Asterisk AI语音智能体

简介

🎉 What's New

<details open> <summary><b>v7.6.2 — Gemini 3.8 Live, Microsoft bookings, and clearer call analytics</b></summary>

v7.6.2 is an in-place feature and reliability release. It does not migrate databases, reassign Agents, or change the selected provider, transport, Audio Profile, or shipped Google Live model defaults.

- Gemini 3.8 Live is opt-in on Developer API and Vertex AI — model-aware regions, Audio Only output, ID-matched tool responses, and full-duplex interruption handling. An unanswered attended transfer returns the caller to AI. Attached Vertex 3.8/2.5 calls validate the changed paths; broader production and Developer API qualification remains outstanding (#674). - Microsoft Calendar supports caller-confirmed invitations and same-call booking changes — check an exact requested interval, reconcile creation retries, and reschedule or cancel the tracked booking with consent. Invitations and hours/horizon enforcement remain opt-in; saved OAuth caches, calendar IDs, and Agent prompts are preserved. Later-call changes require staff; creation does not prove invitation delivery or acceptance (#686). - Call History filters now agree with statistics and exports — multi-outcome Only / Hide, tool usage, duration, transcript, and metadata filters apply consistently, with stale responses ignored (#683, contributed by @Rea-PC08). - Admin UI is easier to read and navigate — aligned numeric displays, accessible icon controls, and shared empty states (#681, #682, #684, contributed by @arnavp27). - The ignored farewell delay is deprecated — existing YAML/API values remain compatible, but misleading controls are removed. Terminal hangup still drains caller-facing audio rather than sleeping for a fixed delay (#678).

See the v7.6.2 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.6.1 — Fish Audio streaming and safer transfer/calendar operations</b></summary>

v7.6.1 is an in-place feature, reliability, and security release. It does not migrate databases, reassign Agents, or change the selected provider, transport, or Audio Profile.

- Fish Audio joins the modular TTS catalog — configure provider-scoped credentials and stream PCM through either the supported HTTP path or the new realtime WebSocket path. WebSocket mode can consume LLM text deltas directly for lower first-audio latency (#653, #654, contributed by @Rea-PC08). - Calendar tools preserve useful structured results — safe event, event-detail, availability, and truncation metadata now reaches every voice provider instead of being discarded by the shared sanitizer (#663). - Google credential status matches effective authentication — unresolved environment references no longer appear configured, legacy Vertex credential files are recognized, and new uploads keep the saved provider path aligned (#664). - Attended transfers fail safer — FreePBX pickup channels inherit transfer ownership before the original ringing leg disappears, while a deferred transfer that cannot drain its caller-facing audio is cancelled and returned to the active AI voice (#665, #666). - msgpack is updated to 1.2.1 — resolving the high-severity Unpacker denial-of-service and out-of-bounds read advisory (#670).

See the v7.6.1 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.6.0 — Asterisk Media WebSocket, call metadata, and safer troubleshooting</b></summary>

v7.6.0 adds a third, opt-in media transport and expands call diagnostics while keeping existing AudioSocket, ExternalMedia RTP, Agent, and provider selections unchanged by default.

- Asterisk Media WebSocket is available as an opt-in transport — supported Asterisk releases can open an authenticated, per-call media WebSocket to AVA, with Admin UI setup, CLI/preflight validation, codec conversion, lifecycle cleanup, and explicit qualification boundaries. Only OpenAI Realtime with ulaw on Asterisk 22.10.1/FreePBX 17 has a live qualified smoke; other combinations remain unqualified until tested (#644). - Selected pre-call data can become bounded call metadata — HTTP lookup fields are opt-in, scalar, and non-authoritative. An Agent may correct only explicitly allowed fields during the active call, without changing caller identity, routing, consent/DNC, transfers, disposition, or external systems (#632). - Call troubleshooting now produces privacy-safe support packages — Call History captures the effective provider, pipeline, Audio Profile, transport, codec, VAD, streaming, and tool settings for new calls, then combines that snapshot with correlated sanitized logs and tool lifecycle evidence. General diagnostics exports are bounded and the legacy export endpoint now uses the same safe path (#657). - Admin UI reliability and configuration handling are hardened — slow Docker log reads no longer block the API event loop, overlapping Logs polls are prevented, and non-finite YAML/JavaScript numbers are rejected with exact paths before persistence (#656).

