ktx/packages/cli/test/context/sl/local-query.test.ts

416 lines
13 KiB
TypeScript
Raw Normal View History

2026-05-10 23:12:26 +02:00
import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, 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 { KtxSemanticLayerComputePort } from '../../../src/context/daemon/semantic-layer-compute.js';
feat: query_policy semantic-layer-only restricts agents to predefined semantic-layer measures (#334) * feat(sl): add predefined_measures_only guard to semantic query planning SemanticQuery gains a predefined_measures_only flag; the planner rejects any measure resolved with Provenance.COMPOSED (runtime aggregate expressions and query-time derivations) while predefined measures, predefined derived chains, dimensions, filters, and segments pass. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(config): add per-connection query_policy to warehouse connections query_policy: semantic-layer-only | read-only-sql (default) on the warehouse connection schema, plus a policy module with the raw-SQL guard, federated member restriction lookup, and the project-level predicate used to gate sql_execution registration. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(cli): enforce query_policy on raw SQL through one shared executor ktx sql and the MCP sql_execution tool now share executeProjectRawSql (resolve, policy check, read-only validation, execute), collapsing their duplicated validate-then-execute paths. Restricted connections are rejected before validation; federated raw SQL is rejected when any member is restricted. sql_execution is not registered when every SQL connection is restricted, and connection_list marks restricted connections so agents route to sl_query. executeProjectReadOnlySql stays generic for ktx-internal SQL (scan, ingest, SL-generated). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(sl): compile queries with predefined_measures_only from query_policy compileLocalSlQuery injects the flag from the connection's query_policy, never from caller input, covering both ktx sl query and the MCP sl_query tool through the daemon compile path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: document query_policy semantic-layer-only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(sl): close semantic-layer-only bypasses via filters and federated hint The predefined_measures_only guard only inspected query.measures, so a composed aggregate written into `filters` slipped through _classify_filters into a HAVING clause untouched — letting a restricted agent evaluate arbitrary aggregates (e.g. threshold-probing `sum(x) BETWEEN a AND b`). Reject filter clauses that compose an aggregate function; a HAVING that compares a predefined measure by name (`orders.revenue > 100`) still works. Also make the federated sl_query error policy-aware: when a member is restricted, raw federated SQL is disabled too, so stop directing the agent to `ktx sql -c _ktx_federated` / sql_execution (a guaranteed failure) and point to per-connection semantic-layer queries instead. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-07-03 01:54:17 -07:00
import { FEDERATED_CONNECTION_ID } from '../../../src/context/connections/federation.js';
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 { initKtxProject, type KtxLocalProject } from '../../../src/context/project/project.js';
import { compileLocalSlQuery } from '../../../src/context/sl/local-query.js';
2026-05-10 23:12:26 +02:00
describe('compileLocalSlQuery', () => {
let tempDir: string;
2026-05-10 23:51:24 +02:00
let project: KtxLocalProject;
let compute: KtxSemanticLayerComputePort;
2026-05-10 23:12:26 +02:00
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-local-query-'));
project = await initKtxProject({ projectDir: join(tempDir, 'project') });
project.config.connections.warehouse = { driver: 'postgres' };
2026-05-10 23:12:26 +02:00
await project.fileStore.writeFile(
'semantic-layer/warehouse/orders.yaml',
`name: orders
table: public.orders
grain:
- id
columns:
- name: id
type: number
- name: status
type: string
measures:
- name: order_count
expr: count(*)
joins: []
`,
2026-05-10 23:51:24 +02:00
'ktx',
'ktx@example.com',
2026-05-10 23:12:26 +02:00
'Add orders source',
);
await project.fileStore.writeFile(
'semantic-layer/warehouse/orders_overlay.yaml',
`name: orders_overlay
inherits_columns_from: orders
columns:
- name: paid_at
type: timestamp
joins: []
measures: []
grain: []
`,
2026-05-10 23:51:24 +02:00
'ktx',
'ktx@example.com',
