2026-05-15 00:08:11 +02:00
|
|
|
import { 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 { connectionConfigSchema } from '../../../src/context/project/driver-schemas.js';
|
2026-05-15 00:08:11 +02:00
|
|
|
|
|
|
|
|
describe('connectionConfigSchema (driver discriminated union)', () => {
|
|
|
|
|
it.each([
|
|
|
|
|
['postgres', 'postgres://user:pass@host:5432/db'], // pragma: allowlist secret
|
|
|
|
|
['mysql', 'mysql://user:pass@host:3306/db'], // pragma: allowlist secret
|
|
|
|
|
['snowflake', 'snowflake://account/db'],
|
|
|
|
|
['bigquery', 'bigquery://project/dataset'],
|
|
|
|
|
['sqlite', 'sqlite:///tmp/db.sqlite'],
|
|
|
|
|
['clickhouse', 'clickhouse://host:8123/db'],
|
|
|
|
|
['sqlserver', 'sqlserver://host:1433;database=db'],
|
|
|
|
|
])('parses %s warehouse connection', (driver, url) => {
|
|
|
|
|
expect(connectionConfigSchema.parse({ driver, url })).toMatchObject({ driver, url });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('preserves unknown warehouse fields via looseObject passthrough', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'postgres',
|
|
|
|
|
url: 'postgres://x',
|
2026-05-24 01:00:20 +02:00
|
|
|
customField: { enabled: true },
|
2026-05-15 00:08:11 +02:00
|
|
|
context: { queryHistory: { enabled: false } },
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'postgres',
|
2026-05-24 01:00:20 +02:00
|
|
|
customField: { enabled: true },
|
2026-05-15 00:08:11 +02:00
|
|
|
context: { queryHistory: { enabled: false } },
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
feat(connectors): add MongoDB connector (#305) (#310)
* refactor(connectors): split KtxDialect into core and KtxSqlDialect
Separate the dialect contract into a driver-agnostic core (display/ref
formatting and type mapping) and a SQL-only extension (query generators).
The catalog and entity-details paths resolve the core dialect for any
snapshot driver, so it must stay free of SQL generation; this is the
prerequisite refactor for adding non-SQL primary sources.
- KtxDialect keeps type, formatDisplayRef, parseDisplayRef,
columnDisplayTablePartCount, mapDataType, mapToDimensionType
- KtxSqlDialect extends it with quoteIdentifier, formatTableName, and the
query/sample/statistics generators; the 7 SQL dialects implement it
- add getSqlDialectForDriver for SQL drivers; the 7 connectors and the
relationship-benchmark harness consume it
- thread the relationship pipeline (profiling/validation/composite/
discovery) as KtxSqlDialect | null so a non-SQL source skips coverage SQL
and its candidates stay in review; local-enrichment builds the SQL
dialect only when the connector advertises readOnlySql
Pure extraction: no behavior change for the existing 7 drivers.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(connectors): add MongoDB connector for issue #305
Add a read-only MongoDB connector that treats a database as a primary
context source: collections map to tables and inferred top-level fields to
columns. MongoDB is the first non-SQL source (readOnlySql: false), so
ktx sql and metric compilation do not apply, but its collections flow
through ingest, descriptions, and relationship discovery.
- schema-inference: infer a flat column schema from the most recent
sample_size documents (by _id desc, or order_by for non-ObjectId keys).
Union BSON types per field, mark multi-type fields mixed (string), keep
sub-documents/arrays as a single opaque json column, derive nullability
from presence, treat _id as the primary key
- connector: KtxMongoDbScanConnector behind an injectable client seam;
strictly read-only (find/listCollections/estimatedDocumentCount only),
no executeReadOnly; resolves env:/file: via resolveKtxConfigReference
- core-only KtxMongoDbDialect and a live-database introspection adapter
- wire the mongodb driver: driver union, dialect registry, driver
registration (scopeConfigKey databases), mongodbConnectionSchema,
connection-drivers, normalizeDriver, the live-database route, and the
ktx setup picker. ktx sql is refused by the read-only SQL capability gate
- tests: schema inference, connector snapshot via a fake client, dialect,
driver-schema parsing, and the ktx sql rejection
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(integrations): document the MongoDB primary source
Add a MongoDB section to the primary-sources reference: connection config
(url, databases, enabled_tables, sample_size, order_by), mongodb+srv/TLS/
Atlas notes, the schema-inference explainer, a features matrix, and the
non-SQL caveat. Update the frontmatter and connection field reference.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(connectors): address review blockers on the MongoDB connector
- introspect: skip estimatedDocumentCount for views. The count command is
rejected on a MongoDB view (CommandNotSupportedOnView), so counting a view
aborted introspect for the whole connection; compute estimatedRows only for
real collections, as ClickHouse does.
