An AI-powered coding assistant for Visual Studio Code using the Qwen3-Coder model. This extension provides a production-grade chat interface and intelligent code assistance similar to GitHub Copilot, helping you write better code faster.
- Real-time Chat Panel: Copilot-style chat interface in the sidebar
- Context-Aware Conversations: Automatically includes code context from your active editor
- File Attachments: Attach files to provide additional context
- Code Block Actions: Copy or apply code snippets directly from responses
- Persistent History: Conversations are saved across sessions
- Smart Suggestions: Quick-start suggestions for common tasks
- Ask Questions: Get instant answers to your coding questions
- Inline Suggestions: Receive contextual code suggestions as you type
- Code Explanations: Understand complex code with detailed explanations
- Code Fixes: Automatically fix bugs and improve code quality
- Code Generation: Generate code snippets from natural language descriptions
- Workspace Search: Search your workspace with natural language queries
- Terminal Commands: Get help with terminal commands and execute them safely
- Response Caching: Improved performance with intelligent caching
- Rate Limiting: Built-in rate limiting to prevent API overuse
- Error Handling: Robust error handling with helpful messages
- Streaming Responses: Real-time response streaming for better UX
- Multi-file Context: Include multiple files for comprehensive analysis
- Visual Studio Code version 1.106.1 or higher
- An API key for Qwen3 model access (configure in settings)
This extension contributes the following settings:
qwen3.apiKey: Your Qwen3 API key for authenticationqwen3.model: Qwen3 model to use (default: qwen/qwen3-coder:free)qwen3.temperature: Temperature for model responses (0-2, higher = more creative)qwen3.maxTokens: Maximum tokens in response (100-4096)qwen3.contextWindow: Number of files to include in multi-file contextqwen3.enableLogging: Enable detailed logging for debuggingqwen3.rateLimitDelay: Delay between API calls in millisecondsqwen3.cacheEnabled: Enable response caching for improved performanceqwen3.cacheTTL: Cache time-to-live in seconds
Ctrl+Shift+Q(Mac:Cmd+Shift+Q): Open Chat PanelCtrl+Shift+A(Mac:Cmd+Shift+A): Ask Qwen3 a QuestionCtrl+Shift+I(Mac:Cmd+Shift+I): Get Inline SuggestionCtrl+Shift+E(Mac:Cmd+Shift+E): Explain Selected Code
- Install the extension from the VS Code Marketplace
- Get an API key:
- Visit OpenRouter and create an account
- Generate an API key for Qwen3 access
- Configure the extension:
- Open VS Code Settings (
Ctrl+,) - Search for "qwen3"
- Enter your API key in
Qwen3: Api Key
- Open VS Code Settings (
- Open the chat panel:
- Click the Qwen3 icon in the Activity Bar (sidebar)
- Or press
Ctrl+Shift+Q(Mac:Cmd+Shift+Q)
- Start coding with AI assistance:
- Type your questions in the chat
- Select code and use context menu options
- Attach files for multi-file context
- Apply code suggestions with one click
Initial release of Qwen3 Coder Assistant with core features including code suggestions, explanations, fixes, and generation capabilities.