See the v7.6.0 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.5.6 — Safer outbound context, Agent hangup policies, and configured summary LLMs</b></summary>

v7.5.6 is an in-place feature and reliability release. It does not migrate databases, reassign Agents, or change Audio Profiles.

- Outbound lead context is delivered or the call fails closed — ARI origination now uses its documented variables object, restoring routing, identity, AudioSocket, AMD/consent, and campaign metadata. Nonempty lead custom_vars is bounded, confirmed before provider startup, recovered after an engine restart, and redacted from diagnostics (#613). - Hangup intent markers can be scoped per Agent — each Agent can inherit, extend, or replace the global end-of-call phrases. New calls capture an immutable policy, and Full Local negotiates call-scoped support so older servers and malformed overrides fail closed (#619). - Post-call summaries can use configured modular LLMs — each webhook can select an enabled LLM provider and configure its model readiness, timeout, word limit, and prompt. Explicit selections never fall back to another provider; summary failures leave {summary} empty while webhook delivery continues. Existing webhooks retain the legacy OpenAI behavior until configured (#618). - Summary prompts stay isolated from the live Agent persona — provider adapters receive the webhook's summary instructions as authoritative job context, and the default Groq LLM moves to openai/gpt-oss-120b.

See the v7.5.6 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.5.5 — Sidebar collapse, post-call webhook variables, and configurable extension availability</b></summary>

v7.5.5 is an in-place feature release. It does not migrate databases, reassign Agents, or change Audio Profiles.

- Collapsible Admin UI sidebar — the left navigation can collapse to an icon-only rail, with hover tooltips and a persisted preference, reclaiming space on smaller displays (#596). - Pre-call variables now flow into post-call webhooks — each pre-call output variable is exposed as its own placeholder in webhook payload templates, matching prompt and in-call tool behavior (#608). - Configurable extension availability mapping — check_extension_status now classifies multiple ARI device states per extension (including operator-configured custom states for DND/away) via a configurable free/busy/unavailable mapping, with a fail-closed default and new Admin UI editors for per-extension and global state mapping (#577). - check_extension_status reliability fixes — availability fields survive JSON sanitization across all tool adapters, live-transfer channel activity is cross-checked against stale device state, and an unmapped device_state_id can no longer bypass restrict_to_configured_extensions (#577).

See the v7.5.5 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.5.4 — Privacy-safe diagnostics and provider/update hardening</b></summary>

v7.5.4 is an in-place reliability and privacy release. It does not migrate databases, reassign Agents, or change Audio Profiles.

- Diagnostics are truly opt-in — disabled playback taps and full-call RCA capture perform no per-call conversion, locking, file creation, write, or cleanup deletion. Enabled paths reject symlinks, unsafe writable ancestors, and foreign ownership before audio is written. - ARI silent failures recover promptly — 10-second WebSocket ping and timeout defaults make readiness fail in about 20 seconds before normal reconnect logic takes over. - Deepgram telephony choices are coherent — Flux and Nova receive the right language fields, the UI exposes the commonly used telephony models and seven end-to-end Aura languages, and incompatible language/model/voice combinations fail before a remote session opens. - Docker status is accurate again — Docker SDK 7.1 restores Admin UI socket compatibility and detection follows rootful, rootless, TCP, and named-pipe endpoint configuration. - Updates preserve optional Local AI state — absent and unselected Local AI stays absent, while an installed stopped service can be refreshed without being started, including rollback. - Call History privacy is operator-controlled — strict, routing-visible, and explicit off modes make the redaction boundary visible without rewriting historical records (#589).

