20c1be6531
fix(ms-ai-architect): #7c wire foreldreløse deliverable-KB — nye kommandoer businesscase + anskaffelse (I)
...
Audit P2 I. 6 foreldreløse deliverable-KB-er surfaces nå (var skrevet/betalt for, ikke nåbare).
Operatørvalg: dedikerte kommandoer (audit-primær), ikke kun dokumentasjon. Telling 25→27 kommandoer.
Nye kommandoer:
- businesscase.md → samfunnsokonomisk-analyse-nnv.md + gevinstrealisering-dfo-methodology.md (NNV + DFØ 5-stegs gevinst)
- anskaffelse.md → anskaffelser-ai-procurement-framework.md (kravspec, leverandørevaluering, terskelverdi)
Utvidet eksisterende:
- compare.md: weighted multi-kriterie-modus (alternativanalyse-methodology.md) ved 3+ alternativer / --weighted
- cost.md: kapasitet-/gjennomførbarhetssteg (gpu-compute-sizing.md + capacity-feasibility-benchmarks.md) ved --capacity
De-orphaning (kb-integrity måler orphan via SKILL.md/agents, ikke kommandofiler):
- ms-ai-governance/SKILL.md: ny seksjon 1.4 Beslutningsgrunnlag (3 referanser)
- ms-ai-advisor/SKILL.md: alternativanalyse + capacity-feasibility
- ms-ai-security/SKILL.md: gpu-compute-sizing
→ alle 6 de-orphaned (kb-integrity warnings 268→262)
Registrering/docs: help.md + README + CLAUDE.md-tabell + playground-katalog (2 produces_report:false-
oppføringer, gjenbruker ikke 14-parser/17-renderer-kanonen) + docs/playground.md (25→27) + test 25→27.
validate 231 PASS · playground v3 221 PASS · e2e alle suiter · kb-integrity 115/115 — 0 FAIL overalt.
NB: README:358/418/427 har pre-eksisterende «24 commands»-drift (uavhengig av denne endringen) — flagget for #8 .
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-18 17:50:06 +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
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
