Add official QQ platform support using botpy SDK with WebSocket connection.
Features:
- C2C (private message) support via QQ Open Platform
- WebSocket-based bot connection (no public IP required)
- Message deduplication with efficient deque-based LRU cache
- User whitelist support via allow_from configuration
- Clean async architecture using single event loop
Changes:
- Add QQChannel implementation in nanobot/channels/qq.py
- Add QQConfig schema with appId and secret fields
- Register QQ channel in ChannelManager
- Update README with QQ setup instructions
- Add qq-botpy dependency to pyproject.toml
- Add botpy.log to .gitignore
Setup:
1. Get AppID and Secret from q.qq.com
2. Configure in ~/.nanobot/config.json:
{
"channels": {
"qq": {
"enabled": true,
"appId": "YOUR_APP_ID",
"secret": "YOUR_APP_SECRET",
"allowFrom": []
}
}
}
3. Run: nanobot gateway
Note: Group chat support will be added in future updates.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add moonshot to ProvidersConfig schema
- Add MOONSHOT_API_BASE environment variable for custom endpoint
- Handle kimi-k2.5 model temperature restriction (must be 1.0)
- Fix is_vllm detection to exclude moonshot provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Implement Discord channel functionality with websocket integration.
- Update configuration schema to include Discord settings.
- Enhance README with setup instructions for Discord integration.
- Modify channel manager to initialize Discord channel if enabled.
- Update CLI status command to display Discord channel status.
- Update configuration schema to include Gemini provider
- Modify API key retrieval priority to include Gemini
- Enhance CLI status command to display Gemini API status
- Update LiteLLMProvider to support Gemini integration
- Add vllm provider configuration in config schema
- Auto-detect vLLM endpoints and use hosted_vllm/ prefix for LiteLLM
- Pass api_base directly to acompletion for custom endpoints
- Add vLLM status display in CLI status command
- Add vLLM setup documentation in README
