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
This commit is contained in:
Kjell Tore Guttormsen 2026-06-18 13:37:06 +02:00
commit dd1036ab8a
141 changed files with 399 additions and 399 deletions

View file

@ -390,7 +390,7 @@ workflow = (
3. [Process to build agents across your organization](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/ai-agents/build-secure-process)
Confidence: High — Tool boundaries, human-in-the-loop mandates, compliance frameworks
4. [Guardrails and controls overview in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/guardrails/guardrails-overview)
4. [Guardrails and controls overview in Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/guardrails/guardrails-overview)
Confidence: High — Intervention points, risk categories, agent vs. model guardrails
5. [Secure AI agents at scale using Microsoft Agent 365](https://learn.microsoft.com/en-us/security/security-for-ai/agent-365-security)

View file

@ -482,19 +482,19 @@ results = mlflow.genai.evaluate(
### Microsoft Learn (MCP-verified)
1. **Evaluate your AI agents (preview)**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/agent-evaluate-sdk?view=foundry-classic
https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/agent-evaluate-sdk?view=foundry-classic
*Confidence: Verified* — Hovedreferanse for Azure AI Evaluation SDK, evaluator types, model support
2. **Continuously evaluate your AI agents (preview)**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/continuous-evaluation-agents?view=foundry-classic
https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/continuous-evaluation-agents?view=foundry-classic
*Confidence: Verified* — Continuous evaluation setup, sampling configuration, Application Insights integration
3. **Run evaluations in the cloud by using the Microsoft Foundry SDK**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/cloud-evaluation?view=foundry-classic
https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation?view=foundry-classic
*Confidence: Verified* — Cloud batch evaluation, CI/CD integration, dataset formats
4. **Tutorial: Idea to prototype - Build and evaluate an enterprise agent**
https://learn.microsoft.com/en-us/azure/ai-foundry/tutorials/developer-journey-idea-to-prototype?view=foundry
https://learn.microsoft.com/en-us/azure/foundry/tutorials/developer-journey-idea-to-prototype?view=foundry
*Confidence: Verified* — End-to-end tutorial med cloud evaluation, built-in evaluators
5. **Test and evaluate AI workloads on Azure (Well-Architected Framework)**
@ -502,15 +502,15 @@ results = mlflow.genai.evaluate(
*Confidence: Verified* — Agentic workflow testing strategy, tool call validation, security testing
6. **Observability in generative AI**
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability
https://learn.microsoft.com/en-us/azure/foundry/concepts/observability
*Confidence: Verified* — Built-in evaluators list, GenAIOps evaluation stages, simulators
7. **What are hosted agents? (Evaluate and test hosted agents)**
https://learn.microsoft.com/en-us/azure/ai-foundry/agents/concepts/hosted-agents?view=foundry#evaluate-and-test-hosted-agents
https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/hosted-agents?view=foundry#evaluate-and-test-hosted-agents
*Confidence: Verified* — Hosted agent evaluation best practices, test dataset creation
8. **Agent evaluators**
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/agent-evaluators?view=foundry
https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators?view=foundry
*Confidence: Verified* — Agent-specific evaluator details (Intent Resolution, Task Adherence, Tool Call Accuracy)
9. **Evaluate and monitor AI agents (MLflow 3 on Databricks)**

View file

@ -461,7 +461,7 @@ Gir data lineage tracking og governance-enforcement.
Confidence: ✅ Verified (Mem0Provider, WhiteboardProvider documentation)
2. **Foundry Agent Service Memory (preview)**
https://learn.microsoft.com/en-us/azure/ai-foundry/agents/concepts/what-is-memory?view=foundry
https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/what-is-memory?view=foundry
Confidence: ✅ Verified (Managed Memory Store, extraction/consolidation/retrieval phases)
3. **Agent Framework Chat History Providers**
@ -485,7 +485,7 @@ Gir data lineage tracking og governance-enforcement.
Confidence: ✅ Verified (Hierarchical memory: knowledge, long-term, short-term)
8. **Azure OpenAI Web App Chat History (Cosmos DB)**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/use-web-app
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/use-web-app
Confidence: ✅ Verified (Cosmos DB enablement for chat history)
### Konfidensnivå per seksjon
@ -505,13 +505,13 @@ Gir data lineage tracking og governance-enforcement.
### Unique Microsoft Learn URLs accessed
1. `/semantic-kernel/frameworks/agent/agent-memory`
2. `/azure/ai-foundry/agents/concepts/what-is-memory`
2. `/azure/foundry/agents/concepts/what-is-memory`
3. `/agent-framework/integrations/overview`
4. `/azure/copilot/bring-your-own-storage`
5. `/semantic-kernel/concepts/vector-store-connectors/memory-stores`
6. `/agent-framework/tutorials/agents/multi-turn-conversation`
7. `/azure/cloud-adoption-framework/ai-agents/build-secure-process`
8. `/azure/ai-foundry/openai/how-to/use-web-app`
8. `/azure/foundry-classic/openai/how-to/use-web-app`
**Total unique sources**: 8 Microsoft Learn URLs
**MCP calls**: 6 (3x microsoft_docs_search, 2x microsoft_docs_fetch, 1x microsoft_code_sample_search)

