mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +02:00
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
This commit is contained in:
Andrey Avtomonov
GitHub
parent
924868841d
commit
56985b7e09
548 changed files with 5048 additions and 2228 deletions
|
|
@ -1,137 +0,0 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
import { createKtxEmbeddingProvider } from './embedding-provider.js';
|
||||
import type { KtxEmbeddingConfig } from './types.js';
|
||||
|
||||
describe('createKtxEmbeddingProvider', () => {
|
||||
it('rejects deterministic embeddings', () => {
|
||||
const config = JSON.parse(
|
||||
JSON.stringify({
|
||||
backend: 'deterministic',
|
||||
model: 'sha256',
|
||||
dimensions: 6,
|
||||
}),
|
||||
) as KtxEmbeddingConfig;
|
||||
|
||||
expect(() => createKtxEmbeddingProvider(config)).toThrow('Unsupported KTX embedding backend: deterministic');
|
||||
});
|
||||
|
||||
it('rejects gateway embeddings', () => {
|
||||
const config = JSON.parse(
|
||||
JSON.stringify({
|
||||
backend: 'gateway',
|
||||
model: 'provider/text-embedding',
|
||||
dimensions: 2,
|
||||
gateway: { apiKey: 'gateway-key' }, // pragma: allowlist secret
|
||||
}),
|
||||
) as KtxEmbeddingConfig;
|
||||
|
||||
expect(() => createKtxEmbeddingProvider(config)).toThrow('Unsupported KTX embedding backend: gateway');
|
||||
});
|
||||
|
||||
it('uses OpenAI embeddings with configured dimensions', async () => {
|
||||
const createOpenAIClient = vi.fn(() => ({
|
||||
embeddings: {
|
||||
create: vi.fn().mockResolvedValue({
|
||||
data: [{ index: 0, embedding: [0.1, 0.2] }],
|
||||
usage: { total_tokens: 7 },
|
||||
}),
|
||||
},
|
||||
}));
|
||||
|
||||
const provider = createKtxEmbeddingProvider(
|
||||
{
|
||||
backend: 'openai',
|
||||
model: 'text-embedding-3-small',
|
||||
dimensions: 2,
|
||||
openai: { apiKey: 'openai-key', baseURL: 'https://openai.test/v1' }, // pragma: allowlist secret
|
||||
},
|
||||
{ createOpenAIClient },
|
||||
);
|
||||
|
||||
await expect(provider.embed('hello')).resolves.toEqual([0.1, 0.2]);
|
||||
expect(createOpenAIClient).toHaveBeenCalledWith({
|
||||
apiKey: 'openai-key', // pragma: allowlist secret
|
||||
baseURL: 'https://openai.test/v1',
|
||||
});
|
||||
});
|
||||
|
||||
it('supports sentence-transformers pathPrefix defaults and explicit empty prefix', async () => {
|
||||
const fetch = vi
|
||||
.fn()
|
||||
.mockResolvedValueOnce(new Response(JSON.stringify({ embedding: [0.1, 0.2] }), { status: 200 }))
|
||||
.mockResolvedValueOnce(new Response(JSON.stringify({ embedding: [0.3, 0.4] }), { status: 200 }));
|
||||
|
||||
const provider = createKtxEmbeddingProvider(
|
||||
{
|
||||
backend: 'sentence-transformers',
|
||||
model: 'all-MiniLM-L6-v2',
|
||||
dimensions: 2,
|
||||
sentenceTransformers: { baseURL: 'https://python.test/' },
|
||||
},
|
||||
{ fetch },
|
||||
);
|
||||
|
||||
await expect(provider.embed('hello')).resolves.toEqual([0.3, 0.4]);
|
||||
expect(fetch).toHaveBeenNthCalledWith(
|
||||
1,
|
||||
'https://python.test/api/embeddings/compute',
|
||||
expect.objectContaining({ method: 'POST' }),
|
||||
);
|
||||
expect(fetch).toHaveBeenNthCalledWith(
|
||||
2,
|
||||
'https://python.test/api/embeddings/compute',
|
||||
expect.objectContaining({ method: 'POST' }),
|
||||
);
|
||||
|
||||
const daemonFetch = vi
|
||||
.fn()
|
||||
.mockResolvedValueOnce(new Response(JSON.stringify({ embedding: [0.1, 0.2] }), { status: 200 }))
|
||||
.mockResolvedValueOnce(new Response(JSON.stringify({ embeddings: [[0.5, 0.6]] }), { status: 200 }));
|
||||
|
||||
const daemonProvider = createKtxEmbeddingProvider(
|
||||
{
|
||||
backend: 'sentence-transformers',
|
||||
model: 'all-MiniLM-L6-v2',
|
||||
dimensions: 2,
|
||||
sentenceTransformers: { baseURL: 'https://daemon.test/base/', pathPrefix: '' },
|
||||
},
|
||||
{ fetch: daemonFetch },
|
||||
);
|
||||
|
||||
await expect(daemonProvider.embedMany(['hello'])).resolves.toEqual([[0.5, 0.6]]);
|
||||
expect(daemonFetch).toHaveBeenNthCalledWith(
|
||||
1,
|
||||
'https://daemon.test/base/embeddings/compute',
|
||||
expect.objectContaining({ method: 'POST' }),
|
||||
);
|
||||
expect(daemonFetch).toHaveBeenNthCalledWith(
|
||||
2,
|
||||
'https://daemon.test/base/embeddings/compute-bulk',
|
||||
expect.objectContaining({ method: 'POST' }),
|
||||
);
|
||||
});
|
||||
|
||||
it('reports local HTTP daemon failures without a ktx-daemon spawn fallback cascade', async () => {
|
||||
const fetch = vi
|
||||
.fn()
|
||||
.mockResolvedValue(
|
||||
new Response('Embedding compute failed: httpx.InvalidURL: Invalid port', { status: 500 }),
|
||||
);
|
||||
|
||||
const provider = createKtxEmbeddingProvider(
|
||||
{
|
||||
backend: 'sentence-transformers',
|
||||
model: 'all-MiniLM-L6-v2',
|
||||
dimensions: 2,
|
||||
sentenceTransformers: { baseURL: 'http://127.0.0.1:8765', pathPrefix: '' },
|
||||
},
|
||||
{ fetch },
|
||||
);
|
||||
|
||||
await expect(provider.embed('hello')).rejects.toThrow(
|
||||
'Embedding provider sentence-transformers request failed with HTTP 500: Embedding compute failed: httpx.InvalidURL: Invalid port',
|
||||
);
|
||||
await expect(provider.embed('hello')).rejects.not.toThrow('ktx-daemon fallback failed');
|
||||
expect(fetch).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
});
|
||||
Loading…
Add table
Add a link
Reference in a new issue