fix(ms-ai-architect): R5 G5b — 4 innholds-fikser (retired gpt-35-turbo→gpt-4o-mini, vector-quant GA 2024-07-01, 2 overclaims nyansert), hver live-verifisert per MS Learn-kilde [skip-docs]
This commit is contained in:
parent
21448b2617
commit
36fd4cfe7b
5 changed files with 72 additions and 9 deletions
|
|
@ -7,7 +7,8 @@
|
|||
"note": "This is a SAMPLE of corpus errors (255 volatile claims). Spor 1 surfaces the full set corpus-wide. [2026-06-29] Spor 0 executed: 37 fixes applied (each value live-verified per source before edit; recurrences of each wrong fact fixed file-wide), 1 rejected (#8 model-router-GA: file already correct). Adjacent (non-38) findings captured for Spor 1.",
|
||||
"applied": 37,
|
||||
"rejected": 1,
|
||||
"applied_date": "2026-06-29"
|
||||
"applied_date": "2026-06-29",
|
||||
"g5b_note": "[2026-07-04] R5 G5b-restanse: 4 innholds-fikser påført (adr zero-permission-overclaim, multi-region retired gpt-35-turbo→gpt-4o-mini, network obligatorisk→anbefalt, vector-storage GA 2024-11-01→2024-07-01). Hver live-verifisert per kilde (Opus xhigh verify-agent) før edit. De 38 kjerne-fiksene var allerede applied 2026-06-29. Se g5b_fixes[]."
|
||||
},
|
||||
"fixes": [
|
||||
{
|
||||
|
|
@ -619,5 +620,67 @@
|
|||
"verified": "2026-06-29",
|
||||
"verified_by": "per-source verify-agent (Opus xhigh, live microsoft_docs_fetch) + main-context apply"
|
||||
}
|
||||
],
|
||||
"g5b_fixes": [
|
||||
{
|
||||
"id": "ms-ai-advisor/architecture/adr-template.md#g5b",
|
||||
"file": "skills/ms-ai-advisor/references/architecture/adr-template.md",
|
||||
"skill": "ms-ai-advisor",
|
||||
"claim_type": "capability-overclaim",
|
||||
"verdict": "confirm-fix",
|
||||
"wrong_assertion": "Zero permission management - SharePoint permissions respekteres automatisk",
|
||||
"correction": "Overclaim: Copilot/Graph håndhever eksisterende tilganger (sant), men oversharing må fortsatt styres aktivt (Restricted SharePoint Search, SharePoint Advanced Management, sensitivitetsmerker, Purview). \"Zero permission management\" fjernet.",
|
||||
"source": "https://learn.microsoft.com/microsoft-365/copilot/security-microsoft-365-copilot",
|
||||
"reverify_required": true,
|
||||
"fixed": true,
|
||||
"applied": true,
|
||||
"verified": "2026-07-04",
|
||||
"verified_by": "per-source verify-agent (Opus xhigh, live MS Learn) + main-context apply"
|
||||
},
|
||||
{
|
||||
"id": "ms-ai-infrastructure/bcdr/multi-region-azure-openai-deployment.md#g5b",
|
||||
"file": "skills/ms-ai-infrastructure/references/bcdr/multi-region-azure-openai-deployment.md",
|
||||
"skill": "ms-ai-infrastructure",
|
||||
"claim_type": "retired-model",
|
||||
"verdict": "confirm-fix",
|
||||
"wrong_assertion": "gpt-35-turbo listet som tilgjengelig modell (regionstabeller + kvoteeksempler, 5 forekomster)",
|
||||
"correction": "Alle gpt-35-turbo-versjoner retired (0301/0613 2025-02-13, 16k 2025-04-30, 1106/0125 forbi \"no earlier than 2025-09-01\"-vindu) → byttet til gpt-4o-mini (bekreftet Standard-tilgjengelig i Sweden Central / West Europe / UK South).",
|
||||
"source": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/model-retirements",
|
||||
"reverify_required": true,
|
||||
"fixed": true,
|
||||
"applied": true,
|
||||
"verified": "2026-07-04",
|
||||
"verified_by": "per-source verify-agent (Opus xhigh, live MS Learn) + main-context apply"
|
||||
},
|
||||
{
|
||||
"id": "ms-ai-infrastructure/bcdr/network-resilience-patterns-ai.md#g5b",
|
||||
"file": "skills/ms-ai-infrastructure/references/bcdr/network-resilience-patterns-ai.md",
|
||||
"skill": "ms-ai-infrastructure",
|
||||
"claim_type": "overstatement",
|
||||
"verdict": "confirm-fix",
|
||||
"wrong_assertion": "Circuit Breaker + Retry med exponential backoff er OBLIGATORISK for alle Azure AI API-kall — dette er ikke valgfritt.",
|
||||
"correction": "Overstatement: MS rammer retry/circuit-breaker som anbefalt beste praksis (Well-Architected reliability patterns), ikke krav. Endret til \"sterkt anbefalt ... ikke et absolutt krav\".",
|
||||
"source": "https://learn.microsoft.com/azure/well-architected/reliability/design-patterns",
|
||||
"reverify_required": true,
|
||||
"fixed": true,
|
||||
"applied": true,
|
||||
"verified": "2026-07-04",
|
||||
"verified_by": "per-source verify-agent (Opus xhigh, live MS Learn) + main-context apply"
|
||||
},
|
||||
{
|
||||
"id": "ms-ai-security/cost-optimization/vector-storage-cost-optimization.md#g5b",
|
||||
"file": "skills/ms-ai-security/references/cost-optimization/vector-storage-cost-optimization.md",
|
||||
"skill": "ms-ai-security",
|
||||
"claim_type": "ga-date",
|
||||
"verdict": "confirm-fix",
|
||||
"wrong_assertion": "Vector quantization (GA siden 2024-11-01)",
|
||||
"correction": "GA-dato feil: scalar + binary quantization ble GA i 2024-07-01 stable Search-API. 2024-11-01 var en preview (rescoring/syntaks). Rettet til 2024-07-01.",
|
||||
"source": "https://learn.microsoft.com/azure/search/search-api-migration",
|
||||
"reverify_required": true,
|
||||
"fixed": true,
|
||||
"applied": true,
|
||||
"verified": "2026-07-04",
|
||||
"verified_by": "per-source verify-agent (Opus xhigh, live MS Learn) + main-context apply"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1014,7 +1014,7 @@ Høy risiko hvis permission sync feiler - kan lekke sensitiv data til feil bruke
|
|||
Bruk SharePoint direkte som data source via Microsoft Graph Search API. M365 Copilot har innebygd støtte for SharePoint via Graph connectors. Permissions arves automatisk fra SharePoint.
