Commit graph

4 commits

Author SHA1 Message Date
a6ff17fd45 feat(ms-ai-architect): Spor D steg A — eng+infra K10-fix → korpus-invariant ≥90 oppfylt
Skjerper ms-ai-infrastructure-description for å bryte build↔operate-overlappet
mot ms-ai-engineering (operatør-godkjent leaning, S38): "multi-region"→"cross-region"
og "edge AI architecture"→"edge AI deployment". Fjerner de delte distinktive tokenene
`multi` (vekt 0.5) og `architecture` (0.333) → eng↔infra combined 7.4167→6.5833 (< 7.0
terskel). Korpus-maks faller til 6.8333 (eng↔gov, pass). Begge edits sammen gir lavere
worst-case enn edit #1 alene (6.9167), derfor robust margin.

Resultat: K10-gulvet løftes for begge → eng 89→96, infra 89→96. ALLE 5 skills nå ≥90
(advisor 91, eng/gov/infra/sec 96). Korpus-invarianten (operatør-krav S38) oppfylt.

Judge-cache (🔑-regel): description-edit invaliderer infra K1. Re-judget mot det
operatør-kuraterte 20-settet — UENDRET 1.0/0.0/1.0 (edit fjerner kun tokens → kan ikke
gi falske positive; in-domain #2/#6 trigger fortsatt på BCDR/hybrid-vokabular).
K4/K7/K8/K9 uendret (body/refs urørt). Provenance oppdatert S11→S39.

Test: K10-real-five-testen pinnet pre-fix-baseline (eng+infra FAIL) — oppdatert til å
pinne korpus-invarianten (alle 5 pass, eng↔infra < 7.0). kb-eval 142/142, kb-update
316/316, validate 239/0, kb-integrity 192/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 17:56:43 +02:00
6b3c44adc3 fix(ms-ai-architect): Sesjon 10 — K9-destale eng+infra (volatil status → ref)
Begge S10-kriterier møtt (operatør-gated kald LLM-judge): engineering K9 PASS,
infrastructure K9 PASS. Deterministisk ikke regredert: validate 239 · kb-eval 15
· kb-update 122 · kb-integrity 192/192. K4 hevet 4→5 begge skills.

Engineering: modellversjoner (GPT-4o/Whisper/Florence/text-embedding-3) →
generisk kapabilitets-framing; MAF-«erstatter SK»-transisjon + Foundry Agent
Service GA → pekere; «Start med GPT-4o» (ABSENT i ref) droppet.

Infrastructure: SLA-tabell (ABSENT i ref) → relativ-veiledning + MCP-peker;
RTO/RPO-tabell → sammendrag + peker (ref bærer hele tier-modellen); «peak+30%»
(ref sier 20%) → generisk; Phi-3/Phi-4 + parametertall → «Phi-familien»
(fjernet faktafeil «Phi-4 14B»).

Metode: read-only verifiserings-agenter kartla ref-dekning FØR sletting.
judge-results.json oppdatert med ferske kalde eng+infra-verdikter (_updated: S10).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-20 09:31:21 +02:00
b03fcd8880 chore: WIP marketplace doc adjustments across plugins
Pre-trekexecute snapshot of in-progress CLAUDE.md/SKILL.md edits and
extracted docs/ files. Captured as one commit so /trekexecute claude-design
can run against a clean working tree.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-18 12:04:02 +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