ktx/packages/cli/test/context/scan/credentials.test.ts

184 lines
5.8 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 { REDACTED_KTX_CREDENTIAL_VALUE } from '../../../src/context/core/redaction.js';
2026-05-10 23:12:26 +02:00
import {
2026-05-10 23:51:24 +02:00
redactKtxCredentialEnvelope,
redactKtxCredentialValue,
redactKtxScanMetadata,
redactKtxScanReport,
redactKtxScanWarning,
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
} from '../../../src/context/scan/credentials.js';
import type { KtxCredentialEnvelope, KtxScanReport, KtxScanWarning } from '../../../src/context/scan/types.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('KTX scan credential redaction', () => {
2026-05-10 23:12:26 +02:00
it('keeps credential references inspectable', () => {
2026-05-10 23:51:24 +02:00
const envReference: KtxCredentialEnvelope = { kind: 'env', name: 'DATABASE_URL' };
const fileReference: KtxCredentialEnvelope = { kind: 'file', path: '~/.config/ktx/warehouse' };
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
expect(redactKtxCredentialEnvelope(envReference)).toEqual(envReference);
expect(redactKtxCredentialEnvelope(fileReference)).toEqual(fileReference);
2026-05-10 23:12:26 +02:00
});
it('redacts resolved credential envelope values recursively', () => {
expect(
2026-05-10 23:51:24 +02:00
redactKtxCredentialEnvelope({
2026-05-10 23:12:26 +02:00
kind: 'resolved',
source: 'host',
values: {
username: 'readonly',
password: 'secret-password', // pragma: allowlist secret
nested: {
api_key: 'phx_123', // pragma: allowlist secret
warehouse: 'compute_wh',
},
headers: [{ authorizationToken: 'token-value' }, { label: 'safe' }],
},
}),
).toEqual({
kind: 'resolved',
source: 'host',
redacted: true,
values: {
username: 'readonly',
2026-05-10 23:51:24 +02:00
password: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
nested: {
2026-05-10 23:51:24 +02:00
api_key: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
warehouse: 'compute_wh',
},
2026-05-10 23:51:24 +02:00
headers: [{ authorizationToken: REDACTED_KTX_CREDENTIAL_VALUE }, { label: 'safe' }],
2026-05-10 23:12:26 +02:00
},
});
});
it('redacts scan metadata fields that commonly contain secrets', () => {
expect(
2026-05-10 23:51:24 +02:00
redactKtxScanMetadata({
2026-05-10 23:12:26 +02:00
driver: 'postgres',
url: 'postgres://user:pass@example.test/db', // pragma: allowlist secret
serviceAccountJson: {
client_email: 'reader@example.test',
private_key: 'pem-value', // pragma: allowlist secret
},
safeCount: 3,
}),
).toEqual({
driver: 'postgres',
2026-05-10 23:51:24 +02:00
url: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
serviceAccountJson: {
client_email: 'reader@example.test',
2026-05-10 23:51:24 +02:00
private_key: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
},
safeCount: 3,
});
});
it('redacts scan warning messages and metadata without hiding safe context', () => {
2026-05-10 23:51:24 +02:00
const warning: KtxScanWarning = {
2026-05-10 23:12:26 +02:00
code: 'sampling_failed',
message: 'sample failed for postgres://reader:secret@example.test/db', // pragma: allowlist secret
recoverable: true,
metadata: {
table: 'orders',
url: 'postgres://reader:secret@example.test/db', // pragma: allowlist secret
nested: {
api_key: 'sk_test_123', // pragma: allowlist secret
schema: 'public',
},
},
};
2026-05-10 23:51:24 +02:00
expect(redactKtxScanWarning(warning)).toEqual({
2026-05-10 23:12:26 +02:00
code: 'sampling_failed',
message: 'sample failed for postgres://reader:<redacted>@example.test/db',
recoverable: true,
metadata: {
table: 'orders',
2026-05-10 23:51:24 +02:00
url: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
nested: {
2026-05-10 23:51:24 +02:00
api_key: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
schema: 'public',
},
},
});
});
it('redacts scan report warning metadata recursively', () => {
2026-05-10 23:51:24 +02:00
const report: KtxScanReport = {
2026-05-10 23:12:26 +02:00
connectionId: 'warehouse',
driver: 'postgres',
syncId: 'sync-1',
runId: 'run-1',
trigger: 'cli',
mode: 'structural',
dryRun: false,
artifactPaths: {
rawSourcesDir: 'raw-sources/warehouse/live-database/sync-1',
reportPath: 'raw-sources/warehouse/live-database/sync-1/scan-report.json',
manifestShards: [],
enrichmentArtifacts: [],
},
diffSummary: {
tablesAdded: 0,
tablesModified: 0,
tablesDeleted: 0,
tablesUnchanged: 0,
columnsAdded: 0,
columnsModified: 0,
columnsDeleted: 0,
},
manifestShardsWritten: 0,
structuralSyncStats: {
tablesCreated: 0,
tablesUpdated: 0,
tablesDeleted: 0,
columnsCreated: 0,
columnsUpdated: 0,
columnsDeleted: 0,
},
enrichment: {
dataDictionary: 'skipped',
tableDescriptions: 'skipped',
columnDescriptions: 'skipped',
embeddings: 'skipped',
deterministicRelationships: 'skipped',
llmRelationshipValidation: 'skipped',
statisticalValidation: 'skipped',
},
capabilityGaps: [],
warnings: [
{
code: 'credential_redacted',
message: 'metadata redacted',
recoverable: true,
metadata: {
credentials_json: '{"private_key":"pem-value"}', // pragma: allowlist secret
safeCount: 2,
},
},
],
relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
enrichmentState: {
resumedStages: [],
completedStages: [],
failedStages: [],
},
createdAt: '2026-04-29T00:00:00.000Z',
};
2026-05-10 23:51:24 +02:00
const redacted = redactKtxScanReport(report);
2026-05-10 23:12:26 +02:00
expect(redacted.warnings[0]?.metadata).toEqual({
2026-05-10 23:51:24 +02:00
credentials_json: REDACTED_KTX_CREDENTIAL_VALUE,
2026-05-10 23:12:26 +02:00
safeCount: 2,
});
expect(report.warnings[0]?.metadata).toEqual({
credentials_json: '{"private_key":"pem-value"}', // pragma: allowlist secret
safeCount: 2,
});
});
it('redacts standalone primitive credential values only when the field key is sensitive', () => {
2026-05-10 23:51:24 +02:00
expect(redactKtxCredentialValue('password', 'abc')).toBe(REDACTED_KTX_CREDENTIAL_VALUE);
expect(redactKtxCredentialValue('schema', 'public')).toBe('public');
2026-05-10 23:12:26 +02:00
});
});