上下文钻石

60-Second Demo

Install from GitHub:

pip install git+https://github.com/RainCherb/context-diamond.git

Compress a long handoff:

context-diamond examples/long_handoff.md --budget 320 --title "Sprint Handoff"

Get JSON with an audit trail:

context-diamond examples/long_handoff.md --format json --loss-report

Benchmark it against dumb head/tail clipping:

context-diamond-bench examples/long_handoff.md --budget 320

Inspect why shards were selected:

ctxd explain examples/long_handoff.md

Build a capsule from a repository:

ctxd repo . --budget 1200

Compare or merge capsules as the handoff evolves:

ctxd diff old_capsule.json new_capsule.json
ctxd merge chat.json repo.json issue.json --budget 900

Batch-process multiple files:

ctxd batch notes/*.md --output-dir capsules/ --budget 400 --template coding

Use a domain-specific template:

context-diamond incident_report.md --template incident --budget 500

Stream capsules incrementally:

from context_diamond import StreamingCompressor

streamer = StreamingCompressor()
streamer.add_message("Goal: build a login form.")
streamer.add_message("Decision: use JWT tokens.")
capsule = streamer.current_capsule

Example benchmark output:

535 source tokens -> 387 rendered capsule tokens
1.38x ratio
constraints:1.00 decisions:1.00 risks:1.00 code:1.00

Precise tokenizers (optional extras)

context-diamond notes.md --tokenizer tiktoken --budget 500

Use a JSON message list:

Middleware (Transparent API Savings)

Auto-compress messages before sending to an LLM:

```python from context_diamond import AutoCompressMiddleware

middleware = AutoCompressMiddleware(threshold_tokens=1200) compressed = middleware.compress_messages(messages, model_name="gpt-4o")

Python API

from context_diamond import CompressionConfig, ContextDiamondCompressor

text = """
Goal: reduce token waste in LLM handoffs.
The tool must run locally and avoid API keys by default.
Decision: emit markdown and JSON capsules.
"""

compressor = ContextDiamondCompressor(CompressionConfig(token_budget=220))
capsule = compressor.compress(text)

print(capsule.to_markdown())

Integration helpers:

from context_diamond import compress_documents, compress_messages, compress_tool_payload

See docs/integrations.md.

Open Questions And Risks

- Unresolved items that need attention. ```