ktx/packages/cli/test/context/ingest/report-snapshot.test.ts

349 lines
10 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, it } 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 { parseIngestReportSnapshot } from '../../../src/context/ingest/report-snapshot.js';
2026-05-10 23:12:26 +02:00
function validReportSnapshot() {
return {
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
createdAt: '2026-04-30T12:00:00.000Z',
body: {
syncId: 'sync-1',
diffSummary: { added: 2, modified: 1, deleted: 0, unchanged: 4 },
commitSha: 'abc12345',
workUnits: [
{
unitKey: 'cards',
rawFiles: ['cards/1.json', 'cards/2.json'],
status: 'success',
actions: [
{ target: 'wiki', type: 'created', key: 'wiki/global/revenue.md', detail: 'Revenue overview' },
2026-05-10 23:12:26 +02:00
{ target: 'sl', type: 'updated', key: 'warehouse.orders', detail: 'Added order amount measure' },
],
touchedSlSources: [{ connectionId: 'warehouse', sourceName: 'orders' }],
2026-05-10 23:12:26 +02:00
},
],
failedWorkUnits: [],
reconciliationSkipped: false,
conflictsResolved: [],
evictionsApplied: [],
unmappedFallbacks: [],
evictionInputs: [],
unresolvedCards: [],
supersededBy: null,
overrideOf: null,
provenanceRows: [
{
rawPath: 'cards/1.json',
artifactKind: 'wiki',
artifactKey: 'wiki/global/revenue.md',
2026-05-10 23:12:26 +02:00
actionType: 'wiki_written',
},
],
toolTranscripts: [
{
unitKey: 'cards',
path: 'tool-transcripts/cards.jsonl',
toolCallCount: 3,
errorCount: 0,
toolNames: ['wiki_capture'],
2026-05-10 23:12:26 +02:00
},
],
reconciliationActions: [],
evictionDecisions: [],
context: {
documentsIndexed: 2,
chunksIndexed: 2,
documentsDeleted: 0,
embeddingFailures: 0,
candidatesCreated: 1,
candidatesPromoted: 1,
candidatesRejected: 0,
knowledgeCreates: 1,
knowledgeUpdates: 0,
capped: false,
warnings: [],
},
},
};
}
describe('parseIngestReportSnapshot', () => {
it('parses a bundle ingest report snapshot and preserves report detail arrays', () => {
const snapshot = parseIngestReportSnapshot(validReportSnapshot());
expect(snapshot).toMatchObject({
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
body: {
syncId: 'sync-1',
commitSha: 'abc12345',
failedWorkUnits: [],
},
});
expect(snapshot.body.workUnits[0]?.actions).toEqual([
{
target: 'wiki',
type: 'created',
key: 'wiki/global/revenue.md',
2026-05-10 23:12:26 +02:00
detail: 'Revenue overview',
targetConnectionId: null,
},
{
target: 'sl',
type: 'updated',
key: 'warehouse.orders',
detail: 'Added order amount measure',
targetConnectionId: null,
},
]);
expect(snapshot.body.provenanceRows).toHaveLength(1);
expect(snapshot.body.toolTranscripts).toHaveLength(1);
});
it('parses target-aware actions and touched source objects', () => {
2026-05-10 23:12:26 +02:00
const report = validReportSnapshot();
report.body.workUnits[0] = {
...report.body.workUnits[0],
actions: [
{
target: 'sl',
type: 'created',
key: 'looker__b2b__sales_pipeline',
detail: 'Created source',
targetConnectionId: 'warehouse-1',
},
],
touchedSlSources: [{ connectionId: 'warehouse-1', sourceName: 'looker__b2b__sales_pipeline' }],
2026-05-10 23:12:26 +02:00
} as never;
const snapshot = parseIngestReportSnapshot(report);
expect(snapshot.body.workUnits[0]?.actions).toEqual([
{
target: 'sl',
type: 'created',
key: 'looker__b2b__sales_pipeline',
detail: 'Created source',
targetConnectionId: 'warehouse-1',
},
]);
expect(snapshot.body.workUnits[0]?.touchedSlSources).toEqual([
{ connectionId: 'warehouse-1', sourceName: 'looker__b2b__sales_pipeline' },
2026-05-10 23:12:26 +02:00
]);
});
it('parses captured memory-flow snapshots in report bodies', () => {
const report = validReportSnapshot();
report.body = {
...report.body,
memoryFlow: {
metadata: {
schemaVersion: 1,
mode: 'full',
origin: 'captured',
timing: 'captured',
capturedAt: '2026-05-01T10:00:03.000Z',
sourceReportId: null,
sourceReportPath: null,
fallbackReason: null,
},
runId: 'run-1',
connectionId: 'warehouse',
adapter: 'lookml',
status: 'running',
sourceDir: null,
syncId: 'sync-2',
errors: [],
plannedWorkUnits: [],
