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>

components/transactions/AiCategorizeProposal.tsx

@@ -34,11 +34,22 @@ interface ProposalDto {
   reverseCharge: boolean
   confidence: number
   agreement: number
+  modelConfidence: 'high' | 'medium' | 'low'
+  fromCandidate: boolean
   reasoning: string
   choice: { kind: 'candidate' | 'category' | 'needs_review' }
   candidates: CandidateDto[]
 }
 
+/** What the dialog needs to log a calibration sample when the user books. */
+export interface AiProposalMeta {
+  account: string
+  confidence: number
+  agreement: number
+  modelConfidence: 'high' | 'medium' | 'low'
+  source: string
+}
+
 type State =
   | { status: 'loading' }
   | { status: 'error' }
@@ -51,6 +62,8 @@ interface Props {
   open: boolean
   /** Apply an account + VAT to the dialog fields. */
   onApply: (account: string, vat: VatTreatment | 'none') => void
+  /** Surface the proposal metadata so the dialog can log a calibration sample on book. */
+  onProposal?: (meta: AiProposalMeta) => void
 }
 
 type Band = 'sure' | 'likely' | 'review'
@@ -63,7 +76,7 @@ function bandOf(p: ProposalDto): Band {
 
 const BAND_LABEL: Record<Band, string> = { sure: 'Säker', likely: 'Trolig', review: 'Välj konto' }
 
-export default function AiCategorizeProposal({ transactionId, open, onApply }: Props) {
+export default function AiCategorizeProposal({ transactionId, open, onApply, onProposal }: Props) {
   const [state, setState] = useState<State>({ status: 'loading' })
   // Apply the pick to the dialog exactly once per fetch, so the user's later
   // manual edits are never clobbered by a re-render.
@@ -98,15 +111,34 @@ export default function AiCategorizeProposal({ transactionId, open, onApply }: P
     }
   }, [open, transactionId])
 
-  // Pre-fill the dialog once, when a confident proposal with a real account arrives.
+  const reportedRef = useRef(false)
+
+  // When a proposal with a real account arrives: surface its metadata to the
+  // dialog (for calibration logging on book) and pre-fill the fields.
   useEffect(() => {
     if (state.status !== 'ready') return
     const p = state.proposal
-    if (!p.account || appliedRef.current === p.account) return
-    if (bandOf(p) === 'review') return
+    if (!p.account) return
+
+    if (!reportedRef.current) {
+      reportedRef.current = true
+      const source = p.fromCandidate
+        ? (p.candidates.find((c) => c.account === p.account)?.source ?? 'candidate')
+        : 'category'
+      onProposal?.({
+        account: p.account,
+        confidence: p.confidence,
+        agreement: p.agreement,
+        modelConfidence: p.modelConfidence,
+        source,
+      })
+    }
+
+    // Pre-fill only when it's not the low "review" band, and only once.
+    if (appliedRef.current === p.account || bandOf(p) === 'review') return
     appliedRef.current = p.account
     onApply(p.account, p.vatTreatment ?? 'none')
-  }, [state, onApply])
+  }, [state, onApply, onProposal])
 
   if (state.status === 'loading') {
     return (

components/transactions/QuickReviewDialog.tsx

@@ -27,7 +27,7 @@ import InboxDocumentPicker from '@/components/bookkeeping/InboxDocumentPicker'
 import type { UploadedFile } from '@/components/bookkeeping/DocumentUploadZone'
 import type { AvailableInboxDoc } from '@/components/bookkeeping/InboxDocumentPicker'
 import VatTreatmentSelect from './VatTreatmentSelect'
-import AiCategorizeProposal from './AiCategorizeProposal'
+import AiCategorizeProposal, { type AiProposalMeta } from './AiCategorizeProposal'
 import { VAT_TREATMENT_OPTIONS } from './transaction-types'
 import type { TransactionWithInvoice } from './transaction-types'
 import type { TransactionCategory, VatTreatment, BASAccount, EntityType, LinePatternEntry } from '@/types'
@@ -91,6 +91,9 @@ export default function QuickReviewDialog({
   const [accountOverride, setAccountOverride] = useState(defaultAccount ?? '')
   const [vatTreatment, setVatTreatment] = useState<VatTreatment | 'none'>(defaultVat)
   const [accounts, setAccounts] = useState<BASAccount[]>([])
+  // The AI proposal shown this session, kept so we can log a calibration sample
+  // (proposed vs actually booked) once the user confirms.
+  const [aiProposal, setAiProposal] = useState<AiProposalMeta | null>(null)
   const [isProcessing, setIsProcessing] = useState(false)
   const [error, setError] = useState<string | null>(null)
   const [uploadedFiles, setUploadedFiles] = useState<UploadedFile[]>([])
@@ -291,6 +294,24 @@ export default function QuickReviewDialog({
         Object.keys(cleanedDims).length > 0 ? cleanedDims : undefined,
       )
 
+      // Calibration telemetry: what the model proposed vs what was actually
+      // booked. Best-effort and fire-and-forget — never blocks the booking.
+      if (journalEntryId && aiProposal) {
+        void fetch('/api/agent/categorize/outcome', {
+          method: 'POST',
+          headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify({
+            confidence: aiProposal.confidence,
+            agreement: aiProposal.agreement,
+            model_confidence: aiProposal.modelConfidence,
+            source: aiProposal.source,
+            proposed_account: aiProposal.account,
+            booked_account: override ?? catDefault,
+            amount: Math.abs(sekAmount),
+          }),
+        }).catch(() => {})
+      }
+
       // Attach the uploaded underlag to the verifikat the booking just created.
       // BFL 5 kap 7 § requires the verifikation to reference its underlag and
       // BFL 7 kap requires that underlag to be archived with it; the verifikat
@@ -447,6 +468,7 @@ export default function QuickReviewDialog({
             key={tx.id}
             transactionId={tx.id}
             open={open}
+            onProposal={setAiProposal}
             onApply={(account, vat) => {
               handleAccountChange(account)
               // handleAccountChange clears VAT for class-2 accounts; for the