c0ecf2fa3bebd46bdfd0169efd73b89653d1dfed
5
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
9fe37b85b5 |
feat(agents): per-key approval authority, the amount an agent may post unattended (#2079)
* feat(agents): per-key approval authority, the amount an agent may post unattended An API key gets an optional ceiling in SEK. Above it the agent may still stage the work, it just may not finish it alone: a human approves the same verifikat in the app. Default is NULL, so every existing key keeps its behaviour and turning this on is entirely opt-in. Enforced at the two places an API key reaches the ledger, and at both the refusal happens BEFORE the point of no return: - MCP: in commitPendingOperation, before the atomic claim, so the operation stays 'pending'. Behind the claim it would be caught by the generic handler, marked terminal 'rejected', and the staged verifikat would be gone. - REST: in journal-entries.commit, before commitEntry, so the draft stays a draft and the voucher sequence never advances (BFL 5 kap. 7 §). The dry run refuses too, rather than promising a voucher number the key cannot deliver. Not enforced inside commit_journal_entry: a RAISE there is swallowed by engine.ts into a retryable 500, and it would cost a DROP+CREATE on the function that issues every voucher number. Operations whose amount is only known during dispatch (batch allocation, bulk booking, the settlement link paths) fail OPEN behind an explicit allowlist. Pricing them ahead of dispatch would be a guess, and a wrong guess silently breaks batch allocation the day someone sets a limit. The allowlist is derived from what production actually stores: create_voucher carries total_debit on 1389 of 1389 rows, categorize_transaction carries amount on 2002 of 2003, create_supplier_invoice_from_inbox carries total on 208 of 228. This is a blast-radius cap, not a security boundary. A per-entry ceiling is defeated by splitting one entry into several, and an LLM will find that, so UNATTENDED_COMMIT_LIMIT_EXCEEDED forbids splitting first: one affärshändelse is one verifikat (BFL 5 kap. 6 §). A cumulative rolling-window limit is the primitive that actually bounds exposure and is left to a separate change. The guard is written NULL-first everywhere. An absent, unparseable or non-positive ceiling always means unlimited, never "block everything". Agents read their own ceiling from gnubok_get_agent_briefing instead of discovering it by burning a staged verifikat on a 403. Changing a ceiling is auditable: it now renders in behandlingshistorik (BFL 5 kap. 11 §). The audit trigger already fired on the column, but the report dropped the event because the field was not in its diff map. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(skill): regenerate accounted-api skill for the new commit pitfall apiskill:check is a ratchet: the generated reference must match the endpoint registry. Never hand-edited. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(agents): pin the DB default itself, and declare the briefing field required Two review findings, both real: - the default test stored an explicit NULL, so it stayed green even if the column default changed to a positive ceiling: the one change that would silently start blocking every existing key. It now omits the column. - gnubok_get_agent_briefing documents unattended_commit_limit as always present and emits it unconditionally, so it belongs in the output schema's required list. Declined the NOT VALID constraint suggestion, with the reason recorded in the migration: api_keys is 388 rows / 768 kB in production. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(agents): name the TOCTOU window in the REST ceiling check A security scan flagged that the line sum is read before commitEntry, so a concurrent write to the draft's lines can post over the ceiling. Real, and accepted: closing it means enforcing inside commit_journal_entry, where a RAISE becomes a retryable 500 and destroys the staged operation on the MCP path. Recorded in the code rather than left implicit, so nobody later mistakes this for a hard control. A per-entry ceiling is already defeated by splitting, which needs no race; the cumulative rolling-window limit is the primitive that bounds exposure. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(agents): price the settlement and batch paths that were bypassing the ceiling A security scan flagged that known money-posting operations fail open, and it was right. The first cut priced only create_voucher, categorize_transaction and create_supplier_invoice_from_inbox, on the belief that the batch and settlement paths computed their totals only inside SQL at dispatch. Production says otherwise: the staged preview already carries the amount, because it is the number a human is shown when approving the operation. Over the last 120 days each of these is present and numeric on 100% of that type's staged rows: link_transaction_journal_entry transaction_amount 1369 rows bulk_book_transactions tx_sum 273 rows link_supplier_invoice_voucher payment_amount 55 rows match_batch_allocate total_allocated 24 rows