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

285 lines
9.7 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import Database from 'better-sqlite3';
import { writeFileSync } from 'node:fs';
import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, describe, expect, it } 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 { createSqliteLiveDatabaseIntrospection } from '../../../src/connectors/sqlite/live-database-introspection.js';
import { isKtxSqliteConnectionConfig, KtxSqliteScanConnector, sqliteDatabasePathFromConfig } from '../../../src/connectors/sqlite/connector.js';
import { tableRefSet } from '../../../src/context/scan/table-ref.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('KtxSqliteScanConnector', () => {
2026-05-10 23:12:26 +02:00
let tempDir: string;
let dbPath: string;
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-connector-sqlite-'));
2026-05-10 23:12:26 +02:00
dbPath = join(tempDir, 'warehouse.db');
const db = new Database(dbPath);
db.exec(`
PRAGMA foreign_keys = ON;
CREATE TABLE customers (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
tier TEXT
);
CREATE TABLE orders (
id INTEGER PRIMARY KEY,
customer_id INTEGER NOT NULL,
status TEXT,
total NUMERIC,
created_at TEXT,
FOREIGN KEY(customer_id) REFERENCES customers(id)
);
CREATE VIEW recent_orders AS SELECT id, customer_id, status FROM orders;
INSERT INTO customers (id, name, tier) VALUES (1, 'Ada', 'enterprise'), (2, 'Grace', 'growth');
INSERT INTO orders (id, customer_id, status, total, created_at)
VALUES (10, 1, 'paid', 42.5, '2026-04-28'), (11, 2, 'open', 9.5, '2026-04-29');
`);
db.close();
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('resolves SQLite path configuration safely', () => {
2026-05-10 23:51:24 +02:00
const originalDatabaseUrl = process.env.KTX_SQLITE_TEST_URL;
2026-05-10 23:12:26 +02:00
const pointerPath = join(tempDir, 'sqlite-path.txt');
2026-05-10 23:51:24 +02:00
process.env.KTX_SQLITE_TEST_URL = `sqlite:${dbPath}`;
2026-05-10 23:12:26 +02:00
writeFileSync(pointerPath, dbPath, 'utf-8');
try {
expect(isKtxSqliteConnectionConfig({ driver: 'sqlite', path: 'warehouse.db' })).toBe(true);
expect(isKtxSqliteConnectionConfig({ driver: 'postgres', url: 'env:DATABASE_URL' })).toBe(false);
2026-05-10 23:12:26 +02:00
expect(
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', path: 'warehouse.db' },
2026-05-10 23:12:26 +02:00
}),
).toBe(dbPath);
expect(
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', url: 'env:KTX_SQLITE_TEST_URL' },
2026-05-10 23:12:26 +02:00
}),
).toBe(dbPath);
expect(
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', url: `file://${dbPath}` },
2026-05-10 23:12:26 +02:00
}),
).toBe(dbPath);
expect(
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', path: `file:${pointerPath}` },
2026-05-10 23:12:26 +02:00
}),
).toBe(dbPath);
expect(
2026-05-10 23:12:26 +02:00
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', path: 'warehouse.db' },
2026-05-10 23:12:26 +02:00
}),
).toBe(dbPath);
expect(() =>
sqliteDatabasePathFromConfig({
connectionId: 'warehouse',
projectDir: tempDir,
connection: { driver: 'sqlite', file_path: 'warehouse.db' },
}),
).toThrow('Native SQLite connector requires connections.warehouse.path or url');
2026-05-10 23:12:26 +02:00
} finally {
if (originalDatabaseUrl === undefined) {
2026-05-10 23:51:24 +02:00
delete process.env.KTX_SQLITE_TEST_URL;
2026-05-10 23:12:26 +02:00
} else {
2026-05-10 23:51:24 +02:00
process.env.KTX_SQLITE_TEST_URL = originalDatabaseUrl;
2026-05-10 23:12:26 +02:00
}
}
});
it('introspects schema, primary keys, row counts, views, and foreign keys', async () => {
2026-05-10 23:51:24 +02:00
const connector = new KtxSqliteScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: { driver: 'sqlite', path: dbPath },
2026-05-10 23:12:26 +02:00
now: () => new Date('2026-04-29T10:00:00.000Z'),
});
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'sqlite' },
{ runId: 'scan-run-1' },
);
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
driver: 'sqlite',
extractedAt: '2026-04-29T10:00:00.000Z',
metadata: {
file_path: dbPath,
