ktx/packages/cli/test/connectors/mysql/connector.test.ts

575 lines
21 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, it, vi } from 'vitest';
import type { FieldPacket, RowDataPacket } from 'mysql2/promise';
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 { createMysqlLiveDatabaseIntrospection } from '../../../src/connectors/mysql/live-database-introspection.js';
import { isKtxMysqlConnectionConfig, KtxMysqlScanConnector, mysqlConnectionPoolConfigFromConfig, prepareMysqlReadOnlyQuery, type KtxMysqlConnectionConfig, type KtxMysqlPoolFactory } from '../../../src/connectors/mysql/connector.js';
import { tableRefSet } from '../../../src/context/scan/table-ref.js';
2026-05-10 23:12:26 +02:00
function mysqlResult(rows: Record<string, unknown>[], fields: Array<{ name: string; type?: number }>): [RowDataPacket[], FieldPacket[]] {
return [rows as RowDataPacket[], fields as FieldPacket[]];
}
2026-05-10 23:51:24 +02:00
function fakePoolFactory(): KtxMysqlPoolFactory {
2026-05-10 23:12:26 +02:00
const query = vi.fn(async (sql: string, params?: unknown): Promise<[RowDataPacket[], FieldPacket[]]> => {
if (sql.includes('INFORMATION_SCHEMA.TABLES')) {
return mysqlResult(
[
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
{ TABLE_SCHEMA: 'analytics', TABLE_NAME: 'customers', TABLE_TYPE: 'BASE TABLE', TABLE_COMMENT: 'Customer table', TABLE_ROWS: 2 },
{ TABLE_SCHEMA: 'analytics', TABLE_NAME: 'orders', TABLE_TYPE: 'BASE TABLE', TABLE_COMMENT: 'InnoDB free: 1 kB; Order table', TABLE_ROWS: 2 },
{ TABLE_SCHEMA: 'analytics', TABLE_NAME: 'order_summary', TABLE_TYPE: 'VIEW', TABLE_COMMENT: '', TABLE_ROWS: null },
2026-05-10 23:12:26 +02:00
],
[{ name: 'TABLE_NAME' }, { name: 'TABLE_TYPE' }, { name: 'TABLE_COMMENT' }, { name: 'TABLE_ROWS' }],
);
}
if (sql.includes('INFORMATION_SCHEMA.COLUMNS')) {
return mysqlResult(
[
{ TABLE_NAME: 'customers', COLUMN_NAME: 'id', DATA_TYPE: 'int', IS_NULLABLE: 'NO', COLUMN_COMMENT: 'PK' },
{ TABLE_NAME: 'customers', COLUMN_NAME: 'name', DATA_TYPE: 'varchar', IS_NULLABLE: 'NO', COLUMN_COMMENT: '' },
{ TABLE_NAME: 'orders', COLUMN_NAME: 'id', DATA_TYPE: 'int', IS_NULLABLE: 'NO', COLUMN_COMMENT: '' },
{ TABLE_NAME: 'orders', COLUMN_NAME: 'customer_id', DATA_TYPE: 'int', IS_NULLABLE: 'NO', COLUMN_COMMENT: '' },
{ TABLE_NAME: 'orders', COLUMN_NAME: 'status', DATA_TYPE: 'varchar', IS_NULLABLE: 'YES', COLUMN_COMMENT: '' },
{ TABLE_NAME: 'order_summary', COLUMN_NAME: 'status', DATA_TYPE: 'varchar', IS_NULLABLE: 'YES', COLUMN_COMMENT: '' },
],
[{ name: 'TABLE_NAME' }, { name: 'COLUMN_NAME' }, { name: 'DATA_TYPE' }, { name: 'IS_NULLABLE' }],
);
}
if (sql.includes('INFORMATION_SCHEMA.KEY_COLUMN_USAGE') && sql.includes("CONSTRAINT_NAME = 'PRIMARY'")) {
return mysqlResult([{ TABLE_NAME: 'customers', COLUMN_NAME: 'id' }, { TABLE_NAME: 'orders', COLUMN_NAME: 'id' }], []);
}
if (sql.includes('INFORMATION_SCHEMA.KEY_COLUMN_USAGE') && sql.includes('REFERENCED_TABLE_NAME IS NOT NULL')) {
return mysqlResult(
[
{
TABLE_NAME: 'orders',
COLUMN_NAME: 'customer_id',
REFERENCED_TABLE_NAME: 'customers',
REFERENCED_COLUMN_NAME: 'id',
CONSTRAINT_NAME: 'orders_customer_id_fk',
},
],
[],
);
}
if (sql.includes('SELECT `id`, `status` FROM `analytics`.`orders` LIMIT 1')) {
return mysqlResult([{ id: 10, status: 'paid' }], [{ name: 'id', type: 3 }, { name: 'status', type: 253 }]);
}
2026-05-10 23:51:24 +02:00
if (sql.includes('select * from (select id, status from analytics.orders) as ktx_query_result limit 1')) {
2026-05-10 23:12:26 +02:00
return mysqlResult([{ id: 10, status: 'paid' }], [{ name: 'id', type: 3 }, { name: 'status', type: 253 }]);
}
if (sql.includes('SELECT `status` FROM `analytics`.`orders`')) {
return mysqlResult([{ status: 'paid' }, { status: 'open' }], [{ name: 'status', type: 253 }]);
}
if (sql.includes('COUNT(DISTINCT val)')) {
