9a166f93bb
fix(ms-ai-architect): #7a ruting — RAG/MLOps-KB-ruting (F) + forson ROS-last-kontrakt (G)
...
Audit P2 §94-118. Latent engineering-dybde gjøres nåbar; determinisme-løftet repareres.
F (ruting til RAG/MLOps-KB): betinget, navngitt Read-ruting (samme mønster som security/cost):
- architecture-review-agent.md: RAG-arkitektur + MLOps/GenAIOps lagt i domene-spesifikk last-blokk
- research-agent.md: ny lokal KB-baseline for RAG/MLOps-temaer — leses som hypotese, MCP er fasit, avvik flagges
- poc.md: betinget steg 3b — RAG/MLOps-kjernefiler forankrer scope + suksesskriterier
G (forson ROS-rutingsmotsetning): ett eksplisitt last-kontrakt forsont på tvers av tre kilder.
Tidligere: CLAUDE.md «max 3» vs agent 11 filer flatt vs ros.md 5 → ikke-deterministisk lasting.
Nå: kjerne (alltid, 4: trusselbibliotek/rubrikker/metodikk/mal) + betinget på trigger
(sektor/MAESTRO/DPIA-integrasjon/AI Act). Reflektert i:
- ros-analysis-agent.md: «Knowledge Base References» omskrevet til last-kontrakt + AI Act-blokk + «Load KB»-steg bundet til den
- CLAUDE.md: header «typisk 3 kjernefiler»; ROS dokumentert som unntak med 4 kjerne + betinget
- ros.md: delegeringsprompt skiller kjerne/betinget per kontrakt
validate-plugin: 223 PASS
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 17:22:48 +02:00
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
70f24fa9df
fix(ms-ai-architect): re-baseline EU AI Act-tidslinje (Digital Omnibus) + Art 99-bøtesatser
...
- Annex III hoyrisiko utsatt 2026-08-02 -> 2027-12-02 (provisorisk, Omnibus); Annex I -> 2028-08-02. Oppdatert CLAUDE.md frister, session-start-hook, ai-act-assessor output-mal + 5 AI Act-KB-filer.
- Art 99-boter: 30M/6% (finnes ikke) -> 35M/7% (Art 5), 15M/3% (ovrig), 7.5M/1% (feilinfo) i 4 filer.
- Art 50 transparens presisert (gjelder 2026-08-02; eksist. generative systemer frist 2026-12-02). Fjernet hardkodede dag-nedtellinger i CLAUDE.md.
Verifisert mot Consilium/Gibson Dunn/Latham/artificialintelligenceact.eu 2026-06-18.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 12:00:34 +02:00
Kjell Tore Guttormsen
781d98f62f
chore(privacy): scrub real-org references from plugin internals (phase 2)
...
Same bulk replacement applied to plugin-internal KB, examples, fixtures,
tests, and docs. Real organization names, persona names, internal system
identifiers, and domain-specific terms replaced with fictional generic
public-sector entity (DDT) and generic terminology.
Scope:
- okr/ — examples, governance, framework, integrations, sources
- ms-ai-architect/ — KB references (engineering, governance, security,
infrastructure, advisor), tests/fixtures, agents, docs
- linkedin-thought-leadership/ — voice samples, network-builder,
examples (genericized identifying headlines to "[your organization]")
- llm-security/ — research notes, scan report
Manual genericization beyond bulk replace:
- okr SKILL.md "Primary user / Domain" — generic Norwegian public sector
- linkedin-voice SKILL.md headline placeholder
- network-builder.md headline placeholder
- high-engagement-posts.md voice sample employer line + hashtag
Phase 3 (factual-attribution review) remains: a few KB files attribute
publicly known transport-sector docs/datasets (e.g. håndbok V440, NVDB)
to the fictional DDT after bulk replace. Needs manual semantic review
to either remove or restore correct citation without re-introducing
affiliation references.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-03 04:28:15 +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