2026-05-10 23:12:26 +02:00
'Add overlay source',
);
compute = {
query: vi.fn(async (input) => ({
sql: 'select status, count(*) as order_count from public.orders group by status',
dialect: input.dialect,
columns: [{ name: 'orders.status' }, { name: 'orders.order_count' }],
plan: { measures: input.query.measures, dimensions: input.query.dimensions },
})),
validateSources: vi.fn(),
generateSources: vi.fn(),
};
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
feat: query_policy semantic-layer-only restricts agents to predefined semantic-layer measures (#334) * feat(sl): add predefined_measures_only guard to semantic query planning SemanticQuery gains a predefined_measures_only flag; the planner rejects any measure resolved with Provenance.COMPOSED (runtime aggregate expressions and query-time derivations) while predefined measures, predefined derived chains, dimensions, filters, and segments pass. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(config): add per-connection query_policy to warehouse connections query_policy: semantic-layer-only | read-only-sql (default) on the warehouse connection schema, plus a policy module with the raw-SQL guard, federated member restriction lookup, and the project-level predicate used to gate sql_execution registration. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(cli): enforce query_policy on raw SQL through one shared executor ktx sql and the MCP sql_execution tool now share executeProjectRawSql (resolve, policy check, read-only validation, execute), collapsing their duplicated validate-then-execute paths. Restricted connections are rejected before validation; federated raw SQL is rejected when any member is restricted. sql_execution is not registered when every SQL connection is restricted, and connection_list marks restricted connections so agents route to sl_query. executeProjectReadOnlySql stays generic for ktx-internal SQL (scan, ingest, SL-generated). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(sl): compile queries with predefined_measures_only from query_policy compileLocalSlQuery injects the flag from the connection's query_policy, never from caller input, covering both ktx sl query and the MCP sl_query tool through the daemon compile path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: document query_policy semantic-layer-only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(sl): close semantic-layer-only bypasses via filters and federated hint The predefined_measures_only guard only inspected query.measures, so a composed aggregate written into `filters` slipped through _classify_filters into a HAVING clause untouched — letting a restricted agent evaluate arbitrary aggregates (e.g. threshold-probing `sum(x) BETWEEN a AND b`). Reject filter clauses that compose an aggregate function; a HAVING that compares a predefined measure by name (`orders.revenue > 100`) still works. Also make the federated sl_query error policy-aware: when a member is restricted, raw federated SQL is disabled too, so stop directing the agent to `ktx sql -c _ktx_federated` / sql_execution (a guaranteed failure) and point to per-connection semantic-layer queries instead. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-07-03 01:54:17 -07:00
it('injects predefined_measures_only when the connection query_policy is semantic-layer-only', async () => {
project.config.connections.warehouse = { driver: 'postgres', query_policy: 'semantic-layer-only' };
await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: { measures: ['orders.order_count'], dimensions: [], limit: 10 },
compute,
});
expect(compute.query).toHaveBeenCalledWith(
expect.objectContaining({
query: expect.objectContaining({ predefined_measures_only: true }),
}),
);
});
it('rejects a federated sl_query, pointing to per-connection SL when a member is restricted', async () => {
project.config.connections.warehouse = { driver: 'postgres', query_policy: 'semantic-layer-only' };
project.config.connections.analytics = { driver: 'postgres' };
let message = '';
try {
await compileLocalSlQuery(project, {
connectionId: FEDERATED_CONNECTION_ID,
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
});
throw new Error('expected compileLocalSlQuery to reject');
} catch (e) {
message = (e as Error).message;
}
expect(message).toContain("member connection(s) 'warehouse'");
expect(message).toContain('query_policy: semantic-layer-only');
// Must not send the agent down the raw-SQL path that assertRawSqlAllowed rejects.