mark_invoice_paid total 3 rows So a key with a ceiling could post any amount through the four largest settlement paths. Now priced, and the ceiling applies. Only reconciliation_match stays unpriced: it carries pair_count, which is a COUNT. Pricing off that would compare pairs against kronor, which is worse than not enforcing. link_document_to_voucher and attach_document_to_transaction move no money at all; the transaction_amount they carry is context, not a posting. Genuinely unpriceable types still fail OPEN. This control can only ever narrow what a key does, and a wrong guess at an amount blocks a legitimate commit, so guessing high would leave an agent unable to work. Adds a test that walks the whole allowlist, so a typo'd field name cannot silently make a type unpriceable again: that is exactly the hole this closes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(mcp): drop the ceiling from the agent briefing, the payload budget has no room The tools/list context-budget bench sits at 65 000 tokens and main now leaves roughly 20 tokens of headroom. An always-present field on the briefing's output schema costs about 85, so this addition alone pushed the bench red. The bench's own note is explicit that the answer is to demote a tool rather than raise the ceiling, so raising it here would be the wrong trade for a nice-to-have. Nothing is lost that matters: the operation is never destroyed when it is refused, so discovering the ceiling from UNATTENDED_COMMIT_LIMIT_EXCEEDED costs one round trip and no work. That error already carries both attempted and limit, and GET /api/settings/api-keys returns the value. Re-exposing it on the briefing is worth doing once there is budget to spend. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(api): spell affärshändelse correctly in the commit pitfall Fixed in the route's registerEndpoint pitfalls, which is the source; the skill reference is regenerated from it and never hand-edited. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
|
3447da027a |
feat(api): agent-substrate quick wins: worked examples in the spec, honest Retry-After, and a payload guard that covers the namespace new installs get (#1974)
* feat(api): surface the registry's worked examples in the OpenAPI spec and generated skill EndpointDefinition.example is required and every one of the 125 v1 endpoints populates example.response, but generateOpenApiSpec() never emitted it. The examples reached only the docs markdown builder, so /api/v1/openapi.json carried none and the generated skills/accounted-api had zero json blocks in all 12 reference files: every agent reading the spec or installing the skill got schemas with no concrete body. Emit example on the application/json media types (request body and 200 response) and teach the portable renderOperationMd to print it as a fenced json block. 178 worked examples now reach the skill. SKILL.md is unchanged: the examples land in the on-demand reference files, not the entry file. Attached to JSON media types only, so a multipart body and a binary application/pdf response do not advertise an example they cannot send. Adds the one missing example.request (currency-revaluation) so the new exhaustive coverage assertions hold. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(api): emit Retry-After on a v1 429 so the documented contract is real The published accounted-api skill has told agents to honor Retry-After on a 429 since it shipped, but no /api/v1 route ever sent one: the wrapper's auth failure path early-returns through v1ErrorResponseFromCode, whose finalize() set only X-Request-Id and Gnubok-Version. Unattended clients had nothing to pace against and had to back off blindly. 60 seconds is an exact upper bound rather than a guess: the rate limiter is a fixed one-minute tumbling window per key row and the limited branch does not slide it. The value moves into an exported constant next to that limiter, so the MCP server's hardcoded '60' now reads from the same place. Also corrects the withApiV1 doc comment, which claimed step 8 stamps X-RateLimit-Limit. It never did. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(mcp): guard the tools/list payload for the namespace new installs get The payload ratchet only ever serialized the gnubok_* projection. The accounted_* projection is inherently larger (every tool reference gains 3 chars, ~209 tokens across the default catalog) and CLAUDE.md points new MCP installs at exactly that namespace, so the payload a new user's client receives was never measured. It had already drifted ~90 tokens past the 63.4K ceiling while the guarded number sat comfortably under it. Measure both and assert on the larger. The ceiling moves to 63.6K to cover the real worst case; this buys no new catalog surface. A second test pins the direction of the delta so Math.max cannot silently stop describing reality. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
MattssonandClaude Fable 5
|
05380ddf54 |
feat(bookkeeping): correction-chain depth guard + Bedrock stream retry (#1581)
