open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Activity
244 commits 1 branch 8 tags 133 MiB
Commit graph

5 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
441f7d48a8 docs(ms-ai-architect): KB-refresh critical cost 7/8 — request-batching verifisert mot batch-docs (Data Zone Batch + fail-fast) 
Verifisert mot live Microsoft Learn (ai-foundry/openai/how-to/batch + deployment-types):
- Data Zone Batch lagt til som deployment-type (SKU `DataZoneBatch`): samme 50% rabatt som
  Global Batch, men inferens-prosessering begrenset til Microsofts definerte datasone (EU/US),
  data-at-rest forblir i ressursens Azure-geografi. Lagt til 4 steder: kjernekomponent-tabell,
  setup-steg, prismodell-tabell, og som FØRSTE Schrems II-mitigering (høy verdi for offentlig sektor).
- «Exponential backoff queuing» reframet til «fail-fast token-quota-håndtering»: serveren feiler
  raskt på enqueued-token-grensen, KLIENTEN gjør exponential backoff-retry (kodeeksempel er
  klient-side) — filens «automatisk retry» antydet feilaktig server-side auto-retry. Region-listen
  verifisert current (urørt).
- Header 2026-05→2026-06, kilde #1 + konfidens-tabell Verified 2026-02→2026-06.
- 50%/24t/expiration verifisert current (doc: «doesn't expire jobs that take longer»). Disclaimed
  priser (GPT-4o Jan-2026 + NOK) urørt. validate 239/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-24 09:54:38 +02:00
Kjell Tore Guttormsen
03d596e4ec docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer) 
Verifisert mot offisiell MS-doc (juni 2026): «Microsoft Foundry» er det
gjeldende produkt-/portalnavnet; «Foundry (classic)» = gamle «Azure AI Foundry»
(/azure/foundry/ vs /azure/foundry-classic/). Premiss bekreftet før sveip.

Multi-regel, IKKE naiv s/Azure AI Foundry/Microsoft Foundry/ — MS dropper
«Azure AI» (legger IKKE til «Microsoft») for to produktvarianter:
- «Azure AI Foundry Agent[ Service|s]» → «Foundry Agent Service/Agents» (MS-form)
- «Azure AI Foundry Models» → «Foundry Models» (i «Azure OpenAI in Foundry Models»)
- «Azure AI Foundry SDK» → «Microsoft Foundry SDK» (operatør-valg)
- «Azure AI Foundry portal/project» + generisk → «Microsoft Foundry»
- Pre-eksisterende «Microsoft Foundry Models» (4) normalisert → «Foundry Models»

Bevart: «Azure OpenAI», «Azure AI Inference SDK», «Azure AI Search»,
«Azure AI Services», kode-IDer. Historisk ref «(tidligere Azure AI Foundry)»
i model-catalog-2026.md beskyttet via lookbehind. URL /azure/ai-foundry/→
/azure/foundry/ kun i owasp-llm-top10 (KB-ref); docs/-filer deferred.

Scope: skills (inkl. 3 SKILL.md) + commands + agents + README + CLAUDE.
Ekskludert: docs/ (interne), playground/+tests/ fixtures (testdata),
CHANGELOG.md (historisk logg), STATE.md (gitignored).

3 SKILL.md endret (advisor/engineering/security) → judge-cache teknisk
invalidert for disse, men scorer uendret: advisor 91, eng/gov/infra/sec 96
(alle ≥90). validate 239/0. 0 «Azure AI Foundry» igjen (utenom bevart ref).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-23 21:00:27 +02:00
Kjell Tore Guttormsen
dd1036ab8a 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
 2026-06-18 13:37:06 +02:00
Kjell Tore Guttormsen
d60bbd4bff chore(ms-ai-architect): KB checkpoint refresh — 30 files (critical 9 + high batch 1) [skip-docs] 
- Critical bucket (9 files): substantive content updates basert på MCP-fetch
  - enterprise-governance: DSPM front door, AI-app-kategorier (3), single-tenant Entra ID
  - rag-cost-optimization, observability, ai-services-enterprise, multi-model-strategy: dato-bump
  - deterministic-cost: Copilot Credits offisiell common currency (2025-09-01), CCCU prepurchase
  - gpt5-gpt41-pricing: utvidet Copilot Studio modell-lineup (GPT-5.2, GPT-5.3, Claude 4.6, Grok 4.1)
  - vector-storage, request-batching: dato-bump (DS allerede dekkende)

- High batch 1 (21 files, 10-30): Last updated 2026-04→2026-05 dato-bump
  Substantive Microsoft Learn-endringer var marginale per fetch — kosmetiske oppdateringer.

Resterende: high batch 2 (filer 31-53, 23 filer) i ny sesjon. Se NEXT-SESSION-PROMPT.local.md.
 2026-05-05 14:28:35 +02:00
Kjell Tore Guttormsen
baa2d0220b feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command 
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-08 08:58:35 +02:00