ad8566f1ae
* feat(settings): per-company opt-in for data analysis of bookkeeping outcomes (#1346) Adds company_settings.data_analysis_opt_in (default false, no grandfathering) and gates every path that reads bookkeeping outcomes across companies on it: POST /api/agent/categorize/outcome stops writing calibration samples for companies that have not opted in, and the backtest / calibration-fit scripts filter to opted-in company ids. One helper (lib/company/data-analysis.ts) is the single gate for future analysis paths. A toggle on Inställningar > Företag states plainly what is analysed (proposed vs booked account, amount, confidence; no free text, no personal data) in sv and en. The flag is UI-only by design: consent is a human action, so it is absent from the v1 REST / MCP settings pick lists. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015nAd8XJ2RPCmG2eKoLBdna * fix(settings): make data-analysis consent copy true for the backtest path (#1346) Addresses adversarial review findings on PR #2007: - Findings 1-3 (consent narrower than the gated processing): the flag also gates scripts/backtest-categorize.ts, which re-runs transaction descriptions, merchant names and matched underlag through the model. The sv/en toggle help and disclosure now state that explicitly as "evaluation runs" and no longer claim that free text or underlag are excluded. The migration header and COMMENT, the lib/company/data-analysis.ts docstring, the backtest script header and the DECISIONS line say the same. Kept the gate (un-gating would put the script back to reading every company with no consent at all). A test pins that both locales name those inputs and contain no "no free text / no underlag" denial. - Finding 4 (member sees an active switch that RLS rejects): the toggle is now enabled only for owner/admin, matching the company_settings update policy; the disclosure says only administrators can change the choice. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015nAd8XJ2RPCmG2eKoLBdna * fix(scripts): address round-2 review findings (#1346) 1. [minor] Opted-in company filter was an unbounded PostgREST `in` list in the URL (scripts/fit-categorize-calibration.ts, scripts/backtest-categorize.ts). Both scripts now read the opted-in ids through a shared, paginated helper (listDataAnalysisOptedInCompanyIds, fetchAllRows so the pre-fetch no longer caps at 1000) and query per chunk of 100 ids (chunkCompanyIds). The fit script pages each chunk on the id PK; the backtest merges per-chunk results and re-cuts to the N most recent overall. Early exit on zero opt-ins is kept. Pinned with tests in lib/company/__tests__/data-analysis.test.ts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015nAd8XJ2RPCmG2eKoLBdna * fix(scripts): coerce a null transaction description in the backtest (#1346) The typed row from the chunked consent query made description nullable, which TransactionForSelect does not accept; fall back to the original description or an empty string, as the untyped row did implicitly before. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015nAd8XJ2RPCmG2eKoLBdna --------- Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
122 lines
5.1 KiB
TypeScript
122 lines
5.1 KiB
TypeScript
import { describe, it, expect, beforeEach, vi } from 'vitest'
|
|
import type { SupabaseClient } from '@supabase/supabase-js'
|
|
import { createMockSupabase } from '@/tests/helpers'
|
|
import { readFileSync } from 'node:fs'
|
|
import { join } from 'node:path'
|
|
import { createQueuedMockSupabase } from '@/tests/helpers'
|
|
import {
|
|
isDataAnalysisOptedIn,
|
|
listDataAnalysisOptedInCompanyIds,
|
|
chunkCompanyIds,
|
|
OPTED_IN_COMPANY_ID_CHUNK,
|
|
} from '../data-analysis'
|
|
|
|
const { supabase, mockResult } = createMockSupabase()
|
|
const client = supabase as unknown as SupabaseClient
|
|
|
|
describe('isDataAnalysisOptedIn', () => {
|
|
beforeEach(() => {
|
|
vi.clearAllMocks()
|
|
mockResult({ data: null, error: null })
|
|
})
|
|
|
|
it('is true when the company has opted in', async () => {
|
|
mockResult({ data: { data_analysis_opt_in: true } })
|
|
expect(await isDataAnalysisOptedIn(client, 'company-1')).toBe(true)
|
|
})
|
|
|
|
it('is false when the company has not opted in', async () => {
|
|
mockResult({ data: { data_analysis_opt_in: false } })
|
|
expect(await isDataAnalysisOptedIn(client, 'company-1')).toBe(false)
|
|
})
|
|
|
|
it('is false when the settings row is missing', async () => {
|
|
mockResult({ data: null })
|
|
expect(await isDataAnalysisOptedIn(client, 'company-1')).toBe(false)
|
|
})
|
|
|
|
it('fails closed when the query errors', async () => {
|
|
mockResult({ data: { data_analysis_opt_in: true }, error: { message: 'boom' } })
|
|
expect(await isDataAnalysisOptedIn(client, 'company-1')).toBe(false)
|
|
})
|
|
|
|
it('reads company_settings for the given company', async () => {
|
|
mockResult({ data: { data_analysis_opt_in: true } })
|
|
await isDataAnalysisOptedIn(client, 'company-9')
|
|
expect(supabase.from).toHaveBeenCalledWith('company_settings')
|
|
})
|
|
})
|
|
|
|
describe('listDataAnalysisOptedInCompanyIds', () => {
|
|
// Round-2 review of #1346: the read-side scripts pre-fetched opted-in ids
|
|
// without paging (PostgREST caps at 1000) and then passed the whole list to
|
|
// one `.in()` (URL length). The helper pages, the scripts chunk.
