ktx/packages/cli/test/context/ingest/adapters/notion/cluster.test.ts
Andrey Avtomonov 56985b7e09
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

137 lines
5.2 KiB
TypeScript

import { mkdir, mkdtemp, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { describe, expect, test } from 'vitest';
import type { KtxEmbeddingPort } from '../../../../../src/context/core/embedding.js';
import type { WorkUnit } from '../../../../../src/context/ingest/types.js';
import { clusterNotionWorkUnits, MIN_PAGES_TO_CLUSTER } from '../../../../../src/context/ingest/adapters/notion/cluster.js';
function fakeEmbedding(text: string): number[] {
const v = [0, 0, 0, 0];
for (const ch of text) {
v[ch.charCodeAt(0) % 4] += 1;
}
return v;
}
const mockEmbed: KtxEmbeddingPort = {
maxBatchSize: 100,
computeEmbedding: async (t: string) => fakeEmbedding(t),
computeEmbeddingsBulk: async (texts: string[]) => texts.map(fakeEmbedding),
};
async function makeStaged(pages: Array<{ id: string; title: string; body: string }>): Promise<string> {
const dir = await mkdtemp(join(tmpdir(), 'notion-cluster-'));
for (const p of pages) {
const pageDir = join(dir, 'pages', p.id);
await mkdir(pageDir, { recursive: true });
await writeFile(join(pageDir, 'page.md'), p.body);
await writeFile(
join(pageDir, 'metadata.json'),
JSON.stringify({
id: p.id,
title: p.title,
path: p.title,
objectType: 'page',
properties: {},
}),
);
}
return dir;
}
function makeWorkUnits(pages: Array<{ id: string }>): WorkUnit[] {
return pages.map((p) => ({
unitKey: `notion-${p.id}`,
rawFiles: [`pages/${p.id}/page.md`, `pages/${p.id}/metadata.json`],
peerFileIndex: [],
dependencyPaths: ['manifest.json'],
}));
}
describe('clusterNotionWorkUnits', () => {
test('returns input unchanged when below threshold', async () => {
const pages = Array.from({ length: 3 }, (_, i) => ({
id: `p${i}`,
title: `Page ${i}`,
body: 'short body',
}));
const stagedDir = await makeStaged(pages);
const wus = makeWorkUnits(pages);
const out = await clusterNotionWorkUnits({ workUnits: wus, stagedDir, embedding: mockEmbed });
expect(out).toHaveLength(3);
expect(out[0].unitKey).toBe('notion-p0');
});
test('groups pages into k=ceil(N/8) clusters when above threshold', async () => {
const n = MIN_PAGES_TO_CLUSTER + 4;
const pages = Array.from({ length: n }, (_, i) => ({
id: `p${i}`,
title: `Topic ${i % 2 === 0 ? 'alpha' : 'beta'} ${i}`,
body: `Body for page ${i}`.repeat(20),
}));
const stagedDir = await makeStaged(pages);
const wus = makeWorkUnits(pages);
const out = await clusterNotionWorkUnits({ workUnits: wus, stagedDir, embedding: mockEmbed });
expect(out.length).toBeLessThanOrEqual(wus.length);
expect(out.length).toBe(Math.ceil(wus.length / 8));
for (const wu of out) {
expect(wu.unitKey).toMatch(/^notion-cluster-\d+$/);
expect(wu.rawFiles.length).toBeGreaterThan(0);
expect(wu.notes).toMatch(/Synthesize/);
expect(wu.notes).toContain('emit_unmapped_fallback');
expect(wu.notes).toContain('Do not create SL sources under the Notion connection');
}
});
test('merges pages into one synthesis unit at the clustering threshold', async () => {
const pages = Array.from({ length: MIN_PAGES_TO_CLUSTER }, (_, i) => ({
id: `p${i}`,
title: `Customer source reference ${i}`,
body: `Customer source reference maps to orbit_analytics.customer ${i}`.repeat(10),
}));
const stagedDir = await makeStaged(pages);
const wus = makeWorkUnits(pages);
const out = await clusterNotionWorkUnits({ workUnits: wus, stagedDir, embedding: mockEmbed });
expect(out).toHaveLength(1);
expect(out[0].unitKey).toBe('notion-cluster-1');
expect(new Set(out[0].rawFiles)).toEqual(new Set(wus.flatMap((wu) => wu.rawFiles)));
expect(out[0].notes).toContain('emit_unmapped_fallback');
expect(out[0].notes).toContain('Do not create SL sources under the Notion connection');
});
test('preserves coverage: every input rawFile appears in some cluster', async () => {
const pages = Array.from({ length: 12 }, (_, i) => ({
id: `p${i}`,
title: `Page ${i}`,
body: 'body content',
}));
const stagedDir = await makeStaged(pages);
const wus = makeWorkUnits(pages);
const inputFiles = new Set(wus.flatMap((wu) => wu.rawFiles));
const out = await clusterNotionWorkUnits({ workUnits: wus, stagedDir, embedding: mockEmbed });
const outFiles = new Set(out.flatMap((wu) => wu.rawFiles));
expect(outFiles).toEqual(inputFiles);
});
test('falls back to input when embedding fails', async () => {
const pages = Array.from({ length: 10 }, (_, i) => ({
id: `p${i}`,
title: `Page ${i}`,
body: 'b',
}));
const stagedDir = await makeStaged(pages);
const wus = makeWorkUnits(pages);
const failingEmbed: KtxEmbeddingPort = {
maxBatchSize: 100,
computeEmbedding: async () => {
throw new Error('embedding down');
},
computeEmbeddingsBulk: async () => {
throw new Error('embedding down');
},
};
const out = await clusterNotionWorkUnits({ workUnits: wus, stagedDir, embedding: failingEmbed });
expect(out).toEqual(wus);
});
});