The support chat showed 'Tänker' and then went quiet with no answer and
no error. Root cause: the 2026-08-21 RIP-3 cutover moved general.help to
the single-call POST /api/agent/ask, whose 1500-token default cap made
stop_reason max_tokens routine on tool-loop turns. The empty answer then
passed unlogged through the service, the route answered 200 with an
empty string, and the console appended an invisible empty bubble.
Fixes, single-call path:
- ask-service: default maxTokens 1500 -> 5400 (the streaming chat's
reply ceiling); an empty final answer now logs model + usage and
throws the typed EmptyModelAnswerError instead of passing through.
- /api/agent/ask: maxDuration 300, logger, empty answer maps to 502
with 'Assistenten gav inget svar. Försök igen.'; an empty assistant
turn is never persisted (the question stays, so retry works).
- AskConsole: a 200 with an empty answer shows the error box instead of
appending an invisible bubble.
- anthropic-family: serialized tool results are bounded at 40000 chars
(mirrors run-turn) so one big read cannot eat the output budget; the
step-exhausted fallback keeps tools declared with tool_choice none,
because replaying tool_use/tool_result without tools is an API 400.
Fixes, streaming path (same silent class):
- /api/agent/invoke: maxDuration 300 so deep thinking turns are not
killed mid-stream at the platform default cap.
- run-turn: stop_reason max_tokens with no visible text emits an error
event, not a bare turn_complete.
- AgentChat: an NDJSON stream that ends without turn_complete or error
(and was not aborted) shows 'Anslutningen bröts innan svaret blev
klart. Försök igen.'
The lib/ai request-shape tests were updated deliberately for the
fallback change; general.help stays on the single-call runtime
(founder decision, not reverted).
Claude-Session: https://claude.ai/code/session_01SyDuePXxUFowaPBKpAv8SF
Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The /chat assistant (audit Option A / rip) shipped in #1759 reading only the
company name + entity type, so it answered "jag har ingen bokföringsdata" to
every figures question ("vad är min största utgiftspost?"). It now behaves like
an MCP client: it answers over a bounded, READ-only tool loop across the same
MCP read tools the old streaming assistant had, plus an always-on company
snapshot as the backstop.
Provider-agnostic by construction, so it still runs on a local model:
- lib/ai generateText gains optional `tools` + `maxSteps`. The OpenAI-compatible
service forwards them to the Vercel AI SDK (stopWhen: stepCountIs), which runs
the loop; the Anthropic-family service hand-rolls a small loop against
messages.create. Kept on the raw Anthropic SDK: no new deps, and the no-tools
path is byte-identical, so hosted extraction/composer/etc. are unchanged.
- lib/agent/ask/ledger-tools.ts: the read slice of general.help's whitelist
(income statement, VAT, ledgers, query_journal, reskontror, lists…) from
agentToolRegistry, dispatched with the agent_chat actor run-turn uses. Write/
staging + memory-write tools are excluded; readOnlyHint/destructiveHint are
re-checked. Empty in a core-only build → snapshot-only, graceful.
- lib/agent/ask/snapshot.ts: a compact company_settings + deadlines block so a
model that can't/won't call tools still answers status questions. Never carries
figures (those come from the live tools).
- ask-service attaches tools + snapshot when a userId is present and uses a
tool-aware system prompt; the route calls ensureInitialized() so the registry
is populated and threads userId/conversationId through.
Works on Bedrock and on any local model with function-calling (Qwen). Tests:
the anthropic hand-rolled loop (tool call → result → answer, is_error handling,
step-budget forced answer), openai tool forwarding, the read-only adapter
filter, the snapshot format, and the ask-service wiring. 457 agent+ai tests
green, lint/guards clean.
Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(ai): job-shaped AI service with OpenAI-compatible backend, extraction-first; stop extracting every inbox document twice
Sovereign plan WS1 PR1 (#1406 Tier 2, extraction-first, aligned with the
AI surface audit).
lib/ai grows a job-shaped service (generateText / generateStructured /
extractFromDocument; no streaming members yet, see plan rule R3):
- services/anthropic-family delegates to the existing createAiClient()
and sends the exact request literals the inbox extractor sent before
(request-shape tests deep-equal them), so hosted Bedrock stays
byte-identical.