|
||||
|
||||
**Pros:**
|
||||
- ✅ Zero permission management - SharePoint permissions respekteres automatisk
|
||||
- ✅ Permissions arves automatisk fra SharePoint - Copilot/Graph håndhever eksisterende tilganger (men oversharing må fortsatt styres aktivt: Restricted SharePoint Search, SharePoint Advanced Management, sensitivitetsmerker, Purview)
|
||||
- ✅ Ingen custom code - M365 Copilot har native SharePoint connector
|
||||
- ✅ Real-time updates - ingen indexing delay, data er alltid oppdatert
|
||||
- ✅ Lavere kostnad - ingen separat search service, inkludert i M365 license
|
||||
|
|
|
|||
|
|
@ -35,9 +35,9 @@ Denne referansen dekker regionvalg for Norge og EU, lastbalanseringsmonstre via
|
|||
| Region | Primaer bruk | Modellstotte | Latens fra Norge | Datasuverenitet |
|
||||
|--------|-------------|--------------|------------------|-----------------|
|
||||
| Norway East | Primaer region | Begrenset (gpt-4o 2024-11-20) | < 10 ms | Norge/EU |
|
||||
| Sweden Central | Sekundaer/failover | Bred (gpt-4o, o1, gpt-35-turbo) | ~15-25 ms | EU |
|
||||
| West Europe | Alternativ | Begrenset (gpt-35-turbo) | ~30-40 ms | EU |
|
||||
| UK South | Alternativ | Moderat (gpt-4o, gpt-35-turbo) | ~35-45 ms | UK (tilstrekkelig for mange bruksomrader) |
|
||||
| Sweden Central | Sekundaer/failover | Bred (gpt-4o, o1, gpt-4o-mini) | ~15-25 ms | EU |
|
||||
| West Europe | Alternativ | Begrenset (gpt-4o-mini) | ~30-40 ms | EU |
|
||||
| UK South | Alternativ | Moderat (gpt-4o, gpt-4o-mini) | ~35-45 ms | UK (tilstrekkelig for mange bruksomrader) |
|
||||
| France Central | Alternativ | Bred (gpt-4o, o1) | ~35-45 ms | EU |
|
||||
|
||||
### Anbefalte regionkombinasjoner
|
||||
|
|
@ -295,11 +295,11 @@ Abonnement: DDT-AI-Prod
|
|||
|
|
||||
+-- Norway East
|
||||
| +-- gpt-4o Data Zone: 120K TPM (primaer)
|
||||
| +-- gpt-35-turbo: 60K TPM
|
||||
| +-- gpt-4o-mini: 60K TPM
|
||||
|
|
||||
+-- Sweden Central
|
||||
| +-- gpt-4o Data Zone: 120K TPM (sekundaer)
|
||||
| +-- gpt-35-turbo: 120K TPM
|
||||
| +-- gpt-4o-mini: 120K TPM
|
||||
| +-- o1-mini Global Standard: 80K TPM
|
||||
|
|
||||
+-- France Central (failover)
|
||||
|
|
|
|||
|
|
@ -426,7 +426,7 @@ az network nsg rule create \
|
|||
## For Cosmo
|
||||
|
||||
- **Bruk denne referansen** når kunden designer nettverksarkitektur for resiliente AI-løsninger, eller når de implementerer failover med private endepunkter.
|
||||
- Circuit Breaker + Retry med exponential backoff er OBLIGATORISK for alle Azure AI API-kall — dette er ikke valgfritt.
|
||||
- Circuit Breaker + Retry med exponential backoff er sterkt anbefalt for Azure AI API-kall — Microsoft omtaler dette som beste praksis for resiliens (Azure Well-Architected), ikke et absolutt krav.
|
||||
- For private endpoints: Husk at failover mellom regioner krever at Private DNS-soner er linket til begge VNets.
|
||||
- Graceful degradation bør alltid designes i lag — full AI → enklere søk → cached svar → statisk fallback.
|
||||
- Anbefal Azure Front Door (Premium) for AI-workloads som trenger global load balancing med DDoS-beskyttelse og WAF i ett produkt.
|
||||
|
|
|
|||
|
|
@ -261,7 +261,7 @@ Kombinerer ett high-precision vector field (float32, ingen quantization) med ett
|
|||
|
||||
### Azure AI Search
|
||||
|
||||
**Vector quantization (GA siden 2024-11-01):**
|
||||
**Vector quantization (GA siden 2024-07-01):**
|
||||
```http
|
||||
POST https://[service].search.windows.net/indexes?api-version=2025-09-01
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue