
   106	| `implementation-summary.md` | Create | This file |
   107	| `description.json` | Create | Memory-indexer metadata |
   108	| `graph-metadata.json` | Create | Graph traversal metadata |
   109	<!-- /ANCHOR:what-built -->
   110	
   111	---
   112	
   113	<!-- ANCHOR:how-delivered -->
   114	## How It Was Delivered
   115	
   116	1. Read the canonical command spec at `.opencode/commands/memory/search.md` to establish the contract.
   117	2. Reviewed the conversation transcript for observable defects.
   118	3. Ran live MCP probes (`memory_context`, `memory_causal_stats`) to confirm and expand the defect set with hard evidence.
   119	4. Cross-referenced each defect against the spec to separate contract violations from undocumented gaps.
   120	5. Clustered defects by suspected root cause to enable independent remediation.
   121	6. Captured every probe's literal output in `spec.md` §8 so regressions can be detected.
   122	<!-- /ANCHOR:how-delivered -->
   123	
   124	---
   125	
   126	<!-- ANCHOR:decisions -->
   127	## Key Decisions
   128	
   129	| Decision | Why |
   130	|----------|-----|
   131	| Findings-only packet | Remediation crosses 7 surfaces in `mcp_server/`; bundling them risks scope creep. A separate packet can sequence Phase A/B/C from `plan.md`. |
   132	| Capture probe literals in `spec.md` §8 | Future runs can diff against the recorded output to confirm fix or regression. |
   133	| Cluster by root cause, not by severity | Defects sharing a root cause (e.g., REQ-001/004/016 all flow from intent classifier) are easier to fix together. |
   134	| 17 separate REQs even when clustered | Granular IDs let tasks reference exact acceptance criteria; clustering happens in plan.md. |
   135	<!-- /ANCHOR:decisions -->
   136	
   137	---
   138	
   139	<!-- ANCHOR:verification -->
   140	## Verification
   141	
   142	| Check | Result |
   143	|-------|--------|
   144	| All 17 defects map to a REQ ID | PASS |
   145	| Each REQ has a falsifiable acceptance criterion | PASS |
   146	| Probe evidence captured verbatim | PASS — see spec §8 |
   147	| Validation via `validate.sh --strict` | PENDING — runs at packet close |
   148	| Sibling cross-references resolve | PASS — siblings are 001-cache-warning-hooks, 002-memory-quality-remediation, 003-continuity-refactor-gates, 004-memory-save-rewrite |
   149	<!-- /ANCHOR:verification -->
   150	
   151	---
   152	
   153	<!-- ANCHOR:limitations -->
   154	## Known Limitations
   155	
   156	1. **No remediation in this packet.** All 7 clusters are deferred to a follow-up packet. This packet exists to capture findings while they are fresh; consuming the catalog requires a separate code-changing packet.
   157	2. **Probes are timestamp-bound.** Causal-graph edge counts grow continuously; regression detection should use coverage percent and presence-of-relation-type rather than absolute counts.
   158	3. **Some defects may share root causes not yet identified.** Cluster 2 may be fully explained by a single classifier-threshold fix; Cluster 1 may be one line in the budget enforcement wrapper. Until the source is read, clustering is informed-guess based on observable behavior.
   159	4. **CocoIndex daemon health was not directly probed.** REQ-012 is based on the conversation transcript reporting daemon-not-running; verify the daemon's actual state before remediation.
   160	<!-- /ANCHOR:limitations -->