return mysqlResult([{ cardinality: 2 }], [{ name: 'cardinality', type: 8 }]);
}
if (sql.includes('SELECT DISTINCT CAST(`status` AS CHAR) AS val')) {
return mysqlResult([{ val: 'open' }, { val: 'paid' }], [{ name: 'val', type: 253 }]);
}
if (sql.includes('COUNT(*) AS count')) {
return mysqlResult([{ count: 2 }], [{ name: 'count', type: 8 }]);
}
if (sql.includes('INFORMATION_SCHEMA.SCHEMATA')) {
return mysqlResult([{ SCHEMA_NAME: 'analytics' }, { SCHEMA_NAME: 'warehouse' }], [{ name: 'SCHEMA_NAME' }]);
}
if (sql.trim() === 'SELECT 1') {
return mysqlResult([{ '1': 1 }], [{ name: '1', type: 8 }]);
}
throw new Error(`Unexpected SQL: ${sql} params=${JSON.stringify(params)}`);
});
const release = vi.fn();
const end = vi.fn(async () => undefined);
return {
createPool: vi.fn(() => ({
getConnection: vi.fn(async () => ({ query, release })),
end,
})),
};
}
function multiSchemaMysqlPoolFactory(
options: { primaryKeyError?: Error; foreignKeyError?: Error } = {},
): KtxMysqlPoolFactory {
const query = vi.fn(async (sql: string, params?: unknown): Promise<[RowDataPacket[], FieldPacket[]]> => {
if (sql.includes('INFORMATION_SCHEMA.TABLES')) {
expect(params).toEqual(['analytics', 'mart']);
return mysqlResult(
[
{
TABLE_SCHEMA: 'analytics',
TABLE_NAME: 'customers',
TABLE_TYPE: 'BASE TABLE',
TABLE_COMMENT: '',
TABLE_ROWS: 2,
},
{
TABLE_SCHEMA: 'mart',
TABLE_NAME: 'orders',
TABLE_TYPE: 'BASE TABLE',
TABLE_COMMENT: '',
TABLE_ROWS: 3,
},
],
[
{ name: 'TABLE_SCHEMA' },
{ name: 'TABLE_NAME' },
{ name: 'TABLE_TYPE' },
{ name: 'TABLE_COMMENT' },
{ name: 'TABLE_ROWS' },
],
);
}
if (sql.includes('INFORMATION_SCHEMA.COLUMNS')) {
expect(params).toEqual(['analytics', 'mart']);
return mysqlResult(
[
{
TABLE_SCHEMA: 'analytics',
TABLE_NAME: 'customers',
COLUMN_NAME: 'id',
DATA_TYPE: 'int',
IS_NULLABLE: 'NO',
COLUMN_COMMENT: '',
},
{
TABLE_SCHEMA: 'mart',
TABLE_NAME: 'orders',
COLUMN_NAME: 'id',
DATA_TYPE: 'int',
IS_NULLABLE: 'NO',
COLUMN_COMMENT: '',
},
],
[],
);
}
if (sql.includes('INFORMATION_SCHEMA.KEY_COLUMN_USAGE') && sql.includes("CONSTRAINT_NAME = 'PRIMARY'")) {
if (options.primaryKeyError) {
throw options.primaryKeyError;
}
expect(params).toEqual(['analytics', 'mart']);
return mysqlResult(
[
{ TABLE_SCHEMA: 'analytics', TABLE_NAME: 'customers', COLUMN_NAME: 'id' },
{ TABLE_SCHEMA: 'mart', TABLE_NAME: 'orders', COLUMN_NAME: 'id' },
],
[],
);
}
if (sql.includes('INFORMATION_SCHEMA.KEY_COLUMN_USAGE') && sql.includes('REFERENCED_TABLE_NAME IS NOT NULL')) {
if (options.foreignKeyError) {
throw options.foreignKeyError;
}
expect(params).toEqual(['analytics', 'mart']);
return mysqlResult([], []);
}
throw new Error(`Unexpected SQL: ${sql} params=${JSON.stringify(params)}`);
});
return {
createPool: vi.fn(() => ({
getConnection: vi.fn(async () => ({ query, release: vi.fn() })),
end: vi.fn(async () => undefined),
})),
};
}
2026-05-10 23:51:24 +02:00
describe('KtxMysqlScanConnector', () => {
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
it('prepares read-only SQL parameters with MySQL positional placeholders', () => {
expect(
prepareMysqlReadOnlyQuery('select * from orders where id = :id and status = :status', {
status: 'paid',
id: 10,
}),
).toEqual({
sql: 'select * from orders where id = ? and status = ?',
params: [10, 'paid'],
});
expect(prepareMysqlReadOnlyQuery('select 1')).toEqual({ sql: 'select 1', params: undefined });
});
2026-05-10 23:12:26 +02:00
it('resolves MySQL connection configuration safely', () => {
expect(isKtxMysqlConnectionConfig({ driver: 'mysql', host: 'localhost', database: 'analytics' })).toBe(true);
2026-05-10 23:51:24 +02:00
expect(isKtxMysqlConnectionConfig({ driver: 'postgres', host: 'localhost', database: 'analytics' })).toBe(false);
2026-05-10 23:12:26 +02:00
expect(
mysqlConnectionPoolConfigFromConfig({
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
port: 3307,
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