details: { actions: [], provenance: [], transcripts: [] },
events: [
{
type: 'source_acquired',
adapter: 'lookml',
trigger: 'manual_resync',
fileCount: 2,
emittedAt: '2026-05-01T10:00:00.000Z',
},
],
},
} as typeof report.body;
expect(parseIngestReportSnapshot(report).body.memoryFlow?.events).toEqual([
{
type: 'source_acquired',
adapter: 'lookml',
trigger: 'manual_resync',
fileCount: 2,
emittedAt: '2026-05-01T10:00:00.000Z',
},
]);
});
it('applies defaults for optional report fields emitted by older reports', () => {
const report = validReportSnapshot();
delete (report.body as Record<string, unknown>).conflictsResolved;
delete (report.body as Record<string, unknown>).evictionsApplied;
delete (report.body as Record<string, unknown>).unmappedFallbacks;
delete (report.body as Record<string, unknown>).supersededBy;
delete (report.body as Record<string, unknown>).overrideOf;
delete (report.body as Record<string, unknown>).provenanceRows;
delete (report.body as Record<string, unknown>).toolTranscripts;
const snapshot = parseIngestReportSnapshot(report);
expect(snapshot.body.conflictsResolved).toEqual([]);
expect(snapshot.body.evictionsApplied).toEqual([]);
expect(snapshot.body.unmappedFallbacks).toEqual([]);
expect(snapshot.body.supersededBy).toBeNull();
expect(snapshot.body.overrideOf).toBeNull();
expect(snapshot.body.provenanceRows).toEqual([]);
expect(snapshot.body.toolTranscripts).toEqual([]);
});
feat(ingest): default local ingest to isolated diffs (#128) * docs: add isolated-diff ingestion design * Refine isolated-diff ingestion design after adversarial review iteration 1 * Refine isolated-diff ingestion design after adversarial review iteration 2 * Refine isolated-diff ingestion design after adversarial review iteration 3 * feat: persist ingest trace events * feat: add isolated ingest patch helpers * feat: validate wiki body semantic references * feat: add final ingest artifact gates * feat: execute ingest work units in child worktrees * feat: integrate isolated work unit patches * feat: route selected ingest sources through isolated diffs * test: cover isolated diff ingestion regressions * feat: add isolated diff ingestion v1 core * docs: document ingest trace inspection * docs: add isolated diff ingestion v1 core plan * fix(ingest): tighten final artifact gates * fix(ingest): gate isolated final integration tree * fix(ingest): persist postmortem failure traces * fix(ingest): trace policy conflicts and cleanup child worktrees * test(ingest): verify isolated diff postmortem coverage * docs: add isolated diff ingestion gates and trace closure plan * fix(ingest): gate provenance before isolated diff squash * docs: add isolated diff ingestion provenance gate closure plan * fix(ingest): gate final wiki references * fix(ingest): enforce SL target connection scope * fix(ingest): trace isolated SL target policy gates * test(ingest): cover isolated diff reference and target gates * chore(ingest): verify isolated diff gate closure * docs: add isolated diff ingestion reference and target gate closure plan * fix(ingest): gate global wiki references * docs: add isolated diff ingestion global wiki reference gate closure plan * fix(ingest): validate scan sources and wiki refs * test(ingest): cover isolated diff textual conflict resolver * test(ingest): cover isolated diff resolver integration * feat(ingest): repair isolated diff textual conflicts * feat(ingest): report isolated diff resolver outcomes * test(ingest): verify isolated diff textual conflict repair * test(ingest): align textual conflict failure coverage * docs: add isolated diff textual conflict resolver plan * test(ingest): cover isolated diff gate repair * feat(ingest): add isolated diff gate repair agent * feat(ingest): repair isolated diff semantic gate failures * feat(ingest): wire isolated diff gate repair * test(ingest): verify isolated diff final gate repair * chore(ingest): verify isolated diff gate repair * docs: add isolated diff gate repair plan * Improve ingest progress updates * feat(ingest): route direct-write connectors through