exec
/bin/zsh -lc "rg -n \"TODO|REQ-00|Cluster|Semantic Search|folderDiscovery|quality|gap|causal-stats|memory_causal_stats|CocoIndex|fallback_tier\" .opencode/skills/system-spec-kit/mcp_server .opencode/commands/memory/search.md .opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs -g '"'!*.map'"'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/commands/memory/search.md:3:argument-hint: "<query> [--intent:<type>] | preflight <specFolder> <taskId> | postflight <specFolder> <taskId> | history <specFolder> | causal <memoryId> | link <sourceId> <targetId> <relation> | unlink <edgeId> | causal-stats | ablation | dashboard"
.opencode/commands/memory/search.md:4:allowed-tools: Read, spec_kit_memory_memory_context, spec_kit_memory_memory_quick_search, spec_kit_memory_memory_search, spec_kit_memory_memory_match_triggers, spec_kit_memory_task_preflight, spec_kit_memory_task_postflight, spec_kit_memory_memory_drift_why, spec_kit_memory_memory_causal_link, spec_kit_memory_memory_causal_stats, spec_kit_memory_memory_causal_unlink, spec_kit_memory_eval_run_ablation, spec_kit_memory_eval_reporting_dashboard, spec_kit_memory_memory_get_learning_history
.opencode/commands/memory/search.md:96:- Causal graph: Trace decision lineage, create/remove causal links, view graph stats (`memory_drift_why`, `memory_causal_link`, `memory_causal_unlink`, `memory_causal_stats`)
.opencode/commands/memory/search.md:106:- CocoIndex semantic search (`mcp__cocoindex_code__search`) integrates as the vector/semantic channel, providing natural-language code discovery alongside indexed-continuity vector search
.opencode/commands/memory/search.md:113:- Evidence-gap detection (026) to flag low-confidence retrievals with explicit gap warnings, enabling downstream reasoning to remain cautious and avoid acting on sparse evidence
.opencode/commands/memory/search.md:155:| `/memory:search causal-stats` | View causal graph statistics |
.opencode/commands/memory/search.md:172:    │   "causal-stats", "ablation", "dashboard"
.opencode/commands/memory/search.md:228:| **refactor** | architecture, patterns, decisions | technical-specs, code-quality | Need structure understanding + rationale |
.opencode/commands/memory/search.md:326:- **Leaf folder name only** as group header (last path segment, e.g., `010-search-retrieval-quality-fixes/`)
.opencode/commands/memory/search.md:329:- If two leaf names collide, prefix with parent number: `023/010-search-quality/`
.opencode/commands/memory/search.md:363:##### Forbidden Phrase Enforcement (REQ-003 / Cluster 3)
.opencode/commands/memory/search.md:455:    ├─ "causal-stats"                         → CAUSAL GRAPH (Section 5B)
.opencode/commands/memory/search.md:479:| `knowledgeGaps` | string[] | No | Identified knowledge gaps |
.opencode/commands/memory/search.md:504:  <gap1>
.opencode/commands/memory/search.md:505:  <gap2>
.opencode/commands/memory/search.md:527:| `gapsClosed` | string[] | No | Knowledge gaps closed during task |
.opencode/commands/memory/search.md:528:| `newGapsDiscovered` | string[] | No | New gaps discovered during task |
.opencode/commands/memory/search.md:558:  <gap1>
.opencode/commands/memory/search.md:559:  <gap2>
.opencode/commands/memory/search.md:694:**Trigger:** `/memory:search causal-stats`
.opencode/commands/memory/search.md:717:STATUS=OK ACTION=causal-stats COVERAGE=<pct>%
.opencode/commands/memory/search.md:851:| Causal stats | `memory_causal_stats()` | SINGLE | Show error msg |
.opencode/commands/memory/search.md:862:> **MMR and Evidence Gap Prevention:** Post-fusion MMR reduces redundant context chunks, and low-confidence retrieval can trigger an early evidence-gap warning so sparse results are treated cautiously.
.opencode/commands/memory/search.md:903:spec_kit_memory_task_postflight({ specFolder, taskId, knowledgeScore, uncertaintyScore, contextScore, gapsClosed, newGapsDiscovered })
.opencode/commands/memory/search.md:909:spec_kit_memory_memory_causal_stats({})
.opencode/commands/memory/search.md:929:| 9 | `memory_causal_stats` | L6 | Analysis | `causal-stats` |
.opencode/commands/memory/search.md:971:| `min_quality_score` | number | - | Minimum quality score threshold (0.0-1.0) |
.opencode/commands/memory/search.md:972:| `minQualityScore` | number | - | **Deprecated alias** for `min_quality_score`. Prefer the snake_case parameter name |
.opencode/commands/memory/search.md:1018:  [causal-stats]  View graph coverage statistics
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:4:description: "Findings spec cataloging /memory:search runtime bugs and refinements observed via live conversation + reproduction probes (intent classifier, truncation wrapper, output rendering, causal-stats hygiene)."
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:11:  - "causal-stats relation omission"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:14:  - "context quality degraded false hint"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:23:    next_safe_action: "Cluster fixes by root cause, then sequence remediation work in plan.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:60:| **Sibling Phases** | `001-cache-warning-hooks`, `002-memory-quality-remediation`, `003-continuity-refactor-gates`, `004-memory-save-rewrite` |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:69:A live `/memory:search` session against the indexed-continuity runtime exposed contract violations and degraded UX across the retrieval, output rendering, and causal-graph subcommands. The empty-arguments gate fired correctly, but every downstream stage produced at least one observable defect: the intent classifier emitted `fix_bug` (confidence 0.098) for the query "Semantic Search" despite the spec mandating `understand` as the no-keyword-match fallback; the `memory_context` wrapper reported `truncated=true` and zero `results` while consuming only 2% of its 3000-3500 token budget; the assistant rendering used the explicitly-forbidden phrase "Auto-triggered memories"; `causal-stats` returned three of six valid relation types and labeled itself `health: "healthy"` while reporting `meetsTarget: false`. The root spec at `.opencode/commands/memory/search.md` documents the intended behavior, but the runtime drifts from it on multiple axes.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:81:- Documenting every observed defect from the conversation transcript and the live reproduction probes against `memory_context`, `memory_search`, and `memory_causal_stats`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:82:- Cross-referencing each defect against the canonical spec at `.opencode/commands/memory/search.md` to separate documented contract violations from undocumented gaps.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:83:- Clustering defects by root cause to enable independent remediation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:113:| REQ-001 | Intent classifier MUST honor the documented no-keyword-match fallback. | For queries with no keyword hit and `confidence < 0.30`, the classifier returns `understand` (per spec §4A "Default fallback") instead of an arbitrary low-confidence intent such as `fix_bug` (currently observed at 0.098 for "Semantic Search"). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:114:| REQ-002 | `memory_context` MUST NOT zero out results when token usage is far below budget. | Reproduction: `memory_context({input:"Semantic Search", mode:"auto"})` currently returns `meta.tokenBudgetEnforcement.{enforced:true, truncated:true, returnedResultCount:2}` with `actualTokens:71` against `budgetTokens:3000`, and `data.content[0].text` containing `{"count":0,"results":[]}`. After fix, when `actualTokens / budgetTokens < 0.50`, the result count must equal `originalResultCount`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:115:| REQ-003 | Output rendering MUST use canonical vocabulary from spec §4A Step 4b. | Render layer (assistant or formatter) emits "Trigger-matched spec-doc records" and "Constitutional rules" — never "Auto-triggered memories", "Triggered memories", or "Memories". |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:116:| REQ-004 | Single intent source-of-truth MUST be exposed per response. | Currently `meta.intent.type = "fix_bug"` (conf 0.098) and `data.queryIntentRouting.queryIntent = "semantic"` (conf 0.8) appear in the SAME response with different values. Define one as authoritative for downstream rendering and either remove the other or label it explicitly as a separate concern (e.g., backend-routing vs intent-classification). |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:122:| REQ-005 | `causal-stats` MUST emit all six valid relation types (zero-filled if absent). | Spec §5B lists `caused`, `enabled`, `supersedes`, `contradicts`, `derived_from`, `supports`. Runtime returns only the three with non-zero counts. After fix, `data.by_relation` always contains all six keys. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:123:| REQ-006 | `causal-stats` health field MUST agree with `meetsTarget`. | Currently returns `health: "healthy"` AND `meetsTarget: false`. After fix, `meetsTarget=false` ⇒ `health ∈ {"degraded","below_target"}`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:124:| REQ-007 | `QUALITY=gap` flag MUST trigger automatic broadening before returning. | Spec §1 promises 3-tier FTS fallback (FTS5 → BM25 → Grep) on weak retrievals. Currently `avg_score:0.13`, `quality:"gap"` is reported but no broadening occurs. After fix, gap-flagged retrievals attempt at least one fallback tier before returning. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:125:| REQ-008 | Folder-discovery MUST NOT auto-bind on weak signal. | Currently "Semantic Search" caused `folderDiscovery.specFolder = "skilled-agent-orchestration/023-sk-deep-research-creation"` (no semantic relationship). After fix, folder-binding requires either explicit `specFolder` parameter or per-token similarity above a documented threshold. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:126:| REQ-009 | "Context quality is degraded" hint MUST be conditional on actual session state. | Currently emitted on every fresh ephemeral session. After fix, hint is suppressed when `sessionScope=="ephemeral"` and `eventCounterStart==0`. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:134:| REQ-012 | CocoIndex daemon health MUST be checked before relying on the vector channel. | Current behavior: command attempts CocoIndex search, fails silently when daemon is down. After fix, command emits an explicit `WARN: vector channel unavailable, lexical-only` line in the result block when daemon is unreachable. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:135:| REQ-013 | Sub-target coverage MUST emit a remediation suggestion. | Currently `causal-stats` reports below-target coverage with no actionable hint. After fix, output includes "Top N unlinked records" or "Run X to backfill". |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:136:| REQ-014 | AskUserQuestion custom-answer routing MUST be defined. | Spec §4 offers 7 intents + "Analysis tools". A custom answer like "Semantic Search" currently becomes the QUERY (auto-detect intent) — undocumented. Either document this routing or add explicit "Code search / Explore codebase" option that routes to CocoIndex. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:138:| REQ-016 | Intent classifier MUST be stable across paraphrased queries. | "Semantic Search" → `fix_bug`; "Find stuff related to semantic search" → `understand`. Refinement: add a stability test corpus and tune keywords or add embedding-based classification for low-confidence cases. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:139:| REQ-017 | Naming collision between "code graph" (structural) and "causal graph" (memory) MUST be disambiguated. | Currently the startup hook says `Code Graph: empty` while `causal-stats` reports 1135 edges across 675 linked records. After fix, startup hook says "structural code graph" and `causal-stats` says "memory causal graph", or reuse a single canonical noun.|
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:150:**Given** a `causal-stats` call, **when** the response is built, **then** `by_relation` contains all six valid relation keys (zero-filled if absent) and `health` agrees with `meetsTarget`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:175:| Dependency | CocoIndex daemon must be runnable for REQ-012 verification. | Medium | Document the start command and add a smoke test before remediation lands. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:195:memory_context({input:"Semantic Search", mode:"auto"})
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:207:memory_context({input:"Semantic Search", mode:"auto"})
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:216:memory_causal_stats()
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:225:memory_context({input:"Semantic Search"})
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:226:→ meta.folderDiscovery.specFolder = "skilled-agent-orchestration/023-sk-deep-research-creation"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:237:Authoritative sources: `.opencode/commands/memory/search.md` (canonical spec), `.opencode/skills/system-spec-kit/mcp_server/` (runtime), sibling packets `001-cache-warning-hooks` (token-budget patterns), `002-memory-quality-remediation` (prior repair history).
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:56:<!-- ANCHOR:quality-gates -->
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:60:- [x] All 17 defects mapped to REQ-001..017 in spec.md
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:63:- [x] Defects grouped into root-cause clusters (Cluster 1-7 in §3 below)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:72:- [ ] Each Cluster 1-7 addressed by a discrete code change
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:74:- [ ] Regression tests added for P0 fixes (REQ-001, REQ-002, REQ-003, REQ-004)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:75:<!-- /ANCHOR:quality-gates -->
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:86:### Root-Cause Clusters
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:88:- **Cluster 1 — Truncation Wrapper (P0)** — REQ-002. `memory_context` budget enforcement drops `data.content` to `count:0,results:[]` while reporting `returnedResultCount > 0`. Token usage measured at 2% of budget when truncation fires. Suspect: per-result token estimation grossly inflated, OR wrapper unconditionally stub-replaces content when `truncated=true`. Change surface: `mcp_server/.../memory_context.ts` budget enforcement layer.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:90:- **Cluster 2 — Intent Classifier Drift (P0/P1)** — REQ-001, REQ-004, REQ-016. `meta.intent.type = "fix_bug"` (confidence 0.098) returned for "Semantic Search" instead of documented `understand` fallback. Same response also carries `data.queryIntentRouting.queryIntent = "semantic"` (confidence 0.8) — two classifiers, no resolution policy. Change surface: intent detection logic + threshold gate.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:92:- **Cluster 3 — Output Rendering Vocabulary (P0)** — REQ-003. Spec §4A Step 4b mandates "Trigger-matched spec-doc records" / "Constitutional rules" wording; assistant emitted forbidden "Auto-triggered memories" phrase. Change surface: server-side renderer OR stronger spec enforcement with literal forbidden-phrase list.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:94:- **Cluster 4 — Causal-Stats Output Hygiene (P1)** — REQ-005, REQ-006, REQ-013. `causal-stats` emits 3 of 6 documented relation types (zero-omission), labels `health: "healthy"` while `meetsTarget: false`, no remediation hint when target missed. Change surface: `memory_causal_stats` serializer.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:96:- **Cluster 5 — State Hygiene (P1)** — REQ-009, REQ-011, REQ-015. Default ephemeral session lifecycle defeats `enableDedup`; "Context quality is degraded" hint emitted unconditionally; trigger/constitutional channels not deduped. Change surface: command harness session-id threading + server hint emitter guard.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:98:- **Cluster 6 — Folder Discovery + Channel Health (P1/P2)** — REQ-008, REQ-012, REQ-017. Folder-discovery binds on weak signal ("Semantic Search" → `skilled-agent-orchestration/023-sk-deep-research-creation`); CocoIndex daemon failure is silent; "code graph" vs "causal graph" naming collides. Change surface: similarity threshold + startup health check + naming disambiguation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:100:- **Cluster 7 — Quality Fallback + Edge Growth (P1/P2)** — REQ-007, REQ-010, REQ-014. `QUALITY=gap` flag is informational only; spec §1 promises 3-tier FTS fallback that never activates. Causal-graph edge growth dominated by autonomous `supersedes`-only backfill (+344 in 15 min, `caused`/`supports` unchanged). AskUserQuestion custom-answer routing undocumented. Change surface: retrieval pipeline + backfill job + command spec.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:114:- [x] Author `spec.md` with all 17 defects mapped to REQ-001..017
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:122:- [ ] **Phase 2A — P0 fixes:** Cluster 1 (truncation), Cluster 2 (intent classifier), Cluster 3 (rendering vocabulary)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:123:- [ ] **Phase 2B — P1 hygiene:** Cluster 4 (causal-stats), Cluster 5 (state hygiene), Cluster 6 (folder discovery + channel health)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:124:- [ ] **Phase 2C — P2 refinement:** Cluster 7 (quality fallback + edge growth + custom-answer routing)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:130:- [ ] Mark spec.md REQ-001..017 acceptance criteria with evidence in checklist
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:140:| Probe-based regression | Each REQ has a probe in spec §8 — re-run after fix lands | Direct MCP tool calls (memory_context, memory_causal_stats) |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:154:| Sibling packet `002-memory-quality-remediation` (backend repair history) | Internal | Green (complete) | None — informs root-cause analysis |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/plan.md:156:| CocoIndex daemon | External | Red (down — observed in conversation) | REQ-012 verification blocked until daemon runnable |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:58:- [x] T002 Author spec.md with all 17 defects mapped to REQ-001..017 (spec.md)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:74:### Cluster 1 — Truncation Wrapper (P0; REQ-002)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:81:### Cluster 2 — Intent Classifier Drift (P0/P1; REQ-001, REQ-004, REQ-016)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:86:- [x] T205 [P] Regression test verified inline: "Semantic Search" → understand (was fix_bug 0.098); "Find stuff related to semantic search" → understand; "fix the login bug" → fix_bug (single-keyword regression-safe)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:88:### Cluster 3 — Output Rendering Vocabulary (P0; REQ-003)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:91:- [x] T303 Added "Forbidden Phrase Enforcement (REQ-003 / Cluster 3)" subsection to `.opencode/commands/memory/search.md` with full forbidden→required substitution table, mandatory pre-render gate steps, and a verification grep
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:94:### Cluster 4 — Causal-Stats Output Hygiene (P1; REQ-005, REQ-006, REQ-013)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:95:- [ ] T401 Update memory_causal_stats serializer to emit all 6 relation keys (zero-fill if absent)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:100:### Cluster 5 — State Hygiene (P1; REQ-009, REQ-011, REQ-015)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:102:- [ ] T502 [P] Guard "Context quality is degraded" hint emission on fresh ephemeral
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:106:### Cluster 6 — Folder Discovery + Channel Health (P1/P2; REQ-008, REQ-012, REQ-017)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:108:- [ ] T602 [P] Add CocoIndex daemon health check at `/memory:search` invocation start
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:110:- [ ] T604 [P] Disambiguate "code graph" vs "causal graph" naming in startup hook + causal-stats output
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:111:- [ ] T605 Regression test: "Semantic Search" → `folderDiscovery=null`; daemon-down probe shows warning
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:113:### Cluster 7 — Quality Fallback + Edge Growth (P1/P2; REQ-007, REQ-010, REQ-014)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:114:- [ ] T701 Wire 3-tier FTS fallback (FTS5 → BM25 → Grep) to trigger automatically when quality=gap
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:118:- [ ] T705 Regression test: weak query triggers fallback; output includes `fallback_tier` field
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:128:- [ ] T901 Re-run spec §8 Probe 1 (intent classifier); confirm "Semantic Search" → `understand`
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:130:- [ ] T903 Re-run spec §8 Probe 3 (causal-stats); confirm all 6 relations present + health agrees with meetsTarget
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:135:- [ ] T908 Mark all REQ-001..017 acceptance criteria as PASSED in checklist or implementation-summary
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:157:- **Specification**: See `spec.md` (REQ-001..017 with acceptance criteria + probe evidence in §8)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:163:  - `../002-memory-quality-remediation/` — prior backend repair history
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:122:// Phase 023: Context metrics — lightweight session quality tracking
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:736:    hints.push(`Code graph: ${pkg.codeGraphStatus}, CocoIndex: ${pkg.cocoIndexAvailable ? 'available' : 'not installed'}`);
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:823:      lines.push(`- Session quality: ${snap.sessionQuality}`);
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:939:      // Phase 023: Record metric event for context quality tracking
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:1184:    // REQ-004: Include recovery hints in all error responses
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/description.json:9:    "causal-stats relation omission",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/description.json:12:    "context quality degraded false hint",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/description.json:14:    "quality gap fallback missing"
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:17:**Graph as a first-class feature family.** The `SPECKIT_GRAPH_*` variables form a dedicated feature family (see [Section 6](#6-graph) and [Section 7](#7-graph-calibration)) controlling structural code graph indexing, graph-first routing in the search pipeline, causal graph traversal, and calibration profiles. Since graph-first routing is now the default query dispatch order (Code Graph -> CocoIndex -> Memory), the graph env vars are among the most impactful configuration levers.
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:102:| `SPECKIT_QUALITY_AUTO_FIX` | `false` | boolean | Opt-in save-time quality auto-fix retries for planner-first flows. Disabled by default on saves. | `lib/search/search-flags.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:122:| `SPECKIT_CONFIDENCE_TRUNCATION` | `true` | boolean | Confidence-gap truncation for low-confidence result tails. Graduated ON. | `lib/search/search-flags.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:125:| `SPECKIT_TRM` | `true` | boolean | Transparent Reasoning Module: evidence-gap detection. Graduated ON. | `lib/search/search-flags.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:203:`code_graph_status` and the startup brief now surface a packet-independent `graphQualitySummary` derived from persisted detector provenance plus the latest edge-enrichment summary. Operators can use that reader to confirm whether the current graph was built with `structured`/`regex` provenance and whether the latest edge-quality signal is coming from `direct_call`, `import`, `type_reference`, `test_coverage`, or `inferred_heuristic` evidence.
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:260:| `SPECKIT_SAVE_QUALITY_GATE` | `true` | boolean | Pre-storage quality gate for memory saves. Graduated ON. | `lib/search/search-flags.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:261:| `SPECKIT_SAVE_QUALITY_GATE_EXCEPTIONS` | `true` | boolean | Short-critical quality gate exception for decision context types (REQ-D4-003). Graduated ON. | `lib/search/search-flags.ts`, `lib/validation/save-quality-gate.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:262:| `SPECKIT_QUALITY_LOOP` | `true` | boolean | Verify-fix-verify memory quality loop (T008). Graduated ON. | `lib/search/search-flags.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:304:| `SPECKIT_EVAL_LOGGING` | `false` | boolean | Enable evaluation event logging. Opt-in: set `true` to enable. | `lib/eval/eval-logger.ts`, `handlers/quality-loop.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:306:| `SPECKIT_EXTENDED_TELEMETRY` | `false` | boolean | Detailed retrieval metrics collection (latency breakdown, quality scores). Opt-in: set `true` to enable. | `lib/telemetry/retrieval-telemetry.ts` |
.opencode/skills/system-spec-kit/mcp_server/ENV_REFERENCE.md:401:# Disable the quality gate
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:16:    next_safe_action: "Schedule remediation packet to consume Cluster 1-7 from plan.md"
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:55:A findings-only spec packet documenting 17 defects in the `/memory:search` command runtime, observed during a live conversation and confirmed via direct MCP probes. Defects are organized into 4 P0 (correctness), 7 P1 (degraded signal), and 6 P2 (refinement) requirements (REQ-001 through REQ-017). The plan groups them into 7 root-cause clusters; tasks decompose each cluster into work units for a follow-up remediation packet.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:57:### Cluster 1-3 Remediation (landed in this packet on 2026-04-26)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:61:- **Cluster 1 — Truncation Wrapper (REQ-002)**:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:66:- **Cluster 2 — Intent Classifier Drift (REQ-001 / REQ-004 / REQ-016)**:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:67:  - Added a centroid-only confidence floor (0.30, per spec §4A "Default fallback") that fires only when the winning intent has zero keyword + zero regex-pattern evidence. Existing single-keyword classification stays at the legacy 0.08 floor, so the 80%-accuracy regression suite (T037 / T060 / C138) keeps passing while the "Semantic Search" → fix_bug bug is eliminated.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:71:- **Cluster 3 — Output Rendering Vocabulary (REQ-003)**:
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:79:  - `classifyIntent("Semantic Search")` → `understand` (was `fix_bug` at 0.098)
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:88:Clusters 4-7 (P1 / P2) remain deferred per the original plan. Boundary respected: did not refactor surrounding code beyond the bug surface; did not modify the empty-arguments interactive prompt structure; did not touch the canonical command spec for anything except the Cluster 3 forbidden-phrase enforcement section.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:92:- **Truncation drops results to zero at 2% budget usage** — `memory_context({input:"Semantic Search"})` reports `actualTokens:71 / budgetTokens:3000`, yet `data.content` returns `count:0,results:[]` with `truncated:true`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:93:- **Intent classifier returns `fix_bug` for "Semantic Search"** at confidence 0.098 — spec §4A documents `understand` as the no-match fallback.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:96:- **`causal-stats` returns 3 of 6 relation types**, reports `health: "healthy"` while `meetsTarget: false`.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:103:| `spec.md` | Create | Bug catalog with REQ-001..017 and live probe evidence |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:118:3. Ran live MCP probes (`memory_context`, `memory_causal_stats`) to confirm and expand the defect set with hard evidence.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:119:4. Cross-referenced each defect against the spec to separate contract violations from undocumented gaps.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:120:5. Clustered defects by suspected root cause to enable independent remediation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:133:| Cluster by root cause, not by severity | Defects sharing a root cause (e.g., REQ-001/004/016 all flow from intent classifier) are easier to fix together. |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:148:| Sibling cross-references resolve | PASS — siblings are 001-cache-warning-hooks, 002-memory-quality-remediation, 003-continuity-refactor-gates, 004-memory-save-rewrite |
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:158:3. **Some defects may share root causes not yet identified.** Cluster 2 may be fully explained by a single classifier-threshold fix; Cluster 1 may be one line in the budget enforcement wrapper. Until the source is read, clustering is informed-guess based on observable behavior.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/implementation-summary.md:159:4. **CocoIndex daemon health was not directly probed.** REQ-012 is based on the conversation transcript reporting daemon-not-running; verify the daemon's actual state before remediation.
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:11:      "system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/002-memory-quality-remediation",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:27:      "causal-stats relation omission",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:31:      "quality gap fallback",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:45:      "causal-stats",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:91:        "name": "memory_causal_stats",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:109:        "name": "Root-Cause Clusters",
.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/graph-metadata.json:115:    "causal_summary": "Live /memory:search invocation against the indexed-continuity runtime exposed 17 defects across the retrieval, output rendering, and causal-graph subcommands. P0 issues: intent classifier returns fix_bug at confidence 0.098 for 'Semantic Search' instead of the documented understand fallback; memory_context wrapper reports truncated=true with returnedResultCount>0 yet emits count:0,results:[] in the payload while consuming only 2% of token budget; output rendering uses 'Auto-triggered memories' — explicitly forbidden by spec §4A Step 4b; dual classifiers (meta.intent vs data.queryIntentRouting) emit different intents with no resolution policy. P1 issues: causal-stats returns 3 of 6 documented relation types, labels itself healthy while meetsTarget=false, exhibits lopsided supersedes-only edge growth (+344 in 15 min, caused/supports unchanged); ephemeral session defaults defeat enableDedup; 'Context quality is degraded' hint emitted unconditionally; folder-discovery binds on weak signal. P2 issues: CocoIndex daemon failure silent; QUALITY=gap flag does not trigger documented 3-tier FTS fallback; AskUserQuestion custom-answer routing undefined; 'code graph' vs 'causal graph' naming collision. Findings clustered into 7 root-cause buckets in plan.md for staged remediation by a follow-up packet.",
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:48:  description: '[L1:Orchestration] Unified entry point for context retrieval with intent-aware routing. START HERE for most context-retrieval operations across indexed spec docs and constitutional rules. For session recovery, use mode: \'resume\' with profile: \'resume\'. Automatically detects task intent (add_feature, fix_bug, refactor, security_audit, understand, find_spec, find_decision) and routes to optimal retrieval strategy. Modes: auto (default), quick (trigger-based), deep (comprehensive), focused (intent-optimized), resume (session recovery). Token Budget: 3500. For code search by concept/intent, prefer mcp__cocoindex_code__search (CocoIndex). For structural code queries (callers, imports), prefer code_graph_query.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:55:  description: '[L2:Core] Search indexed spec-doc continuity semantically using vector similarity. Returns ranked results with similarity scores. Constitutional tier rules are ALWAYS included at the top of results (~2000 tokens max), regardless of query. Requires query (string), concepts (array of 2-5 strings), or cursor (string) for continuation pagination. Supports intent-aware retrieval (REQ-006) with task-specific weight adjustments. When implicit feedback logging is enabled, searches also emit shadow-only feedback signals such as search_shown and, for includeContent runs, result_cited. Token Budget: 3500. For code search by concept/intent, prefer mcp__cocoindex_code__search (CocoIndex). For structural code queries (callers, imports), prefer code_graph_query.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:81:        description: 'Session identifier for working memory and session deduplication (REQ-001). When provided with enableDedup=true, prevents duplicate spec-doc records from being returned in the same session (~50% token savings on follow-up queries).'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:86:        description: 'Enable session deduplication (REQ-001). When true and sessionId provided, filters out already-sent spec-doc records.'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:120:      min_quality_score: {
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:124:        description: 'Minimum quality score threshold (0.0-1.0). Results with lower quality_score are filtered out.'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:130:        description: 'Deprecated alias for min_quality_score. Prefer snake_case parameter name.'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:161:        description: 'Task intent for weight adjustments (REQ-006). Explicitly set query intent to optimize scoring for specific tasks.'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:405:  inputSchema: { type: 'object', additionalProperties: false, properties: { specFolder: { type: 'string', minLength: 1, description: 'Path to spec folder (e.g., "specs/003-memory/077-upgrade")' }, taskId: { type: 'string', minLength: 1, description: 'Task identifier (e.g., "T1", "T2", "implementation")' }, knowledgeScore: { type: 'number', minimum: 0, maximum: 100, description: 'Current knowledge level (0-100): How well do you understand the task requirements and codebase context?' }, uncertaintyScore: { type: 'number', minimum: 0, maximum: 100, description: 'Current uncertainty level (0-100): How uncertain are you about the approach or implementation?' }, contextScore: { type: 'number', minimum: 0, maximum: 100, description: 'Current context completeness (0-100): How complete is your understanding of relevant context?' }, knowledgeGaps: { type: 'array', items: { type: 'string' }, description: 'List of identified knowledge gaps (optional)' }, sessionId: { type: 'string', description: 'Optional session identifier' } }, required: ['specFolder', 'taskId', 'knowledgeScore', 'uncertaintyScore', 'contextScore'] },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:411:  inputSchema: { type: 'object', additionalProperties: false, properties: { specFolder: { type: 'string', minLength: 1, description: 'Path to spec folder (must match preflight)' }, taskId: { type: 'string', minLength: 1, description: 'Task identifier (must match preflight)' }, knowledgeScore: { type: 'number', minimum: 0, maximum: 100, description: 'Post-task knowledge level (0-100)' }, uncertaintyScore: { type: 'number', minimum: 0, maximum: 100, description: 'Post-task uncertainty level (0-100)' }, contextScore: { type: 'number', minimum: 0, maximum: 100, description: 'Post-task context completeness (0-100)' }, gapsClosed: { type: 'array', items: { type: 'string' }, description: 'List of knowledge gaps closed during task (optional)' }, newGapsDiscovered: { type: 'array', items: { type: 'string' }, description: 'List of new gaps discovered during task (optional)' }, sessionId: { type: 'string', description: 'Optional session identifier. Required when multiple sessions share the same taskId and you need to target a specific learning cycle.' } }, required: ['specFolder', 'taskId', 'knowledgeScore', 'uncertaintyScore', 'contextScore'] },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:429:  name: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:600:  description: '[L6:Analysis] Get LLM-oriented compact graph neighborhoods. Accepts CocoIndex search results as seeds — use CocoIndex (mcp__cocoindex_code__search) for semantic search first, then pass results here for structural expansion. Supports manual seeds (provider: manual) and graph seeds (provider: graph). Modes: neighborhood (1-hop calls+imports), outline (file symbols), impact (reverse callers). When readiness requires a full scan, returns an explicit blocked payload with requiredAction `code_graph_scan`, readiness metadata, and lastPersistedAt instead of degraded graph answers. Successful responses include metadata.partialOutput for deadline/budget truncation details (reasons, omittedSections, omittedAnchors, truncatedText). Token Budget: 1200.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:618:            file: { type: 'string', description: 'CocoIndex file path (provider: cocoindex)' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:619:            range: { type: 'object', properties: { start: { type: 'number' }, end: { type: 'number' } }, description: 'CocoIndex line range' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:620:            score: { type: 'number', description: 'CocoIndex relevance score' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:621:            snippet: { type: 'string', description: 'CocoIndex snippet text preserved with the seed' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:628:        description: 'Seeds from CocoIndex, manual input, or graph lookups',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:718:  description: '[L7:Maintenance] Check CocoIndex availability. Returns available, binaryPath, indexExists, indexSize, and recommendation.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:724:  description: '[L7:Maintenance] Trigger CocoIndex incremental (or full) re-indexing of the workspace.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:736:  description: '[L7:Maintenance] Submit quality feedback on CocoIndex search results to improve future searches.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:759:  description: '[L1:Orchestration] Resume session with combined memory, code graph, and CocoIndex status in a single call. Use when you want the detailed merged resume payload directly. For the canonical first-call recovery path on session start or after /clear, prefer session_bootstrap. Use minimal: true to skip the heavy memory context call and return code graph, CocoIndex, structural context, hints, and session-quality metadata without the full memory payload.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:766:      minimal: { type: 'boolean', description: 'When true, skip the heavy memory context call and return code-graph, CocoIndex, structural-context, hints, and session-quality fields without the full memory payload' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:846:  description: '[L9:CoverageGraph] Structured analysis of deep-loop coverage graph state. Supports query types: uncovered_questions (questions with no coverage), unverified_claims (claims without verification), contradictions (CONTRADICTS edge pairs), provenance_chain (BFS from a node following citation/evidence edges), coverage_gaps (nodes missing incoming coverage edges), and hot_nodes (most connected nodes by edge count + weight).',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:852:      queryType: { type: 'string', enum: ['uncovered_questions', 'unverified_claims', 'contradictions', 'provenance_chain', 'coverage_gaps', 'hot_nodes'], description: 'Type of query to execute (required)' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:954:  // L8: CocoIndex
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:126:- startup/bootstrap payloads may also include `graphQualitySummary` so operators can see detector provenance and edge-enrichment quality from the last persisted scan
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:640:### memory_search: Semantic Search
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:696:When Z-score analysis signals low-confidence retrieval (insufficient signal in the indexed corpus), the server prepends an evidence gap warning to the LLM payload. This tells the AI assistant that results may be incomplete rather than letting it treat sparse results as authoritative.
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:706:- `quality`: Result quality score based on embedding confidence and match density
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:941:`sqlite-vec-darwin-arm64` is an optional dependency installed automatically on Apple Silicon. On other platforms, the equivalent platform package is resolved by npm. The server degrades to non-vector behavior when sqlite-vec is unavailable. Semantic similarity quality drops until you fix the extension.
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:1163:| v1.7.x | 2026-02-20 | Cross-encoder reranking enabled by default. Co-activation score boost fix. Query expansion on deep mode. Evidence gap warnings. MMR reranking with intent-mapped lambda. Phase system support (recursive validation, phase detection scoring). Feature flag updates. `memory_context` tokenUsage parameter. 28-tool surface area. |
.opencode/skills/system-spec-kit/mcp_server/README.md:53:> Note: When this server says "memory," it means our local indexed-continuity store — the SQLite-backed spec-doc record index that ships with this skill. It is **not** Anthropic Claude Memory (the managed product surfaced in claude.ai) and it is **not** the MCP reference `memory` server (the upstream community example). Identifiers (`memory_*` MCP tools, `memory_*` SQL tables, `memory-*.ts` handlers, `MEMORY_*` constants) are frozen by REQ-001; the disambiguation lives in operator-facing prose only.
.opencode/skills/system-spec-kit/mcp_server/README.md:59:| **MCP tools** | Live registry | Core memory layers plus dedicated code graph, CocoIndex dispatch, and Skill Advisor groups |
.opencode/skills/system-spec-kit/mcp_server/README.md:60:| **Search channels** | 5 core + CocoIndex bridge | Vector, FTS5, BM25, Causal Graph, Degree (+ CocoIndex semantic code search as external bridge) |
.opencode/skills/system-spec-kit/mcp_server/README.md:73:| **Search** | Vector similarity only | 5 core channels + CocoIndex bridge, fused with Reciprocal Rank Fusion (K tuned per intent) |
.opencode/skills/system-spec-kit/mcp_server/README.md:74:| **Routing** | No routing | Graph-first structural routing: Code Graph -> CocoIndex -> Memory; 3-tier FTS fallback when graph/semantic miss |
.opencode/skills/system-spec-kit/mcp_server/README.md:82:| **Save quality** | Accept everything | 3-layer gate (structure, semantic sufficiency, duplicate) with dry-run preview |
.opencode/skills/system-spec-kit/mcp_server/README.md:89:The indexed-continuity store exposes its MCP tools through 4 memory slash commands plus the borrowed recovery workflow in `/spec_kit:resume`. Dedicated code-graph, CocoIndex, and Skill Advisor tools live in the same server. Think of commands as doors into the system. Each door opens access only to the tools it needs.
.opencode/skills/system-spec-kit/mcp_server/README.md:245:**Five core search channels** work together, with **CocoIndex** available as an external semantic code search bridge:
.opencode/skills/system-spec-kit/mcp_server/README.md:254:| **CocoIndex** *(bridge)* | Semantic code search via vector embeddings across source files | Finding code implementations when memory channels miss; concept-first code discovery |
.opencode/skills/system-spec-kit/mcp_server/README.md:256:**Graph-first routing** determines query dispatch order: structural queries route to the Code Graph first, then CocoIndex for semantic code discovery, then the 5-channel memory pipeline. This avoids forcing one search system to handle both structural relationships and semantic similarity.
.opencode/skills/system-spec-kit/mcp_server/README.md:270:**Confidence truncation** cuts off results at 2x the median score gap so you never get a long tail of irrelevant items.
.opencode/skills/system-spec-kit/mcp_server/README.md:272:**Evidence gap detection** (TRM Z-score) flags when retrieved memories do not adequately cover the query and suggests broadening the search.
.opencode/skills/system-spec-kit/mcp_server/README.md:284:**Stage 1 -- Gather candidates** using graph-first routing: structural queries dispatch to Code Graph first, then CocoIndex for semantic code discovery, then the spec-doc record pipeline's active channels in parallel. Constitutional-tier memories are always injected regardless of score.
.opencode/skills/system-spec-kit/mcp_server/README.md:331:- **LLM query reformulation** -- asks the LLM to rephrase the query more abstractly, grounding in actual knowledge base content. Reformulated hits pass through the same scope, context and quality checks as ordinary results
.opencode/skills/system-spec-kit/mcp_server/README.md:393:**Temporal contiguity** -- gives a time-proximity boost to memories created around the same time. If one memory from a Tuesday afternoon session is relevant, others from that same session probably are too. The boost fades as the time gap grows.
.opencode/skills/system-spec-kit/mcp_server/README.md:428:**Verify-fix-verify loop** -- runs quality checks before saving. If the spec-doc record falls short, the system tries to fix problems automatically and checks again before storing.
.opencode/skills/system-spec-kit/mcp_server/README.md:434:**Signal vocabulary expansion** -- recognizes correction signals ("actually", "wait") and preference signals ("prefer", "want") in your language, shaping quality scoring.
.opencode/skills/system-spec-kit/mcp_server/README.md:468:**Result confidence scoring** -- tags each result as high, medium or low confidence using fast heuristics (no LLM needed). Checks: top-K separation, multi-channel agreement, quality score and source document structure.
.opencode/skills/system-spec-kit/mcp_server/README.md:522:Research-grade infrastructure for measuring and improving search quality over time.
.opencode/skills/system-spec-kit/mcp_server/README.md:524:**12-metric core computation** -- grades every query across twelve quality dimensions (MRR@1/3/10, NDCG@10, MAP and more). Together they pinpoint exactly where search is struggling, like a doctor running multiple tests instead of just asking "do you feel sick?"
.opencode/skills/system-spec-kit/mcp_server/README.md:526:**Synthetic ground truth corpus** -- 110 test questions with known correct answers in everyday language plus trick questions. Makes it possible to measure objectively whether changes improve or hurt quality. The corpus is keyed to live parent-memory IDs, so after DB rebuilds or imports you should rerun `scripts/evals/map-ground-truth-ids.ts` against the active `context-index.sqlite` before trusting ablation or reporting deltas.
.opencode/skills/system-spec-kit/mcp_server/README.md:528:**Ablation study framework** -- turns off each search channel one at a time and measures quality degradation (Recall@20 delta). Identifies which components are critical.
.opencode/skills/system-spec-kit/mcp_server/README.md:542:**Architecture:** CocoIndex (semantic, external MCP) finds code by concept. Code Graph (structural, this server) maps imports, calls and hierarchy. Memory (session, this server) preserves decisions. The compact-merger combines all three under a 4000-token budget for compaction injection. Code-graph source is self-contained under `code-graph/` with `handlers/`, `lib/`, `tools/`, and `tests/`.
.opencode/skills/system-spec-kit/mcp_server/README.md:566:**Query routing:** Structural queries (callers, imports, dependencies) go to `code_graph_query`. Semantic and concept queries go to CocoIndex (`mcp__cocoindex_code__search`). Session and memory queries go to `memory_context`.
.opencode/skills/system-spec-kit/mcp_server/README.md:655:Resume session with combined memory, code graph and CocoIndex status in a single call. Use when you want the detailed merged resume payload directly. The response carries freshness-aware code-graph status (`fresh`, `stale`, `empty`, `error`) instead of count-only health. Session-resume auth binds `args.sessionId` to the transport caller context from `lib/context/caller-context.ts`; mismatches are rejected by default, with `MCP_SESSION_RESUME_AUTH_MODE=permissive` available for canary rollout. For the canonical first-call recovery path on session start or after `/clear`, prefer `session_bootstrap`, and for operator-facing packet recovery prefer `/spec_kit:resume`, which reconstructs context from `handover.md`, then `_memory.continuity`, then packet docs.
.opencode/skills/system-spec-kit/mcp_server/README.md:660:| `minimal` | boolean | Skip heavy memory context, return code graph, CocoIndex, structural context, hints, and optional session quality without the full memory payload |
.opencode/skills/system-spec-kit/mcp_server/README.md:695:| `min_quality_score` | number | Filter out low-quality results |
.opencode/skills/system-spec-kit/mcp_server/README.md:760:| `skipPreflight` | boolean | Bypass quality gate (not recommended) |
.opencode/skills/system-spec-kit/mcp_server/README.md:808:| `includeScores` | boolean | Include composite quality scores |
.opencode/skills/system-spec-kit/mcp_server/README.md:816:Run a health check. This is the diagnostic tool for when search quality degrades or something feels off. It checks for stale indexes, divergent aliases, broken embeddings and other issues. It can also attempt automatic repairs.
.opencode/skills/system-spec-kit/mcp_server/README.md:955:| `knowledgeGaps` | string[] | Known gaps before starting |
.opencode/skills/system-spec-kit/mcp_server/README.md:973:| `gapsClosed` | string[] | Gaps resolved during the task |
.opencode/skills/system-spec-kit/mcp_server/README.md:974:| `newGapsDiscovered` | string[] | New gaps found during the task |
.opencode/skills/system-spec-kit/mcp_server/README.md:1006:##### `memory_causal_stats`
.opencode/skills/system-spec-kit/mcp_server/README.md:1075:Get LLM-oriented compact graph neighborhoods. Accepts CocoIndex search results as seeds for structural expansion. Modes: `neighborhood` (1-hop calls plus imports), `outline` (file symbols), `impact` (reverse callers). Successful responses return `status: "ok"` plus readiness/trust metadata, resolved anchors, graph context, and `data.metadata.partialOutput` so callers can see whether deadline or token-budget pressure produced partial output. When the read path determines the graph needs a full scan, the tool returns an explicit `status: "blocked"` payload with `data.blocked`, `graphAnswersOmitted`, `requiredAction: "code_graph_scan"`, and the same readiness/trust metadata instead of partial graph answers.
.opencode/skills/system-spec-kit/mcp_server/README.md:1082:| `seeds` | array | Seeds from CocoIndex, manual input or graph lookups |
.opencode/skills/system-spec-kit/mcp_server/README.md:1095:Scan the workspace for new or changed packet continuity docs and supporting generated context artifacts and add them to the index. Use after adding files manually or after a git pull. Processes three source families: constitutional rules, spec documents, and supporting generated context artifacts. Spec documents stay indexed by default; during scan they run through the save pipeline in warn-only quality mode so validation issues surface as warnings instead of silently bypassing retrieval.
.opencode/skills/system-spec-kit/mcp_server/README.md:1190:Check CocoIndex availability, binary path and index status.
.opencode/skills/system-spec-kit/mcp_server/README.md:1194:| _(none required)_ |  | Returns CocoIndex health |
.opencode/skills/system-spec-kit/mcp_server/README.md:1200:Trigger CocoIndex incremental or full re-indexing of the workspace.
.opencode/skills/system-spec-kit/mcp_server/README.md:1210:Submit quality feedback on CocoIndex search results to improve future searches.
.opencode/skills/system-spec-kit/mcp_server/README.md:1258:| `handlers/memory-save.ts` | Runs the save pipeline: validates structure, checks dedup/quality gates, generates embeddings, and stores the result. |
.opencode/skills/system-spec-kit/mcp_server/README.md:1287:| L8 | Code Graph + Skill Graph + CocoIndex bridge + Skill Advisor | 15 | 1,400 | Code graph scan/query/status/context, `detect_changes`, skill graph + advisor (`advisor_recommend`/`advisor_status`/`advisor_validate`), CocoIndex bridge (`ccc_status`/`ccc_reindex`/`ccc_feedback`) |
.opencode/skills/system-spec-kit/mcp_server/README.md:1510:    "gapsClosed": ["RRF k-value tuning", "MPAB aggregation logic"]
.opencode/skills/system-spec-kit/mcp_server/README.md:1546:**Common causes**: Stale BM25 index, divergent aliases in FTS5 or memories with low quality scores surfacing.
.opencode/skills/system-spec-kit/mcp_server/README.md:1548:**Fix**: Run a health check with auto-repair, then retry with a higher quality floor:
.opencode/skills/system-spec-kit/mcp_server/README.md:1555:{ "tool": "memory_search", "arguments": { "query": "your query", "min_quality_score": 0.5 } }
.opencode/skills/system-spec-kit/mcp_server/README.md:1572:If it shows `INSUFFICIENT_CONTEXT_ABORT`, add more real evidence. If it shows a template-contract failure, fix the markdown structure. Do not lower quality thresholds to bypass legitimate rejections.
.opencode/skills/system-spec-kit/mcp_server/README.md:1662:No. The server runs with HuggingFace local embeddings out of the box whenever no cloud API key is present. Leave `EMBEDDINGS_PROVIDER=auto` for that fallback, or force `EMBEDDINGS_PROVIDER=hf-local` if you want to pin the local provider explicitly. Voyage AI gives better retrieval quality but is optional.
.opencode/skills/system-spec-kit/mcp_server/README.md:1704:A dry run validates the file against the quality gate, estimates the token budget, checks for duplicates and returns a report, all without writing anything to the database. Use it to verify a file will pass before committing.
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:149:  'coverage_gaps',
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:197:  min_quality_score: boundedNumber(0, 1).optional(),
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:371:  gapsClosed: optionalStringArray,
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:606:  memory_causal_stats: memoryCausalStatsSchema as unknown as ToolInputSchema,
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:647:  memory_search: ['cursor', 'query', 'concepts', 'specFolder', 'tenantId', 'userId', 'agentId', 'limit', 'sessionId', 'enableDedup', 'tier', 'contextType', 'useDecay', 'includeContiguity', 'includeConstitutional', 'enableSessionBoost', 'enableCausalBoost', 'includeContent', 'anchors', 'min_quality_score', 'minQualityScore', 'bypassCache', 'rerank', 'applyLengthPenalty', 'applyStateLimits', 'minState', 'intent', 'autoDetectIntent', 'trackAccess', 'includeArchived', 'mode', 'includeTrace', 'profile'],
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:663:  task_postflight: ['specFolder', 'taskId', 'knowledgeScore', 'uncertaintyScore', 'contextScore', 'gapsClosed', 'newGapsDiscovered', 'sessionId'],
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:666:  memory_causal_stats: [],
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:735:        // Always spread caller-provided extraData (pipeline trace, timing, evidence gaps, etc.)
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1031:    // REQ-D5-004: Request-level quality assessment (additive)
.opencode/skills/system-spec-kit/mcp_server/formatters/search-results.ts:1036:  // Always spread caller-provided extraData (pipeline trace, timing, evidence gaps, etc.).
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/scorer/lanes/explicit.ts:168:  if (WRITE_VERBS.test(lower) && /\b(error classes|trigger gap|reporter|mismatches?|bucket|gate 3)\b/.test(lower)) {
.opencode/skills/system-spec-kit/mcp_server/tests/fsrs-scheduler.vitest.ts:299:    // Accept strict equality or floating point precision
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill-graph.json:1:{"schema_version": 1, "generated_at": "2026-04-26T07:02:59.657976+00:00", "skill_count": 22, "families": {"cli": ["cli-claude-code", "cli-codex", "cli-copilot", "cli-gemini", "cli-opencode"], "mcp": ["mcp-chrome-devtools", "mcp-clickup", "mcp-coco-index", "mcp-code-mode", "mcp-figma"], "sk-code": ["sk-code-full-stack", "sk-code-opencode", "sk-code-review", "sk-code-web"], "sk-deep": ["sk-deep-research", "sk-deep-review"], "sk-util": ["sk-doc", "sk-git", "sk-improve-agent", "sk-improve-prompt"], "system": ["skill-advisor", "system-spec-kit"]}, "adjacency": {"cli-claude-code": {"siblings": {"cli-codex": 0.5, "cli-copilot": 0.5, "cli-gemini": 0.5, "cli-opencode": 0.5}}, "cli-codex": {"siblings": {"cli-claude-code": 0.5, "cli-copilot": 0.5, "cli-gemini": 0.5, "cli-opencode": 0.5}}, "cli-copilot": {"siblings": {"cli-claude-code": 0.5, "cli-codex": 0.5, "cli-gemini": 0.5, "cli-opencode": 0.5}}, "cli-gemini": {"siblings": {"cli-claude-code": 0.5, "cli-codex": 0.5, "cli-copilot": 0.5, "cli-opencode": 0.5}}, "cli-opencode": {"siblings": {"cli-claude-code": 0.5, "cli-codex": 0.5, "cli-copilot": 0.5, "cli-gemini": 0.5}}, "mcp-chrome-devtools": {"depends_on": {"mcp-code-mode": 0.7}, "enhances": {"sk-code-web": 0.5}}, "mcp-clickup": {"depends_on": {"mcp-code-mode": 0.9}}, "mcp-coco-index": {"enhances": {"system-spec-kit": 0.3}, "prerequisite_for": {"skill-advisor": 0.7}}, "mcp-code-mode": {"prerequisite_for": {"mcp-figma": 0.9, "mcp-clickup": 0.9, "mcp-chrome-devtools": 0.7}}, "mcp-figma": {"depends_on": {"mcp-code-mode": 0.9}, "enhances": {"sk-code-web": 0.4}}, "sk-code-full-stack": {"enhances": {"sk-code-review": 0.3}, "siblings": {"sk-code-opencode": 0.4, "sk-code-web": 0.4}}, "sk-code-opencode": {"enhances": {"sk-code-review": 0.3}, "siblings": {"sk-code-full-stack": 0.4, "sk-code-web": 0.4}}, "sk-code-review": {"enhances": {"sk-code-opencode": 0.7, "sk-code-web": 0.7, "sk-code-full-stack": 0.7}, "prerequisite_for": {"sk-deep-review": 0.8}}, "sk-code-web": {"enhances": {"sk-code-review": 0.3}, "siblings": {"sk-code-opencode": 0.4, "sk-code-full-stack": 0.4}}, "sk-deep-research": {"siblings": {"sk-deep-review": 0.5}}, "sk-deep-review": {"depends_on": {"sk-code-review": 0.8}, "siblings": {"sk-deep-research": 0.5}}, "sk-doc": {"enhances": {"system-spec-kit": 0.5}, "siblings": {"sk-git": 0.4}}, "sk-git": {"siblings": {"sk-doc": 0.4}}, "sk-improve-agent": {"siblings": {"sk-improve-prompt": 0.4}}, "sk-improve-prompt": {"enhances": {"cli-claude-code": 0.4, "cli-codex": 0.4, "cli-copilot": 0.4, "cli-gemini": 0.4}, "siblings": {"sk-improve-agent": 0.4}}, "skill-advisor": {"depends_on": {"mcp-coco-index": 0.7}, "enhances": {"cli-claude-code": 0.7, "cli-codex": 0.7, "cli-copilot": 0.7, "cli-gemini": 0.7, "mcp-chrome-devtools": 0.7, "mcp-clickup": 0.7, "mcp-coco-index": 0.7, "mcp-code-mode": 0.7, "mcp-figma": 0.7, "sk-code-full-stack": 0.7, "sk-code-opencode": 0.7, "sk-code-review": 0.7, "sk-code-web": 0.7, "sk-deep-research": 0.7, "sk-deep-review": 0.7, "sk-doc": 0.7, "sk-git": 0.7, "sk-improve-agent": 0.7, "sk-improve-prompt": 0.7, "system-spec-kit": 0.7}}, "system-spec-kit": {"enhances": {"sk-doc": 0.4, "sk-git": 0.3, "sk-code-opencode": 0.3}}}, "signals": {"cli-claude-code": ["claude code", "claude cli", "delegate to claude"], "cli-codex": ["codex cli", "codex exec", "delegate to codex"], "cli-copilot": ["copilot cli", "delegate to copilot"], "cli-gemini": ["gemini cli", "delegate to gemini", "google search"], "cli-opencode": ["opencode cli", "opencode run", "delegate to opencode", "parallel detached session", "spec kit runtime"], "mcp-chrome-devtools": ["chrome devtools", "browser debug", "dom inspect", "lighthouse"], "mcp-clickup": ["clickup", "project management", "clickup task"], "mcp-coco-index": ["semantic search", "code search", "find code", "coco index"], "mcp-code-mode": ["code mode", "mcp tool", "call tool chain"], "mcp-figma": ["figma", "design file", "figma component", "figma export"], "sk-code-full-stack": ["full stack", "implement feature", "stack detection"], "sk-code-opencode": ["opencode", "system code", "mcp server code", "skill code"], "sk-code-review": ["code review", "pr review", "security review", "quality gate", "findings"], "sk-code-web": ["web code", "frontend", "webflow", "css standards"], "sk-deep-research": ["deep research", "research loop", "investigate"], "sk-deep-review": ["deep review", "review loop", "iterative review", "spec folder review"], "sk-doc": ["create readme", "write documentation", "install guide", "feature catalog"], "sk-git": ["git workflow", "worktree", "conventional commit", "pull request", "finish work"], "sk-improve-agent": ["improve agent", "evaluate agent", "agent scoring"], "sk-improve-prompt": ["improve prompt", "enhance prompt", "prompt framework", "clear score"], "skill-advisor": ["skill routing", "gate 2", "which skill", "route request"], "system-spec-kit": ["spec folder", "save context", "save memory", "spec kit", "memory search"]}, "conflicts": [], "hub_skills": ["cli-claude-code", "cli-codex", "cli-copilot", "cli-gemini", "cli-opencode", "mcp-code-mode", "sk-code-full-stack", "sk-code-opencode", "sk-code-review", "sk-code-web"], "topology_warnings": {}}
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/scorer/scoring-constants.ts:108:  readonly semanticSearchCocoIndexBonus: number;
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/scorer/scoring-constants.ts:175:    semanticSearchCocoIndexBonus: 0.5,
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator.vitest.ts:27:  qualityScore: number;
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator.vitest.ts:28:  qualityFlags: string[];
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator.vitest.ts:162:    qualityScore: 0.9,
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator.vitest.ts:163:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/README.md:14:| `context.ts` | `code_graph_context` | Build LLM-oriented graph neighborhoods from manual, graph, or CocoIndex seeds; successful responses include anchors, graph context, and `metadata.partialOutput`, while full-scan-required reads return an explicit blocked payload with `requiredAction: "code_graph_scan"` |
.opencode/skills/system-spec-kit/mcp_server/tools/types.ts:67:  min_quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/tools/types.ts:255:  gapsClosed?: string[];
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/03--lifecycle-routing/01-age-haircut.md:31:`lib/lifecycle/age-haircut.ts` reads each skill's source modification time and applies a documented decay curve to the derived lane only. The `explicit_author`, `lexical`, `graph_causal`, and `semantic_shadow` lanes are untouched. The haircut shows up as a gap between `rawScore` and `weightedScore` in lane attribution for the derived lane.
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-reindex.ts:2:// MODULE: CocoIndex Re-index Handler
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-reindex.ts:39:            error: 'CocoIndex binary not found. Install: bash .opencode/skills/mcp-coco-index/scripts/install.sh',
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/scorer/fusion.ts:220:    if (recommendation.skill === 'mcp-coco-index') return R.semanticSearchCocoIndexBonus;
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:27:  'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:36:    case 'memory_causal_stats':  return handleMemoryCausalStats(parseArgs<CausalStatsArgs>(validateToolArgs('memory_causal_stats', args)));
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/fixtures/skill_advisor_regression_cases.jsonl:40:{"id":"P1-ABSTAIN-002","priority":"P1","prompt":"optimize skill_advisor.py execution speed and recommendation quality","confidence_only":false,"expect_result":false,"expected_top_any":[],"allow_command_bridge":false}
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:138:  it('T8: truncates at clear gap above threshold', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:141:    // Median gap (of 4): sort=[0.02,0.03,0.05,0.72] → (0.03+0.05)/2 = 0.04
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:175:  it('T11: cutoffGap reflects the gap that triggered truncation', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:199:    // Even if there is a gap at index 0, we must respect minResults=3
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:200:    // Gap[0] between index 0 and 1 = 0.9-0.1 = 0.8; median gap with 4 items = large
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:201:    // Since minResults=3 and we start search at index 2, gap[0] is skipped
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:213:    // With the actual numbers the large gap at 0 is not searched; no truncation
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:218:    // With minResults=2 we start searching at gap[1]
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:224:    // Start at i=1 (minResults-1=1): gap[1] = 0.75 > 0.10 → cutoffIndex=1 (keep 2 results)
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:255:  it('T18: no truncation when all gaps are equal', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:258:    // No gap exceeds threshold
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:272:  it('T20: no truncation returned with correct metadata when no gap found', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:334:    // 4 relevant (high scores, tight gaps) + 8 irrelevant (low scores, tight gaps).
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:335:    // Cliff at index 3→4 (gap ≈ 0.65, vs tiny gaps elsewhere).
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:374:    const gaps = computeGaps([1.0, 0.8, 0.5, 0.1]);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:375:    expect(gaps).toHaveLength(3);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:376:    expect(gaps[0]).toBeCloseTo(0.2, 10);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:377:    expect(gaps[1]).toBeCloseTo(0.3, 10);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:378:    expect(gaps[2]).toBeCloseTo(0.4, 10);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:457:    const gaps = computeGaps([0.9, NaN, 0.5]);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:459:    expect(gaps).toHaveLength(1);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:460:    expect(gaps[0]).toBeCloseTo(0.4, 10);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:464:    const gaps = computeGaps([Infinity, 0.9, 0.5]);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:466:    expect(gaps).toHaveLength(1);
.opencode/skills/system-spec-kit/mcp_server/tests/confidence-truncation.vitest.ts:467:    expect(gaps[0]).toBeCloseTo(0.4, 10);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_regression.py:6:"""Regression harness for skill_advisor routing quality.
.opencode/skills/system-spec-kit/mcp_server/tests/spec-folder-hierarchy.vitest.ts:153:  it('creates implicit parent nodes for gaps in hierarchy', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/graph-regression-flag-off.vitest.ts:92:    it('T022-5f: Strict equality — "false" disables flag', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-extended.vitest.ts:263:    it.skipIf(!resolveFn)('prefers exact path equality before fuzzy path fallback', () => {
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-feedback.ts:2:// MODULE: CocoIndex Feedback Handler
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-feedback.ts:4:// MCP tool handler for ccc_feedback — accepts search result quality feedback.
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:138:      qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:139:      qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:193:        qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:194:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:239:        qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:240:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:312:        qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:313:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:375:        qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:376:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:432:        qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/reconsolidation-bridge.vitest.ts:433:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:92:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:105:    '../handlers/quality-loop.js',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:106:    '../lib/validation/save-quality-gate.js',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:241:  vi.doMock('../handlers/quality-loop.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:242:    const actual = await importOriginal<typeof import('../handlers/quality-loop.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:255:  vi.doMock('../lib/validation/save-quality-gate.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:256:    const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate.js')>();
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:3:# check-prompt-quality-card-sync.sh — Verify prompt quality card sync
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:5:# Verifies that prompt quality framework tables stay in sync across CLI skills.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:7:# Usage: check-prompt-quality-card-sync.sh [repo-root]
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:13:  "$ROOT/.opencode/skills/sk-improve-prompt/assets/cli_prompt_quality_card.md"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:14:  "$ROOT/.opencode/skills/cli-claude-code/assets/prompt_quality_card.md"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:15:  "$ROOT/.opencode/skills/cli-codex/assets/prompt_quality_card.md"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:16:  "$ROOT/.opencode/skills/cli-copilot/assets/prompt_quality_card.md"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/check-prompt-quality-card-sync.sh:17:  "$ROOT/.opencode/skills/cli-gemini/assets/prompt_quality_card.md"
.opencode/skills/system-spec-kit/mcp_server/tests/reranker-eval-comparison.vitest.ts:4:// Cohere/Voyage reranker quality. Documents comparison protocol and
.opencode/skills/system-spec-kit/mcp_server/tests/reranker-eval-comparison.vitest.ts:99:    { id: 902, content: 'Prompt improvement rubric for assistant response quality. '.repeat(2) },
.opencode/skills/system-spec-kit/mcp_server/tests/reranker-eval-comparison.vitest.ts:395:      tolerance: 0.15, // max acceptable quality gap
.opencode/skills/system-spec-kit/mcp_server/tests/migration-lineage-identity.vitest.ts:36:  '001-memory-search-routing-tuning/003-graph-metadata-validation/007-entity-quality-improvements',
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-status.ts:2:// MODULE: CocoIndex Status Handler
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-status.ts:4:// MCP tool handler for ccc_status — reports CocoIndex availability and stats.
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-status.ts:55:              ? 'Install CocoIndex: bash .opencode/skills/mcp-coco-index/scripts/install.sh'
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/ccc-status.ts:58:                : 'CocoIndex is ready. Use mcp__cocoindex_code__search for semantic queries.',
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/routing-accuracy/labeled-prompts.jsonl:131:{"id":"rr-iter3-131","bucket":"mixed_ambiguous","source_type":"synthetic-edge","prompt":"Analyze the current error classes and patch the obvious trigger gap.","gate3_triggers":"yes","gate3_reason_category":"mixed_ambiguous","skill_top_1":"sk-code-opencode","skill_correct":"yes","notes":"analyze plus patch"}
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-search.vitest.ts:119:  it('C138-T1: evidence gap warning format is valid markdown blockquote', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-ux-regressions.vitest.ts:387:  // Optional enrichment and quality-gate suites are covered elsewhere and can
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/04--scorer-fusion/03-ambiguity.md:31:`lib/scorer/ambiguity.ts` measures the gap between the top-1 and top-2 aggregate scores. When the delta is <= 0.05, the response carries an ambiguity signal that the render path surfaces as an ambiguous brief. When the delta exceeds the window, top-1 is returned unambiguously.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1128:    # Code quality & fixes
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1132:    "test": ["verify", "validate", "check", "spec", "quality"],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1444:    "quality gate": [("sk-code-review", 2.0)],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1445:    "quality gate validation": [("sk-code-review", 1.8)],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1508:    "evaluate agent quality": [("sk-improve-agent", 2.8)],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1517:    # --- CocoIndex semantic code search ---
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1789:# Multiplier applied to CocoIndex relevance score (0-1) to produce an advisor boost.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1799:# Max results from CocoIndex when using built-in search.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1860:        "phrases": ["code review", "pr review", "security review", "quality gate", "request changes"],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:1981:    """Map a CocoIndex result file path to a known skill name.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2100:    """Blend CocoIndex semantic search results into keyword scoring.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2124:    """Return the preferred CocoIndex binary path, favoring the repo-local install."""
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2131:    """Return True when external CocoIndex lookup is disabled via environment."""
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2548:# appear as candidates within a thin margin, enforce a ≥ 0.10 confidence gap
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2616:        gap = winner_conf - loser_conf
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2617:        if gap >= DISAMBIGUATION_MARGIN:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2694:        semantic_hits: Optional CocoIndex search results as a list of
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2722:    # Blend CocoIndex semantic search results when available
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3144:  # CocoIndex semantic search (built-in, requires ccc daemon):
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3148:  # CocoIndex semantic search (pre-computed MCP results):
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3182:                         help='Run CocoIndex semantic search (via ccc CLI) to supplement keyword matching.')
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3184:                         help='Pre-computed CocoIndex results as JSON array of {"path": str, "score": float} objects.')
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:98:  it('returns true when upstream evidence-gap detection marks coverage incomplete', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:156:  it('emits status "partial" when evidence-gap detection marks incomplete coverage', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:196:  it('emits reason "knowledge_gap" as default for medium-length query with no filter', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:202:    expect(payload.reason).toBe('knowledge_gap');
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:205:  it('emits reason "knowledge_gap" when query is null', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:211:    expect(payload.reason).toBe('knowledge_gap');
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:236:  it('recommends "save_memory" for no_results + knowledge_gap', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:250:  it('recommends "ask_user" for low_confidence + knowledge_gap', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-recovery-payload.vitest.ts:330:    const validReasons = ['spec_filter_too_narrow', 'low_signal_query', 'knowledge_gap'] as const;
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_graph_compiler.py:40:    "cli-orchestrator", "mcp-tool", "code-quality",
.opencode/skills/system-spec-kit/mcp_server/tests/handler-helpers.vitest.ts:455:  it('requires exact scope equality when a governance scope is supplied', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-reconsolidation.vitest.ts:98:    qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-reconsolidation.vitest.ts:99:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:37:      'Continue from the last stable checkpoint after validating the atomic save path and its quality-gate ordering.',
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:218:  vi.doMock('../handlers/quality-loop', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:219:    const actual = await importOriginal<typeof import('../handlers/quality-loop')>();
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:226:  vi.doMock('../lib/validation/save-quality-gate', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:227:    const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate')>();
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:234:  vi.doMock('../lib/validation/save-quality-gate.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:235:    const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:395:    vi.doUnmock('../handlers/quality-loop');
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:396:    vi.doUnmock('../lib/validation/save-quality-gate');
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-fallback-fingerprint.vitest.ts:397:    vi.doUnmock('../lib/validation/save-quality-gate.js');
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:8:// T1-T5   : extractValidationMetadata — quality score signals
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:39:describe('extractValidationMetadata — quality score signals', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:40:  it('T1: extracts qualityScore from db quality_score when present and positive', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:41:    const row = makeRow({ quality_score: 0.85 });
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:45:    expect(meta!.qualityScore).toBeCloseTo(0.85, 5);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:48:  it('T2: clamps qualityScore above 1.0 to 1.0; treats negative as absent (no tier fallback → null)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:50:    const rowHigh = makeRow({ quality_score: 1.5 });
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:51:    expect(extractValidationMetadata(rowHigh)!.qualityScore).toBe(1.0);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:53:    // Negative quality_score is treated as absent. Without a tier, returns null.
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:54:    const rowLow = makeRow({ quality_score: -0.3 });
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:57:    // Negative quality_score with a tier falls back to tier score.
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:58:    const rowLowWithTier = makeRow({ quality_score: -0.3, importance_tier: 'normal' });
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:59:    expect(extractValidationMetadata(rowLowWithTier)!.qualityScore).toBe(TIER_QUALITY_SCORES['normal']);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:62:  it('T3: falls back to tier score when quality_score is zero', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:63:    const row = makeRow({ quality_score: 0, importance_tier: 'critical' });
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:67:    expect(meta!.qualityScore).toBe(TIER_QUALITY_SCORES['critical']);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:70:  it('T4: falls back to tier score when quality_score is absent', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:75:    expect(meta!.qualityScore).toBe(TIER_QUALITY_SCORES['important']);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:78:  it('T5: maps all known importance tiers to expected quality scores', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:92:      expect(meta!.qualityScore).toBe(score);
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:233:  it('T15: returns null when row has no signals (no tier, no quality_score, no content)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:253:    expect(meta!.qualityScore).toBe(0.5); // from tier
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:278:      makeRow({ id: 1, importance_tier: 'critical', quality_score: 0.9 }),
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:313:        quality_score: 0.92,
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:322:    expect(meta.qualityScore).toBeCloseTo(0.92, 5); // DB score takes priority
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:343:        quality_score: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:404:  it('applies higher score to higher-quality validation metadata', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:410:          qualityScore: 0.95,
.opencode/skills/system-spec-kit/mcp_server/tests/validation-metadata.vitest.ts:420:          qualityScore: 0.2,
.opencode/skills/system-spec-kit/mcp_server/tests/empty-result-recovery.vitest.ts:13:  'knowledge_gap',
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/README.md:3:Core implementation for the structural code graph system. Provides file parsing, SQLite storage, graph queries, CocoIndex bridge, budget allocation, and compaction merging.
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/README.md:14:| `seed-resolver.ts` | Resolves CocoIndex file:line results to graph nodes |
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/README.md:18:| `compact-merger.ts` | 3-source merge (Memory + Code Graph + CocoIndex) for compaction |
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/README.md:24:- **CocoIndex** (semantic, external MCP): finds relevant code by concept
.opencode/skills/system-spec-kit/mcp_server/tests/short-critical-quality-gate.vitest.ts:10:} from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/intent-classifier.vitest.ts:34:    'improve code quality in handlers',
.opencode/skills/system-spec-kit/mcp_server/tests/intent-classifier.vitest.ts:593:        'improve and optimize code quality',
.opencode/skills/system-spec-kit/mcp_server/tests/intent-classifier.vitest.ts:662:      refactor: ['refactor code', 'clean up codebase', 'restructure project', 'improve quality', 'reduce debt'],
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:50:  isCocoIndexAvailable: vi.fn(() => false),
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:77:    expect(brief.startupSurface).toContain('- CocoIndex: missing');
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:134:    vi.mocked(cocoIndexPath.isCocoIndexAvailable).mockReturnValueOnce(true);
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:137:    expect(brief.startupSurface).toContain('- CocoIndex: available');
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:143:    expect(brief.graphOutline).toContain('CocoIndex');
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/manual_testing_playbook.md:261:Archived scenario-execution reports. Each report captures a dated end-to-end pass across all 42 scenarios with PASS/FAIL evidence, test counts, and known gaps.
.opencode/skills/system-spec-kit/mcp_server/tests/spec-folder-prefilter.vitest.ts:127:    qualityThreshold: undefined,
.opencode/skills/system-spec-kit/mcp_server/tests/retry-budget-telemetry.vitest.ts:65:        qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/retry-budget-telemetry.vitest.ts:121:      qualityScore: 0.9,
.opencode/skills/system-spec-kit/mcp_server/tests/retry-budget-telemetry.vitest.ts:186:      qualityScore: 0.95,
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/query-intent-classifier.ts:6:// (CocoIndex) vs hybrid (both).
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/query-intent-classifier.ts:118: * (code graph) and semantic (CocoIndex) retrieval backends.
.opencode/skills/system-spec-kit/mcp_server/tests/search-flags.vitest.ts:285:  it('save reconsolidation, post-insert enrichment, quality auto-fix default to false (opt-in)', () => {
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:323:          qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:324:          qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:339:          qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:340:          qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:359:      quality_score: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/create-record.ts:360:      quality_flags: JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:24:  { tool: 'memory_causal_stats', handler: 'handleMemoryCausalStats', layer: 'L6' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:51:  { camel: 'handleMemoryCausalStats', snake: 'handle_memory_causal_stats' },
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-context.ts:4:// LLM-oriented compact graph neighborhoods with CocoIndex seed support.
.opencode/skills/system-spec-kit/mcp_server/tests/adversarial/README.md:40:  folder's new `compact-prime-identity-race.vitest.ts` closes the gap.
.opencode/skills/system-spec-kit/mcp_server/tests/adversarial/README.md:174:adversarial regression here to close the coverage gap noted in the
.opencode/skills/system-spec-kit/mcp_server/tests/archive/coverage-graph-tools.vitest.ts:219:    it('graph signals participate in quality gate sub-checks', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/archive/coverage-graph-tools.vitest.ts:220:      const qualityGateChecks = [
.opencode/skills/system-spec-kit/mcp_server/tests/archive/coverage-graph-tools.vitest.ts:227:      expect(qualityGateChecks).toContain('graphCoverage');
.opencode/skills/system-spec-kit/mcp_server/handlers/save/embedding-pipeline.ts:209:  console.error(`[memory-save] Embedding cache STORE after quality gate for ${path.basename(filePath)}`);
.opencode/skills/system-spec-kit/mcp_server/tests/n3lite-consolidation.vitest.ts:9:  buildContradictionClusters,
.opencode/skills/system-spec-kit/mcp_server/tests/n3lite-consolidation.vitest.ts:174:  it('T-N3-08: buildContradictionClusters includes seed pair members', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/n3lite-consolidation.vitest.ts:186:    const clusters = buildContradictionClusters(db, [pair]);
.opencode/skills/system-spec-kit/mcp_server/tests/n3lite-consolidation.vitest.ts:208:    const clusters = buildContradictionClusters(db, [pair]);
.opencode/skills/system-spec-kit/mcp_server/tests/n3lite-consolidation.vitest.ts:216:    const clusters = buildContradictionClusters(db, []);
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:57:      quality_score REAL DEFAULT 0,
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:58:      quality_flags TEXT
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:122:    qualityScore: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:123:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:456:          spec_folder, file_path, canonical_file_path, title, content_hash, embedding_status, trigger_phrases, quality_score, quality_flags, parent_id
.opencode/skills/system-spec-kit/mcp_server/tests/content-hash-dedup.vitest.ts:486:          spec_folder, file_path, canonical_file_path, title, content_hash, embedding_status, trigger_phrases, quality_score, quality_flags, parent_id
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:514:            gap = float(dr.get("confidence", 0.0)) - float(cr.get("confidence", 0.0))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:515:            if gap + 1e-9 < 0.10:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:516:                margin_failures.append(f"{prompt!r} gap={gap:.2f}")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:544:            gap = float(drv.get("confidence", 0.0)) - float(cr.get("confidence", 0.0))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:545:            if gap + 1e-9 < 0.10:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:546:                review_failures.append(f"{prompt!r} gap={gap:.2f}")
.opencode/skills/system-spec-kit/mcp_server/handlers/save/types.ts:195:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/types.ts:196:  qualityFlags?: string[];
.opencode/skills/system-spec-kit/mcp_server/handlers/save/types.ts:205:  qualityGate?: {
.opencode/skills/system-spec-kit/mcp_server/handlers/save/types.ts:321:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/types.ts:322:  quality_flags?: string; // pre-stringified JSON
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:10:import { isCocoIndexAvailable } from '../../lib/utils/cocoindex-path.js';
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:139:    `- CocoIndex: ${args.cocoIndexAvailable ? 'available' : 'missing'}`,
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:234:    const qualityLine = formatGraphQualitySummary(graphQualitySummary);
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:235:    if (qualityLine) {
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:236:      lines.push(`Graph quality: ${qualityLine}`);
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:239:      lines.push('Orientation: use code graph highlights for structural entry points and call paths; use CocoIndex for semantic discovery when the symbol or file is still unknown.');
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:302:  const cocoIndexAvailable = isCocoIndexAvailable();
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:25:} from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:26:import type { QualityGateResult } from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:240:  it('S4-INT-05: Quality gate rejects low-quality saves when flag is ON', withEnvVars(
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:246:      // Content with no title, no triggers, very short — should fail structural + quality
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:266:trigger_phrases: [integration test, quality gate, validation]
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:272:This memory contains substantial content about the implementation of the quality gate feature.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:277:The quality gate uses a 3-layer approach for maximum coverage while maintaining low false-positive rates.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:281:Signal density is computed as a weighted average of title quality, trigger quality, length quality,
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:282:anchor quality, and metadata quality dimensions. The threshold is set at ${SIGNAL_DENSITY_THRESHOLD}.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:289:        triggerPhrases: ['integration test', 'quality gate', 'validation'],
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:304:      // Even low-quality content passes when gate is off
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:484:  it('S4-INT-11: Save with similarity in [0.88, 0.92] passes quality gate then triggers reconsolidation merge', withEnvVars(
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:490:trigger_phrases: [implementation, quality gate, reconsolidation]
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:496:This document describes the implementation of the Sprint 4 quality gate
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:501:The quality gate runs BEFORE reconsolidation in the save pipeline.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:502:This ensures only quality content gets merged or stored.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:510:        triggerPhrases: ['implementation', 'quality gate', 'reconsolidation'],
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:527:  it('S4-INT-12: Both quality gate and reconsolidation disabled means no Sprint 4 save behavior', withEnvVars(
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:683:    // Enable only quality gate — explicitly disable others
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:817:    // This is a critical invariant: the quality gate's semantic dedup threshold
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:819:    // Otherwise, quality gate would reject saves that reconsolidation could merge.
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:831:    // In this range, reconsolidation merges but quality gate does NOT reject as duplicate
.opencode/skills/system-spec-kit/mcp_server/tests/mpab-quality-gate-integration.vitest.ts:845:    // At this similarity, quality gate WOULD reject as near-duplicate
.opencode/skills/system-spec-kit/mcp_server/handlers/save/README.md:27:`handlers/save/` contains the decomposed pipeline for the `memory_save` MCP tool. Each file owns a single stage of the save flow, from deduplication through embedding generation, save quality gating, prediction-error gating, reconsolidation, record creation, post-insert enrichment, and final response assembly.
.opencode/skills/system-spec-kit/mcp_server/handlers/save/README.md:57:3. save-quality-gate -- Evaluate semantic/structural quality before persistence
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:337:          quality_score: 0.91,
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:345:    mockSearch.mockResolvedValue([{ id: 1, score: 0.93, title: 'baseline-hit', quality_score: 0.93 }]);
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:371:      quality_score: 0.99,
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:380:    mockSearch.mockResolvedValue([{ id: 1, score: 0.95, title: 'baseline-version', quality_score: 0.95 }]);
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:403:          title: 'high-quality-summary',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:404:          spec_folder: 'specs/quality/high',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:405:          file_path: 'specs/quality/high/implementation-summary.md',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:408:          quality_score: 0.95,
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:414:          title: 'low-quality-summary',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:415:          spec_folder: 'specs/quality/low',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:416:          file_path: 'specs/quality/low/implementation-summary.md',
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:419:          quality_score: 0.3,
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:430:      config: makeConfig({ qualityThreshold: 0.8 }),
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:436:    expect(result.candidates[0]?.title).toBe('high-quality-summary');
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:456:          quality_score: 0.92,
.opencode/skills/system-spec-kit/mcp_server/tests/stage1-expansion.vitest.ts:469:          quality_score: 0.9,
.opencode/skills/system-spec-kit/mcp_server/tests/session-manager.vitest.ts:10:// REQ-001: Session Deduplication - Hash-based duplicate prevention
.opencode/skills/system-spec-kit/mcp_server/tests/session-manager.vitest.ts:101:        // TODO(P6-05): Intentional test cast — exercises non-function property check
.opencode/skills/system-spec-kit/mcp_server/tests/session-manager.vitest.ts:161:      // TODO(P6-05): Intentional test cast — validates null input handling
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/compact-merger.ts:4:// Merges context from multiple sources (Memory, Code Graph, CocoIndex, Session)
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/compact-merger.ts:18:  cocoIndex: string;         // Semantic neighbors (from CocoIndex)
.opencode/skills/system-spec-kit/mcp_server/handlers/save/reconsolidation-bridge.ts:233:// `!== null`, `candidateMatchesRequestedScope` strict-equality) is unaffected.
.opencode/skills/system-spec-kit/mcp_server/handlers/save/reconsolidation-bridge.ts:588:                  qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/reconsolidation-bridge.ts:589:                  qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/reconsolidation-bridge.ts:604:                  quality_score: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/reconsolidation-bridge.ts:605:                  quality_flags: JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/tests/content-normalizer.vitest.ts:366:    const input = '<!-- TODO: remove -->\nKeep this.';
.opencode/skills/system-spec-kit/mcp_server/tests/content-normalizer.vitest.ts:367:    expect(normalizeContentForEmbedding(input)).not.toContain('TODO');
.opencode/skills/system-spec-kit/mcp_server/tests/content-normalizer.vitest.ts:430:      '<!-- TODO: update once OAuth is live -->',
.opencode/skills/system-spec-kit/mcp_server/tests/content-normalizer.vitest.ts:466:    expect(result).not.toContain('TODO');
.opencode/skills/system-spec-kit/mcp_server/tests/query-classifier.vitest.ts:67:  'review code quality in handlers',
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-benchmark-memory-search.vitest.ts:61:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:5:// population, request-level quality assessment, and feature flag gating.
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:312:    // May have drivers from margin if gap is still >= 0.15 as proportion — but here it's not
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:337:  it('returns "gap" when results array is empty', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:339:    expect(requestQuality.label).toBe('gap');
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:353:  it('returns "gap" when all results have low confidence', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:357:    expect(requestQuality.label).toBe('gap');
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:364:    // Scores around 0.4–0.45 → should be "weak" (not gap, not good)
.opencode/skills/system-spec-kit/mcp_server/tests/d5-confidence-scoring.vitest.ts:369:    const validLabels = ['good', 'weak', 'gap'];
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:41:  quality_score: number | null;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:42:  quality_flags: string | null;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:102:    SELECT id, content_hash, embedding_status, trigger_phrases, quality_score, quality_flags
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:148:    quality_score: number | null;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:149:    quality_flags: string | null;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:158:  const persistedQualityFlags = parseJsonStringArray(existing.quality_flags);
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:159:  if (!areEquivalentStringArrays(persistedQualityFlags, parsed.qualityFlags ?? [])) {
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:163:  const persistedQualityScore = existing.quality_score ?? 0;
.opencode/skills/system-spec-kit/mcp_server/handlers/save/dedup.ts:164:  const parsedQualityScore = parsed.qualityScore ?? 0;
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:3:// T001-T095: Error catalog with recovery hints (REQ-004, REQ-009)
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:434:  it('T058: DEFAULT_HINT actions include memory_health() reference (REQ-009)', () => {
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:4:// Resolves CocoIndex search results (file:line) to code graph nodes.
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:10:/** A seed from CocoIndex or other providers */
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:19:/** Native CocoIndex search result as a seed */
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:20:export interface CocoIndexSeed {
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:47:export type AnySeed = CodeGraphSeed | CocoIndexSeed | ManualSeed | GraphSeed;
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:75:function isCocoIndexSeed(seed: unknown): seed is CocoIndexSeed {
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:95:/** Resolve a CocoIndex seed by converting to CodeGraphSeed and delegating */
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:96:export function resolveCocoIndexSeed(seed: CocoIndexSeed): ArtifactRef {
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/seed-resolver.ts:334:  if (isCocoIndexSeed(seed)) return resolveCocoIndexSeed(seed);
.opencode/skills/system-spec-kit/mcp_server/tests/file-watcher.vitest.ts:410:    // Write 5 times rapidly (20ms gaps) with unique content each time
.opencode/skills/system-spec-kit/mcp_server/tests/adaptive-ranking.vitest.ts:479:  it('summarizes adaptive signal quality and threshold bounds', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/adaptive-ranking.vitest.ts:491:    buildAdaptiveShadowProposal(db, 'quality summary query', [
.opencode/skills/system-spec-kit/mcp_server/tests/community-search.vitest.ts:89:      { id: 2, summary: 'graph retrieval search quality', memberIds: [3, 4, 5], count: 3 },
.opencode/skills/system-spec-kit/mcp_server/tests/community-search.vitest.ts:93:    const result = searchCommunities('search quality', db);
.opencode/skills/system-spec-kit/mcp_server/handlers/save/post-insert.ts:406:      qualityScore: typeof parsed.qualityScore === 'number' ? parsed.qualityScore : 0,
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:98:│   ├── ccc-status.ts               # CocoIndex status bridge
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:99:│   ├── ccc-reindex.ts              # CocoIndex reindex bridge
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:100:│   ├── ccc-feedback.ts             # CocoIndex feedback bridge
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:137:The subsystem exposes four operator-visible contract families: `code_graph_status`, `code_graph_context`, `code_graph_query`, and startup/compaction payloads. They share the readiness vocabulary (`readiness`, `canonicalReadiness`, `trustState`) and surface graph-quality and structured transport metadata. Both `code_graph_context` and `code_graph_query` enforce the same explicit blocked/degraded contract when readiness requires a suppressed `full_scan`, and `code_graph_query` additionally carries CALLS ambiguity resolution metadata.
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:143:| **`code_graph_status`** | `status: "ok"` | `freshness`, `readiness`, `canonicalReadiness`, `trustState`, `parseHealth`, `graphQualitySummary` | Primary operator health probe; keeps counts plus parser/enrichment quality in one response |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:159:| `anchors[*]` | `source`, `provider`, `score`, `snippet`, `range` | Preserves seed provenance so CocoIndex/manual/graph-sourced anchors stay traceable |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:175:| `graphQualitySummary` | `detectorProvenanceSummary`, `graphEdgeEnrichmentSummary` | Mirrors the quality summary emitted by `code_graph_status` |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:178:| `provenance` | `producer`, `sourceSurface`, `trustState`, `generatedAt`, `lastUpdated`, `sourceRefs` | Preserves startup-quality/source metadata across runtime boundaries |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:184:| Status quality summary | `handlers/status.ts` | `code_graph_status` includes `parseHealth` and `graphQualitySummary` in the public payload |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:187:| Startup quality + transport | `lib/startup-brief.ts` | `buildStartupBrief()` returns `graphQualitySummary`, `sharedPayload`, and `sharedPayloadTransport` |
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:223:          'Continue from the last stable checkpoint after validating the atomic save path and its quality-gate ordering.',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:462:      qualityLoopResult?: Record<string, unknown>;
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:492:      vi.doMock('../lib/validation/save-quality-gate', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:493:        const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:500:      vi.doMock('../lib/validation/save-quality-gate.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:501:        const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:587:      const qualityLoopModule = await import('../handlers/quality-loop');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:588:      const runQualityLoopSpy = vi.spyOn(qualityLoopModule, 'runQualityLoop').mockReturnValue({
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:593:        ...options.qualityLoopResult,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:594:      } as Awaited<ReturnType<typeof qualityLoopModule.runQualityLoop>>);
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:794:      vi.doMock('../handlers/quality-loop', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:795:        const actual = await importOriginal<typeof import('../handlers/quality-loop')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:875:      vi.doMock('../lib/validation/save-quality-gate', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:876:        const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:883:      vi.doMock('../lib/validation/save-quality-gate.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:884:        const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1043:      vi.doUnmock('../handlers/quality-loop');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1058:      vi.doUnmock('../lib/validation/save-quality-gate');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1059:      vi.doUnmock('../lib/validation/save-quality-gate.js');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1081:      const filePath = createAtomicSaveTargetPath('behavioral-quality-loop.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1087:      const qualityLoopCall = harness.runQualityLoopSpy.mock.calls[0];
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1088:      expect(qualityLoopCall[0]).toBe(buildParsedMemory(filePath).content);
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1089:      expect(qualityLoopCall[1]).toEqual(expect.objectContaining({
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:1095:      expect(qualityLoopCall[2]).toEqual({ emitEvalMetrics: undefined, mode: 'advisory' });
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2193:    it('does not persist embedding cache writes before hard quality-gate rejection', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2222:      const filePath = createAtomicSaveTargetPath('quality-gate-rejected.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2230:    it('persists deferred embedding cache write after quality gate passes', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2259:      const filePath = createAtomicSaveTargetPath('quality-gate-passed.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2266:    it('runs quality gate before chunked indexing and rejects failing large files', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2305:      const filePath = createAtomicSaveTargetPath('chunked-quality-gate-reject.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2435:    it.skip('persists quality-loop trigger phrase fixes into downstream save inputs', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2494:        fixedContent: buildParsedMemory('quality-loop-trigger-fix.md').content,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2498:      const filePath = createAtomicSaveTargetPath('quality-loop-trigger-fix.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2506:      expect((createMemoryRecordMock.mock.calls[0] as any)?.[1].content).toBe(buildParsedMemory('quality-loop-trigger-fix.md').content);
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2507:      expect(fs.readFileSync(filePath, 'utf8')).toBe(buildParsedMemory('quality-loop-trigger-fix.md').content);
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2537:      const filePath = createAtomicSaveTargetPath('quality-loop-same-path-exclusion.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:2637:      const filePath = createAtomicSaveTargetPath('quality-gate-scope.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3131:    it('passes emitEvalMetrics=false into quality loop during dry-run with skipPreflight', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3149:    it('passes emitEvalMetrics=false into quality loop during dry-run preflight', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3264:    it.skip('persists quality-loop fixed content after successful chunked indexing', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3303:        fixedContent: buildParsedMemory('chunked-quality-fix.md').content,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3306:      const filePath = createAtomicSaveTargetPath('chunked-quality-fix.md');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3311:      expect(fs.readFileSync(filePath, 'utf8')).toBe(buildParsedMemory('chunked-quality-fix.md').content);
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3314:    it('does not persist quality-loop fixed content when chunked indexing fails', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3353:        fixedContent: buildParsedMemory('chunked-quality-fix-error.md').content,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-save.vitest.ts:3356:      const filePath = createAtomicSaveTargetPath('chunked-quality-fix-error.md');
.opencode/skills/system-spec-kit/mcp_server/tests/chunk-thinning.vitest.ts:192:  it('should retain high-quality chunks and drop low-quality ones', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/chunk-thinning.vitest.ts:235:    // All chunks are low quality
.opencode/skills/system-spec-kit/mcp_server/tests/chunk-thinning.vitest.ts:286:        content: '## Medium quality\n\nSome content that is long enough to have moderate density but no anchors attached to it.',
.opencode/skills/system-spec-kit/mcp_server/tests/chunk-thinning.vitest.ts:393:      qualityScore: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/chunk-thinning.vitest.ts:394:      qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-constitutional-memory.vitest.ts:190:          qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-types.vitest.ts:168:        { title: 'TODO: Fix bug in nav', expected: 'prospective' },
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:346:      qualityScore: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:364:    qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:365:    qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:532:        qualityScore: result.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:533:        qualityFlags: result.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:537:        ...(result.qualityGate ? { qualityGate: result.qualityGate } : {}),
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:548:        : ['Rejected saves do not mutate the memory index', 'Review quality issues and retry the save'],
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:578:    qualityScore: result.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/response-builder.ts:579:    qualityFlags: result.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/tests/codex-session-start-hook.vitest.ts:28:        '- CocoIndex: available',
.opencode/skills/system-spec-kit/mcp_server/tests/codex-session-start-hook.vitest.ts:65:          '- CocoIndex: available',
.opencode/skills/system-spec-kit/mcp_server/tests/channel-representation.vitest.ts:113:  // ---- T3: Channel missing but its best result is below quality floor — no promotion ----
.opencode/skills/system-spec-kit/mcp_server/tests/channel-representation.vitest.ts:114:  it('T3: channel missing and best result below quality floor — no promotion', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/channel-representation.vitest.ts:248:  it('T10: quality floor is exact — score 0.005 qualifies, 0.004 does not', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/channel-representation.vitest.ts:391:  // ---- T18: Mixed quality floor — some channels qualify, some don't ----
.opencode/skills/system-spec-kit/mcp_server/tests/channel-representation.vitest.ts:407:    // Graph is under-represented but could not promote due to quality floor
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:14:import type { QualityLoopResult } from '../../handlers/quality-loop.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:25:// Feature catalog: Verify-fix-verify memory quality loop
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:33:    parsed.qualityScore = Math.min(parsed.qualityScore ?? 1, sufficiencyResult.score * 0.6);
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:34:    parsed.qualityFlags = Array.from(new Set([...(parsed.qualityFlags || []), 'has_insufficient_context']));
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:51:    qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:52:    qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:75:    qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:76:    qualityFlags: Array.from(new Set([...(parsed.qualityFlags || []), 'violates_template_contract'])),
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:85:  qualityLoopResult: QualityLoopResult,
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:88:  if (!qualityLoopResult.passed && qualityLoopResult.rejected) {
.opencode/skills/system-spec-kit/mcp_server/handlers/save/validation-responses.ts:89:    return qualityLoopResult.rejectionReason ?? 'Quality loop rejected the save';
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:51:      quality_score REAL DEFAULT 0
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:722:    const result = onIndex(db, 5, content, { qualityScore: 0.9 });
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:726:  it('schedules LLM backfill for high-quality docs when flag is on', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:734:    const result = onIndex(db, 6, content, { qualityScore: 0.9 });
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:738:  it('does not schedule LLM backfill for low-quality docs', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/graph-lifecycle.vitest.ts:746:    const result = onIndex(db, 7, content, { qualityScore: 0.3, llmBackfillThreshold: 0.7 });
.opencode/skills/system-spec-kit/mcp_server/tests/structural-contract.vitest.ts:46:    isCocoIndexAvailable: vi.fn(() => false),
.opencode/skills/system-spec-kit/mcp_server/tests/channel-enforcement.vitest.ts:18:// T9:  quality floor prevents low-quality promotions
.opencode/skills/system-spec-kit/mcp_server/tests/channel-enforcement.vitest.ts:299:  // ---- T9: Quality floor prevents low-quality promotions ----
.opencode/skills/system-spec-kit/mcp_server/tests/channel-enforcement.vitest.ts:300:  it('T9: quality floor blocks promotions below 0.005, preventing low-quality pollution', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/channel-enforcement.vitest.ts:312:    // No promotions — both channels below quality floor.
.opencode/skills/system-spec-kit/mcp_server/tests/deferred-features-integration.vitest.ts:52:      quality_score REAL DEFAULT 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/ablation-framework.vitest.ts:49: * When all channels active (baseline): returns memoryIds 1..count (high quality).
.opencode/skills/system-spec-kit/mcp_server/tests/ablation-framework.vitest.ts:50: * When a channel is disabled: drops some results to simulate quality degradation.
.opencode/skills/system-spec-kit/mcp_server/tests/concept-extraction.vitest.ts:16:    it('extracts meaningful words from "Semantic Search"', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/concept-extraction.vitest.ts:17:      expect(nounPhrases('Semantic Search')).toEqual(['semantic', 'search']);
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:31:  quality_score: number;
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:32:  quality_flags: string | null;
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:537:        'ALTER TABLE memory_index ADD COLUMN quality_score REAL DEFAULT 0',
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:538:        'ALTER TABLE memory_index ADD COLUMN quality_flags TEXT',
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:556:            quality_score = ?,
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:557:            quality_flags = ?,
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:581:            quality_score = 0,
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:582:            quality_flags = NULL,
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:593:        SELECT canonical_file_path, content_hash, content_text, quality_score, quality_flags, chunk_index, chunk_label
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:603:      expect(restored.quality_score).toBe(0.91);
.opencode/skills/system-spec-kit/mcp_server/tests/checkpoints-extended.vitest.ts:604:      expect(restored.quality_flags).toBe('["flag_a","flag_b"]');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-session-learning.vitest.ts:158:          knowledge_gaps TEXT,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-session-learning.vitest.ts:166:          gaps_closed TEXT,
.opencode/skills/system-spec-kit/mcp_server/tests/handler-session-learning.vitest.ts:167:          new_gaps_discovered TEXT,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:5:// code graph status, and CocoIndex availability into a single call.
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:13:import { isCocoIndexAvailable } from '../lib/utils/cocoindex-path.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:107:interface CocoIndexStatus {
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:115:  cocoIndex: CocoIndexStatus;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:128:  cocoIndex: CocoIndexStatus;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:141:  cocoIndex: CocoIndexStatus;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:182:        title: 'CocoIndex Status',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:609:  // ── Sub-call 3: CocoIndex availability (F046/F051: shared helper) ──
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:610:  const cocoIndex: CocoIndexStatus = {
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:611:    available: isCocoIndexAvailable(),
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:615:    hints.push('CocoIndex not installed. Install: `bash .opencode/skills/mcp-coco-index/scripts/install.sh`');
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:707:      title: 'CocoIndex Status',
.opencode/skills/system-spec-kit/mcp_server/tests/modularization.vitest.ts:19:// TODO: Extract quality gate, reconsolidation, chunked-indexing from memory-save (2,553 LOC source).
.opencode/skills/system-spec-kit/mcp_server/tests/modularization.vitest.ts:28:  'handlers/memory-save.js': 2560,  // actual: 2524 — Save logic with parsing, validation, indexing + quality gate + reconsolidation + Phase 019 Wave A save_lineage option forwarding
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:181:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:302:      'memory_drift_why', 'memory_causal_link', 'memory_causal_stats', 'memory_causal_unlink',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:2097:    // T24: Error response contains recovery hints (REQ-004)
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:2628:      'memory_causal_stats': '[L6:Analysis]',
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-embedding-semantic-search.vitest.ts:65:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-intent-routing.vitest.ts:266:  // is required to close this coverage gap.  See review finding S3.5 #13.
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-intent-routing.vitest.ts:459:  // TODO(S3.5 #13): Add integration tests that exercise the live canonical-
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:149:    tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:306:export const handle_memory_causal_stats = lazyFunction(getCausalGraphModule, 'handle_memory_causal_stats');
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-v2.vitest.ts:74:      row.evidenceGap = { gapDetected: false };
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-v2.vitest.ts:332:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-quality-gates.vitest.ts:89:describe('Gate D regression quality gates', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-quality-gates.vitest.ts:91:    const folder = makeTempDir('gate-d-regression-quality-gates-');
.opencode/skills/system-spec-kit/mcp_server/tests/smart-router-telemetry.vitest.ts:151:        allowedResources: ['conditional:references/code_quality_checklist.md'],
.opencode/skills/system-spec-kit/mcp_server/tests/smart-router-telemetry.vitest.ts:152:        actualReads: ['references/code_quality_checklist.md'],
.opencode/skills/system-spec-kit/mcp_server/tests/layer-definitions.vitest.ts:138:        memory_causal_stats: 'L6',
.opencode/skills/system-spec-kit/mcp_server/tests/graph-aware-stop.vitest.ts:77:        { id: 's-1', kind: 'SOURCE', name: 'Primary source', metadata: { quality_class: 'primary' } },
.opencode/skills/system-spec-kit/mcp_server/tests/graph-aware-stop.vitest.ts:78:        { id: 's-2', kind: 'SOURCE', name: 'Secondary source', metadata: { quality_class: 'secondary' } },
.opencode/skills/system-spec-kit/mcp_server/tests/quality-gate-exception.vitest.ts:15:} from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/quality-gate-exception.vitest.ts:21:describe('Save quality gate short-decision exception', () => {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:464:  // REQ-002 (Cluster 1) Sanity guard: when reported usage is far below budget but
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:500:    // REQ-002 (Cluster 1): When structural truncation already produced a non-empty
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:691:  // REQ-002 (Cluster 1): Track survivors so the fallback path can preserve them
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:753:        // REQ-002 (Cluster 1): Snapshot survivors before any further compaction
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:802:  // REQ-002 (Cluster 1): Hand the fallback the survivors from structural
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1273:    // REQ-004 (Cluster 2): `meta.intent` is the AUTHORITATIVE intent for output
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1286:    folderDiscovery: discoveredFolder ? {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1679:    // REQ-004 (Cluster 2): Annotate explicitly so callers do not confuse this
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:14:  qualityFlags: string[];
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:15:  qualityScore: number;
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:43:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:44:    qualityScore: 0.95,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:171:  vi.doMock('../handlers/quality-loop.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:172:    const actual = await importOriginal<typeof import('../handlers/quality-loop.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:185:  vi.doMock('../lib/validation/save-quality-gate.js', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:186:    const actual = await importOriginal<typeof import('../lib/validation/save-quality-gate.js')>();
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:326:        qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:327:        qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-eval-channels.vitest.ts:41:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/budget-allocator.vitest.ts:34:      // CocoIndex and triggered are empty, their floors + overflow go to others
.opencode/skills/system-spec-kit/mcp_server/tests/orchestrator-error-cascade.vitest.ts:111:    qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:6:import { detectEvidenceGap } from '../lib/search/evidence-gap-detector';
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:82:  // Delegates to production detectEvidenceGap from evidence-gap-detector.ts
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:85:    evidenceGapDetected: trm.gapDetected,
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:89:    warnings: trm.gapDetected ? ['[EVIDENCE GAP DETECTED]'] : [],
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:222:  // ---- T5: Evidence gap warning appears when gap detected ----
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:223:  it('T5: evidence gap warning in payload iff trm.evidenceGapDetected is true', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:227:    // Of whether a gap was detected — an unconditional check avoids vacuous truths.
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:386:    expect(flat.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:393:    expect(clear.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:399:    expect(empty.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:405:    // Single score above MIN_ABSOLUTE_SCORE → no gap
