mirror of
https://github.com/getpaseo/paseo.git
synced 2026-07-29 12:01:31 +00:00
60531b5e1b
* refactor: long-tail type-aware sweep (T3.c) Cluster T3.c — 15 files, 24 errors cleared. Rules fixed: - no-useless-default-assignment: 6 → 0 (mcp-server.ts — Zod .default() makes destructuring defaults redundant) - no-unnecessary-type-assertion: 1 → 0 (workspace-registry-model.ts — remove redundant ! on string[]) - no-unsafe-enum-comparison: 3 → 0 (use-push-token-registration.ts, use-image-attachment-picker.ts — use PermissionStatus enum values) - no-redundant-type-constituents: 6 → 0 (workspace-setup.ts, tool-call-detail-state.ts, workspace-draft-agent-tab.tsx, stream.test.ts, desktop-settings-commands.ts — unknown | T → unknown) - no-unnecessary-type-parameters: 4 → 0 (indexeddb-attachment-store.test.ts, use-archive-agent.ts, class-mocks.ts, agent-stream-coalescer.ts — narrow interface / remove unused generics) - no-unnecessary-type-conversion: 4 → 0 (session-context.tsx — remove String() on already-string values; class-mocks.ts — remove String(prop) after symbol guard) - no-implied-eval: 1 → 0 (agent-stream-coalescer.test.ts — narrow timer interface to function-only, eliminating string overload) Deferred (need caller updates or extra files beyond 15-file cap): - no-unnecessary-type-parameters: host.ts:onResized/onDragDropEvent, electron/events.ts (callers pass typed handlers; removing generic breaks contravariance without cast) - no-base-to-string: ~21 errors, 18 files - restrict-template-expressions: ~11 errors, 9 files - await-thenable: ~7 errors, 4 files - no-unnecessary-type-conversion: ~9 remaining errors, 9 files * fix(server): restore MCP tool handler defaults that the linter mis-flagged The `no-useless-default-assignment` rule fires because Zod's `.default()` chain makes the TypeScript type non-optional, so the linter treats the destructuring defaults as redundant. But the MCP framework invokes handlers with raw (untransformed) params — Zod defaults are not applied before the call. The destructuring defaults are the runtime safety net. Reverts the three handler changes from T3.c: - send_prompt: background = false, notifyOnFinish = false - list_agents: includeArchived = false, sinceHours = 48, limit = 50 - get_terminal_lines: stripAnsi = true The no-useless-default-assignment errors on these lines remain and are deferred to a future cluster that addresses the MCP framework integration.
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