* feat(bookkeeping): bypassable chain-depth guard on corrections and stornos Correcting or reversing an entry that already sits 3+ links deep in a rattelse chain (correction_of_id/reverses_id walked in the DB, never description matching) now throws CORRECTION_CHAIN_TOO_DEEP, steering the caller to book ONE correction expressing the chain's net effect. Agents looped storno+rattelse 10 deep on a live company (63/193 vouchers noise). The guard is advisory, never a dead end: allow_deep_chain bypasses it on every surface (correctEntry/reverseEntry option, REST body, MCP tool arg staged through pending_operations, and confirm dialogs with Ratta anda / Aterfor anda in the web UI). MCP staging pre-flight fires the guard at stage time so the agent reconsiders in the same turn, and the executor re-checks at commit. tools/list payload ceiling bumped 59K -> 59.5K for the two bypass properties (trimmed to one sentence first). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(agent): retry the Bedrock stream once on transient failures A transient stream death (429/5xx, transport cut, or the two known stream-corruption signatures: 'Unexpected event order' and 'request ended without sending any chunks') killed the whole chat turn, stranding the user mid-answer. The turn now retries once per turn after a short backoff: safe because nothing is persisted until finalMessage() succeeds. A new stream_restart event carries the pre-attempt text snapshot so the chat client resets the partial bubble, drops uncompleted tool chips, and shows 'Forsoker igen...' until the retried stream produces text. Non-transient errors (403, 400) keep the existing immediate-error path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(api): regenerate accounted-api skill and wire allow_deep_chain through v1 apiskill:check failed: CorrectJournalEntrySchema gained allow_deep_chain, making references/journal-entries.md stale. Regenerated (hand-applied: the generator output is deterministic from the registry). While wiring: the v1 correct route validated allow_deep_chain but dropped it, and the v1 reverse route's strict body schema would have rejected it outright, leaving API clients no bypass when the chain-depth guard fires. Both now forward the flag to the engine and document CORRECTION_CHAIN_TOO_DEEP as a pitfall. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: re-trigger CI after Vercel infra hang The preview for e527e4044 compiled in 91s then hung 40 minutes in the TypeScript phase and was killed with no error output; a CLI redeploy of the identical code went Ready in 5m. Empty commit to refresh the git- triggered deployment status. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(bookkeeping): address CodeRabbit review on the chain-depth guard - correction-chain: report rootVoucher only when the walk reached a genuine parentless root; a broken link, cycle, or hop-cap now yields null instead of presenting an intermediate voucher as the chain root. - recordate: propagate allow_deep_chain end-to-end (recordateEntry option, route schema, and a Flytta anda bypass confirm in the dialog); a date move is another storno+rattelse layer and carried the guard with no override path. - v1 correct/reverse: run the chain-depth guard before the dry-run return so a dry run gives the same verdict as the real execution. - dashboard reverse route: 400 on malformed JSON or a non-boolean allow_deep_chain instead of silently reversing without the override; empty body stays the supported no-body case. Tests added. - AgentChat stream_restart: discard the dead attempt's reasoning and re-arm the post-tool paragraph break so a retried turn doesn't render thinking twice or glue its continuation onto restored text. - v1 reverse route doc comment updated for allow_deep_chain. Not changed: the journal-list reverse flow (flagged as a dead end) can never receive CORRECTION_CHAIN_TOO_DEEP: the list renders Aterfor only for entries that are neither storno nor correction, and such entries have no backward chain links, so their depth is always 0. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(bookkeeping): recordate route test expects the new options arg recordateEntry now takes { allowDeepChain } as a sixth argument; the route test's called-with assertion predates it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
MattssonandClaude Fable 5
|
c35b2547fb |
feat(webshop-orders): Orders page with per-store, per-payment-method booking (#1525)
