open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity

chore(ms-ai-architect): refresh KB medium-bucket — 74 files [skip-docs]

Browse source 
KB-currency refresh (medium priority, 2026-06-19) via /architect:kb-update.
74 medium-prioritets filer re-verifisert mot Microsoft Learn (MCP) — delegert
til 15 parallelle Opus-subagenter (3 bølger) gruppert etter delt kilde, med
disjunkte fil-sett. Verifisert i hovedkontekst (scope-sjekk + diff-review av
de faktatunge gruppene + tester).

Hovedendringer (faktuelle korreksjoner + currency):
- Azure AI Search semantic ranker: TILGJENGELIG PÅ ALLE TIERS (også Free/Basic
  m/ gratis månedlig kvote) — gammel KB sa feilaktig "kun S1+". Korrigert i
  tier-tabell, anti-patterns og beslutningstabell (azure-ai-search-setup).
- APIM score-threshold = DISTANSE (lavere = strengere): tuning-tabellen i
  rag-caching-optimization hadde retningen baklengs — invertert til korrekt.
- Agentic retrieval GA/preview-nyanse presisert (hovedkontekst-korreksjon mot
  agentic-retrieval-how-to-migrate): GA via REST 2026-04-01 returnerer EKSTRAKTIV
  grounding (references + activity), IKKE syntetiserte svar. Answer synthesis,
  ikke-minimal reasoning effort (LLM query planning) og multi-turn messages
  forblir preview (2026-05-01-preview). Subagent hadde overforenklet til "hele
  kjernepipelinen GA"; rettet i agentic-rag-patterns + citation-tracking.
- Copilot Studio modell-tabeller (platforms/copilot-studio): fjernet Claude Opus
  4.5 + GPT-5.2 (borte fra kilde), lagt til Claude Sonnet 4.6/Opus 4.6 (GA),
  Opus 4.7 + Mistral Medium 3.5 (experimental); GPT-5 Reasoning/Auto = preview;
  A2A GA (apr 2026).
- Computer Use (CUA): Copilot Studio GA 2026-05-07; 4 modeller m/ tier/status
  (OpenAI CUA + Sonnet 4.5 GA, Sonnet 4.6 + Opus 4.6 experimental); 5 credits/
  steg standard, 15 premium; US-only region-krav FJERNET i GA-dok; Cloud PC pool
  + Hosted browser + bring-your-own-machine.
- Azure AI Search REST API-versjoner bumpet: 2025-09-01 -> 2026-04-01 (stabil),
  2025-11-01-preview -> 2026-05-01-preview (hybrid-search, rag-security-rbac,
  chunking).
- Power Automate-integrasjon: trigger "Run a flow from Copilot" -> "When an agent
  calls the flow"; App Service innebygd MCP (preview) lagt til.
- M365 Copilot-manifest v1.26 -> v1.28 (GA, mai) / v1.29 dokumentert (juni);
  "Tenant graph grounding" -> "Work IQ".
- Speech fast transcription 2t/300MB -> 5t/500MB; multilingual 14 -> 15 locales
  (+ pt-BR). Content Understanding reasoning preview -> GA (v1.0, 2025-11-01).
- Security Copilot E5 -> E5+E7. Død Databricks-URL ci-cd/best-practices ->
  ci-cd/flows. Prompt Flow retirement (2027-04-20 -> MAF) notert der den
  presenteres som go-forward. Gateway-topologi-tabell-feil rettet.
- Alle 74 Last updated -> 2026-06-19.