expect(message).not.toContain(`ktx sql -c ${FEDERATED_CONNECTION_ID}`);
expect(message).not.toContain('sql_execution');
expect(compute.query).not.toHaveBeenCalled();
});
it('rejects a federated sl_query, pointing to raw federated SQL when no member is restricted', async () => {
project.config.connections.analytics = { driver: 'postgres' };
await expect(
compileLocalSlQuery(project, {
connectionId: FEDERATED_CONNECTION_ID,
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
}),
).rejects.toThrow(`ktx sql -c ${FEDERATED_CONNECTION_ID}`);
expect(compute.query).not.toHaveBeenCalled();
});
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('refuses a non-SQL (context-only) connection instead of compiling it as Postgres', async () => {
project.config.connections['mongo-prod'] = { driver: 'mongodb', url: 'mongodb://localhost:27017/app' };
await expect(
compileLocalSlQuery(project, {
connectionId: 'mongo-prod',
query: { measures: ['orders.order_count'], dimensions: ['orders.status'], limit: 25 },
compute,
}),
).rejects.toThrow(/non-SQL driver 'mongodb'|require a SQL warehouse connection/);
expect(compute.query).not.toHaveBeenCalled();
});
2026-05-10 23:12:26 +02:00
it('compiles a local semantic-layer query with computable sources only', async () => {
const result = await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: {
measures: ['orders.order_count'],
dimensions: ['orders.status'],
limit: 25,
},
compute,
});
expect(compute.query).toHaveBeenCalledWith({
sources: [
{
name: 'orders',
table: 'public.orders',
grain: ['id'],
columns: [
{ name: 'id', type: 'number' },
{ name: 'status', type: 'string' },
],
measures: [{ name: 'order_count', expr: 'count(*)' }],
joins: [],
},
],
dialect: 'postgres',
query: {
measures: ['orders.order_count'],
dimensions: ['orders.status'],
limit: 25,
feat: query_policy semantic-layer-only restricts agents to predefined semantic-layer measures (#334) * feat(sl): add predefined_measures_only guard to semantic query planning SemanticQuery gains a predefined_measures_only flag; the planner rejects any measure resolved with Provenance.COMPOSED (runtime aggregate expressions and query-time derivations) while predefined measures, predefined derived chains, dimensions, filters, and segments pass. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(config): add per-connection query_policy to warehouse connections query_policy: semantic-layer-only | read-only-sql (default) on the warehouse connection schema, plus a policy module with the raw-SQL guard, federated member restriction lookup, and the project-level predicate used to gate sql_execution registration. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(cli): enforce query_policy on raw SQL through one shared executor ktx sql and the MCP sql_execution tool now share executeProjectRawSql (resolve, policy check, read-only validation, execute), collapsing their duplicated validate-then-execute paths. Restricted connections are rejected before validation; federated raw SQL is rejected when any member is restricted. sql_execution is not registered when every SQL connection is restricted, and connection_list marks restricted connections so agents route to sl_query. executeProjectReadOnlySql stays generic for ktx-internal SQL (scan, ingest, SL-generated). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(sl): compile queries with predefined_measures_only from query_policy compileLocalSlQuery injects the flag from the connection's query_policy, never from caller input, covering both ktx sl query and the MCP sl_query tool through the daemon compile path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: document query_policy semantic-layer-only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(sl): close semantic-layer-only bypasses via filters and federated hint The predefined_measures_only guard only inspected query.measures, so a composed aggregate written into `filters` slipped through _classify_filters into a HAVING clause untouched — letting a restricted agent evaluate arbitrary aggregates (e.g. threshold-probing `sum(x) BETWEEN a AND b`). Reject filter clauses that compose an aggregate function; a HAVING that compares a predefined measure by name (`orders.revenue > 100`) still works. Also make the federated sl_query error policy-aware: when a member is restricted, raw federated SQL is disabled too, so stop directing the agent to `ktx sql -c _ktx_federated` / sql_execution (a guaranteed failure) and point to per-connection semantic-layer queries instead. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-07-03 01:54:17 -07:00