isolated diffs * test(ingest): cover non-metabase isolated diff routing * feat(ingest): project metricflow semantic models before work units * test(ingest): verify metricflow isolated projection path * chore(ingest): verify isolated diff connector migration * docs: add isolated diff connector migration plan * feat(ingest): make isolated diff routing the private default * feat(ingest): promote isolated diff to default runner path * feat(ingest): default local ingest to isolated diffs * chore(ingest): remove isolated diff allowlist references * fix(ingest): preserve transient evidence for isolated work units * docs: add isolated diff default promotion plan * refactor(ingest): remove shared worktree WorkUnit path * docs(ingest): align WorkUnit prompts with isolated diffs * test(ingest): drop unused runner import * docs: add isolated diff shared worktree removal plan * docs: add isolated diff gate repair classification plan * fix: restrict claude-code mcp servers * docs: align ingest trace guidance with public CLI --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-18 13:38:06 +02:00
it('parses failed ingest reports with trace and failure details', () => {
const snapshot = parseIngestReportSnapshot({
id: 'report-failed',
runId: 'run-failed',
jobId: 'job-failed',
connectionId: 'warehouse',
sourceKey: 'metabase',
createdAt: '2026-05-17T12:00:00.000Z',
body: {
status: 'failed',
syncId: 'sync-failed',
diffSummary: { added: 1, modified: 0, deleted: 0, unchanged: 0 },
commitSha: null,
tracePath: '/project/.ktx/ingest-traces/job-failed/trace.jsonl',
failure: {
phase: 'final_gates',
message: 'final artifact gates failed',
},
workUnits: [],
failedWorkUnits: [],
reconciliationSkipped: true,
conflictsResolved: [],
evictionsApplied: [],
unmappedFallbacks: [],
evictionInputs: [],
unresolvedCards: [],
supersededBy: null,
overrideOf: null,
provenanceRows: [],
toolTranscripts: [],
},
});
expect(snapshot.body.status).toBe('failed');
expect(snapshot.body.failure).toEqual({
phase: 'final_gates',
message: 'final artifact gates failed',
});
expect(snapshot.body.tracePath).toContain('trace.jsonl');
});
2026-05-10 23:12:26 +02:00
it('rejects malformed report snapshots with a concise message', () => {
const report = validReportSnapshot();
report.body.workUnits[0] = {
...report.body.workUnits[0],
actions: [{ target: 'database', type: 'created', key: 'bad', detail: 'bad target' }],
} as never;
expect(() => parseIngestReportSnapshot(report)).toThrow('Invalid ingest report snapshot');
});
feat(ingest): default local ingest to isolated diffs (#128) * docs: add isolated-diff ingestion design * Refine isolated-diff ingestion design after adversarial review iteration 1 * Refine isolated-diff ingestion design after adversarial review iteration 2 * Refine isolated-diff ingestion design after adversarial review iteration 3 * feat: persist ingest trace events * feat: add isolated ingest patch helpers * feat: validate wiki body semantic references * feat: add final ingest artifact gates * feat: execute ingest work units in child worktrees * feat: integrate isolated work unit patches * feat: route selected ingest sources through isolated diffs * test: cover isolated diff ingestion regressions * feat: add isolated diff ingestion v1 core * docs: document ingest trace inspection * docs: add isolated diff ingestion v1 core plan * fix(ingest): tighten final artifact gates * fix(ingest): gate isolated final integration tree * fix(ingest): persist postmortem failure traces * fix(ingest): trace policy conflicts and cleanup child worktrees * test(ingest): verify isolated diff postmortem coverage * docs: add isolated diff ingestion gates and trace closure plan * fix(ingest): gate provenance before isolated diff squash * docs: add isolated diff ingestion provenance gate closure plan * fix(ingest): gate final wiki references * fix(ingest): enforce SL target connection scope * fix(ingest): trace isolated SL target policy gates * test(ingest): cover isolated diff reference and target gates * chore(ingest): verify