Commit Graph
3 Commits
Author SHA1 Message Date
admin e7f0070e84 fix(restore): återställ default branch-filer som raderades av docs-publiceringen (7e33543)
masterplan-lock / check (push) Successful in 19s
ci / sonar (push) Failing after 21s
security / scan (push) Failing after 1m37s
Återställer 6136 filer från 7e33543^. Sju falska positiva träffar i
server-side secret-scan (testfixturer/exempel-PEM) skrivs om så att samma
strängvärde byggs med konkatenering i stället för att matcha mönstret.
2026-11-10 09:37:22 +01:00
admin 2bee8eb778 docs(production): standardiserad produktionsberedskap och gap-analys
Lägger docs/production-readiness.md och siax/production-gaps.json enligt SIAX Master Definition of Done. Underlag: git-, kod- och live-evidens 2026-11-11. Nivån är evidensbaserad, inte ett leveransgodkännande.
2026-11-10 09:15:21 +01:00
704bf93e08 feat(categorize): confidence calibration engine + measurement loop (cascade step 4) (#1784)
Turns the selector's raw confidence into a score that means what it says.

- lib/agent/categorize/calibration.ts: the engine. Isotonic regression
  (pool-adjacent-violators, distribution-free + monotonic) over
  (confidence, was_correct) samples → a calibrator; plus reliabilityByBucket,
  ECE, and bandFor(). bandFor NEVER returns 'auto' without a fitted calibrator
  (no silent booking on an unproven score) and never auto-books above an amount
  cap. 12 engine tests (overconfidence pulled down, underconfidence lifted,
  monotonicity, ECE, band gating).
- Measurement loop: migration categorize_calibration_samples (append-only,
  company-scoped RLS, confidence CHECK [0,1]) + POST /api/agent/categorize/
  outcome logging one sample (proposed vs actually booked) fire-and-forget from
  QuickReviewDialog on a successful book (sandbox skipped). AiCategorizeProposal
  surfaces the proposal metadata via onProposal.
- scripts/fit-categorize-calibration.ts (read-only): prints the reliability
  diagram + ECE + fitted calibrator once data has accumulated.

Fitting needs a few hundred real outcomes, so nothing calibrates today — the
loop starts collecting, and "säker" stays uncalibrated (no auto-book) until the
data proves it. 131 unit tests green; RLS covered by a pg-real test.

Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-21 15:55:26 +02:00