Three MCP feedback reports (seq 265062, 288474, 288577; three companies) hit
the same hole: link_document_to_voucher attaches the document to the
verifikat but never stamps the inbox item it came from, and both inbox read
surfaces derive "handled" from the inbox row's own link columns, never from
document_attachments.journal_entry_id. So an attached document stayed
"unprocessed" forever: agents re-saw it as missing underlag (one reporter
paged 750 rows to find the ~15 real ones), and one user read the five
leftover rows as duplicates and was about to delete the only copies of
underlag sitting on posted verifikat.
- commitLinkDocumentToVoucher and the bulk twin now stamp
invoice_inbox_items.created_journal_entry_id, keyed on document_id, CAS on
both link columns, 23505 tolerated (samlingsverifikat). Same shape as the
create_voucher + inbox_item_id stamp; best-effort so inbox bookkeeping
never rolls back a committed link.
- gnubok_list_unmatched_documents returns file_name (same embed
list_inbox_items uses) and the extraction's page coverage, so an agent can
tell "no total on this document" from "we read 3 of 38 pages" and does not
have to fetch each document to learn what it is (seq 265062, 288574).
- gnubok_list_transactions_without_documents no longer echoes the column
default "uncategorized" on rows that are booked by construction:
list_uncategorized_transactions uses the same word for "no journal entry
yet", and an agent read the label and tried to re-book an already-booked
share-capital deposit (seq 288574).
No tools/list payload change: the unmatched-documents item schema is
untyped and the category field already allowed null.
Claude-Session: https://claude.ai/code/session_013yw62FMXGSzo6icFDiBwP3
Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Jakob Wennberg
01d903d3a3