open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
ms-ai-architect/tests/kb-eval
History
Kjell Tore Guttormsen 3e39f2df6b feat(ms-ai-architect): S1 judge bake-off harness + forhåndsregistrert gate (TDD) [skip-docs] 
Deterministisk de-risk-harness for Fase 3-judgen (kjøres på frosset 373-påstands gull-sett):
- lib/judge-bakeoff.mjs: P-filter (volatil+fetchbar, price ekskl.), confusion-matrix
  for 3 armer (staleness/judge/hybrid), Wilson-bånd, forhåndsregistrert gate. 14 tester.
- extract-judge-claims.mjs: blind manifest (255 påstander, 0 label-lekkasje — testet invariant).
- judge-claim-prompt.md: blind per-påstands groundedness-judge (Opus xhigh, microsoft_docs_fetch).
- run-judge-bakeoff.mjs: join gull+results på id, gate-rapport (.json/.md).

Gate FORHÅNDSREGISTRERT (operatørvalg, før fan-out): recall ≥0.80, presisjon ≥0.70,
OG slår staleness (0/38). Evalueringspop P = 240 verifiserbare, 38 positive.
Suite 551/551 (538 + 13 nye).
2026-06-26 20:10:58 +02:00
..
test-apply-score-cache.test.mjs feat(ms-ai-architect): Spor D steg 1 — apply regenererer hel-korpus score-cache post-mutasjon (TDD) [skip-docs] 2026-06-23 19:51:04 +02:00
test-base-rate.test.mjs feat(ms-ai-architect): Fase 0 steg 2 — verifiserings-fan-out (373 påstander) + gull-sett m/ deterministisk lastmod-join + TDD [skip-docs] 2026-06-26 15:16:10 +02:00
test-build-sample-frame.test.mjs feat(ms-ai-architect): Fase 0 steg 1 — deterministisk sample-frame (45 volatil + 10 kontroll) + TDD [skip-docs] 2026-06-26 14:18:53 +02:00
test-eval.test.mjs feat(ms-ai-architect): Spor D N1–N5 — Anthropic-deterministiske skill-sjekker (TDD) [skip-docs] 2026-06-23 17:09:29 +02:00
test-judge-bakeoff.test.mjs feat(ms-ai-architect): S1 judge bake-off harness + forhåndsregistrert gate (TDD) [skip-docs] 2026-06-26 20:10:58 +02:00
test-k10-sibling-overlap.test.mjs feat(ms-ai-architect): Spor D steg A — eng+infra K10-fix → korpus-invariant ≥90 oppfylt 2026-06-23 17:56:43 +02:00
test-score-skill.test.mjs feat(ms-ai-architect): Spor D steg 2 — score-skill CLI (--json/--gate/--skill) (TDD) 2026-06-23 17:16:44 +02:00
test-skill-lifecycle-detect.test.mjs feat(ms-ai-architect): Sesjon 14 — B1 fullført (coverage/gap + bloat/stale) [skip-docs] 2026-06-20 11:34:57 +02:00
test-skill-ops-apply.test.mjs feat(ms-ai-architect): Sesjon 19 — B3 merge-apply (cross-skill + taksonomi-persist) [skip-docs] 2026-06-20 20:54:13 +02:00
test-skill-ops-create.test.mjs feat(ms-ai-architect): Sesjon 20 — B3 create_skill (dvelende, konstruktiv op) [skip-docs] 2026-06-20 21:37:19 +02:00
test-skill-ops-merge-apply.test.mjs feat(ms-ai-architect): Sesjon 19 — B3 merge-apply (cross-skill + taksonomi-persist) [skip-docs] 2026-06-20 20:54:13 +02:00
test-skill-ops-merge.test.mjs feat(ms-ai-architect): Sesjon 16 — B3 ledger action-lag + merge_skills dry-run-planner 2026-06-20 17:10:33 +02:00
test-skill-ops-sanitize-retire.test.mjs feat(ms-ai-architect): Sesjon 17 — B3 sanitize_skill + retire_skill dry-run-planners [skip-docs] 2026-06-20 17:45:37 +02:00
test-skill-score-gate.test.mjs feat(ms-ai-architect): Spor D Steg B — skill-quality lifecycle-gate + score-cache (TDD) 2026-06-23 18:26:29 +02:00
test-skill-score.test.mjs feat(ms-ai-architect): Spor D N1–N5 — Anthropic-deterministiske skill-sjekker (TDD) [skip-docs] 2026-06-23 17:09:29 +02:00
test-transform-criterion.test.mjs feat(ms-ai-architect): generator-anti-regresjon Fase 1c — composeKbFile + TOC-gate 2026-06-26 10:59:40 +02:00