Two issues surfaced on first live run:
- The per-run cap truncated the PR list to the lowest-numbered PR, so a
comment on a higher-numbered PR was never scanned. The cap now limits only
how many PRs Claude RUNS on; comment-less PRs are skipped for free, so newer
PRs are never crowded out.
- The bot posts as the repo owner's account, so excluding "the bot's own
comments" by author also excluded the owner's legitimate review comments
(and required a read:user token scope, which 403'd). Replaced with a guard
that excludes only comments carrying the HANDLED_TAG marker -- robust even
when the bot and the reviewer are the same account. The /user call is gone.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Sibling to claude-issue-watcher.sh: polls open Claude-raised PRs (head
branch under claude/, or labelled claude-pr) for review comments carrying
the marker `claude-review:` — in the PR conversation, review summaries, or
inline on-file comments — and runs headless Claude Code on the PR's own
branch to address them, pushing the follow-up commit(s) to the same branch.
- Authorization gate: only repo collaborators (write access) + the owner can
trigger it; the bot's own comments are ignored.
- Idempotent: handled comments are tracked by a hidden marker on the bot's
acknowledgements, so the 10-min poll never redoes a comment.
- Own clone (~/pelagia-pr-review), config, and lock so it never races the
issue watcher. Token needs write:repository + write:issue.
Adds the script, an example config, .gitignore entries for the live
config/lock, and an automation/README.md section with deploy + cron steps.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
