feat(invoice-inbox): receipt-aware extraction + OCR pipeline fixes (#1331)

Receipts and invoices were extracted through one invoice-shaped prompt
with no document classification. The extractor now also returns
documentKind, payment method (+ card last4), purchaseTime,
merchantCategory and legibility, validated with .catch(null) so a
hallucinated label degrades to unknown instead of sinking the parse.
The FieldsRail shows type and payment method above the editable fields.

Pipeline fixes, all verified against real failure paths:
- PDFs >3 pages: extract from a pdf-lib slice of the first 3 pages
  instead of skipping entirely (issue #553 gate); truncation recorded
  in extracted_data.pages and shown in the UI.
- Oversized images (>4 MB, over Bedrock's 5 MB cap): downscale to
  <=2000px JPEG via sharp before base64, instead of erroring to an
  empty result.
- HEIC/HEIF: attempt sharp transcode to JPEG; when libvips lacks HEIF
  (prebuilt binaries), fall through to today's behavior but show an
  explicit hint instead of silently blank fields.
- Oresavrundning: prompt rule + totals.roundingAmount so receipt totals
  reconcile with subtotal+VAT for exact-amount transaction matching.
- retry-extraction overwrites extracted_data wholesale: a confirm now
  guards against silently destroying manual field edits.

Deliberately NOT added: retry-on-transient-Bedrock-error; the SDK
already retries twice by default (maxRetries=2).

Co-authored-by: Jakob Wennberg <jakob.wennberg@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Jakob Wennberg
2026-08-05 14:20:40 +02:00
committed by GitHub
co-authored by Jakob Wennberg Claude Fable 5
parent b1f71912a2
commit 3b3adf96c7
9 changed files with 466 additions and 26 deletions
+16 -1
View File
@@ -2797,7 +2797,22 @@
"document_loading": "Fetching the document…",
"document_load_failed": "The document is still stored but could not be shown right now.",
"email_body_label": "Email content",
"email_body_empty": "The email had no text."
"email_body_empty": "The email had no text.",
"doc_kind_label": "Type",
"doc_kind_receipt": "Receipt",
"doc_kind_supplier_invoice": "Supplier invoice",
"doc_kind_government_letter": "Government letter",
"doc_kind_other": "Other document",
"payment_label": "Paid with",
"payment_card": "Card",
"payment_swish": "Swish",
"payment_cash": "Cash",
"payment_invoice": "Invoiced",
"payment_other": "Other",
"pages_partial_note": "Extracted from the first {analyzed} of {total} pages.",
"heic_hint": "HEIC images cannot be AI-extracted yet. Upload the receipt as JPEG or PDF, or fill in the fields manually.",
"skipped_hint": "AI extraction did not run for this document. You can link the document to a transaction or create a supplier invoice manually.",
"retry_overwrite_confirm": "Re-running extraction overwrites the fields, including your own edits. Continue?"
},
"inbox_custom_domain": {
"title": "Custom inbox domain",
+16 -1
View File
@@ -2797,7 +2797,22 @@
"document_loading": "Hämtar underlaget…",
"document_load_failed": "Underlaget finns kvar men kunde inte visas just nu.",
"email_body_label": "Mejlets innehåll",
"email_body_empty": "Mejlet hade ingen text."
"email_body_empty": "Mejlet hade ingen text.",
"doc_kind_label": "Typ",
"doc_kind_receipt": "Kvitto",
"doc_kind_supplier_invoice": "Leverantörsfaktura",
"doc_kind_government_letter": "Myndighetsbrev",
"doc_kind_other": "Övrigt dokument",
"payment_label": "Betalsätt",
"payment_card": "Kort",
"payment_swish": "Swish",
"payment_cash": "Kontant",
"payment_invoice": "Faktureras",
"payment_other": "Annat",
"pages_partial_note": "Tolkad från de första {analyzed} av {total} sidorna.",
"heic_hint": "HEIC-bilder kan inte AI-tolkas ännu. Ladda upp kvittot som JPEG eller PDF, eller fyll i fälten manuellt.",
"skipped_hint": "AI-tolkning kördes inte för det här dokumentet. Du kan koppla dokumentet till en transaktion eller skapa leverantörsfaktura manuellt.",
"retry_overwrite_confirm": "Ny tolkning skriver över fälten, även ändringar du gjort själv. Fortsätta?"
},
"inbox_custom_domain": {
"title": "Egen domän för inkorgen",