fix(ms-ai-architect): Foundry URL-navnerom-migrering (ai-foundry → foundry/foundry-classic, 141 filer)

Task #5 del 1/3 (URL-migrering). Verifiseringen motbeviste STATE.md-premisset om ren prefix-swap: rebrand er per-URL, ikke mekanisk. En blind sed ai-foundry→foundry ville lagd 56 nye 404-er (classic-stiene finnes ikke under nytt foundry/-prefiks — bekreftet empirisk).

Metode: resolverte alle 237 unike KB-URLer mot live redirects (curl -L), bygde full-URL→full-URL-mapping fra faktisk url_effective. Bevarer locale-form, query (?view=) og #fragment per lenke.

- 231 navnerom-erstatninger over 141 filer (408 forekomster):
  - 161 → azure/foundry/ (98 ren prefix-swap + 10 sti-reorg + reorg-tilfeller)
  - 69 → azure/foundry-classic/ (eldre hub-spor: assistants, hub-DR, on-your-data; faktisk redirect-mål per operatorvalg)
  - 1 → azure/foundry-local/

- 2 døde lenker (404) fikset til verifiserte mål:
  - agent-service → azure/foundry/agents/overview
  - concepts/evaluation-evaluators/ → azure/foundry/how-to/evaluate-generative-ai-app

- 5 path-/display-referanser (uten https://, i backticks/lenketekst) rettet manuelt.

- 6 slug-baserte ai-foundry-treff urørt (scope-grense): managed-grafana-dashboard, security-baseline, power-platform prompt-builder, architecture baseline-chat (sistnevnte slug-rebrand i annet navnerom — mulig fremtidig funn).

- Parkert til task #5 del 2/3: Norway East GPT-5-datasuverenitet-fiks + modellkatalog-utvidelse (5.3/5.4/5.5, gpt-oss, sora-2).

Verifisert: 0 gjenværende azure/ai-foundry/-navnerom i skills/. validate-plugin.sh 219 PASS. test-kb-integrity.sh 117/117 passed.

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

Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ

skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md

@@ -284,9 +284,9 @@ result = groundedness_eval(
 ### Verified (MCP-research)
 - [RAG overview in Azure AI Search](https://learn.microsoft.com/en-us/azure/search/retrieval-augmented-generation-overview)
 - [Agentic retrieval overview](https://learn.microsoft.com/en-us/azure/search/agentic-retrieval-overview)
-- [Transparency note for Azure AI Search](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/search/transparency-note)
+- [Transparency note for Azure AI Search](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note)
 - [Grounding data design](https://learn.microsoft.com/en-us/azure/well-architected/ai/grounding-data-design)
-- [Azure AI Foundry agents - AI Search tools](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/ai-search)
+- [Azure AI Foundry agents - AI Search tools](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search)
 
 ### Baseline (modellkunnskap)
 - Norsk lovgivning (Forvaltningsloven, Offentleglova, Arkivloven)

skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md

@@ -280,7 +280,7 @@ GraphRAG introduserer spesifikke personvernrisiki i offentlig sektor:
 | CosmosAIGraph arkitektur | https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/cosmos-ai-graph | ✅ Verified (2026-02) |
 | Graph semantics i KQL | https://learn.microsoft.com/en-us/kusto/query/graph-semantics-overview | ✅ Verified (2026-02) |
 | Entity Recognition skill (v3) | https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-entity-recognition-v3 | ✅ Verified (2026-02) |
-| Azure AI Search transparency note | https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/search/transparency-note | ✅ Verified (2026-02) |
+| Azure AI Search transparency note | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note | ✅ Verified (2026-02) |
 | RAG solution design guide | https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide | ✅ Verified (2026-02) |
 | Labeled Property Graphs (LPG) | https://learn.microsoft.com/en-us/fabric/graph/graph-data-models | ✅ Verified (2026-02) |
 

skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md

@@ -244,5 +244,5 @@ for i, chunk in enumerate(chunks):
 | arXiv:2409.04701 (forskningspaper) | **Verified** | [arxiv.org](https://arxiv.org/abs/2409.04701) |
 | Jina Embeddings on Azure Marketplace | **Verified** | [azuremarketplace.microsoft.com](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/jinaai.jina-embeddings-v4) |
 | Jina Embeddings v3 announcement | **Verified** | [jina.ai](https://jina.ai/news/jina-embeddings-v3-a-frontier-multilingual-embedding-model/) |
-| Azure OpenAI Embeddings | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/tutorials/embeddings) |
+| Azure OpenAI Embeddings | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings) |
 | Late Chunking tutorial (DataCamp) | **Baseline** | [datacamp.com](https://www.datacamp.com/tutorial/late-chunking) |

skills/ms-ai-engineering/references/rag-architecture/rag-context-windows.md

@@ -388,7 +388,7 @@ Hvis du har 10,000 queries per måned: **11,300 NOK/måned** (kun LLM-kostnad, i
 ### Microsoft Learn (Verified via MCP)
 
