ktx/packages/cli/test/sql.test.ts

403 lines
12 KiB
TypeScript
Raw Normal View History

import { mkdtemp, readFile, 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 { initKtxProject } from '../src/context/project/project.js';
import { parseKtxProjectConfig, serializeKtxProjectConfig } from '../src/context/project/config.js';
import type { KtxScanConnector } from '../src/context/scan/types.js';
import type { SqlAnalysisPort } from '../src/context/sql-analysis/ports.js';
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 { runKtxSql } from '../src/sql.js';
const reportExceptionMock = vi.hoisted(() => vi.fn(async () => {}));
vi.mock('../src/telemetry/exception.js', () => ({
reportException: reportExceptionMock,
}));
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
function makeIo(options: { isTTY?: boolean } = {}) {
let stdout = '';
let stderr = '';
return {
io: {
stdout: {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
isTTY: options.isTTY,
write: (chunk: string) => {
stdout += chunk;
},
},
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stdout: () => stdout,
stderr: () => stderr,
};
}
function makeSqlAnalysis(result: Awaited<ReturnType<SqlAnalysisPort['validateReadOnly']>>): SqlAnalysisPort {
return {
analyzeForFingerprint: vi.fn(),
analyzeBatch: vi.fn(async () => new Map([['cli-sql', { tablesTouched: [{ catalog: null, db: null, name: 'orders' }], columnsByClause: {} }]])),
validateReadOnly: vi.fn(async () => result),
};
}
function makeConnector(overrides: Partial<KtxScanConnector> = {}): KtxScanConnector {
return {
id: 'sqlite:warehouse',
driver: 'sqlite',
capabilities: {
structuralIntrospection: true,
tableSampling: true,
columnSampling: true,
columnStats: true,
readOnlySql: true,
nestedAnalysis: false,
eventStreamDiscovery: false,
formalForeignKeys: true,
estimatedRowCounts: true,
},
introspect: vi.fn(),
executeReadOnly: vi.fn(async () => ({
headers: ['id', 'status'],
headerTypes: ['integer', 'text'],
rows: [
[1, 'paid'],
[2, 'open'],
],
totalRows: 2,
rowCount: 2,
})),
cleanup: vi.fn(async () => undefined),
...overrides,
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
listSchemas: overrides.listSchemas ?? vi.fn(async () => []),
listTables: overrides.listTables ?? vi.fn(async () => []),
};
}
describe('runKtxSql', () => {
let tempDir: string;
beforeEach(async () => {
tempDir = await mkdtemp(join(tmpdir(), 'ktx-cli-sql-'));
reportExceptionMock.mockClear();
});
afterEach(async () => {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
vi.unstubAllEnvs();
await rm(tempDir, { recursive: true, force: true });
});
async function writeConnections(
projectDir: string,
connections: ReturnType<typeof parseKtxProjectConfig>['connections'],
): Promise<void> {
const config = parseKtxProjectConfig(await readFile(join(projectDir, 'ktx.yaml'), 'utf-8'));
await writeFile(join(projectDir, 'ktx.yaml'), serializeKtxProjectConfig({ ...config, connections }), 'utf-8');
}
it('validates SQL, executes through the scan connector, and prints a pretty table', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const sqlAnalysis = makeSqlAnalysis({ ok: true, error: null });
const connector = makeConnector();
const createScanConnector = vi.fn(async () => connector);
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id, status from orders',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => sqlAnalysis,
createScanConnector,
},
),
).resolves.toBe(0);
expect(sqlAnalysis.validateReadOnly).toHaveBeenCalledWith('select id, status from orders', 'sqlite');
expect(createScanConnector).toHaveBeenCalledWith(expect.objectContaining({ projectDir }), 'warehouse');
expect(connector.executeReadOnly).toHaveBeenCalledWith(
{ connectionId: 'warehouse', sql: 'select id, status from orders', maxRows: 1000 },
{ runId: 'cli-sql' },
);
expect(connector.cleanup).toHaveBeenCalledTimes(1);
expect(io.stdout()).toContain('id status');
expect(io.stdout()).toContain('1 paid');
expect(io.stdout()).toContain('2 open');
expect(io.stdout()).toContain('2 rows');
expect(io.stderr()).toBe('');
});
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
it('emits debug telemetry for SQL without raw query text', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const io = makeIo({ isTTY: true });
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select count(*) from orders',
maxRows: 10,
output: 'json',
json: true,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => makeConnector()),
},
),
).resolves.toBe(0);
expect(io.stderr()).toContain('"event":"sql_completed"');
expect(io.stderr()).toContain('"queryVerb":"select"');
expect(io.stderr()).not.toContain('select count(*)');
});
it('prints JSON output', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id from orders',
maxRows: 10,
output: undefined,
json: true,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => makeConnector()),
},
),
).resolves.toBe(0);
expect(JSON.parse(io.stdout())).toEqual({
connectionId: 'warehouse',
headers: ['id', 'status'],
headerTypes: ['integer', 'text'],
rows: [
[1, 'paid'],
[2, 'open'],
],
rowCount: 2,
});
});
it('prints plain TSV output', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id from orders',
maxRows: 10,
output: 'plain',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => makeConnector()),
},
),
).resolves.toBe(0);
expect(io.stdout()).toBe('id\tstatus\n1\tpaid\n2\topen\n');
expect(io.stderr()).toBe('');
});
it('rejects non-read-only SQL before executing connector SQL', async () => {
vi.stubEnv('SQL_DB_PASSWORD', 'sql-db-password'); // pragma: allowlist secret
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'postgres', password: 'env:SQL_DB_PASSWORD' } }); // pragma: allowlist secret
const connector = makeConnector();
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'delete from orders',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: false, error: 'SQL contains read/write operation: Delete' }),
createScanConnector: vi.fn(async () => connector),
},
),
).resolves.toBe(1);
expect(connector.executeReadOnly).not.toHaveBeenCalled();
expect(connector.cleanup).not.toHaveBeenCalled();
expect(io.stderr()).toContain('SQL contains read/write operation: Delete');
expect(reportExceptionMock).toHaveBeenCalledWith(
expect.objectContaining({
context: expect.objectContaining({ source: 'sql run', handled: true, fatal: false }),
projectDir,