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:406:    expect(single.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:412:    // StdDev=0, all scores (0.3) above MIN_ABSOLUTE_SCORE → no gap
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:413:    expect(identical.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-138-pipeline.vitest.ts:473:    const { predictGraphCoverage } = await import('../lib/search/evidence-gap-detector');
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:82:        { id: 's-1', kind: 'SOURCE', name: 'Primary source', metadata: { quality_class: 'primary' } },
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:83:        { id: 's-2', kind: 'SOURCE', name: 'Secondary source', metadata: { quality_class: 'secondary' } },
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:111:    const gaps = (queryData.gaps as Array<Record<string, unknown>>) ?? [];
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:115:    expect(gaps[0]).toMatchObject({
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:140:  it('queries review coverage gaps through the live MCP handlers instead of archived stubs', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:165:      queryType: 'coverage_gaps',
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:174:    const gaps = (queryData.gaps as Array<Record<string, unknown>>) ?? [];
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:177:    expect(queryData.queryType).toBe('coverage_gaps');
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:179:    expect(gaps).toEqual(
.opencode/skills/system-spec-kit/mcp_server/tests/deep-loop-graph-query.vitest.ts:217:    expect(uncoveredQuestionsResponse.error).toContain('coverage_gaps for review graphs');
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:70:  qualityScore: QualityScore;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:189:  // Phase 023: Compute quality score from context metrics
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:190:  const qualityScore = computeQualityScore();
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:193:  const qualityScoreContent = `level=${qualityScore.level}; score=${qualityScore.score}`;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:205:        key: 'quality-score',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:207:        content: qualityScoreContent,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:248:      key: 'quality-score',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:250:      content: qualityScoreContent,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:287:    qualityScore,
.opencode/skills/system-spec-kit/mcp_server/tests/cross-encoder.vitest.ts:90:  // SUITE: Length Penalty Tests (REQ-008, T049)
.opencode/skills/system-spec-kit/mcp_server/tests/cross-encoder.vitest.ts:91:  describe('Length Penalty Tests (REQ-008, T049)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-integration.vitest.ts:153:  it('evidence-gap-detector exports: detectEvidenceGap, predictGraphCoverage', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-integration.vitest.ts:154:    const mod = await import('../lib/search/evidence-gap-detector');
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-architecture-remediation.vitest.ts:42:      quality_score: 0.98,
.opencode/skills/system-spec-kit/mcp_server/tests/pipeline-architecture-remediation.vitest.ts:50:      quality_score: 0.1,
.opencode/skills/system-spec-kit/mcp_server/tests/p0-c-graph-metadata-laundering.vitest.ts:84:    expect(parsedMigrated.qualityFlags).toContain(GRAPH_METADATA_MIGRATED_QUALITY_FLAG);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-c-graph-metadata-laundering.vitest.ts:92:          quality_flags: JSON.stringify(parsedMigrated.qualityFlags),
.opencode/skills/system-spec-kit/mcp_server/tests/create-record-identity.vitest.ts:64:    qualityScore: 0.9,
.opencode/skills/system-spec-kit/mcp_server/tests/create-record-identity.vitest.ts:65:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/query-router-channel-interaction.vitest.ts:294:      // Fts results are all below quality floor (0.005)
.opencode/skills/system-spec-kit/mcp_server/tests/description/fixtures/017-review-findings-remediation.description.json:6:  "description": "Remediation charter for 27 consolidated tasks closing the Phase 017 review backlog across four waves. The headline fix is H-56-1: the canonical `/memory:save` path had been a deterministic metadata-freshness no-op because of a dead-code guard, a full-auto-only graph refresh gate, and the default plan-only execution mode; the packet also closes the code-graph readiness asymmetry, the Copilot compact-cache observability gap, the session-resume auth binding work, and the deferred maintainability follow-ups that Phase 018 depends on for traceable recovery and rollout hygiene.",
.opencode/skills/system-spec-kit/mcp_server/tests/README.md:36:- Save/index regressions including content-hash dedup, quality-loop behavior, and incremental-index edge cases.
.opencode/skills/system-spec-kit/mcp_server/tests/README.md:106:- `quality-loop.vitest.ts` - verify-fix-verify scoring and rejection behavior.
.opencode/skills/system-spec-kit/mcp_server/tests/README.md:152:npx vitest run tests/content-hash-dedup.vitest.ts tests/quality-loop.vitest.ts tests/batch-processor.vitest.ts
.opencode/skills/system-spec-kit/mcp_server/tests/description/fixtures/017-002-cluster-consumers.description.json:3:  "description": "Phase 017 Wave B child packet: 9 tasks / 30h across 3 parallel lanes consuming Wave A primitives. Lane B1 (Cluster B consumers, 12h, 4 tasks): T-CNS-02 research folder backfill, T-W1-CNS-05 continuity freshness validator, T-CGC-02 context.ts explicit error branch, T-RBD-03 design-intent comments. Lane B2 (Cluster D + Cluster E, 16h, 2 tasks): T-W1-CGC-03 5-sibling code-graph readiness propagation (atomic-ship or stub rollout), T-W1-HOK-01 Copilot compact-cache + session-prime (depends Wave A T-W1-HOK-02). Lane B3 (Cluster A + C + Standalone P1, 12h, 3 tasks): T-SCP-02 normalizer lint rule, T-SAN-01 + T-SAN-02 + T-SAN-03 NFKC unicode normalization + tests, T-PIN-RET-01 retry-exhaustion counter. Resolves FC-3 (research iteration folders metadata), FC-4 (6 code-graph handlers readiness vocabulary), FC-5 (Copilot compact-cache wiring), FC-6 (NFKC Gate 3 hardening), FC-8 (partial_causal_link_unresolved retry-exhaustion). Wave B gate: /spec_kit:deep-review :auto ×7 + validate.sh --strict on 017 folder.",
.opencode/skills/system-spec-kit/mcp_server/tests/description/fixtures/017-002-cluster-consumers.description.json:24:    "copilot-observability-gap-resolution",
.opencode/skills/system-spec-kit/mcp_server/tests/description/fixtures/017-002-cluster-consumers.description.json:26:    "r51-p1-003-continuity-freshness-gap",
.opencode/skills/system-spec-kit/mcp_server/tests/description/fixtures/017-002-cluster-consumers.description.json:67:  "qualityGate": {
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:23:  quality?: { resultCount?: number; password?: unknown };
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:65:  'mode' | 'fallback' | 'quality' | 'tracePayload'
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:69:  quality: ReturnType<typeof createTelemetry>['quality'] & Record<string, unknown>;
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:120:    expect(t.quality.resultCount).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:121:    expect(t.quality.avgRelevanceScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:122:    expect(t.quality.topResultScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:123:    expect(t.quality.boostImpactDelta).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:124:    expect(t.quality.extractionCountInSession).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:125:    expect(t.quality.qualityProxyScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:234:  it('T06b: quality proxy increases with good results', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:238:    // Add high-quality results
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:246:    expect(t.quality.qualityProxyScore).toBeGreaterThan(baseScore);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:247:    expect(t.quality.qualityProxyScore).toBeGreaterThanOrEqual(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:248:    expect(t.quality.qualityProxyScore).toBeLessThanOrEqual(1);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:251:  it('T06c: quality proxy with max latency reduces score', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:262:    expect(t.quality.qualityProxyScore).toBeLessThan(0.85);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:265:  // T07: recordQualityProxy populates quality fields
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:266:  it('T07: recordQualityProxy sets all quality metrics', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:275:    expect(t.quality.resultCount).toBe(3);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:276:    expect(t.quality.topResultScore).toBe(0.9);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:277:    expect(t.quality.avgRelevanceScore).toBeCloseTo((0.9 + 0.7 + 0.6) / 3, 4);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:278:    expect(t.quality.boostImpactDelta).toBe(0.05);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:279:    expect(t.quality.extractionCountInSession).toBe(3);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:280:    expect(t.quality.qualityProxyScore).toBeGreaterThan(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:281:    expect(t.quality.qualityProxyScore).toBeLessThanOrEqual(1);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:288:    expect(t.quality.resultCount).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:289:    expect(t.quality.avgRelevanceScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:290:    expect(t.quality.topResultScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:310:    expect((json as TelemetryJson).quality?.resultCount).toBe(1);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:341:    expect(t.quality.topResultScore).toBe(0.8);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:342:    expect(t.quality.avgRelevanceScore).toBeCloseTo(0.7, 4);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:349:    expect(t.quality.topResultScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:350:    expect(t.quality.avgRelevanceScore).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:351:    expect(t.quality.resultCount).toBe(2);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:357:    expect(t.quality.boostImpactDelta).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:360:    expect(t.quality.boostImpactDelta).toBe(0);
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:429:    t.quality.password = 'should-not-leak';
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:450:    const quality = expectPresent(json.quality, 'Expected quality payload');
.opencode/skills/system-spec-kit/mcp_server/tests/retrieval-telemetry.vitest.ts:456:    expect(quality.password).toBeUndefined();
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-links-processor.ts:197:  // 2) Batch exact path matches via canonical_file_path/file_path equality
.opencode/skills/system-spec-kit/mcp_server/tests/hook-session-start.vitest.ts:259:            '- CocoIndex: available',
.opencode/skills/system-spec-kit/mcp_server/tests/hook-session-start.vitest.ts:311:      // TODO: subprocess test needs hook-state seeded with lastSpecFolder OR a code_graph_scan
.opencode/skills/system-spec-kit/mcp_server/tests/hook-session-start.vitest.ts:342:      // TODO: same as gemini — needs seeded continuity/graph state for sharedPayloadTransport
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:20:    gaps: Array<{ nodeId: string; kind: string; name: string; reason: string }>;
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:25:describe('coverage graph review gap regression', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:54:      id: 'dim-gap',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:66:      id: 'file-gap',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:103:      targetId: 'file-gap',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:110:      queryType: 'coverage_gaps',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:114:    expect(result.queryType).toBe('coverage_gaps');
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:116:    expect(result.gaps).toEqual([
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:118:        nodeId: 'dim-gap',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:124:        nodeId: 'file-gap',
.opencode/skills/system-spec-kit/mcp_server/tests/coverage-graph-signals.vitest.ts:130:    expect(result.gaps.every((gap) => gap.kind === 'DIMENSION' || gap.kind === 'FILE')).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/memory-parser-extended.vitest.ts:50:    qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-parser-extended.vitest.ts:51:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/result-confidence-scoring.vitest.ts:23:  label: 'good' | 'weak' | 'gap';
.opencode/skills/system-spec-kit/mcp_server/tests/result-confidence-scoring.vitest.ts:352:  it('assesses request quality as good, weak, or gap at the query level', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/result-confidence-scoring.vitest.ts:393:    const gapEnvelope = await formatEnvelope([], {
.opencode/skills/system-spec-kit/mcp_server/tests/result-confidence-scoring.vitest.ts:402:    expect(gapEnvelope.data.requestQuality?.label).toBe('gap');
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:32:/** Approximate equality for floating-point comparisons */
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:119:     T020-03: Large folder damping — quality over quantity
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:122:    it('T020-03: folder with 100 low-score results does NOT dominate small high-quality folder', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:125:      // Folder "quality" has 3 results each with score 0.95 → sum = 2.85
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:136:        [201, 'quality'],
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:137:        [202, 'quality'],
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:138:        [203, 'quality'],
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:143:      // Small high-quality folder should beat large low-quality folder
.opencode/skills/system-spec-kit/mcp_server/tests/folder-relevance.vitest.ts:144:      expect(scores.get('quality')!).toBeGreaterThan(scores.get('massive')!);
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:57:- `quality-loop.ts` - Verify-fix-verify scoring and auto-fix loop used by `memory-save.ts`.
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:58:- `v-rule-bridge.ts` - Runtime bridge to validation scripts for memory quality checks.
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:67:- `quality-loop.ts` supports `emitEvalMetrics` so callers can suppress eval-side writes while still using the quality loop itself.
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:122:  qualityScore: number;
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:123:  qualityFlags: string[];
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:154:      quality_score REAL DEFAULT 0,
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:155:      quality_flags TEXT,
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:178:    qualityScore: 0.85,
.opencode/skills/system-spec-kit/mcp_server/tests/chunking-orchestrator-swap.vitest.ts:179:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:22:} from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:23:import type { FindSimilarFn } from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:54:/** Create a mock config-table DB with minimal SQL behavior needed by quality-gate persistence. */
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:87:      throw new Error(`Unexpected SQL in save-quality-gate test mock: ${sql}`);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:232:      expect(dbA.store.get('quality_gate_activated_at')).toBeDefined();
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:233:      expect(dbB.store.get('quality_gate_activated_at')).toBeDefined();
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:241:        quality_gate_activated_at: String(fifteenDaysAgo),
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:391:        expect(scoreTitleQuality('Implement save quality gate for TM-04')).toBe(0.8);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:395:        expect(scoreTitleQuality('Implement the pre-storage quality gate validation for memory saves in Sprint 4')).toBe(1.0);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:409:        expect(scoreTriggerQuality(['save memory', 'quality gate'])).toBe(0.5);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:413:        expect(scoreTriggerQuality(['save', 'quality', 'gate'])).toBe(1.0);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:433:        const score = scoreTriggerQuality(['save memory', '   ', 'quality gate']);
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:511:          trigger_phrases: '[save, quality]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:520:      it('SD1: High-quality memory scores above threshold', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:522:          title: 'Comprehensive implementation of save quality gate for Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:523:          trigger_phrases: '[save, quality, gate, TM-04]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:529:          title: 'Comprehensive implementation of save quality gate for Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:531:          triggerPhrases: ['save', 'quality', 'gate', 'TM-04'],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:539:      it('SD2: Low-quality memory scores below threshold', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:570:          trigger_phrases: '[save, quality, gate]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:577:          triggerPhrases: ['save', 'quality', 'gate'],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:753:        title: 'Comprehensive implementation of save quality gate for Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:754:        trigger_phrases: '[save, quality, gate, TM-04]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:760:        title: 'Comprehensive implementation of save quality gate for Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:763:        triggerPhrases: ['save', 'quality', 'gate', 'TM-04'],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:787:    it('UG4: Gate ON, low quality content rejects', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:792:        title: 'x', // Very short, low quality
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:809:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:810:        trigger_phrases: '[save, quality, gate]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:815:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:818:        triggerPhrases: ['save', 'quality', 'gate'],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:855:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:856:        trigger_phrases: '[save, quality, gate]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:861:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:864:        triggerPhrases: ['save', 'quality', 'gate'],
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:891:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:892:        trigger_phrases: '[save, quality, gate]',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:897:        title: 'A well-structured memory about quality gates in Sprint 4',
.opencode/skills/system-spec-kit/mcp_server/tests/save-quality-gate.vitest.ts:900:        triggerPhrases: ['save', 'quality', 'gate'],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:68:        qualityScore: 0.91,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:69:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:116:        qualityScore: 0.73,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:117:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:180:        qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:181:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:228:        qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:229:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:284:        qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:285:        qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:370:      { content: 'Extraction fails here.', hasCausalLinks: false, qualityScore: 0.5 } as never,
.opencode/skills/system-spec-kit/mcp_server/tests/post-insert-deferred.vitest.ts:421:      qualityScore: 0.8,
.opencode/skills/system-spec-kit/mcp_server/tests/integration-search-pipeline.vitest.ts:290:  it('C138-T4: SPECKIT_TRM=false disables evidence gap detection; absent re-enables it', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-context.vitest.ts:572:          input: 'resume previous work on memory quality',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-context.vitest.ts:633:          input: 'resume previous work on memory quality',
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-compatibility.vitest.ts:49:          quality_score REAL
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-compatibility.vitest.ts:56:        CREATE INDEX idx_quality_score ON memory_index(quality_score);
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:117:  it('T045-04: stays at Tier 1 when results meet quality thresholds', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:256:        expect(['low_quality', 'insufficient_results', 'both']).toContain(event.trigger.reason);
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:310:  it('T045-17b: quality degradation uses absolute+relative confidence checks', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:325:    expect(['low_quality', 'both']).toContain(weak?.reason);
.opencode/skills/system-spec-kit/mcp_server/tests/graph-payload-validator.vitest.ts:212:      isCocoIndexAvailable: vi.fn(() => true),
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:39:  gapsClosed?: string[];
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:84:  gapsClosed: string[];
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:117:  knowledge_gaps?: string;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:140:    knowledge_gaps TEXT,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:151:    gaps_closed TEXT,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:152:    new_gaps_discovered TEXT,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:179:  'knowledge_gaps',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:187:  'gaps_closed',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:188:  'new_gaps_discovered',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:333:  const gapsJson = JSON.stringify(knowledgeGaps);
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:352:      SET session_id = ?, pre_knowledge_score = ?, pre_uncertainty_score = ?, pre_context_score = ?, knowledge_gaps = ?, updated_at = ?
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:362:        gapsJson,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:399:    (spec_folder, task_id, phase, session_id, pre_knowledge_score, pre_uncertainty_score, pre_context_score, knowledge_gaps, created_at, updated_at)
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:411:      gapsJson,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:443:        'Knowledge gaps can guide your exploration focus'
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:465:    gapsClosed = [],
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:563:  const gapsClosedJson = JSON.stringify(gapsClosed);
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:577:        gaps_closed = ?,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:578:        new_gaps_discovered = ?,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:590:      gapsClosedJson,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:601:      originalGaps = preflightRecord.knowledge_gaps ? JSON.parse(preflightRecord.knowledge_gaps) : [];
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:634:          gaps: {
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:636:            closed: gapsClosed,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:644:        gapsClosed.length > 0 ? `${gapsClosed.length} knowledge gaps closed` : null,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:645:        newGapsDiscovered.length > 0 ? `${newGapsDiscovered.length} new gaps discovered for future sessions` : null
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:709:      let gapsClosed: string[] = [];
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:712:      try { knowledgeGaps = row.knowledge_gaps ? JSON.parse(row.knowledge_gaps as string) : []; } catch (_error: unknown) { /* ignore */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:713:      try { gapsClosed = row.gaps_closed ? JSON.parse(row.gaps_closed as string) : []; } catch (_error: unknown) { /* ignore */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:714:      try { newGapsDiscovered = row.new_gaps_discovered ? JSON.parse(row.new_gaps_discovered as string) : []; } catch (_error: unknown) { /* ignore */ }
.opencode/skills/system-spec-kit/mcp_server/handlers/session-learning.ts:747:          gapsClosed: gapsClosed,
.opencode/skills/system-spec-kit/mcp_server/tests/error-sanitization.vitest.ts:93:    expect(getDefaultErrorCodeForTool('memory_causal_stats')).toBe('E104');
.opencode/skills/system-spec-kit/mcp_server/tests/error-sanitization.vitest.ts:98:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:51:        'handle_memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:216:  it('T006-01: scores [0.9, 0.85, 0.8, 0.3, 0.1] truncates after 0.8 (large gap)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:228:    // Median gap: median of [0.05, 0.05, 0.50, 0.20] = (0.05+0.20)/2 = 0.125
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:236:  it('T006-02: minimum 3 results kept even with large early gaps', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:239:      { id: 2, score: 0.1 }, // huge gap after #1
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:272:  it('T006-04: uniform scores (no gaps) returns all results', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/feature-eval-query-intelligence.vitest.ts:291:      { id: 2, score: 0.1 }, // massive gap
.opencode/skills/system-spec-kit/mcp_server/tests/graph-metadata-integration.vitest.ts:160:          quality_flags: JSON.stringify([GRAPH_METADATA_MIGRATED_QUALITY_FLAG]),
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:334:  min_quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:643:    rerank = true, // Enable reranking by default for better result quality
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:650:    min_quality_score,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:704:  const qualityThreshold = resolveQualityThreshold(minQualityScore, min_quality_score);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:871:    qualityThreshold,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:930:      qualityThreshold,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:974:                     importance_tier, context_type, quality_score, created_at
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1167:    // Prepend evidence gap warning if present
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-integration.vitest.ts:384:  describe('Integration coverage gaps (S3.5 #14)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/cross-feature-integration-eval.vitest.ts:347:    it('7. Confidence truncation respects minimum: even with large gaps, min 3 results remain', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/cross-feature-integration-eval.vitest.ts:350:      // Create results with a huge gap after the 2nd result
.opencode/skills/system-spec-kit/mcp_server/tests/cross-feature-integration-eval.vitest.ts:355:        { id: 4, score: 0.10 }, // Large gap between 3 and 4
.opencode/skills/system-spec-kit/mcp_server/tests/cross-feature-integration-eval.vitest.ts:507:      // All same scores — no meaningful gap
.opencode/skills/system-spec-kit/mcp_server/tests/cross-feature-integration-eval.vitest.ts:514:      // When all scores are equal, median gap is 0, so no truncation
.opencode/skills/system-spec-kit/mcp_server/tests/gate-d-regression-4-stage-search-pipeline.vitest.ts:160:          qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/skill-graph-schema.vitest.ts:4:// Finding #30: The validation gap was easy to ship because there is no
.opencode/skills/system-spec-kit/mcp_server/tests/shadow-scoring-holdout.vitest.ts:400:  it('preserves sparse rank gaps instead of compressing judged items upward', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-ux-hooks.vitest.ts:37:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-ux-hooks.vitest.ts:255:          qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:25:// Feature catalog: Causal graph statistics (memory_causal_stats)
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:103:  tool: 'memory_drift_why' | 'memory_causal_link' | 'memory_causal_stats' | 'memory_causal_unlink',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:647:        'Use memory_causal_stats() to check overall graph coverage'
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:667:/** Handle memory_causal_stats tool - returns graph coverage and health metrics */
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:678:        tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:682:        recovery: getRecoveryHint('memory_causal_stats', 'E020'),
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:735:      tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:755:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:784:          'Use memory_causal_stats() to see graph overview'
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:854:const handle_memory_causal_stats = handleMemoryCausalStats;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:860:  handle_memory_causal_stats,
.opencode/skills/system-spec-kit/mcp_server/tests/shadow-comparison.vitest.ts:64:  'review code quality in handlers',
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:9:} from '../lib/search/evidence-gap-detector';
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:10:import type { TRMResult } from '../lib/search/evidence-gap-detector';
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:18:  // ---- T1: Well-separated scores → no gap ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:19:  it('T1: high Z-score distribution returns gapDetected=false', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:24:    expect(result.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:30:  // ---- T2: Flat distribution → gap detected ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:31:  it('T2: uniform scores produce low Z-score and detect gap', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:36:    expect(result.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:40:  // ---- T3: All identical scores above threshold → no gap ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:41:  it('T3: identical scores above MIN_ABSOLUTE_SCORE return gapDetected=false', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:46:    // Uniform strong results, not an evidence gap.
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:47:    expect(result.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:52:  // ---- T4: Empty array → gap detected ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:53:  it('T4: empty score array returns gap with zeroed stats', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:56:    expect(result.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:62:  // ---- T5: Single score above threshold → no gap ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:63:  it('T5: single high score returns no gap', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:66:    expect(result.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:71:  // ---- T6: Single score below MIN_ABSOLUTE_SCORE → gap ----
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:72:  it('T6: single very low score triggers gap via absolute threshold', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:75:    expect(result.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:85:    expect(belowThreshold.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:95:    expect(aboveThreshold.gapDetected).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:100:  it('T8: all scores below MIN_ABSOLUTE_SCORE trigger gap regardless of Z', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:104:    expect(result.gapDetected).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:119:    const trm: TRMResult = { gapDetected: true, zScore: 0.87, mean: 0.3, stdDev: 0.15 };
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:135:    expect(typeof result.gapDetected).toBe('boolean');
.opencode/skills/system-spec-kit/mcp_server/tests/evidence-gap-detector.vitest.ts:144:    expect(typeof result.gapDetected).toBe('boolean');
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:6:// Verify-fix-verify memory quality loop:
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:30:} from '../handlers/quality-loop';
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:35:} from '../handlers/quality-loop';
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:41:/** Good quality content with anchors, headings, and sufficient length */
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:54:- Chose MRR@5 and NDCG@10 as primary retrieval quality metrics
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:62:- Build feedback quality loop
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:67:  triggerPhrases: ['sprint 0', 'measurement foundation', 'eval infrastructure', 'retrieval quality'],
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:280:  it('returns high score for good quality content', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:289:  it('returns low score for bad quality content', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:447:  it('passes immediately for high-quality content when enabled', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:457:  it('enforces quality loop when SPECKIT_QUALITY_LOOP is not set (graduated default-ON)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:502:  it('succeeds after auto-fix improves quality above threshold', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/quality-loop.vitest.ts:636:  it('T-eval-logging: quality loop handles eval logging enabled', () => {
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-manager.ts:12:// Feature catalog: Session-manager transaction gap fixes
.opencode/skills/system-spec-kit/mcp_server/tests/embedding-pipeline-weighting.vitest.ts:77:    qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/tests/embedding-pipeline-weighting.vitest.ts:78:    qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:5:type Row = { id: string | number; quality_score?: number };
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:16:describe('C136: minQualityScore and min_quality_score behavior', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:32:      { id: 'a', quality_score: 0.2 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:33:      { id: 'b', quality_score: 0.5 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:34:      { id: 'c', quality_score: 0.9 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:43:      { id: 'a', quality_score: 0.0 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:44:      { id: 'b', quality_score: 0.6 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:45:      { id: 'c', quality_score: 1.0 },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:105:  it('includes deep-mode and archival/quality/state-limit controls in cache args', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:117:      qualityThreshold: 0.75,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:134:    expect(args.qualityThreshold).toBe(0.75);
.opencode/skills/system-spec-kit/mcp_server/tests/memory-search-quality-filter.vitest.ts:150:      qualityThreshold: undefined,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:474:  const gaps = findCoverageGaps(ns);
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:475:  if (gaps.length > 0) {
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:478:      description: `${gaps.length} question(s) have no coverage edges`,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:479:      count: gaps.length,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:573:    const gaps = findCoverageGaps(ns);
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:576:      description: `Dimension coverage (${(signals.dimensionCoverage * 100).toFixed(0)}%) is below threshold (${(t.dimensionCoverage * 100).toFixed(0)}%). ${gaps.length} gap(s) found. STOP is blocked until all required dimensions have meaningful coverage.`,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/convergence.ts:577:      count: gaps.length,
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts:36:    database.exec('DROP INDEX IF EXISTS idx_quality_score');
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts:41:      if (sql.includes('CREATE INDEX IF NOT EXISTS idx_quality_score')) {
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts:42:        throw new Error('simulated idx_quality_score failure');
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts:47:    expect(() => ensureSchemaVersion(database)).toThrow(/simulated idx_quality_score failure/);
.opencode/skills/system-spec-kit/mcp_server/tests/vector-index-schema-migration-refinements.vitest.ts:54:    expect(compatibility.missingIndexes).toContain('idx_quality_score');
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts:80:  'quality_score',
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts:81:  'quality_flags',
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts:158:      quality_score REAL DEFAULT 0,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts:159:      quality_flags TEXT,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/schema-downgrade.ts:184:    CREATE INDEX IF NOT EXISTS idx_quality_score ON memory_index(quality_score);
.opencode/skills/system-spec-kit/mcp_server/lib/contracts/README.md:281:Packet `007-detector-provenance-and-regression-floor` treats frozen detector fixtures as a regression-integrity floor only. The acceptance criterion from research recommendation R6 is the governing boundary: Public must land frozen detector fixtures that fail on structural regressions, while follow-on task corpora for user-visible structural quality are defined separately.
.opencode/skills/system-spec-kit/mcp_server/lib/contracts/README.md:285:- Fixture success proves detector integrity for the covered regex or heuristic lanes only; it does not prove user-visible structural quality, routing quality, or graph-context usefulness.
.opencode/skills/system-spec-kit/mcp_server/lib/contracts/README.md:291:Packet `007` adds honest provenance markers for audited detector modules and a reusable frozen Vitest floor under `scripts/tests/detector-regression-floor.vitest.ts.test.ts`. Future packets may extend that floor, but they must pair any quality claims with separate outcome-oriented evaluation.
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-snapshot.ts:12:import { isCocoIndexAvailable } from '../utils/cocoindex-path.js';
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-snapshot.ts:155:  // CocoIndex availability
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-snapshot.ts:158:    cocoIndexAvailable = isCocoIndexAvailable();
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:25:  | 'coverage_gaps'
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:69:	          return errorResponse('uncovered_questions is only valid for research graphs; use coverage_gaps for review graphs');
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:71:	        const gaps = findCoverageGaps(ns);
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:76:	          gaps: gaps.slice(0, limit),
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:77:	          totalGaps: gaps.length,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:81:	      case 'coverage_gaps': {
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:82:	        const gaps = findCoverageGaps(ns);
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:84:	          queryType: 'coverage_gaps',
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:87:	          gaps: gaps.slice(0, limit),
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:88:	          totalGaps: gaps.length,
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/query.ts:150:          `Unknown queryType: "${args.queryType}". Valid types: uncovered_questions, unverified_claims, contradictions, provenance_chain, coverage_gaps, hot_nodes`,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:19:} from '../handlers/quality-loop';
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:27:} from '../lib/validation/save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:77:      { path: 'mcp_server/lib/validation/save-quality-gate.ts', description: 'Three-layer quality gate that validates structure, content density, and semantic deduplication before persisting.' },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:82:        narrative: 'The save pipeline enforces gates in strict sequence: parser validation, quality loop scoring, sufficiency evaluation, template contract validation, and save quality gate. Each gate blocks downstream processing on failure.',
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:171:This pipeline enforcement fixture validates that every gate in the memory save pipeline correctly rejects malformed content. The gates include parser validation, quality loop scoring, sufficiency evaluation, template contract validation, and the save quality gate.
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:200:- Verified template contract failures block the save-quality gate when evidence remains sufficient.
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:430:  it('returns advisory-only failures for low-quality content on the planner-default path', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:442:  it('passes when quality loop is disabled regardless of score', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:485:  it('full-auto quality loop rejection blocks downstream sufficiency evaluation in pipeline', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:487:    // Build content that would fail quality loop (no triggers, short, no structure)
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:490:    const content = 'too short for quality loop';
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:498:    // Confirm quality loop rejects
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:728:    // Empty array is valid for template contract — may fail elsewhere (quality loop)
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:783:      title: null,         // 0 title quality
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:784:      content: 'short',    // low length quality, no frontmatter
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:786:      triggerPhrases: [],  // 0 trigger quality
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:787:      anchors: [],         // 0 anchor quality
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:825:  it('passes when save quality gate is disabled', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:914:  it('content that passes quality loop can still fail sufficiency', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:954:        { path: 'other.ts', description: 'Three-layer quality gate that validates structure, content density, and semantic deduplication.' },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:970:  it('content that passes template contract can still fail save quality gate', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:978:    // Now run quality gate with empty title and no triggers to force failure
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:993:  it('planner-default quality advisories do not preempt downstream sufficiency evaluation', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:996:    // Content that would fail quality loop (no triggers, short, no anchors)
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1004:    // On the planner-default path the quality loop stays advisory, so downstream
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1010:      replaceContent: 'x'.repeat(100), // passes parser but fails quality loop
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1016:      // The pipeline still rejects, but not because the quality loop hard-blocked first.
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1024:    // Build content that passes parser and quality loop (disabled) but fails sufficiency
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1044:  it('template contract rejection blocks save quality gate (gate ordering proof)', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1091:    // Actually the raw content is > 5 chars so parser passes, but quality/sufficiency will reject
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-pipeline-enforcement.vitest.ts:1195:  it('quality loop handles exactly 3 trigger phrases at boundary', () => {
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:4:// Phase 023: Lightweight session quality tracking.
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:5:// Collects events during MCP tool dispatch and computes quality scores.
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:206:/** Compute overall quality score and level. */
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:215:  // F065: Weight rationale for quality score factors:
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:218:  //                          degradation signal. A 60-min gap almost certainly means
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:222:  //                          context fragmentation; stable focus correlates with quality.
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:230:  //                          "enabling" factors rather than direct quality signals.
.opencode/skills/system-spec-kit/mcp_server/lib/config/README.md:71:| **prospective** | 14 days | 60 days | Future intentions: TODOs, next steps, plans |
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:40: * Describes the ContradictionCluster shape.
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:42:export interface ContradictionCluster {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:53:  contradictions: ContradictionCluster[];
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:288:export function buildContradictionClusters(
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:291:): ContradictionCluster[] {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:292:  const clusters: ContradictionCluster[] = [];
.opencode/skills/system-spec-kit/mcp_server/lib/storage/consolidation.ts:441:  const contradictions = buildContradictionClusters(database, contradictionPairs);
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:79:- Purpose: Owns large-file chunk production and quality-based chunk thinning before indexing. It defines how anchor-tagged and structurally segmented content becomes retrieval-sized units.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:82:  - `chunk-thinning.ts` — chunk quality scoring and threshold-based thinning before index write.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:141:- Purpose: Owns evaluation, baselines, shadow measurements, quality proxies, and reporting artifacts for retrieval quality. It is the measurement and experimentation layer for search behavior.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:153:  - `handlers/quality-loop.ts`
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:169:- Purpose: Owns implicit-feedback capture, shadow-feedback evaluation, ranking-comparison metrics, and batch-learning helpers used to measure learned-signal quality without mutating live rankings.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:356:  - `retrieval-telemetry.ts` — retrieval-run telemetry factory and quality-proxy metrics.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:386:- Purpose: Owns preflight validation and save-time quality gates that reject malformed, duplicate, or low-signal writes before expensive work happens. It is a defensive boundary ahead of mutation and indexing paths.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:389:  - `save-quality-gate.ts` — multi-layer structural/content/semantic quality gate.
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:415:- `13--memory-quality-and-indexing`
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:428:| `cache` | `01--retrieval`, `13--memory-quality-and-indexing`, `15--retrieval-enhancements` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:429:| `chunking` | `13--memory-quality-and-indexing`, `15--retrieval-enhancements` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:436:| `extraction` | `02--mutation`, `13--memory-quality-and-indexing`, `17--governance` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:437:| `feedback` | `11--scoring-and-calibration`, `13--memory-quality-and-indexing`, `19--feature-flag-reference` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:443:| `ops` | `04--maintenance`, `13--memory-quality-and-indexing`, `16--tooling-and-scripts` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:444:| `parsing` | `01--retrieval`, `12--query-intelligence`, `13--memory-quality-and-indexing` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:445:| `providers` | `01--retrieval`, `13--memory-quality-and-indexing`, `15--retrieval-enhancements` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:451:| `storage` | `02--mutation`, `04--maintenance`, `05--lifecycle`, `08--bug-fixes-and-data-integrity`, `10--graph-signal-activation`, `13--memory-quality-and-indexing`, `17--governance` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:454:| `validation` | `02--mutation`, `08--bug-fixes-and-data-integrity`, `13--memory-quality-and-indexing` |
.opencode/skills/system-spec-kit/mcp_server/lib/MODULE_MAP.md:472:| `13--memory-quality-and-indexing` | `cache`, `chunking`, `extraction`, `feedback`, `ops`, `parsing`, `providers`, `storage`, `validation` |
.opencode/skills/system-spec-kit/mcp_server/lib/learning/README.md:32:The learning module tracks corrections over time and applies stability adjustments that help the system learn which entries are most reliable. This applies to both standard memory notes and indexed spec documents, improving ranking quality for spec and decision retrieval.
.opencode/skills/system-spec-kit/mcp_server/lib/config/memory-types.ts:73:    description: 'Future intentions: TODOs, next steps, planned actions',
.opencode/skills/system-spec-kit/mcp_server/lib/storage/post-insert-metadata.ts:36:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/post-insert-metadata.ts:37:  quality_flags?: string;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/post-insert-metadata.ts:62:  'spec_level', 'quality_score', 'quality_flags', 'parent_id',
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:7:// Feature catalog: Verify-fix-verify memory quality loop
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:8:// Feature catalog: Pre-storage quality gate
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:88: * Compute trigger phrase quality sub-score.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:120: * Compute anchor format quality sub-score.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:214: * Compute token budget quality sub-score.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:250: * Compute coherence quality sub-score.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:369: * Compute composite quality score for a memory file.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:425: * Attempt automatic fixes for quality issues.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:568: * Run the verify-fix-verify quality loop on memory content.
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:571: * Computes quality score, attempts auto-fix if below threshold,
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:703: * Log quality metrics to the eval infrastructure (eval_metric_snapshots table).
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:733:      0, // No eval run for quality metrics
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:734:      'memory_quality_score',
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:736:      'quality_loop',
.opencode/skills/system-spec-kit/mcp_server/handlers/quality-loop.ts:742:    console.warn('[quality-loop] logQualityMetrics failed (non-fatal):', msg);
.opencode/skills/system-spec-kit/mcp_server/lib/storage/checkpoints.ts:1197:  if ((column === 'trigger_phrases' || column === 'quality_flags') && Array.isArray(value)) {
.opencode/skills/system-spec-kit/mcp_server/lib/storage/checkpoints.ts:1261:    'quality_score',
.opencode/skills/system-spec-kit/mcp_server/lib/storage/checkpoints.ts:1262:    'quality_flags',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts:145:    qualityGateMode?: 'enforce' | 'warn-only';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts:151:    qualityGateMode: options?.qualityGateMode,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-index.ts:419:        ...(useWarnOnly ? { qualityGateMode: 'warn-only' as const } : {}),
.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/tier-classifier.ts:86:   1.5 TYPE-SPECIFIC HALF-LIVES (REQ-002, T008)
.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/tier-classifier.ts:154: * Get effective half-life for a memory based on its type (REQ-002, CHK-017)
.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/adaptive-ranking.ts:58:/** Aggregate signal quality and rollout readiness metrics across stored adaptive events. */
.opencode/skills/system-spec-kit/mcp_server/lib/cognitive/adaptive-ranking.ts:510: * Summarize adaptive signal quality and rollout readiness across stored events.
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:4:// Structured query helpers for coverage gap detection, contradiction
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:91: * Find nodes with coverage gaps.
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:107:  const gaps: CoverageGap[] = [];
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:111:    // A gap means the node has no outgoing coverage edges.
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:134:        gaps.push({
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:166:        gaps.push({
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-query.ts:176:  return gaps;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:470:      quality_score,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:471:      quality_flags
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:490:    parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:491:    JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:504:    quality_score: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/lineage-state.ts:505:    quality_flags: JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:43:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:44:  qualityFlags?: string[];
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:73:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:74:  quality_flags?: string;
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:97:  'spec_level', 'quality_score', 'quality_flags', 'parent_id',
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:240:        qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:241:        qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:257:        quality_score: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:258:        quality_flags: JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:523:            quality_score = ?,
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:524:            quality_flags = ?
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:536:        parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/chunking-orchestrator.ts:537:        JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:3:description: "Pre-flight quality gates for memory operations: anchor validation, duplicate detection and token budget verification."
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:12:> Pre-flight quality gates for memory operations: anchor validation, duplicate detection, token budget verification and content size checks.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:38:| Modules | 2 | preflight.ts, save-quality-gate.ts |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:40:| Quality Gate Layers | 3 | Structural, content quality, semantic dedup |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:52:| **Save Quality Gate** | 3-layer pre-storage validation (structural, content quality scoring, semantic dedup). Behind `SPECKIT_SAVE_QUALITY_GATE` flag |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:62: save-quality-gate.ts # 3-layer pre-storage quality gate (structural, content, semantic dedup)
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:71:| `save-quality-gate.ts` | 3-layer pre-storage quality gate: structural validation, content quality scoring (title, triggers, length, anchors, metadata, signal density), and semantic dedup. Behind `SPECKIT_SAVE_QUALITY_GATE` |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:157:**Purpose**: 3-layer pre-storage quality gate before memory writes. Behind `SPECKIT_SAVE_QUALITY_GATE` flag.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:167:**Exported functions (save-quality-gate.ts):**
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:176:| `scoreTitleQuality(title)` | Layer 2 dimension: title quality (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:177:| `scoreTriggerQuality(triggerPhrases)` | Layer 2 dimension: trigger phrase quality (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:178:| `scoreLengthQuality(content)` | Layer 2 dimension: content length quality (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:179:| `scoreAnchorQuality(anchors)` | Layer 2 dimension: anchor quality (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:180:| `scoreMetadataQuality(content)` | Layer 2 dimension: metadata quality (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:181:| `scoreContentQuality(params)` | Layer 2: combined content quality scoring |
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:254:import { runQualityGate } from './save-quality-gate';
.opencode/skills/system-spec-kit/mcp_server/lib/validation/README.md:282:| Content scoring | `scoreContentQuality()` | Evaluate memory content quality |
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:331: * source metadata quality classes reachable through ANSWERS -> CITES paths,
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:357:    const qualityClasses = new Set<string>();
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:361:        const qualityClass = sourceMetadataById.get(sourceId)?.quality_class;
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:362:        if (typeof qualityClass === 'string' && qualityClass.length > 0) {
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:363:          qualityClasses.add(qualityClass);
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/coverage-graph-signals.ts:368:    totalDiversity += qualityClasses.size;
.opencode/skills/system-spec-kit/mcp_server/lib/feedback/rank-metrics.ts:152: * Accepts sparse rankings with gaps. Missing positions are treated as
.opencode/skills/system-spec-kit/mcp_server/lib/storage/reconsolidation.ts:1061:    quality_score: existingRow.quality_score,
.opencode/skills/system-spec-kit/mcp_server/lib/storage/reconsolidation.ts:1062:    quality_flags: existingRow.quality_flags,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:40:import { runQualityGate, isQualityGateEnabled } from '../lib/validation/save-quality-gate.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:72:} from './quality-loop.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:75:} from './quality-loop.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:166:// Feature catalog: Verify-fix-verify memory quality loop
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:180:  qualityLoopResult: QualityLoopResult;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:305:    qualityLoopMode?: 'advisory' | 'full-auto';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:347:    validation.warnings.push('V-rule validator module unavailable — quality gate bypassed. Save proceeds without V-rule enforcement.');
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:357:      // Return early with a rejected quality loop result so callers see the block
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:362:        qualityLoopResult: {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:393:  const qualityLoopResult = runQualityLoop(parsed.content, buildQualityLoopMetadata(parsed, database), {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:395:    mode: options.qualityLoopMode ?? 'advisory',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:397:  parsed.qualityScore = qualityLoopResult.score.total;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:398:  parsed.qualityFlags = Array.from(new Set([
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:399:    ...(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:400:    ...qualityLoopResult.score.issues,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:402:  if (qualityLoopResult.fixedTriggerPhrases) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:403:    parsed.triggerPhrases = qualityLoopResult.fixedTriggerPhrases;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:405:  const finalizedFileContent = qualityLoopResult.fixedContent
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:406:    && qualityLoopResult.passed
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:407:    ? qualityLoopResult.fixedContent
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:456:    qualityLoopResult,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:580:    qualityScore: args.parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:581:    qualityFlags: args.parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1349:      qualityLoopMode: params.plannerMode === 'full-auto' ? 'full-auto' : 'advisory',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1366:  if (preparedMemory.qualityLoopResult.fixes.length > 0 && preparedMemory.qualityLoopResult.passed && preparedMemory.qualityLoopResult.fixedContent) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1367:    console.error(`[memory-save] Quality loop applied ${preparedMemory.qualityLoopResult.fixes.length} auto-fix(es) for ${path.basename(params.file_path)} before canonical pending-file promotion`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1809:  if (!prepared.preparedMemory.qualityLoopResult.passed || prepared.preparedMemory.qualityLoopResult.fixes.length > 0) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1810:    const qualityMessage = prepared.preparedMemory.qualityLoopResult.rejectionReason
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1811:      ?? (prepared.preparedMemory.qualityLoopResult.fixes.length > 0
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1812:        ? `Quality loop would apply ${prepared.preparedMemory.qualityLoopResult.fixes.length} fix(es) in full-auto mode.`
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:1816:      message: qualityMessage,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2027:    qualityGateMode?: 'enforce' | 'warn-only';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2041:    qualityGateMode = 'enforce',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2051:      qualityLoopResult,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2058:    if (!qualityLoopResult.passed && qualityLoopResult.rejected) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2059:      if (qualityGateMode === 'warn-only') {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2060:        console.warn(`[memory-save] V-rule warn-only (spec doc) for ${path.basename(filePath)}: ${qualityLoopResult.rejectionReason}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2070:          qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2071:          qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2073:          rejectionReason: qualityLoopResult.rejectionReason,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2074:          message: qualityLoopResult.rejectionReason,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2080:      if (qualityGateMode === 'warn-only') {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2092:      } else if (qualityGateMode === 'warn-only') {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2115:          qualityLoopMode: 'full-auto',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2184:        const qualityGateResult = runQualityGate({
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2208:        if (!qualityGateResult.pass && !qualityGateResult.warnOnly && qualityGateMode !== 'warn-only') {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2209:          console.error(`[memory-save] TM-04: Quality gate REJECTED save for ${path.basename(routedFilePath)}: ${qualityGateResult.reasons.join('; ')}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2215:            qualityScore: routedParsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2216:            qualityFlags: routedParsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2217:            rejectionReason: `Quality gate rejected: ${qualityGateResult.reasons.join('; ')}`,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2218:            message: `Quality gate rejected: ${qualityGateResult.reasons.join('; ')}`,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2219:            qualityGate: {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2221:              reasons: qualityGateResult.reasons,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2222:              layers: qualityGateResult.layers,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2227:        if (!qualityGateResult.pass && qualityGateMode === 'warn-only') {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2228:          console.warn(`[memory-save] TM-04: Quality gate warn-only (spec doc) for ${path.basename(routedFilePath)}: ${qualityGateResult.reasons.join('; ')}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2231:        if (qualityGateResult.wouldReject) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2232:          console.warn(`[memory-save] TM-04: Quality gate WARN-ONLY for ${path.basename(routedFilePath)}: ${qualityGateResult.reasons.join('; ')}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2592:  qualityGateMode?: 'enforce' | 'warn-only';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2615:    qualityGateMode = 'enforce' as 'enforce' | 'warn-only',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2629:  if (prepared.qualityLoopResult.fixes.length > 0 && prepared.qualityLoopResult.passed && prepared.qualityLoopResult.fixedContent) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2630:    console.error(`[memory-save] Quality loop applied ${prepared.qualityLoopResult.fixes.length} auto-fix(es) for ${path.basename(filePath)}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2641:    qualityGateMode,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2783:            preparedDryRun.qualityLoopResult,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2789:      && preparedDryRun.qualityLoopResult.rejected !== true
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2827:        qualityLoop: {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2828:          passed: preparedDryRun.qualityLoopResult.passed,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2829:          rejected: preparedDryRun.qualityLoopResult.rejected,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2830:          fixes: preparedDryRun.qualityLoopResult.fixes,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2831:          rejectionReason: preparedDryRun.qualityLoopResult.rejectionReason,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2848:      qualityLoopMode: 'advisory',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:2894:          qualityLoopMode: 'advisory',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3149:          qualityLoopMode: currentParams.plannerMode === 'full-auto' ? 'full-auto' : 'advisory',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3167:      if (prepared.qualityLoopResult.fixes.length > 0 && prepared.qualityLoopResult.passed && prepared.qualityLoopResult.fixedContent) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3168:        console.error(`[memory-save] Quality loop applied ${prepared.qualityLoopResult.fixes.length} auto-fix(es) for ${path.basename(currentFilePath)} before pending-file promotion`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3175:        persistedContent: prepared.qualityLoopResult.passed && prepared.qualityLoopResult.fixedContent
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3176:          ? prepared.qualityLoopResult.fixedContent
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:3218:          qualityGateMode: 'warn-only',
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:5:import { isCocoIndexAvailable } from '../lib/utils/cocoindex-path.js';
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:451:  // F046: CocoIndex availability via shared helper (no process.cwd())
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:452:  const cocoIndexAvailable = isCocoIndexAvailable();
.opencode/skills/system-spec-kit/mcp_server/lib/storage/causal-edges.ts:163:  // Processes; consumers only compare for inequality, so wrapping is safe.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:8:// - Layer 2: Content quality scoring (title, triggers, length,
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:16:// Gate logs quality scores and would-reject decisions but does
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:44:/** Result from Layer 2: Content quality scoring */
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:63:/** Combined result from all quality gate layers */
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:77:/** Parameters for running the quality gate */
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:101:/** Signal density threshold: below this score, content is too low quality */
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:114:// REQ-D4-003: Short-critical quality gate exception
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:130:/** Generic/low-quality title patterns */
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:152:const ACTIVATION_CONFIG_KEY = 'quality_gate_activated_at';
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:223:let qualityGateActivatedAt: number | null = null;
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:226: * Check if the quality gate feature flag is enabled.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:236: * Check if the quality gate is in warn-only mode.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:247:  if (qualityGateActivatedAt === null) {
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:250:      qualityGateActivatedAt = persisted;
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:254:  if (qualityGateActivatedAt === null) {
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:257:  const elapsed = Date.now() - qualityGateActivatedAt;
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:263: * Called when the quality gate is first enabled.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:270:  qualityGateActivatedAt = timestamp ?? Date.now();
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:271:  persistActivationTimestampToDb(qualityGateActivatedAt);
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:279:  qualityGateActivatedAt = null;
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:291:  if (qualityGateActivatedAt !== null) return;
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:296:  if (qualityGateActivatedAt === null) {
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:306: * REQ-D4-003: Check whether the save quality gate exceptions feature is enabled.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:454: * Score title quality (0-1).
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:488: * Score trigger phrase quality (0-1).
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:501: * Score content length quality (0-1).
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:514: * Score anchor quality (0-1).
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:527: * Score metadata quality (0-1).
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:565: * Compute a lightweight quality score for backfilled rows.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:595: * Layer 2: Compute content quality score across all dimensions.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:636:      reasons.push('Low title quality: use a specific, descriptive title');
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:735:    console.warn('[quality-gate] Semantic dedup check failed:', message);
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:753: * Run the full 3-layer quality gate for a memory save operation.
.opencode/skills/system-spec-kit/mcp_server/lib/validation/save-quality-gate.ts:810:  // Layer 2: Content quality scoring
.opencode/skills/system-spec-kit/mcp_server/lib/providers/embeddings.ts:16:  generateClusteringEmbedding,
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:4:// O2-5/O2-12: Runtime bridge to scripts/memory/validate-memory-quality
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:11:// Feature catalog: Verify-fix-verify memory quality loop
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:12:// Feature catalog: Pre-storage quality gate
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:15:// 1. TYPES (mirrored from validate-memory-quality.ts)
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:61:      path.resolve(import.meta.dirname, '../../scripts/dist/memory/validate-memory-quality.js'),
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:62:      path.resolve(import.meta.dirname, '../../../scripts/dist/memory/validate-memory-quality.js'),
.opencode/skills/system-spec-kit/mcp_server/handlers/v-rule-bridge.ts:80:    console.error(`[v-rule-bridge] Failed to load validate-memory-quality: ${msg} — V-rule checks unavailable`);
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:8://   2. Session continuity warning if quality score is degraded/critical
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:120: * Enrich with session continuity warning if quality is degraded.
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:126:    const quality = computeQualityScore();
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:128:    if (quality.level === 'critical') {
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:129:      return ['[session] Context quality is CRITICAL. Consider running `memory_context({ mode: "resume" })` or `session_health` to diagnose.'];
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:131:    if (quality.level === 'degraded') {
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:132:      return ['[session] Context quality is degraded. Session may benefit from a `session_resume` call.'];
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/content-normalizer.ts:11:// The quality of semantic embeddings and keyword retrieval.
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/content-normalizer.ts:61: *   <!-- TODO: remove -->
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:2:// MODULE: CocoIndex Path Helper
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:4:// F046/F051: Shared helper for resolving the CocoIndex binary path.
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:12:/** Relative path from project root to the CocoIndex CLI binary. */
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:48: * Get the absolute path to the CocoIndex binary.
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:51:export function getCocoIndexBinaryPath(): string {
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:56: * Check whether the CocoIndex binary exists on disk.
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:58:export function isCocoIndexAvailable(): boolean {
.opencode/skills/system-spec-kit/mcp_server/lib/utils/cocoindex-path.ts:59:  return existsSync(getCocoIndexBinaryPath());
.opencode/skills/system-spec-kit/mcp_server/lib/validation/preflight.ts:234:  // Token budget estimation (~4 chars/token — harmonized with quality-loop.ts)
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts:196: * REQ-001 / REQ-016 (Cluster 2): Centroid-only confidence floor. When the
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts:204: * Reproduction: `classifyIntent("Semantic Search")` previously returned
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts:441:  // REQ-001 (Cluster 2): Track per-intent keyword + pattern evidence so the
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts:443:  // hashed bag-of-words centroid match (e.g. "Semantic Search" → fix_bug 0.098).
.opencode/skills/system-spec-kit/mcp_server/lib/search/intent-classifier.ts:508:  // REQ-001 / REQ-016 (Cluster 2): Centroid-only fallback gate.
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:202:  reason: 'low_quality' | 'insufficient_results' | 'both';
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:217: * Absolute quality floor for degradation checks.
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:221: * pair it with a relative-gap check to avoid score-scale coupling.
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:239:/** Tier-2 vector similarity floor for quality-aware fallback (percentage units). */
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:1789: * When SPECKIT_SEARCH_FALLBACK=true: delegates to the 3-tier quality-aware
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2102: * Evaluate whether results meet quality thresholds.
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2125:      : lowQuality ? 'low_quality'
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2160: *   → Pass if quality signal is healthy AND count >= 3
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2164: *   → Pass if quality signal is healthy AND count >= 3
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2191:    // Tier 1 passed quality thresholds — attach empty degradation metadata
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:33:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:34:  qualityFlags?: string[];
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:306:      qualityScore: parsed.qualityScore,
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:307:      qualityFlags: parsed.qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:319:      quality_score: parsed.qualityScore ?? 0,
.opencode/skills/system-spec-kit/mcp_server/handlers/pe-gating.ts:320:      quality_flags: JSON.stringify(parsed.qualityFlags ?? []),
.opencode/skills/system-spec-kit/mcp_server/lib/architecture/layer-definitions.ts:98:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:74:  qualityScore: number;
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:75:  qualityFlags: string[];
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:290:      qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:291:      qualityFlags: [],
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:331:      qualityScore: 1,
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:332:      qualityFlags: validation.migrated ? [GRAPH_METADATA_MIGRATED_QUALITY_FLAG] : [],
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:342:  const qualityScore = extractQualityScore(content);
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:343:  const qualityFlags = extractQualityFlags(content);
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:377:    qualityScore,
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:378:    qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/lib/parsing/memory-parser.ts:383:import { extractQualityScore, extractQualityFlags } from '@spec-kit/shared/parsing/quality-extractors';
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:101:Post-channel: constitutional memory injection, quality score filtering, tier/contextType filtering.
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:115:10. Validation signals — quality scoring multiplier (clamped 0.8-1.2)
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:121:**Score immutability invariant**: Stage 4 MUST NOT modify scores. Enforced via compile-time `Stage4ReadonlyRow` readonly fields and runtime `captureScoreSnapshot` / `verifyScoreInvariant` defence-in-depth. Applies memory-state filtering, per-tier limits, evidence gap detection (Z-score confidence check), quality floor (`QUALITY_FLOOR=0.005`), and token budget truncation. Lowest-priority retained-history rows remain fallback evidence only when filters allow them.
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:226:**Length Penalty** (REQ-008): Short content (<50 chars) is penalized to `0.9x`; very long content (>2000 chars) is penalized to `0.95x`.
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:252:| **TypeScript**       | `channel-representation.ts`, `channel-enforcement.ts`, `confidence-truncation.ts` (quality)   |
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:307:| `confidence-truncation.ts` | -      | TypeScript | Removes low-confidence tail using 2x median gap heuristic (min 3 results) (Sprint 3) |
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:311:| `evidence-gap-detector.ts` | -      | TypeScript | Z-score confidence check on RRF scores to detect low-confidence retrieval |
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:423:| `SPECKIT_SAVE_QUALITY_GATE`| `true` | Enable 3-layer pre-storage quality gate (TM-04) |
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:568:**Length Penalty** (REQ-008):
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:677:**PI-A5: Verify-Fix-Verify Loop** (`memory-save.ts` / `quality-loop.ts`):
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:678:Opt-in quality loop gated by `SPECKIT_QUALITY_LOOP`. When enabled, the save path performs 1 initial evaluation plus up to 2 immediate auto-fix retries by default. The reported `attempts` count reflects actual evaluations used, so early-break cases can stop before the configured ceiling. Accepted saves persist metadata fixes and carry rewritten body content in-memory until later hard-reject gates clear under lock. Rejected memories return structured rejection feedback instead of continuing to storage.
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:683:**TM-04: Quality Gate** (`save-quality-gate.ts`):
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:692:Signal density threshold: **0.4** — below this, content quality is too low. Activation metadata can still be recorded for diagnostics, but continuity no longer depends on staged rollout windows.
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:954:| REQ-008 | Length penalty for short content | cross-encoder.ts                |
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:7:// This allows the scoring layer to incorporate spec quality information.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:10:// 1. importance_tier  → qualitative quality signal (tier → numeric score)
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:11:// 2. quality_score    → direct numeric quality metric from DB column
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:24: * Importance tier → quality score mapping.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:25: * Higher tiers (constitutional, critical) map to higher quality signals.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:26: * Used when quality_score is absent or zero.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:71:  /** Normalised quality score in [0, 1] derived from quality_score or importance_tier. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:72:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:80: * Derive a normalised quality score from importance_tier, clamped to [0, 1].
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:83:function qualityScoreFromTier(tier: string | undefined): number | undefined {
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:160: *   1. `quality_score` from the DB column (direct metric, highest priority).
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:162: *   2. `importance_tier` → tier quality score mapping.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:168: * (no tier, no quality_score, no content with markers).
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:180:  // A positive, finite quality_score from the DB is the authoritative signal.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:183:  const dbQualityScore = typeof row.quality_score === 'number' && Number.isFinite(row.quality_score) && row.quality_score > 0
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:184:    ? row.quality_score
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:188:    result.qualityScore = Math.min(1, dbQualityScore); // clamp upper bound
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:191:    // Fall back to tier-derived score when no DB quality_score is available.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:192:    const tierScore = qualityScoreFromTier(row.importance_tier);
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:194:      result.qualityScore = tierScore;
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:236:  // -- 4. Importance tier signal (even without quality score fallback above) --
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:237:  // If we have a tier name at all, it's a signal — record qualityScore if not yet set.
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:239:    const tierScore = qualityScoreFromTier(row.importance_tier);
.opencode/skills/system-spec-kit/mcp_server/lib/search/validation-metadata.ts:241:      result.qualityScore = tierScore;
.opencode/skills/system-spec-kit/mcp_server/lib/errors/core.ts:64:  memory_causal_stats: ERROR_CODES.CAUSAL_GRAPH_ERROR,
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:16:// Feature catalog: Verify-fix-verify memory quality loop
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:83: * Transparent Reasoning Module (evidence-gap detection).
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:156: * Save-time quality auto-fix retries gate for planner-first flows.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:174: * Pre-storage quality gate for memory saves.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:190: * Confidence-gap truncation for low-confidence tails.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:369: * T008: Verify-fix-verify memory quality loop.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-flags.ts:433: * REQ-D4-003: Short-critical quality gate exception.
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:56:| **Semantic Search** | Vector-based similarity search with SQLite vector index and hybrid keyword matching |
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:67:| **Confidence Truncation** | Removes low-confidence tail results using 2x median gap detection |
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:157:│   ├── confidence-truncation.ts # Confidence truncation (2x median gap, min 3 results)
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:159:│   ├── evidence-gap-detector.ts # TRM with Z-score confidence
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:238:│   ├── eval-quality-proxy.ts   # Quality proxy scoring
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:263:│   ├── save-quality-gate.ts    # Save-time quality gate
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:271:│   ├── retrieval-telemetry.ts  # Latency, mode, fallback and quality metrics
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:336:| `search/confidence-truncation.ts` | Low-confidence tail removal (2x median gap) |
.opencode/skills/system-spec-kit/mcp_server/lib/README.md:578:const results = await hybridSearch('TODO authentication', queryEmbedding, {
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:6:// quality filtering, threshold resolution, cache key building,
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:25:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:42:  qualityThreshold?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:107: * Filter results by minimum quality score.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:117:    const rawScore = result.quality_score as number | undefined;
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:124: * Resolve the quality threshold from camelCase or snake_case parameter.
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:155:  qualityThreshold,
.opencode/skills/system-spec-kit/mcp_server/lib/search/search-utils.ts:197:    qualityThreshold,
.opencode/skills/system-spec-kit/mcp_server/hooks/gemini/session-prime.ts:180:        '- CocoIndex: unknown',
.opencode/skills/system-spec-kit/mcp_server/hooks/claude/session-prime.ts:172:    '- CocoIndex: unknown',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/README.md:184:| [../validation/](../validation/) | Pre-flight quality gates |
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:40:  | 'validation_quality'
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:143:  // Validation quality
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:148:    const qualityScore = typeof validationMeta.qualityScore === 'number'
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:149:      ? validationMeta.qualityScore
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:151:    if (qualityScore > 0.7) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:152:      signals.push('validation_quality');
.opencode/skills/system-spec-kit/mcp_server/lib/search/result-explainability.ts:212:    if (signal === 'validation_quality') return 'high spec quality';
.opencode/skills/system-spec-kit/mcp_server/hooks/copilot/session-prime.ts:102:    '- CocoIndex: unknown',
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:212:    qualityScore = 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:213:    qualityFlags = [],
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:251:      qualityScore,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:252:      qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:267:        content_text, quality_score, quality_flags, parent_id
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:272:      encodingIntent ?? 'document', documentType, specLevel, contentText, qualityScore, JSON.stringify(qualityFlags), parentId
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:321:    qualityScore = 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:322:    qualityFlags = [],
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:350:            quality_score = ?,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:351:            quality_flags = ?,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:355:      `).run(title, triggers_json, importanceWeight, canonicalFilePath, failureReason, now, encodingIntent, documentType, specLevel, contentText, qualityScore, JSON.stringify(qualityFlags), existing.id);
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:366:        content_text, quality_score, quality_flags, parent_id
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:370:      importanceWeight, now, now, failureReason, encodingIntent ?? 'document', documentType, specLevel, contentText, qualityScore, JSON.stringify(qualityFlags), parentId
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:410:    qualityScore,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:411:    qualityFlags,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:499:    if (qualityScore !== undefined) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:500:      updates.push('quality_score = ?');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:501:      values.push(qualityScore);
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:503:    if (qualityFlags !== undefined) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:504:      updates.push('quality_flags = ?');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-mutations.ts:505:      values.push(JSON.stringify(qualityFlags));
.opencode/skills/system-spec-kit/mcp_server/lib/search/entity-linker.ts:141:  // Search quality / ranking domain (Phase B T015)
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:30:  /** Minimum number of results to always return, regardless of gap. Default: 3. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:37:/** Gap multiplier: gap must exceed this multiple of the median gap to trigger truncation.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:38: * 2x median is the elbow heuristic — a gap twice the typical spread signals a relevance cliff. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:44: * Compute consecutive score gaps for a sorted (descending) score array.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:45: * gap[i] = scores[i] - scores[i+1]   for i in [0, n-2]
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:46: * NaN and Infinity scores are filtered out before gap computation.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:50: * @returns Array of consecutive score gaps (length = scores.length - 1).
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:53:  // NaN/Infinity from upstream bugs would corrupt gap statistics — filter them first
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:56:  const gaps: number[] = [];
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:58:    gaps.push(finite[i] - finite[i + 1]);
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:60:  return gaps;
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:83: * Truncate results based on confidence gap analysis.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:87: * 2. Compute consecutive score gaps.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:88: * 3. Compute median gap.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:89: * 4. Find first index >= (minResults - 1) where gap > 2 * medianGap.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:91: * 6. If no threshold-exceeding gap found, return all results unchanged.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:143:  const gaps = computeGaps(scores);
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:144:  const medianGap = computeMedian(gaps);
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:147:  // When medianGap is 0 (all same scores), no meaningful gap exists — return all
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:160:  // Search for the first gap that exceeds the threshold, starting from minResults - 1.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:161:  // Gap[i] is the gap between result i and result i+1.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:162:  // If gap[i] > threshold, we keep results 0..i (cutoffIndex = i).
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:166:  for (let i = minResults - 1; i < gaps.length; i++) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:167:    if (gaps[i] > threshold) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:169:      cutoffGap = gaps[i];
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-truncation.ts:174:  // No significant gap found — return all results
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:5:// Error catalog with recovery hints (REQ-004, REQ-009)
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:590:      'Check memory_causal_stats() for graph status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:593:    toolTip: 'memory_causal_stats()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:628:      'Run memory_causal_stats() to inspect graph health',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:632:    toolTip: 'memory_causal_stats()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:638:      'Run memory_causal_stats() to inspect graph integrity',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:668:// 4. DEFAULT HINT (REQ-009)
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:836:  // 3. Return default hint (REQ-009)
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:67:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:68:  quality_flags?: string | string[] | null;
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:112:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:113:  qualityFlags?: string[];
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:128:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-types.ts:129:  qualityFlags?: string[];
.opencode/skills/system-spec-kit/mcp_server/lib/scoring/confidence-tracker.ts:106: *   which Stage 2 validation metadata scoring treats as a quality signal.
.opencode/skills/system-spec-kit/mcp_server/lib/scoring/composite-scoring.ts:482:      'checklist': ['checklist', 'verify', 'check', 'qa', 'quality'],
.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-representation.ts:127:  // No gaps — nothing to promote.
.opencode/skills/system-spec-kit/mcp_server/lib/search/channel-representation.ts:145:    // Find the highest-scoring result that meets the quality floor.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:20://     "label": "good" | "weak" | "gap"
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:41:// Margin thresholds (gap between top score and next score, 0–1 scale)
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:63:export type RequestQualityLabel = 'good' | 'weak' | 'gap';
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:87:/** Request-level quality assessment (one per search call). */
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:170: * more likely to be a high-quality, well-structured memory.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:191:  const gap = score - nextScore;
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:192:  return Math.max(0, gap);
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:284: * Compute request-level quality assessment based on the overall result set.
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:288: * - "gap":   no results, or all results have low confidence
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:298:    return { requestQuality: { label: 'gap' } };
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:307:  const qualityRatio = highOrMediumCount / results.length;
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:309:  if (topScore >= HIGH_THRESHOLD && qualityRatio >= 0.6) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:312:  if (results.length > 0 && (topScore >= LOW_THRESHOLD || qualityRatio >= 0.3)) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:315:  return { requestQuality: { label: 'gap' } };
.opencode/skills/system-spec-kit/mcp_server/lib/search/progressive-disclosure.ts:7:// 1. Summary layer — compact digest of result quality distribution
.opencode/skills/system-spec-kit/mcp_server/lib/search/progressive-disclosure.ts:31:/** Compact digest of result quality distribution. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/progressive-disclosure.ts:238: * Produces a compact digest of result quality distribution.
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts:493: * and the document is considered "high-value" (qualityScore >= threshold).
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts:498: * @param options    - Optional override for quality threshold.
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts:505:  options?: { qualityScore?: number; llmBackfillThreshold?: number },
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts:594:      const qualityScore = options?.qualityScore ?? 0;
.opencode/skills/system-spec-kit/mcp_server/lib/search/graph-lifecycle.ts:596:      if (qualityScore >= threshold) {
.opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:230:        "tags": ["preflight", "scores", "baseline", "gaps"],
.opencode/skills/system-spec-kit/mcp_server/lib/routing/routing-prototypes.json:240:        "chunk": "postflight knowledgeScore 88; uncertaintyScore 24; contextScore 84; gapsClosed routing overlap confirmed, schema blocker isolated; newGapsDiscovered prototype confusion tests still needed; learningIndex 0.74. The structure is score-heavy and field-heavy."
.opencode/skills/system-spec-kit/mcp_server/lib/scoring/README.md:120:- Decay triggered by event gaps rather than wall-clock time
.opencode/skills/system-spec-kit/mcp_server/hooks/claude/compact-inject.ts:6:// using the 3-source merge pipeline (Memory, Code Graph, CocoIndex)
.opencode/skills/system-spec-kit/mcp_server/hooks/claude/compact-inject.ts:151:  // Hint for AI to use CocoIndex for semantic neighbors after recovery
.opencode/skills/system-spec-kit/mcp_server/hooks/claude/compact-inject.ts:153:    sections.push('## Semantic Context (CocoIndex)\nUse `mcp__cocoindex_code__search` to find semantic neighbors of active files listed above.');
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:34:// 9.  Validation metadata     — spec quality signals enrichment + quality scoring
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:115:  qualityScore?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:223: * Uses quality metadata extracted from spec artifacts to apply a bounded
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:235:    const quality = typeof metadata.qualityScore === 'number' && Number.isFinite(metadata.qualityScore)
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:236:      ? Math.max(0, Math.min(1, metadata.qualityScore))
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:239:    const qualityFactor = 0.9 + (quality * 0.2); // [0.9, 1.1]
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:251:    const multiplier = clampMultiplier(qualityFactor + specLevelBonus + completionBonus + checklistBonus);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:946: *   9.  Validation metadata (spec quality signals + quality scoring)
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:970:    qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:1291:            return typeof vm?.qualityScore === 'number' ? vm.qualityScore : undefined;
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:17:/** Absolute minimum score; any top score below this triggers a gap. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:31: * Result of a Transparent Reasoning Module evidence-gap check.
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:36:  gapDetected: boolean;
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:96: * @returns GraphCoverageResult with early-gap flag and connected node count.
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:144: * Detect evidence gaps in an RRF score distribution.
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:146: * A gap is detected when either:
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:152: * @returns TRMResult with gap flag, Z-score, mean, and standard deviation.
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:156:    return { gapDetected: true, zScore: 0, mean: 0, stdDev: 0 };
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:161:    return { gapDetected: true, zScore: 0, mean: 0, stdDev: 0 };
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:168:      gapDetected: score < MIN_ABSOLUTE_SCORE,
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:182:    return { gapDetected: true, zScore: 0, mean: 0, stdDev: 0 };
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:189:  // Only flag a gap if the uniform score is below the absolute threshold.
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:190:  const gapDetected = stdDev === 0
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:194:  return { gapDetected, zScore, mean, stdDev };
.opencode/skills/system-spec-kit/mcp_server/lib/search/evidence-gap-detector.ts:198: * Format an evidence-gap warning for MCP markdown output.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:31://     - All rows pass qualityThreshold (if set) and tier/contextType filters
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:51:import { computeBackfillQualityScore } from '../../validation/save-quality-gate.js';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:92: * Filter results by a minimum quality score threshold.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:96: * - Rows with a missing or non-finite `quality_score` are treated as 0.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:99: * @param threshold - Minimum quality score in [0, 1] (inclusive).
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:113:    const rawScore = row.quality_score as number | undefined;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:122:    if (row.quality_score !== 0 && row.quality_score != null) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:128:      quality_score: computeBackfillQualityScore(row),
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:233:  const qualityFlags = readQualityFlags(row.quality_flags ?? row.qualityFlags);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:234:  return qualityFlags.includes(GRAPH_METADATA_MIGRATED_QUALITY_FLAG);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:530: * enabled, followed by constitutional injection, quality filtering, and
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:561:    qualityThreshold,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1137:  candidates = filterByMinQualityScore(candidates, qualityThreshold);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1197:              rows = filterByMinQualityScore(rows, qualityThreshold);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1247:        // H11 FIX: Apply the same tier/context/quality filters as main candidates
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1255:        newHydeCandidates = filterByMinQualityScore(newHydeCandidates, qualityThreshold);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1303:                `SELECT id, title, spec_folder, file_path, importance_tier, importance_weight, quality_score, created_at, context_type, tenant_id, user_id, agent_id, session_id FROM memory_index WHERE id IN (${placeholders})`
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1332:            // Apply the same quality threshold that other candidates go through
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1334:            const filteredSummaryHits = filterByMinQualityScore(backfilledSummaryHits, qualityThreshold);
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:59:    'idx_quality_score',
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:405:// Added memory_type column for type-specific half-lives (REQ-002)
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:415:// V15: Add quality_score and quality_flags columns for memory quality gates
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:512:      // V4 -> v5: Add memory_type column for type-specific half-lives (REQ-002, T006)
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:837:        database.exec('ALTER TABLE memory_index ADD COLUMN quality_score REAL DEFAULT 0');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:838:        logger.info('Migration v15: Added quality_score column');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:841:          console.warn('[VectorIndex] Migration v15 warning (quality_score):', get_error_message(e));
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:846:        database.exec('ALTER TABLE memory_index ADD COLUMN quality_flags TEXT');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:847:        logger.info('Migration v15: Added quality_flags column');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:850:          console.warn('[VectorIndex] Migration v15 warning (quality_flags):', get_error_message(e));
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:856:        'idx_quality_score',
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:857:        'CREATE INDEX IF NOT EXISTS idx_quality_score ON memory_index(quality_score)',
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:860:      logger.info('Migration v15: Created quality score index');
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:1380:      'Backward-compatibility validation detected schema gaps',
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2410:      quality_score REAL DEFAULT 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2411:      quality_flags TEXT,
.opencode/skills/system-spec-kit/mcp_server/lib/search/vector-index-schema.ts:2529:    CREATE INDEX IF NOT EXISTS idx_quality_score ON memory_index(quality_score);
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:15://   "reason": "spec_filter_too_narrow" | "low_signal_query" | "knowledge_gap",
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:26:export type RecoveryReason = 'spec_filter_too_narrow' | 'low_signal_query' | 'knowledge_gap';
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:45:  /** Whether upstream search logic detected an evidence gap for this result set. */
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:94:  // Default to knowledge_gap — the information may simply not be indexed
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:95:  return 'knowledge_gap';
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:156:    return 'save_memory'; // knowledge_gap — user may need to add context first
.opencode/skills/system-spec-kit/mcp_server/lib/search/recovery-payload.ts:159:    if (reason === 'knowledge_gap') return 'ask_user';
.opencode/skills/system-spec-kit/mcp_server/lib/routing/content-router.ts:9:import { cosineSimilarity } from '../validation/save-quality-gate.js';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:30:// 3. Apply evidence gap detection via TRM (Z-score confidence check)
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:40:import { detectEvidenceGap, formatEvidenceGapWarning } from '../evidence-gap-detector.js';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:203: * Extract the best available numeric score from a row for evidence-gap
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:227: * (TRM) evidence-gap check, attaches annotation metadata, and verifies the
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:264:  // -- Step 3: Evidence gap detection (TRM) --
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:272:    evidenceGapDetected = trm.gapDetected;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:274:    if (trm.gapDetected) {
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:277:      // Annotate each result with the gap metadata (non-score field).
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:280:        evidenceGap: { gapDetected: true, warning: evidenceGapWarning },
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:48:| `stage1-candidate-gen.ts` | Stage 1: Candidate Generation. Runs search channels (hybrid, vector, multi-concept), applies deep-mode query expansion (R6), embedding-based expansion (R12), summary embeddings (R8), constitutional memory injection, quality threshold filtering and tier/contextType filtering. |
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:51:| `stage4-filter.ts` | Stage 4: Filter + Annotate. Removes results below minimum memory state priority, enforces per-tier limits, runs TRM evidence-gap detection and attaches annotation metadata. Enforces the score immutability invariant at runtime. |
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:63:      |  search channels, constitutional injection, quality filter
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:73:      |  state filter, per-tier limits, TRM evidence gap, annotations
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:83:- Applies quality threshold and tier/contextType filters.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:100:- TRM evidence-gap detection (Z-score confidence check on score distribution).
.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts:387:        // Detects per-folder description edits (CHK-024 / REQ-008).
.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts:797:  // Equality check covers the case where folderPath IS basePath; path.sep boundary
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2b-enrichment.ts:20: * Step 9: Validation metadata — spec quality signals enrichment
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2b-enrichment.ts:39:  // Extract spec quality signals (SPECKIT_LEVEL, quality_score,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:145:  // Fragile reference inequality check `results !== scored` (A1-P2-3)
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:615:                quality_score, created_at, context_type
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:639:      quality_score: (parentRow.quality_score as number | undefined) ?? bestChunk.quality_score,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/orchestrator.ts:106:        qualityFiltered: 0,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:7:  - "quality metrics"
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:35:The telemetry module provides structured observability for the retrieval pipeline and scoring subsystem. It records per-stage latency, search mode selection, fallback triggers, composite quality scores, scoring observation samples, trace payload validation, and agent consumption events. Telemetry data flows to governance tooling and is used by retrieval handlers to surface pipeline health metrics.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:55:| **QualityMetrics** | Composite 0-1 quality proxy derived from relevance, result count, and latency |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:96:| `SPECKIT_EXTENDED_TELEMETRY` | `false` | Enable extended metric collection (latency breakdown, quality scoring, trace payload validation, and architecture updates). Set to `true` to activate |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:107:When `SPECKIT_EXTENDED_TELEMETRY` is disabled (default), the minimal `RetrievalTelemetry` shell is still created so callers can rely on a stable shape. Latency, mode, fallback, quality, graph-health, and adaptive sub-metrics remain zeroed/empty, while the baseline architecture snapshot still records the current memory-roadmap phase/capability defaults.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:120:| `quality` | `QualityMetrics` | Composite quality assessment |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:164:**Purpose**: Composite quality score for the retrieval run.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:173:| `qualityProxyScore` | `number` | Composite quality proxy score (0-1) |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:179:| 0.80-1.00 | High quality |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:259:| `caveat` | `string \| undefined` | Optional caveat when forecast quality is limited or unavailable |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:365:const quality: QualityMetrics = {
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:371:  qualityProxyScore: 0.87,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:380:  quality,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:390:  // Collect full latency breakdown and quality score
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:392:  telemetry.quality = computeQualityScore(results, requestedLimit, telemetry.latency.totalLatencyMs);
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:444:| Check `fallback.fallbackTriggered` to gate quality alerts | Governance / SLO monitoring |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:445:| Use `quality.qualityProxyScore < 0.6` to log degraded-run warnings | Observability dashboards |
.opencode/skills/system-spec-kit/mcp_server/lib/eval/edge-density.ts:204:    '              first, as they contribute most to retrieval quality.',
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:9:// Contribution to retrieval quality.
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:636:        let queriesChannelHelped = 0;   // ablated < baseline (removing channel decreased quality — channel was helpful)
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:637:        let queriesChannelHurt = 0;    // ablated > baseline (removing channel increased quality — channel was harmful)
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:657:        // QueriesChannelHelped = channel was helping (removing it hurt quality)
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:658:        // QueriesChannelHurt = channel was harmful (removing it helped quality)
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:977:    // Removing the channel hurt quality — channel is valuable
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ablation-framework.ts:982:    // Removing the channel helped quality — channel may be harmful
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:40:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:41:  quality_flags?: string | string[] | null;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:42:  qualityFlags?: string | string[] | null;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:109:  quality_score?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:112:  evidenceGap?: { gapDetected: boolean; warning?: string };
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:139:  qualityThreshold?: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:256:    qualityFiltered: number;
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/chunk-thinning.ts:5:// Applies a thinning threshold to drop low-quality chunks.
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:3:description: "Anchor-aware chunking and quality-based thinning for large markdown documents. Splits content at ANCHOR tag boundaries or markdown structure, then scores and filters chunks before indexing."
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:13:> Anchor-aware chunking and quality-based thinning for large markdown documents. Splits content at ANCHOR tag boundaries or markdown structure, then scores and filters chunks before indexing.
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:39:- **Chunk thinning** scores each chunk on anchor presence (60% weight) and content density (40% weight), then drops chunks below a quality threshold. At least one chunk is always retained.
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:49:| Anchor weight 0.6 vs density 0.4 | Author-placed anchors are a stronger quality signal than computed density metrics. |
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:70:| `chunk-thinning.ts` | Scores chunks using a weighted composite of anchor presence and content density, then applies a configurable threshold (default 0.3) to filter low-quality chunks before indexing. Always retains at least one chunk. |
.opencode/skills/system-spec-kit/mcp_server/lib/chunking/README.md:83:| `scoreChunk` | chunk-thinning.ts | Function | Computes composite quality score for a single chunk |
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/consumption-logger.ts:297:        description: 'Queries repeated more than 3 times — may indicate missing context or poor result quality',
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/consumption-logger.ts:325:        description: 'Queries that returned 0 results — gaps in memory coverage',
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:3:description: "Evaluation, logging, baselines, quality proxies, ablation, and reporting for the spec-doc record retrieval pipeline."
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:8:  - "quality proxy"
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:25:`lib/eval/` contains the measurement stack for retrieval quality, eval logging, baseline comparisons, and reporting. The directory currently has 14 TypeScript modules plus the static `data/ground-truth.json` fixture.
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:30:- Metric computation and quality proxy scoring.
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:47:| `eval-quality-proxy.ts` | Pure quality proxy formula for latency/result quality tradeoff scoring |
.opencode/skills/system-spec-kit/mcp_server/lib/eval/README.md:61:- `eval-quality-proxy.ts` is a pure calculation module with no DB writes, making it safe for inline quality scoring and tests.
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:5:// Automated quality proxy metric that correlates with manual
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:32:/** Input parameters for the quality proxy computation. */
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:80:/** Result of the quality proxy computation. */
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:82:  /** Composite quality score in [0, 1]. */
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:86:  /** Human-readable quality tier: 'excellent' | 'good' | 'acceptable' | 'poor'. */
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-quality-proxy.ts:151: * Compute the quality proxy score for a single search result set.
.opencode/skills/system-spec-kit/mcp_server/lib/eval/eval-db.ts:6:// Retrieval quality metrics, ground truth, and eval results.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:5:// Captures latency, mode selection, fallback, and quality-proxy
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:14:// F6.06 fix: Import canonical quality proxy from eval module
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:15:import { computeQualityProxy as computeQualityProxyCanonical } from '../eval/eval-quality-proxy.js';
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:41:/** Maximum latency value (ms) for quality proxy normalization.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:42: *  Latencies at or above this ceiling map to a 0.0 quality score component. */
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:83:  qualityProxyScore: number; // 0-1
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:163:  quality: QualityMetrics;
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:201:    quality: {
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:207:      qualityProxyScore: 0,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:282:  t.quality.resultCount = count;
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:283:  t.quality.extractionCountInSession = Math.max(0, extractionCount || 0);
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:292:    t.quality.topResultScore = scores.reduce((a, b) => Math.max(a, b), -Infinity);
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:293:    t.quality.avgRelevanceScore = scores.reduce((sum, s) => sum + s, 0) / count;
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:296:  t.quality.boostImpactDelta = Number.isFinite(boostDelta) ? boostDelta : 0;
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:297:  t.quality.qualityProxyScore = computeQualityProxy(t);
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:477: * Compute a 0-1 quality proxy score from the telemetry record.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:479: * F6.06 fix: Delegates to the canonical eval-quality-proxy implementation
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:485:    avgRelevance: Math.max(0, Math.min(1, t.quality.avgRelevanceScore)),
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:486:    topResultRelevance: Math.max(0, Math.min(1, t.quality.topResultScore)),
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:487:    resultCount: t.quality.resultCount,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:663:    quality: {
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:664:      resultCount: t.quality.resultCount,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:665:      avgRelevanceScore: t.quality.avgRelevanceScore,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:666:      topResultScore: t.quality.topResultScore,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:667:      boostImpactDelta: t.quality.boostImpactDelta,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:668:      extractionCountInSession: t.quality.extractionCountInSession,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/retrieval-telemetry.ts:669:      qualityProxyScore: t.quality.qualityProxyScore,
.opencode/skills/system-spec-kit/mcp_server/lib/eval/data/ground-truth.json:60:      "expectedResultDescription": "Should surface sprint-0 baseline measurement (T000a) which records graphHitRate=0, and any related spec memories about graph channel initialization or telemetry gaps.",
.opencode/skills/system-spec-kit/mcp_server/lib/eval/data/ground-truth.json:125:      "query": "what is the current test coverage gap for the eval logging system",
.opencode/skills/system-spec-kit/mcp_server/lib/eval/data/ground-truth.json:130:      "expectedResultDescription": "Should surface T000a baseline (19 skipped tests, deferred DB fixture tests) and T005 eval-logger.ts module. May surface spec tasks.md identifying coverage gaps.",
.opencode/skills/system-spec-kit/mcp_server/lib/eval/data/ground-truth.json:170:      "expectedResultDescription": "Should return NO relevant results. This codebase has no Python code, no billing module, and no pytest setup. A high-quality retrieval system returns empty or near-empty results.",

