ktx/packages/cli/test/context/ingest/local-metabase-ingest.test.ts

268 lines
10 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
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 { AgentRunnerPort, RunLoopParams } from '../../../src/context/llm/runtime-port.js';
2026-05-10 23:12:26 +02:00
import { afterEach, beforeEach, 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 { initKtxProject, type KtxLocalProject } from '../../../src/context/project/project.js';
import { LocalMetabaseDiscoveryCache } from '../../../src/context/ingest/adapters/metabase/local-source-state-store.js';
import { getLocalIngestStatus, runLocalMetabaseIngest } from '../../../src/context/ingest/local-ingest.js';
import type { ChunkResult, FetchContext, SourceAdapter } from '../../../src/context/ingest/types.js';
2026-05-10 23:12:26 +02:00
feat: add claude-code llm backend with runtime port (#115) * docs: revise claude-code ingest backend spec * docs: keep claude-code spec focused on ingest * docs: expand claude-code spec to full llm parity * Refine claude-code backend spec after adversarial review iteration 1 * Refine claude-code backend spec after adversarial review iteration 2 * Refine claude-code backend spec after adversarial review iteration 3 * feat: recognize claude-code llm backend * feat: add ktx llm runtime port * feat: add claude-code llm runtime * feat: route non-agent llm calls through runtime * feat: run ingest agents through llm runtime * feat: support claude-code setup and status * test: verify claude-code backend runtime * docs: add claude-code backend v1 runtime plan * fix: close claude-code runtime isolation checks * fix: warn on claude-code prompt caching during setup * chore: verify claude-code v1 closure * docs: add claude-code backend v1 isolation closure plan * fix: update claude-code ingest setup guidance * docs: add claude-code backend v1 ingest guidance closure plan * docs: align claude-code isolation spec with sdk metadata * test: cover claude-code host discovery metadata * fix: tolerate claude-code host discovery metadata * docs: clarify claude-code host discovery metadata * docs: add claude-code auth-probe isolation fix plan * chore: prepare kaelio ktx rc1 release * chore: add semantic release workflow * fix: unblock ci checks * chore(release): 0.1.0-rc.1 * feat: add Claude Code model selection to setup * fix: keep git maintenance attached in local repos
2026-05-16 12:06:34 +02:00
class TestAgentRunner implements AgentRunnerPort {
runLoop = vi.fn(async (params: RunLoopParams) => {
2026-05-10 23:12:26 +02:00
if (params.userPrompt.includes('metabase-db-2')) {
return { stopReason: 'error' as const, error: new Error('database 2 failed') };
}
return { stopReason: 'natural' as const };
});
}
class FakeMetabaseSourceAdapter implements SourceAdapter {
readonly source = 'metabase';
readonly skillNames: string[] = [];
detect(): Promise<boolean> {
return Promise.resolve(true);
}
async fetch(pullConfig: unknown, stagedDir: string, ctx: FetchContext): Promise<void> {
const config = pullConfig as { metabaseConnectionId: string; metabaseDatabaseId: number };
await mkdir(join(stagedDir, 'cards'), { recursive: true });
await mkdir(join(stagedDir, 'databases'), { recursive: true });
await writeFile(
join(stagedDir, 'cards', `${config.metabaseDatabaseId}.json`),
JSON.stringify({ connectionId: ctx.connectionId, databaseId: config.metabaseDatabaseId }),
'utf-8',
);
await writeFile(
join(stagedDir, 'databases', `${config.metabaseDatabaseId}.json`),
JSON.stringify({ metabaseConnectionId: config.metabaseConnectionId }),
'utf-8',
);
}
async chunk(stagedDir: string): Promise<ChunkResult> {
const databaseId = Number(stagedDir.match(/metabase-child-(\d+)/)?.[1] ?? 1);
return {
workUnits: [
{
unitKey: `metabase-db-${databaseId}`,