- sl: refuse a semantic-layer query against a non-SQL connection instead of
defaulting it to the Postgres dialect. compileLocalSlQuery (the shared CLI +
MCP path) now rejects a driver with no SQL dialect via the new
isSqlQueryableDriver authority, keeping MongoDB context-only per issue #305.
- tests: cover input.tableScope and the empty-scope skip for the Mongo
connector (the scan layer does not post-filter), the view no-count path, and
the ktx sl query refusal for a mongodb connection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* polish(mongodb): compute sampled nullCount and document sampling caveats
Address the non-blocking review notes:
- sampleColumn now counts null/absent values over the sampled window instead of
returning nullCount: null, since the documents are already in hand
- warn that a custom order_by must be indexed (an unindexed sort hits MongoDB's
in-memory sort limit on large collections) in the connection schema and docs
- note that sampled values for nested fields are stringified, not faithfully
serialized, so the json opacity is deliberate
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(examples): add a MongoDB connector example
A manual, container-backed example mirroring examples/postgres-historic:
- docker-compose.yml + init/seed.js seed a representative dataset (nested
documents, arrays, a Decimal128, a mixed-type field, a nullable field, an
ObjectId reference, and a view) on first container start
- scripts/smoke.sh + introspect-smoke.mjs assert the connector's inferred
schema with no LLM credentials — the same introspection entry point ktx
ingest's database-schema stage uses, including the view-no-count path
- README.md documents the smoke and a full keyless ktx ingest run
(claude-code LLM + managed sentence-transformers embeddings)
Works with Docker Compose or podman compose. Verified end to end.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: ignore examples/** in knip to fix dead-code false positives
The MongoDB connector example files (examples/mongodb/init/seed.js and
examples/mongodb/scripts/introspect-smoke.mjs) are used at runtime but were
flagged as unused by knip. Add examples/** to the ignore array, matching the
existing .context/** entry.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0114qQV8fJ5a5ME3XbMVRzbL
* fix(mongodb): refuse non-SQL connections before SQL analysis
`ktx sql` and the MCP sql_execution tool resolved a SQL-analysis dialect
(falling back to Postgres for a non-SQL driver) and ran read-only
validation before the connector capability gate refused the connection.
For a MongoDB connection that spun up the parser/daemon and produced
Postgres parser diagnostics instead of a clean non-SQL refusal.
Route both entry points through a shared assertSqlQueryableConnection
guard before dialect selection, mirroring compileLocalSlQuery. The
federated duckdb path has no driver and is exempted at each call site.
Add CLI and MCP regression tests asserting validation/connector work
never starts for a MongoDB connection.
* fix(mongodb): pass CI gates (dialect boundary, secrets, setup test)
Three latent failures in the connector surfaced once CI ran on the branch:
- connector.ts imported the concrete KtxMongoDbDialect, which the connector
dialect-import boundary forbids. Route it through getDialectForDriver('mongodb')
and widen inferKtxMongoCollectionColumns to the base KtxDialect (it only uses
mapDataType/mapToDimensionType).
- detect-secrets flagged a test ObjectId hex and the mongodb+srv example URL;
annotate both with allowlist pragmas.
- the "shows every supported database" setup test omitted the new MongoDB option.
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Luca Martial <48870843+luca-martial@users.noreply.github.com>
Co-authored-by: Luca Martial <lucamrtl@gmail.com>
Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-06-29 15:17:56 +02:00
|
|
|
it('parses a mongodb connection with sampling fields', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'mongodb',
|
|
|
|
|
url: 'env:MONGO_URL',
|
|
|
|
|
databases: ['app'],
|
|
|
|
|
enabled_tables: ['app.users'],
|
|
|
|
|
sample_size: 500,
|
|
|
|
|
order_by: 'createdAt',
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'mongodb',
|
|
|
|
|
url: 'env:MONGO_URL',
|
|
|
|
|
databases: ['app'],
|
|
|
|
|
sample_size: 500,
|
|
|
|
|
order_by: 'createdAt',
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects a mongodb connection without a url', () => {
|
|
|
|
|
expect(() => connectionConfigSchema.parse({ driver: 'mongodb', databases: ['app'] })).toThrow();
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-15 00:08:11 +02:00
|
|
|
it('rejects an unknown driver', () => {
|
|
|
|
|
expect(() => connectionConfigSchema.parse({ driver: 'nope', url: 'x' })).toThrow();