ssl: true,
},
}),
).toMatchObject({
host: 'db.example.test',
port: 3307,
database: 'analytics',
user: 'reader',
password: 'secret', // pragma: allowlist secret
ssl: { rejectUnauthorized: false },
});
});
it('defaults and validates MySQL maxConnections', () => {
const baseConnection: KtxMysqlConnectionConfig = {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
};
expect(
mysqlConnectionPoolConfigFromConfig({
connectionId: 'warehouse',
connection: baseConnection,
}),
).toMatchObject({ connectionLimit: 10 });
expect(
mysqlConnectionPoolConfigFromConfig({
connectionId: 'warehouse',
connection: { ...baseConnection, maxConnections: 25 },
}),
).toMatchObject({ connectionLimit: 25 });
expect(
mysqlConnectionPoolConfigFromConfig({
connectionId: 'warehouse',
connection: { ...baseConnection, maxConnections: '12' as never },
}),
).toMatchObject({ connectionLimit: 12 });
for (const maxConnections of [0, -1, 1.5, Number.NaN, 'abc' as never]) {
expect(() =>
mysqlConnectionPoolConfigFromConfig({
connectionId: 'warehouse',
connection: { ...baseConnection, maxConnections },
}),
).toThrow('connections.warehouse.maxConnections must be a positive integer');
}
});
2026-05-10 23:12:26 +02:00
it('introspects schema, primary keys, comments, row counts, views, and foreign keys', async () => {
2026-05-10 23:51:24 +02:00
const connector = new KtxMysqlScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
poolFactory: fakePoolFactory(),
now: () => new Date('2026-04-29T12:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'mysql' },
{ runId: 'scan-run-1' },
);
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
driver: 'mysql',
extractedAt: '2026-04-29T12:00:00.000Z',
scope: { schemas: ['analytics'] },
metadata: {
database: 'analytics',
host: 'db.example.test',
table_count: 3,
total_columns: 6,
},
});
expect(snapshot.tables.map((table) => [table.name, table.kind, table.estimatedRows, table.comment])).toEqual([
['customers', 'table', 2, 'Customer table'],
['orders', 'table', 2, 'Order table'],
['order_summary', 'view', null, null],
]);
expect(snapshot.tables.find((table) => table.name === 'customers')?.columns[0]).toMatchObject({
name: 'id',
nativeType: 'int',
normalizedType: 'int',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'PK',
});
expect(snapshot.tables.find((table) => table.name === 'orders')?.foreignKeys).toEqual([
{
fromColumn: 'customer_id',
toCatalog: null,
toDb: 'analytics',
toTable: 'customers',
toColumn: 'id',
constraintName: 'orders_customer_id_fk',
},
]);
});
it('introspects every configured MySQL schema scope', async () => {
const connector = new KtxMysqlScanConnector({
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
schemas: ['analytics', 'mart'],
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
poolFactory: multiSchemaMysqlPoolFactory(),
now: () => new Date('2026-05-21T10:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'mysql' },
{ runId: 'scan-run-1' },
);
expect(snapshot.scope).toEqual({ schemas: ['analytics', 'mart'] });
expect(snapshot.metadata).toMatchObject({ database: 'analytics', schemas: ['analytics', 'mart'] });
expect(snapshot.tables.map((table) => `${table.db}.${table.name}`)).toEqual([
'analytics.customers',
'mart.orders',
]);
});
it('soft-fails denied MySQL constraint discovery with one warning per schema and kind', async () => {
const connector = new KtxMysqlScanConnector({
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
schemas: ['analytics', 'mart'],
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
poolFactory: multiSchemaMysqlPoolFactory({
primaryKeyError: Object.assign(new Error('select command denied'), {
code: 'ER_TABLEACCESS_DENIED_ERROR',
errno: 1142,
}),
foreignKeyError: Object.assign(new Error('database access denied'), {
code: 'ER_DBACCESS_DENIED_ERROR',
errno: 1044,
}),
}),
