- Raise VAD thresholds (activation 0.65→0.75, min speech 0.4→0.6s,
min silence 0.55→0.65s) to reduce false triggers from background noise
- Add "focus on latest message" instruction to all prompts (voice + text)
- Add "greet and wait" behavior for new conversations instead of auto-continuing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
MAT-58: Add recent_confluence_pages tool to both voice and text chat.
Shows last 5 recently modified pages so users can pick directly
instead of having to search every time.
MAT-59: Integrate sentry-sdk in all three entry points (agent.py,
bot.py, voice.py). SENTRY_DSN env var, traces at 10% sample rate.
Requires creating project in Sentry UI and setting DSN.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Element Call uses HKDF-SHA256 + AES-128-GCM for frame encryption,
while the LiveKit Rust SDK defaults to PBKDF2 + AES-256-GCM.
- Multi-stage Dockerfile builds patched Rust FFI from EC-compat fork
- Generates Python protobuf bindings with new fields
- patch_sdk.py modifies installed livekit-rtc for new proto fields
- agent.py passes E2EE options with HKDF to ctx.connect()
- bot.py exchanges encryption keys via Matrix state events
- Separate Dockerfile.bot for bot service (no Rust build needed)
Ref: livekit/rust-sdks#904, livekit/python-sdks#570
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
AgentServer in livekit-agents 1.4.x does not support --agent-name CLI
flag. The agent_name must be set on @server.rtc_session() decorator.
Also reverts docker-compose.yml command back to plain python agent.py start.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Custom rtc.Room skipped ctx.connect(), leaving framework audio
input pipeline uninitialized. STT/VAD never received audio frames.
Switch to standard approach: ctx.connect() + ctx.room.
Added debug event logging for speech pipeline.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Agent disconnects custom room when all real participants leave
(prevents zombie participants blocking auto-dispatch)
- Bot sends m.call.member state event on call detection
(Element Call shows bot as joined)
- Use RoomInputOptions(participant_identity=...) to target real user
audio input (framework agent-AJ_xxx participant was confusing RoomIO)
- Removed incorrect bot dispatch (Matrix room ID != LiveKit room name)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- STT: elevenlabs.STT() (Scribe) instead of Whisper via LiteLLM
- TTS: elevenlabs.TTS() (already direct)
- LLM: still routed through LiteLLM/OpenRouter
- No extra API accounts needed — only ElevenLabs + OpenRouter
CF-1147
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