See the v7.5.4 changelog, migration notes, and validation matrix.

</details>

<details> <summary><b>v7.5.3 — One-click audio recovery and safer transfers</b></summary>

v7.5.3 focuses on getting an installation back to a known-good configuration without undoing the operator's unrelated work.

- Restore audio defaults in context — Providers, Audio Profiles, and modular Pipelines each expose their own restore action in the Admin UI. Provider restores keep credentials, models, voices, prompts, enabled state, and provider identity; profile restores keep Agent assignments; pipeline restores keep STT/LLM/TTS provider selections and non-audio options. - Backend-owned baselines — restore values come from the same canonical registry used by validation, including the supported OpenAI Realtime GA linear16/24 kHz contract. Environment-owned overrides remain visible and are never silently rewritten. - Explicit apply guidance — each restore reports whether no action, a hot reload, or an AI Engine restart is needed before new calls use the baseline. - Fail-closed dialplan transfers — extension, queue, and ring-group transfers validate known-missing targets, require a confirmed ARI handoff, and preserve ownership safely when Asterisk's response is indeterminate. FreePBX queues use the standard ext-queues context by default (#577). - Query what the agent actually did — completed in-call tools now expose a stable tool_call_id, normalized success/failure status, action, and reconcilable target_id in Call History and its API without mixing telemetry into the transcript (#587).

These recovery actions are intentionally narrow: they do not provide a global factory reset and do not change secrets or Agent routing.

See the v7.5.3 changelog for implementation and compatibility details.

</details>

<details> <summary><b>v7.5.2 — Opt-in HD Voice over 16 kHz AudioSocket</b></summary>

v7.5.2 adds a call-scoped wideband path without changing existing Agent profiles or the established 8 kHz compatibility defaults.

- Native 16 kHz AudioSocket — assign wideband_pcm_16k to an Agent to use Asterisk slin16 and rate-specific AudioSocket framing in both directions. - Provider and pipeline alignment — Grok, Google Live, Deepgram, OpenAI, ElevenLabs, Local Hybrid, and Full Local retain truthful per-call media contracts, including retries, tool continuations, interruption, and cleanup. - Fail-closed compatibility — wideband requires Asterisk 20.17+, 21.12+, 22.7+, or 23.1+ and a genuinely wideband endpoint or SIP trunk path such as G.722. ExternalMedia RTP and PSTN/G.711 calls remain on an 8 kHz profile. - Simple rollback — switch the Agent back to telephony_ulaw_8k or telephony_enhanced_8k; no global transport or provider-default change is required.

See the v7.5.2 changelog, v7.5.2 migration notes, and v7.5.2 validation matrix.

</details>

<details> <summary><b>v7.5.1 — Safer Admin apply and complete call history</b></summary>

The v7.5.1 hotfix focuses on recovery and observability without changing audio profiles, provider transport, or fresh-install defaults.

- Recoverable Apply Changes — the Admin UI prepares its updater runner before touching a live service and restores the previous image and container environment if a Compose replacement fails or does not become healthy. - Complete realtime transcripts — OpenAI and Grok keep assistant transcript state separate from interleaved caller-final events, preventing clipped prefixes in Call History and post-call consumers. - Apply instead of unnecessary restart — tool-only edits advertise and use hot reload for new calls. Provider, environment, and process-level changes remain on the restart/recreate path.

No database migration or audio-profile reassignment is required. Existing stored transcripts are not rewritten.

See the v7.5.1 changelog and v7.5.1 migration notes.

</details>

<details> <summary><b>v7.5.0 — Enhanced telephony audio and VICIdial integration 🎧</b></summary>

v7.5.0 improves narrowband call audio without changing the established 8 kHz Asterisk wire contract, and adds a production-oriented VICIdial Remote Agent integration.

