Pair Coding Agent - VS Code Extension

Your intelligent AI pair programming partner with complete privacy using your own fine-tuned local LLM.

🚀 Features

🎯 Intelligent Pair Programming

• Modern AI Interface: Beautiful, responsive interface with professional design
• Unified Experience: Single panel containing all functionality - chat, workspace analysis, auto mode
• Intuitive Design: Clean, modern UI optimized for developer productivity

🔒 Complete Privacy

• 100% Local Processing: Your code never leaves your machine
• Fine-tuned Model: Uses your own locally trained LLM for personalized assistance
• No External Dependencies: Works entirely offline once set up

🤖 Intelligent Features

• Context-Aware Chat: Understands your codebase and provides relevant suggestions
• Auto Mode: Autonomous task execution with step-by-step planning
• Workspace Analysis: Deep understanding of your project structure and dependencies
• Code Generation: Generate, optimize, and refactor code with AI assistance

⚡ Advanced Capabilities

• Real-time Context: Automatically includes relevant files and code in conversations
• Multi-language Support: Works with all major programming languages
• Code Actions: Copy, insert, and modify code directly from chat
• Session Management: Persistent conversations with history

📦 Installation

Prerequisites

1. Local LLM Server: Ensure your fine-tuned LLM server is running on http://localhost:8001
2. VS Code: Version 1.80.0 or higher

Install Extension

1. Download the .vsix file from releases
2. Open VS Code
3. Go to Extensions view (Ctrl+Shift+X)
4. Click "..." menu → "Install from VSIX..."
5. Select the downloaded file

Quick Setup

1. Open VS Code
2. Click the robot icon in the Activity Bar
3. The extension will automatically connect to your local LLM server
4. Start chatting with your AI assistant!

🔧 Configuration

Settings

• Server URL: pairCodingAgent.serverUrl (default: http://localhost:8001)
• Temperature: pairCodingAgent.temperature (default: 0.7)
• Max Tokens: pairCodingAgent.maxTokens (default: 2000)
• Auto Mode: pairCodingAgent.autoMode (default: false)
• Context Lines: pairCodingAgent.contextLines (default: 50)

Local LLM Server

Ensure your local server provides these endpoints:

• GET /health - Health check with model status
• POST /api/chat/completions - OpenAI-compatible chat completions

🎯 Usage

Basic Chat

1. Click the robot icon in the Activity Bar
2. Type your question in the input field
3. Get intelligent responses from your fine-tuned model

Auto Mode

1. Enable Auto Mode toggle in the chat panel
2. Ask for complex tasks like "Create a REST API with authentication"
3. Watch as the AI autonomously plans and executes the task

Context Awareness

• The AI automatically includes relevant files from your workspace
• Selected code is automatically included in the context
• Project structure and dependencies are analyzed for better responses

Code Actions

• Copy: Copy generated code to clipboard
• Insert: Insert code at cursor position
• Optimize: Get optimized versions of your code
• Test: Generate unit tests for your functions

🔄 Comparison with Cloud AI Assistants

🛠️ Development

Building from Source

# Clone the repository
git clone <repository-url>
cd augment-ai-clone

# Install dependencies
npm install

# Compile TypeScript
npm run compile

# Package extension
vsce package

Local Development

# Watch mode for development
npm run watch

# Open in VS Code
code .

# Press F5 to launch Extension Development Host

🔧 Troubleshooting

Connection Issues

• Ensure your local LLM server is running on the configured port
• Check the server URL in settings
• Verify the server provides the required endpoints

Performance Issues

• Adjust the temperature and max tokens settings
• Reduce context lines if responses are slow
• Check your local model's performance capabilities

Auto Mode Issues

• Ensure Auto Mode is enabled in settings
• Check that the AI service is connected
• Review the task results panel for detailed error information

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

📞 Support

• Issues: Report bugs and feature requests on GitHub
• Documentation: Check the wiki for detailed guides
• Community: Join our Discord for discussions

Experience intelligent pair programming with complete privacy and control using your own fine-tuned local model!