rawFiles: [`cards/${databaseId}.json`],
peerFileIndex: [],
dependencyPaths: [`databases/${databaseId}.json`],
},
],
};
}
}
class ThrowingFetchMetabaseSourceAdapter extends FakeMetabaseSourceAdapter {
override async fetch(pullConfig: unknown, stagedDir: string, ctx: FetchContext): Promise<void> {
const config = pullConfig as { metabaseConnectionId: string; metabaseDatabaseId: number };
if (config.metabaseDatabaseId === 2) {
throw new Error('Metabase fetch failed for database 2');
}
await super.fetch(pullConfig, stagedDir, ctx);
}
}
describe('runLocalMetabaseIngest', () => {
let tempDir: string;
2026-05-10 23:51:24 +02:00
let project: KtxLocalProject;
2026-05-10 23:12:26 +02:00
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-metabase-fanout-'));
project = await initKtxProject({ projectDir: tempDir, force: true });
2026-05-10 23:12:26 +02:00
project.config.connections = {
'prod-metabase': {
driver: 'metabase',
api_url: 'https://metabase.example.com',
api_key: 'literal-test-key', // pragma: allowlist secret
},
warehouse_a: { driver: 'postgres', url: 'postgres://localhost/a' },
warehouse_b: { driver: 'postgres', url: 'postgres://localhost/b' },
};
project.config.ingest.adapters = ['metabase'];
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
async function seedMetabaseState(): Promise<void> {
project.config.connections['prod-metabase'].mappings = {
databaseMappings: { '1': 'warehouse_a', '2': 'warehouse_b' },
syncEnabled: { '1': true, '2': true },
2026-05-10 23:12:26 +02:00
syncMode: 'ALL',
2026-05-10 23:51:24 +02:00
defaultTagNames: ['ktx'],
selections: { collections: [], items: [] },
};
const discoveryCache = new LocalMetabaseDiscoveryCache({ dbPath: join(tempDir, '.ktx', 'db.sqlite') });
await discoveryCache.refreshDiscoveredDatabases({
connectionId: 'prod-metabase',
discovered: [
{ id: 1, name: 'Warehouse A', engine: 'postgres', host: 'localhost', dbName: 'a' },
{ id: 2, name: 'Warehouse B', engine: 'postgres', host: 'localhost', dbName: 'b' },
2026-05-10 23:12:26 +02:00
],
});
}
it('runs one child job per sync-enabled Metabase mapping', async () => {
await seedMetabaseState();
const agentRunner = new TestAgentRunner();
const ids = ['metabase-child-1', 'metabase-child-3'];
const result = await runLocalMetabaseIngest({
project,
adapters: [new FakeMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner,
jobIdFactory: () => ids.shift() ?? 'metabase-child-extra',
});
expect(result.metabaseConnectionId).toBe('prod-metabase');
expect(result.status).toBe('all_succeeded');
expect(result.children.map((child) => child.targetConnectionId)).toEqual(['warehouse_a', 'warehouse_b']);
expect(result.children.map((child) => child.metabaseDatabaseId)).toEqual([1, 2]);
expect(new Set(result.children.map((child) => child.jobId)).size).toBe(2);
await expect(getLocalIngestStatus(project, result.children[0].jobId)).resolves.toMatchObject({
jobId: result.children[0].jobId,
connectionId: 'warehouse_a',
sourceKey: 'metabase',
});
});
it('throws before runner work when there are no sync-enabled mapped rows', async () => {
project.config.connections['prod-metabase'].mappings = {
databaseMappings: { '1': null },
syncEnabled: { '1': true },
};
2026-05-10 23:12:26 +02:00
await expect(
runLocalMetabaseIngest({
project,
adapters: [new FakeMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner: new TestAgentRunner(),
}),
).rejects.toThrow('no sync-enabled mappings with a target connection');
});
it('seeds yaml-only Metabase mappings before the unhydrated fanout preflight', async () => {
project.config.connections['prod-metabase'].mappings = {
databaseMappings: { '1': 'warehouse_a' },
syncEnabled: { '1': true },
};
const result = await runLocalMetabaseIngest({
project,
