feat(ms-ai-architect): Spor D steg A — eng+infra K10-fix → korpus-invariant ≥90 oppfylt

Skjerper ms-ai-infrastructure-description for å bryte build↔operate-overlappet
mot ms-ai-engineering (operatør-godkjent leaning, S38): "multi-region"→"cross-region"
og "edge AI architecture"→"edge AI deployment". Fjerner de delte distinktive tokenene
`multi` (vekt 0.5) og `architecture` (0.333) → eng↔infra combined 7.4167→6.5833 (< 7.0
terskel). Korpus-maks faller til 6.8333 (eng↔gov, pass). Begge edits sammen gir lavere
worst-case enn edit #1 alene (6.9167), derfor robust margin.

Resultat: K10-gulvet løftes for begge → eng 89→96, infra 89→96. ALLE 5 skills nå ≥90
(advisor 91, eng/gov/infra/sec 96). Korpus-invarianten (operatør-krav S38) oppfylt.

Judge-cache (🔑-regel): description-edit invaliderer infra K1. Re-judget mot det
operatør-kuraterte 20-settet — UENDRET 1.0/0.0/1.0 (edit fjerner kun tokens → kan ikke
gi falske positive; in-domain #2/#6 trigger fortsatt på BCDR/hybrid-vokabular).
K4/K7/K8/K9 uendret (body/refs urørt). Provenance oppdatert S11→S39.

Test: K10-real-five-testen pinnet pre-fix-baseline (eng+infra FAIL) — oppdatert til å
pinne korpus-invarianten (alle 5 pass, eng↔infra < 7.0). kb-eval 142/142, kb-update
316/316, validate 239/0, kb-integrity 192/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

scripts/kb-eval/data/judge-results.json

@@ -30,8 +30,8 @@
     "K9_noTimeSensitive": { "pass": true, "findings": [] }
   },
   "ms-ai-infrastructure": {
-    "_updated": "S11 (2026-06-20) — K1 authoritative (blinded judge vs curated 20-set); K9 prior S10",
-    "K1_triggerPrecision": { "provisional": false, "inDomainHitRate": 1.0, "outDomainFalsePositiveRate": 0.0, "precision": 1.0, "pass": true, "misclassified": [], "notes": "S11 authoritative: blinded judge vs operator-curated 20-set. 10/10 in-domain hits, 0/10 false positives. BCDR/edge/sovereign/hybrid in-domain all triggered; engineering/governance/security/advisor/cost correctly excluded." },
+    "_updated": "S39 (2026-06-23) — K1 RE-JUDGED after K10 description edit (multi-region→cross-region, edge AI architecture→deployment); K4/K7/K8/K9 unchanged (body/refs untouched), prior S10/S11",
+    "K1_triggerPrecision": { "provisional": false, "inDomainHitRate": 1.0, "outDomainFalsePositiveRate": 0.0, "precision": 1.0, "pass": true, "misclassified": [], "notes": "S39 re-judge vs operator-curated 20-set after K10 boundary-sharpening edit. 10/10 in-domain hits, 0/10 false positives — UNCHANGED from S11. Edit only removed tokens (multi, architecture) → cannot add false positives; in-domain #2 (multi-region failover) and #6 (hybrid arkitektur) still trigger on remaining BCDR/resilience/hybrid vocabulary. engineering/governance/security/advisor/cost still correctly excluded." },
     "K4_noDuplication": { "score": 5, "pass": true, "evidence": "S10 re-judge: consistent summary+pointer pattern; §1.2 RTO/RPO now ~2 lines delegating to bcdr/rto-rpo-planning-ai-services.md (265 lines). SLA table replaced by relative-guidance prose. No procedural duplication." },
     "K7_imperativeStyle": { "ratio": 1.0, "pass": true, "notes": "10/10 sampled instruction sentences imperative/infinitive." },
     "K8_sourceCitation": { "ratio": 1.0, "pass": true, "notes": "5/5 'Last updated: 2026-02' + Status; no source-URL on header line." },