- services/openai-compatible talks to any chat-completions endpoint
(BYO Swedish provider) via Vercel AI SDK 6.x, exact-pinned and
guarded: images as parts, PDFs rasterized with poppler (AI_PDF_MODE)
or sent natively, AI_VISION / AI_STRICT_JSON declared, honest skips
(ai_no_vision, pdf_rasterizer_missing) instead of fake failures.
- config.ts: AI_PROVIDER/AI_BASE_URL/AI_API_KEY/AI_MODEL and per-tier
AI_*_MODEL with the legacy BEDROCK_* names kept as the same overrides;
getAiStatus() is the single source of truth for "is AI wired up".
- provider.ts: openai-compatible in the auto-detect chain (after Bedrock
and the direct API); createAiClient() refuses it loudly.
Document extraction moves onto the service and gets the audit's fixes:
- Inbox documents were extracted TWICE (pipeline A ran inside
uploadDocument() before the inbox row existed, so its dedupe branch
never fired; 3 707 + 1 666 calls / 30 d). The inbox now declares
extractionOwner on the upload, the extension yields, and the inbox
mirrors its single outcome onto document_attachments from every
writer (sync, deferred, attach, retry, MCP).
- Every "no extraction will ever happen" outcome is stamped
(skipped:no_ai_entitlement / ai_unconfigured / system_generated /
...); the status route maps the quiet ones to 'disabled' on the first
poll instead of a 30 s client timeout. Prod showed 309 of the 327
never-extracted uploads were the paywall working silently.
- Self-generated documents (our own invoice PDFs, payout files) are no
longer OCR'd.
- Agent invoke answers 503 ai_unconfigured when the deployment has no
assistant backend, distinct from the paywall.
Guard: new direct-ai-client antipattern check (shrink-only allowlist of
the pre-abstraction SDK callers) plus exact pins for @anthropic-ai/sdk,
ai and @ai-sdk/openai-compatible.
Verified: 15 958 unit tests green, guards, lint ratchet, typecheck, and a
live smoke against hosted Bedrock through the new service (ping, streamed
tool turn, thinking+cache, PDF extraction).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(ai): make AI_API_KEY optional for OpenAI-compatible endpoints (keyless local model servers)
A local model server (llama.cpp's server, Ollama /v1, LM Studio, vLLM)
usually has no auth. Before, the OpenAI-compatible backend required both
AI_BASE_URL and AI_API_KEY to count as configured, so running Accounted on a
local model meant setting a meaningless placeholder key.
- resolveAiProvider / hasAiCredentials: a base URL alone is now enough.
- services/openai-compatible: only send Authorization: Bearer when AI_API_KEY
is set, so a keyless server is never handed an empty bearer; a hosted
provider that needs a key still sets it.
- Docs (SELF-HOSTING Option 3: local-model example, key marked optional),
DECISIONS.
Verified: with no AI_API_KEY, just AI_BASE_URL + AI_MODEL, getAiStatus()
reports configured=true / provider=openai-compatible (live). lib/ai suite
71 green; tsc, guards, lint clean. Bedrock/Anthropic logic unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat(ai): resolve the Claude backend from the environment
Tier 1 of #1406: a self-hosted deployment can now run every AI feature on a
plain ANTHROPIC_API_KEY, with no AWS account. Hosted behaviour is unchanged.
lib/ai/provider.ts resolves the backend once, from the environment:
AI_PROVIDER explicit override, bedrock|anthropic
AWS static key pair Bedrock
ANTHROPIC_API_KEY the direct Anthropic API
nothing set Bedrock, so the AWS credential provider chain
(instance profile, IRSA) still resolves
Bedrock deliberately wins when both credential sets are present. EU residency
in eu-north-1 is a BFL/GDPR posture rather than a default, so adding an
Anthropic key for an experiment must not silently move production inference
out of the region. AI_PROVIDER is the way to say you meant it.
