Shane
d3f9f2c4ed
Critical frontend bugs: - Add TrackSubscribed/attach() for agent audio playback - Fix decodeToString TypeError with TextDecoder - XSS fix: innerHTML -> textContent in addMessage - Fresh token on reconnect retry Agent fixes: - GemmaLLM subclass with reasoning_content fallback wrapper - Disable Gemma 4 thinking mode via chat_template_kwargs (6.8s -> 0.5s) - Remove duplicate session-level LLM - Replace global _active_session with closure-based handler - asyncio.create_task instead of deprecated get_event_loop - Explicit silero VAD, topic filter on voice-control Infra: - supervisord: all programs log to /dev/stdout - Dockerfile: uv sync --frozen with committed uv.lock - nginx config moved to real file, token_server.py no longer served - entrypoint.sh: cert persisted, only regenerated on IP change - compose: healthcheck + cert volume - token_server: CORS removed, room pinned to voice-room UI upgrade: - Orb UI with state machine (idle/connecting/listening/thinking/speaking) - Streaming transcripts via lk.transcription text streams - Barge-in hint, thinking chip, audio visualizer - Glassmorphism, chat bubbles, settings sheet, light mode - PWA manifest, favicon, wake-lock, safe-area insets - localStorage conversation history Docs: AGENTS.md drift fixed
20 lines
456 B
TOML
20 lines
456 B
TOML
[build-system]
|
|
requires = ["setuptools>=61.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "voice-agent"
|
|
version = "0.1.0"
|
|
description = "Real-time voice assistant: Azure STT/TTS + Gemma LLM via LiveKit Agents"
|
|
requires-python = ">=3.10,<3.15"
|
|
|
|
dependencies = [
|
|
"livekit-agents[mcp]~=1.7",
|
|
"livekit-plugins-azure~=1.7",
|
|
"livekit-plugins-openai~=1.7",
|
|
"python-dotenv",
|
|
]
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|