ATOCore/openclaw-plugins/atocore-capture/README.md

# AtoCore Capture + Context Plugin for OpenClaw

Two-way bridge between OpenClaw agents and AtoCore:

**Capture (since v1)**
- watches user-triggered assistant turns
- POSTs `prompt` + `response` to `POST /interactions`
- sets `client="openclaw"`, `reinforce=true`
- fails open on network or API errors

**Context injection (Phase 7I, v2+)**
- on `before_agent_start`, fetches a context pack from `POST /context/build`
- prepends the pack to the agent's prompt so whatever LLM runs underneath
  (sonnet, opus, codex, local model — whichever OpenClaw delegates to)
  answers grounded in what AtoCore already knows
- original user prompt is still what gets captured later (no recursion)
- fails open: context unreachable → agent runs as before

## Config

```json
{
  "baseUrl": "http://dalidou:8100",
  "minPromptLength": 15,
  "maxResponseLength": 50000,
  "injectContext": true,
  "contextCharBudget": 4000
}
```

- `baseUrl` — defaults to `ATOCORE_BASE_URL` env or `http://dalidou:8100`
- `injectContext` — set to `false` to disable the Phase 7I context injection and make this a pure one-way capture plugin again
- `contextCharBudget` — cap on injected context size. `/context/build` respects it too; this is a client-side safety net. Default 4000 chars (~1000 tokens).

## Notes

- Project detection is intentionally left empty — AtoCore's extraction pipeline handles unscoped interactions and infers the project from content.
- Extraction is **not** part of this plugin. Interactions are captured; batch extraction runs via cron on the AtoCore host.
- Context injection only fires for user-triggered turns (not heartbeats or system-only runs).
- Timeouts: context fetch is 5s (short so a slow AtoCore never blocks a user turn); capture post is 10s.