f0ce0f7884
- Expand sitemap from 2 to 13 URLs (all docs pages) - Update JSON-LD featureList with Anthropic, OpenCode, TypeScript SDK - Update llms.txt with docs links, TS SDK, OpenCode plugin sections - Add READMEs for agentlens-sdk and opencode-agentlens packages - Add repository, homepage, author, bugs fields to both package.json
89 lines
2.9 KiB
Markdown
89 lines
2.9 KiB
Markdown
# opencode-agentlens
|
|
|
|
OpenCode plugin for AgentLens — trace your coding agent's decisions, tool calls, and sessions.
|
|
|
|
[](https://www.npmjs.com/package/opencode-agentlens)
|
|
[](https://github.com/repi/agentlens/blob/main/LICENSE)
|
|
|
|
## Requirements
|
|
|
|
- OpenCode >= 1.1.0
|
|
|
|
## Install
|
|
|
|
```bash
|
|
npm install opencode-agentlens
|
|
```
|
|
|
|
## Configuration
|
|
|
|
### Environment Variables
|
|
|
|
| Variable | Required | Default | Description |
|
|
|---|---|---|---|
|
|
| `AGENTLENS_API_KEY` | Yes | — | Your AgentLens API key. |
|
|
| `AGENTLENS_ENDPOINT` | No | AgentLens cloud | API endpoint URL. |
|
|
| `AGENTLENS_ENABLED` | No | `true` | Set to `false` to disable tracing. |
|
|
| `AGENTLENS_CAPTURE_CONTENT` | No | `true` | Capture message and tool output content. |
|
|
| `AGENTLENS_MAX_OUTPUT_LENGTH` | No | `10000` | Max characters to capture per output. |
|
|
| `AGENTLENS_FLUSH_INTERVAL` | No | `5000` | Flush interval in milliseconds. |
|
|
| `AGENTLENS_BATCH_SIZE` | No | `100` | Max items per batch before auto-flush. |
|
|
|
|
### OpenCode Setup
|
|
|
|
Add the plugin to your OpenCode configuration at `~/.config/opencode/opencode.json`:
|
|
|
|
```json
|
|
{
|
|
"plugins": [
|
|
{
|
|
"name": "agentlens",
|
|
"module": "opencode-agentlens"
|
|
}
|
|
]
|
|
}
|
|
```
|
|
|
|
Set your API key:
|
|
|
|
```bash
|
|
export AGENTLENS_API_KEY="your-api-key"
|
|
```
|
|
|
|
The plugin activates automatically when OpenCode starts. No code changes required.
|
|
|
|
## What Gets Captured
|
|
|
|
The plugin hooks into OpenCode's event system and records:
|
|
|
|
- **Sessions** — Full session lifecycle from start to finish, including duration and metadata.
|
|
- **Tool calls** — Every tool invocation with input arguments and output results (e.g., file reads, shell commands, code edits).
|
|
- **LLM calls** — Chat messages sent to and received from the model, including token usage.
|
|
- **Permission flows** — When the agent requests permission and whether it was granted or denied.
|
|
- **File edits** — File paths and change summaries produced by the agent.
|
|
|
|
All data is sent to your AgentLens instance where you can inspect traces, replay sessions, and analyze agent behavior.
|
|
|
|
## How It Works
|
|
|
|
The plugin registers handlers for OpenCode's event hooks:
|
|
|
|
| Event | What is recorded |
|
|
|---|---|
|
|
| Session start/end | Trace lifecycle, session metadata |
|
|
| `tool.execute.before` | Tool name, input arguments |
|
|
| `tool.execute.after` | Tool output, duration, success/failure |
|
|
| `chat.message` | LLM responses and assistant messages |
|
|
| `chat.params` | Model parameters and prompt configuration |
|
|
| `permission.ask` | Permission requests and user decisions |
|
|
|
|
Each OpenCode session maps to a single AgentLens trace. Tool calls and LLM interactions become spans within that trace.
|
|
|
|
## Documentation
|
|
|
|
Full documentation: [agentlens.vectry.tech/docs/opencode-plugin](https://agentlens.vectry.tech/docs/opencode-plugin)
|
|
|
|
## License
|
|
|
|
MIT
|