mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-10 08:05:14 +02:00
* 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
91 lines
3.2 KiB
TypeScript
91 lines
3.2 KiB
TypeScript
import { describe, expect, it, vi } from 'vitest';
|
|
import { createMemoryFlowLiveBuffer, sanitizeMemoryFlowError } from '../../../../src/context/ingest/memory-flow/live-buffer.js';
|
|
import type { MemoryFlowReplayInput } from '../../../../src/context/ingest/memory-flow/types.js';
|
|
|
|
function initialReplay(): MemoryFlowReplayInput {
|
|
return {
|
|
runId: 'live-run-1',
|
|
connectionId: 'warehouse',
|
|
adapter: 'fake',
|
|
status: 'running',
|
|
sourceDir: '/tmp/source',
|
|
syncId: 'pending',
|
|
errors: [],
|
|
events: [],
|
|
plannedWorkUnits: [],
|
|
details: { actions: [], provenance: [], transcripts: [] },
|
|
};
|
|
}
|
|
|
|
describe('createMemoryFlowLiveBuffer', () => {
|
|
it('emits immutable replay snapshots on every live change', () => {
|
|
const onChange = vi.fn();
|
|
const buffer = createMemoryFlowLiveBuffer(initialReplay(), { onChange });
|
|
|
|
buffer.emit({ type: 'source_acquired', adapter: 'fake', trigger: 'manual_resync', fileCount: 2 });
|
|
buffer.update({
|
|
syncId: 'sync-1',
|
|
plannedWorkUnits: [
|
|
{
|
|
unitKey: 'fake-orders',
|
|
rawFiles: ['orders.json'],
|
|
peerFileCount: 0,
|
|
dependencyCount: 0,
|
|
},
|
|
],
|
|
});
|
|
buffer.emit({ type: 'chunks_planned', chunkCount: 1, workUnitCount: 1, evictionCount: 0 });
|
|
buffer.finish('done');
|
|
|
|
expect(onChange).toHaveBeenCalledTimes(4);
|
|
expect(buffer.snapshot()).toMatchObject({
|
|
runId: 'live-run-1',
|
|
status: 'done',
|
|
syncId: 'sync-1',
|
|
plannedWorkUnits: [{ unitKey: 'fake-orders' }],
|
|
});
|
|
expect(buffer.snapshot().events.map((event) => event.type)).toEqual(['source_acquired', 'chunks_planned']);
|
|
|
|
const staleSnapshot = onChange.mock.calls[1][0] as MemoryFlowReplayInput;
|
|
expect(staleSnapshot.details).toEqual({ actions: [], provenance: [], transcripts: [] });
|
|
staleSnapshot.events.push({ type: 'report_created', runId: 'mutated' });
|
|
expect(buffer.snapshot().events.map((event) => event.type)).toEqual(['source_acquired', 'chunks_planned']);
|
|
});
|
|
|
|
it('stamps live events with emittedAt without mutating caller events', () => {
|
|
const event = { type: 'source_acquired', adapter: 'fake', trigger: 'manual_resync', fileCount: 2 } as const;
|
|
const buffer = createMemoryFlowLiveBuffer(initialReplay(), {
|
|
now: () => new Date('2026-05-01T10:00:00.000Z'),
|
|
});
|
|
|
|
buffer.emit(event);
|
|
|
|
expect(event).not.toHaveProperty('emittedAt');
|
|
expect(buffer.snapshot().events).toEqual([
|
|
{
|
|
type: 'source_acquired',
|
|
adapter: 'fake',
|
|
trigger: 'manual_resync',
|
|
fileCount: 2,
|
|
emittedAt: '2026-05-01T10:00:00.000Z',
|
|
},
|
|
]);
|
|
});
|
|
|
|
it('marks failed runs with sanitized error messages', () => {
|
|
const onChange = vi.fn();
|
|
const buffer = createMemoryFlowLiveBuffer(initialReplay(), { onChange });
|
|
|
|
buffer.finish('error', [
|
|
sanitizeMemoryFlowError(
|
|
new Error('Connection failed for postgres://user:password@localhost:5432/db?api_key=abc password=secret'), // pragma: allowlist secret
|
|
),
|
|
]);
|
|
|
|
expect(buffer.snapshot()).toMatchObject({
|
|
status: 'error',
|
|
errors: ['Connection failed for postgres://[redacted] password=[redacted]'],
|
|
});
|
|
expect(onChange).toHaveBeenCalledTimes(1);
|
|
});
|
|
});
|