Files

Anto01 9c91d778d9 feat: Claude Code context injection (UserPromptSubmit hook)

Closes the asymmetry the user surfaced: before this, Claude Code
captured every turn (Stop hook) but retrieval only happened when
Claude chose to call atocore_context (opt-in MCP tool). OpenClaw had
both sides covered after 7I; Claude Code did not.

Now symmetric. Every Claude Code prompt is auto-sent to
/context/build and the returned pack is prepended via
hookSpecificOutput.additionalContext — same as what OpenClaw's
before_agent_start hook now does.

- deploy/hooks/inject_context.py — UserPromptSubmit hook. Fail-open
  (always exit 0). Skips short/XML prompts. 5s timeout. Project
  inference mirrors capture_stop.py cwd→slug table. Kill switch:
  ATOCORE_CONTEXT_DISABLED=1.
- ~/.claude/settings.json registered the hook (local config, not
  committed; copy-paste snippet in docs/capture-surfaces.md).
- Removed /wiki/capture from topnav. Endpoint still exists but the
  page is now labeled "fallback only" with a warning banner. The
  sanctioned surfaces are Claude Code + OpenClaw; manual paste is
  explicitly not the design.
- docs/capture-surfaces.md — scope statement: two surfaces, nothing
  else. Anthropic API polling explicitly prohibited.

Tests: +8 for inject_context.py (exit 0 on all failure modes, kill
switch, short prompt filter, XML filter, bad stdin, mock-server
success shape, project inference from cwd). Updated 2 wiki tests
for the topnav change. 450 → 459.

Verified live with real AtoCore: injected 2979 chars of atocore
project context on a cwd-matched prompt.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-19 12:01:41 -04:00

2.9 KiB

Raw Blame History

AtoCore — sanctioned capture surfaces

Scope statement: AtoCore captures conversations from two surfaces only. Everything else is intentionally out of scope.

Surface	Hooks	Status
Claude Code (local CLI)	`Stop` (capture) + `UserPromptSubmit` (context injection)	both installed
OpenClaw (agent framework on T420)	`before_agent_start` (context injection) + `llm_output` (capture)	both installed (v0.2.0 plugin, Phase 7I)

Both surfaces are symmetric — push (capture) and pull (context injection on prompt submit) — so AtoCore learns from every turn AND every turn is grounded in what AtoCore already knows.

Why these two?

Stable hook APIs. Claude Code exposes Stop and UserPromptSubmit lifecycle hooks with documented JSON contracts. OpenClaw exposes before_agent_start and llm_output. Both run locally where we control the process.
Passive from the user's perspective. No paste, no manual capture command, no "remember this" prompt. You just use the tool and AtoCore absorbs everything durable.
Failure is graceful. If AtoCore is down, hooks exit 0 with no output — the user's turn proceeds uninterrupted.

Why not Claude Desktop / Claude.ai web / Claude mobile / ChatGPT / …?

Claude Desktop has MCP but no Stop-equivalent hook for auto-capture; auto-capture would require system-prompt coercion ("call atocore_remember every turn"), which is fragile.
Claude.ai web has no hook surface — would need a browser extension (real project, not shipped).
Claude mobile app has neither hooks nor MCP — nothing to wire into.
ChatGPT etc. — same as above.

Anthropic API log polling is explicitly prohibited.

If you find yourself wanting to capture from one of these, the real answer is: use Claude Code or OpenClaw for the work that matters. Don't paste chat transcripts into AtoCore — that contradicts the whole design principle of passive capture.

A /wiki/capture fallback form still exists (the endpoint /interactions is public) but it is not promoted in the UI and is documented as a last-resort escape hatch. If you're reaching for it, something is wrong with your workflow, not with AtoCore.

Hook files

deploy/hooks/capture_stop.py — Claude Code Stop → POSTs /interactions
deploy/hooks/inject_context.py — Claude Code UserPromptSubmit → POSTs /context/build, returns pack via hookSpecificOutput.additionalContext
openclaw-plugins/atocore-capture/index.js — OpenClaw plugin v0.2.0: capture + context injection

Both Claude Code hooks share a _infer_project table mapping cwd to project slug. Keep them in sync when adding a new project path.

Kill switches

ATOCORE_CAPTURE_DISABLED=1 → skip Stop capture
ATOCORE_CONTEXT_DISABLED=1 → skip UserPromptSubmit injection
OpenClaw plugin config injectContext: false → skip context injection (capture still fires)

All three are documented in the respective hook/plugin files.

2.9 KiB Raw Blame History