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

437 lines
16 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, it, vi } from 'vitest';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { clickHouseClientConfigFromConfig, isKtxClickHouseConnectionConfig, KtxClickHouseScanConnector, prepareClickHouseReadOnlyQuery, type KtxClickHouseClientFactory } from '../../../src/connectors/clickhouse/connector.js';
import { createClickHouseLiveDatabaseIntrospection } from '../../../src/connectors/clickhouse/live-database-introspection.js';
import { tableRefSet } from '../../../src/context/scan/table-ref.js';
2026-05-10 23:12:26 +02:00
function result<T>(payload: T) {
return {
async json(): Promise<T> {
return payload;
},
};
}
2026-05-10 23:51:24 +02:00
function fakeClientFactory(): KtxClickHouseClientFactory {
2026-05-10 23:12:26 +02:00
const query = vi.fn(async (input: { query: string; format: string; query_params?: Record<string, unknown> }) => {
if (input.query.includes('FROM system.tables')) {
return result([
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
{ database: 'analytics', name: 'event_summary', engine: 'View', comment: '' },
{ database: 'analytics', name: 'events', engine: 'MergeTree', comment: 'Event stream' },
2026-05-10 23:12:26 +02:00
]);
}
if (input.query.includes('FROM system.columns')) {
return result([
{ table: 'events', name: 'id', type: 'UInt64', comment: 'PK', is_in_primary_key: 1 },
{ table: 'events', name: 'event_name', type: 'LowCardinality(String)', comment: '', is_in_primary_key: 0 },
{ table: 'event_summary', name: 'event_name', type: 'String', comment: '', is_in_primary_key: 0 },
]);
}
if (input.query.includes('FROM system.parts') && input.query.includes('GROUP BY')) {
2026-05-10 23:12:26 +02:00
return result([{ table: 'events', row_count: '2' }]);
}
if (input.query.includes('SELECT `id`, `event_name` FROM `analytics`.`events` LIMIT 1')) {
return result({
meta: [
{ name: 'id', type: 'UInt64' },
{ name: 'event_name', type: 'String' },
],
data: [[10, 'signup']],
rows: 1,
});
}
if (input.query.includes('SELECT `event_name` FROM `analytics`.`events`')) {
return result({
meta: [{ name: 'event_name', type: 'String' }],
data: [['signup'], ['purchase']],
rows: 2,
});
}
if (input.query.includes('COUNT(DISTINCT val)')) {
return result({
meta: [{ name: 'cardinality', type: 'UInt64' }],
data: [[2]],
rows: 1,
});
}
if (input.query.includes('SELECT DISTINCT toString(`event_name`) AS val')) {
return result({
meta: [{ name: 'val', type: 'String' }],
data: [['purchase'], ['signup']],
rows: 2,
});
}
if (input.query.includes('sum(rows) AS count')) {
return result({
meta: [{ name: 'count', type: 'UInt64' }],
data: [[2]],
rows: 1,
});
}
if (input.query.includes('FROM system.databases')) {
return result([{ name: 'analytics' }, { name: 'warehouse' }]);
}
if (input.query.trim() === 'SELECT 1') {
return result({ meta: [{ name: '1', type: 'UInt8' }], data: [[1]], rows: 1 });
}
2026-05-10 23:51:24 +02:00
if (input.query.includes('select * from (select id, event_name from analytics.events) as ktx_query_result limit 1')) {
2026-05-10 23:12:26 +02:00
return result({
meta: [
{ name: 'id', type: 'UInt64' },
{ name: 'event_name', type: 'String' },
],
data: [[10, 'signup']],
rows: 1,
});
}
throw new Error(`Unexpected SQL: ${input.query}`);
});
const close = vi.fn(async () => undefined);
return {
createClient: vi.fn(() => ({ query, close })),
};
}
function multiDatabaseClickHouseClientFactory(): KtxClickHouseClientFactory {
const query = vi.fn(async (input: { query: string; format: string; query_params?: Record<string, unknown> }) => {
if (input.query.includes('FROM system.tables')) {
expect(input.query_params).toEqual({ databases: ['analytics', 'mart'] });
return result([
{ database: 'analytics', name: 'events', engine: 'MergeTree', comment: 'Event stream' },
{ database: 'mart', name: 'order_events', engine: 'MergeTree', comment: '' },
]);
}
if (input.query.includes('FROM system.columns')) {
expect(input.query_params).toEqual({ databases: ['analytics', 'mart'] });
return result([
{
database: 'analytics',
table: 'events',
name: 'id',
type: 'UInt64',
comment: '',
is_in_primary_key: 1,
},
{
database: 'mart',
table: 'order_events',
name: 'id',
type: 'UInt64',
comment: '',
is_in_primary_key: 1,
},
]);
}
if (input.query.includes('FROM system.parts') && input.query.includes('GROUP BY')) {
expect(input.query_params).toEqual({ databases: ['analytics', 'mart'] });
return result([
{ database: 'analytics', table: 'events', row_count: '2' },
