Jakob WennbergandClaude Fable 5
001de3c844
* feat(mcp): structured supplier-resolution failure with candidates in create_supplier_invoice_from_inbox When supplier resolution failed (no match on id, org_number, or exact name), the tool threw an opaque error — a dead end for the inbox pipeline on small ad hoc vendors, which are most of the backlog (agent.feedback). The error prose did mention supplier_id_override, but gave the agent no candidate ids and no machine-readable next step. Resolution failure now returns the staged-operation envelope with staged:false: preview carries the extracted supplier identity and near-miss candidates (normalized-name + org-digit matching — catches punctuation/legal-suffix OCR variants like "Polarn o Pyret" vs "Polarn O. Pyret AB", and formatted org numbers '556677-8899' vs '5566778899'); next hints either retry-with-override on the best candidate or a prefilled gnubok_create_supplier. Fuzzy scores never auto-resolve — the agent confirms against the underlag. Part of dev_docs/mcp_optimization_plan.md (P1-4). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(mcp): review fixes — EF org-number forms, candidate-pool truncation flag, override tenancy validation Addresses the three substantive review-bot findings on #873: - orgNumberKey(): canonical 10-digit key. Swedish orgnr is exactly 10 digits; enskild firma org numbers are personnummer that appear in both 10- and 12-digit forms — exact digit-equality missed that legitimate match, and >= 10 accepted non-orgnr garbage lengths. - No silent caps: preview.candidate_pool_truncated + message note when the 500-supplier candidate pool is hit. - The defaults fetch now validates supplier existence in THIS company on every resolution path and rejects a bad supplier_id_override with a clear error — the unresolved next-hint actively promotes overrides, so a bogus id must fail at staging, not opaquely at commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
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.
additionalProperties: falseon everyinputSchema. Guarded bystrict-schemas.test.ts. Forces clear rejections on hallucinated fields instead of silent ignores.- Descriptions ≤ 280 chars. Guarded by
output-schema.test.ts. NoArgs:/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?. Thestaged: trueboolean is the explicit completion signal; agents must not infer completion from prose. Do NOT introduce a parallel{ success, shouldContinue, output }envelope. period_statusthreading — any tool that ties to a fiscal-period-bound date (categorize, mark paid, create voucher, correct/reverse entry, approve supplier invoice) passesdateForPeriodChecktostagePendingOperation. Response then includesperiod_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.tsTOOL_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 tolib/pending-operations/__tests__/voucher-executors.test.tsif the tool stages a newoperation_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 dispatchertool-result.ts—withNext(),toToolError()response helpersresources/— read-onlyAccounted://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 promptsskills/— domain-knowledge skill bodies served viagnubok_load_skill__tests__/— strictness guards + per-tool coverage