ktx/packages/cli/test/context/ingest/context-evidence/store.test.ts

67 lines
2.6 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
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 type { ContextEvidenceIndexStorePort } from '../../../../src/context/ingest/context-evidence/store.js';
import type { ReplaceContextEvidenceChunk, UpsertContextEvidenceDocument } from '../../../../src/context/ingest/context-evidence/types.js';
2026-05-10 23:12:26 +02:00
const documentInput: UpsertContextEvidenceDocument = {
runId: 'run-1',
connectionId: 'connection-1',
sourceKey: 'notion',
externalId: 'page-1',
externalParentId: null,
databaseId: null,
dataSourceId: null,
title: 'Revenue Recognition',
path: 'Company Handbook / Finance / Revenue Recognition',
url: 'https://notion.example/page-1',
objectType: 'page',
lastEditedAt: new Date('2026-04-12T10:15:00.000Z'),
lastEditedBy: 'Jane Doe',
rawPath: 'pages/page-1/page.md',
syncId: 'sync-1',
contentHash: 'page-hash',
publishState: 'pending',
metadata: { properties: { Status: 'Approved' } },
};
const chunkInput: ReplaceContextEvidenceChunk = {
chunkKey: 'h2:policy:0000',
headingPath: ['Revenue Recognition', 'Policy'],
ordinal: 0,
content: 'Booked revenue excludes refunds and test accounts.',
searchText: 'Revenue Recognition\nPolicy\nBooked revenue excludes refunds and test accounts.',
embedding: [0.1, 0.2, 0.3],
tokenCount: 8,
citation: {
source: 'notion',
pageId: 'page-1',
title: 'Revenue Recognition',
path: 'Company Handbook / Finance / Revenue Recognition',
rawPath: 'pages/page-1/page.md',
},
stableCitationKey: 'notion:page-1:policy:abc123',
syncId: 'sync-1',
contentHash: 'chunk-hash',
};
describe('ContextEvidenceIndexStorePort', () => {
it('describes the persistence operations required by the package indexer', async () => {
const store: ContextEvidenceIndexStorePort = {
upsertDocument: vi.fn().mockResolvedValue({ id: 'doc-1' }),
replaceChunks: vi.fn().mockResolvedValue(undefined),
countPublishedDocumentsByRawPaths: vi.fn().mockResolvedValue(1),
publishSync: vi.fn().mockResolvedValue({ documentsPublished: 1, documentsDeleted: 0 }),
};
await expect(store.upsertDocument(documentInput)).resolves.toEqual({ id: 'doc-1' });
await store.replaceChunks('doc-1', [chunkInput]);
await expect(
store.countPublishedDocumentsByRawPaths('connection-1', 'notion', ['pages/page-1/page.md']),
).resolves.toBe(1);
await expect(
store.publishSync('connection-1', 'notion', 'sync-1', ['pages/page-1/page.md']),
).resolves.toEqual({ documentsPublished: 1, documentsDeleted: 0 });
expect(store.replaceChunks).toHaveBeenCalledWith('doc-1', [chunkInput]);
});
});