ms-ai-architect/tests/kb-eval
Kjell Tore Guttormsen 6985ed1f5d feat(ms-ai-architect): Fase 0 steg 2 — verifiserings-fan-out (373 påstander) + gull-sett m/ deterministisk lastmod-join + TDD [skip-docs]
15 batcher (Opus 4.8 xhigh, read-only) verifiserte 55 sample-frame-filer mot live
MS Learn (strikt v2 bevis-krav: correct/outdated/wrong krever hentet learn-sitat,
ellers unsourced). 373 påstander: 259 correct, 29 outdated, 11 wrong, 74 unsourced.
40 reelle feil. lastmod_changed joinet i kode (registry sitemap_lastmod vs filens
dato): 0 filer ville staleness-loopen flagget -> alle 40 feil er judge-unike (rå
funn, krever tolkning i base-rate-rapporten). lib/base-rate.mjs (Wilson, lastmod,
aggregering) TDD 15 tester. Suite 538/538. Steg 3 (compute-base-rate + gate) gjenstår.
2026-06-26 15:16:10 +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-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