now: () => new Date('2026-04-29T12:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'mysql' },
{ runId: 'scan-run-mysql-denied-constraints' },
);
expect(snapshot.warnings).toEqual([
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped primary-key discovery in analytics (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'analytics', kind: 'primary_key' },
},
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped primary-key discovery in mart (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'mart', kind: 'primary_key' },
},
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped foreign-key discovery in analytics (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'analytics', kind: 'foreign_key' },
},
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped foreign-key discovery in mart (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'mart', kind: 'foreign_key' },
},
]);
expect(snapshot.tables.every((table) => table.columns.every((column) => column.primaryKey === false))).toBe(true);
expect(snapshot.tables.every((table) => table.foreignKeys.length === 0)).toBe(true);
});
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204) * feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure Snowflake setup previously asked for a single schema as free text, then ran a multiselect against the discovered schemas — two schema questions back-to-back, with the first being only a session bootstrap. The SDK's `schema` is optional, so the bootstrap step is unnecessary. - Remove the free-text Snowflake schema prompt; only pass `schema` to snowflake-sdk when one is configured. - When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the user for a comma-separated list, persist it as `schema_names`, and use it as both the table-list filter and the multiselect default. Applies to every driver with a scope-discovery spec, not just Snowflake. - Update docs to lead with `schema_names`; keep `schema_name` as a documented single-schema shorthand. * fix(snowflake): keep introspecting when primary-key discovery is denied The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the connection role may not have. Previously a 'SQL compilation error: Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist or not authorized' aborted the entire introspect — schemas, columns, and row counts were all discarded over a missing nice-to-have. Wrap the constraint query in try/catch, log a one-line warning per schema, and return an empty PK map. Columns end up with primaryKey=false; relationship inference still has FK and profiling to fall back on. * fix(scan): unblock relationship discovery on Snowflake Two adjacent bugs prevented the scan's relationship pipeline from producing any joins on a Snowflake warehouse: - relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table profile query failed with "Unknown function GROUP_CONCAT". Add an explicit Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter (Snowflake requires the delimiter to be a constant, so CHR(31) is rejected). - description-generation.ts destructured `connector.sampleTable` and `connector.sampleColumn` into bare locals, losing the `this` binding when the class-method connectors (Snowflake, Postgres, MySQL) were invoked. Every sample call threw "Cannot read properties of undefined (reading 'assertConnection')" and degraded LLM descriptions to metadata-only prompts. Call the methods through the connector instead. Without these, even after the primary-key probe is allowed to fail softly, the scan ends up with 0 validated relationships and an empty `joins:` block in every shard YAML. * test(scan): cover table-ref helpers * feat(scan): plumb tableScope through live-database introspection port * feat(scan): apply tableScope during metadata fetch * feat(scan): enforce table scope at fetch boundary * feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206) * feat(cli): add