Renn F 88d00aaa0a fix(pr-review): reject a verdict that contradicts the review's findings ...

post_pr_review (inbound external/fork PR review) derived both the recorded
notes_structured.pr_review.verdict AND the posted GitHub review event solely
from its `event` argument, which defaults to REQUEST_CHANGES — and, unlike the
in-path gate's pr_fail, it never required any findings. A reviewer that
concluded 'approve' in the summary but left event at the default filed (and
posted to the contributor's PR) a blocking 'changes requested' with nothing
cited, contradicting the approving summary the CEO saw on the PR Reviewer Notes
card.

Enforce a verdict<->findings invariant before any record or GitHub post:
- REQUEST_CHANGES must cite >=1 finding (almost always a forgotten
  event='APPROVE'), mirroring pr_fail's 'at least one issue' rule;
- APPROVE may not carry a blocker/major finding.
The check is the pure policy fn pr_review_conflict() wired through the new
choreographer _verdict_consistency_gate, rejected with a clear remediate hint.
Steer the agent at the source too: the flow MCP tool + request schema now spell
out the invariant and to pass event='APPROVE' explicitly for a clean PR.

2026-06-26 02:13:41 +02:00

..

content

fix(pr-review): reject a verdict that contradicts the review's findings

2026-06-26 02:13:41 +02:00

conventions

feat(conventions): modularity checks + scan-derived, language-aware rules

2026-06-22 14:26:25 +02:00

test_batch.py

MegaTask (#248)

2026-06-24 01:15:57 +02:00