ktx/packages/cli/test/context/ingest/context-candidates/context-candidate-carryforward.service.test.ts

184 lines
6.3 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { createHash } from 'node:crypto';
import { describe, expect, it, vi } from 'vitest';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { ContextCandidateCarryforwardService } from '../../../../src/context/ingest/context-candidates/context-candidate-carryforward.service.js';
import type { ContextCandidateStorePort } from '../../../../src/context/ingest/context-candidates/store.js';
import type { BudgetExhaustedCandidateForCarryForward, CurrentRunEvidenceChunkForCarryForward } from '../../../../src/context/ingest/context-candidates/types.js';
2026-05-10 23:12:26 +02:00
function candidate(
overrides: Partial<BudgetExhaustedCandidateForCarryForward> = {},
): BudgetExhaustedCandidateForCarryForward {
return {
sourceRunId: 'prior-run-1',
candidateKey: 'budget-revenue-policy',
topic: 'Revenue policy',
assertion: 'Booked revenue excludes refunds.',
rationale: 'The finance handbook states this reusable rule.',
evidenceChunkIds: ['prior-chunk-1'],
evidenceRefs: [
{
chunkId: 'prior-chunk-1',
stableCitationKey: 'notion:page-1:revenue-policy',
syncId: 'sync-prior',
rawPath: 'pages/page-1/page.md',
},
],
suggestedPageKey: 'revenue-policy',
actionHint: 'create',
durabilityScore: 3,
authorityScore: 3,
reuseScore: 3,
noveltyScore: 2,
riskScore: 1,
promotionScore: 10,
lane: 'full',
...overrides,
};
}
function chunk(
overrides: Partial<CurrentRunEvidenceChunkForCarryForward> = {},
): CurrentRunEvidenceChunkForCarryForward {
return {
chunkId: 'current-chunk-1',
stableCitationKey: 'notion:page-1:revenue-policy',
syncId: 'sync-current',
rawPath: 'pages/page-1/page.md',
title: 'Revenue Policy',
path: 'Company / Revenue Policy',
url: 'https://notion.example/page-1',
lastEditedAt: new Date('2026-04-30T12:00:00.000Z'),
citation: {
source: 'notion',
pageId: 'page-1',
syncId: 'sync-current',
rawPath: 'pages/page-1/page.md',
},
content: 'Booked revenue excludes refunds and test accounts.',
...overrides,
};
}
function buildHarness(reExamineBudgetExhaustedOnRerun: boolean) {
const store = {
listPendingCandidatesForDedup: vi.fn(),
updateCandidateEmbedding: vi.fn(),
markCandidatesAsMergedToCluster: vi.fn(),
listBudgetExhaustedCandidatesForCarryForward: vi.fn(),
listCurrentRunEvidenceChunksForCarryForward: vi.fn(),
insertCandidate: vi.fn().mockResolvedValue({ id: 'new-candidate-1' }),
};
const service = new ContextCandidateCarryforwardService({
store: store as unknown as ContextCandidateStorePort,
settings: { reExamineBudgetExhaustedOnRerun },
});
return { service, store };
}
describe('ContextCandidateCarryforwardService', () => {
it('carries a prior budget-exhausted candidate with remapped current evidence', async () => {
const { service, store } = buildHarness(true);
store.listBudgetExhaustedCandidatesForCarryForward.mockResolvedValueOnce([candidate()]);
store.listCurrentRunEvidenceChunksForCarryForward.mockResolvedValueOnce([chunk()]);
const result = await service.carryForward({
runId: 'current-run-1',
connectionId: 'connection-1',
sourceKey: 'notion',
});
expect(result).toMatchObject({
considered: 1,
carriedForward: 1,
skippedNotReemitted: 0,
remappedEvidenceRefs: 1,
staleEvidenceRefs: 0,
});
expect(store.insertCandidate).toHaveBeenCalledWith(
expect.objectContaining({
runId: 'current-run-1',
connectionId: 'connection-1',
sourceKey: 'notion',
candidateKey: 'budget-revenue-policy',
evidenceChunkIds: ['current-chunk-1'],
evidenceRefs: [
expect.objectContaining({
chunkId: 'current-chunk-1',
stableCitationKey: 'notion:page-1:revenue-policy',
syncId: 'sync-current',
snippetHash: createHash('sha256')
.update('Booked revenue excludes refunds and test accounts.')
.digest('hex'),
}),
],
status: 'pending',
rejectionReason: null,
lane: 'full',
embedding: null,
}),
);
expect(result.warnings).toEqual(['Re-examined 1 prior budget-exhausted context candidate.']);
});
it('skips stale prior candidates when config requires current evidence re-emission', async () => {
const { service, store } = buildHarness(false);
store.listBudgetExhaustedCandidatesForCarryForward.mockResolvedValueOnce([candidate()]);
store.listCurrentRunEvidenceChunksForCarryForward.mockResolvedValueOnce([]);
const result = await service.carryForward({
runId: 'current-run-1',
connectionId: 'connection-1',
sourceKey: 'notion',
});
expect(result).toMatchObject({
considered: 1,
carriedForward: 0,
skippedNotReemitted: 1,
remappedEvidenceRefs: 0,
staleEvidenceRefs: 0,
});
expect(store.insertCandidate).not.toHaveBeenCalled();
expect(result.warnings).toEqual([
'Skipped 1 budget-exhausted context candidate because its evidence was not re-emitted in this run.',
]);
});
it('carries stale prior evidence when reExamineBudgetExhaustedOnRerun is enabled', async () => {
const { service, store } = buildHarness(true);
store.listBudgetExhaustedCandidatesForCarryForward.mockResolvedValueOnce([candidate()]);
store.listCurrentRunEvidenceChunksForCarryForward.mockResolvedValueOnce([]);
const result = await service.carryForward({
runId: 'current-run-1',
connectionId: 'connection-1',
sourceKey: 'notion',
});
expect(result).toMatchObject({
considered: 1,
carriedForward: 1,
skippedNotReemitted: 0,
remappedEvidenceRefs: 0,
staleEvidenceRefs: 1,
});
expect(store.insertCandidate).toHaveBeenCalledWith(
expect.objectContaining({
runId: 'current-run-1',
evidenceChunkIds: ['prior-chunk-1'],
evidenceRefs: [
{
chunkId: 'prior-chunk-1',
stableCitationKey: 'notion:page-1:revenue-policy',
syncId: 'sync-prior',
rawPath: 'pages/page-1/page.md',
},
],
}),
);
expect(result.warnings).toEqual([
'Re-examined 1 prior budget-exhausted context candidate.',
'Carried 1 budget-exhausted evidence ref without a current-run chunk remap.',
]);
});
});