exec
/bin/zsh -lc 'rg -n "function discoverSpecFolder|export function discoverSpecFolder|threshold|score|similarity|confidence" .opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts | head -120' in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
309:function discoverSpecFolders(basePath: string): DiscoveredSpecFolder[] {
538: * - Normalize score: matchCount / totalQueryTerms
539: * - Return top `limit` folders with score > 0, sorted descending
546: * @returns Array of { specFolder, relevanceScore } sorted by score desc.
1098: * Orchestrates: ensureCache → findRelevantFolders → threshold check.
1102: * @param threshold - Minimum relevance score to accept (default 0.3).
1103: * @returns The best-matching specFolder path, or null if none meets threshold.
1105:export function discoverSpecFolder(
1108:  threshold = 0.3,
1118:    if (best.relevanceScore < threshold) return null;

exec
/bin/zsh -lc "rg -n \"QUALITY=gap|quality:\\s*'gap'|quality\\\"|evidenceGap|fallback_tier|fallbackTriggered|fallback\" .opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline .opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:109:// Feature catalog: Quality-aware 3-tier search fallback
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:145:  contentSource?: 'reassembled_chunks' | 'file_read_fallback';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:340:  /** Phase B T019: Dual-level retrieval — 'local' (entity), 'global' (community), 'auto' (local + fallback). */
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:492:  if (typeof data.fallbackState !== 'string' && snapshot) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:493:    data.fallbackState = snapshot.fallbackState;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:801:    if (classification.fallback) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:802:      console.error(`[memory-search] Intent auto-detected as '${detectedIntent}' (fallback: ${classification.reason})`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:835:  // Re-run artifact routing with detected intent for fallback coverage
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:952:    // Phase B T018/T019: Community search fallback — inject community members on weak results
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:998:          console.warn(`[memory-search] Community search fallback failed (fail-open): ${msg}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1057:        `[memory-search] Lexical capability path '${lexicalCapability.lexicalPath}' (fallbackState: ${lexicalCapability.fallbackState})`
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1070:      extraData.fallbackState = lexicalCapability.fallbackState;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1073:    if (pipelineResult.annotations.evidenceGapWarning) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1074:      extraData.evidenceGapWarning = pipelineResult.annotations.evidenceGapWarning;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1168:    if (pipelineResult.annotations.evidenceGapWarning && formatted?.content?.[0]?.text) {
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:1172:          parsed.summary = `${pipelineResult.annotations.evidenceGapWarning}\n\n${parsed.summary}`;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:268:  const fallbackScores: Record<string, number> = {};
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:270:    fallbackScores[source] = resolvedScore;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:272:  return fallbackScores;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:983:            addTraceEntry(trace, 'fallback', 0, candidates.length, 0, {
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage1-candidate-gen.ts:1400:              // Using the canonical fallback chain prevents overwriting
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/orchestrator.ts:62:  // -- Stage 1: Candidate Generation (MANDATORY — no fallback possible) --
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/orchestrator.ts:138:          fallback: 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/orchestrator.ts:169:        evidenceGapDetected: false,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:21://     - contentSource is set to 'reassembled_chunks' or 'file_read_fallback'
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:68:function resolveRerankOutputScore(raw: unknown, fallback: number): number {
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:72:  return floorScore(fallback);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:100:  fallback: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:116:type RerankProvider = 'cross-encoder' | 'local-gguf' | 'fallback-sort' | 'none';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:199:              // Use effectiveScore() for consistent fallback chain
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:269:        fallback: chunkStats.fallback,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:373:  // P1-015: Use effectiveScore() for consistent fallback chain
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:394:      (result) => result.scoringMethod === 'fallback'
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:396:      ? 'fallback-sort'
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:485:    fallback: 0,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:596: *   `contentSource: 'file_read_fallback'`.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:623:      // Parent not found in DB — use best chunk as fallback
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:624:      stats.fallback++;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:666:      `[stage3-rerank] MPAB DB reassembly failed for parent ${parentId}: ${toErrorMessage(err)} — using chunk fallback`
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:668:    stats.fallback++;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:674: * Mark a pipeline row as a chunk-content fallback.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:679: * @returns A new PipelineRow annotated as a fallback parent representation.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage3-rerank.ts:691:    contentSource: 'file_read_fallback',
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:194:        console.warn(`[stage2-fusion] learned stage2 model at ${modelPath} is invalid; shadow scoring will use manual-only fallback`);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:265: * from types.ts. The shared function uses the correct fallback chain:
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage2-fusion.ts:976:  // the same row objects, creating a race condition if the orchestrator's timeout fallback
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:265:  let evidenceGapDetected = false;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:266:  let evidenceGapWarning: string | undefined;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:272:    evidenceGapDetected = trm.gapDetected;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:275:      evidenceGapWarning = formatEvidenceGapWarning(trm);
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:280:        evidenceGap: { gapDetected: true, warning: evidenceGapWarning },
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:300:    evidenceGapWarning,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:331:        evidenceGapDetected,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:346:      evidenceGapDetected,
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:38:  contentSource?: 'reassembled_chunks' | 'file_read_fallback';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:57: * Shared score resolution function — canonical fallback chain for deriving the
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:62: * separate implementations with different fallback orders and clamping. This shared
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:107:  contentSource?: 'reassembled_chunks' | 'file_read_fallback';
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:112:  evidenceGap?: { gapDetected: boolean; warning?: string };
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:282:      fallback: number;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:312:    evidenceGapDetected: boolean;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/types.ts:316:    evidenceGapWarning?: string;
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:98:- Memory state priority filtering, with the coldest retained-history rows treated as fallback evidence only.
.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/README.md:110:4. **Score Resolution Consistency.** All stages use the shared `resolveEffectiveScore()` function from `types.ts` with fallback chain: `intentAdjustedScore` > `rrfScore` > `score` > `similarity/100`, clamped to [0, 1].

