ktx/packages/cli/test/context/ingest/memory-flow/acceptance-fixtures.ts

169 lines
6.2 KiB
TypeScript
Raw Permalink Normal View History

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 type { MemoryFlowReplayInput } from '../../../../src/context/ingest/memory-flow/types.js';
2026-05-10 23:12:26 +02:00
function baseScenario(overrides: Partial<MemoryFlowReplayInput> = {}): MemoryFlowReplayInput {
return {
runId: 'run-success',
connectionId: 'warehouse',
adapter: 'metricflow',
status: 'done',
sourceDir: '/tmp/source',
syncId: 'sync-success',
reportPath: 'ingest-report.json',
errors: [],
events: [
{ type: 'source_acquired', adapter: 'metricflow', trigger: 'manual_resync', fileCount: 4 },
{ type: 'scope_detected', fingerprint: 'metricflow:demo' },
{ type: 'raw_snapshot_written', syncId: 'sync-success', rawFileCount: 4 },
{ type: 'diff_computed', added: 2, modified: 1, deleted: 0, unchanged: 1 },
{ type: 'chunks_planned', chunkCount: 2, workUnitCount: 2, evictionCount: 0 },
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
{ type: 'candidate_action', unitKey: 'orders', target: 'wiki', action: 'created', key: 'wiki/global/orders.md' },
2026-05-10 23:12:26 +02:00
{ type: 'candidate_action', unitKey: 'orders', target: 'sl', action: 'updated', key: 'warehouse.orders' },
{ type: 'work_unit_finished', unitKey: 'orders', status: 'success' },
{ type: 'work_unit_started', unitKey: 'revenue', skills: ['wiki_capture'], stepBudget: 40 },
{ type: 'candidate_action', unitKey: 'revenue', target: 'wiki', action: 'updated', key: 'wiki/global/revenue.md' },
2026-05-10 23:12:26 +02:00
{ type: 'work_unit_finished', unitKey: 'revenue', status: 'success' },
{ type: 'reconciliation_finished', conflictCount: 0, fallbackCount: 0 },
{ type: 'saved', commitSha: 'abc123456789', wikiCount: 2, slCount: 1 }, // pragma: allowlist secret
{ type: 'provenance_recorded', rowCount: 4 },
{ type: 'report_created', runId: 'run-success', reportPath: 'ingest-report.json' },
],
plannedWorkUnits: [
{ unitKey: 'orders', rawFiles: ['models/orders.yml', 'models/customers.yml'], peerFileCount: 1, dependencyCount: 1 },
{ unitKey: 'revenue', rawFiles: ['docs/revenue.md'], peerFileCount: 0, dependencyCount: 0 },
],
details: {
actions: [
{
unitKey: 'orders',
target: 'wiki',
action: 'created',
key: 'wiki/global/orders.md',
2026-05-10 23:12:26 +02:00
summary: 'Captured order definitions',
rawFiles: ['models/orders.yml'],
status: 'success',
},
{
unitKey: 'orders',
target: 'sl',
action: 'updated',
key: 'warehouse.orders',
summary: 'Updated orders source',
rawFiles: ['models/orders.yml'],
status: 'success',
},
{
unitKey: 'revenue',
target: 'wiki',
action: 'updated',
key: 'wiki/global/revenue.md',
2026-05-10 23:12:26 +02:00
summary: 'Updated revenue notes',
rawFiles: ['docs/revenue.md'],
status: 'success',
},
],
provenance: [
{
rawPath: 'models/orders.yml',
artifactKind: 'wiki',
artifactKey: 'wiki/global/orders.md',
2026-05-10 23:12:26 +02:00
actionType: 'created',
},
{ rawPath: 'models/orders.yml', artifactKind: 'sl', artifactKey: 'warehouse.orders', actionType: 'updated' },
],
transcripts: [
{
unitKey: 'orders',
path: 'transcripts/orders.json',
toolCallCount: 3,
errorCount: 0,
toolNames: ['wiki_write', 'sl_write_source'],
},
],
},
...overrides,
};
}
export function successfulReplayScenario(): MemoryFlowReplayInput {
return baseScenario();
}
export function deletedRawPathsScenario(): MemoryFlowReplayInput {
return baseScenario({
events: baseScenario().events.map((event) =>
event.type === 'diff_computed'
? { ...event, deleted: 2 }
: event.type === 'chunks_planned'
? { ...event, evictionCount: 2 }
: event,
),
});
}
export function validationRevertScenario(): MemoryFlowReplayInput {
return baseScenario({
runId: 'run-validation-failure',
status: 'error',
errors: ['semantic-layer validation failed for warehouse.orders'],
events: [
{ type: 'source_acquired', adapter: 'metricflow', trigger: 'manual_resync', fileCount: 1 },
{ type: 'raw_snapshot_written', syncId: 'sync-validation', rawFileCount: 1 },
{ type: 'diff_computed', added: 1, modified: 0, deleted: 0, unchanged: 0 },
{ type: 'chunks_planned', chunkCount: 1, workUnitCount: 1, evictionCount: 0 },
{ type: 'work_unit_started', unitKey: 'orders', skills: ['wiki_capture'], stepBudget: 40 },
2026-05-10 23:12:26 +02:00
{ type: 'candidate_action', unitKey: 'orders', target: 'sl', action: 'updated', key: 'warehouse.orders' },
{
type: 'work_unit_finished',
unitKey: 'orders',
status: 'failed',
reason: 'semantic-layer validation failed for warehouse.orders',
},
],
plannedWorkUnits: [{ unitKey: 'orders', rawFiles: ['models/orders.yml'], peerFileCount: 0, dependencyCount: 0 }],
details: {
actions: [
{
unitKey: 'orders',
target: 'sl',
action: 'updated',
key: 'warehouse.orders',
summary: 'Invalid measure was reverted',
rawFiles: ['models/orders.yml'],
status: 'failed',
},
],
provenance: [],
transcripts: [
{
unitKey: 'orders',
path: 'transcripts/orders.json',
toolCallCount: 2,
errorCount: 1,
toolNames: ['sl_write_source'],
},
],
},
});
}
export function flaggedFallbackScenario(): MemoryFlowReplayInput {
return baseScenario({
runId: 'run-flagged-fallback',
events: baseScenario().events.map((event) =>
event.type === 'reconciliation_finished' ? { ...event, fallbackCount: 1 } : event,
),
});
}
export function postSaveSecretFailureScenario(): MemoryFlowReplayInput {
return baseScenario({
runId: 'run-post-save-failure',
status: 'error',
errors: ['index refresh failed https://example.com/private token=abc123'],
events: baseScenario().events.map((event) =>
event.type === 'saved' ? { ...event, commitSha: 'def456789012' } : event, // pragma: allowlist secret
),
});
}