- Opt-in enhanced telephony audio — assign telephony_enhanced_8k to an Agent to use stateful band-limited downsampling for cleaner G.711 playback. Existing profiles keep their compatibility behavior, and switching back to telephony_ulaw_8k is the immediate rollback. - Consistent provider and pipeline policy — hosted providers and modular TTS pipelines inherit the Agent's Audio Profile by default, expose narrow troubleshooting overrides, and validate incompatible encoding, rate, resampler, overlap, and segmentation combinations before apply. - Safer interruption and teardown — resampler state is isolated per call and reset across responses, interruptions, and cleanup; replaced streams cannot be removed by stale cleanup; and late pipeline output is blocked after call teardown takes ownership. - VICIdial Remote Agents — VICIdial remains authoritative for campaigns, customer channels, reporting, dispositions, DNC, callbacks, and transfers, while AAVA supplies the mapped AI Agent with fail-closed ownership checks and sanitized lifecycle evidence. - More recoverable upgrades — the host recovery script handles mixed Git ownership, stale updater images, /root traversal constraints, and tracked local edits while preserving bounded backups and exact release targeting.

See the v7.5.0 changelog, Audio Profiles, and VICIdial Remote Agent setup for details.

</details>

<details> <summary><b>v7.4.1 — Reliable, simpler outbound calling 📞</b></summary>

Outbound campaigns are easier to prepare, safer to schedule, and much easier to troubleshoot from the Admin UI.

- Simpler lead intake — import validated CSV or Excel .xlsx files, or add individual leads manually. Samples and new campaigns use the canonical AI_AGENT/agent routing model while legacy AI_CONTEXT/context inputs remain compatible. - Safer campaign scheduling — scheduled calls consistently receive the lead's called number, malformed timezone or calling-window settings fail closed, campaign concurrency is counted correctly, and stale attempts recover through one validated timeout policy. - More reliable human handling — human-first AMD defaults reduce false voicemail classification, and terminal farewell/hangup handling prevents new caller input from reviving a call that is already ending. - Better HTTP-tool workflows — pre-call, in-call, and post-call HTTP tools enforce method/body compatibility; pre-call output variables remain available for enriched greetings; and bounded, sanitized tool responses and diagnostics are visible in Call History and Scheduling. - Safer upgrades — updater recovery now handles older Git installations, Docker Compose access after privilege drops, and mixed-ownership checkouts more predictably without sacrificing local tracked changes.

See the Outbound Calling guide and v7.4.1 changelog for details.

</details>

<details> <summary><b>v7.4.0 — Agent-scoped tools and Agent-only routing 🧰</b></summary>

Each Agent can now receive only the transfer destinations, calendars, and voicemail mailboxes it should be allowed to use.

- Per-Agent resource access — configure the global inventory on Tools, then choose Inherit, Selected, or None under Agents → Edit Agent → Tools for the transfer family, Google Calendar, Microsoft Calendar, and voicemail. - One enforced call snapshot — provider schemas, prompt guidance, execution, deferred transfers, and audit metadata all use the same effective resource set. Empty or stale selections fail closed, and a globally disabled tool always wins. - Restart-free tool updates — Tools → Save & Apply validates and publishes a new tool generation for new calls. Active calls keep the generation they started with; a failed build leaves the previous generation running. - Contexts retired — runtime persona routing now reads Agents from agents.db. Legacy YAML Contexts are imported atomically on upgrade, and AI_CONTEXT remains a deprecated compatibility alias while dialplans move to AI_AGENT. - Cleaner first run — empty installations start with Receptionist, Sales, and Support instead of a collection of demonstration Contexts. - Call History compatibility — tool names remain google_calendar, microsoft_calendar, and leave_voicemail, so existing filters and reports keep working.

Before upgrading—especially from v7.3.0–v7.3.3—read the current upgrade procedure and Contexts → Agents migration guide.

</details>

<details> <summary><b>v7.3.5 — Caller connection ringback 📞</b></summary>

Callers no longer wait through silent provider or pipeline startup.

