BuzzbeeSCD/openchamber
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: make AI review verdicts advisory

Browse Source 
Removes the separate review check and relies on review labels/comments instead
Marks workflow/tooling failures with review:automation-failed
Updates review guidance to reflect the advisory verdict model
This commit is contained in:
Bohdan Triapitsyn
2026-07-22 10:33:25 +03:00
parent a62731bd6e
commit 733bd37c37
3 changed files with 25 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.opencode/agent/pr-review.md
+1 -1
View File
@@ -179,7 +179,7 @@ Choose exactly one review verdict:
- `blocked`: at least one concrete correctness, security, mandatory-guidance, or contribution-contract blocker must be fixed.
- `human-review-required`: the PR changes review policy/automation or another trust boundary that automation must not clear by itself, or safe automated review is otherwise impossible.
Verdict precedence is `human-review-required`, `blocked`, `needs-evidence`, then `pass`. CI status is intentionally outside this verdict: a review may return `pass` while a separate required check fails, and both gates must pass independently before merge.
Verdict precedence is `human-review-required`, `blocked`, `needs-evidence`, then `pass`. CI status is intentionally outside this verdict: a review may return `pass` while a separate required check fails. The AI verdict is advisory, is communicated through the `review:*` label and review comment, and must not fail the pull request check.
## Comment style