open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
386 commits 1 branch 8 tags 130 MiB
Commit graph

5 commits

Author SHA1 Message Date
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
8ff73b7fe3 feat(ms-ai-architect): C2.2 valgfritt fritekst-felt free-context.md i onboarding (TDD) [skip-docs] 
Spor C / C2.2 (#3, akseptanse K3): fanger et fritt prosa-felt i onboarding og
overflater det (kappet) ambient i hver sesjon.

- lib/user-data.mjs: FREE_CONTEXT_FILE (utenfor ORG_FILES — valgfri, teller ikke
  mot fullføring), collapseProse() surfacer fri kontekst som ÉTT felt uansett
  markdown-struktur (ingen stille drop), capValue() ekstrahert (DRY).
- session-start-context.mjs: leser free-context.md valgfritt (ingen count++).
- onboarding-agent.md: ny Phase 6 (valgfri); onboard.md: prosess/Task/status.
- 11 agenter: uniform 6. bullet (grep 11/11).
- Tester FØR kode: user-data 25/25 (+9), test-hooks 11/11 (+1 K3-ambient).

Gates: validate 239/0/0 · kb-update 200 · kb-eval 100 · kb-integrity 192/192
(220 baseline-warns) · discovery 13/13 · gitleaks 3 pre-eksisterende.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 14:16:00 +02:00
Kjell Tore Guttormsen
466094f2a2 feat(ms-ai-architect): C2.1 onboarding skriver bruker-sti + 11-agent fallback + docs [skip-docs] 
- onboard.md (orkestrator): resolver absolutt $ORG_DIR via Bash + mkdir -p, gir
  agenten stien. allowed-tools +Bash. Status/resume globber bruker-sti.
- onboarding-agent.md: skriver de 5 org-filene til den absolutte bruker-stien
  (~/.claude/ms-ai-architect/org/), aldri plugin-rot.
- 11 org-bevisste agenter: uniform Virksomhetskontekst-blokk -> bruker-sti +
  note om ambient injeksjon + subagent-fallback (grep-verifisert 11/11).
  Risiko 1 BEVIST: Task-subagent arver IKKE SessionStart-injeksjon; Read/Glob
  ekspanderer ~ -> fallback lesbar uten Bash.
- README + plan: sti-referanse + C2.1-resultat. CLAUDE.md uendret (ingen sti-ref).

Verifisert: validate PASSED · kb-integrity 192/192 · discovery 13/13.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 13:34:19 +02:00
Kjell Tore Guttormsen
84e3cfaa03 fix(ms-ai-architect): re-baseline kostnadslaget (GPT-5 $1.25/$10, én prissannhet, 10 filer) 
Audit-funn Tema B + action-items 149/150. Verifiseringen avdekket at kostnadslag-råten var bredere enn auditens 3 navngitte filer (10 filer totalt).

- GPT-5 flagship $10-15/$40-60 -> $1.25/$10.00 (verifisert juni 2026, 8-12x for hoy). gpt-5-mini $0.25/$2.00, gpt-5-nano $0.05/$0.40. Fjernet falske "Verified MCP"-stempel pa estimat-band.

- deterministic-cost-calculation-model.md gjort til ENESTE kanoniske prissannhet (§1.1). Strippet duplikat pris-tabell fra cost-models.md (rotarsak til GPT-4o $10/$30-motsetning) -> peker til registeret.

- Reconcile-funn utover audit: deterministic hadde GPT-4.1-serien HALVERT ($1/$4 og $0.20/$0.80) -> verifisert $2.00/$8.00 og $0.40/$1.60. multi-model-strategy-costs.md NOK-tabell var fabrikkert 10-47x for hoy (gpt-4o 250/1000 NOK -> 26/105). model-selection (GPT-5 $3/$12), reasoning-models (GPT-5 $20-30/$80-100), token-counting (gpt-4.1 cached $1->$0.50), small-language-models (GPT-4o output 60->105 NOK) rettet.

- Recalk alle NOK-scenarioer reproduserbart: gpt-5 ~= gpt-4.1 i kost (ikke 30-55x dyrere som gammel tekst pasto) - billigere input ($1.25 vs $2.00), dyrere output. Reell kostnadsdriver = resonnerings-tokens (fakturert som output).

- Fjernet GPT-3.5 Turbo-anbefaling (utfaset). Alignet kurs 11->10.5 NOK/USD i cost-kommando. Cost-agent eksempel: legacy GPT-4 -> GPT-4o-mini, fjernet falskt Verified-stempel.

- kb-update apply cost-bucket deferret til task #8 (kommando-feature, ikke tall-justering).

Verifisert mot OpenAI API pricing + Azure OpenAI pricing via WebSearch 2026-06-18. validate-plugin.sh 219 PASS.

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

Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
 2026-06-18 12:45:21 +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