RSA key-pair auth option to Snowflake setup wizard Extends the interactive Snowflake setup flow with an authentication-method prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key path (env/file/absolute) and an optional passphrase; the resulting connection config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead of `password`. * feat(scan): pool Snowflake sessions * fix(scan): reuse structural snapshots and cleanup connectors * feat(scan): parallelize relationship profiling * feat(scan): batch table description generation * docs: document Snowflake ingest concurrency knobs * fix(scan): close Snowflake ingest perf verification gaps * fix(scan): keep batched description failure bounded * feat(scan): dispatch query-history probes by connection driver Extract historic-sql dialect resolution into a shared helper so the status-project readiness check and the local ingest factory agree on which connections enable query history and which probe to run. The status command now picks the postgres/snowflake/bigquery probe based on the connection's driver instead of always reporting against postgres, which previously caused snowflake connections with queryHistory.enabled to surface a misleading "driver is snowflake" failure. Also drops a noisy console.warn from Snowflake primary-key discovery — INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only roles and the FK + profiling paths handle the empty PK map already. * fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject The Claude Code agent SDK announces an internal pseudo-tool named StructuredOutput in the system/init message whenever outputFormat is set to { type: 'json_schema' }. The runtime's isolation check built its allowedToolIds set only from MCP tool ids and treated StructuredOutput as an unexpected host-injected tool, so every generateObject call threw "Claude Code runtime isolation failed: tools=StructuredOutput ..." and the table-descriptions and relationship-LLM-proposal enrichment stages recorded null output across the board. Whitelist StructuredOutput specifically in generateObject's allowedToolIds — the check also enforces missing_tools symmetry, so generateText and runAgentLoop, which do not see StructuredOutput, must not require it. generateObject also ran with maxTurns: 1, which the model intermittently breached when it emitted thinking text before the structured response. Raised to 5 to give the schema-bound call enough headroom without allowing unbounded loops. The existing tests now exercise the path with an init message that announces StructuredOutput so the regression cannot slip back in. * chore(scripts): add ktx-reset.sh project-cleanup helper Convenience script for repeatable ingest testing: takes a project directory and prunes everything except ktx.yaml and .ktx/secrets/, so the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
it('limits introspection to tables in tableScope', async () => {
const queries: Array<{ sql: string; params?: unknown }> = [];
const poolFactory: KtxMysqlPoolFactory = {
createPool: vi.fn(() => ({
getConnection: vi.fn(async () => ({
query: vi.fn(async (sql: string, params?: unknown): Promise<[RowDataPacket[], FieldPacket[]]> => {
queries.push({ sql, params });
if (sql.includes('INFORMATION_SCHEMA.TABLES')) {
return mysqlResult(
[
{
TABLE_SCHEMA: 'analytics',
TABLE_NAME: 'orders',
TABLE_TYPE: 'BASE TABLE',
TABLE_COMMENT: '',
TABLE_ROWS: 2,
},
],
[],
);
}
if (sql.includes('INFORMATION_SCHEMA.COLUMNS')) {
return mysqlResult(
[
{
TABLE_SCHEMA: 'analytics',
TABLE_NAME: 'orders',
COLUMN_NAME: 'id',
DATA_TYPE: 'int',
IS_NULLABLE: 'NO',
COLUMN_COMMENT: '',
},
],
[],
);
}
return mysqlResult([], []);
}),
release: vi.fn(),
})),
end: vi.fn(async () => undefined),
})),
};
const connector = new KtxMysqlScanConnector({
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