isolated diff gate closure * docs: add isolated diff ingestion reference and target gate closure plan * fix(ingest): gate global wiki references * docs: add isolated diff ingestion global wiki reference gate closure plan * fix(ingest): validate scan sources and wiki refs * test(ingest): cover isolated diff textual conflict resolver * test(ingest): cover isolated diff resolver integration * feat(ingest): repair isolated diff textual conflicts * feat(ingest): report isolated diff resolver outcomes * test(ingest): verify isolated diff textual conflict repair * test(ingest): align textual conflict failure coverage * docs: add isolated diff textual conflict resolver plan * test(ingest): cover isolated diff gate repair * feat(ingest): add isolated diff gate repair agent * feat(ingest): repair isolated diff semantic gate failures * feat(ingest): wire isolated diff gate repair * test(ingest): verify isolated diff final gate repair * chore(ingest): verify isolated diff gate repair * docs: add isolated diff gate repair plan * Improve ingest progress updates * feat(ingest): route direct-write connectors through isolated diffs * test(ingest): cover non-metabase isolated diff routing * feat(ingest): project metricflow semantic models before work units * test(ingest): verify metricflow isolated projection path * chore(ingest): verify isolated diff connector migration * docs: add isolated diff connector migration plan * feat(ingest): make isolated diff routing the private default * feat(ingest): promote isolated diff to default runner path * feat(ingest): default local ingest to isolated diffs * chore(ingest): remove isolated diff allowlist references * fix(ingest): preserve transient evidence for isolated work units * docs: add isolated diff default promotion plan * refactor(ingest): remove shared worktree WorkUnit path * docs(ingest): align WorkUnit prompts with isolated diffs * test(ingest): drop unused runner import * docs: add isolated diff shared worktree removal plan * docs: add isolated diff gate repair classification plan * fix: restrict claude-code mcp servers * docs: align ingest trace guidance with public CLI --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-18 13:38:06 +02:00
it('parses isolated-diff textual resolver counters', () => {
const snapshot = parseIngestReportSnapshot({
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
createdAt: '2026-05-18T00:00:00.000Z',
body: {
status: 'completed',
syncId: 'sync-1',
diffSummary: { added: 0, modified: 1, deleted: 0, unchanged: 0 },
commitSha: 'abc123',
isolatedDiff: {
enabled: true,
acceptedPatches: 2,
textualConflicts: 1,
semanticConflicts: 0,
resolverAttempts: 1,
resolverRepairs: 1,
resolverFailures: 0,
},
workUnits: [],
failedWorkUnits: [],
reconciliationSkipped: true,
conflictsResolved: [],
evictionsApplied: [],
unmappedFallbacks: [],
artifactResolutions: [],
evictionInputs: [],
unresolvedCards: [],
supersededBy: null,
overrideOf: null,
provenanceRows: [],
toolTranscripts: [],
},
});
expect(snapshot.body.isolatedDiff).toMatchObject({
resolverAttempts: 1,
resolverRepairs: 1,
resolverFailures: 0,
});
});
it('parses isolated-diff gate repair counters', () => {
const snapshot = parseIngestReportSnapshot({
id: 'report-1',
runId: 'run-1',
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
createdAt: '2026-05-18T00:00:00.000Z',
body: {
status: 'completed',
syncId: 'sync-1',
diffSummary: { added: 1, modified: 0, deleted: 0, unchanged: 0 },
commitSha: 'abc123',
isolatedDiff: {
enabled: true,
acceptedPatches: 1,
textualConflicts: 0,
semanticConflicts: 1,
gateRepairAttempts: 1,
gateRepairs: 1,
gateRepairFailures: 0,
},
workUnits: [],
failedWorkUnits: [],
reconciliationSkipped: true,
conflictsResolved: [],
evictionsApplied: [],
unmappedFallbacks: [],
evictionInputs: [],
unresolvedCards: [],
supersededBy: null,
overrideOf: null,
provenanceRows: [],
toolTranscripts: [],
},
});
expect(snapshot.body.isolatedDiff).toMatchObject({
gateRepairAttempts: 1,
gateRepairs: 1,
gateRepairFailures: 0,
});
});
2026-05-10 23:12:26 +02:00
});