table_count: 3,
total_columns: 11,
},
});
expect(snapshot.tables.map((table) => [table.name, table.kind, table.estimatedRows])).toEqual([
['customers', 'table', 2],
['orders', 'table', 2],
['recent_orders', 'view', null],
]);
expect(snapshot.tables.find((table) => table.name === 'customers')?.columns[0]).toMatchObject({
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'INTEGER',
dimensionType: 'number',
nullable: false,
primaryKey: true,
});
expect(snapshot.tables.find((table) => table.name === 'orders')?.foreignKeys).toEqual([
{
fromColumn: 'customer_id',
toCatalog: null,
toDb: null,
toTable: 'customers',
toColumn: 'id',
constraintName: 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
it('lists schemaless tables and views for setup discovery', async () => {
const connector = new KtxSqliteScanConnector({
connectionId: 'warehouse',
connection: { driver: 'sqlite', path: dbPath },
});
await expect(connector.listSchemas()).resolves.toEqual([]);
await expect(connector.listTables(['ignored'])).resolves.toEqual([
{ catalog: null, schema: '', name: 'customers', kind: 'table' },
{ catalog: null, schema: '', name: 'orders', kind: 'table' },
{ catalog: null, schema: '', name: 'recent_orders', kind: 'view' },
]);
});
2026-05-10 23:12:26 +02:00
it('runs samples, distinct values, statistics, and read-only SQL', async () => {
2026-05-10 23:51:24 +02:00
const connector = new KtxSqliteScanConnector({
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
connection: { driver: 'sqlite', path: dbPath },
2026-05-10 23:12:26 +02:00
});
await expect(
connector.sampleTable(
{ connectionId: 'warehouse', table: { catalog: null, db: null, name: 'orders' }, columns: ['id'], limit: 1 },
{ runId: 'scan-run-1' },
),
).resolves.toEqual({ headers: ['id'], rows: [[10]], totalRows: 1 });
await expect(
connector.sampleColumn(
{ connectionId: 'warehouse', table: { catalog: null, db: null, 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: null, 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 orders order by id', maxRows: 1 },
{ runId: 'scan-run-1' },
),
).resolves.toEqual({ 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.columnStats(
{ connectionId: 'warehouse', table: { catalog: null, db: null, name: 'orders' }, column: 'status' },
{ runId: 'scan-run-1' },
),
).resolves.toBeNull();
});
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 connector = new KtxSqliteScanConnector({
connectionId: 'warehouse',
connection: { driver: 'sqlite', path: dbPath },
});
const scope = tableRefSet([{ catalog: null, db: null, name: 'orders' }]);
const snapshot = await connector.introspect(
{ connectionId: 'warehouse', driver: 'sqlite', tableScope: scope },
{ runId: 'scope-test' },
);
expect(snapshot.tables.map((table) => table.name)).toEqual(['orders']);
});
2026-05-10 23:12:26 +02:00
it('adapts native SQLite snapshots to live-database introspection for local ingest', async () => {
const introspection = createSqliteLiveDatabaseIntrospection({
projectDir: tempDir,
connections: {
warehouse: { driver: 'sqlite', path: 'warehouse.db' },
2026-05-10 23:12:26 +02:00
},
now: () => new Date('2026-04-29T10:00:00.000Z'),
});
const snapshot = await introspection.extractSchema('warehouse');
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
extractedAt: '2026-04-29T10:00:00.000Z',
});
expect(snapshot.tables.find((table) => table.name === 'customers')).toMatchObject({
name: 'customers',
catalog: null,
db: null,
columns: [
{
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'INTEGER',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: null,
},
{
name: 'name',
nativeType: 'TEXT',
normalizedType: 'TEXT',
dimensionType: 'string',
nullable: false,
primaryKey: false,
comment: null,
},
{
name: 'tier',
nativeType: 'TEXT',
normalizedType: 'TEXT',
dimensionType: 'string',
nullable: true,
primaryKey: false,
comment: null,
},
],
foreignKeys: [],
});
expect(snapshot.tables.find((table) => table.name === 'orders')).toMatchObject({
name: 'orders',
catalog: null,
db: null,
foreignKeys: [{ fromColumn: 'customer_id', toTable: 'customers', toColumn: 'id' }],
});
});
});