mirror of
https://github.com/getpaseo/paseo.git
synced 2026-10-24 18:22:38 +00:00
0458988825
* fix(server): give the web UI connection hint an explicit port (#1) injectConnectionHint built `listen` straight from the Host header, which carries no port when the client used the scheme's default — exactly what a browser sends to a proxy terminating TLS on 443. The app parses `listen` with parseHostPort, which requires an explicit port, so connectionFromListen returned null and bootstrapInitialConnectionHint bailed before probing, silently. Boot then fell through to the localhost:6767 fallback, which is the viewer's own machine rather than the daemon, and the app landed on the welcome screen with no host at all. Reaching the daemon directly never hit this: http://host:6767 puts the port in the Host header. It only appears behind a reverse proxy on 443 or 80, such as a Tailscale Ingress, and only in a browser profile with no host already stored. Spell the scheme default out when the header omits it, leaving the IPv6 bracket form intact. Co-authored-by: Claude Opus 5 <noreply@anthropic.com> * fix(server): compute the web bootstrap port before its connection hint Keep the default-port fix for reverse proxy bootstrap within the repository branching style. Co-authored-by: Sian Lerk Lau <kiawin@gmail.com> --------- Co-authored-by: Sian Lerk Lau <kiawin@gmail.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Voice Assistant
A voice-controlled terminal assistant that runs as a single local service.
Quick Start
# Install dependencies
npm install
# Copy environment variables
cp .env.example .env
# Edit .env and add your API keys (OpenAI, Deepgram)
# Run development servers
npm run dev
# Open browser to http://localhost:5173
Architecture
- Express Server (port 3000) - Serves API and built UI in production
- Vite Dev Server (port 5173) - Hot-reload React UI in development
- WebSocket (
/ws) - Real-time bidirectional communication - Agent - STT → LLM → TTS pipeline with terminal control
- Daemon - tmux-based terminal management (in-process)
Development
# Run both servers (recommended)
npm run dev
# Or run separately:
npm run dev:server # Express on port 3000
npm run dev:ui # Vite on port 5173
# Type checking
npm run typecheck
# Build for production
npm run build
# Start production server
npm start
Project Status
✅ Completed (Phases 1-2):
- Package setup and configuration
- Express server with WebSocket
- React UI with Vite
- WebSocket client with ping/pong testing
⏳ In Progress (Phase 3):
- Terminal control (tmux integration)
📋 Planned (Phases 4-9):
- LLM integration (OpenAI GPT-4)
- Agent orchestrator
- Speech-to-Text (Deepgram)
- Text-to-Speech (OpenAI)
- Audio streaming
- UI polish
See IMPLEMENTATION_PLAN.md for complete details.
Environment Variables
OPENAI_API_KEY=your-openai-key-here # GPT-4 and TTS
DEEPGRAM_API_KEY=your-deepgram-key-here # Streaming STT
STT_MODEL=whisper-1 # Optional: override to gpt-4o-transcribe, etc.
STT_CONFIDENCE_THRESHOLD=-3.0 # Optional: reject low-confidence clips
STT_DEBUG_AUDIO_DIR=.stt-debug # Optional: persist raw dictation audio for debugging
PASEO_HOME=~/.paseo # Runtime state directory (agents/, etc.)
PASEO_LISTEN=127.0.0.1:6767 # Listen address (host:port or /path/to/socket)
PASEO_HOME defaults to ~/.paseo and isolates runtime artifacts like agents/. PASEO_LISTEN controls the daemon listen address. For blue/green testing you can run a parallel server without touching production state:
PASEO_HOME=~/.paseo-blue PASEO_LISTEN=127.0.0.1:7777 npm run dev
Tech Stack
- Server: Express, TypeScript, ws (WebSocket)
- Client: React 18, Vite, TypeScript
- Terminal: tmux (via child_process)
- AI: OpenAI (LLM + TTS), Deepgram (STT)
Testing
Currently manual testing via:
- Start servers:
npm run dev - Open http://localhost:5173
- Test WebSocket connection (green status indicator)
- Click "Send Ping" button to test communication
More testing guidance as features are implemented.
License
MIT