View file

@ -654,11 +654,11 @@ app.MapA2A(agent, "/a2a/my-agent", agentCard: new()
### Microsoft Learn (Verified)
1. **Foundry Agent Service — A2A Tool**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/agent-to-agent
- https://learn.microsoft.com/azure/foundry/agents/how-to/tools/agent-to-agent
- Confidence: **Verified** (offisiell guide, preview, februar 2026)
2. **A2A Authentication in Foundry**
- https://learn.microsoft.com/azure/ai-foundry/agents/concepts/agent-to-agent-authentication
- https://learn.microsoft.com/azure/foundry/agents/concepts/agent-to-agent-authentication
- Confidence: **Verified** (offisiell auth-guide, februar 2026)
3. **Copilot Studio — Connect A2A Agent**

View file

@ -482,7 +482,7 @@ Kostnader basert på:
### Microsoft Learn (Verified)
1. **Foundry Agent Service Computer Use Tool**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/computer-use
- https://learn.microsoft.com/azure/foundry/agents/how-to/tools/computer-use
- Confidence: **Verified** (offisiell Foundry-dokumentasjon, sep 2025)
2. **Automate web and desktop apps with computer use — Copilot Studio**
@ -494,7 +494,7 @@ Kostnader basert på:
- Confidence: **Verified** (Copilot Studio docs, 2025)
4. **Browser Automation (preview) — Foundry Agent Service**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/browser-automation
- https://learn.microsoft.com/azure/foundry/agents/how-to/tools/browser-automation
- Confidence: **Verified** (aug 2025, public preview)
5. **CUA vs RPA — Use agent tools to extend agents**

View file

@ -327,7 +327,7 @@ Foundry Agent Service er tilgjengelig i følgende Azure-regioner (per februar 20
- Code Interpreter er ikke tilgjengelig i alle regioner
**Sjekk regional verktøytilgjengelighet:**
[learn.microsoft.com/azure/ai-foundry/agents/concepts/tool-best-practice#tool-support-by-region-and-model](https://learn.microsoft.com/azure/ai-foundry/agents/concepts/tool-best-practice?view=foundry#tool-support-by-region-and-model)
[learn.microsoft.com/azure/foundry/agents/concepts/tool-best-practice#tool-support-by-region-and-model](https://learn.microsoft.com/azure/foundry/agents/concepts/tool-best-practice?view=foundry#tool-support-by-region-and-model)
## Enterprise-sikkerhet og governance
@ -475,27 +475,27 @@ Rate limiting skjer på modell-deployment-nivå, ikke Agent Service-nivå. Se Az
### Microsoft Learn (Verified)
1. **What is Foundry Agent Service?**
- https://learn.microsoft.com/azure/ai-foundry/agents/overview?view=foundry-classic
- https://learn.microsoft.com/azure/foundry/agents/overview?view=foundry-classic
- Confidence: **Verified** (offisiell oversikt, GA-dokumentasjon)
2. **What's new in Foundry Agent Service (GA mai 2025)**
- https://learn.microsoft.com/azure/ai-foundry/agents/whats-new?view=foundry-classic
- https://learn.microsoft.com/azure/foundry-classic/agents/whats-new?view=foundry-classic
- Confidence: **Verified** (changelog, maijuni 2025)
3. **Connected Agents**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/connected-agents?view=foundry-classic
- https://learn.microsoft.com/azure/foundry-classic/agents/how-to/connected-agents?view=foundry-classic
- Confidence: **Verified** (multi-agent SDK guide og eksempler)
4. **Foundry Agent Service limits, quotas, and regional support**
- https://learn.microsoft.com/azure/ai-foundry/agents/concepts/limits-quotas-regions?view=foundry
- https://learn.microsoft.com/azure/foundry/agents/concepts/limits-quotas-regions?view=foundry
- Confidence: **Verified** (komplett region- og grense-tabell)
5. **MCP tool — Foundry Agent Service**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools-classic/model-context-protocol-samples?view=foundry-classic
- https://learn.microsoft.com/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol-samples?view=foundry-classic
- Confidence: **Verified** (C# og Python code samples)
6. **Threads, runs, and messages**
- https://learn.microsoft.com/azure/ai-foundry/agents/concepts/threads-runs-messages?view=foundry-classic
- https://learn.microsoft.com/azure/foundry-classic/agents/concepts/threads-runs-messages?view=foundry-classic
- Confidence: **Verified** (kjernekonsept-dokumentasjon)
7. **AzureAIAgent Foundry GA Migration Guide (SK Python)**
@ -503,11 +503,11 @@ Rate limiting skjer på modell-deployment-nivå, ikke Agent Service-nivå. Se Az
- Confidence: **Verified** (breaking changes og migrasjonsguide)
8. **Transparency Note for Azure Agent Service**
- https://learn.microsoft.com/azure/ai-foundry/responsible-ai/agents/transparency-note?view=foundry-classic
- https://learn.microsoft.com/azure/foundry/responsible-ai/agents/transparency-note?view=foundry-classic
- Confidence: **Verified** (ansvarlig AI-rammeverk)
9. **Foundry Agent Service FAQ (prising)**
- https://learn.microsoft.com/azure/ai-foundry/agents/faq?view=foundry-classic
- https://learn.microsoft.com/azure/foundry/agents/faq?view=foundry-classic
- Confidence: **Verified** (offisiell prisingsforklaring)
### Confidence per seksjon