adapters: [new FakeMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner: new TestAgentRunner(),
jobIdFactory: () => 'metabase-child-1',
2026-05-10 23:12:26 +02:00
});
expect(result.status).toBe('all_succeeded');
expect(result.children).toMatchObject([
{
2026-05-10 23:12:26 +02:00
metabaseConnectionId: 'prod-metabase',
metabaseDatabaseId: 1,
targetConnectionId: 'warehouse_a',
2026-05-10 23:12:26 +02:00
},
]);
2026-05-10 23:12:26 +02:00
});
it('rejects source-dir uploads through the Metabase fanout runner', async () => {
2026-05-10 23:12:26 +02:00
await expect(
runLocalMetabaseIngest({
project,
adapters: [new FakeMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner: new TestAgentRunner(),
sourceDir: tempDir,
} as Parameters<typeof runLocalMetabaseIngest>[0] & { sourceDir: string }),
).rejects.toThrow('source-dir uploads are not supported for the Metabase fanout adapter');
2026-05-10 23:12:26 +02:00
});
it('reports partial failure when a child job fails', async () => {
await seedMetabaseState();
const agentRunner = new TestAgentRunner();
const ids = ['metabase-child-1', 'metabase-child-2'];
const result = await runLocalMetabaseIngest({
project,
adapters: [new FakeMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner,
jobIdFactory: () => ids.shift() ?? 'metabase-child-extra',
});
expect(result.status).toBe('partial_failure');
expect(result.totals).toEqual({ workUnits: 2, failedWorkUnits: 1 });
expect(result.children[1]?.report.body.failedWorkUnits).toEqual(['metabase-db-2']);
});
it('captures fetch-time child failures and continues later mappings', async () => {
await seedMetabaseState();
project.config.connections.warehouse_c = { driver: 'postgres', url: 'postgres://localhost/c' };
project.config.connections['prod-metabase'].mappings = {
databaseMappings: { '1': 'warehouse_a', '2': 'warehouse_b', '3': 'warehouse_c' },
syncEnabled: { '1': true, '2': true, '3': true },
syncMode: 'ALL',
defaultTagNames: ['ktx'],
selections: { collections: [], items: [] },
};
const discoveryCache = new LocalMetabaseDiscoveryCache({ dbPath: join(tempDir, '.ktx', 'db.sqlite') });
await discoveryCache.refreshDiscoveredDatabases({
2026-05-10 23:12:26 +02:00
connectionId: 'prod-metabase',
discovered: [
{ id: 1, name: 'Warehouse A', engine: 'postgres', host: 'localhost', dbName: 'a' },
{ id: 2, name: 'Warehouse B', engine: 'postgres', host: 'localhost', dbName: 'b' },
{ id: 3, name: 'Warehouse C', engine: 'postgres', host: 'localhost', dbName: 'c' },
],
});
const ids = ['metabase-child-1', 'metabase-child-2', 'metabase-child-3'];
const result = await runLocalMetabaseIngest({
project,
adapters: [new ThrowingFetchMetabaseSourceAdapter()],
metabaseConnectionId: 'prod-metabase',
agentRunner: new TestAgentRunner(),
jobIdFactory: () => ids.shift() ?? 'metabase-child-extra',
});
expect(result.status).toBe('partial_failure');
expect(result.children.map((child) => child.jobId)).toEqual([
'metabase-child-1',
'metabase-child-2',
'metabase-child-3',
]);
expect(result.children.map((child) => child.metabaseDatabaseId)).toEqual([1, 2, 3]);
expect(result.children.map((child) => child.targetConnectionId)).toEqual(['warehouse_a', 'warehouse_b', 'warehouse_c']);
expect(result.totals).toEqual({ workUnits: 3, failedWorkUnits: 1 });
const failed = result.children[1];
expect(failed.result).toMatchObject({
jobId: 'metabase-child-2',
failedWorkUnits: ['metabase-fetch'],
artifactsWritten: 0,
commitSha: null,
});
expect(failed.report.body.workUnits).toMatchObject([
{
unitKey: 'metabase-fetch',
status: 'failed',
reason: 'Metabase fetch failed for database 2',
},
]);
await expect(getLocalIngestStatus(project, failed.jobId)).resolves.toMatchObject({
jobId: 'metabase-child-2',
connectionId: 'warehouse_b',
sourceKey: 'metabase',
body: {
failedWorkUnits: ['metabase-fetch'],
},
});
});
});