Files
accounted/extensions/general/mcp-server
Jakob WennbergandClaude Fable 5 755e0f7e47 feat(dimensions): PR7 producers — auto-tagged documents (invoices, supplier invoices, bulk-book, templates, MCP) (#868)
* feat(dimensions): PR7 producers — invoices/supplier invoices carry dims, generators propagate, BulkBook + templates + MCP bags

Source documents now carry dimension tags and every entry generator
propagates them onto journal lines (dev_docs/dimensions_implementation_plan.md PR7):

- invoices/supplier_invoices.default_dimensions + per-item dimensions
  (migration 20260702200000; jsonb DEFAULT '{}' + object CHECK)
- invoice-entries: issuance/payment/cash/credit propagate — item bags merge
  over the invoice default per revenue line (account+bag aggregation
  identity), payment vouchers re-propagate the linked invoice's bag onto
  every leg incl. FX result lines; ROT/RUT 1513 carries the item bag
- supplier-invoice-entries: registration/payment/cash/privately-paid/credit
  propagate with the same merge rules (expense buckets keyed account+bag)
- bulk_book_transactions RPC persists per-line bags + derives
  cost_center/project mirrors in SQL (migration 20260702201000; malformed
  bags rejected with BULK_BOOK_INVALID_DIMENSIONS); route merges the header
  default into template/manual lines
- counterparty templates: LinePatternEntry.dimensions learned from SIE
  voucher history (kept only when every occurrence agrees), applied to
  business lines on booking; QuickReviewDialog shows a dims badge
- categorize: staged dimensions bag tags business lines only (bank/VAT
  untagged); credit/convert/inbox copy paths carry bags forward
- propose-payment/send-lines stamp the invoice default so the editable
  payment grid books what the preview shows; mark-paid override lines
  accept dimensions
- UI: InvoiceEditor + NewSupplierInvoiceForm header KS/Projekt pair with
  per-row override; BulkBookDialog header default pair (both tabs)
- MCP: default_dimensions/items[].dimensions on create_invoice +
  create_supplier_invoice_from_inbox, dimensions on categorize_transaction,
  per-line bags on bulk_book_transactions — resolve-don't-select via the
  shared registry helpers, resolutions echoed

32 new propagation unit tests + 4 pg-real tests for the RPC migration.

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

* test: use roundOre in new dims rounding assertions (ratchet)

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

* fix: copy dimension bag per payment line, document dimensionsBagKey normalization contract (review)

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

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-02 21:21:01 +02:00
..
2026-05-04 11:12:29 +02:00

Accounted MCP server

JSON-RPC 2.0 server exposing the Accounted bookkeeping engine to MCP clients (Claude Desktop, Claude Code, etc.). Endpoint: /api/extensions/ext/mcp-server/mcp. OAuth and stdio bridge live alongside the API surface — see app/api/mcp-oauth/ and packages/gnubok-mcp/.

Tool authoring contract

Enforced by tests in __tests__/ — these are not style preferences, they're guard rails.

  1. additionalProperties: false on every inputSchema. Guarded by strict-schemas.test.ts. Forces clear rejections on hallucinated fields instead of silent ignores.
  2. Descriptions ≤ 280 chars. Guarded by output-schema.test.ts. No Args: / Returns: / Examples: prose — those belong in JSON Schema. Use agent-native hints ("Use to…", "Call X first", "HIGH risk").
  3. Staged-operation envelope for write tools — outputSchema: STAGED_OPERATION_SCHEMA (server.ts). Fields: staged, risk_level, actor, message, preview, period_status?, next?. The staged: true boolean is the explicit completion signal; agents must not infer completion from prose. Do NOT introduce a parallel { success, shouldContinue, output } envelope.
  4. period_status threading — any tool that ties to a fiscal-period-bound date (categorize, mark paid, create voucher, correct/reverse entry, approve supplier invoice) passes dateForPeriodCheck to stagePendingOperation. Response then includes period_status: { period_id, status: open|locked|closed, lock_date } so widgets and agents disable writes without round-trips.
  5. Scope mapping — every new tool needs an entry in lib/auth/api-keys.ts TOOL_SCOPE_MAP. Missing entries default to deny.
  6. Tests for new write tools — add staging-gate coverage to __tests__/voucher-tools.test.ts (or a sibling) plus executor coverage to lib/pending-operations/__tests__/voucher-executors.test.ts if the tool stages a new operation_type.

Determinism / cache stability

Tool definitions (name, description, inputSchema, outputSchema, annotations) are declared as static object literals at module load — no timestamps, no UUIDs, no Date/Math.random in the definition layer. This makes the tools/list JSON payload byte-stable across requests, which lets agent-side prompt caches stay warm. Do not introduce per-request non-determinism into the definitions block. Anything time-bound or random belongs inside execute().

For internal Anthropic API usage (today only extensions/general/invoice-inbox/lib/extract-invoice-fields.ts): annotate stable prefixes with cache_control: { type: 'ephemeral' } and log usage.cache_read_input_tokens for hit-ratio observability. The 1h TTL from the agent-native API plan (item 10) requires the direct Anthropic API; Accounted's Bedrock path defaults to a shorter TTL.

Payload-size watchdog

payload-size.bench.test.ts enforces a tools/list JSON payload ceiling (currently 36,000 tokens — bumped from 32,000 when top-level Tool.title landed on all tools for Claude Connectors Directory readiness). If the test fires, the right answer is rarely "raise the ceiling" — instead, trim descriptions or leverage gnubok_search_tools (already deployed; tool definitions can defer to it for discovery rather than enumerating in tools/list).

Where things live

  • server.ts — the tools array + JSON-RPC dispatcher
  • tool-result.ts — withNext(), toToolError() response helpers
  • resources/ — read-only Accounted:// URIs (active company, period, recent activity, capabilities, attention items, voucher gaps, chart of accounts, VAT treatments)
  • widgets/ — inline HTML widgets (receipt-matcher, vat-review)
  • prompts/ — slash-command-style prompts
  • skills/ — domain-knowledge skill bodies served via gnubok_load_skill
  • __tests__/ — strictness guards + per-tool coverage