 1. **Azure OpenAI Assistants API — Context Window Management**
-   https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/assistants#context-window-management
+   https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/assistants#context-window-management
    *Dekning: max_prompt_tokens, max_completion_tokens, truncation strategy, File Search recommendations*
    **Confidence: Verified**
 
@@ -398,12 +398,12 @@ Hvis du har 10,000 queries per måned: **11,300 NOK/måned** (kun LLM-kostnad, i
    **Confidence: Verified**
 
 3. **Azure OpenAI in Microsoft Foundry Models — Quotas and Limits**
-   https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits
+   https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
    *Dekning: TPM limits per model, context window sizes, rate limits*
    **Confidence: Verified**
 
 4. **Azure OpenAI On Your Data — Token Usage Estimation**
-   https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data
+   https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data
    *Dekning: Intent prompt vs. generation prompt token breakdown, RAG pipeline token costs*
    **Confidence: Verified**
 
@@ -413,12 +413,12 @@ Hvis du har 10,000 queries per måned: **11,300 NOK/måned** (kun LLM-kostnad, i
    **Confidence: Verified**
 
 6. **Chat Markup Language ChatML — Managing Conversations**
-   https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chat-markup-language#preventing-unsafe-user-inputs
+   https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses#preventing-unsafe-user-inputs
    *Dekning: Token counting med tiktoken, conversation history truncation*
    **Confidence: Verified**
 
 7. **Code Sample: Token Counting with tiktoken (Python)**
-   https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt
+   https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt
    *Dekning: Praktisk implementasjon av token management i conversation loops*
    **Confidence: Verified**
 

skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md

@@ -501,15 +501,15 @@ Metrics:
 - [Vector compression best practices](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/azure-ai-search-cut-vector-costs-up-to-92-5-with-new-compression-techniques/4404866) — *Verified: Compression techniques (92.5% reduction)*
 
 **Azure OpenAI Cost Management:**
-- [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs) — *Verified: Token-based billing, fine-tuning costs*
-- [Azure OpenAI Batch API](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch) — *Verified: 50% cost reduction for batch workloads*
-- [Fine-tuning cost management](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-cost-management) — *Verified: Hosting + inference + training costs*
+- [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs) — *Verified: Token-based billing, fine-tuning costs*
+- [Azure OpenAI Batch API](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch) — *Verified: 50% cost reduction for batch workloads*
+- [Fine-tuning cost management](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management) — *Verified: Hosting + inference + training costs*
 
 **RAG Architecture & Optimization:**
 - [RAG design and evaluation guide](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide) — *Verified: End-to-end RAG considerations*
 - [RAG chunking economics](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-chunking-phase#understand-chunking-economics) — *Verified: Chunking cost optimization*
 - [RAG embedding economics](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-generate-embeddings#understand-embedding-economics) — *Verified: Embedding model selection trade-offs*
-- [Retrieval cost and latency considerations](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/retrieval-augmented-generation#cost-and-latency-considerations) — *Verified: Query cost analysis*
+- [Retrieval cost and latency considerations](https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation#cost-and-latency-considerations) — *Verified: Query cost analysis*
 
 **Cloud Adoption Framework:**
 - [Manage AI costs](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/manage#manage-ai-costs) — *Verified: Enterprise cost governance*

skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md

@@ -311,11 +311,11 @@ Bruk `mlflow.log_feedback()` med `AssessmentSourceType.HUMAN` for å logge menne
 ## Kilder og verifisering
 
 ### Verified (MCP-research)
-- [Azure AI Evaluation SDK](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/evaluate-sdk)
+- [Azure AI Evaluation SDK](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk)
 - [RAG LLM Evaluation Phase](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-llm-evaluation-phase)
 - [RAG Solution Design Guide](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide)
-- [Built-in RAG Evaluators](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/rag-evaluators)
-- [Azure AI Foundry Observability](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability)
+- [Built-in RAG Evaluators](https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators)
+- [Azure AI Foundry Observability](https://learn.microsoft.com/en-us/azure/foundry/concepts/observability)
 - [RAG Experiment Accelerator](https://github.com/microsoft/rag-experiment-accelerator)
 
