open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
ms-ai-architect/tests
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
..
fixtures feat(ms-ai-architect): Sesjon 4 - verifisering-ut (lag 5) + adversarial regresjonstest 2026-06-19 22:00:36 +02:00
kb-eval feat(ms-ai-architect): S1 judge bake-off harness + forhåndsregistrert gate (TDD) [skip-docs] 2026-06-26 20:10:58 +02:00
kb-update feat(ms-ai-architect): insertToc + backfill-toc applier (Fase 1b-verktøy) — store-fil-TOC foldet inn i Cosmo-utfasing 2026-06-26 11:43:30 +02:00
lib feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
screenshot chore: roll up in-progress changes across plugins 2026-05-16 21:02:23 +02:00
capture-fixture.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
run-e2e.sh test(ms-ai-architect): C2.4 lås K4 privat-sektor-paritet (regresjonsvakt) + omdøp feildøpt doc [skip-docs] 2026-06-22 17:39:11 +02:00
test-ai-act-output.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
test-cost-output.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
test-hooks.sh feat(ms-ai-architect): C2.2 valgfritt fritekst-felt free-context.md i onboarding (TDD) [skip-docs] 2026-06-22 14:16:00 +02:00
test-kb-integrity.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
test-onboarding-parity.sh feat(ms-ai-architect): Spor E E-polish — per-kategori typisk/sjelden-hint i onboarding Phase 1–5 (TDD) [skip-docs] 2026-06-23 20:00:07 +02:00
test-playground-actions.sh feat(ms-ai-architect): v1.15.0 — playground v3 project-view integration 2026-05-16 20:58:51 +02:00
test-playground-fingerprints.sh feat(ms-ai-architect): v1.15.0 — playground v3 project-view integration 2026-05-16 20:58:51 +02:00
test-playground-migrations.sh feat(ms-ai-architect): v1.15.0 — playground v3 project-view integration 2026-05-16 20:58:51 +02:00
test-playground-parsers.sh feat(ms-ai-architect): replace playground v2 with v3 + docs update 2026-05-03 20:16:37 +02:00
test-playground-projectview.sh feat(ms-ai-architect): v1.15.0 — playground v3 project-view integration 2026-05-16 20:58:51 +02:00
test-playground-v3.sh fix(ms-ai-architect): #7d privat-sektor-paritet — sektor-parametrisering + onboarding-forgrening + 2 nye kommandoer (audit §5) 2026-06-18 18:27:51 +02:00
test-plugin-discovery.sh test(ms-ai-architect): Sesjon 23 — auto_discover stale-felt assertion korrigert (søk-verifisert, 13/13) [skip-docs] 2026-06-21 13:48:40 +02:00
test-ros-output.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
test-security-output.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
test-summary-output.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00
validate-plugin.sh feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 2026-04-08 08:58:35 +02:00