ktx/packages/cli/test/context/ingest/historic-sql-probes.test.ts

158 lines
5 KiB
TypeScript
Raw Permalink Normal View History

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 type { HistoricSqlDialect } from '../../../src/context/ingest/adapters/historic-sql/types.js';
import {
historicSqlProbeCatalogName,
runHistoricSqlReadinessProbe,
type HistoricSqlProbeRunner,
type HistoricSqlProbeRunnerFactoryEntry,
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
} from '../../../src/context/ingest/historic-sql-probes.js';
function fakeRunner(
dialect: HistoricSqlDialect,
catalogName: string,
options: { result?: unknown; error?: unknown } = {},
): HistoricSqlProbeRunner & { runCalls: () => number } {
let calls = 0;
return {
dialect,
catalogName,
async run() {
calls += 1;
if (options.error) {
throw options.error;
}
return options.result ?? { warnings: [], info: [] };
},
formatSuccessDetail() {
return { detail: `${catalogName} ready`, warnings: [] };
},
fixAdvice(error) {
return {
failHeadline: error instanceof Error ? error.message : String(error),
remediation: 'Fix the test probe.',
};
},
runCalls: () => calls,
};
}
function factories(
overrides: Partial<Record<HistoricSqlDialect, HistoricSqlProbeRunner>>,
): Record<HistoricSqlDialect, HistoricSqlProbeRunnerFactoryEntry> {
const postgres = overrides.postgres ?? fakeRunner('postgres', 'pg_stat_statements');
const snowflake =
overrides.snowflake ??
fakeRunner('snowflake', 'SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY');
const bigquery =
overrides.bigquery ?? fakeRunner('bigquery', 'INFORMATION_SCHEMA.JOBS_BY_PROJECT');
return {
postgres: {
catalogName: 'pg_stat_statements',
load: vi.fn(async () => postgres),
},
snowflake: {
catalogName: 'SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY',
load: vi.fn(async () => snowflake),
},
bigquery: {
catalogName: 'INFORMATION_SCHEMA.JOBS_BY_PROJECT',
load: vi.fn(async () => bigquery),
},
};
}
describe('historic-SQL probe registry', () => {
it('returns null when the connection has no query-history dialect', async () => {
const deps = { factories: factories({}), cache: new Map() };
await expect(
runHistoricSqlReadinessProbe(
{
projectDir: '/work/project',
connectionId: 'mysql',
connection: {
driver: 'mysql',
context: { queryHistory: { enabled: true } },
},
env: {},
},
deps,
),
).resolves.toBeNull();
expect(deps.factories.postgres.load).not.toHaveBeenCalled();
expect(deps.factories.snowflake.load).not.toHaveBeenCalled();
expect(deps.factories.bigquery.load).not.toHaveBeenCalled();
});
it('dispatches to the dialect runner and caches the runner instance', async () => {
const runner = fakeRunner('postgres', 'pg_stat_statements', {
result: { pgServerVersion: 'PostgreSQL 16.4', warnings: [], info: [] },
});
const deps = { factories: factories({ postgres: runner }), cache: new Map() };
const input = {
projectDir: '/work/project',
connectionId: 'warehouse',
connection: {
driver: 'postgres' as const,
url: 'env:DATABASE_URL',
context: { queryHistory: { enabled: true } },
},
env: {},
};
const first = await runHistoricSqlReadinessProbe(input, deps);
const second = await runHistoricSqlReadinessProbe(input, deps);
expect(first).toMatchObject({ ok: true, dialect: 'postgres', runner });
expect(second).toMatchObject({ ok: true, dialect: 'postgres', runner });
expect(deps.factories.postgres.load).toHaveBeenCalledTimes(1);
expect(runner.runCalls()).toBe(2);
});
it('normalizes runner errors into a failed outcome', async () => {
const error = new Error('missing grants');
const runner = fakeRunner('bigquery', 'INFORMATION_SCHEMA.JOBS_BY_PROJECT', {
error,
});
const deps = { factories: factories({ bigquery: runner }), cache: new Map() };
await expect(
runHistoricSqlReadinessProbe(
{
projectDir: '/work/project',
connectionId: 'bq',
connection: {
driver: 'bigquery',
credentials_json: '{"project_id":"project-1"}',
context: { queryHistory: { enabled: true } },
},
env: {},
},
deps,
),
).resolves.toEqual({
ok: false,
dialect: 'bigquery',
runner,
error,
});
});
it('returns catalog names without loading runner modules', () => {
const deps = { factories: factories({}), cache: new Map() };
expect(historicSqlProbeCatalogName('postgres', deps)).toBe('pg_stat_statements');
expect(historicSqlProbeCatalogName('snowflake', deps)).toBe(
'SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY',
);
expect(historicSqlProbeCatalogName('bigquery', deps)).toBe(
'INFORMATION_SCHEMA.JOBS_BY_PROJECT',
);
expect(deps.factories.postgres.load).not.toHaveBeenCalled();
expect(deps.factories.snowflake.load).not.toHaveBeenCalled();
expect(deps.factories.bigquery.load).not.toHaveBeenCalled();
});
});