- pipeline.py: switched LLM from OpenClaw/Claude to local Ollama, added settings loading, sentence aggregator, async SpeechBrain, tuned VAD
- main.py: simplified (no more token server thread, just pipeline)
- token_server.py: NEW - standalone token + settings API server
- docker-compose.yml: all services on GPU machine, added token-server service, CUDA speaches, Ollama LLM
- web-client/index.html: added settings panel with sliders
- web-client/app.js: settings management, localStorage persistence, push to server
- web-client/style.css: settings panel styles
- web-client/nginx.conf: proxy to token-server instead of pipecat-agent
- patch_livekit.py: updated with proper indentation-safe patching
- pipeline.py: completely rewritten to use Speaches STT/TTS and OpenClaw LLM
- main.py: v2 with OPENCLAW_TOKEN support
- requirements.txt: slimmed (removed anthropic, faster-whisper direct deps)
- Dockerfile: slimmer build (no model pre-download)
- whisper_stt.py, piper_tts.py: removed (replaced by Speaches API)
- docker-compose.yml: v2 with speaches + openclaw services, piper-tts removed
- openclaw-agent/system_prompt.md: new directory with agent system prompt
Adds a lightweight HTTP token server (port 8080) alongside the voice
pipeline so web clients can obtain LiveKit access tokens without a
separate service. Adds fastapi and uvicorn to requirements. Adds
LIVEKIT_PUBLIC_URL env var (wss://voice.hobbs.farm) to docker-compose
so tokens carry the correct public WebSocket URL for browser clients.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
jeremy