Garry Tan 6fda08a692 ci(eval): brainbench gate job — compares HEAD's run against MAIN's baseline ...

git show origin/master:evals/brainbench/baselines/main.json is the compare
target, so a PR cannot rewrite the thing it's graded by (plan decision 4).
Hermetic, zero keys, ~15s. ci-brainbench-gate.sh is local parity (with an
ungated first-landing path); render-brainbench-delta.ts emits the step-summary
/ PR-body delta block from the --out artifact.

2026-06-12 12:06:22 -07:00

..

e2e.yml

v0.40.4.0 feat(search): selective graph signals + per-stage attribution + audit-writer unification (#1300)

2026-05-23 10:01:08 -07:00

heavy-tests.yml

v0.40.4.0 feat(search): selective graph signals + per-stage attribution + audit-writer unification (#1300)

2026-05-23 10:01:08 -07:00

release.yml

v0.40.4.0 feat(search): selective graph signals + per-stage attribution + audit-writer unification (#1300)

2026-05-23 10:01:08 -07:00

test.yml

ci(eval): brainbench gate job — compares HEAD's run against MAIN's baseline

2026-06-12 12:06:22 -07:00