CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-18 19:02:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(eval-harness): eng-review qid boundary matches the real skill-name prefix

Browse Source 
Live qids render as gstack-qid:plan-eng-review-<slug> ({skill}-{slug}
convention); the boundary anchored eng-review- immediately after the
colon and never matched, leaving the batching counter blind while the
transcript showed per-finding questions being asked one by one.
This commit is contained in:
Garry Tan
2026-08-15 00:09:51 -07:00
parent 5a6a686635
commit 9889f27491
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/claude-pty-runner.ts
+5 -3
View File
@@ -1257,10 +1257,12 @@ export const engStep0Boundary: Step0BoundaryPredicate = (fp) =>
) || ) ||
// plan-eng-review's Step 0 may legitimately end with NO scope-reduction / // plan-eng-review's Step 0 may legitimately end with NO scope-reduction /
// learnings AUQ. When it does, the first answered review-phase question — // learnings AUQ. When it does, the first answered review-phase question —
// tagged <gstack-qid:eng-review-...> by the question-tuning resolver — // tagged <gstack-qid:plan-eng-review-...> ({skill}-{slug} convention) —
// must fire the boundary, or every per-finding AUQ stays classified // must fire the boundary, or every per-finding AUQ stays classified
// preReview and the multi-finding batching counter reads 0. // preReview and the multi-finding batching counter reads 0. Anchor allows
/gstack-qid:\s*eng-review-/i.test(fp.promptSnippet); // the skill-name prefix; live qids observed: plan-eng-review-jitter,
// plan-eng-review-idempotency, plan-eng-review-todos-e2e-concurrent.
/gstack-qid:\s*(?:plan-)?eng-review-/i.test(fp.promptSnippet);
export const designStep0Boundary: Step0BoundaryPredicate = (fp) => export const designStep0Boundary: Step0BoundaryPredicate = (fp) =>
/design system|design posture|design score|first dimension/i.test( /design system|design posture|design score|first dimension/i.test(