|
|
|
|
|
});
|
2026-05-24 16:57:23 +02:00
|
|
|
|
|
|
|
|
it('rejects legacy warehouse driver aliases', () => {
|
|
|
|
|
expect(() => connectionConfigSchema.parse({ driver: 'postgresql', url: 'postgresql://host/db' })).toThrow();
|
|
|
|
|
});
|
2026-05-15 00:08:11 +02:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('connectionConfigSchema - context source drivers with mappings', () => {
|
|
|
|
|
it('parses a metabase connection with mappings', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'metabase',
|
|
|
|
|
api_url: 'https://metabase.example.com',
|
|
|
|
|
api_key_ref: 'env:METABASE_API_KEY', // pragma: allowlist secret
|
|
|
|
|
mappings: {
|
|
|
|
|
databaseMappings: { '3': 'prod-warehouse' },
|
|
|
|
|
syncEnabled: { '3': true },
|
|
|
|
|
syncMode: 'ONLY',
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'metabase',
|
|
|
|
|
api_url: 'https://metabase.example.com',
|
|
|
|
|
mappings: {
|
|
|
|
|
databaseMappings: { '3': 'prod-warehouse' },
|
|
|
|
|
syncMode: 'ONLY',
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('parses a looker connection with connectionMappings', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'looker',
|
|
|
|
|
base_url: 'https://looker.example.com',
|
|
|
|
|
client_id: 'abc',
|
|
|
|
|
client_secret_ref: 'env:LOOKER_CLIENT_SECRET', // pragma: allowlist secret
|
|
|
|
|
mappings: { connectionMappings: { bigquery_prod: 'wh' } },
|
|
|
|
|
});
|
|
|
|
|
expect(parsed.mappings).toEqual({ connectionMappings: { bigquery_prod: 'wh' } });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('parses a lookml connection with expectedLookerConnectionName', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'lookml',
|
|
|
|
|
repoUrl: 'https://github.com/acme/looker.git',
|
|
|
|
|
branch: 'main',
|
|
|
|
|
mappings: { expectedLookerConnectionName: 'bigquery_prod' },
|
|
|
|
|
});
|
|
|
|
|
expect(parsed.mappings).toEqual({ expectedLookerConnectionName: 'bigquery_prod' });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects metabase mapping with non-integer database key', () => {
|
|
|
|
|
expect(() =>
|
|
|
|
|
connectionConfigSchema.parse({
|
|
|
|
|
driver: 'metabase',
|
|
|
|
|
api_url: 'https://x',
|
|
|
|
|
mappings: { databaseMappings: { abc: 'wh' } },
|
|
|
|
|
}),
|
|
|
|
|
).toThrow();
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-06-27 14:41:32 -07:00
|
|
|
describe('connectionConfigSchema - notion / gdrive / dbt / metricflow', () => {
|
2026-05-15 00:08:11 +02:00
|
|
|
it('parses a notion connection with selected_roots crawl', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'notion',
|
|
|
|
|
auth_token_ref: 'env:NOTION_TOKEN',
|
|
|
|
|
crawl_mode: 'selected_roots',
|
|
|
|
|
root_page_ids: ['abc', 'def'],
|
|
|
|
|
max_pages_per_run: 500,
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'notion',
|
|
|
|
|
crawl_mode: 'selected_roots',
|
|
|
|
|
root_page_ids: ['abc', 'def'],
|
|
|
|
|
max_pages_per_run: 500,
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects notion with unknown crawl_mode', () => {
|
|
|
|
|
expect(() =>
|
|
|
|
|
connectionConfigSchema.parse({
|
|
|
|
|
driver: 'notion',
|
|
|
|
|
auth_token_ref: 'env:NOTION_TOKEN',
|
|
|
|
|
crawl_mode: 'everything',
|
|
|
|
|
}),
|
|
|
|
|
).toThrow();
|
|
|
|
|
});
|
|
|
|
|
|
2026-06-27 14:41:32 -07:00
|
|
|
it('parses a gdrive connection', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'gdrive',
|
|
|
|
|
service_account_key_ref: 'file:/tmp/google-service-account.json', // pragma: allowlist secret
|
|
|
|
|
folder_id: 'folder-123',
|
|
|
|
|
recursive: true,
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'gdrive',
|
|
|
|
|
service_account_key_ref: 'file:/tmp/google-service-account.json', // pragma: allowlist secret
|
|
|
|
|
folder_id: 'folder-123',
|
|
|
|
|
recursive: true,
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-15 00:08:11 +02:00
|
|
|
it('parses a dbt connection from a local source_dir', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'dbt',
|
|
|
|
|
source_dir: '/tmp/dbt-project',
|
|
|
|
|
target: 'dev',
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({ driver: 'dbt', source_dir: '/tmp/dbt-project', target: 'dev' });
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('parses a metricflow connection with nested config', () => {
|
|
|
|
|
const parsed = connectionConfigSchema.parse({
|
|
|
|
|
driver: 'metricflow',
|
|
|
|
|
metricflow: {
|
|
|
|
|
repoUrl: 'https://github.com/acme/sl.git',
|
|
|
|
|
branch: 'main',
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
expect(parsed).toMatchObject({
|
|
|
|
|
driver: 'metricflow',
|
|
|
|
|
metricflow: { repoUrl: 'https://github.com/acme/sl.git' },
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
});
|