|
|
it('pages through more than 1000 opted-in companies', async () => {
|
|
const { supabase, enqueue, findCall, findCalls } = createQueuedMockSupabase()
|
|
const page1 = Array.from({ length: 1000 }, (_, i) => ({ company_id: `c-${i}` }))
|
|
const page2 = [{ company_id: 'c-1000' }, { company_id: 'c-1001' }]
|
|
enqueue({ data: page1 })
|
|
enqueue({ data: page2 })
|
|
const ids = await listDataAnalysisOptedInCompanyIds(supabase as unknown as SupabaseClient)
|
|
expect(ids).toHaveLength(1002)
|
|
expect(ids[0]).toBe('c-0')
|
|
expect(ids[1001]).toBe('c-1001')
|
|
expect(findCall('company_settings', 'eq')).toEqual(['data_analysis_opt_in', true])
|
|
expect(findCalls('company_settings', 'range')).toEqual([[0, 999], [1000, 1999]])
|
|
})
|
|
|
|
it('returns an empty list when nobody has opted in', async () => {
|
|
const { supabase, enqueue } = createQueuedMockSupabase()
|
|
enqueue({ data: [] })
|
|
expect(await listDataAnalysisOptedInCompanyIds(supabase as unknown as SupabaseClient)).toEqual([])
|
|
})
|
|
|
|
it('throws on a query error instead of fitting on a partial corpus', async () => {
|
|
const { supabase, enqueue } = createQueuedMockSupabase()
|
|
enqueue({ data: null, error: { message: 'boom' } })
|
|
await expect(listDataAnalysisOptedInCompanyIds(supabase as unknown as SupabaseClient)).rejects.toThrow('boom')
|
|
})
|
|
})
|
|
|
|
describe('chunkCompanyIds', () => {
|
|
it('keeps every `.in()` list at or under the chunk size', () => {
|
|
const ids = Array.from({ length: 250 }, (_, i) => `id-${i}`)
|
|
const chunks = chunkCompanyIds(ids)
|
|
expect(OPTED_IN_COMPANY_ID_CHUNK).toBeLessThanOrEqual(100)
|
|
expect(chunks.map((c) => c.length)).toEqual([100, 100, 50])
|
|
expect(chunks.flat()).toEqual(ids)
|
|
})
|
|
|
|
it('returns no chunks for an empty list', () => {
|
|
expect(chunkCompanyIds([])).toEqual([])
|
|
})
|
|
})
|
|
|
|
describe('data analysis consent copy', () => {
|
|
// The flag also gates scripts/backtest-categorize.ts, which re-runs
|
|
// transaction descriptions, merchant names and matched underlag through
|
|
// the model. The consent copy must say so in both locales and must not
|
|
// claim that free text or underlag are excluded (review of #1346).
|
|
const locales = ['sv', 'en'] as const
|
|
const messages = {
|
|
sv: readFileSync(join(process.cwd(), 'messages/sv.json'), 'utf8'),
|
|
en: readFileSync(join(process.cwd(), 'messages/en.json'), 'utf8'),
|
|
}
|
|
|
|
it.each(locales)('%s names the evaluation-run inputs the backtest reads', (locale) => {
|
|
const { data_analysis } = JSON.parse(messages[locale]) as {
|
|
data_analysis: { settings_toggle_help: string; settings_disclosure: string }
|
|
}
|
|
const help = data_analysis.settings_toggle_help
|
|
const disclosure = data_analysis.settings_disclosure
|
|
const wordsFor = locale === 'sv'
|
|
? { text: /transaktionstexter/, underlag: /underlag/, denial: /ingen fritext|inga underlag/i }
|
|
: { text: /transaction descriptions/, underlag: /supporting documents/, denial: /no free text|no supporting documents/i }
|
|
expect(help).toMatch(wordsFor.text)
|
|
expect(help).toMatch(wordsFor.underlag)
|
|
expect(help).not.toMatch(wordsFor.denial)
|
|
expect(disclosure).toMatch(wordsFor.text)
|
|
expect(disclosure).not.toMatch(wordsFor.denial)
|
|
})
|
|
})
|