predefined_measures_only: false,
2026-05-10 23:12:26 +02:00
},
});
expect(result).toEqual({
connectionId: 'warehouse',
dialect: 'postgres',
sql: 'select status, count(*) as order_count from public.orders group by status',
headers: ['orders.status', 'orders.order_count'],
rows: [],
totalRows: 0,
plan: {
measures: ['orders.order_count'],
dimensions: ['orders.status'],
execution: {
mode: 'compile_only',
reason: 'Local semantic-layer query compiled SQL but no data-source execution adapter is configured.',
},
},
});
});
it('compiles a local semantic-layer query from manifest-backed scan sources', async () => {
await project.fileStore.writeFile(
'semantic-layer/warehouse/_schema/public.yaml',
`tables:
payments:
table: public.payments
columns:
- name: payment_id
type: number
pk: true
- name: amount
type: number
`,
2026-05-10 23:51:24 +02:00
'ktx',
'ktx@example.com',
2026-05-10 23:12:26 +02:00
'Add manifest shard',
);
await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: {
measures: ['sum(payments.amount)'],
dimensions: [],
},
compute,
});
expect(compute.query).toHaveBeenLastCalledWith({
sources: expect.arrayContaining([
{
name: 'payments',
table: 'public.payments',
grain: ['payment_id'],
columns: [
{
name: 'payment_id',
type: 'number',
role: undefined,
descriptions: undefined,
constraints: undefined,
enum_values: undefined,
tests: undefined,
},
{
name: 'amount',
type: 'number',
role: undefined,
descriptions: undefined,
constraints: undefined,
enum_values: undefined,
tests: undefined,
},
],
joins: [],
measures: [],
},
]),
dialect: 'postgres',
query: {
measures: ['sum(payments.amount)'],
dimensions: [],
feat: query_policy semantic-layer-only restricts agents to predefined semantic-layer measures (#334) * feat(sl): add predefined_measures_only guard to semantic query planning SemanticQuery gains a predefined_measures_only flag; the planner rejects any measure resolved with Provenance.COMPOSED (runtime aggregate expressions and query-time derivations) while predefined measures, predefined derived chains, dimensions, filters, and segments pass. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(config): add per-connection query_policy to warehouse connections query_policy: semantic-layer-only | read-only-sql (default) on the warehouse connection schema, plus a policy module with the raw-SQL guard, federated member restriction lookup, and the project-level predicate used to gate sql_execution registration. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(cli): enforce query_policy on raw SQL through one shared executor ktx sql and the MCP sql_execution tool now share executeProjectRawSql (resolve, policy check, read-only validation, execute), collapsing their duplicated validate-then-execute paths. Restricted connections are rejected before validation; federated raw SQL is rejected when any member is restricted. sql_execution is not registered when every SQL connection is restricted, and connection_list marks restricted connections so agents route to sl_query. executeProjectReadOnlySql stays generic for ktx-internal SQL (scan, ingest, SL-generated). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(sl): compile queries with predefined_measures_only from query_policy compileLocalSlQuery injects the flag from the connection's query_policy, never from caller input, covering both ktx sl query and the MCP sl_query tool through the daemon compile path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: document query_policy semantic-layer-only Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(sl): close semantic-layer-only bypasses via filters and federated hint The predefined_measures_only guard only inspected query.measures, so a composed aggregate written into `filters` slipped through _classify_filters into a HAVING clause untouched — letting a restricted agent evaluate arbitrary aggregates (e.g. threshold-probing `sum(x) BETWEEN a AND b`). Reject filter clauses that compose an aggregate function; a HAVING that compares a predefined measure by name (`orders.revenue > 100`) still works. Also make the federated sl_query error policy-aware: when a member is restricted, raw federated SQL is disabled too, so stop directing the agent to `ktx sql -c _ktx_federated` / sql_execution (a guaranteed failure) and point to per-connection semantic-layer queries instead. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