* feat(webshop-orders): schema, types and error codes for the orders surface webshop_orders (order/refund rows, financial-freeze trigger, member select/update RLS, no DELETE) + webshop_store_settings (per-store payment method -> account map), source_type 'webshop_order', multi-store index drop, customer_country, and a one-time woo cursor reset so the switch-over backfills and cross-marks existing feed rows. Tables classified in the full-archive export; pg-real coverage for RLS, freeze and CHECK. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(webshop-orders): core service (ingest, booking lines) upsertWebshopOrders: two-phase order/refund upsert with FX enrichment, legacy-feed cross-marking, frozen-row protection and field-wise jsonb comparisons (Postgres does not preserve object key order). Booking-line builder: per-rate VAT split with SIGNED buckets (discounts book as revenue reductions), refund mirroring, 3740 residual, per-store account prefill, and advisory export/EU + OSS warnings. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(webshop-orders): API routes for list, booking, invoicing and mapping Booking is draft -> atomic claim -> commit (conditional link-back closes the concurrent double-book race; a lost claim cancels the voucher-free draft). Legacy-feed guard honors transactions.is_ignored on both the book and create-invoice paths. Invoice conversion reuses buildInvoiceWriteData for an unnumbered draft with dominant-rate fallback and drift-safe unit prices. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(webshop-orders): Orders page, booking/invoice dialogs and gated nav /orders lists per-store orders with status tabs (server-side filters), exception chips and one action per row. Booking dialog prefills from the per-store payment-method mapping with an opt-in remember; invoice dialog converts to a draft kundfaktura. The Order nav item renders only for companies with an active WooCommerce connection or existing order rows (Shopify deliberately excluded until its sync writes webshop_orders). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(woocommerce): switch the order sync to webshop_orders, multi-store The sync maps rich wc/v3 payloads (billing, line/shipping/fee taxes, refund allocations with parent-prorated VAT fallback) and upserts order rows instead of transactions-inbox rows; already-imported feed rows stay bookable and get cross-marked. Multi-store: several active connections per company, per-store panel cards with the account-mapping editor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(webshop-orders): decision log entries and ratchet baseline Baseline moves DOWN only: naive-ore-round 638 -> 637 via roundOre adoption; hand-rolled invariants stay at 115 (ACCOUNT_NUMBER_RE imported, not inlined). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(webshop-orders): resolve PR #1525 review findings and CI failures Review batch (Superagent, CodeRabbit, Swedish compliance review): - Mutual-exclusion claims: booking guards invoice_id, invoice link-back guards journal_entry_id AND treats zero matched rows as the conflict it is (409 + rollback), closing both TOCTOU races. - Freeze v2 migration (20260812124858): the link columns themselves are protected: invoice links immutable, journal links clearable only while the entry is still a draft (the booking rollback path). - Scraped orgnr no longer auto-written to customers.org_number; rate fallback applies only on single-VAT-bucket orders; refunds get their own WEBSHOP_ORDER_REFUND_NOT_CONVERTIBLE code; VAT advisories outrank the invoice-mode hint in the booking dialog. - Ingest compares every synced field (billing corrections no longer drop as unchanged); sync guards absent refunds arrays; /sync aggregates per-store results; panel disables all cards while a request runs; orders page separates load failure from empty; account field explains itself. CI: regenerated skills/accounted-api; pg tests restructured for transaction-abort/rollback semantics + freeze-link coverage; unresolvable- expression ceiling 375 -> 378 with documented reason (partial-update payloads in ingest, shapes covered by unit tests). Declined: CodeRabbit docstring-coverage advisory (house style: comments only where the code cannot say it). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
|
11b82cbb91 |
feat(api): installable accounted-api agent skill + openapi-to-skill generator (#1516)
* feat(api): installable accounted-api agent skill + openapi-to-skill generator Three layers, per the July/August 2026 agent-skills ecosystem (skills.sh / npx skills add, as used by Stripe/Cloudflare/Supabase for their APIs): - skills/openapi-to-skill/: generic, installable skill that turns any OpenAPI spec into a consumer-side integration skill, with a portable stdlib-only inventory/condenser tool and an output template + quality checklist encoding the distill-not-restate methodology. - skills/accounted-api/: the installable skill for our own API, rendered deterministically by scripts/api-skill/generate.ts from the v1 endpoint registry + hand-authored overlays (auth, conventions, domain gotchas). CI gate: npm run apiskill:check (core-build.yml). - lib/api/v1/registry.ts: generateOpenApiSpec now emits requestBody (incl. multipart binary parts) and path parameters, and the Zod converter learned .default()/z.record()/.pipe()/.transform(), so the public spec carries request contracts instead of prose-only. Docs: /docs/api landing + /llms.txt now point agents at the skill install; corrected the stale test-key description in the landing (test keys read real data and force dry-run writes; they are not sandbox-company bound). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): escape backslashes in markdown table cells (CodeQL js/incomplete-sanitization) 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> |