- Per-agent ringback control — enable Play ringback while connecting in the Agents UI; tone:ring is supplied as the default repeating Asterisk tone. - One implementation for every call path — full-agent providers and modular pipelines share the same caller-only lifecycle, without sending setup audio to the AI provider. - Clean audio handoff — ringback stops on the first provider or pipeline greeting audio and is also cleared on no-greeting readiness, startup failure, disconnect, or call cleanup. - Safe and opt-in — existing agents remain unchanged until the setting is enabled. YAML/API users may configure an Asterisk-local tone:, sound:, or recording: media URI.

See Connection Audio / Ringback and the v7.3.5 changelog.

</details>

<details> <summary><b>v7.3.3 — Local AI stabilization 🧠</b></summary>

v7.3.3 is a Local-AI-only stabilization release. It adds no providers and keeps the cloud-provider call paths unchanged.

- Calls are isolated by session — agent prompts and conversation state no longer mutate shared Local AI Server configuration or leak across reused WebSocket connections. AI Engine and Local AI Server should be upgraded together; the legacy unscoped switch remains temporarily compatible. - Barge-in abandons interrupted output — late LLM/TTS work is quarantined, the interrupted exchange is removed from weak-model history, and the replacement turn stays focused on what the caller just said. - Farewells finish exactly once — Local hangup_call speaks the selected Kokoro/Piper/etc. farewell without a second LLM rewrite, drains partial AudioSocket or RTP tails, records agent_hangup, and then disconnects. - CPU/GPU deployment is safer — dependency pins, CUDA/cuDNN validation, optional llama.cpp architecture targeting, and idempotent preflight checks reduce first-build and rerun failures. - Community GPU evidence — Tesla V100S testing passed Faster-Whisper CUDA float16, Llama 3.1 8B Q4_K_M, Kokoro, AudioSocket, ExternalMedia, barge-in, terminal hangup, concurrent session isolation, and restart recovery.

See the Local AI community test matrix and the Unreleased changelog for the complete scope.

</details>

<details> <summary><b>v7.3.2 — stabilization release 🛡️</b></summary>

v7.3.2 is a stabilization-only patch release built from the supervised AudioSocket and ExternalMedia validation cycle.

- No new providers — scope is limited to reliability, deployment safety, documentation, and contributor-facing CI. - Grok ExternalMedia repaired — clean barge-in, cancelled-output quarantine, named-instance runtime inheritance, complete replacement turns, and exact inactivity announcements through xAI force_message. - AudioSocket and modular pipelines hardened — terminal playback, pipeline producer ownership, talk-detect echo, and inactivity-grace regressions are covered by focused tests and supervised calls. - Updater and provider-failure recovery hardened — safer ownership, rollback/stash handling, readiness validation, and an opt-in dialplan redirect. - PR quality gates expanded — Admin backend/frontend checks and CLI cross-compilation now run before merge.

Release evidence and remaining gates are tracked in the v7.3.2 validation matrix.

</details>

<details> <summary><b>v7.3.1 — Silence watchdog & safe call endings ☎️</b></summary>

AVA now protects silent calls and finishes every terminal message before disconnecting.

• 30-second inbound inactivity protection by default — AVA asks “Are you still there?”, waits 15 seconds for a reply, then speaks a configurable final warning and ends the call. Outbound agents remain opt-in.
• The agent keeps its configured voice — check-ins and final warnings are synthesized by the active Google Live, OpenAI Realtime, Grok, Deepgram, ElevenLabs, local full-agent, or pipeline voice.
• Transport-safe hangup — watchdog and hangup_call farewells drain AudioSocket or ExternalMedia/RTP streaming buffers and ARI file playback before ARI disconnects the caller. Fixed sleeps no longer clip long final sentences.
• Deepgram and ElevenLabs lifecycle fixes — Deepgram control frames no longer split greetings, and ElevenLabs response-completion plus hosted-silence handling keeps AVA's watchdog authoritative.
• Global and per-agent controls — configure defaults under Advanced Settings → Voice Activity Detection → Caller Inactivity, then optionally override them per agent. Call History labels watchdog endings as No input timeout.

