ktx/packages/cli/test/embedding-resolution.test.ts

147 lines
5.4 KiB
TypeScript
Raw Permalink Normal View History

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 { buildDefaultKtxProjectConfig, type KtxProjectConfig } from '../src/context/project/config.js';
import type { KtxLocalProject } from '../src/context/project/project.js';
import { resolveProjectEmbeddingProvider } from '../src/embedding-resolution.js';
import type { ManagedLocalEmbeddingsDaemon } from '../src/managed-local-embeddings.js';
function projectWithConfig(config: KtxProjectConfig): KtxLocalProject {
return {
projectDir: '/work/proj',
configPath: '/work/proj/ktx.yaml',
config,
coreConfig: {} as KtxLocalProject['coreConfig'],
git: {} as KtxLocalProject['git'],
fileStore: {} as KtxLocalProject['fileStore'],
};
}
function withManagedEmbedding(config: KtxProjectConfig, base_url?: string): KtxProjectConfig {
return {
...config,
ingest: {
...config.ingest,
embeddings: {
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
...(base_url === undefined
? {}
: { sentenceTransformers: { base_url, pathPrefix: '' } }),
},
},
};
}
const noopIo = {
stdout: { write: (_chunk: string) => {} },
stderr: { write: (_chunk: string) => {} },
} as const;
const fakeDaemon: ManagedLocalEmbeddingsDaemon = {
baseUrl: 'http://127.0.0.1:51234',
stdoutLog: '/tmp/o',
stderrLog: '/tmp/e',
};
describe('resolveProjectEmbeddingProvider', () => {
it('returns disabled when backend is none', async () => {
const project = projectWithConfig(buildDefaultKtxProjectConfig());
const result = await resolveProjectEmbeddingProvider(project, {
mode: 'use-if-running',
cliVersion: '0.5.0',
io: noopIo,
});
expect(result.kind).toBe('disabled');
});
it('returns a configured provider when base_url is explicit', async () => {
const project = projectWithConfig(withManagedEmbedding(buildDefaultKtxProjectConfig(), 'http://my-st:8080'));
const createKtxEmbeddingProvider = vi.fn(() => ({ id: 'fake' }) as never);
const result = await resolveProjectEmbeddingProvider(project, {
mode: 'use-if-running',
cliVersion: '0.5.0',
io: noopIo,
createKtxEmbeddingProvider,
});
expect(result.kind).toBe('configured');
expect(createKtxEmbeddingProvider).toHaveBeenCalledOnce();
});
it('connects to the running managed daemon when base_url is omitted', async () => {
const project = projectWithConfig(withManagedEmbedding(buildDefaultKtxProjectConfig(), undefined));
const tryUseManaged = vi.fn(async () => fakeDaemon);
const createKtxEmbeddingProvider = vi.fn(() => ({ id: 'fake' }) as never);
const ensureManaged = vi.fn(async () => fakeDaemon);
const result = await resolveProjectEmbeddingProvider(project, {
mode: 'use-if-running',
cliVersion: '0.5.0',
io: noopIo,
createKtxEmbeddingProvider,
tryUseManagedDaemon: tryUseManaged,
ensureManagedDaemon: ensureManaged,
});
expect(result.kind).toBe('managed-running');
expect(tryUseManaged).toHaveBeenCalledOnce();
expect(ensureManaged).not.toHaveBeenCalled();
});
it('passes pathPrefix="" to the embedding provider when targeting the managed daemon', async () => {
const project = projectWithConfig(withManagedEmbedding(buildDefaultKtxProjectConfig(), undefined));
const tryUseManaged = vi.fn(async () => fakeDaemon);
const createKtxEmbeddingProvider = vi.fn(() => ({ id: 'fake' }) as never);
await resolveProjectEmbeddingProvider(project, {
mode: 'use-if-running',
cliVersion: '0.5.0',
io: noopIo,
createKtxEmbeddingProvider,
tryUseManagedDaemon: tryUseManaged,
});
expect(createKtxEmbeddingProvider).toHaveBeenCalledWith(
expect.objectContaining({
sentenceTransformers: expect.objectContaining({
baseURL: fakeDaemon.baseUrl,
pathPrefix: '',
}),
}),
);
});
it('returns managed-unavailable when no daemon is running and mode is use-if-running', async () => {
const project = projectWithConfig(withManagedEmbedding(buildDefaultKtxProjectConfig(), ''));
const tryUseManaged = vi.fn(async () => null);
const ensureManaged = vi.fn(async () => fakeDaemon);
const result = await resolveProjectEmbeddingProvider(project, {
mode: 'use-if-running',
cliVersion: '0.5.0',
io: noopIo,
tryUseManagedDaemon: tryUseManaged,
ensureManagedDaemon: ensureManaged,
});
expect(result.kind).toBe('managed-unavailable');
expect(ensureManaged).not.toHaveBeenCalled();
});
it('starts the managed daemon when mode is ensure', async () => {
const project = projectWithConfig(withManagedEmbedding(buildDefaultKtxProjectConfig(), undefined));
const tryUseManaged = vi.fn(async () => null);
const ensureManaged = vi.fn(async () => fakeDaemon);
const createKtxEmbeddingProvider = vi.fn(() => ({ id: 'fake' }) as never);
const result = await resolveProjectEmbeddingProvider(project, {
mode: 'ensure',
installPolicy: 'auto',
cliVersion: '0.5.0',
io: noopIo,
createKtxEmbeddingProvider,
tryUseManagedDaemon: tryUseManaged,
ensureManagedDaemon: ensureManaged,
});
expect(result.kind).toBe('managed-started');
expect(ensureManaged).toHaveBeenCalledWith({
cliVersion: '0.5.0',
projectDir: '/work/proj',
installPolicy: 'auto',
io: noopIo,
});
});
});