 ### Baseline (modellkunnskap)

skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md

@@ -385,9 +385,9 @@ Hvis AI-systemet gir feil informasjon som fører til skade:
 **Microsoft Learn (Verified via MCP):**
 - [Groundedness Detection Concepts](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/groundedness) — **Verified**
 - [Groundedness Detection Quickstart](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-groundedness) — **Verified**
-- [Groundedness Detection Filter](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-groundedness) — **Verified**
-- [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering) — **Verified**
-- [Transparency Note: Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note) — **Verified**
+- [Groundedness Detection Filter](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness) — **Verified**
+- [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering) — **Verified**
+- [Transparency Note: Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note) — **Verified**
 - [RAG Solution Design Guide](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide) — **Verified**
 - [Secure Multitenant RAG](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/secure-multitenant-rag) — **Verified**
 

skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md

@@ -418,7 +418,7 @@ public async Task ApplyRetentionPolicyAsync()
 | [Multi-turn conversations with an agent](https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/multi-turn-conversation) | Agent Framework session management | **Verified** |
 | [Chat history (Semantic Kernel)](https://learn.microsoft.com/en-us/semantic-kernel/concepts/ai-services/chat-completion/chat-history) | ChatHistory API, reduction strategies | **Verified** |
 | [Using memory with Agents](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory) | Whiteboard memory, memory providers | **Verified** |
-| [Use the Azure OpenAI web app](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/use-web-app) | Cosmos DB chat history enablement | **Verified** |
+| [Use the Azure OpenAI web app](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/use-web-app) | Cosmos DB chat history enablement | **Verified** |
 | [RAG with Azure DocumentDB](https://learn.microsoft.com/en-us/azure/documentdb/rag) | History-aware retrieval chains | **Verified** |
 | [Storing Chat History in 3rd Party Storage](https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/third-party-chat-history-storage) | Custom ChatHistoryProvider | **Verified** |
 | [IChatClient documentation](https://learn.microsoft.com/en-us/dotnet/ai/ichatclient) | Stateless vs stateful clients | **Verified** |

skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md

@@ -473,7 +473,7 @@ Authorization: Bearer <user-token>
    - Dekning: Hierarchical permissions, POSIX-like ACLs, indexer configuration
 
 5. **Azure OpenAI On Your Data - Document-level access control**
-   - URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/on-your-data-configuration#document-level-access-control
+   - URL: https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-configuration#document-level-access-control
    - Confidence: **Verified** (MCP-search 2026-02)
    - Dekning: RAG integration, filter parameter, group_ids field mapping
 
@@ -493,7 +493,7 @@ Authorization: Bearer <user-token>
    - Dekning: RAG challenges, security & governance
 
 9. **Retrieval augmented generation (RAG) and indexes (AI Foundry)**
-   - URL: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/retrieval-augmented-generation?view=foundry-classic
+   - URL: https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation?view=foundry-classic
    - Confidence: **Verified** (MCP-search 2026-02)
    - Dekning: Security considerations, access control at retrieval time
 

skills/ms-ai-engineering/references/rag-architecture/self-reflective-rag.md

@@ -265,7 +265,7 @@ Hvis self-reflective RAG reduserer feilaktige svar fra 15% til 5%:
 
 | Kilde | Konfidens | URL |
 |-------|-----------|-----|
-| RAG Evaluators (Azure AI Foundry) | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/rag-evaluators) |
+| RAG Evaluators (Azure AI Foundry) | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators) |
 | RAG LLM Evaluation Phase | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-llm-evaluation-phase) |
 | Semantic Kernel Agent RAG | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-rag) |
 | Corrective RAG (CRAG) paper | **Verified** | [arxiv.org](https://arxiv.org/abs/2401.15884) |

skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md

@@ -407,11 +407,11 @@ Ved bruk av streaming med `code_interpreter` tool:
 
 ### Verified (fra MCP microsoft-learn)
 
-- Azure OpenAI Responses API streaming: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/responses (Verified: 2026-02)
+- Azure OpenAI Responses API streaming: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses (Verified: 2026-02)
 - Semantic Kernel Agent streaming: https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-streaming (Verified: 2026-02)
 - SSE med Application Gateway: https://learn.microsoft.com/en-us/azure/application-gateway/use-server-sent-events (Verified: 2026-02)
-- Azure OpenAI REST API reference: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/reference (Verified: 2026-02)
-- Chat Completions API streaming: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/reference#chat-completions (Verified: 2026-02)
+- Azure OpenAI REST API reference: https://learn.microsoft.com/en-us/azure/foundry/openai/reference (Verified: 2026-02)
+- Chat Completions API streaming: https://learn.microsoft.com/en-us/azure/foundry/openai/reference#chat-completions (Verified: 2026-02)
 
 ### Baseline (modellkunnskap)