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>
This commit is contained in:
Luca Martial 2026-07-03 01:54:17 -07:00 committed by GitHub
parent 66768fe009
commit a651b82e2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 887 additions and 68 deletions

View file

@ -3,6 +3,7 @@ import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import type { KtxSemanticLayerComputePort } from '../../../src/context/daemon/semantic-layer-compute.js';
import { FEDERATED_CONNECTION_ID } from '../../../src/context/connections/federation.js';
import { initKtxProject, type KtxLocalProject } from '../../../src/context/project/project.js';
import { compileLocalSlQuery } from '../../../src/context/sl/local-query.js';
@ -67,6 +68,59 @@ grain: []
await rm(tempDir, { recursive: true, force: true });
});
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();
});
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(
@ -109,6 +163,7 @@ grain: []
measures: ['orders.order_count'],
dimensions: ['orders.status'],
limit: 25,
predefined_measures_only: false,
},
});
expect(result).toEqual({
@ -190,6 +245,7 @@ grain: []
query: {
measures: ['sum(payments.amount)'],
dimensions: [],
predefined_measures_only: false,
},
});
});