exec
/bin/zsh -lc 'rg -n "memory_causal_stats|handle.*Causal|causalStats|by_relation|meetsTarget|targetCoverage|currentCoverage|health" .opencode/skills/system-spec-kit/mcp_server' in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:808:  // 'error' recommends memory_health because structural context is
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:817:        snap.graphFreshness === 'error' ? 'call memory_health (structural context unavailable)' :
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:830:  // resume, health, and code_graph_query (ready | stale | absent |
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:840:  lines.push('- If "unavailable" (DB unreachable / readiness probe failed): call memory_health for repair guidance instead of code_graph_query');
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:846:  // recommend memory_health because the database probe failed.
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:859:      routingRules.push('Structural queries → unavailable: call memory_health to diagnose (graph readiness unavailable)');
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:935:    // T018: Track last tool call timestamp for all tools except session_health.
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:936:    if (name !== 'session_health') {
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:1028:    if (name !== 'memory_search' && name !== 'memory_context' && name !== 'memory_quick_search' && name !== 'session_health') {
.opencode/skills/system-spec-kit/mcp_server/context-server.ts:1898:    console.error('[context-server] Startup health: memory_index=%d, active_memory_projection=%d', memoryCount, projectionCount);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/handlers/advisor-status.ts:133:    // `freshness` see artifact health independent of daemon availability.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:61:  readonly key: 'advisor-hook-health';
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:356:/** Build the rolling health section shown in advisor observability output. */
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:364:    key: 'advisor-hook-health',
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:446:/** Small in-memory collector for advisor hook metrics and health snapshots. */
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/lib/metrics.ts:466:  healthSection(): AdvisorHookHealthSection {
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-snapshot.ts:27:  sessionQuality: 'healthy' | 'degraded' | 'critical' | 'unknown';
.opencode/skills/system-spec-kit/mcp_server/lib/session/session-snapshot.ts:43:  sourceSurface: 'auto-prime' | 'session_bootstrap' | 'session_resume' | 'session_health';
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/README.md:13:| `status.ts` | `code_graph_status` | Probe freshness plus totals, persistence metadata, parse health, readiness/trust fields, and `graphQualitySummary` so operators can inspect graph provenance instead of relying on counts alone |
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_runtime.py:240:    degraded state instead of assuming a healthy cache.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_runtime.py:273:    """Expose cache diagnostics for health output."""
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_runtime.py:282:        "healthy": cached and len(skipped) == 0,
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_runtime.py:297:    R42-002 flagged that `health_check()` previously returned ``ok`` even when
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor_runtime.py:307:    both inputs and returns a structured parity report that ``health_check``
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:26:export type QualityLevel = 'healthy' | 'degraded' | 'critical';
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:200: * session-health.ts should use this instead of the memory-surface duplicate.
.opencode/skills/system-spec-kit/mcp_server/lib/session/context-metrics.ts:241:  if (score > 0.7) level = 'healthy';
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/init-skill-graph.sh:6:# report the current advisor health from the repository root.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/init-skill-graph.sh:59:log_step "Running advisor health check"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/init-skill-graph.sh:60:run_from_repo python3 .opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py --health
.opencode/skills/system-spec-kit/mcp_server/code_graph/handlers/status.ts:4:// MCP tool handler for code_graph_status — reports graph health.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/06--mcp-surface/02-advisor-status.md:25:Give operators and runtimes a single read that summarizes whether advisor state is healthy enough to trust for routing.
.opencode/skills/system-spec-kit/mcp_server/README.md:192:After connecting your MCP client, call the health check:
.opencode/skills/system-spec-kit/mcp_server/README.md:196:  "tool": "memory_health",
.opencode/skills/system-spec-kit/mcp_server/README.md:560:**Startup/recovery surfaces:** `session_resume`, `session_bootstrap`, and the startup brief report freshness-aware graph status instead of count-only health. Startup surfaces are intentionally non-mutating snapshots, so later structural reads may still differ if repo state changes.
.opencode/skills/system-spec-kit/mcp_server/README.md:655:Resume session with combined memory, code graph and CocoIndex status in a single call. Use when you want the detailed merged resume payload directly. The response carries freshness-aware code-graph status (`fresh`, `stale`, `empty`, `error`) instead of count-only health. Session-resume auth binds `args.sessionId` to the transport caller context from `lib/context/caller-context.ts`; mismatches are rejected by default, with `MCP_SESSION_RESUME_AUTH_MODE=permissive` available for canary rollout. For the canonical first-call recovery path on session start or after `/clear`, prefer `session_bootstrap`, and for operator-facing packet recovery prefer `/spec_kit:resume`, which reconstructs context from `handover.md`, then `_memory.continuity`, then packet docs.
.opencode/skills/system-spec-kit/mcp_server/README.md:666:Complete session bootstrap in one call. This is the canonical first-call recovery step on session start or after `/clear`. It wraps the full `session_resume` payload plus `session_health` and returns context, health, structural readiness and recommended next actions. Startup/bootstrap surfaces are freshness-aware but non-mutating; use `code_graph_scan` when readiness shows an empty or broad full-scan state. In packet workflows, `/spec_kit:resume` sits above this tool as the operator-facing recovery surface.
.opencode/skills/system-spec-kit/mcp_server/README.md:814:##### `memory_health`
.opencode/skills/system-spec-kit/mcp_server/README.md:816:Run a health check. This is the diagnostic tool for when search quality degrades or something feels off. It checks for stale indexes, divergent aliases, broken embeddings and other issues. It can also attempt automatic repairs.
.opencode/skills/system-spec-kit/mcp_server/README.md:828:##### `session_health`
.opencode/skills/system-spec-kit/mcp_server/README.md:834:| _(none required)_ |  | Returns health status with hints |
.opencode/skills/system-spec-kit/mcp_server/README.md:1006:##### `memory_causal_stats`
.opencode/skills/system-spec-kit/mcp_server/README.md:1167:Report code graph index health: file count, node and edge counts by type, parse health summary, last scan timestamp, DB file size, schema version, readiness/trust fields for the current freshness probe, and `graphQualitySummary` so operators can inspect detector provenance plus edge-enrichment confidence instead of relying on counts alone.
.opencode/skills/system-spec-kit/mcp_server/README.md:1171:| _(none required)_ |  | Returns health report |
.opencode/skills/system-spec-kit/mcp_server/README.md:1194:| _(none required)_ |  | Returns CocoIndex health |
.opencode/skills/system-spec-kit/mcp_server/README.md:1282:| L3 | Discovery | 4 | 800 | Browse what is stored, check system health |
.opencode/skills/system-spec-kit/mcp_server/README.md:1530:| Diagnose search problems | `memory_health` | Set `reportMode: "full"` |
.opencode/skills/system-spec-kit/mcp_server/README.md:1548:**Fix**: Run a health check with auto-repair, then retry with a higher quality floor:
.opencode/skills/system-spec-kit/mcp_server/README.md:1551:{ "tool": "memory_health", "arguments": { "reportMode": "full", "autoRepair": true } }
.opencode/skills/system-spec-kit/mcp_server/README.md:1650:{ "tool": "memory_health", "arguments": { "reportMode": "divergent_aliases", "limit": 20 } }
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-types.ts:50:/** Arguments for the memory_health handler. */
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-types.ts:64:  healthy?: boolean;
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:16:    --health      Run health check diagnostics
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:477:    """Record malformed source metadata so health checks cannot look green."""
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:484:def _source_metadata_health() -> Dict[str, Any]:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:495:        "healthy": len(issues) == 0,
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2972:def health_check() -> Dict[str, Any]:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2981:    source_metadata = _source_metadata_health()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:2999:    # downgrades health to `degraded` even when both sources loaded cleanly.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3012:        or not bool(cache_status.get("healthy"))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3013:        or not bool(source_metadata.get("healthy"))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3141:  python skill_advisor.py --health
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3159:    parser.add_argument('--health', action='store_true',
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3160:                        help='Run health check diagnostics')
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3195:    if args.health:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3197:        health = health_check()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3198:        health["cocoindex_available"] = cocoindex_binary is not None
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3199:        health["cocoindex_binary"] = cocoindex_binary or ""
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_advisor.py:3200:        print(json.dumps(health, indent=2))
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:110:// T018: Session-level tracking for prime package and session_health
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:220:      WHERE parse_health = 'error' OR parse_health = 'recovered'
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:680:  // T018: Session tracking for session_health tool
.opencode/skills/system-spec-kit/mcp_server/hooks/memory-surface.ts:689:// T018: Export types for session-health handler
.opencode/skills/system-spec-kit/mcp_server/hooks/index.ts:12:  // T018: Session tracking for session_health tool
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:593:  memory_health: memoryHealthSchema as unknown as ToolInputSchema,
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:606:  memory_causal_stats: memoryCausalStatsSchema as unknown as ToolInputSchema,
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:637:  session_health: getSchema({}) as unknown as ToolInputSchema,
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:653:  memory_health: ['reportMode', 'limit', 'specFolder', 'autoRepair', 'confirmed'],
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:666:  memory_causal_stats: [],
.opencode/skills/system-spec-kit/mcp_server/schemas/tool-input-schemas.ts:695:  session_health: [],
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_graph_compiler.py:909:            (``health_check()``) can detect degraded topology state without
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_graph_compiler.py:999:    # Normalize and embed topology warnings so that `health_check()` can
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/scripts/skill_graph_compiler.py:1105:    # downstream `health_check()` consumers can report degraded state without
.opencode/skills/system-spec-kit/mcp_server/lib/context/opencode-transport.ts:201:  healthPayload?: SharedPayloadEnvelope | null;
.opencode/skills/system-spec-kit/mcp_server/lib/context/opencode-transport.ts:210:    args.healthPayload?.kind,
.opencode/skills/system-spec-kit/mcp_server/lib/context/opencode-transport.ts:215:  const messagePayloads = [args.resumePayload, args.healthPayload].filter(
.opencode/skills/system-spec-kit/mcp_server/lib/context/opencode-transport.ts:268:            compactionPayload.kind === 'health' ? null : args.graphOps,
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud.ts:9:import { handleMemoryHealth } from './memory-crud-health.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud.ts:14:// Feature catalog: Health diagnostics (memory_health)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud.ts:36:const handle_memory_health = handleMemoryHealth;
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud.ts:45:  handle_memory_health,
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/INSTALL_GUIDE.md:151:Use `advisor_status` as the prompt-safe health source:
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/01--daemon-and-freshness/03-lifecycle.md:3:description: "Daemon boot, shutdown, SIGTERM handling, and health reporting that make daemon state observable without coupling readers to writer state."
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/01--daemon-and-freshness/03-lifecycle.md:8:  - "daemon health"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/01--daemon-and-freshness/03-lifecycle.md:25:Give operators a predictable daemon lifecycle: graceful boot, graceful SIGTERM shutdown, and always-available health reporting exposed through `advisor_status`.
.opencode/skills/system-spec-kit/mcp_server/lib/coverage-graph/README.md:17:- `coverage-graph-signals.ts` - convergence and graph-health metrics.
.opencode/skills/system-spec-kit/mcp_server/lib/context/shared-payload.ts:14:  'health',
.opencode/skills/system-spec-kit/mcp_server/lib/context/shared-payload.ts:261:  'session_health',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:240:  name: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:241:  description: '[L3:Discovery] Check health status of the indexed-continuity store. Token Budget: 800.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:266:        description: 'When true in full mode, attempts best-effort repair actions for detected health issues (e.g., FTS rebuild).'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:271:        description: 'Required with autoRepair:true to execute repair actions. When false or omitted, the indexed-continuity health check returns a confirmation-only response.'
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:429:  name: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:594:  description: '[L7:Maintenance] Report code graph index health. Returns totalFiles, totalNodes, totalEdges, freshness, readiness, canonicalReadiness, trustState, lastScanAt, lastPersistedAt, lastGitHead, dbFileSize, schemaVersion, nodesByKind, edgesByType, parseHealth, and graphQualitySummary. Token Budget: 500.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:706:  description: '[L7:Maintenance] Report skill graph health. Returns totalSkills, totalEdges, lastIndexedAt, families, categories, schemaVersions, staleness, validation, and dbStatus from the live SQLite graph. Token Budget: 500.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:749:// T018: Session health diagnostic tool
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:751:  name: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:775:  description: '[L1:Orchestration] Complete session bootstrap in one call. Returns session context, system health, structural readiness, and recommended next actions. This is the canonical first recovery call on session start or after /clear; it wraps the full session_resume payload plus session_health.',
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:788:      health: { type: 'object', description: 'session_health payload (system status, database health, MCP connectivity)' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:791:      nextActions: { type: 'array', items: { type: 'string' }, description: 'Up to 3 recommended next actions derived from resume, health, and structural status' },
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:793:    required: ['resume', 'health', 'hints', 'nextActions'],
.opencode/skills/system-spec-kit/mcp_server/tool-schemas.ts:864:  description: '[L9:CoverageGraph] Report deep-loop coverage graph health. Returns totalNodes, totalEdges, nodesByKind, edgesByRelation, lastIteration, schemaVersion, dbFileSize, signals, and momentum for the requested session-scoped subgraph. Suitable for dashboards and synthesis surfaces.',
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:438:- `code_graph_status` (graph health check)
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:440:- `session_health` (session readiness check)
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:446:- `advisor_status` (daemon freshness and trust-state health)
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:671:`memory_stats()` returns counts, dates and top-ranked folders for the indexed-continuity store. Use it to confirm indexing is working and to inspect database health.
.opencode/skills/system-spec-kit/mcp_server/INSTALL_GUIDE.md:995:Use `code_graph_status` as the quickest operator probe for structural health. Expect `freshness`, `readiness`, `canonicalReadiness`, `trustState`, `parseHealth`, and `graphQualitySummary` in the response when the graph has persisted scan metadata.
.opencode/skills/system-spec-kit/mcp_server/lib/providers/retry-manager.ts:36:/** In-memory-only snapshot of embedding retry health — no DB access. */
.opencode/skills/system-spec-kit/mcp_server/lib/providers/retry-manager.ts:537: * Return a lightweight in-memory snapshot of embedding retry health.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/feature_catalog/feature_catalog.md:65:| Daemon lifecycle and health | [01--daemon-and-freshness/03-lifecycle.md](./01--daemon-and-freshness/03-lifecycle.md) |
.opencode/skills/system-spec-kit/mcp_server/lib/providers/README.md:121:| `getEmbeddingRetryStats` | `() => EmbeddingRetryStats` | Get a lightweight in-memory retry health snapshot without DB access |
.opencode/skills/system-spec-kit/mcp_server/lib/providers/README.md:137:| `EmbeddingRetryStats` | In-memory retry health snapshot returned by `getEmbeddingRetryStats()`, including pending/failed counts, retry attempts, circuit-breaker state, last run and queue depth |
.opencode/skills/system-spec-kit/mcp_server/lib/providers/README.md:191:| Check queue stats | `getRetryStats()` | Monitor health |
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-search.vitest.ts:170:  it('P010-T2: handleMemorySearch returns lexicalPath and fallbackState on cached healthy responses', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-search.vitest.ts:188:    const response = await handler.handleMemorySearch({ query: 'healthy query' });
.opencode/skills/system-spec-kit/mcp_server/handlers/save/atomic-index-memory.ts:266:      'Retry memory_save({ filePath, force: true }) once dependencies are healthy',
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/10--python-compat/005-bench-runner.md:66:| Bench hangs | No output after expected runtime | Check daemon health per AU-003 and OP-003. |
.opencode/skills/system-spec-kit/mcp_server/lib/architecture/layer-definitions.ts:67:    useCase: 'Explore available memories, check system health, view statistics.',
.opencode/skills/system-spec-kit/mcp_server/lib/architecture/layer-definitions.ts:68:    tools: ['memory_list', 'memory_stats', 'memory_health', 'session_health']
.opencode/skills/system-spec-kit/mcp_server/lib/architecture/layer-definitions.ts:98:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:44:import { handleSessionHealth } from '../handlers/session-health.js';
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:69:    sourceSurface: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:72:      sourceSurface: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:101:    level: 'healthy',
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:121:describe('session-health handler', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:122:  it('attaches live trust metadata to health sections and keeps shared payload structural trust', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:125:    const sessionSection = getSection(parsed, 'session-health');
.opencode/skills/system-spec-kit/mcp_server/tests/session-health.vitest.ts:164:    expect(getSection(parsed, 'session-health')?.structuralTrust).toEqual({
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/startup-brief.ts:116:      'healthy',
.opencode/skills/system-spec-kit/mcp_server/lib/architecture/README.md:51:| L3 | Discovery | 800 | Browse and explore (list, stats, health) |
.opencode/skills/system-spec-kit/mcp_server/handlers/save/README.md:41:| `dedup.ts`                  | Pre-save deduplication. `checkExistingRow` matches by file path but returns `unchanged` only for healthy rows (`success`, `pending`, `partial`); `checkContentHashDedup` matches by content hash and accepts chunked parents only when their status is valid `partial`. |
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:281: * Return current graph channel metrics for health check reporting.
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2160: *   → Pass if quality signal is healthy AND count >= 3
.opencode/skills/system-spec-kit/mcp_server/lib/search/hybrid-search.ts:2164: *   → Pass if quality signal is healthy AND count >= 3
.opencode/skills/system-spec-kit/mcp_server/lib/search/confidence-scoring.ts:286: * - "good":  most results have high/medium confidence and a healthy top score
.opencode/skills/system-spec-kit/mcp_server/lib/errors/core.ts:64:  memory_causal_stats: ERROR_CODES.CAUSAL_GRAPH_ERROR,
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ground-truth-feedback.ts:99:  meetsTarget: boolean;
.opencode/skills/system-spec-kit/mcp_server/lib/eval/ground-truth-feedback.ts:495:    meetsTarget: exactAgreementRate >= targetRate,
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/05--auto-update-daemon/003-daemon-lifecycle-shutdown.md:3:description: "Manual validation that daemon boot, health reporting, and SIGTERM shutdown behave as documented in lib/daemon/lifecycle.ts."
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/05--auto-update-daemon/003-daemon-lifecycle-shutdown.md:8:  - "daemon health"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/manual_testing_playbook/05--auto-update-daemon/003-daemon-lifecycle-shutdown.md:26:Validate graceful boot, health reporting, and SIGTERM-based shutdown for the advisor daemon in `lib/daemon/lifecycle.ts`.
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:237:      expect(result.meetsTarget).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:255:      expect(result.meetsTarget).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:279:      expect(result.meetsTarget).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:302:      expect(result.meetsTarget).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:353:      expect(result.meetsTarget).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:368:      expect(result50.meetsTarget).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/ground-truth-feedback.vitest.ts:372:      expect(result80.meetsTarget).toBe(false);
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/ops-hardening.ts:31:    surface: 'memory_health';
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/ops-hardening.ts:88:      surface: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/ops-hardening.ts:100:      recommendedAction: 'Use memory_health({ autoRepair: true, confirmed: true }) for bounded repair workflows and transparent partial-success reporting.',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:138:// Default hint is "Run memory_health() for diagnostics".
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:149:      'Run memory_health() to check embedding system status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:152:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:179:      'Run memory_health() to see current provider status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:182:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:242:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:247:      'Run memory_health() to check database integrity',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:252:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:268:      'Contact support with schema version info from memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:271:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:276:      'Run memory_health() to assess damage',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:286:      'Run memory_health() to check database status',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:291:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:316:      'Use memory_health() to see current system limits'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:336:      'Check memory_health() for system status',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:340:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:345:      'Check embedding provider status with memory_health()',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:350:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:447:      'Run memory_health() to check system status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:450:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:487:      'Check memory_health() for recovery options'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:490:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:529:      'Run memory_health() to check database status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:532:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:590:      'Check memory_causal_stats() for graph status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:593:    toolTip: 'memory_causal_stats()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:628:      'Run memory_causal_stats() to inspect graph health',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:632:    toolTip: 'memory_causal_stats()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:638:      'Run memory_causal_stats() to inspect graph integrity',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:659:      'Check memory_health() for system status',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:663:    toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:677:    'Run memory_health() for diagnostics',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:682:  toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:699:        'Check embedding provider status: memory_health()',
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:734:        'Run memory_health() to verify database integrity'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:737:      toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:757:        'Check memory_health() for embedding provider status'
.opencode/skills/system-spec-kit/mcp_server/lib/errors/recovery-hints.ts:760:      toolTip: 'memory_health()'
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:63:    parse_health TEXT DEFAULT 'clean',
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:342:        file_mtime_ms = ?, parse_health = ?, indexed_at = ?, parse_duration_ms = ?
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:350:      file_path, language, content_hash, file_mtime_ms, node_count, edge_count, parse_health, indexed_at, parse_duration_ms
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:748:  const healthRows = d.prepare('SELECT parse_health, COUNT(*) as c FROM code_files GROUP BY parse_health').all() as { parse_health: string; c: number }[];
.opencode/skills/system-spec-kit/mcp_server/code_graph/lib/code-graph-db.ts:749:  for (const r of healthRows) parseHealthSummary[r.parse_health] = r.c;
.opencode/skills/system-spec-kit/mcp_server/lib/storage/README.md:67:- `incremental-index.ts` uses `file_mtime_ms`, `content_hash`, and `embedding_status` together, so unchanged-path fast paths still requeue rows whose embeddings are unhealthy.
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-error-format.vitest.ts:123:        handler: 'handleMemoryCausalLink',
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:59:| **Status diagnostics** | `code_graph_status` returns readiness, parse-health, and `graphQualitySummary` for operator-visible health checks |
.opencode/skills/system-spec-kit/mcp_server/code_graph/README.md:143:| **`code_graph_status`** | `status: "ok"` | `freshness`, `readiness`, `canonicalReadiness`, `trustState`, `parseHealth`, `graphQualitySummary` | Primary operator health probe; keeps counts plus parser/enrichment quality in one response |
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:118:  sessionQuality?: 'healthy' | 'degraded' | 'critical' | 'unknown';
.opencode/skills/system-spec-kit/mcp_server/handlers/session-resume.ts:131:  sessionQuality: 'healthy' | 'degraded' | 'critical' | 'unknown';
.opencode/skills/system-spec-kit/mcp_server/tests/startup-brief.vitest.ts:76:    expect(brief.startupSurface).toContain('- Code Graph: healthy');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:78:type SessionHealthModule = typeof import('./session-health.js');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:192:    sessionHealthModule = loadHandlerModule<SessionHealthModule>('session-health');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:258:export const handle_memory_health = lazyFunction(getMemoryCrudModule, 'handle_memory_health');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:300:export const handleMemoryDriftWhy = lazyFunction(getCausalGraphModule, 'handleMemoryDriftWhy');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:301:export const handleMemoryCausalLink = lazyFunction(getCausalGraphModule, 'handleMemoryCausalLink');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:302:export const handleMemoryCausalStats = lazyFunction(getCausalGraphModule, 'handleMemoryCausalStats');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:303:export const handleMemoryCausalUnlink = lazyFunction(getCausalGraphModule, 'handleMemoryCausalUnlink');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:304:export const handle_memory_drift_why = lazyFunction(getCausalGraphModule, 'handle_memory_drift_why');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:305:export const handle_memory_causal_link = lazyFunction(getCausalGraphModule, 'handle_memory_causal_link');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:306:export const handle_memory_causal_stats = lazyFunction(getCausalGraphModule, 'handle_memory_causal_stats');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:307:export const handle_memory_causal_unlink = lazyFunction(getCausalGraphModule, 'handle_memory_causal_unlink');
.opencode/skills/system-spec-kit/mcp_server/handlers/index.ts:313:// Session health handler
.opencode/skills/system-spec-kit/mcp_server/tests/retry-budget-telemetry.vitest.ts:157:    vi.doMock('../handlers/causal-links-processor.js', () => ({ processCausalLinks }));
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/phase-runner.test.ts:243:      phase('healthy', [], () => 'ok'),
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/phase-runner.test.ts:244:      phase('broken', ['healthy'], () => {
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:5:// + session_health in one call, merging results with hints.
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:9:import { handleSessionHealth } from './session-health.js';
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:76:  health: Record<string, unknown>;
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:164:  healthData: Record<string, unknown>,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:173:  if (healthData.error) {
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:174:    nextActions.add('Call `session_health()` directly to inspect the current health-check failure.');
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:378:  // Sub-call 2: session_health
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:379:  let healthData: Record<string, unknown> = {};
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:381:    const healthResponse = await handleSessionHealth();
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:382:    healthData = extractData(healthResponse);
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:383:    allHints.push(...extractHints(healthData));
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:386:    healthData = { error: message };
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:387:    allHints.push('session_health failed. Try calling it manually.');
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:413:  const completeness = resumeData.error || healthData.error || resumeData._extractionFailed || healthData._extractionFailed ? 'partial' : 'full';
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:417:  const healthCertainty: SharedPayloadCertainty = healthData.error ? 'unknown' : 'estimated';
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:423:  const healthPayload = coerceSharedPayloadEnvelope(healthData.payloadContract);
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:468:      key: 'health-surface',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:470:      content: summarizeUnknown(healthData),
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:472:      certainty: healthCertainty,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:494:      content: buildNextActions(resumeData, healthData, structuralContext).join(' | '),
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:505:      { label: 'health', certainty: healthCertainty },
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:516:      sourceRefs: ['session-resume', 'session-health', 'session-snapshot'],
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:530:    health: healthData,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:538:      healthPayload,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-bootstrap.ts:547:    nextActions: buildNextActions(resumeData, healthData, structuralContext),
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:12:  { tool: 'memory_health', handler: 'handleMemoryHealth', layer: 'L3' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:23:  { tool: 'memory_causal_link', handler: 'handleMemoryCausalLink', layer: 'L6' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:24:  { tool: 'memory_causal_stats', handler: 'handleMemoryCausalStats', layer: 'L6' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:25:  { tool: 'memory_causal_unlink', handler: 'handleMemoryCausalUnlink', layer: 'L6' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:38:  { camel: 'handleMemoryHealth', snake: 'handle_memory_health' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:50:  { camel: 'handleMemoryCausalLink', snake: 'handle_memory_causal_link' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:51:  { camel: 'handleMemoryCausalStats', snake: 'handle_memory_causal_stats' },
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-tool-dispatch.vitest.ts:52:  { camel: 'handleMemoryCausalUnlink', snake: 'handle_memory_causal_unlink' },
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/README.md:303:| `degraded` | Stale generation or impaired health | OP-001 playbook |
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:4:// T018: MCP tool handler for session_health — reports session
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:40:// session-health observes (it never emits 'cached'/'imported'/etc.).
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:120:/** Handle session_health tool call */
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:156:  // Phase 027: Structural bootstrap contract for health surface
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:157:  const structuralContext = buildStructuralBootstrapContract('session_health');
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:196:    kind: 'health',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:199:        key: 'session-health',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:218:    summary: `Session health is ${status}; graph freshness is ${graphFreshness}; structural status is ${structuralContext.status}`,
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:220:      producer: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:221:      sourceSurface: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:230:    sourceSurface: 'session_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/session-health.ts:237:      key: 'session-health',
.opencode/skills/system-spec-kit/mcp_server/lib/search/README.md:681:Same-path `unchanged` only applies to healthy existing rows (`success`, `pending`, `partial`), so unhealthy embedding states still re-enter indexing. Cross-path content-hash dedup accepts chunked parents only when the parent row is in valid `partial` state and ignores invalid parent rows marked `complete`.
.opencode/skills/system-spec-kit/mcp_server/code_graph/tests/code-graph-ops-hardening.vitest.ts:27:    expect(contract.doctor.surface).toBe('memory_health');
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:28:// Feature catalog: Health diagnostics (memory_health)
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:30:// Feature catalog: Memory health autoRepair metadata
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:222:/** Handle memory_health tool -- returns system health status and diagnostics. */
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:231:    console.error(`[memory-health] Database refresh failed [requestId=${requestId}]: ${message}`);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:233:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:251:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:260:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:269:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:278:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:287:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:331:      console.error(`[memory-health] Schema missing [requestId=${requestId}]:`, message);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:333:        tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:340:    console.warn(`[memory-health] Failed to get memory count [requestId=${requestId}]:`, message);
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:359:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:363:        status: isEmbeddingModelReady() && database ? 'healthy' : 'degraded',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:380:  const status = isEmbeddingModelReady() && database ? 'healthy' : 'degraded';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:407:      // Resolve the lazy profile so health reflects the active runtime provider
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:428:      tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:439:        'Re-run memory_health with autoRepair:true and confirmed:true to execute repair actions.',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:503:  // (referencing deleted memories) are cleaned up during health checks.
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:570:    tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-crud-health.ts:587:        healthy: providerMetadata.healthy !== false,
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:35:The telemetry module provides structured observability for the retrieval pipeline and scoring subsystem. It records per-stage latency, search mode selection, fallback triggers, composite quality scores, scoring observation samples, trace payload validation, and agent consumption events. Telemetry data flows to governance tooling and is used by retrieval handlers to surface pipeline health metrics.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:107:When `SPECKIT_EXTENDED_TELEMETRY` is disabled (default), the minimal `RetrievalTelemetry` shell is still created so callers can rely on a stable shape. Latency, mode, fallback, quality, graph-health, and adaptive sub-metrics remain zeroed/empty, while the baseline architecture snapshot still records the current memory-roadmap phase/capability defaults.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:273:**Purpose**: Return shape from `sampleTracePayloads()` containing sanitized trace details and graph-health context.
.opencode/skills/system-spec-kit/mcp_server/lib/telemetry/README.md:278:| `graphHealth` | `GraphHealthMetrics` | Graph-health counters associated with the sampled retrieval payload |
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:46:- `code-graph/status.ts` - `code_graph_status`: report graph health and statistics.
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:51:- `memory-crud-delete.ts`, `memory-crud-update.ts`, `memory-crud-list.ts`, `memory-crud-stats.ts`, `memory-crud-health.ts` - Focused CRUD implementations behind `memory-crud.ts`.
.opencode/skills/system-spec-kit/mcp_server/handlers/README.md:70:- `memory-crud-health.ts` surfaces embedding retry stats and FTS/index sync diagnostics as part of the health response.
.opencode/skills/system-spec-kit/mcp_server/lib/enrichment/passive-enrichment.ts:129:      return ['[session] Context quality is CRITICAL. Consider running `memory_context({ mode: "resume" })` or `session_health` to diagnose.'];
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:25:} from '@spec-kit/shared/parsing/spec-doc-health';
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:430:  // Non-blocking spec doc health annotation
.opencode/skills/system-spec-kit/mcp_server/handlers/memory-save.ts:448:        `[memory-save] spec-doc-health annotation skipped for ${path.basename(parsed.filePath)}: ${message}`
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:25:// Feature catalog: Causal graph statistics (memory_causal_stats)
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:103:  tool: 'memory_drift_why' | 'memory_causal_link' | 'memory_causal_stats' | 'memory_causal_unlink',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:558:async function handleMemoryCausalLink(args: CausalLinkArgs): Promise<MCPResponse> {
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:647:        'Use memory_causal_stats() to check overall graph coverage'
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:667:/** Handle memory_causal_stats tool - returns graph coverage and health metrics */
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:668:async function handleMemoryCausalStats(_args: CausalStatsArgs): Promise<MCPResponse> {
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:678:        tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:682:        recovery: getRecoveryHint('memory_causal_stats', 'E020'),
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:718:    const meetsTarget = coveragePercent >= 60;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:719:    const health = orphanedEdges.length === 0 ? 'healthy' : 'has_orphans';
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:721:    const summary = `Causal graph: ${safeTotalEdges} edges, ${coveragePercent}% coverage (${health})`;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:724:    if (!meetsTarget) {
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:735:      tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:739:        by_relation: stats.byRelation,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:745:        health,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:746:        targetCoverage: '60%',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:747:        currentCoverage: coveragePercent + '%',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:748:        meetsTarget: meetsTarget
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:755:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:770:async function handleMemoryCausalUnlink(args: CausalUnlinkArgs): Promise<MCPResponse> {
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:784:          'Use memory_causal_stats() to see graph overview'
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:845:  handleMemoryCausalLink,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:846:  handleMemoryCausalStats,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:847:  handleMemoryCausalUnlink,
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:853:const handle_memory_causal_link = handleMemoryCausalLink;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:854:const handle_memory_causal_stats = handleMemoryCausalStats;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:855:const handle_memory_causal_unlink = handleMemoryCausalUnlink;
.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:860:  handle_memory_causal_stats,
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:12:- skill_advisor.py: analyze_prompt, analyze_batch, health_check, get_skills
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:144:    # T243-SA-005: health_check returns dict with expected keys
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:146:        health = advisor.health_check()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:147:        if isinstance(health, dict):
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:149:            found_keys = set(health.keys())
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:151:                ok("T243-SA-005: health_check returns expected keys", f"keys={list(health.keys())[:5]}")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:154:                fail_test("T243-SA-005: health_check returns expected keys", f"missing={missing}")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:156:            fail_test("T243-SA-005: health_check returns dict", f"type={type(health)}")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:158:        fail_test("T243-SA-005: health_check returns dict", str(exc))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:160:    # T243-SA-005b: corrupt source graph-metadata degrades health visibly.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:192:                health = advisor.health_check()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:193:                source_metadata = health.get("source_metadata") or {}
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:195:                    health.get("status") == "degraded"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:196:                    and source_metadata.get("healthy") is False
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:199:                    ok("T243-SA-005b: corrupt source metadata degrades health")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:202:                        "T243-SA-005b: corrupt source metadata degrades health",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:203:                        f"status={health.get('status')} source_metadata={source_metadata}",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:211:        fail_test("T243-SA-005b: corrupt source metadata degrades health", str(exc))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:213:    # T243-SA-005c: SKILL.md parse drops make cache health degraded, not green.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:247:                health = advisor.health_check()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:248:                cache = health.get("cache") or {}
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:250:                    health.get("status") == "degraded"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:251:                    and cache.get("healthy") is False
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:254:                    ok("T243-SA-005c: cache parse drops degrade health")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:257:                        "T243-SA-005c: cache parse drops degrade health",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:258:                        f"status={health.get('status')} cache={cache}",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:266:        fail_test("T243-SA-005c: cache parse drops degrade health", str(exc))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:617:    # T243-SA-014: T-SGC-02 / R45-003 health_check exposes topology_warnings payload
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:634:            health = advisor.health_check()
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:635:            warnings_payload = health.get("topology_warnings") or {}
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:637:                health.get("status") == "degraded"
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:641:                ok("T243-SA-014: health_check exposes topology_warnings")
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:644:                    "T243-SA-014: health_check exposes topology_warnings",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:645:                    f"status={health.get('status')} warnings={warnings_payload}",
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/python/test_skill_advisor.py:651:        fail_test("T243-SA-014: health_check exposes topology_warnings", str(exc))
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-privacy.vitest.ts:82:  it('keeps raw prompts out of envelope sources, metrics, stderr JSONL, health, and cache keys', async () => {
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-privacy.vitest.ts:105:      const health = buildAdvisorHookHealthSection([diagnostic]);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-privacy.vitest.ts:114:      assertRawPromptAbsent('advisor-hook-health', health, prompt);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:105:  it('builds advisor-hook-health with last-N records, rolling cache hit rate, and p95', () => {
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:115:    const health = buildAdvisorHookHealthSection(records);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:117:    expect(health.key).toBe('advisor-hook-health');
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:118:    expect(health.lastInvocations).toHaveLength(30);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:119:    expect(health.rollingCacheHitRate).toBeGreaterThan(0);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:120:    expect(health.rollingP95Ms).toBeGreaterThan(0);
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-observability.vitest.ts:121:    expect(health.rollingFailOpenRate).toBeCloseTo(1 / 30, 4);
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:47:vi.mock('../handlers/session-health.js', () => ({
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:51:      text: JSON.stringify({ status: 'ok', data: { state: 'ok', hints: ['health ok'] } }),
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:133:import { handleSessionHealth } from '../handlers/session-health.js';
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:151:    expect(parsed.data.health.state).toBe('ok');
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:184:      health: expect.any(Object),
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap.vitest.ts:188:    expect(parsed.data.hints).toEqual(expect.arrayContaining(['resume ok', 'health ok']));
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/status.ts:5:// health, counts, relation breakdowns, and signal summaries.
.opencode/skills/system-spec-kit/mcp_server/handlers/coverage-graph/README.md:19:- `status.ts` - reports graph health and convergence metrics.
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-graph-health.vitest.ts:21:describe('advisor graph health', () => {
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-graph-health.vitest.ts:33:  it('keeps health ok when skill-advisor is the only graph-only node', () => {
.opencode/skills/system-spec-kit/mcp_server/skill_advisor/tests/legacy/advisor-graph-health.vitest.ts:34:    const result = spawnSync('python3', [advisorPath, '--health'], {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:58:    // Fix F23 — include cleanupOrphanedEdges in mock for health auto-repair coverage.
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:440:    providerMetadata = { provider: 'test', model: 'test-model', healthy: true },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:592:   SUITE: handleMemoryDelete - Causal Edge Cleanup
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:595:describe('handleMemoryDelete - Causal Edge Cleanup', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1119:  it('EXT-H1: Healthy system returns status=healthy', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1125:    expect(parsed?.data?.status).toBe('healthy');
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1153:      providerMetadata: { provider: 'huggingface', model: 'gte-small', healthy: true },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1176:      .mockImplementation(() => ({ provider: 'voyage', model: 'voyage-4', healthy: true, dim: 1024 }));
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1193:      providerMetadata: { provider: 'voyage', healthy: true },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1215:      providerMetadata: { provider: 'voyage', healthy: true },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1244:      providerMetadata: { provider: 'voyage', healthy: true },
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1448:      healthy: true,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1522:      healthy: true,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1591:      healthy: true,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1642:      healthy: true,
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1707:  it('EXT-EMR1: setEmbeddingModelReady(true) reflected in health', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1726:  it('EXT-EMR3: Toggle sequence ends healthy', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-crud-extended.vitest.ts:1734:    expect(parsed?.data?.status).toBe('healthy');
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:118:    '@spec-kit/shared/parsing/spec-doc-health',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:233:  vi.doMock('@spec-kit/shared/parsing/spec-doc-health', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-index.vitest.ts:234:    const actual = await importOriginal<typeof import('@spec-kit/shared/parsing/spec-doc-health')>();
.opencode/skills/system-spec-kit/mcp_server/tests/integration-error-recovery.vitest.ts:112:      if (causalHandlerModule?.handleMemoryCausalLink) {
.opencode/skills/system-spec-kit/mcp_server/tests/integration-error-recovery.vitest.ts:115:          run: () => causalHandlerModule.handleMemoryCausalLink({} as Parameters<typeof causalHandlerModule.handleMemoryCausalLink>[0]),
.opencode/skills/system-spec-kit/mcp_server/tests/migration-lineage-identity.vitest.ts:162:      'health = advisor.health_check()',
.opencode/skills/system-spec-kit/mcp_server/tests/migration-lineage-identity.vitest.ts:163:      'print(json.dumps({"loaded": loaded is not None, "source": advisor._SKILL_GRAPH_SOURCE, "error": health.get("skill_graph_error")}))',
.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:451:describe('memory_health schema', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:454:      validateToolInputSchema('memory_health', { reportMode: 'divergent_aliases', limit: 201 }, TOOL_DEFINITIONS);
.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:460:      validateToolInputSchema('memory_health', { autoRepair: true, confirmed: true }, TOOL_DEFINITIONS);
.opencode/skills/system-spec-kit/mcp_server/tests/tool-input-schema.vitest.ts:465:    const parsed = validateToolArgs('memory_health', { autoRepair: true, confirmed: true });
.opencode/skills/system-spec-kit/mcp_server/tests/opencode-transport.vitest.ts:28:          : 'session_health',
.opencode/skills/system-spec-kit/mcp_server/tests/opencode-transport.vitest.ts:54:      surface: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tests/opencode-transport.vitest.ts:80:    const health = makePayload('health', 'health summary');
.opencode/skills/system-spec-kit/mcp_server/tests/opencode-transport.vitest.ts:85:      healthPayload: health,
.opencode/skills/system-spec-kit/mcp_server/tools/types.ts:122:/** Arguments for memory health checks.
.opencode/skills/system-spec-kit/mcp_server/tests/handler-helpers.vitest.ts:98:  if (!causalLinksProcessor?.processCausalLinks) exportErrors.push('handlers/causal-links-processor.processCausalLinks');
.opencode/skills/system-spec-kit/mcp_server/tools/README.md:29:- `memory-tools.ts` - dispatch for search, quick search, triggers, save, CRUD, stats, health, validate, and bulk delete.
.opencode/skills/system-spec-kit/mcp_server/tests/embeddings.vitest.ts:129:        'healthCheck',
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:8:  handleMemoryCausalLink,
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:9:  handleMemoryCausalStats,
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:10:  handleMemoryCausalUnlink,
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:27:  'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:35:    case 'memory_causal_link':   return handleMemoryCausalLink(parseArgs<CausalLinkArgs>(validateToolArgs('memory_causal_link', args)));
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:36:    case 'memory_causal_stats':  return handleMemoryCausalStats(parseArgs<CausalStatsArgs>(validateToolArgs('memory_causal_stats', args)));
.opencode/skills/system-spec-kit/mcp_server/tools/causal-tools.ts:37:    case 'memory_causal_unlink': return handleMemoryCausalUnlink(parseArgs<CausalUnlinkArgs>(validateToolArgs('memory_causal_unlink', args)));
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:311:    const healthy = __testables.checkDegradation([
.opencode/skills/system-spec-kit/mcp_server/tests/search-fallback-tiered.vitest.ts:316:    expect(healthy).toBeNull();
.opencode/skills/system-spec-kit/mcp_server/tools/memory-tools.ts:5:// List, stats, health, delete, update, validate (T303).
.opencode/skills/system-spec-kit/mcp_server/tools/memory-tools.ts:68:  'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tools/memory-tools.ts:102:    case 'memory_health':         return handleMemoryHealth(parseArgs<HealthArgs>(validateToolArgs('memory_health', args)));
.opencode/skills/system-spec-kit/mcp_server/tests/query-classifier.vitest.ts:30:  'memory health',
.opencode/skills/system-spec-kit/mcp_server/tools/lifecycle-tools.ts:49:  'session_health',
.opencode/skills/system-spec-kit/mcp_server/tools/lifecycle-tools.ts:66:    case 'session_health':             return handleSessionHealth();
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-crud.vitest.ts:77:        'handle_memory_health',
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:9:type CausalLinkArgs = Parameters<typeof causalHandler.handleMemoryCausalLink>[0];
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:11:type CausalStatsArgs = Parameters<typeof causalHandler.handleMemoryCausalStats>[0];
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:12:type CausalUnlinkArgs = Parameters<typeof causalHandler.handleMemoryCausalUnlink>[0];
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:108:      const response = await causalHandler.handleMemoryCausalLink({} as CausalLinkArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:124:      const response = await causalHandler.handleMemoryCausalStats({} as CausalStatsArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:134:      expect(envelope.data).toHaveProperty('targetCoverage');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:135:      expect(envelope.data).toHaveProperty('meetsTarget');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:139:      const response = await causalHandler.handleMemoryCausalUnlink({} as CausalUnlinkArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:158:        const response = await causalHandler.handleMemoryCausalLink({
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:188:      const response = await causalHandler.handleMemoryCausalLink({
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:225:      const response = await causalHandler.handleMemoryCausalLink({
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:238:      const response = await causalHandler.handleMemoryCausalStats({} as CausalStatsArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:246:      expect(envelope.data).toHaveProperty('by_relation');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:248:      expect(envelope.data).toHaveProperty('health');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:253:    it('T014-CS2: Stats response includes targetCoverage field', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:254:      const response = await causalHandler.handleMemoryCausalStats({} as CausalStatsArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:261:      expect(envelope.data.targetCoverage).toBe('60%');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:262:      expect(typeof envelope.data.meetsTarget).toBe('boolean');
.opencode/skills/system-spec-kit/mcp_server/tests/integration-causal-graph.vitest.ts:266:      const response = await causalHandler.handleMemoryCausalStats({} as CausalStatsArgs);
.opencode/skills/system-spec-kit/mcp_server/tests/graph-first-routing-nudge.vitest.ts:264:    vi.doMock('../handlers/session-health.js', () => ({
.opencode/skills/system-spec-kit/mcp_server/tests/graph-first-routing-nudge.vitest.ts:268:          text: JSON.stringify({ status: 'ok', data: { state: 'ok', hints: ['health ok'] } }),
.opencode/skills/system-spec-kit/mcp_server/tests/structural-contract.vitest.ts:197:    const contract = buildStructuralBootstrapContract('session_health');
.opencode/skills/system-spec-kit/mcp_server/tests/structural-contract.vitest.ts:200:    expect(contract.sourceSurface).toBe('session_health');
.opencode/skills/system-spec-kit/mcp_server/tests/structural-contract.vitest.ts:214:    const surfaces = ['auto-prime', 'session_bootstrap', 'session_resume', 'session_health'] as const;
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:434:  it('T058: DEFAULT_HINT actions include memory_health() reference (REQ-009)', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:437:      a.includes('memory_health()')
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:446:  it('T060: DEFAULT_HINT has toolTip for memory_health()', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/recovery-hints.vitest.ts:447:    expect(DEFAULT_HINT.toolTip).toBe('memory_health()');
.opencode/skills/system-spec-kit/mcp_server/tests/session-resume.vitest.ts:187:    expect(parsed.data.graphOps.doctor.surface).toBe('memory_health');
.opencode/skills/system-spec-kit/mcp_server/tests/graph-payload-validator.vitest.ts:218:      computeQualityScore: vi.fn(() => ({ level: 'healthy' })),
.opencode/skills/system-spec-kit/mcp_server/tests/graph-payload-validator.vitest.ts:221:    vi.doMock('../handlers/session-health.js', () => ({
.opencode/skills/system-spec-kit/mcp_server/tests/graph-payload-validator.vitest.ts:225:          text: JSON.stringify({ status: 'ok', data: { state: 'ok', hints: ['health ok'] } }),
.opencode/skills/system-spec-kit/mcp_server/database/README.md:72:- Use MCP tools (`memory_stats`, `memory_health`, `memory_index_scan`) for normal operations.
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-health-edge.vitest.ts:106:  it('T007b-H8: Empty args return the default full health payload', async () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-memory-health-edge.vitest.ts:130:        'Re-run memory_health with autoRepair:true and confirmed:true to execute repair actions.',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:36:      'handleMemoryCausalLink',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:37:      'handleMemoryCausalStats',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:38:      'handleMemoryCausalUnlink',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:51:        'handle_memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:232:  describe('handleMemoryCausalLink Validation', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:235:        const result = await handler.handleMemoryCausalLink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:236:          invalidArgs<Parameters<typeof handler.handleMemoryCausalLink>[0]>({}),
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:250:        const result = await handler.handleMemoryCausalLink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:251:          invalidArgs<Parameters<typeof handler.handleMemoryCausalLink>[0]>({
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:271:        const result = await handler.handleMemoryCausalLink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:272:          invalidArgs<Parameters<typeof handler.handleMemoryCausalLink>[0]>({
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:291:        const result = await handler.handleMemoryCausalLink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:292:          invalidArgs<Parameters<typeof handler.handleMemoryCausalLink>[0]>({}),
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:314:      const result = await handler.handleMemoryCausalLink({
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:334:      const result = await handler.handleMemoryCausalStats({});
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:351:      const result = await handler.handleMemoryCausalUnlink({ edgeId: 123 });
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:360:  describe('handleMemoryCausalUnlink Validation', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:362:      const result = await handler.handleMemoryCausalUnlink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:363:        invalidArgs<Parameters<typeof handler.handleMemoryCausalUnlink>[0]>({}),
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:372:      const result = await handler.handleMemoryCausalUnlink(
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:373:        invalidArgs<Parameters<typeof handler.handleMemoryCausalUnlink>[0]>({ edgeId: null }),
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:382:  describe('handleMemoryCausalStats', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/handler-causal-graph.vitest.ts:385:        const result = await handler.handleMemoryCausalStats({});
.opencode/skills/system-spec-kit/mcp_server/tests/README.md:91:| Infrastructure and utilities | `batch-processor.vitest.ts`, `tool-input-schema.vitest.ts`, `transaction-manager.vitest.ts`, `retry-manager-health.vitest.ts`, `vector-index-store-remediation.vitest.ts` | Shared helpers and runtime hardening |
.opencode/skills/system-spec-kit/mcp_server/tests/context-metrics.vitest.ts:85:      expect(score.level).toMatch(/^(healthy|degraded|critical)$/);
.opencode/skills/system-spec-kit/mcp_server/tests/token-budget-enforcement.vitest.ts:24:        memory_health: 1000,
.opencode/skills/system-spec-kit/mcp_server/tests/graph-roadmap-finalization.vitest.ts:37:  it('serializes graph-health and adaptive telemetry contracts', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/graph-roadmap-finalization.vitest.ts:75:  it('summarizes graph-health dashboard metrics across telemetry payloads', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/graph-roadmap-finalization.vitest.ts:119:  it('samples sanitized trace payloads using graph-health thresholds', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/modularization.vitest.ts:27:  'handlers/memory-crud.js': 40,    // actual: 32 — Re-export barrel (decomposed into memory-crud-{health,update,delete,stats,list,utils,types}.js)
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:168:      'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:181:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:203:      'session_health',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:299:      'memory_validate', 'memory_save', 'memory_index_scan', 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:302:      'memory_drift_why', 'memory_causal_link', 'memory_causal_stats', 'memory_causal_unlink',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:307:      'session_health', 'session_resume',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:324:    it('T16d: only session_health is excluded from tool-call tracking', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:325:      expect(sourceCode).toMatch(/if \(name !== 'session_health'\) \{/)
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:326:      expect(sourceCode).not.toMatch(/name !== 'session_health' && name !== 'session_bootstrap'/)
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:1472:          if (name !== 'memory_search' && name !== 'memory_context' && name !== 'memory_quick_search' && name !== 'session_health') {
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:2616:      'memory_health': '[L3:Discovery]',
.opencode/skills/system-spec-kit/mcp_server/tests/context-server.vitest.ts:2628:      'memory_causal_stats': '[L6:Analysis]',
.opencode/skills/system-spec-kit/mcp_server/tests/layer-definitions.vitest.ts:128:        memory_health: 'L3',
.opencode/skills/system-spec-kit/mcp_server/tests/layer-definitions.vitest.ts:138:        memory_causal_stats: 'L6',
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:163:  vi.doMock('@spec-kit/shared/parsing/spec-doc-health', async (importOriginal) => {
.opencode/skills/system-spec-kit/mcp_server/tests/memory-save-index-scope.vitest.ts:164:    const actual = await importOriginal<typeof import('@spec-kit/shared/parsing/spec-doc-health')>();
.opencode/skills/system-spec-kit/mcp_server/tests/folder-discovery-integration.vitest.ts:993:  it('healthy workspace — no repairs needed, no writes', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/folder-discovery-integration.vitest.ts:995:    const specDir = createSpecFolder(tmpDir, '001-healthy', '# Healthy Spec');
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:68:    tool: 'memory_health',
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:144:    handler: 'handleMemoryCausalLink',
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:149:    tool: 'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:150:    handler: 'handleMemoryCausalStats',
.opencode/skills/system-spec-kit/mcp_server/tests/mcp-input-validation.vitest.ts:156:    handler: 'handleMemoryCausalUnlink',
.opencode/skills/system-spec-kit/mcp_server/tests/embedding-retry-stats.vitest.ts:3:// Phase 004 CHK-023 (memory_health embeddingRetry), CHK-024 (retry manager edge cases)
.opencode/skills/system-spec-kit/mcp_server/tests/hook-session-start.vitest.ts:392:    vi.doMock('../handlers/session-health.js', () => ({
.opencode/skills/system-spec-kit/mcp_server/tests/hook-session-start.vitest.ts:396:          text: JSON.stringify({ status: 'ok', data: { state: 'ok', hints: ['health ok'] } }),
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:97:    const healthySessionId = 'healthy-session';
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:98:    const healthySpecFolder = 'specs/system-spec-kit/026-graph-and-context-optimization/016-foundational-runtime/001-initial-research';
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:99:    const transcriptPath = join(sandboxRoot!, 'healthy-transcript.jsonl');
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:104:    const healthyState: HookState = {
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:105:      claudeSessionId: healthySessionId,
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:107:      lastSpecFolder: healthySpecFolder,
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:138:    expect(saveState(healthySessionId, healthyState)).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:146:      lastSpecFolder: healthySpecFolder,
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:168:    const healthyStopResult = await processStopHook(
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:170:        session_id: healthySessionId,
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:175:    expect(healthyStopResult.autosaveOutcome).toBe('skipped');
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:176:    expect(healthyStopResult.transcriptOutcome).toMatchObject({
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:181:    const geminiSections = handleGeminiCompact(healthySessionId);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:186:    const startupBrief = buildStartupBrief(undefined, { claudeSessionId: healthySessionId });
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:187:    expect(startupBrief.sessionContinuity).toContain(healthySpecFolder);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:190:    const cachedSummaryDecision = getCachedSessionSummaryDecision({ claudeSessionId: healthySessionId });
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:195:    expect(cachedSummaryDecision.cachedSummary?.lastSpecFolder).toBe(healthySpecFolder);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:197:    const healthyStateResult = loadState(healthySessionId);
.opencode/skills/system-spec-kit/mcp_server/tests/p0-a-cross-runtime-tempdir-poisoning.vitest.ts:198:    expect(healthyStateResult.ok).toBe(true);
.opencode/skills/system-spec-kit/mcp_server/tests/errors-comprehensive.vitest.ts:448:  it('J2: DEFAULT_HINT actions reference memory_health()', () => {
.opencode/skills/system-spec-kit/mcp_server/tests/errors-comprehensive.vitest.ts:450:    expect(actionsStr).toContain('memory_health');
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap-gate-d.vitest.ts:54:    vi.doMock('../handlers/session-health.js', () => ({
.opencode/skills/system-spec-kit/mcp_server/tests/session-bootstrap-gate-d.vitest.ts:60:            data: { state: 'warning', hints: ['health warning'] },
.opencode/skills/system-spec-kit/mcp_server/tests/error-sanitization.vitest.ts:93:    expect(getDefaultErrorCodeForTool('memory_causal_stats')).toBe('E104');
.opencode/skills/system-spec-kit/mcp_server/tests/error-sanitization.vitest.ts:98:      'memory_causal_stats',
.opencode/skills/system-spec-kit/mcp_server/tests/shadow-comparison.vitest.ts:44:  'memory health',
.opencode/skills/system-spec-kit/mcp_server/tests/shadow-comparison.vitest.ts:89:  'implement zero-downtime deployment strategy using blue-green deployment with automated health checks and rollback',

