snowspeeder/hope-voice-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
16 Commits 1 Branch 0 Tags
c6208678549a88caa53748b4696ffc517483d656
Commit Graph
7 Commits
Author SHA1 Message Date
Shane c620867854 fix: disable preemptive_generation for tool call compatibility; add get_time tool 
- preemptive_generation was incompatible with MCP tool calls: it starts
  generating before the turn finalizes, breaking the tool execution loop
  (agent said 'let me check' then hung forever)
- Add get_time(location?) to weather_mcp.py for date/time queries
- Update system prompt with Weather & Time section
 2026-08-22 16:13:06 -04:00
Shane 510a577761 feat: add get_weather MCP tool using wttr.in API 
- New agent/weather_mcp.py: stdio MCP server with get_weather(location)
  that returns a short conversational summary (temp, conditions, high/low)
- Register weather toolset in build_mcp_toolsets() alongside web-access
- Update system prompt with Weather section
 2026-08-22 15:26:25 -04:00
Shane d3f9f2c4ed feat: implement full UPDATE.md review — critical fixes, UI upgrade, infra hardening 
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
 2026-08-22 15:21:59 -04:00
Shane b55e6ed39a refactor: use MCPToolset instead of deprecated mcp_servers param 
- Switch from Agent(mcp_servers=[...]) to Agent(tools=[MCPToolset(...)])
- Add WEB_MCP_ENABLED + FIRECRAWL_BASE to supervisord agent env
- Fixes deprecation warning in livekit-agents 1.7
 2026-08-22 12:40:07 -04:00
Shane 045ddabac7 feat: web access via MCP (Firecrawl search/scrape) + mcp server attach support 
- agent/web_mcp.py: stdio MCP server exposing web_search and web_scrape,
  backed by the self-hosted Firecrawl stack on xNAS (no API key needed)
- agent.py: Agent now attaches mcp_servers built from config; EXTRA_MCP_SERVERS
  env var allows adding arbitrary HTTP/SSE MCP servers as JSON
- Dockerfile: installs livekit-agents[mcp], copies web_mcp.py
- .env.example: WEB_MCP_ENABLED, FIRECRAWL_BASE, EXTRA_MCP_SERVERS documented
 2026-08-22 12:29:04 -04:00
Shane e807ade45d fix: agent data_received handler + livekit config 2026-08-22 08:24:42 -04:00
Shane bbca8505d7 feat: agent.py with Azure STT/TTS + Gemma LLM pipeline, voice switching 2026-08-22 07:40:58 -04:00