chore(ms-ai-architect): refresh KB critical-bucket — 15 files [skip-docs]

KB-currency refresh (critical priority, 2026-06-19) via /architect:kb-update.
15 critical cost/arkitektur-filer re-verifisert mot Microsoft Learn (MCP).

Hovedendringer:
- Azure AI Search Serverless (Preview) prismodell (rag-cost, rag-query,
  vector-storage, rag-enterprise-scale)
- Agentic retrieval GA-split (2026-04-01 REST GA, portal preview) + Foundry IQ
- AI gateway multi-provider (Anthropic v2 / Google Vertex), unified model API
  (preview), Foundry-integrasjon (enterprise-arch, ai-services-cost,
  multi-model, cost-tracking)
- FOCUS-skjema + Cost Mgmt -> ADLS Gen2 -> Fabric -> Power BI pipeline
  (cost-management, cost-allocation)
- FinOps hub AI-agent via Azure MCP / Copilot Studio (budget-forecasting)
- OTel trace-based sampling for logs (observability)
- Korreksjoner: semantic-cache score-threshold = AVSTAND (0.15, ikke 0.85
  cosine-likhet); llm-emit-token-metric maks 5 custom dimensions;
  Foundry RBAC-renames (Owner/Contributor = kun mgmt); Researcher/Analyst er
  ikke agenter
- Alle 15 Last updated -> 2026-06-19

High-bucket (49 filer) UTSATT til egen sesjon (operatoer-valg).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ

skills/ms-ai-security/references/cost-optimization/vector-storage-cost-optimization.md

@@ -1,6 +1,6 @@
 # Vector Storage and Embedding Cost Optimization
 
-**Last updated:** 2026-05
+**Last updated:** 2026-06-19
 **Status:** GA
 **Category:** Cost Optimization & FinOps for AI
 
@@ -403,6 +403,8 @@ Eksempel: 5 millioner dokumenter, gjennomsnittlig 2000 tokens per dokument
 
 **Viktig:** Eldre services (pre-April 2024) har lavere quotas. Sjekk oppgraderingsmulighet: `az search service show --name <service> --resource-group <rg>`.
 
+**Serverless (Preview, MCP 2026-06):** Azure AI Search tilbyr nå også en **Serverless**-prismodell (forbruksbasert: Compute Units/time + per-GB/mnd lagring) ved siden av Dedicated-tierne over. For store, men sporadisk aksesserte vektor-indekser kan Serverless redusere idle-kost. Per juni 2026 er den i preview (West Central US, Switzerland North, Japan East), uten SLA, mangler enkelte features (index aliases, debug sessions, shared private link), og støtter ikke migrering til/fra Dedicated.
+
 ### Embedding-kostnader (Azure OpenAI)
 
 | Modell | Input (per 1M tokens) | Use case |