2026-07-03 01:54:17 -07:00
predefined_measures_only: false,
2026-05-10 23:12:26 +02:00
},
});
});
feat(setup): add Claude Desktop target and MCP-first agent setup (#114) * feat(setup): add Claude Desktop target and MCP-first agent setup Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces the CLI-only agent install mode with MCP+analytics (default) and an optional admin CLI skill, renames the research skill to analytics, and lets interactive setup pick project vs global scope when every target supports it. Extracts a shared MCP server factory used by both HTTP and stdio entrypoints. * Add MCP agent client setup support * Polish setup output formatting * Add MCP tool polish design spec Design for slimming the MCP-registered surface from 25 to 11 tools, introducing memory_ingest, applying the per-tool polish kit (annotations, outputSchema, .describe(), in-band error wrapping, union-drift fixes, type-narrowed jsonToolResult), emitting progress notifications on sql_execution + sl_query, and refining the ktx-analytics SKILL.md to match. * Refine MCP tool polish design spec after adversarial review iteration 1 * Refine MCP tool polish design spec after adversarial review iteration 2 * Refine MCP tool polish design spec after adversarial review iteration 3 * refactor(context): rename memory capture service to ingest * feat(mcp): slim research tool surface * refactor(mcp): remove admin ports from server factory * refactor(cli): rename text ingest memory port * docs: update analytics skill for memory ingest * chore: verify mcp surface rename * Add MCP tool polish v1 surface change plan * feat(context): polish mcp tool metadata * fix(context): enforce resolved semantic layer compute sources * feat(context): emit mcp query progress stages * fix(context): keep mcp progress event internal * Add MCP tool polish v1 metadata & progress plan * Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
it('strips authoring-only fields (usage, inherits_columns_from) before sending sources to the daemon', async () => {
await project.fileStore.writeFile(
'semantic-layer/warehouse/_schema/public.yaml',
`tables:
invoices:
table: public.invoices
columns:
- name: invoice_id
type: number
pk: true
- name: amount
type: number
usage:
narrative: Activation policy windows table for invoice analytics.
frequencyTier: mid
commonFilters:
- amount
commonGroupBys: []
commonJoins: []
staleSince: null
`,
'ktx',
'ktx@example.com',
'Add manifest shard with usage',
);
await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: { measures: ['sum(invoices.amount)'], dimensions: [] },
compute,
});
const lastCall = (compute.query as ReturnType<typeof vi.fn>).mock.calls.at(-1)?.[0];
const invoices = lastCall?.sources.find((s: Record<string, unknown>) => s.name === 'invoices');
expect(invoices).toBeDefined();
expect(invoices).not.toHaveProperty('usage');
expect(invoices).not.toHaveProperty('inherits_columns_from');
expect(invoices).not.toHaveProperty('source_type');
});
2026-05-10 23:12:26 +02:00
it('resolves the only configured connection when connectionId is omitted', async () => {
await compileLocalSlQuery(project, {
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
});
expect(compute.query).toHaveBeenCalledWith(
expect.objectContaining({
dialect: 'postgres',
}),
);
});
it('executes compiled SQL through a local query executor when requested', async () => {
const queryExecutor = {
execute: vi.fn(async () => ({
headers: ['status', 'order_count'],
rows: [['paid', 2]],
totalRows: 1,
command: 'SELECT',
rowCount: 1,
})),
};
const result = await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: {
measures: ['orders.order_count'],
dimensions: ['orders.status'],
limit: 25,
},
compute,
execute: true,
maxRows: 10,
queryExecutor,
});