See Caller inactivity configuration, ElevenLabs setup, and the full v7.3.1 changelog.

</details>

<details> <summary><b>v7.3.0 — Per-agent voices 🎙️</b></summary>

Voice now belongs to agents. Configure one provider, create multiple agents that share it — each with its own voice.

• Provider-aware voice picker in the Agent form: a dropdown of OpenAI's 10 GA voices, suggestions + custom clone IDs for Grok, Google Live's 30 prebuilt voices, Deepgram's Aura models — the control adapts to the agent's selected AI Engine.
• Provider-specific safety — the provider-level voice becomes the default voice; agents without one behave exactly as before. OpenAI and Google log and fall back for unknown values. Deepgram preserves a configured Aura value for review but fails the call before connection when the voice is unknown or its language does not match the Deepgram Agent language.
• Observable — every call logs the resolved voice and its source, and Call History shows "Voice: marin (from agent)" per call.
• Agent voice changes apply instantly — no engine restart.

Thanks @foytech for seeding this feature (#497). Full guide: docs/VOICE_SELECTION.md.

</details>

<details> <summary><b>v7.2.0 — Live-status dashboard 📡</b></summary>

Real-time system status for the Admin UI — pushed, not polled.

• Live-status hub — a single /api/live-status snapshot endpoint plus an SSE stream (/api/live-status/stream) aggregates AI Engine health, Local AI connectivity, active sessions, audio directories, platform checks, and Asterisk ARI into one normalized status feed.
• Push-first — ai_engine and local_ai_server push their own readiness to the Admin UI (POST /api/live-status/publish, authenticated with LIVE_STATUS_PUSH_TOKEN), so the dashboard converges in sub-second time after a restart instead of waiting on staggered polls. Legacy /api/system/* probes remain as fallback/enrichment.
• Configurable — LIVE_STATUS_POLL_INTERVAL_SECONDS (default 30 s, min 2 s) and LIVE_STATUS_INITIAL_PROBE_TIMEOUT_SECONDS (default 2 s), read live from .env.

Full notes in CHANGELOG.md.

</details>

<details> <summary><b>v7.1.1 — Dashboard reliability & Admin UI polish 🛠️</b></summary>

A focused quality release across the Admin UI — no call-path changes.

• Dashboard reliability — the Asterisk status pill no longer flaps on a transient ARI blip: it reads the engine's authoritative, reconnect-supervised ARI state and applies hysteresis. The system endpoints the Dashboard polls every 5s no longer block the admin event loop, the heaviest is TTL-cached, polling backs off on errors, failed polls surface in the error banner, and a single bad poll no longer flashes cards to "Loading…".
• No more "Loading configuration…" flash — ~11 config pages now seed from a shared stale-while-revalidate cache of the config document, so revisiting a settings page is instant.
• Accessibility (WCAG AA) — form labels programmatically associated with inputs, a focus-trapping modal, a navigation landmark + "skip to content" link, accessible names on icon-only buttons, non-colour status cues on the topology, a visible dark-mode toggle on-state, and light-mode contrast fixes. Debug console.logs (including one that leaked the auth token to the browser console) were removed.
• Prompt editor — configured tool names are colour-coded by their in-call status (enabled / global / not-enabled) as you type.
• Fix (#436) — a canonical google_live: { type: full } provider can be edited and saved again.

Full notes in CHANGELOG.md.

</details>

<details> <summary><b>v7.0.0 — the Agents release 🎯</b></summary>

The biggest release yet: manage your AI agents from the Admin UI, not a config file.

• 🤖 Agents tab — create, edit, and manage agents in the UI. Start from a template (receptionist, after-hours, appointment booker, and more), set the prompt and provider, and copy a ready-to-paste dialplan snippet.
• 📊 Multi-agent dashboard — live KPIs (active agents, active calls, calls routed, transfers), per-agent stats, and routing breakdowns at a glance.
• ☎️ New AI_AGENT dialplan variable — route a call to an agent by name. Your existing AI_CONTEXT dialplans keep working unchanged.
• 🔄 Automatic migration — your existing contexts move into a local agents database on first start. Back up agents.db before later major-version upgrades; see the operator migration guide for rollback boundaries.
• 🔒 Security hardening — no more admin/admin: a one-time admin password is generated and must be changed at first login. Config exports no longer bundle your .env by default.

