Garry Tan b3fd66bfc6 fix: codex adversarial round — CI aggregate gap + first-landing verification + scoring honesty ...

(1) test-status never read needs.brainbench.result: a failing gate job left
the branch-protection aggregate green — merge-bypassable. Now in the loop.
(2) The first-landing path verifies the run against the COMMITTED baseline
(an unverified initial merge could seed a doctored baseline for every future
PR). (3) One stored fact row may satisfy at most one gold probe (merged/
broad extractions inflated fidelity via unconstrained find()). (4) The
slug-granularity limit of source-isolation detection is disclosed in the
methodology doc with a pointer to the engine-layer fuzz that covers the
content-leak case. Plus 30s timeouts on engine-touching tests (observed 5s
default flaking at load avg 20).

2026-06-12 13:24:34 -07:00

..

BRAINBENCH.md

fix: codex adversarial round — CI aggregate gap + first-landing verification + scoring honesty

2026-06-12 13:24:34 -07:00

METRIC_GLOSSARY.md

fix: pre-landing review fixes — specialist round (4 reviewers, 22 findings)

2026-06-12 12:38:34 -07:00

SEARCH_MODE_METHODOLOGY.md

v0.42.25.0 fix(pricing): unify chat-model pricing into one canonical source; add Opus 4.8 (#1819) (#1827)

2026-06-03 23:00:11 -07:00