Model ids are written bare in code and prefixed to eu.anthropic.* only for
Bedrock, which needs the cross-region inference profile for on-demand
throughput. An operator override that already carries a prefix passes through
untouched, so BEDROCK_MODEL_ID and friends keep working as written.
Converted call sites: the agent composer, invoice-inbox extraction, the
document-extraction model label, and both receipt-hunt clients. The last two
are not named in the issue, which predates receipt-hunt landing in main.
@anthropic-ai/sdk is declared at 0.95.0, the version @anthropic-ai/bedrock-sdk
0.29.1 already pulled in transitively, so the lockfile dedupes to one copy
with no new download.
scripts/smoke-bedrock.ts becomes scripts/smoke-ai.ts and grows two steps.
Unit tests can only prove which provider and model id get resolved; they
cannot prove the resulting request is one the backend accepts. The script now
sends real traffic over all three shapes the app uses: a plain create, a
streamed turn carrying adaptive thinking, an effort level, an hour-long cache
breakpoint and a tool, and document extraction end to end when given a file.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* docs(self-hosting): document the AI smoke test
The script added alongside the provider split is what closes the #1406
acceptance criterion ("document extraction and the assistant both work"), so
a self-hoster needs to know it exists. Covers both invocations and states
that it exits non-zero, which is what makes it usable as a post-deploy check.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* test(ai): split the smoke test's thinking probe from its tool probe
The combined probe could not falsify what it claimed to. It asked a question
that needs a tool call, so the tool was used and adaptive thinking correctly
declined to reason about it: the zero thinking-block count that came back was
uninformative rather than a signal.
2a keeps the tool and drops thinking. 2b asks a question with several
dependent steps (reverse charge, then a partial deduction, then the affected
boxes) so that a model honouring the parameter must reason, and reports the
thinking text length as well as the block count, since display:"summarized"
can yield blocks with empty text.
The cached system prompt is also padded past the 1024-token minimum cacheable
prefix. Below that the API caches nothing and reports no error, so the old
probe's cache counters read zero whether or not caching worked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* fix(document-extraction): stop requiring AWS_REGION in the manifest
The extension now needs one of two credential sets, AWS static keys or
ANTHROPIC_API_KEY, and the manifest schema cannot express "one of". Since
requiredEnvVars only drives a build-time warning and never gates anything,
listing AWS_REGION told every self-hoster running the direct API to set a
variable that has no effect for them.
The description was also still promising Sonnet 4.6 via Bedrock specifically,
which is no longer what the extension does.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* fix(ai): read documentKind defensively in the smoke test
The field arrived with the receipt-aware extraction work, so referencing it
directly stops the script compiling against any checkout from before that
landed. tsconfig includes **/*.ts and next.config does not disable type
checking, so on such a checkout this failed the production build rather than
just the script: caught while preparing a test branch for a self-hosted
instance that had not synced yet.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* fix(deps): restore the nested @swc/helpers entry in the lockfile
Declaring @anthropic-ai/sdk with `npm install --package-lock-only` also pruned
node_modules/next-intl/node_modules/@swc/helpers@0.5.23, an optional peer entry
the local npm 11 considers redundant and the image's npm 10.9.8 does not. The
result passed every local check and failed `npm ci` inside the Docker build,
which is the only place the lockfile is actually enforced.
The lockfile is now the previous one plus the single root dependency line,
verified with `npm ci --dry-run`. @anthropic-ai/sdk needed nothing else: it was
already in the tree as a transitive dependency of @anthropic-ai/bedrock-sdk.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
* Update DECISIONS.md
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* Update Docker documentation for AI provider credentials
Clarify the role of credentials in AI provider selection and document extraction requirements.
* Update SELF-HOSTING.md with smoke-ai script details
Clarify usage of smoke-ai script for credential checks and document extraction.