redactionSecrets: expect.arrayContaining(['sql-db-password']),
}),
);
});
it('rejects missing connections', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select 1',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
},
),
).resolves.toBe(1);
expect(io.stderr()).toContain(
'Connection "warehouse" is not configured in ktx.yaml. No connections are configured in ktx.yaml.',
);
});
it('rejects connectors without read-only SQL support and still cleans up', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const connector = makeConnector({
capabilities: {
...makeConnector().capabilities,
readOnlySql: false,
},
});
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select 1',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => connector),
},
),
).resolves.toBe(1);
expect(connector.executeReadOnly).not.toHaveBeenCalled();
expect(connector.cleanup).toHaveBeenCalledTimes(1);
feat(duckdb): cross-database federation via derived DuckDB connection (#295) * feat(duckdb): add @duckdb/node-api dependency for federation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(connectors): extract resolveStringReference to shared module Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(connectors): route all identical connectors through shared resolveStringReference Collapse the 5 remaining private copies in bigquery, clickhouse, mysql, snowflake, and sqlserver into the shared module. Fix a latent bug in the shared module where `~/path` was incorrectly sliced (dropping only `~`, leaving the leading `/` and making resolve() ignore homedir). Add a tilde-expansion test that caught the bug and now covers that branch. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(sl): reserve _ktx_ connection-id prefix for virtual connections Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(connections): derive virtual federated connection from compatible members Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(duckdb): federated executor builds READ_ONLY attaches and runs SQL Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(duckdb): close federated DuckDB instance and escape quotes in attach url Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(sl): union member source directories for _ktx_federated Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(query): route _ktx_federated through DuckDB executor Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(sl): use duckdb dialect for federated query compilation Bypass assertSafeConnectionId for _ktx_federated in resolveLocalConnectionId and loadComputableSources, and resolve the compute dialect to 'duckdb' when connectionId is FEDERATED_CONNECTION_ID instead of falling through to the default postgres lookup. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * test(duckdb): end-to-end cross-catalog federated join Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(duckdb): harden federated join test with multi-book join-key coverage Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(ingest): keep declared cross-DB joins to federated siblings Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(setup): surface federated connection availability after adding a member Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(setup): mark federationNoticeFor @internal for dead-code gate Also marks attachTypeForDriver, buildAttachStatements, and isReservedConnectionId @internal — all three are exported solely for unit-test access with no production cross-file consumer. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(concepts): document cross-database federation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(concepts): correct sqlite two-part naming in federation doc Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(duckdb): quote federated catalog alias so hyphenated connection ids attach * refactor(duckdb): single-source federation driver list, dedup attach loads Collapse the parallel ATTACH_COMPATIBLE_DRIVERS set and ATTACH_TYPE_BY_DRIVER map into one map in federation.ts whose keys are the membership rule. Replace FederatedMember.config (read only via a type-erasing cast) with a typed url field extracted at derive time. Emit INSTALL/LOAD once per distinct driver type instead of once per member. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(duckdb): close federated DuckDB instance on connect failure; dedup id validation Wrap the federated DuckDB instance in its own try/finally so a failing connect() or a throwing connection.closeSync() no longer leaks the native instance. Route setup-sources connection-id validation through the canonical assertSafeConnectionId so the reserved _ktx_ prefix guard applies there too. Derive the federated dialect through sqlAnalysisDialectForDriver instead of a hardcoded literal. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): carry member connection config and projectDir on FederatedMember Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): resolve per-member attach targets via canonical connector resolvers Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): quote mysql attach-string values like postgres Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): resolve member attach targets via canonical resolvers, supporting sqlite path: Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): thread projectDir through deriveFederatedConnection callers Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): add shared project read-only SQL executor that routes _ktx_federated Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(federation): exercise shared executor default federated path with real DuckDB Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): route ingest query executor through shared executor Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): route MCP sql_execution _ktx_federated through shared executor Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): preserve cross-DB joins to federated siblings in manifest re-emit Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): preserve declared cross-DB joins through scan re-ingest Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): document sibling-ref invariant, drop unsafe casts in test Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): namespace federated source names by member to avoid collisions Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(federation): document member-namespaced federated source names Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): preserve member SSL/search_path in attach, classify federated MCP errors Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): simplify federated dispatch and parallelize sibling reads Dedup the federated driver ternary in local-query, derive the prefixed source.name from the already-built name, drop the duplicated error in federatedAttachTarget's exhaustive switch, inline the one-line cleanupConnector wrapper, and parallelize federatedSiblingTargets' shard reads (was sequential await-in-for on the scan hot path). