Ai/full autonomous flow (#359)

* Refactor bookkeeping error handling and introduce new error classes

- Introduced new error classes for better error categorization:
  - JournalEntryNotBalancedError
  - FiscalPeriodNotFoundError
  - EntryDateOutsideFiscalPeriodError
  - JournalEntryNotFoundError
  - CannotReverseNonPostedError
  - CannotCorrectNonPostedError
  - EntryAlreadyReversedError
  - CurrencyRevaluationAlreadyExistsError
  - InvalidMappingResultError
  - BookkeepingDatabaseError

- Updated existing functions in engine.ts and transaction-entries.ts to throw specific errors instead of generic ones.
- Enhanced error response handling in get-error-message.ts to provide localized messages for new error types.
- Added unit tests for new error classes and error handling functions to ensure correctness and coverage.

* feat(ai): implement AI proposal application and persistence

- Add apply.ts to handle the application of AI proposals, including match and booking steps.
- Introduce persist.ts for inserting and managing AI requests and proposals, ensuring unique constraints.
- Create re-validate.ts for validating proposals before acceptance, checking for stale conditions.
- Define database migrations for ai_requests and ai_proposals tables, including constraints and indexes.
- Enhance journal_entries with AI provenance tracking, linking entries to AI proposals.
- Update categorization_templates to distinguish AI-corrected templates.
- Add company settings for toggling AI flow and managing backfill processes.
- Extend processing_history to include AI-related events for better tracking.

* feat: add uncategorized transactions API and UI for transaction selection

- Implemented a new API endpoint for fetching uncategorized transactions with pagination and filtering options.
- Created ChangeTransactionDialog component for selecting alternative transactions based on AI proposals.
- Developed ReceiptDetailDialog to display detailed information about receipts, including upload functionality.
- Added TransactionDetailDialog for viewing transaction details with links to the transaction list.
- Introduced receipt quality assessment logic to evaluate extracted receipt data.
- Implemented feature flagging for the AI bookkeeping agent to control availability in different environments.

* feat: add manual receipt extraction dialog and integrate AWS Textract for expense analysis

- Added ManualExtractDialog component for user input when AI fails to extract receipt data.
- Implemented ReceiptsList component to manage and display uploaded receipts, including upload and rescan functionalities.
- Introduced Textract integration for analyzing expenses, extracting fields like total, vendor, and date.
- Updated package.json to include @aws-sdk/client-textract dependency.

* fix(ai): handle livsmedel VAT transition (12% → 6%) in booking prompt and re-validate guard

Add date-aware guidance to BOOKING_SYSTEM_PROMPT for the temporary livsmedel
VAT cut (Prop. 2025/26:55, 2026-04-01 to 2027-12-31), with restaurang/servering
carve-out at 12%. Add a re-validate safety net that rejects clearly-stale rate
labels for grocery-chain merchants relative to the entry date.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

lib/transactions/__tests__/ingest.test.ts

@@ -414,6 +414,8 @@ describe('ingestTransactions', () => {
     enqueue({ data: [], error: null })
     // Transaction 1: insert OK
     enqueue({ data: inserted1, error: null })
+    // AI flow flag lookup (lazy, fires once on first auto-categorize branch)
+    enqueue({ data: { ai_flow_enabled: false }, error: null })
     // Transaction 2: insert OK
     enqueue({ data: inserted2, error: null })
 

lib/transactions/ingest.ts

@@ -120,6 +120,28 @@ export async function ingestTransactions(
   // by incoming enable_banking rows to avoid blocking unrelated CSV imports.
   const existingMaps = await buildExistingTransactionMaps(supabase, companyId, rawTransactions)
 
+  // AI agent gate: when the company has opted into the agent flow, every
+  // uncategorized transaction becomes a review proposal — no silent auto-book.
+  // Matching/suggestion still runs (it only sets potential_*_id fields), but
+  // the mapping-rule auto-categorize branch below is disabled. Fetched lazily
+  // the first time the auto-categorize branch is about to run, and cached for
+  // the rest of the batch so we don't hit the DB per-transaction.
+  let aiFlowEnabledCache: boolean | null = null
+  const isAiFlowEnabled = async (): Promise<boolean> => {
+    if (aiFlowEnabledCache !== null) return aiFlowEnabledCache
+    try {
+      const { data: aiSettings } = await supabase
+        .from('company_settings')
+        .select('ai_flow_enabled')
+        .eq('company_id', companyId)
+        .maybeSingle()
+      aiFlowEnabledCache = Boolean(aiSettings?.ai_flow_enabled)
+    } catch {
+      aiFlowEnabledCache = false
+    }
+    return aiFlowEnabledCache
+  }
+
   // When rawInsertOnly is set (viewer imports), skip pre-fetching GL lines,
   // supplier invoices, and exchange rates — they are not used.
   let glLinePool: UnlinkedGLLine[] = []
@@ -372,7 +394,9 @@ export async function ingestTransactions(
     // Skipped when SIE-imported entries overlap the sync range — prevents
     // double-booking. Reconciliation (step 2.5) still links transactions to
     // existing GL lines; only the "create new journal entry" path is suppressed.
-    if (!options?.skipAutoCategorization) {
+    // Also skipped when the company has opted into the AI agent flow — every
+    // uncategorized transaction must become a proposal, not a silent post.
+    if (!options?.skipAutoCategorization && !(await isAiFlowEnabled())) {
       try {
         const mappingResult = await evaluateMappingRules(
           supabase,