OpenCode Go Chat Provider for VS Code

Integrates OpenCode Go models into VS Code Copilot Chat with advanced features including vision support and tool calling.

Features

• Multiple Model Support

  • GLM-5: 202K context window, up to 131K output tokens
  • GLM-5.1: 202K context window, up to 131K output tokens
  • Kimi K2.5: 262K context window, up to 65K output tokens, vision support
  • MiMo-V2-Pro: 1,048K context window, up to 131K output tokens
  • MiMo-V2-Omni: 262K context window, up to 65K output tokens, vision support
  • MiniMax M2.5: 196K context window, up to 131K output tokens
  • MiniMax M2.7: 196K context window, up to 131K output tokens

• Advanced Capabilities

  • Tool calling support for VS Code chat participants
  • Streaming responses via Server-Sent Events (SSE)
  • Vision support via Kimi K2.5 and MiMo-V2-Omni
  • Automatic image-to-text conversion for non-vision models

• Secure API Key Management

  • Stored securely in VS Code SecretStorage
  • Managed via Command Palette (OpenCode Go: Manage OpenCode Go Provider)

Installation

From Source

1. Clone the repository:

git clone https://github.com/Ryosuke-Asano/oc-go-provider-extension.git
cd oc-go-provider-extension

2. Install dependencies:

npm install

3. Compile the project:

npm run compile

4. Package the extension:

npm run package

5. Install the .vsix file:

code --install-extension opencode-go-vscode-chat-*.vsix

Setup

1. Open VS Code
2. Open Command Palette (Cmd/Ctrl + Shift + P)
3. Run OpenCode Go: Manage OpenCode Go Provider
4. Enter your OpenCode Go API key

Get your API key from OpenCode.

Usage

Once configured, select OpenCode Go as your chat provider in VS Code Copilot Chat:

• Open the Chat view (Cmd/Ctrl + Alt + I)
• Click the provider selector
• Choose an OpenCode Go model (GLM-5, GLM-5.1, Kimi K2.5, MiMo-V2-Pro, MiMo-V2-Omni, MiniMax M2.5, or MiniMax M2.7)

Supported Models

Token limits below are the values currently used by this extension and may change if OpenCode Go updates model limits.

MCP Integration

This extension integrates with OpenCode Go's MCP (Model Context Protocol) server:

• Vision MCP: Image analysis using MiMo-V2-Omni

Development

See CONTRIBUTING.md for detailed development guidelines.

Quick Start

# Install dependencies
npm install

# Watch for changes
npm run watch

# Run tests
npm test

# Lint code
npm run lint

# Format code
npm run format

Project Structure

src/
├── extension.ts    # Extension entry point, activation
├── provider.ts     # Main chat provider implementation
├── types.ts        # Type definitions and model configuration
├── tools.ts        # Language model tool definitions
├── mcp.ts          # MCP client for tool integration
└── utils.ts        # Utility functions for message/tool conversion

Requirements

• VS Code 1.104.0 or later
• Node.js 20 or later (for development)
• OpenCode Go API key

Troubleshooting

API Key Issues

If you see authentication errors:

1. Run OpenCode Go: Manage OpenCode Go Provider
2. Verify your API key is correct
3. Ensure your OpenCode Go subscription is active

Vision Not Working

For non-vision models (GLM-5, GLM-5.1, MiMo-V2-Pro, MiniMax M2.5, MiniMax M2.7):

• Images are automatically converted to text descriptions using Vision MCP
• If the MCP tool fails, the extension internally uses MiMo-V2-Omni for image analysis
• MiMo-V2-Omni is also available as a selectable model with direct vision support

Large Context Errors

If you encounter token limit errors:

• Reduce the amount of code/context in your message
• The extension enforces model-specific context limits

Changelog

See CHANGELOG.md for version history.

License

MIT © 2025 Ryosuke Asano

License

Links

• Repository
• Issue Tracker
• OpenCode