exec
/bin/zsh -lc "nl -ba .opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts | sed -n '1,260p;300,380p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
     1	// ────────────────────────────────────────────────────────────────
     2	// MODULE: Causal Graph
     3	// ────────────────────────────────────────────────────────────────
     4	
     5	/* ───────────────────────────────────────────────────────────────
     6	   0. DEPENDENCIES
     7	──────────────────────────────────────────────────────────────── */
     8	
     9	// Lib modules
    10	import * as vectorIndex from '../lib/search/vector-index.js';
    11	import * as causalEdges from '../lib/storage/causal-edges.js';
    12	import type { CausalChainNode, CausalEdge } from '../lib/storage/causal-edges.js';
    13	
    14	// Core utilities
    15	import { checkDatabaseUpdated } from '../core/index.js';
    16	import { toErrorMessage } from '../utils/index.js';
    17	import { ErrorCodes, getRecoveryHint } from '../lib/errors.js';
    18	
    19	// REQ-019: Standardized Response Structure
    20	import { createMCPSuccessResponse, createMCPErrorResponse, createMCPEmptyResponse } from '../lib/response/envelope.js';
    21	
    22	// Shared handler types
    23	import type { MCPResponse } from './types.js';
    24	
    25	// Feature catalog: Causal graph statistics (memory_causal_stats)
    26	// Feature catalog: Causal chain tracing (memory_drift_why)
    27	
    28	
    29	/* ───────────────────────────────────────────────────────────────
    30	   1. TYPES
    31	──────────────────────────────────────────────────────────────── */
    32	
    33	/** Flat edge representation for API responses */
    34	export interface FlatEdge {
    35	  id: number;               // T202: causal_edges.id for unlink workflow
    36	  from: string;
    37	  to: string;
    38	  relation: string;
    39	  strength: number;
    40	  depth: number;
    41	  direction: 'incoming' | 'outgoing';
    42	}
    43	
    44	/** Flattened chain produced from CausalChainNode tree */
    45	export interface FlattenedChain {
    46	  all: FlatEdge[];
    47	  by_cause: FlatEdge[];
    48	  by_enabled: FlatEdge[];
    49	  by_supersedes: FlatEdge[];
    50	  by_contradicts: FlatEdge[];
    51	  by_derived_from: FlatEdge[];
    52	  by_supports: FlatEdge[];
    53	  total_edges: number;
    54	  max_depth_reached: boolean;
    55	  truncated: boolean;
    56	  truncation_limit: number | null;
    57	}
    58	
    59	interface DirectionalBuckets {
    60	  caused: FlatEdge[];
    61	  enabled: FlatEdge[];
    62	  supersedes: FlatEdge[];
    63	  contradicts: FlatEdge[];
    64	  derivedFrom: FlatEdge[];
    65	  supports: FlatEdge[];
    66	  allEdges: FlatEdge[];
    67	  totalEdges: number;
    68	  maxDepthReached: boolean;
    69	  truncated: boolean;
    70	  truncationLimit: number | null;
    71	}
    72	
    73	interface DriftWhyArgs {
    74	  memoryId: string | number;
    75	  maxDepth?: number;
    76	  direction?: string;
    77	  relations?: string[] | null;
    78	  includeMemoryDetails?: boolean;
    79	}
    80	
    81	interface CausalLinkArgs {
    82	  sourceId: string | number;
    83	  targetId: string | number;
    84	  relation: string;
    85	  strength?: number;
    86	  evidence?: string | null;
    87	}
    88	
    89	interface CausalStatsArgs {
    90	  _?: never;
    91	}
    92	
    93	interface CausalUnlinkArgs {
    94	  edgeId: number;
    95	}
    96	
    97	function logCausalHandlerError(tool: string, error: unknown): void {
    98	  const message = error instanceof Error ? error.message : String(error);
    99	  console.error(`[${tool}] ${message}`);
   100	}
   101	
   102	function createSanitizedCausalError(
   103	  tool: 'memory_drift_why' | 'memory_causal_link' | 'memory_causal_stats' | 'memory_causal_unlink',
   104	  error: unknown,
   105	  code: string,
   106	  details: Record<string, unknown>,
   107	  startTime: number,
   108	  publicMessage: string,
   109	): MCPResponse {
   110	  logCausalHandlerError(tool, error);
   111	  return createMCPErrorResponse({
   112	    tool,
   113	    error: publicMessage,
   114	    code,
   115	    details,
   116	    recovery: getRecoveryHint(tool, code),
   117	    startTime,
   118	  });
   119	}
   120	
   121	/* ───────────────────────────────────────────────────────────────
   122	   2. TREE-TO-FLAT CONVERTER
   123	──────────────────────────────────────────────────────────────── */
   124	
   125	/**
   126	 * Flatten a CausalChainNode tree into flat edge lists grouped by relation.
   127	 * The tree from getCausalChain() encodes parent→child relationships;
   128	 * for 'forward' direction: parent=source, child=target.
   129	 * For 'backward' direction: parent=target, child=source.
   130	 */
   131	function flattenCausalTree(
   132	  root: CausalChainNode,
   133	  maxDepth: number,
   134	  direction: 'forward' | 'backward'
   135	): FlattenedChain {
   136	  const edgeDirection = direction === 'forward' ? 'outgoing' : 'incoming';
   137	  const result: FlattenedChain = {
   138	    all: [],
   139	    by_cause: [],
   140	    by_enabled: [],
   141	    by_supersedes: [],
   142	    by_contradicts: [],
   143	    by_derived_from: [],
   144	    by_supports: [],
   145	    total_edges: 0,
   146	    max_depth_reached: false,
   147	    truncated: Boolean(root.truncated),
   148	    truncation_limit: root.truncationLimit ?? null,
   149	  };
   150	
   151	  function traverse(node: CausalChainNode): void {
   152	    for (const child of node.children) {
   153	      const edge: FlatEdge = {
   154	        id: child.edgeId ?? 0,          // T202: edge ID from storage layer
   155	        from: direction === 'forward' ? node.id : child.id,
   156	        to: direction === 'forward' ? child.id : node.id,
   157	        relation: child.relation,
   158	        strength: child.strength,
   159	        depth: child.depth,
   160	        direction: edgeDirection,
   161	      };
   162	
   163	      result.all.push(edge);
   164	
   165	      // Group by relation type
   166	      const bucket = relationBucket(child.relation);
   167	      if (bucket) {
   168	        bucket.push(edge);
   169	      }
   170	
   171	      // T006 — Only flag max_depth_reached when a node exists at the depth limit.
   172	      // Nodes at maxDepth-1 with no children are natural leaves (edges were queried).
   173	      // Nodes at maxDepth were added but never explored (traverse returned early).
   174	      if (child.depth >= maxDepth) {
   175	        result.max_depth_reached = true;
   176	      }
   177	
   178	      traverse(child);
   179	    }
   180	  }
   181	
   182	  function relationBucket(relation: string): FlatEdge[] | null {
   183	    switch (relation) {
   184	      case 'caused': return result.by_cause;
   185	      case 'enabled': return result.by_enabled;
   186	      case 'supersedes': return result.by_supersedes;
   187	      case 'contradicts': return result.by_contradicts;
   188	      case 'derived_from': return result.by_derived_from;
   189	      case 'supports': return result.by_supports;
   190	      default: return null;
   191	    }
   192	  }
   193	
   194	  traverse(root);
   195	  result.total_edges = result.all.length;
   196	  return result;
   197	}
   198	
   199	/**
   200	 * Merge two flattened chains (used for 'both' direction).
   201	 * Deduplicates edges by direction+from+to+relation key.
   202	 */
   203	function mergeFlattenedChains(a: FlattenedChain, b: FlattenedChain): FlattenedChain {
   204	  const seen = new Set<string>();
   205	  const merged: FlattenedChain = {
   206	    all: [],
   207	    by_cause: [],
   208	    by_enabled: [],
   209	    by_supersedes: [],
   210	    by_contradicts: [],
   211	    by_derived_from: [],
   212	    by_supports: [],
   213	    total_edges: 0,
   214	    max_depth_reached: a.max_depth_reached || b.max_depth_reached,
   215	    truncated: a.truncated || b.truncated,
   216	    truncation_limit: a.truncation_limit ?? b.truncation_limit ?? null,
   217	  };
   218	
   219	  function addEdge(edge: FlatEdge): void {
   220	    const key = `${edge.direction}:${edge.from}:${edge.to}:${edge.relation}`;
   221	    if (seen.has(key)) return;
   222	    seen.add(key);
   223	
   224	    merged.all.push(edge);
   225	    switch (edge.relation) {
   226	      case 'caused': merged.by_cause.push(edge); break;
   227	      case 'enabled': merged.by_enabled.push(edge); break;
   228	      case 'supersedes': merged.by_supersedes.push(edge); break;
   229	      case 'contradicts': merged.by_contradicts.push(edge); break;
   230	      case 'derived_from': merged.by_derived_from.push(edge); break;
   231	      case 'supports': merged.by_supports.push(edge); break;
   232	    }
   233	  }
   234	
   235	  for (const edge of a.all) addEdge(edge);
   236	  for (const edge of b.all) addEdge(edge);
   237	
   238	  merged.total_edges = merged.all.length;
   239	  return merged;
   240	}
   241	
   242	/**
   243	 * Map tool schema direction values to getCausalChain direction values.
   244	 * Tool schema: 'outgoing' | 'incoming' | 'both'
   245	 * getCausalChain: 'forward' | 'backward'
   246	 */
   247	function mapDirection(direction: string): 'forward' | 'backward' | 'both' {
   248	  switch (direction) {
   249	    case 'outgoing': return 'forward';
   250	    case 'forward': return 'forward';   // backward compat
   251	    case 'incoming': return 'backward';
   252	    case 'backward': return 'backward'; // backward compat
   253	    case 'both': return 'both';
   254	    default: return 'forward';
   255	  }
   256	}
   257	
   258	/**
   259	 * T203: Filter a FlattenedChain to only include edges whose relation
   260	 * is in the provided set. When relations is null/empty, returns the
   300	    truncation_limit: null,
   301	  };
   302	}
   303	
   304	function toDirectionalBuckets(chain: FlattenedChain): DirectionalBuckets {
   305	  return {
   306	    caused: chain.by_cause,
   307	    enabled: chain.by_enabled,
   308	    supersedes: chain.by_supersedes,
   309	    contradicts: chain.by_contradicts,
   310	    derivedFrom: chain.by_derived_from,
   311	    supports: chain.by_supports,
   312	    allEdges: chain.all,
   313	    totalEdges: chain.total_edges,
   314	    maxDepthReached: chain.max_depth_reached,
   315	    truncated: chain.truncated,
   316	    truncationLimit: chain.truncation_limit,
   317	  };
   318	}
   319	
   320	function formatRelationSummary(chain: FlattenedChain, label: 'incoming' | 'outgoing'): string | null {
   321	  const parts: string[] = [];
   322	
   323	  if (chain.by_cause.length > 0) parts.push(`${chain.by_cause.length} caused`);
   324	  if (chain.by_enabled.length > 0) parts.push(`${chain.by_enabled.length} enabled`);
   325	  if (chain.by_supersedes.length > 0) parts.push(`${chain.by_supersedes.length} supersedes`);
   326	  if (chain.by_contradicts.length > 0) parts.push(`${chain.by_contradicts.length} contradicts`);
   327	  if (chain.by_derived_from.length > 0) parts.push(`${chain.by_derived_from.length} derived_from`);
   328	  if (chain.by_supports.length > 0) parts.push(`${chain.by_supports.length} supports`);
   329	
   330	  if (parts.length === 0) return null;
   331	  return `${label}: ${parts.join(', ')}`;
   332	}
   333	
   334	/* ───────────────────────────────────────────────────────────────
   335	   3. MEMORY DRIFT WHY HANDLER
   336	──────────────────────────────────────────────────────────────── */
   337	
   338	/** Handle memory_drift_why tool - traces causal relationships for a given memory */
   339	async function handleMemoryDriftWhy(args: DriftWhyArgs): Promise<MCPResponse> {
   340	  const {
   341	    memoryId,
   342	    maxDepth: rawMaxDepth = 3,
   343	    direction = 'both',
   344	    relations = null,
   345	    includeMemoryDetails = true
   346	  } = args;
   347	  // Clamp maxDepth to [1, 10] server-side
   348	  const maxDepth = Math.min(Math.max(1, Math.floor(rawMaxDepth)), 10);
   349	
   350	  const startTime = Date.now();
   351	
   352	  if (memoryId === undefined || memoryId === null) {
   353	    return createMCPErrorResponse({
   354	      tool: 'memory_drift_why',
   355	      error: 'memoryId is required',
   356	      code: 'E031',
   357	      details: { param: 'memoryId' },
   358	      recovery: getRecoveryHint('memory_drift_why', 'E031'),
   359	      startTime: startTime
   360	    });
   361	  }
   362	
   363	  try {
   364	    await checkDatabaseUpdated();
   365	
   366	    vectorIndex.initializeDb();
   367	    const db = vectorIndex.getDb();
   368	    if (!db) {
   369	      return createMCPErrorResponse({
   370	        tool: 'memory_drift_why',
   371	        error: 'Database not initialized. Server may still be starting up.',
   372	        code: 'E020',
   373	        details: {},
   374	        recovery: getRecoveryHint('memory_drift_why', 'E020'),
   375	        startTime: startTime
   376	      });
   377	    }
   378	    causalEdges.init(db);
   379	
   380	    if (relations && Array.isArray(relations)) {