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): carry headerTypes through shared SQL executor Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): add shared federated connection listing builder Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): route ktx sql through shared executor for _ktx_federated parity Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): show _ktx_federated in ktx connection list Surfaces the virtual federated connection in the output of `ktx connection list` so agents and users can discover cross-database querying when 2+ attach-compatible connections are configured. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(federation): surface _ktx_federated in MCP connection_list Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(federation): ktx sql federated cross-file join end-to-end Drive runKtxSql with the real federated DuckDB executor against two on-disk sqlite files, stubbing only SQL validation. The test surfaced that the JSON output path could not serialize bigint values DuckDB returns for integer columns; printJson now coerces bigint to JSON numbers, matching the plain/pretty paths. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(federation): document direct _ktx_federated query surface Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): coerce DuckDB bigint to number in shared federated executor DuckDB returns integer columns as JS bigint, which JSON.stringify cannot serialize. The CLI --json path worked around this with a replacer, but the MCP sql_execution tool serializes via plain JSON.stringify and crashed on any federated query selecting an integer column. Coerce bigint to Number once in executeFederatedQuery so every consumer (CLI, MCP, ingest, SL) gets a JSON-safe result, and remove the now-redundant CLI replacer. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(federation): simplify driver map and collapse forked MCP SQL path - Replace the identity-valued ATTACH_TYPE_BY_DRIVER record with a ATTACH_COMPATIBLE_DRIVERS Set; the driver name doubles as the attach type, so the map encoded nothing beyond membership. - Switch federatedAttachTarget directly on the driver with a default throw, dropping the unreachable post-switch throw and its comment. - Route the MCP sql_execution standard-connection case through the shared executeProjectReadOnlySql instead of reimplementing the connector create/capability-check/execute/cleanup ceremony, so federated and standard connections share one execution path. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(federation): allowlist placeholder credentials for detect-secrets The federation doc example URL and the federated-attach test fixtures use literal placeholder credentials that trip detect-secrets. Mark them with line-scoped pragma allowlist comments so a real secret added later is still caught. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(federation): correct SL addressing, join pruning, and id-quoting guidance - Federated SL list/search records carry the virtual `_ktx_federated` connection id (member origin stays in the prefixed source name), so rows round-trip to `ktx sl -c _ktx_federated read` and the fts index no longer clobbers per-connection partitions. - Prune semantic-layer joins by membership in the connection's own source set instead of matching the target's first dotted segment against other connection ids; a same-connection join whose target name collides with a sibling connection id is preserved, and orphan targets that would poison the planner are dropped. - Document double-quoting for connection ids that are not bare SQL identifiers (e.g. "books-db".public.books) in the federated naming hint, the sl-query rejection error, and the federation docs. - Preserve exact federated BIGINT values beyond 2^53 as strings instead of rounding, and steer the setup federation notice to raw SQL against `_ktx_federated`. * fix(federation): carry ssl:true into postgres URL attach target A postgres member configured with `url` plus `ssl: true` resolved to both a connectionString and an ssl flag, but the federated attach builder early-returned the bare URL and dropped the ssl intent. DuckDB then handed libpq a URL with no sslmode, so the URL path silently diverged from the discrete-field path (which emits sslmode=require) and from the direct scan path (which enforces TLS). Append sslmode=require to the URL when the member sets ssl, unless the URL already pins a stronger sslmode. --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-06-15 22:01:39 +07:00
expect(io.stderr()).toContain('does not support read-only SQL execution.');
});
it('routes _ktx_federated through the shared federated executor', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, {
books_db: { driver: 'sqlite', path: 'books.db' },
reviews_db: { driver: 'sqlite', path: 'reviews.db' },
});
const executeFederated = vi.fn(async () => ({
headers: ['title', 'rating'],
rows: [['Clean Code', 5]],
totalRows: 1,
command: 'SELECT',
rowCount: 1,
}));
const memberConnector = makeConnector({
executeReadOnly: vi.fn(async () => {
throw new Error('member connector must not be used for federated id');
}),
});
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: '_ktx_federated',
sql: 'select 1',
maxRows: 100,
output: 'json',
json: true,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => memberConnector),
executeFederated,
},
),
).resolves.toBe(0);
expect(executeFederated).toHaveBeenCalledTimes(1);
expect(memberConnector.executeReadOnly).not.toHaveBeenCalled();
expect(JSON.parse(io.stdout())).toEqual({
connectionId: '_ktx_federated',
headers: ['title', 'rating'],
rows: [['Clean Code', 5]],
rowCount: 1,
});
});
});