Rotårsak-mekanisme: scripts/kb-update/data/ai-act-deadlines.json er nå eneste
kilde for AI Act-frister; CLAUDE.md-tabellen, assessor-malen og begge hooks
synk-testes mot den (tests/kb-update/test-ai-act-deadlines-sync.test.mjs, 9
tester, TDD rød→grønn). Suite 815/815.
- B2: «Kommisjonen kan fremskynde»/«ytre grense» fjernet (trigger droppet i
endelig Omnibus-tekst)
- B3: status oppdatert i alle 3 lag — formelt vedtatt (EP 2026-06-16, Rådet
2026-06-29), trer i kraft ved OJ-publisering (ikke publisert per 2026-07-15,
verifisert mot EUR-Lex 32024R1689)
- B4: Art. 50-raden «Gjeldende» → «Fra 2026-08-02»
- B5: stop-hooken feilmerket 2026-08-02 som «GPAI-frist» — begge hooks leser
nå kilden, 0 hardkodede frist-literals
- R3-5: 2026-12-02-raden (Art. 50(2)) inn i assessor-malen
- M10: Nkom navngitt som koordinerende markedstilsynsmyndighet + nasjonalt
kontaktpunkt (kilde: nkom.no/ki/regulering/hvem-handhever)
- pending_oj-markører i kilden for RX-REG² (nudifiserings-forbud, Art. 111)
- .gitignore: whitelist for den kuraterte frist-kilden
Det rapporterende gulvet (§4 Port 3, P3b): SessionStart-hooken surfacer en
KB-tillit-énlinjer fra cachet verified-staleness-report.json. Et GULV, ikke en
gate (§4c — unngå alarm-tretthet på 84 %-signal).
summarizeTrustFreshness (detection-schedule.mjs, ren, speiler
summarizeSkillQuality): surfacer KUN drift (stale-since-verified) +
kontraktbrudd (unverified) — det handlingsbare «bekreft mot kilde»-settet.
unmigrated (Spor-1-backlog, 306 i dag) ekskluderes bevisst: ved det volumet
ville det fyre hver økt og bli støy; migrerings-censusen hører i CT5 (P3c).
Tolererer manglende/malformed cache → null (gitignored, fraværende i fersk
klon, krasjer aldri hooken).
session-start-context.mjs: leser cachen read-only (samme mønster som
skill-quality-blokken), dytter linjen når den finnes.
Ende-til-ende verifisert: injisert stale-rapport → «KB-tillit: 3 filer driftet
siden verifisering, 1 uverifisert — bekreft mot kilde (aldri auto-fiks)»; ekte
korpus (306 unmigrated) → taus (ingen falsk alarm).
TDD (Iron Law): 8 nye tester. Suite 612/612. Plugin-validering PASS.
summarizeSkillQuality(cache) (pure) in detection-schedule.mjs: one-liner
"Skill-kvalitet: N skills < 90 % (navn)"; null when all skills meet target,
when the cache is missing (gitignored → absent in a fresh clone), or when the
shape is malformed. Reads the CACHED skill-score-report.json (from Steg B) —
never scores live (buildReport reads ~400 ref-files). Wired into
session-start-context.mjs after the course-signals block (same
existsSync/try-catch pattern). 7 new tests (kb-update 316 → 323).
[skip-docs]: README is the public end-user doc; skill-quality scoring is
maintainer-only tooling (the cache is gitignored, so the signal never surfaces
for end-users). The right doc homes ARE updated: CLAUDE.md hook table + a
caveat note (this commit), and docs/skill-quality-scoring-plan.md §3 komponent 4.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ToS-vurdering konkluderte med at autonom cron-kjøring er unødvendig kompleks
for en solo-fork-and-own-plugin. Apply-fasen krever LLM-resonnering uansett,
så manuell trigger fra en aktiv Claude Code-sesjon er enklere og holder
pluginen klart innenfor Anthropic Consumer Terms paragraf 3 (automated access
only via API key or where explicitly permitted — Claude Code CLI er
eksemptert som offisielt verktøy).
Lagt til:
- commands/kb-update.md — ny /architect:kb-update slash-kommando som driver
poll, endringsrapport, microsoft_docs_fetch-update og commit fra sesjonen.
Argumenter: --skip-discover, --priorities, --dry-run, --single-commit
- Catalog-entry i playground HTML for kb-update (categori: tool, 4 input-felt)
Slettet (Wave 3-5 reversert, ~1500 linjer + 7 testmoduler):
- scripts/install-kb-cron.mjs (cross-OS scheduler-installer)
- scripts/kb-update/weekly-kb-cron.mjs (cron-orkestrator med pre-flight, lock,
backup, claude -p subprocess, post-run verify, rollback)
- scripts/kb-update/templates/ (4 scheduler-templates: launchd plist, systemd
service+timer, Windows ps1 + README)
- scripts/kb-update/lib/auth-mode.mjs (cron-spesifikk auth validation)
- scripts/kb-update/lib/lock-file.mjs (PID+mtime stale-detection)
- scripts/kb-update/lib/cost-estimat.mjs (pre-flight budget-cap)
- 7 testmoduler under tests/kb-update/ for slettet kode
- tests/test-kb-update.sh (Bash-3.2-shim, erstattet av direkte node --test)
Beholdt (utility-laget fortsatt brukbart):
- run-weekly-update.mjs, report-changes.mjs, build-registry.mjs,
discover-new-urls.mjs (KB change-detection-pipelinen)
- lib/atomic-write, lib/backup, lib/cross-platform-paths, lib/log-rotate
- 4 testmoduler (42/42 tester PASS)
Endret:
- hooks/scripts/session-start-context.mjs: fjern kb-update-status.json-overvaaking
- tests/run-e2e.sh --kb-update kaller node --test direkte i stedet for shim
- README.md, CLAUDE.md: KB-vedlikehold-seksjon rewriter for manuell modell
- plugin.json: 1.11.0 -> 1.12.0
- Rot README + CLAUDE.md: ms-ai-architect-versjon bumpet
Schedulering er bevisst utenfor scope og overlatt til brukeren — eventuelle
forks som vil ha periodisk varsling kan sette opp egen cron / launchd /
GitHub Actions som kjører rapport-fasen og varsler om aa kjore
/architect:kb-update i CC-sesjon.
Verifisering:
- bash tests/validate-plugin.sh: 219 PASS, 0 FAIL
- bash tests/run-e2e.sh --kb-update: 42/42 inner + suite PASS
- bash tests/run-e2e.sh --playground: 271/271 PASS (statisk + parsers)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Adds a zero-dependency Node.js pipeline that polls Microsoft Learn sitemaps
weekly to detect when source documentation changes. Replaces the broken
mtime-based staleness check (all files had identical mtime after release).
Components:
- build-registry.mjs: extracts 1342 URLs from 387 reference files
- poll-sitemaps.mjs: streams ~18 child sitemaps, matches against registry
- report-changes.mjs: prioritized change report (critical/high/medium/low)
- discover-new-urls.mjs: finds relevant new MS Learn pages not yet covered
- run-weekly-update.mjs: orchestrator with --force/--discover/--dry-run
Integration:
- session-start hook reads change-report.json instead of broken mtime check
- hook triggers background poll if >7 days since last check
- generate-skills --update reads change report for targeted MCP updates
Current stats: 69% match rate (924/1342 URLs tracked via sitemaps).
~31% unmatched due to Microsoft URL restructuring (ai-foundry/openai paths).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
