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

..

agentPayloadCorpus.ts

chore(perf): add deterministic request-body heap benchmark (#7847) (#8549)

2026-07-26 03:52:42 -03:00

request-body-heap.ts

chore(perf): add deterministic request-body heap benchmark (#7847) (#8549)

2026-07-26 03:52:42 -03:00

routing-events-bench.ts

feat(routing): adaptive feedback loop v2 — operational/semantic quality, confidence, TTFT/ITL, end-to-end test (#10881)

2026-08-20 17:28:30 -03:00

video-bridge-bench.ts

fix(responses-continuation): recover a real id/output for passthrough and translate-mode replies (#11434)

2026-08-24 19:57:12 -03:00

video-bridge-contact-sheet-eval.ts

fix(responses-continuation): recover a real id/output for passthrough and translate-mode replies (#11434)

2026-08-24 19:57:12 -03:00

video-bridge-fu07-eval.ts

fix(responses-continuation): recover a real id/output for passthrough and translate-mode replies (#11434)

2026-08-24 19:57:12 -03:00

video-bridge-promotion-eval.ts

test(video): freeze FU-07/FU-09 promotion-evidence manifest, aggregator, evaluator and allowlist scaffold (#11656)

2026-08-29 06:49:56 -03:00