* Improve error handling and logging in smoke-ai script
* fix(ai): complete plain-key self-hosting path
Signed-off-by: Emil <emilmattsson14@gmail.com>
---------
Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
Signed-off-by: Emil <emilmattsson14@gmail.com>
Co-authored-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* feat(accounting): update accounting method validation and messaging for aktiebolag and enskild firma
* Remove AI subsystem and related code
- Deleted AI proposals and requests persistence logic from `lib/ai/proposals/persist.ts`.
- Removed re-validation logic for proposals in `lib/ai/proposals/re-validate.ts`.
- Cleaned up schemas related to AI flows in `lib/api/schemas.ts`.
- Removed AI-related fields from bookkeeping engine in `lib/bookkeeping/engine.ts`.
- Eliminated AI event types from `lib/events/types.ts`.
- Updated tests to reflect the removal of AI-related functionality in `lib/extensions/__tests__/sectors.test.ts`.
- Adjusted initialization logic in `lib/init.ts` to exclude AI proposal handler registration.
- Cleaned up transaction ingestion logic in `lib/transactions/ingest.ts` to remove AI flow checks.
- Updated helper functions in `tests/helpers.ts` to remove AI-related settings.
- Removed AI-related types and interfaces from `types/index.ts`.
- Added migration script to drop AI-related tables and settings from the database.
* fix(migrations): ensure foreign key constraint is dropped before removing AI tables
* feat(invoice-inbox): implement deterministic invoice field extraction and inbox provisioning
- Added `extract-invoice-fields.ts` for extracting fields from PDF invoices using regex and pdfjs-dist, replacing the previous AI classifier.
- Introduced `inbox-provisioning.ts` to manage company inbox addresses and rotation of inboxes using Supabase RPCs.
- Created `resend-inbound.ts` for handling inbound email events and attachments via the Resend API.
- Defined the extension manifest for the invoice inbox, specifying required environment variables and descriptions.
- Migrated database schema to remove AI-related columns and tighten the status enum in `invoice_inbox_items`.
* feat(invoice-inbox): remove AI-specific columns and tighten status enum
* fix(skattekonto): remove manual entry creation reference from transaction input
* fix(schemas): remove accounting method validation for aktiebolag in UpdateSettingsSchema
* feat(attachments): enhance document preview functionality for images and PDFs
* feat(reconciliation): enhance transaction matching logic and clarify reconciliation process
* 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>
Remove AI-dependent extensions (ai-chat, ai-categorization, receipt-ocr,
invoice-inbox) and their infrastructure (lib/ai/*, ai-consent, LangChain/
Anthropic/OpenAI deps) to simplify core and reduce bundle size.
Restructure monolithic settings page into dedicated sub-pages (company,
bookkeeping, invoicing, tax, banking, api, account, team, templates) with
shared layout and sidebar navigation.
Add atomic commit_journal_entry RPC so voucher number increment and status
update happen in a single transaction — prevents burned numbers on constraint
failures. Add continuity check report and voucher gap explanation tracking.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Broad update across dashboard pages, components, extensions, and lib code. Includes ESLint config additions, onboarding flow redesign, settings page refactor, help page content expansion, dead code removal, and test mock fixes. Adds dev docs and public assets.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add currency-utils module for SEK conversion with exchange rates
- Refactor createJournalEntry to use draft+commit flow preventing voucher number gaps (BFL 5 kap. 7§)
- Add foreign currency support to invoice entries with per-line SEK conversion
- Centralize category-to-account mapping into single source of truth
- Refactor invoice inbox to use shared document analyzer with document type classification (receipt, supplier invoice, government letter)
- Update mapping engine, supplier invoice entries, and transaction entries
- Fix report component rendering issues
- Add new validation schemas and tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove influencer-specific features (campaigns, TikTok, gifts, shadow ledger,
contracts, briefings) and consolidate into a clean ERP foundation with core
bookkeeping, invoicing, receipts, tax reporting, and calendar functionality.
Reorganize database migrations into a clean numbered sequence.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
