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
165 lines
6 KiB
TypeScript
165 lines
6 KiB
TypeScript
import { describe, expect, it } from 'vitest';
|
|
import {
|
|
memoryFlowReplayInputSchema,
|
|
memoryFlowStreamEventSchema,
|
|
parseMemoryFlowReplayInput,
|
|
} from '../../../../src/context/ingest/memory-flow/schema.js';
|
|
import type { MemoryFlowReplayInput } from '../../../../src/context/ingest/memory-flow/types.js';
|
|
|
|
function snapshot(overrides: Partial<MemoryFlowReplayInput> = {}): MemoryFlowReplayInput {
|
|
return {
|
|
runId: 'job-1',
|
|
connectionId: 'connection-1',
|
|
adapter: 'metabase',
|
|
status: 'running',
|
|
sourceDir: null,
|
|
syncId: 'sync-1',
|
|
errors: [],
|
|
events: [
|
|
{ type: 'source_acquired', adapter: 'metabase', trigger: 'manual_resync', fileCount: 2 },
|
|
{ type: 'scope_detected', fingerprint: 'scope-1' },
|
|
{ type: 'raw_snapshot_written', syncId: 'sync-1', rawFileCount: 2 },
|
|
{ type: 'diff_computed', added: 1, modified: 1, deleted: 0, unchanged: 0 },
|
|
{ type: 'chunks_planned', chunkCount: 1, workUnitCount: 1, evictionCount: 0 },
|
|
{ type: 'stage_progress', stage: 'integration', percent: 80, message: 'Integrating 1/1 patches: orders' },
|
|
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
|
|
{ type: 'work_unit_step', unitKey: 'orders', stepIndex: 1, stepBudget: 40 },
|
|
{ type: 'candidate_action', unitKey: 'orders', target: 'wiki', action: 'created', key: 'wiki/orders.md' },
|
|
{ type: 'work_unit_finished', unitKey: 'orders', status: 'success' },
|
|
{ type: 'reconciliation_finished', conflictCount: 0, fallbackCount: 0 },
|
|
{ type: 'saved', commitSha: 'abc12345', wikiCount: 1, slCount: 0 },
|
|
{ type: 'provenance_recorded', rowCount: 1 },
|
|
{ type: 'report_created', runId: 'run-1', reportPath: 'ingest-report.json' },
|
|
],
|
|
plannedWorkUnits: [{ unitKey: 'orders', rawFiles: ['orders.md'], peerFileCount: 0, dependencyCount: 1 }],
|
|
details: {
|
|
actions: [
|
|
{
|
|
unitKey: 'orders',
|
|
target: 'wiki',
|
|
action: 'created',
|
|
key: 'wiki/orders.md',
|
|
summary: 'Created orders page',
|
|
rawFiles: ['orders.md'],
|
|
status: 'success',
|
|
},
|
|
],
|
|
provenance: [
|
|
{
|
|
rawPath: 'orders.md',
|
|
artifactKind: 'wiki',
|
|
artifactKey: 'wiki/orders.md',
|
|
actionType: 'wiki_written',
|
|
},
|
|
],
|
|
transcripts: [
|
|
{
|
|
unitKey: 'orders',
|
|
path: 'transcripts/orders.jsonl',
|
|
toolCallCount: 2,
|
|
errorCount: 0,
|
|
toolNames: ['wiki_write'],
|
|
},
|
|
],
|
|
},
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
describe('memory-flow schemas', () => {
|
|
it('parses a full replay input snapshot', () => {
|
|
expect(parseMemoryFlowReplayInput(snapshot())).toEqual(snapshot());
|
|
});
|
|
|
|
it('parses replay metadata and timestamped events', () => {
|
|
const parsed = parseMemoryFlowReplayInput(
|
|
snapshot({
|
|
metadata: {
|
|
schemaVersion: 1,
|
|
mode: 'full',
