Omar SobhandClaude Opus 5.5 abfba832e1 feat(judge): Kimi as a fallback independent judge when GLM cannot answer ...

GLM's plan limit ran out for the second time in a month, and with one judge
every conditioned phase on every mission fails until it resets. When the
primary independent judge errors, CLAWMATES_VALIDATOR_FALLBACK_MODEL (prod:
kimi:kimi-for-coding) judges instead, through the same independence checks
(one shared function) plus one more: never the primary's own family.

Measured first: judge-eval 15 cases x 3, kimi-for-coding 44/45 vs glm-5.3
43/45; goodhart — the false positive that once ruled Kimi out — 3/3.

When both fail, the primary's error leads so the phase runner still reads the
z.ai plan-limit code and does not spend the pass. Prod's kimi provider moved
to the anthropic format the eval used (host config, backed up).

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

2026-09-23 07:32:41 -05:00

..

src

feat(judge): Kimi as a fallback independent judge when GLM cannot answer

2026-09-23 07:32:41 -05:00

tests

feat(judge): the judge commits to a verification plan before it reads the evidence

2026-09-20 22:07:39 -05:00

Cargo.toml

feat(decide): cm-decide — typed calibrated decisions; Jev + local NLI backends; skill triage in shadow

2026-09-21 10:08:31 -05:00