Jakob WennbergandClaude Fable 5
a3c6566caf
* feat(mcp): ledger-context resource with per-company booking patterns Adds Accounted://ledger/context: derived account usage, counterparty booking patterns with explicit confidence share (0.7 floor), explicit mapping rules kept separate as authoritative, observed VAT profile, and conventions. Backed by a SECURITY INVOKER get_ledger_usage_stats RPC so group-bys run SQL-side, and surfaced as a top-5 digest stanza on gnubok_get_agent_briefing so one call still bootstraps a session. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat(mcp): fold source-quality prereqs into the ledger-context RPC Merchant-name normalization at the aggregation path (the splinter fix): new normalize_counterparty_key() SQL function mirroring normalizeCounterpartyName() so KORTKÖP/SWISH/date-suffixed labels merge into one counterparty key, which also makes the categorization_templates join exact. New supplier_patterns section (per-supplier dominant expense account + VAT treatment from supplier invoices; credit notes and reversed invoices excluded). account_usage excludes storno lines (they re-inflate the account a correction moved away from); the counterparty CTE keeps corrections because the transaction relink self-heals. Pattern confidence is now count-grounded evidence {seen_12m, agree, share, last_booked} instead of a bare ratio, and the digest frames it as historical frequency, never auto-book permission. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(agent-context): use roundOre for the share ratio (antipattern ratchet) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(agent-context): defensive storno filter on counterparty CTE, fail-loud secondary reads Review follow-ups: the counterparty CTE now excludes source_type='storno' defensively (no live code path links a transaction to a storno, but legacy rows may predate reverseEntry's unlink; a linked storno would count the reversed category as precedent). Corrections stay included: they are the live booking after relink. Secondary reads (rules, templates, settings) now throw instead of silently reading as empty data: an agent must never be told 'no rules' when the truth is 'read failed'. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
22 lines
1.1 KiB
TypeScript
22 lines
1.1 KiB
TypeScript
import type { McpResource } from './types'
|
|
import { buildLedgerContext } from '@/lib/agent-context/ledger-context'
|
|
|
|
/**
|
|
* How this company books things, derived from the ledger itself: account
|
|
* usage, counterparty + supplier booking patterns (with count-grounded
|
|
* evidence), user-authored rules, observed VAT profile, and conventions.
|
|
* Sibling of company-current (state now vs patterns over time); zero field
|
|
* overlap.
|
|
*
|
|
* Read-only and per-request; caching is deferred until measured slow
|
|
* (dev_docs/ledger_context_resource.md).
|
|
*/
|
|
export const ledgerContextResource: McpResource = {
|
|
uri: 'Accounted://ledger/context',
|
|
name: 'Ledger Context',
|
|
description:
|
|
'How this company books things: account usage, counterparty and supplier booking patterns with count-grounded evidence, explicit rules, observed VAT profile, conventions. Read before categorizing or creating vouchers; prefer these patterns over guesses. Explicit rules outrank observed patterns.',
|
|
mimeType: 'application/json',
|
|
read: async ({ supabase, companyId }) => buildLedgerContext(supabase, companyId),
|
|
}
|