Discovery ikke kjørt (historisk kun Databricks-støy) -> 389-telling uendret,
ingen resync. validate 239 PASS, kb-integrity 115/115 (262 orphan-warnings
uendret), gitleaks clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-19 14:02:18 +02:00
commit 070141f06b
74 changed files with 403 additions and 384 deletions
Download patch file Download diff file Expand all files Collapse all files

6
skills/ms-ai-security/references/performance-scalability/connection-pooling-patterns.md
View file

@ -1,6 +1,6 @@
# Connection Pooling Patterns
**Last updated:** 2026-04 | Verified: MCP 2026-04
**Last updated:** 2026-06-19 | Verified: MCP 2026-06-19
**Status:** GA
**Category:** Performance & Scalability
@ -315,7 +315,7 @@ class ConnectionPoolLoadBalancer:
```
## Azure API Management som Connection Pooling-lag (oppdatert 2026-04)
## Azure API Management som Connection Pooling-lag (oppdatert 2026-06-19)
APIM håndterer backend connection pooling mot Azure OpenAI, noe som avlaster klientsiden:
@ -389,7 +389,7 @@ Connection pooling har spesielle hensyn for norsk offentlig sektor:
- [Guidelines for using HttpClient](https://learn.microsoft.com/dotnet/fundamentals/networking/http/httpclient-guidelines) — HttpClient best practices
- [Pool HTTP connections with HttpClientFactory](https://learn.microsoft.com/aspnet/core/performance/performance-best-practices) — ASP.NET performance
- [Manage connections in Azure Functions](https://learn.microsoft.com/azure/azure-functions/manage-connections) — Serverless connection management
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-backend gateway patterns (Azure OpenAI i Foundry Models) — Verified (MCP 2026-04)
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-backend gateway patterns (Azure OpenAI i Foundry Models) — Verified (MCP 2026-06-19)
## For Cosmo

2
skills/ms-ai-security/references/performance-scalability/prompt-caching-performance.md
View file

@ -1,6 +1,6 @@
# Prompt Caching for Performance
**Last updated:** 2026-02
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Performance & Scalability

8
skills/ms-ai-security/references/performance-scalability/rate-limit-management.md
View file

@ -1,6 +1,6 @@
# Rate Limit Management
**Last updated:** 2026-04 | Verified: MCP 2026-04
**Last updated:** 2026-06-19 | Verified: MCP 2026-06-19
**Status:** GA
**Category:** Performance & Scalability
@ -399,13 +399,13 @@ AzureMetrics
```
## Gateway Multi-Backend som Rate Limit-strategi (oppdatert 2026-04)
## Gateway Multi-Backend som Rate Limit-strategi (oppdatert 2026-06-19)
Microsoft dokumenterer multi-backend gateway som den anbefalte arkitekturmønsteret for rate limit management — primært via Azure API Management:
### Anbefalte topologier for rate limit-distribusjon
> **Viktig:** Standard-kvote er subscription-nivå, ikke Azure OpenAI-instansnivå. Load balancing mellom standard-instanser i samme subscription gir IKKE høyere gjennomstrømning — bruk separate subscriptions eller global/data zone deployments for reell kvoteutvidelse. — Verified (MCP 2026-04)
> **Viktig:** Standard-kvote er subscription-nivå, ikke Azure OpenAI-instansnivå. Load balancing mellom standard-instanser i samme subscription gir IKKE høyere gjennomstrømning — bruk separate subscriptions eller global/data zone deployments for reell kvoteutvidelse. — Verified (MCP 2026-06-19)
| Topologi | Kvote-kapasitet | Kompleksitet | Anbefalt for |
|----------|----------------|--------------|------------|
@ -477,7 +477,7 @@ Microsoft dokumenterer multi-backend gateway som den anbefalte arkitekturmønste
- [Manage Azure OpenAI quota](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/quota) — Kvotehåndtering
- [Azure OpenAI quotas and limits](https://learn.microsoft.com/azure/foundry/openai/quotas-limits) — Grenser per modell
- [Azure OpenAI SDK retry handling](https://learn.microsoft.com/azure/foundry/openai/supported-languages) — SDK retry-konfigurasjon
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region gateway (Azure OpenAI i Foundry Models) — Verified (MCP 2026-04)
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region gateway (Azure OpenAI i Foundry Models) — Verified (MCP 2026-06-19)
## For Cosmo

18
skills/ms-ai-security/references/performance-scalability/regional-deployment-latency.md
View file