expect(queryExecutor.execute).toHaveBeenCalledWith({
connectionId: 'warehouse',
projectDir: project.projectDir,
connection: { driver: 'postgres' },
2026-05-10 23:12:26 +02:00
sql: 'select status, count(*) as order_count from public.orders group by status',
maxRows: 10,
});
expect(result.rows).toEqual([['paid', 2]]);
expect(result.totalRows).toBe(1);
expect(result.plan.execution).toEqual({
mode: 'executed',
driver: 'postgres',
maxRows: 10,
rowCount: 1,
});
});
feat(setup): add Claude Desktop target and MCP-first agent setup (#114) * feat(setup): add Claude Desktop target and MCP-first agent setup Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces the CLI-only agent install mode with MCP+analytics (default) and an optional admin CLI skill, renames the research skill to analytics, and lets interactive setup pick project vs global scope when every target supports it. Extracts a shared MCP server factory used by both HTTP and stdio entrypoints. * Add MCP agent client setup support * Polish setup output formatting * Add MCP tool polish design spec Design for slimming the MCP-registered surface from 25 to 11 tools, introducing memory_ingest, applying the per-tool polish kit (annotations, outputSchema, .describe(), in-band error wrapping, union-drift fixes, type-narrowed jsonToolResult), emitting progress notifications on sql_execution + sl_query, and refining the ktx-analytics SKILL.md to match. * Refine MCP tool polish design spec after adversarial review iteration 1 * Refine MCP tool polish design spec after adversarial review iteration 2 * Refine MCP tool polish design spec after adversarial review iteration 3 * refactor(context): rename memory capture service to ingest * feat(mcp): slim research tool surface * refactor(mcp): remove admin ports from server factory * refactor(cli): rename text ingest memory port * docs: update analytics skill for memory ingest * chore: verify mcp surface rename * Add MCP tool polish v1 surface change plan * feat(context): polish mcp tool metadata * fix(context): enforce resolved semantic layer compute sources * feat(context): emit mcp query progress stages * fix(context): keep mcp progress event internal * Add MCP tool polish v1 metadata & progress plan * Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
it('emits progress while compiling and executing a local semantic-layer query', async () => {
const progress: Array<{ progress: number; message: string }> = [];
const queryExecutor = {
execute: vi.fn(async () => ({
headers: ['status', 'order_count'],
rows: [['paid', 2]],
totalRows: 1,
command: 'SELECT',
rowCount: 1,
})),
};
const result = await compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: {
measures: ['orders.order_count'],
dimensions: ['orders.status'],
limit: 25,
},
compute,
execute: true,
maxRows: 10,
queryExecutor,
onProgress: (event) => {
progress.push({ progress: event.progress, message: event.message });
},
});
expect(result.totalRows).toBe(1);
expect(progress).toEqual([
{ progress: 0, message: 'Compiling query' },
{ progress: 0.3, message: 'Generating SQL' },
{ progress: 0.6, message: 'Executing' },
{ progress: 1, message: 'Fetched 1 rows' },
]);
});
2026-05-10 23:12:26 +02:00
it('requires a query executor for executed mode', async () => {
await expect(
compileLocalSlQuery(project, {
connectionId: 'warehouse',
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
execute: true,
}),
).rejects.toThrow('Local semantic-layer execution requires a query executor.');
});
it('requires connectionId, listing the configured connections, when several exist', async () => {
project.config.connections.analytics = { driver: 'bigquery' };
2026-05-10 23:12:26 +02:00
await expect(
compileLocalSlQuery(project, {
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
}),
).rejects.toThrow('connectionId is required. Configured connections: analytics, warehouse.');
});
it('rejects a connectionId that is not configured, listing the configured connections', async () => {
await expect(
compileLocalSlQuery(project, {
connectionId: 'DIG_SMART_REP',
query: { measures: ['orders.order_count'], dimensions: [] },
compute,
}),
).rejects.toThrow('Connection "DIG_SMART_REP" is not configured in ktx.yaml. Configured connections: warehouse.');
2026-05-10 23:12:26 +02:00
});
});