The Reviewers bullet stated a gh-search request trigger and a sequential first-this-second-that ordering; all four reviewer boxes actually run an org-wide pulls-API requested_reviewers sweep merged with the repos.txt backstop, deduplicated by (repo, PR) before acting (crew@b2fd864). The on-paper list narrows to the notifier's needs-ruling queue, repos.txt is the registry only on the triage box, and the Status block now carries the crew ref this description was last reconciled against. Part of the drift #148 reported; spec and citations in #149. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
528 B
528 B
- FLEET.md — the Reviewers wake describes the deployed sweep, not the
gh searchtrigger the bench replaced: the pulls-APIrequested_reviewerssweep across the org plus the named bot forks is source 1, therepos.txt/search poll an adds-only backstop, and the two are merged and deduplicated by (repo, PR) before acting. Only the notifier'sneeds-rulingqueue remains on paper;repos.txtis the registry only on the triage box; and the Status block now stamps the crew ref the file was last reconciled against (#149).