MattssonandClaude Opus 4.7
1af977950b
* 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>
56 lines
1.8 KiB
TypeScript
56 lines
1.8 KiB
TypeScript
import type { AgentInboxItemView } from '@/app/(dashboard)/agent-inbox/page'
|
|
|
|
export type ReceiptQualityIssue =
|
|
| 'missing_merchant'
|
|
| 'missing_total'
|
|
| 'missing_date'
|
|
| 'low_confidence'
|
|
|
|
export interface ReceiptQualityAssessment {
|
|
ok: boolean
|
|
issues: ReceiptQualityIssue[]
|
|
message: string | null
|
|
}
|
|
|
|
const ISSUE_LABELS: Record<ReceiptQualityIssue, string> = {
|
|
missing_merchant: 'handlare saknas',
|
|
missing_total: 'belopp saknas',
|
|
missing_date: 'datum saknas',
|
|
low_confidence: 'låg extraktionssäkerhet',
|
|
}
|
|
|
|
// Heuristic quality check on a classified receipt. Until the classification
|
|
// prompt returns an explicit quality_score, we infer it from which critical
|
|
// fields came back and the LLM's self-reported confidence (stored on
|
|
// invoice_inbox_items.confidence after classification). 0.6 is the cutoff
|
|
// where accepted vs. edited rates diverge noticeably in practice.
|
|
export function assessReceiptQuality(
|
|
inbox: AgentInboxItemView['inbox_item']
|
|
): ReceiptQualityAssessment {
|
|
const data = inbox.extracted_data as {
|
|
merchant?: { name?: string | null } | null
|
|
receipt?: { date?: string | null } | null
|
|
totals?: { total?: number | null } | null
|
|
} | null
|
|
|
|
const issues: ReceiptQualityIssue[] = []
|
|
|
|
if (!data?.merchant?.name) issues.push('missing_merchant')
|
|
if (data?.totals?.total == null) issues.push('missing_total')
|
|
if (!data?.receipt?.date) issues.push('missing_date')
|
|
|
|
const confidence = inbox.confidence == null ? null : Number(inbox.confidence)
|
|
if (confidence != null && confidence < 0.6) issues.push('low_confidence')
|
|
|
|
if (issues.length === 0) {
|
|
return { ok: true, issues, message: null }
|
|
}
|
|
|
|
const labels = issues.map((i) => ISSUE_LABELS[i])
|
|
return {
|
|
ok: false,
|
|
issues,
|
|
message: `Kvittot verkar otydligt — ${labels.join(', ')}.`,
|
|
}
|
|
}
|