⚠️ Major release — please read the Upgrade Notes before upgrading from 6.x.

</details>

<details> <summary><b>v6.5.4 (2026-05-25) — OpenAI Realtime GA cleanup across every code path</b></summary>

Follow-up to the v6.5.3 hotfix. v6.5.3 only flipped config/ai-agent.yaml; v6.5.4 brings the rest of the codebase in line:

• Pydantic defaults in src/config.py now default to api_version: ga + model: gpt-realtime (so fresh wizard installs are correct).
• Admin UI "Add Provider" template for OpenAI Realtime no longer seeds the sunset preview model.
• Model dropdown removes the 5 sunset preview options and adds 3 new GA models — gpt-realtime-1.5 (best audio-in/audio-out quality), gpt-realtime-2 (reasoning voice model, GPT-5-class), and gpt-realtime-mini (cost-optimized) — alongside the existing gpt-realtime.
• Legacy preview values in operator YAML now render in a "Custom (legacy — will not connect)" optgroup with a yellow warning banner above the form so the broken state is visible without silently swapping the operator's config.
• Engine emits a one-shot warning when api_version: beta is detected in config (exactly once per provider lifetime, not per reconnect attempt).
• Docs: full rewrite of docs/Provider-OpenAI-Setup.md model section + fix to docs/TROUBLESHOOTING_GUIDE.md.

</details>

<details> <summary><b>v6.5.3 hotfix (2026-05-25) — OpenAI Realtime restored</b></summary>

OpenAI sunset the Realtime Beta API on 2026-05-12 and removed the gpt-4o-realtime-preview-2024-12-17 model on 2026-05-07. Shipped config/ai-agent.yaml still pinned api_version: beta + that preview model, so every operator using OpenAI Realtime hit error.code: beta_api_shape_disabled and the WebSocket closed immediately. Two-line config flip — no code change required. The provider's GA wire-protocol path has shipped since v6.0.0; v6.5.3 just makes it the default everyone gets:

• api_version: ga (was beta)
• model: gpt-realtime (was gpt-4o-realtime-preview-2024-12-17)

If you have an ai-agent.local.yaml that explicitly pins api_version: beta, remove the override or change it to ga. Refs: OpenAI deprecations, gpt-realtime.

</details>

<details> <summary><b>v6.5.2 (2026-05-24) — xAI Grok + multi-instance full-agent providers</b></summary>

✨ Features

Technical Features

• Tool Calling System: AI-powered actions (transfers, emails) work with any provider.
• Agent CLI Tools: setup, check, rca, update, version commands (legacy aliases: init, doctor, troubleshoot).
• Modular Pipeline System: Independent STT, LLM, and TTS provider selection.
• Multiple Transports: AudioSocket (default in config/ai-agent.yaml), ExternalMedia RTP, and opt-in, version-gated Asterisk Media WebSocket (see the transport matrix).
• Per-Agent Audio Profiles: Stable and enhanced 8 kHz telephony profiles, plus opt-in 16 kHz AudioSocket with provider-native PCM conversion on supported Asterisk versions and G.722/wideband endpoint or trunk legs. ExternalMedia RTP remains on the supported 8 kHz profiles; G.711/PSTN Agents remain on an 8 kHz profile.
• Streaming-First Downstream: Streaming playback when possible, with automatic fallback to file playback for robustness.
• High-Performance Architecture: Separate ai_engine and local_ai_server containers.
• Observability: Built-in Call History for per-call debugging + optional /metrics scraping.
• State Management: SessionStore for centralized, typed call state.
• Barge-In Support: Interrupt handling with configurable gating.