@ -1,6 +1,6 @@
# Regional Deployment for Latency Reduction
**Last updated:** 2026-04 | Verified: MCP 2026-04
**Last updated:** 2026-06-19 | Verified: MCP 2026-06-19
**Status:** GA
**Category:** Performance & Scalability
@ -28,7 +28,7 @@ Latensforskjellen mellom regioner kan være betydelig: en forespørsel fra Oslo
### Deployment-typer og regionvalg
> **Anbefaling (Verified MCP 2026-04):** Hvis du ikke trenger å begrense databehandling til én bestemt region, bruk **Global** eller **Data Zone**-deployments for å utnytte Azures globale infrastruktur til dynamisk ruting til datasentre med ledig kapasitet — fremfor å bygge kompleks multi-region gateway-logikk.
> **Anbefaling (Verified MCP 2026-06-19):** Hvis du ikke trenger å begrense databehandling til én bestemt region, bruk **Global** eller **Data Zone**-deployments for å utnytte Azures globale infrastruktur til dynamisk ruting til datasentre med ledig kapasitet — fremfor å bygge kompleks multi-region gateway-logikk.
| Deployment Type | Data Location | Routing | Bruksområde |
|----------------|---------------|---------|-------------|
@ -309,13 +309,13 @@ class MultiRegionHealthChecker:
| Metadata i EU | Nei | Ja | Ja |
## Azure Front Door — oppdatert (2026-04)
## Azure Front Door — oppdatert (2026-06-19)
### Edge-lokasjoner og kapabiliteter
Azure Front Door har **118+ edge-lokasjoner** globalt (bekreftet 2026-04). Premium-tier støtter:
Azure Front Door har **118+ edge-lokasjoner** på tvers av 100+ metroområder globalt (bekreftet 2026-06-19). Premium-tier støtter:
- **Private Link til origins**: Front Door Premium kan rute trafikk til Azure OpenAI via Private Link — ingen offentlig eksponering av backend
- **WAF-regler**: Innebygd Web Application Firewall med OpenAI-spesifikke regler
- **WAF-regler**: Innebygd Web Application Firewall (managed rule sets, bot manager) foran backend
```bash
# Front Door Premium med Private Link til Azure OpenAI
@ -336,14 +336,14 @@ az afd origin create \
--private-link-sub-resource-type account
```
## Gateway Multi-Backend — 4 topologier (oppdatert 2026-04)
## Gateway Multi-Backend — 4 topologier (oppdatert 2026-06-19)
Microsoft dokumenterer nå fire formelle topologier for Azure OpenAI gateway:
| Topologi | Beskrivelse | Bruksscenario |
|----------|-------------|---------------|
| Single APIM instance | Én APIM mot én Azure OpenAI | Enkel arkitektur, lav kompleksitet |
| Single region, multiple backends | Én region, flere Azure OpenAI-instanser | Load balancing og failover |
| Multiple model deployments, single instance | Flere modell-deployments i én instans | Modellversjoner, blue-green, per-tenant kvoter |
| Single region, multiple instances | Én region, flere Azure OpenAI-instanser | Load balancing og failover |
| Single region, multiple subscriptions | Kvote-utvidelse via flere Azure-subscriptions | Høy TPM-kvote krav |
| Multiple regions | APIM i flere regioner, globalt | Global distribusjon, data residency |
@ -396,7 +396,7 @@ Microsoft dokumenterer nå fire formelle topologier for Azure OpenAI gateway:
## Referanser
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region patterns (Azure OpenAI i Foundry Models) — Verified (MCP 2026-04)
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region patterns (Azure OpenAI i Foundry Models) — Verified (MCP 2026-06-19)
- [Azure Front Door](https://learn.microsoft.com/azure/frontdoor/front-door-overview) — Global load balancing
- [APIM multi-region deployment](https://learn.microsoft.com/azure/api-management/api-management-howto-deploy-multi-region) — Regional gateway
- [Azure OpenAI deployment types](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/deployment-types) — Global vs Regional