View file

@ -583,19 +583,19 @@ Foundry Workflows' visuelle designer gir offentlig sektor-organisasjoner en unik
### Microsoft Learn (Verified)
1. **Build a workflow in Microsoft Foundry**
- https://learn.microsoft.com/azure/ai-foundry/agents/concepts/workflow?view=foundry
- https://learn.microsoft.com/azure/foundry/agents/concepts/workflow?view=foundry
- Confidence: **Verified** (offisiell workflow-guide, Foundry new portal)
2. **Agent development lifecycle**
- https://learn.microsoft.com/azure/ai-foundry/agents/concepts/development-lifecycle?view=foundry
- https://learn.microsoft.com/azure/foundry/agents/concepts/development-lifecycle?view=foundry
- Confidence: **Verified** (versjonering, publisering, livssyklus, januar 2025)
3. **Publish and share agents in Microsoft Foundry**
- https://learn.microsoft.com/azure/ai-foundry/agents/how-to/publish-agent?view=foundry
- https://learn.microsoft.com/azure/foundry/agents/how-to/agent-applications?view=foundry
- Confidence: **Verified** (Agent Application deployment, API-kall, RBAC)
4. **Monitor agents with the Agent Monitoring Dashboard**
- https://learn.microsoft.com/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry
- https://learn.microsoft.com/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry
- Confidence: **Verified** (token usage, latency, success rate, evaluators)
5. **Declarative Workflows — Overview (Agent Framework)**
@ -607,7 +607,7 @@ Foundry Workflows' visuelle designer gir offentlig sektor-organisasjoner en unik
- Confidence: **Verified** (HITL-mønster, pause og resume, compliance)
7. **Transparency Note for Azure Agent Service**
- https://learn.microsoft.com/azure/ai-foundry/responsible-ai/agents/transparency-note?view=foundry-classic
- https://learn.microsoft.com/azure/foundry/responsible-ai/agents/transparency-note?view=foundry-classic
- Confidence: **Verified** (Foundry Workflows capabilities, visioning, governance)
### Microsoft Dev Blog (Verified)

View file

@ -448,12 +448,12 @@ def update_citizen_record(ssn: str, field: str, value: str) -> str:
### Microsoft Learn-kilder (Verified via MCP)
1. [Azure OpenAI Function Calling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/function-calling) — **Verified 2026-02**
1. [Azure OpenAI Function Calling](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling) — **Verified 2026-02**
2. [Semantic Kernel Agent Functions](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-functions) — **Verified 2026-02**
3. [Agent Framework - Agent as Function Tool](https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/agent-as-function-tool) — **Verified 2026-02**
4. [AG-UI Backend Tool Rendering](https://learn.microsoft.com/en-us/agent-framework/integrations/ag-ui/backend-tool-rendering) — **Verified (MCP 2026-04)** — AIFunctionFactory.Create() med serializerOptions for komplekse typer (C#), @tool decorator med Annotated/Field (Python), TOOL_CALL_START/ARGS/END/RESULT events, FunctionCallContent/.Arguments og FunctionResultContent/.Result (C#), klasse-baserte tools-moenster (Python)
5. [Azure OpenAI Assistants Function Calling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/assistant-functions) — **Verified 2026-02**
6. [Structured Outputs](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/structured-outputs) — **Verified 2026-02**
5. [Azure OpenAI Assistants Function Calling](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistant-functions) — **Verified 2026-02**
6. [Structured Outputs](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs) — **Verified 2026-02**
### Konfidensnivå per seksjon