exec
/bin/zsh -lc "nl -ba .opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts | sed -n '600,760p'" in /Users/michelkerkmeester/MEGA/Development/Code_Environment/Public
 succeeded in 0ms:
   600	    const db = vectorIndex.getDb();
   601	    if (!db) {
   602	      return createMCPErrorResponse({
   603	        tool: 'memory_causal_link',
   604	        error: 'Database not initialized. Server may still be starting up.',
   605	        code: 'E020',
   606	        details: {},
   607	        recovery: getRecoveryHint('memory_causal_link', 'E020'),
   608	        startTime: startTime
   609	      });
   610	    }
   611	    causalEdges.init(db);
   612	
   613	    const validRelations = Object.values(causalEdges.RELATION_TYPES) as string[];
   614	    if (!validRelations.includes(relation)) {
   615	      return createMCPErrorResponse({
   616	        tool: 'memory_causal_link',
   617	        error: `Invalid relation type: '${relation}'. Must be one of: ${validRelations.join(', ')}`,
   618	        code: ErrorCodes.CAUSAL_INVALID_RELATION,
   619	        details: { relation, validRelations },
   620	        recovery: getRecoveryHint('memory_causal_link', ErrorCodes.CAUSAL_INVALID_RELATION),
   621	        startTime: startTime
   622	      });
   623	    }
   624	    const safeRelation = relation as causalEdges.RelationType;
   625	    const edge = causalEdges.insertEdge(String(sourceId), String(targetId), safeRelation, strength ?? 1.0, evidence ?? null);
   626	
   627	    if (!edge) {
   628	      return createMCPErrorResponse({
   629	        tool: 'memory_causal_link',
   630	        error: 'Causal link creation failed.',
   631	        code: ErrorCodes.CAUSAL_GRAPH_ERROR,
   632	        details: { sourceId, targetId, relation },
   633	        recovery: getRecoveryHint('memory_causal_link', ErrorCodes.CAUSAL_GRAPH_ERROR),
   634	        startTime: startTime
   635	      });
   636	    }
   637	
   638	    return createMCPSuccessResponse({
   639	      tool: 'memory_causal_link',
   640	      summary: `Created causal link: ${sourceId} --[${relation}]--> ${targetId}`,
   641	      data: {
   642	        success: true,
   643	        edge
   644	      },
   645	      hints: [
   646	        `Use memory_drift_why({ memoryId: "${targetId}" }) to trace this relationship`,
   647	        'Use memory_causal_stats() to check overall graph coverage'
   648	      ],
   649	      startTime: startTime
   650	    });
   651	  } catch (error: unknown) {
   652	    return createSanitizedCausalError(
   653	      'memory_causal_link',
   654	      error,
   655	      ErrorCodes.CAUSAL_GRAPH_ERROR,
   656	      { sourceId, targetId, relation },
   657	      startTime,
   658	      'Causal link creation failed.',
   659	    );
   660	  }
   661	}
   662	
   663	/* ───────────────────────────────────────────────────────────────
   664	   4. CAUSAL GRAPH STATS HANDLER
   665	──────────────────────────────────────────────────────────────── */
   666	
   667	/** Handle memory_causal_stats tool - returns graph coverage and health metrics */
   668	async function handleMemoryCausalStats(_args: CausalStatsArgs): Promise<MCPResponse> {
   669	  const startTime = Date.now();
   670	
   671	  try {
   672	    await checkDatabaseUpdated();
   673	
   674	    vectorIndex.initializeDb();
   675	    const db = vectorIndex.getDb();
   676	    if (!db) {
   677	      return createMCPErrorResponse({
   678	        tool: 'memory_causal_stats',
   679	        error: 'Database not initialized. Server may still be starting up.',
   680	        code: 'E020',
   681	        details: {},
   682	        recovery: getRecoveryHint('memory_causal_stats', 'E020'),
   683	        startTime: startTime
   684	      });
   685	    }
   686	    causalEdges.init(db);
   687	
   688	    const stats = causalEdges.getGraphStats();
   689	    const orphanedEdges: CausalEdge[] = causalEdges.findOrphanedEdges();
   690	
   691	    // Compute link coverage: unique memories linked / total memories
   692	    const totalMemories = (db.prepare('SELECT COUNT(*) as count FROM memory_index') as import('better-sqlite3').Statement).get() as { count: number };
   693	    const uniqueLinked = new Set<string>();
   694	
   695	    // Count unique memory IDs that appear as source or target
   696	    try {
   697	      const linkedRows = (db.prepare(
   698	        'SELECT DISTINCT source_id FROM causal_edges WHERE EXISTS (SELECT 1 FROM memory_index WHERE CAST(id AS TEXT) = source_id) UNION SELECT DISTINCT target_id FROM causal_edges WHERE EXISTS (SELECT 1 FROM memory_index WHERE CAST(id AS TEXT) = target_id)'
   699	      ) as import('better-sqlite3').Statement).all() as Array<{ source_id: string }>;
   700	      for (const row of linkedRows) {
   701	        uniqueLinked.add(row.source_id);
   702	      }
   703	    } catch (error: unknown) {
   704	      const message = toErrorMessage(error).toLowerCase();
   705	      if (message.includes('no such table') && message.includes('causal_edges')) {
   706	        // New/partially initialized DB where causal edges table is absent.
   707	        // Coverage remains 0 in this case.
   708	      } else {
   709	        throw error;
   710	      }
   711	    }
   712	
   713	    const safeTotalEdges = stats.totalEdges ?? 0;
   714	    const coveragePercent = totalMemories.count > 0
   715	      ? Math.round((uniqueLinked.size / totalMemories.count) * 10000) / 100
   716	      : 0;
   717	
   718	    const meetsTarget = coveragePercent >= 60;
   719	    const health = orphanedEdges.length === 0 ? 'healthy' : 'has_orphans';
   720	
   721	    const summary = `Causal graph: ${safeTotalEdges} edges, ${coveragePercent}% coverage (${health})`;
   722	
   723	    const hints: string[] = [];
   724	    if (!meetsTarget) {
   725	      hints.push(`Coverage ${coveragePercent}% below 60% target - add more causal links`);
   726	    }
   727	    if (orphanedEdges.length > 0) {
   728	      hints.push(`${orphanedEdges.length} orphaned edges detected - consider cleanup`);
   729	    }
   730	    if (stats.totalEdges === 0) {
   731	      hints.push('No causal links exist yet - use memory_causal_link to create relationships');
   732	    }
   733	
   734	    return createMCPSuccessResponse({
   735	      tool: 'memory_causal_stats',
   736	      summary,
   737	      data: {
   738	        total_edges: safeTotalEdges,
   739	        by_relation: stats.byRelation,
   740	        avg_strength: stats.avgStrength,
   741	        unique_sources: stats.uniqueSources,
   742	        unique_targets: stats.uniqueTargets,
   743	        link_coverage_percent: coveragePercent + '%',
   744	        orphanedEdges: orphanedEdges.length,
   745	        health,
   746	        targetCoverage: '60%',
   747	        currentCoverage: coveragePercent + '%',
   748	        meetsTarget: meetsTarget
   749	      },
   750	      hints,
   751	      startTime: startTime
   752	    });
   753	  } catch (error: unknown) {
   754	    return createSanitizedCausalError(
   755	      'memory_causal_stats',
   756	      error,
   757	      ErrorCodes.CAUSAL_GRAPH_ERROR,
   758	      {},
   759	      startTime,
   760	      'Causal graph statistics failed.',

