Commit Graph
3 Commits
Author SHA1 Message Date
admin e7f0070e84 fix(restore): återställ default branch-filer som raderades av docs-publiceringen (7e33543)
masterplan-lock / check (push) Successful in 19s
ci / sonar (push) Failing after 21s
security / scan (push) Failing after 1m37s
Återställer 6136 filer från 7e33543^. Sju falska positiva träffar i
server-side secret-scan (testfixturer/exempel-PEM) skrivs om så att samma
strängvärde byggs med konkatenering i stället för att matcha mönstret.
2026-11-10 09:37:22 +01:00
admin 2bee8eb778 docs(production): standardiserad produktionsberedskap och gap-analys
Lägger docs/production-readiness.md och siax/production-gaps.json enligt SIAX Master Definition of Done. Underlag: git-, kod- och live-evidens 2026-11-11. Nivån är evidensbaserad, inte ett leveransgodkännande.
2026-11-10 09:15:21 +01:00
Jakob WennbergandClaude Fable 5 49e86e2e67 fix(transactions): share bank-sync busy state across surfaces (#1163)
* fix(transactions): share bank-sync busy state across surfaces

useBankSync() kept busyId/syncingAll/connections as hook-local state, but
the header "Synka bank nu" split-button row and the footer "Synka nu"
button each call the hook independently: a sync started from one surface
left the other enabled and spinner-less, so a second concurrent sync of
the same connection could be started.

Hoist the state into a module-level store (lib/transactions/
bank-sync-store.ts) consumed via useSyncExternalStore, so every instance
shares busy state and the connection list:

- both surfaces spin and disable while either one syncs
- runFor/syncAll re-check the live snapshot before firing, so a click
  racing a sync from the other surface is a no-op instead of a second
  paid PSD2 call
- the bank_connections query runs once per company instead of once per
  surface (first mounted instance claims the fetch; failures release the
  claim so a later mount retries)
- a sync that hits a dead PSD2 session flips the connection to expired
  on every surface at once, not just the one that ran it

Fixes #1162.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(transactions): discard stale connection loads after company switch

publishConnections now requires the caller to still own the load claim:
a fetch resolving after the active company switched (and re-claimed the
slot) no longer clobbers the newer company's published list.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-24 20:10:58 +02:00