mirror of https://github.com/getpaseo/paseo.git synced 2026-10-23 17:52:49 +00:00

Files

T

paseo-bot[bot]andkywoo26 a2b040869d fix(claude): count input reported late in the context meter (#6703 )

* fix(claude): read cumulative input usage from message_delta

The context meter took input_tokens only from message_start. Backends behind a
translating gateway report 0 there and the real cumulative counts on
message_delta, so contextWindowUsedTokens collapsed to output_tokens.

Keep the message_start counters per field and let a counter present on
message_delta replace it, the same rule the Anthropic SDK MessageStream uses.
A missing counter keeps the message_start value, so a delta without cache
fields does not drop cache_read_input_tokens.

Closes #4294

* test(claude): ignore a message_delta that precedes its message_start

A canceled request can leave its terminal message_delta queued ahead of the
next turn. Pin that such a straggler neither emits usage_updated nor leaks
into the next request's counters.

* test(claude): take the message_delta usage object as a single parameter

Keep createMessageDeltaEvent(outputTokens) for existing call sites and add
createMessageDeltaUsageEvent(usage) for the tests that set input counters on
the delta, instead of a second positional parameter.

* test(claude): verify late input usage through the real provider process

Compare start-side and delta-side counters through two real provider turns against a local Messages API fixture, including omitted cache counters. The delta cases fail on the baseline with output-only context totals.

Co-authored-by: kywoo26 <kywoo26@naver.com>

* test(claude): always close the context usage fixture

---------

Co-authored-by: kywoo26 <kywoo26@naver.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>

2026-10-12 12:59:46 +02:00

scripts

Keep subprocess regression tests independent of terminal colors (#6648 )

2026-10-12 00:47:28 +02:00

src

fix(claude): count input reported late in the context meter (#6703 )

2026-10-12 12:59:46 +02:00

.env.example

Use separate OpenAI endpoints for speech-to-text and text-to-speech (#1823 )

2026-06-30 10:00:27 +02:00

.gitignore

server(codex): normalize file paths, truncate large diffs, and drop turn/diff/updated telemetry

2026-02-06 11:51:59 +07:00

AGENTS.md

refactor(agent): add wait_for_agent tool and simplify prompt sending API

2025-11-03 11:47:15 +01:00

CLAUDE.md

Speed up cold diffs and wrapped text measurement (#4676 )

2026-09-11 08:07:01 +02:00

package.json

Preserve base worktree paths when merging (#6668 )

2026-10-12 06:00:59 +02:00

README.md

chore: reformat codebase with oxfmt

2026-04-23 21:44:48 +07:00

tsconfig.scripts.json

Align script TypeScript lib with server build

2026-05-05 18:54:29 +07:00

tsconfig.server.json

2026-08-02 00:56:05 +08:00

tsconfig.server.typecheck.json

Fix repo typecheck failures

2025-11-15 20:17:47 +01:00

vitest.config.ts

Launch a terminal instead of a chat from New workspace (#2941 )

2026-08-07 14:08:22 +08:00

README.md

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