ktx/packages/cli/test/llm/embedding-health.test.ts

107 lines
3.1 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
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 { runKtxEmbeddingHealthCheck } from '../../src/llm/embedding-health.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('KTX embedding health check', () => {
2026-05-10 23:12:26 +02:00
it('runs a one-shot OpenAI embedding check through the configured provider', async () => {
const createOpenAIClient = vi.fn(() => ({
embeddings: {
create: vi.fn().mockResolvedValue({
data: [{ index: 0, embedding: [0.1, 0.2, 0.3] }],
}),
},
}));
await expect(
2026-05-10 23:51:24 +02:00
runKtxEmbeddingHealthCheck(
2026-05-10 23:12:26 +02:00
{
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 3,
openai: { apiKey: 'sk-openai-test' }, // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
},
{ deps: { createOpenAIClient } },
),
).resolves.toEqual({ ok: true });
expect(createOpenAIClient).toHaveBeenCalledWith({ apiKey: 'sk-openai-test', baseURL: undefined }); // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
});
it('returns failed when the provider returns the wrong dimensions', async () => {
const createOpenAIClient = vi.fn(() => ({
embeddings: {
create: vi.fn().mockResolvedValue({
data: [{ index: 0, embedding: [0.1, 0.2] }],
}),
},
}));
await expect(
2026-05-10 23:51:24 +02:00
runKtxEmbeddingHealthCheck(
2026-05-10 23:12:26 +02:00
{
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 3,
openai: { apiKey: 'sk-openai-test' }, // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
},
{ deps: { createOpenAIClient } },
),
).resolves.toEqual({
ok: false,
message: 'Embedding provider openai returned vector with 2 dimensions; expected 3',
});
});
it('redacts credential values from health-check failures', async () => {
const createOpenAIClient = vi.fn(() => ({
embeddings: {
create: vi.fn(async () => {
throw new Error('401 invalid api key sk-openai-secret');
}),
},
}));
await expect(
2026-05-10 23:51:24 +02:00
runKtxEmbeddingHealthCheck(
2026-05-10 23:12:26 +02:00
{
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 3,
openai: { apiKey: 'sk-openai-secret' }, // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
},
{ deps: { createOpenAIClient } },
),
).resolves.toEqual({
ok: false,
message: '401 invalid api key [redacted]',
});
});
it('returns failed when the health check times out', async () => {
const createOpenAIClient = vi.fn(() => ({
embeddings: {
create: vi.fn(
() =>
new Promise<{ data: Array<{ index?: number; embedding: number[] }>; usage?: { total_tokens?: number } }>(
() => undefined,
),
),
},
}));
await expect(
2026-05-10 23:51:24 +02:00
runKtxEmbeddingHealthCheck(
2026-05-10 23:12:26 +02:00
{
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 3,
openai: { apiKey: 'sk-openai-test' }, // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
},
{ timeoutMs: 1, deps: { createOpenAIClient } },
),
).resolves.toEqual({
ok: false,
message: 'Embedding health check timed out after 1ms',
});
});
});