Files
paseo/packages/server
4ef4a95a42 Keep Claude session listing from loading whole histories into memory (#7626)
* fix(claude): stream and cache session import descriptors

* fix(claude): bound and schedule import reads

Reject JSONL records over 4 MiB explicitly to preserve metadata.
Limit shared reads to four globally and one per listing for fairness.
Deduplicate reads by cacheKey with independent subscriber cancellation.
Set a 45-second provider deadline before the 60-second client timeout.
Clone returned descriptors to isolate overlapping callers.

Validation: 97 focused tests passed; independent review approved.

Detected-By: user

* fix(claude): parallelize resilient session scans

Use up to four workers per listing with a shared four-read limit
and bounded FIFO queuing. Preserve cache-key deduplication,
subscriber cancellation, and candidate order.

Log and skip oversized or unreadable transcripts so healthy
sessions remain visible. Propagate programming and abort errors.

Detected-By: user

* fix(claude): surface session import read failures

Skip expected candidate read failures and return healthy sessions.
Distinguish unreadable metadata from parsed transcripts, and raise
AggregateError when every candidate is unreadable.

Propagate systemic file errors and narrow discovery error suppression.

Detected-By: user

* fix(claude): keep large sessions importable while streaming history

Preserve import metadata for transcripts containing image records above 4 MiB. Stream complete records instead of rejecting otherwise listable sessions, and cover overlapping requests across aliased provider roots under a constrained heap.

Co-authored-by: Josh Lane <joshlane@easypost.com>

* test(app): wait for active agent controls and submitted turns

Observe the mode control before testing Command Center keyboard selection. Observe a running turn before waiting for its completion, so the rewind test cannot mistake the previous idle state and end marker for the new turn.

---------

Co-authored-by: Josh Lane <joshlane@easypost.com>
Co-authored-by: Josh Lane <lane.joshlane@gmail.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
2026-10-22 12:07:39 +02:00
..
2026-10-22 03:53:53 +02:00
2026-04-23 21:44:48 +07:00

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:

  1. Start servers: npm run dev
  2. Open http://localhost:5173
  3. Test WebSocket connection (green status indicator)
  4. Click "Send Ping" button to test communication

More testing guidance as features are implemented.

License

MIT