{ database: 'mart', table: 'order_events', row_count: '5' },
]);
}
throw new Error(`Unexpected SQL: ${input.query}`);
});
return {
createClient: vi.fn(() => ({ query, close: vi.fn(async () => undefined) })),
};
}
2026-05-10 23:51:24 +02:00
describe('KtxClickHouseScanConnector', () => {
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 ClickHouse typed placeholders', () => {
expect(
prepareClickHouseReadOnlyQuery('select * from events where id = :id and event_name = :name', {
id: 10,
name: 'signup',
}),
).toEqual({
sql: 'select * from events where id = {id:Int64} and event_name = {name:String}',
params: { id: 10, name: 'signup' },
});
expect(
prepareClickHouseReadOnlyQuery('select * from events where enabled = :enabled and ratio = :ratio and created_at = :created_at', {
enabled: true,
ratio: 1.5,
created_at: new Date('2026-05-25T00:00:00.000Z'),
}),
).toEqual({
sql: 'select * from events where enabled = {enabled:Bool} and ratio = {ratio:Float64} and created_at = {created_at:DateTime}',
params: {
enabled: true,
ratio: 1.5,
created_at: new Date('2026-05-25T00:00:00.000Z'),
},
});
expect(prepareClickHouseReadOnlyQuery('select 1')).toEqual({ sql: 'select 1', params: undefined });
});
2026-05-10 23:12:26 +02:00
it('resolves ClickHouse connection configuration safely', () => {
2026-05-10 23:51:24 +02:00
expect(isKtxClickHouseConnectionConfig({ driver: 'clickhouse', host: 'localhost', database: 'analytics' })).toBe(
2026-05-10 23:12:26 +02:00
true,
);
2026-05-10 23:51:24 +02:00
expect(isKtxClickHouseConnectionConfig({ driver: 'mysql', host: 'localhost', database: 'analytics' })).toBe(false);
2026-05-10 23:12:26 +02:00
expect(
clickHouseClientConfigFromConfig({
connectionId: 'warehouse',
connection: {
driver: 'clickhouse',
host: 'ch.example.test',
port: 9440,
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
ssl: true,
},
}),
).toMatchObject({
host: 'ch.example.test',
port: 9440,
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
ssl: true,
});
});
it('introspects schema, primary keys, comments, row counts, and views', async () => {
2026-05-10 23:51:24 +02:00
const connector = new KtxClickHouseScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: {
driver: 'clickhouse',
host: 'ch.example.test',
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
},
clientFactory: fakeClientFactory(),
now: () => new Date('2026-04-29T14:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'clickhouse' },
{ runId: 'scan-run-1' },
);
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
driver: 'clickhouse',
extractedAt: '2026-04-29T14:00:00.000Z',
scope: { schemas: ['analytics'] },
metadata: {
database: 'analytics',
host: 'ch.example.test',
table_count: 2,
total_columns: 3,
},
});
expect(snapshot.tables.map((table) => [table.name, table.kind, table.estimatedRows, table.comment])).toEqual([
['event_summary', 'view', null, null],
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
['events', 'table', 2, 'Event stream'],
2026-05-10 23:12:26 +02:00
]);
expect(snapshot.tables.find((table) => table.name === 'events')?.columns[0]).toMatchObject({
name: 'id',
nativeType: 'UInt64',
normalizedType: 'UInt64',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'PK',
});
expect(snapshot.tables.find((table) => table.name === 'events')?.foreignKeys).toEqual([]);
});
it('introspects every configured ClickHouse database scope while preserving the default database', async () => {
const connector = new KtxClickHouseScanConnector({
connectionId: 'warehouse',
connection: {
driver: 'clickhouse',
host: 'ch.example.test',
database: 'analytics',
databases: ['analytics', 'mart'],
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
},
clientFactory: multiDatabaseClickHouseClientFactory(),
now: () => new Date('2026-05-21T10:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'clickhouse' },
{ runId: 'scan-run-1' },
);
expect(snapshot.scope).toEqual({ schemas: ['analytics', 'mart'] });
expect(snapshot.metadata).toMatchObject({ database: 'analytics', databases: ['analytics', 'mart'] });
expect(snapshot.tables.map((table) => `${table.db}.${table.name}`)).toEqual([
'analytics.events',
'mart.order_events',
]);
});
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<{ query: string; query_params?: Record<string, unknown> }> = [];
const clientFactory: KtxClickHouseClientFactory = {
createClient: vi.fn(() => ({
query: vi.fn(async (input: { query: string; format: string; query_params?: Record<string, unknown> }) => {
queries.push({ query: input.query, query_params: input.query_params });
if (input.query.includes('FROM system.tables')) {