codex
Start with this spec:

[005-memory-search-runtime-bugs/spec.md](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:109)

That’s the bug catalog. It lists the concrete failures around `memory_context`, `memory_search`, `memory_causal_stats`, folder discovery, and fallback behavior. Then read the task ledger:

[005-memory-search-runtime-bugs/tasks.md](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:74)

My read: don’t start with the old P0s unless you suspect regression. The summary says clusters 1-3 already landed: truncation, intent fallback, and output vocabulary. The remaining useful debug targets are clusters 4-7: causal stats, session hygiene, folder discovery/channel health, and quality fallback.

Files I’d inspect first:

- [causal-graph.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:667) for `memory_causal_stats`. The likely first live bug is here: `health` is based only on orphaned edges, so it can say `healthy` while `meetsTarget=false`.
- [memory-context.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1162) for folder discovery and [memory-context.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1568) for where discovered folders are threaded into session state.
- [folder-discovery.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts:1105) for the threshold logic. Current default is `0.3`, which is suspiciously likely to over-bind vague prompts.
- [memory-search.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:949) plus [stage4-filter.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:264) for the `QUALITY=gap` / evidence-gap path. The spec says gap should broaden retrieval; the code looks like it annotates more than it retries.

Shortest path: reproduce `memory_causal_stats()` first, because the suspected fix surface is small and the spec already gives exact acceptance criteria. Then move to folder discovery with the `"Semantic Search"` probe.
hook: Stop
hook: Stop Completed
2026-04-26T18:41:49.961851Z ERROR codex_core::session: failed to record rollout items: thread 019dcb17-f484-7fb2-aae8-471dced10262 not found
tokens used
169,854
Start with this spec:

[005-memory-search-runtime-bugs/spec.md](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/spec.md:109)

That’s the bug catalog. It lists the concrete failures around `memory_context`, `memory_search`, `memory_causal_stats`, folder discovery, and fallback behavior. Then read the task ledger:

[005-memory-search-runtime-bugs/tasks.md](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/specs/system-spec-kit/026-graph-and-context-optimization/003-continuity-memory-runtime/005-memory-search-runtime-bugs/tasks.md:74)

My read: don’t start with the old P0s unless you suspect regression. The summary says clusters 1-3 already landed: truncation, intent fallback, and output vocabulary. The remaining useful debug targets are clusters 4-7: causal stats, session hygiene, folder discovery/channel health, and quality fallback.

Files I’d inspect first:

- [causal-graph.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/causal-graph.ts:667) for `memory_causal_stats`. The likely first live bug is here: `health` is based only on orphaned edges, so it can say `healthy` while `meetsTarget=false`.
- [memory-context.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1162) for folder discovery and [memory-context.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-context.ts:1568) for where discovered folders are threaded into session state.
- [folder-discovery.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/folder-discovery.ts:1105) for the threshold logic. Current default is `0.3`, which is suspiciously likely to over-bind vague prompts.
- [memory-search.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/handlers/memory-search.ts:949) plus [stage4-filter.ts](/Users/michelkerkmeester/MEGA/Development/Code_Environment/Public/.opencode/skills/system-spec-kit/mcp_server/lib/search/pipeline/stage4-filter.ts:264) for the `QUALITY=gap` / evidence-gap path. The spec says gap should broaden retrieval; the code looks like it annotates more than it retries.

Shortest path: reproduce `memory_causal_stats()` first, because the suspected fix surface is small and the spec already gives exact acceptance criteria. Then move to folder discovery with the `"Semantic Search"` probe.