poolFactory,
});
const scope = tableRefSet([{ catalog: null, db: 'analytics', name: 'orders' }]);
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'mysql', tableScope: scope },
{ runId: 'scope-test' },
);
expect(snapshot.tables.map((table) => table.name)).toEqual(['orders']);
const tablesQuery = queries.find((query) => query.sql.includes('INFORMATION_SCHEMA.TABLES'));
expect(tablesQuery?.sql).toMatch(/TABLE_NAME IN \(\?\)/);
expect(tablesQuery?.params).toEqual(['analytics', 'orders']);
});
2026-05-10 23:12:26 +02:00
it('runs samples, distinct values, read-only SQL, row count, schema list, and cleanup', async () => {
const poolFactory = fakePoolFactory();
2026-05-10 23:51:24 +02:00
const connector = new KtxMysqlScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
poolFactory,
});
await expect(
connector.sampleTable(
{ connectionId: 'warehouse', table: { catalog: null, db: 'analytics', name: 'orders' }, columns: ['id', 'status'], limit: 1 },
{ runId: 'scan-run-1' },
),
).resolves.toEqual({ headers: ['id', 'status'], rows: [[10, 'paid']], totalRows: 1 });
await expect(
connector.sampleColumn(
{ connectionId: 'warehouse', table: { catalog: null, db: 'analytics', name: 'orders' }, column: 'status', limit: 5 },
{ runId: 'scan-run-1' },
),
).resolves.toMatchObject({ values: ['paid', 'open'], nullCount: null, distinctCount: null });
await expect(
connector.getColumnDistinctValues(
{ catalog: null, db: 'analytics', name: 'orders' },
'status',
{ maxCardinality: 5, limit: 10, sampleSize: 100 },
),
).resolves.toEqual({ values: ['open', 'paid'], cardinality: 2 });
await expect(
connector.executeReadOnly(
{ connectionId: 'warehouse', sql: 'select id, status from analytics.orders', maxRows: 1 },
{ runId: 'scan-run-1' },
),
).resolves.toMatchObject({ headers: ['id', 'status'], rows: [[10, 'paid']], totalRows: 1, rowCount: 1 });
await expect(
connector.executeReadOnly({ connectionId: 'warehouse', sql: 'delete from orders' }, { runId: 'scan-run-1' }),
).rejects.toThrow('Only read-only SELECT/WITH queries can be executed locally');
await expect(connector.getTableRowCount('orders')).resolves.toBe(2);
await expect(connector.listSchemas()).resolves.toEqual(['analytics', 'warehouse']);
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
await expect(connector.listTables(['analytics'])).resolves.toEqual([
{ catalog: null, schema: 'analytics', name: 'customers', kind: 'table' },
{ catalog: null, schema: 'analytics', name: 'orders', kind: 'table' },
{ catalog: null, schema: 'analytics', name: 'order_summary', kind: 'view' },
]);
2026-05-10 23:12:26 +02:00
await expect(connector.columnStats(
{ connectionId: 'warehouse', table: { catalog: null, db: 'analytics', name: 'orders' }, column: 'status' },
{ runId: 'scan-run-1' },
)).resolves.toBeNull();
await connector.cleanup();
});
it('adapts native MySQL snapshots to live-database introspection for local ingest', async () => {
const introspection = createMysqlLiveDatabaseIntrospection({
connections: {
warehouse: {
driver: 'mysql',
host: 'db.example.test',
database: 'analytics',
username: 'reader',
password: 'secret', // pragma: allowlist secret
},
},
poolFactory: fakePoolFactory(),
now: () => new Date('2026-04-29T12:00:00.000Z'),
});
const snapshot = await introspection.extractSchema('warehouse');
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
extractedAt: '2026-04-29T12:00:00.000Z',
});
expect(snapshot.tables.find((table) => table.name === 'customers')).toMatchObject({
name: 'customers',
catalog: null,
db: 'analytics',
columns: [
{
name: 'id',
nativeType: 'int',
normalizedType: 'int',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'PK',
},
{
name: 'name',
nativeType: 'varchar',
normalizedType: 'varchar',
dimensionType: 'string',
nullable: false,
primaryKey: false,
comment: null,
},
],
foreignKeys: [],
});
});
});