return result([{ database: 'analytics', name: 'events', engine: 'MergeTree', comment: '' }]);
}
if (input.query.includes('FROM system.columns')) {
return result([
{
database: 'analytics',
table: 'events',
name: 'id',
type: 'UInt64',
comment: '',
is_in_primary_key: 1,
},
]);
}
if (input.query.includes('FROM system.parts')) {
return result([{ database: 'analytics', table: 'events', row_count: '2' }]);
}
throw new Error(`Unexpected SQL: ${input.query}`);
}),
close: vi.fn(async () => undefined),
})),
};
const connector = new KtxClickHouseScanConnector({
connectionId: 'warehouse',
connection: {
driver: 'clickhouse',
host: 'ch.example.test',
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
},
clientFactory,
});
const scope = tableRefSet([{ catalog: null, db: 'analytics', name: 'events' }]);
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'clickhouse', tableScope: scope },
{ runId: 'scope-test' },
);
expect(snapshot.tables.map((table) => table.name)).toEqual(['events']);
const tablesQuery = queries.find((query) => query.query.includes('FROM system.tables'));
expect(tablesQuery?.query).toContain('AND name IN {table_names:Array(String)}');
expect(tablesQuery?.query_params).toEqual({ databases: ['analytics'], table_names: ['events'] });
});
2026-05-10 23:12:26 +02:00
it('runs samples, distinct values, read-only SQL, row count, schema list, and cleanup', async () => {
const clientFactory = fakeClientFactory();
2026-05-10 23:51:24 +02:00
const connector = new KtxClickHouseScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: {
driver: 'clickhouse',
host: 'ch.example.test',
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
},
clientFactory,
});
await expect(
connector.sampleTable(
{
connectionId: 'warehouse',
table: { catalog: null, db: 'analytics', name: 'events' },
columns: ['id', 'event_name'],
limit: 1,
},
{ runId: 'scan-run-1' },
),
).resolves.toEqual({ headers: ['id', 'event_name'], rows: [[10, 'signup']], totalRows: 1 });
await expect(
connector.sampleColumn(
{ connectionId: 'warehouse', table: { catalog: null, db: 'analytics', name: 'events' }, column: 'event_name', limit: 5 },
{ runId: 'scan-run-1' },
),
).resolves.toMatchObject({ values: ['signup', 'purchase'], nullCount: null, distinctCount: null });
await expect(
connector.getColumnDistinctValues(
{ catalog: null, db: 'analytics', name: 'events' },
'event_name',
{ maxCardinality: 5, limit: 10, sampleSize: 100 },
),
).resolves.toEqual({ values: ['purchase', 'signup'], cardinality: 2 });
await expect(
connector.executeReadOnly(
{ connectionId: 'warehouse', sql: 'select id, event_name from analytics.events', maxRows: 1 },
{ runId: 'scan-run-1' },
),
).resolves.toMatchObject({ headers: ['id', 'event_name'], rows: [[10, 'signup']], totalRows: 1, rowCount: 1 });
await expect(
connector.executeReadOnly({ connectionId: 'warehouse', sql: 'delete from events' }, { runId: 'scan-run-1' }),
).rejects.toThrow('Only read-only SELECT/WITH queries can be executed locally');
await expect(connector.getTableRowCount('events')).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: 'event_summary', kind: 'view' },
{ catalog: null, schema: 'analytics', name: 'events', kind: 'table' },
]);
2026-05-10 23:12:26 +02:00
await expect(
connector.columnStats(
{ connectionId: 'warehouse', table: { catalog: null, db: 'analytics', name: 'events' }, column: 'event_name' },
{ runId: 'scan-run-1' },
),
).resolves.toBeNull();
await connector.cleanup();
});
it('adapts native ClickHouse snapshots to live-database introspection for local ingest', async () => {
const introspection = createClickHouseLiveDatabaseIntrospection({
connections: {
warehouse: {
driver: 'clickhouse',
host: 'ch.example.test',
database: 'analytics',
username: 'reader',
password: 'test-pass', // pragma: allowlist secret
},
},
clientFactory: fakeClientFactory(),
now: () => new Date('2026-04-29T14:00:00.000Z'),
});
const snapshot = await introspection.extractSchema('warehouse');
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
extractedAt: '2026-04-29T14:00:00.000Z',
});
expect(snapshot.tables.find((table) => table.name === 'events')).toMatchObject({
name: 'events',
catalog: null,
db: 'analytics',
columns: [
{
name: 'id',
nativeType: 'UInt64',
normalizedType: 'UInt64',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'PK',
},
{
name: 'event_name',
nativeType: 'LowCardinality(String)',
normalizedType: 'LowCardinality(String)',
dimensionType: 'string',
nullable: false,
primaryKey: false,
comment: null,
},
],
foreignKeys: [],
});
});
});