- Add setup_forge() to bin/disinto: provisions Forgejo via Docker, creates admin + bot users (dev-bot, review-bot), generates API tokens, creates repo, and pushes code — all automated - Rename env vars: CODEBERG_TOKEN→FORGE_TOKEN, REVIEW_BOT_TOKEN→ FORGE_REVIEW_TOKEN, CODEBERG_REPO→FORGE_REPO, CODEBERG_API→ FORGE_API, CODEBERG_WEB→FORGE_WEB, CODEBERG_BOT_USERNAMES→ FORGE_BOT_USERNAMES (with backwards-compat fallbacks) - Rename API helpers: codeberg_api()→forge_api(), codeberg_api_all() →forge_api_all() (with compat aliases) - Add forge_url field to project TOML; load-project.sh derives FORGE_API/FORGE_WEB from forge_url + repo - Update parse_repo_slug() to accept any host URL, not just codeberg - Forgejo data stored under ~/.disinto/forgejo/ (not in factory repo) - Update all 58 files: agent scripts, formulas, docs, site HTML Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2.5 KiB
2.5 KiB
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. It scans for open
issues labeled action that have no active tmux session, then 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.shaction/action-agent.sh— Orchestrator: fetches issue body + prior comments, creates tmux session (action-{project}-{issue_num}) with interactiveclaude, injects formula prompt with phase protocol, entersmonitor_phase_loop(shared viadev/phase-handler.sh) for CI/review lifecycle or direct completion
Session lifecycle:
action-poll.shfinds openactionissues with no active tmux session.- Spawns
action-agent.sh <issue_num>. - Agent creates Matrix thread, exports
MATRIX_THREAD_IDso Claude's output streams to the thread via a Stop hook (on-stop-matrix.sh). - Agent creates tmux session
action-{project}-{issue_num}, injects prompt (formula + prior comments + phase protocol). - Agent enters
monitor_phase_loop(shared with dev-agent viadev/phase-handler.sh). - 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. - 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). - For human input: Claude sends a Matrix message and waits; the reply is injected into the session by
matrix_listener.sh.
Environment variables consumed:
FORGE_TOKEN,FORGE_REPO,FORGE_API,PROJECT_NAME,FORGE_WEBMATRIX_TOKEN,MATRIX_ROOM_ID,MATRIX_HOMESERVER— Matrix notifications + human inputACTION_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