|
|
origin: 'captured',
|
|
timing: 'captured',
|
|
capturedAt: '2026-05-01T10:00:03.000Z',
|
|
sourceReportId: 'report-1',
|
|
sourceReportPath: 'reports/report-1.json',
|
|
fallbackReason: null,
|
|
},
|
|
events: [
|
|
{
|
|
type: 'source_acquired',
|
|
adapter: 'metabase',
|
|
trigger: 'manual_resync',
|
|
fileCount: 2,
|
|
emittedAt: '2026-05-01T10:00:00.000Z',
|
|
},
|
|
],
|
|
}),
|
|
);
|
|
|
|
expect(parsed.metadata).toEqual({
|
|
schemaVersion: 1,
|
|
mode: 'full',
|
|
origin: 'captured',
|
|
timing: 'captured',
|
|
capturedAt: '2026-05-01T10:00:03.000Z',
|
|
sourceReportId: 'report-1',
|
|
sourceReportPath: 'reports/report-1.json',
|
|
fallbackReason: null,
|
|
});
|
|
expect(parsed.events).toEqual([
|
|
{
|
|
type: 'source_acquired',
|
|
adapter: 'metabase',
|
|
trigger: 'manual_resync',
|
|
fileCount: 2,
|
|
emittedAt: '2026-05-01T10:00:00.000Z',
|
|
},
|
|
]);
|
|
});
|
|
|
|
it('parses skipped deterministic stages', () => {
|
|
const parsed = parseMemoryFlowReplayInput(
|
|
snapshot({
|
|
status: 'done',
|
|
events: [
|
|
{ type: 'source_acquired', adapter: 'live-database', trigger: 'demo_deterministic', fileCount: 7 },
|
|
{ type: 'scope_detected', fingerprint: 'sqlite' },
|
|
{ type: 'raw_snapshot_written', syncId: 'sync-demo', rawFileCount: 7 },
|
|
{ type: 'diff_computed', added: 7, modified: 0, deleted: 0, unchanged: 0 },
|
|
{ type: 'chunks_planned', chunkCount: 7, workUnitCount: 0, evictionCount: 0 },
|
|
{ type: 'stage_skipped', stage: 'workUnits', reason: 'deterministic mode' },
|
|
{ type: 'stage_skipped', stage: 'actions', reason: 'requires LLM' },
|
|
{ type: 'stage_skipped', stage: 'gates', reason: 'requires candidate actions' },
|
|
{ type: 'stage_skipped', stage: 'saved', reason: 'requires LLM memory synthesis' },
|
|
{ type: 'saved', commitSha: null, wikiCount: 0, slCount: 0 },
|
|
{ type: 'provenance_recorded', rowCount: 0 },
|
|
{
|
|
type: 'report_created',
|
|
runId: 'scan-demo',
|
|
reportPath: 'raw-sources/orbit_demo/live-database/sync-demo/scan-report.json',
|
|
},
|
|
],
|
|
}),
|
|
);
|
|
|
|
expect(parsed.events).toContainEqual({ type: 'stage_skipped', stage: 'workUnits', reason: 'deterministic mode' });
|
|
expect(parsed.events).toContainEqual({ type: 'stage_skipped', stage: 'actions', reason: 'requires LLM' });
|
|
});
|
|
|
|
it('parses snapshot and closed stream events', () => {
|
|
expect(memoryFlowStreamEventSchema.parse({ type: 'snapshot', snapshot: snapshot({ status: 'done' }) })).toEqual({
|
|
type: 'snapshot',
|
|
snapshot: snapshot({ status: 'done' }),
|
|
});
|
|
|
|
expect(memoryFlowStreamEventSchema.parse({ type: 'closed', status: 'done', errors: [] })).toEqual({
|
|
type: 'closed',
|
|
status: 'done',
|
|
errors: [],
|
|
});
|
|
});
|
|
|
|
it('rejects invalid replay status values', () => {
|
|
expect(() => memoryFlowReplayInputSchema.parse({ ...snapshot(), status: 'complete' })).toThrow();
|
|
});
|
|
});
|