Package Exports

@tarquinen/opencode-dcp
@tarquinen/opencode-dcp/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@tarquinen/opencode-dcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Dynamic Context Pruning Plugin

OpenCode plugin that optimizes token usage by analyzing conversation history and pruning obsolete tool outputs from requests.

Features

Zero Configuration: Uses the free opencode/big-pickle model - no API keys required
Automatic Optimization: Runs in the background when sessions become idle
Smart Analysis: Uses AI to identify truly obsolete context
Debug Logging: Optional file-based logging for troubleshooting

How It Works

When a session becomes idle, the Janitor analyzes the conversation using shadow inference
It identifies tool call outputs that are no longer relevant to the conversation
These IDs are stored in memory for that session
On subsequent requests, a custom fetch function filters out the obsolete tool responses
Result: Fewer tokens sent to the LLM, lower costs, faster responses

Installation

Via NPM (Recommended)

Add the plugin to your OpenCode configuration:

Global: ~/.config/opencode/opencode.json
Project: .opencode/opencode.json

{
  "plugin": [
    "@tarquinen/opencode-dcp"
  ]
}

Then restart OpenCode. The plugin will automatically:

Analyze conversations when sessions become idle
Identify obsolete tool outputs
Prune them from future requests
Save you tokens and money!

Local Development

If you want to modify the plugin, you can clone this repository and use a local path:

{
  "plugin": [
    "./plugin/dynamic-context-pruning"
  ]
}

Configuration

No configuration required! The plugin works out of the box with:

Zero-config setup using opencode/big-pickle model
Automatic background optimization
Smart AI-powered analysis

Optional: Enable debug logging by creating ~/.config/opencode/dynamic-context-pruning-config.json:

{
  "debug": true
}

Debug logs will be written to the plugin's logs/ directory.

Architecture

Janitor: Background process that analyzes sessions using opencode/big-pickle model
State Manager: In-memory store for pruned tool call IDs per session
Fetch Injector: Injects custom fetch via chat.params hook
Pruning Fetch Wrapper: Filters request bodies based on session state
Logger: File-based debug logging system

Development Status

Current implementation status: Step 1 - Project Scaffolding ✅

See @notes/dynamic-context-pruning/IMPLEMENTATION-PLAN.md for full implementation details.

License

MIT