Files

T

Keysat 063e6947f7 Redact thread on merge success even if deploy fails; add clear command

A merge whose post-merge deploy failed left the review thread orphaned (redaction was gated on deploy success). Now the thread always redacts on merge success and the deploy-failure warning is posted at top level so it survives. New clear/resolve command redacts an orphaned thread without touching the PR.

2026-06-28 21:17:36 -05:00

1.3 KiB

Raw Blame History

gitea-review-bot

A thin Matrix bot that reviews and merges your Gitea pull requests, one review room per repo. Separate from matrix-bridge (which runs interactive Claude Code sessions) — this bot's only job is PR review.

How it works

Create a Matrix room named like a repo and invite the bot. It auto-joins and maps the room to <owner>/<repo> (and ~/Projects/<repo> on the Mac), then posts an onboarding message.
It polls that repo's open PRs and posts each as a thread: a headless claude -p review (with an optional subagent panel) run on the Mac over SSH.
In the thread: merge (then yes) or reject. A merge auto-deploys (if enabled) and then redacts the thread, so the room shows only open PRs; if the deploy fails, the thread still clears and a standalone "deploy manually" warning stays in the room. clear redacts an orphaned thread without touching the PR.

Pick which review agents run per room in chat: agents +reviewer +security -adjudicator.

Run (on the Spark)

Copy config.example.toml → config.toml and .env.example → .env; fill them in (Matrix creds, GITEA_TOKEN, the [mac] SSH alias + reused matrix-bridge wrapper paths, [gitea]).
docker compose up -d --build. Logs: docker compose logs -f.

See AGENTS.md for the full design, placement, and decisions.

1.3 KiB Raw Blame History

gitea-review-bot

How it works

Run (on the Spark)

1.3 KiB

Raw Blame History