Files
OmniRoute/scripts
Markus Hartung 392db9558a test(video): freeze FU-07/FU-09 promotion-evidence manifest, aggregator, evaluator and allowlist scaffold (#11656)
Ships the harness and contract the promotion-evidence run needs, all TDD'd: a
frozen Zod manifest schema covering the 8 required scenario kinds with >=3
repetitions per case, deterministic declarative fixture recipes, a pure
medians/p95 metrics aggregator, a pure FU-07/FU-09 promotion-verdict
evaluator applying the ticket's exact thresholds (missing token usage always
holds), a digest-only persistence layer that never retains raw media or raw
model responses, and a versioned per-model promotion allowlist shipped empty
with every model defaulting to hold. The FU-07/FU-09 promotion verdicts
themselves remain HOLD pending a real evidence run on VPS 192.168.0.15 —
this PR does not and cannot fabricate that evidence.
2026-08-29 06:49:56 -03:00
..
2026-06-19 06:49:01 -03:00
2026-06-23 17:06:18 -03:00
2026-08-26 14:25:01 -03:00
2026-08-26 14:25:01 -03:00
2026-06-17 19:26:32 -03:00
2026-07-29 15:18:55 -03:00
2026-06-27 09:07:12 -03:00
2026-07-13 09:12:40 -03:00
2026-07-29 15:18:55 -03:00
2026-07-13 09:12:40 -03:00