Files

T

01d903d3a3 fix(mcp): link_document_to_voucher marks the inbox item handled; document lists stop misleading agents (#2170 )

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>

2026-09-04 08:57:53 +02:00

__tests__

fix(mcp): link_document_to_voucher marks the inbox item handled; document lists stop misleading agents (#2170 )

2026-09-04 08:57:53 +02:00

prompts

feat(bank): expose bank-reported balance (booked + available) in UI, reconciliation, MCP and v1 API (#2118 )

2026-09-01 16:16:29 +02:00

resources

feat(invoices): offert (quote) document type with own OF-series, decisions, conversion, MCP and v1 (#2163 )

2026-09-02 22:40:25 +02:00

skills

feat(invoices): offert (quote) document type with own OF-series, decisions, conversion, MCP and v1 (#2163 )

2026-09-02 22:40:25 +02:00

widgets

fix(bank): 90-day lookback is the default: long PSD2 requests make some banks kill the session (#1964 )

2026-08-26 22:36:06 +02:00

arg-guard.ts

feat(mcp): worked examples on five high-traffic tools, and in the error that rejects a call (#2100 )

2026-09-01 20:18:19 +02:00

auth-mode.ts

fix(mcp): eager-auth flag on the Grok connector links so Grok starts OAuth (#2167 )

2026-09-02 16:55:23 +02:00

company-routing.ts

chore: repo-wide bloat sweep, remove dead code and fold duplicate helpers (#2150 )

2026-09-02 11:51:16 +02:00

dimensions.ts

style: remove em/en dashes repo-wide, add CLAUDE.md rule against them (#890 )

2026-07-04 15:58:06 +02:00

index.ts

fix(mcp): honest tool text and build-derived server version (#1923 )

2026-08-26 13:35:15 +02:00

manifest.json

Bug/invalid imports (#1146 )

2026-07-24 15:03:50 +02:00

origin-guard.ts

style: remove em/en dashes repo-wide, add CLAUDE.md rule against them (#890 )

2026-07-04 15:58:06 +02:00

public-tools.ts

feat(mcp): lazy authentication so a client can connect before an account exists (#1814 PR 2) (#1892 )

2026-08-25 11:38:29 +02:00

README.md

fix(mcp): promote gnubok_update_customer to the default tools/list catalog (#1986 )

2026-08-27 22:28:14 +02:00

recommended-tools.ts

feat(transactions): steer private marking in locked periods to ignore, with v1 and MCP ignore verbs (#1661 ) (#2031 )

2026-08-31 08:39:04 +01:00

server.ts

fix(mcp): link_document_to_voucher marks the inbox item handled; document lists stop misleading agents (#2170 )

2026-09-04 08:57:53 +02:00

staging-pii-guard.ts

fix(customers): personnummer via MCP lands in personal_number, masked everywhere; MCP payment terms follow settings (#1788 )

2026-08-21 18:32:17 +02:00

supplier-candidates.ts

fix(inbox): match suppliers on VAT number, not just org-nr and name (#1630 )

2026-08-17 14:52:50 +02:00

tasks.ts

feat(mcp): Tasks extension (io.modelcontextprotocol/tasks) (#1283 )

2026-07-29 18:15:06 +02:00

tool-namespace.ts

Bug/invalid imports (#1146 )

2026-07-24 15:03:50 +02:00

tool-result.ts

style: remove em/en dashes repo-wide, add CLAUDE.md rule against them (#890 )

2026-07-04 15:58:06 +02:00

README.md

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. Add ?tool_namespace=accounted for the Accounted tool names. Requests without it retain the legacy Gnubok namespace. OAuth and stdio bridges live alongside the API surface: see app/api/mcp-oauth/, packages/accounted-mcp/, and the compatibility package in packages/gnubok-mcp/.

Tool authoring contract

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

additionalProperties: false on every inputSchema. Guarded by strict-schemas.test.ts. Forces clear rejections on hallucinated fields instead of silent ignores.
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").
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.
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.
Scope mapping: every new tool needs an entry in lib/auth/api-keys.ts TOOL_SCOPE_MAP. Missing entries default to deny.
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 (the SDK is called from lib/ai/provider.ts and lib/ai/services/anthropic-family.ts; features such as extensions/general/invoice-inbox/lib/extract-invoice-fields.ts go through getAiService() in lib/ai rather than the SDK directly): 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. If the test fires, the right answer is rarely "raise the ceiling". Instead, trim descriptions or set specialized wide tools to catalogVisibility: 'search'. Those tools remain discoverable with full schemas through gnubok_search_tools and callable through tools/call on the wire without bloating the default catalog. Claude.ai only calls tools present in tools/list, so a tool that a user or a skill must call directly stays in the default catalog.

Where things live

server.ts: the tools array + JSON-RPC dispatcher
tool-result.ts: withNext(), toToolError() response helpers
resources/: read-only Accounted:// URIs, registered in resources/index.ts: company/current, period/active, recent-activity, capabilities, attention, chart-of-accounts, settings/vat-treatments, booking-templates, ledger/context, reconciliation/summary
widgets/: inline HTML widgets (receipt-matcher, vat-review, pending-operations)
prompts/: slash-command-style prompts
skills/: domain-knowledge skill bodies served via gnubok_load_skill
public-tools.ts: lazy authentication (issue #1814). ANONYMOUS_METHODS (initialize, ping, tools/prompts/resources listing) and the three PUBLIC_TOOLS (gnubok_search_tools, gnubok_list_skills, gnubok_load_skill) answer without credentials, rate-limited per truncated IP; every other tools/call gets a transport-level 401 + WWW-Authenticate from handleMcpRequest in server.ts, which is the challenge clients turn into their Connect prompt
tasks.ts: MCP Tasks extension (io.modelcontextprotocol/tasks): durable handles for long-running tool calls, rows in mcp_tasks (service-role writes only)
origin-guard.ts: Origin-header validation on the Streamable HTTP endpoint (DNS-rebinding defence required by the MCP spec)
staging-pii-guard.ts: refuses a plaintext personnummer in staged pending_operations params/preview, so every staging tool inherits the encrypt-at-staging rule
tool-namespace.ts: ?tool_namespace=accounted handling (accounted_* aliases for the canonical gnubok_* ids)
__tests__/: strictness guards + per-tool coverage