Jakob WennbergandClaude Fable 5
678f2ccffd
* feat(mcp): counterparty-tied category suggestions + no_signal (P2-1)
suggest_categories padded every transaction with a company-wide
category-frequency fallback at <=0.5 confidence — an identical four-way
spread on 20+/24 items that agents correctly reported as pure noise
(agent.feedback). Real signal came from memory atoms and query_journal.
- History is now counterparty-keyed: buildMerchantHistory groups past
categorized transactions by normalized merchant; the engine only
surfaces history for THIS transaction's merchant, with provenance
('Bokförd N gånger tidigare för denna motpart') and occurrence-scaled
confidence (0.56 at 1x, capped 0.85). No global padding — an empty
list is the honest answer.
- The MCP tool returns no_signal_transaction_ids for transactions where
NO source matched, steering agents to investigate (query_journal)
instead of pattern-matching on unrelated rows.
- Both callers (REST suggest-categories route + MCP tool) share the new
helpers, so web UI and agents improve together.
Part of dev_docs/mcp_optimization_plan.md (P2-1).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(skills): dangling-reference validation in skills:check + fix 10 dangling links (P2-2)
skills:generate/check now fail when an atom SKILL.md links a
references/*.md that does not exist on disk — a dangling pointer ships
a 404 to every agent that follows it (the weekly-booking-check
incident, agent.feedback).
The validator immediately caught 10 live dangling links in 4 atoms,
three distinct flavors:
- filename typo: swedish-asset-accounting/references/depreciaton.md
renamed to depreciation.md (the link was right, the file misspelled)
- link mismatch: swedish-e-invoicing linked market-providers-pricing.md;
the file is market-provider-pricing.md (link fixed)
- unauthored plans: single-shareholder-ab-fmb TODOs and reklambyra's
'planerad utbyggnad' section used resolvable references/ paths for
files that were never written — rephrased as plans without paths
Seed migration regenerated (4 atoms bumped, renamed reference child).
Part of dev_docs/mcp_optimization_plan.md (P2-2).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs(events): align agent-feedback review cadence copy (P2-4)
gnubok_feedback replies 'we aggregate signal weekly'; the event-log
handler comment said quarterly. One of them was lying — weekly wins
(the mcp_optimization_plan triage is the living example).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
93 lines
3.2 KiB
TypeScript
93 lines
3.2 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import {
|
|
buildMerchantHistory,
|
|
getSuggestedCategories,
|
|
merchantHistoryFor,
|
|
} from '../category-suggestions'
|
|
import type { Transaction } from '@/types'
|
|
|
|
/**
|
|
* P2-1 (mcp_optimization_plan): suggestions must carry signal tied to THIS
|
|
* transaction. The old company-wide frequency fallback emitted an identical
|
|
* ~0.5 four-way spread on every transaction — noise agents correctly
|
|
* distrusted. History is now counterparty-keyed with provenance; when no
|
|
* source matches, the honest answer is an empty list.
|
|
*/
|
|
|
|
const tx = (overrides: Partial<Transaction> = {}): Transaction =>
|
|
({
|
|
id: 'tx-1',
|
|
company_id: 'company-1',
|
|
date: '2026-06-01',
|
|
description: 'KORTKÖP POLARN O PYRET',
|
|
amount: -500,
|
|
currency: 'SEK',
|
|
merchant_name: 'Polarn O. Pyret',
|
|
...overrides,
|
|
}) as Transaction
|
|
|
|
describe('buildMerchantHistory / merchantHistoryFor', () => {
|
|
const rows = [
|
|
{ merchant_name: 'Polarn O. Pyret', category: 'expense_office' },
|
|
{ merchant_name: 'polarn o. pyret', category: 'expense_office' },
|
|
{ merchant_name: 'Polarn O. Pyret', category: 'expense_consumables' },
|
|
{ merchant_name: 'DNB Bank', category: 'expense_bank_fees' },
|
|
{ merchant_name: null, category: 'expense_other' },
|
|
{ merchant_name: 'Ghost AB', category: null },
|
|
]
|
|
|
|
it('groups case-insensitively by merchant and ignores null merchants/categories', () => {
|
|
const map = buildMerchantHistory(rows)
|
|
expect(merchantHistoryFor(map, 'POLARN O. PYRET')).toEqual({
|
|
expense_office: 2,
|
|
expense_consumables: 1,
|
|
})
|
|
expect(merchantHistoryFor(map, 'DNB Bank')).toEqual({ expense_bank_fees: 1 })
|
|
expect(merchantHistoryFor(map, 'Unknown Vendor')).toEqual({})
|
|
expect(merchantHistoryFor(map, null)).toEqual({})
|
|
})
|
|
})
|
|
|
|
describe('getSuggestedCategories — counterparty history', () => {
|
|
it('returns an empty list (not a fabricated spread) when nothing matches', () => {
|
|
const result = getSuggestedCategories(
|
|
tx({ merchant_name: 'Helt Okänd Motpart', description: 'XYZ 123' }),
|
|
[],
|
|
{},
|
|
)
|
|
expect(result).toEqual([])
|
|
})
|
|
|
|
it('surfaces merchant history with provenance and occurrence-scaled confidence', () => {
|
|
const result = getSuggestedCategories(tx({ description: 'XYZ 123' }), [], {
|
|
expense_office: 3,
|
|
expense_consumables: 1,
|
|
})
|
|
expect(result.length).toBe(2)
|
|
expect(result[0]).toMatchObject({
|
|
category: 'expense_office',
|
|
source: 'history',
|
|
confidence: Math.min(0.85, 0.5 + 3 * 0.06),
|
|
})
|
|
expect(result[0].match_reason).toMatch(/3 gånger tidigare för denna motpart/)
|
|
expect(result[1].category).toBe('expense_consumables')
|
|
expect(result[1].match_reason).toMatch(/1 gång tidigare/)
|
|
})
|
|
|
|
it('caps history confidence at 0.85', () => {
|
|
const result = getSuggestedCategories(tx({ description: 'XYZ 123' }), [], {
|
|
expense_office: 50,
|
|
})
|
|
expect(result[0].confidence).toBe(0.85)
|
|
})
|
|
|
|
it('filters history to the transaction direction', () => {
|
|
const result = getSuggestedCategories(
|
|
tx({ amount: 1000, description: 'XYZ 123' }), // income direction
|
|
[],
|
|
{ expense_office: 5 },
|
|
)
|
|
expect(result).toEqual([])
|
|
})
|
|
})
|