johba/disinto
1
0
Fork 0
Code Issues 4 Pull requests Projects Releases Packages Wiki Activity Actions
disinto/action/AGENTS.md
johba daf08fe62d chore: gardener housekeeping 2026-03-27 
- Update AGENTS.md watermarks to current HEAD across all 10 files
- dev/AGENTS.md: document rebase-before-push and _inject_into_session
- review/AGENTS.md: document formal forge review fallback in review-poll
- gardener/pending-actions.json: close #3 (already implemented in PR #2)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-27 00:05:07 +00:00

2.9 KiB
Raw Blame History

Action Agent

Role: Execute operational tasks described by action formulas — run scripts, call APIs, send messages, collect human approval. Shares the same phase handler as the dev-agent: if an action produces code changes, the orchestrator creates a PR and drives the CI/review loop; otherwise Claude closes the issue directly.

Trigger: action-poll.sh runs every 10 min via cron. Sources lib/guard.sh and calls check_active action first — skips if $FACTORY_ROOT/state/.action-active is absent. Then scans for open issues labeled action that have no active tmux session, and spawns action-agent.sh <issue-number>.

Key files:

  • action/action-poll.sh — Cron scheduler: finds open action issues with no active tmux session, spawns action-agent.sh
  • action/action-agent.sh — Orchestrator: fetches issue body + prior comments, checks all dependencies via lib/parse-deps.sh before spawning (skips silently if any dep is still open), creates tmux session (action-{project}-{issue_num}) with interactive claude, injects formula prompt with phase protocol, enters monitor_phase_loop (shared via dev/phase-handler.sh) for CI/review lifecycle or direct completion

Session lifecycle:

  1. action-poll.sh finds open action issues with no active tmux session.
  2. Spawns action-agent.sh <issue_num>.
  3. Agent creates tmux session action-{project}-{issue_num}, injects prompt (formula + prior comments + phase protocol).
  4. Agent enters monitor_phase_loop (shared with dev-agent via dev/phase-handler.sh).
  5. Path A (git output): Claude pushes branch → PHASE:awaiting_ci → handler creates PR, polls CI → injects failures → Claude fixes → push → re-poll → CI passes → PHASE:awaiting_review → handler polls reviews → injects REQUEST_CHANGES → Claude fixes → approved → merge → cleanup.
  6. Path B (no git output): Claude posts results as comment, closes issue → PHASE:done → handler cleans up (kill session, docker compose down, remove temp files).
  7. For human input: Claude writes PHASE:escalate; human responds via vault/forge.

Crash recovery: on PHASE:crashed or non-zero exit, the worktree is preserved (not destroyed) for debugging. Location logged. Supervisor housekeeping removes stale crashed worktrees older than 24h.

Environment variables consumed:

  • FORGE_TOKEN, FORGE_ACTION_TOKEN (falls back to FORGE_TOKEN), FORGE_REPO, FORGE_API, FORGE_URL, PROJECT_NAME, FORGE_WEB
  • ACTION_IDLE_TIMEOUT — Max seconds before killing idle session (default 14400 = 4h)
  • ACTION_MAX_LIFETIME — Max total session wall-clock seconds (default 28800 = 8h); caps session independently of idle timeout

FORGE_REMOTE: action-agent.sh auto-detects the git remote for FORGE_URL (same logic as dev-agent). Exported as FORGE_REMOTE, used for worktree creation and push instructions injected into the Claude prompt.