2026-05-10 23:12:26 +02:00
|
|
|
import { readFile } from 'node:fs/promises';
|
|
|
|
|
import { join } from 'node:path';
|
|
|
|
|
import { fileURLToPath } from 'node:url';
|
|
|
|
|
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 { PromptService } from '../../../src/context/prompts/prompt.service.js';
|
|
|
|
|
import { SkillsRegistryService } from '../../../src/context/skills/skills-registry.service.js';
|
2026-05-10 23:12:26 +02:00
|
|
|
|
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
|
|
|
const promptsDir = fileURLToPath(new URL('../../../src/prompts', import.meta.url));
|
|
|
|
|
const skillsDir = fileURLToPath(new URL('../../../src/skills', import.meta.url));
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
const adapterSkillNames = [
|
|
|
|
|
'live_database_ingest',
|
|
|
|
|
'lookml_ingest',
|
|
|
|
|
'metabase_ingest',
|
|
|
|
|
'metricflow_ingest',
|
|
|
|
|
'notion_synthesize',
|
2026-05-11 18:48:31 +02:00
|
|
|
'historic_sql_table_digest',
|
|
|
|
|
'historic_sql_patterns',
|
2026-05-10 23:12:26 +02:00
|
|
|
'ingest_triage',
|
2026-05-13 16:05:58 +02:00
|
|
|
'wiki_capture',
|
2026-05-10 23:12:26 +02:00
|
|
|
'sl_capture',
|
|
|
|
|
] as const;
|
|
|
|
|
|
|
|
|
|
const adapterReconcileSkillNames = [
|
|
|
|
|
'ingest_triage',
|
2026-05-13 16:05:58 +02:00
|
|
|
'wiki_capture',
|
2026-05-10 23:12:26 +02:00
|
|
|
'sl_capture',
|
|
|
|
|
] as const;
|
|
|
|
|
|
|
|
|
|
const pageTriagePromptNames = ['skills/page_triage_classifier', 'skills/light_extraction'] as const;
|
|
|
|
|
|
|
|
|
|
function forbiddenProductPattern() {
|
|
|
|
|
return new RegExp([['Kae', 'lio'].join(''), ['kae', 'lio'].join(''), ['KAE', 'LIO_'].join('')].join('|'));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe('ingest runtime assets', () => {
|
2026-05-10 23:51:24 +02:00
|
|
|
it('resolves every reusable ingest skill from packaged KTX assets without server fallback', async () => {
|
2026-05-10 23:12:26 +02:00
|
|
|
const registry = new SkillsRegistryService({ skillsDir });
|
|
|
|
|
const expected = [...new Set([...adapterSkillNames, ...adapterReconcileSkillNames])].sort();
|
|
|
|
|
|
|
|
|
|
const skills = await registry.listSkills(expected, 'memory_agent');
|
|
|
|
|
|
|
|
|
|
expect(skills.map((skill) => skill.name).sort()).toEqual(expected);
|
|
|
|
|
for (const skill of skills) {
|
|
|
|
|
expect(skill.path.startsWith(skillsDir)).toBe(true);
|
|
|
|
|
const body = await readFile(join(skill.path, 'SKILL.md'), 'utf-8');
|
|
|
|
|
expect(body).not.toMatch(forbiddenProductPattern());
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-10 23:51:24 +02:00
|
|
|
it('loads page-triage and light-extraction prompts from packaged KTX prompt assets', async () => {
|
2026-05-10 23:12:26 +02:00
|
|
|
const prompts = new PromptService({ promptsDir, partials: [] });
|
|
|
|
|
|
|
|
|
|
for (const promptName of pageTriagePromptNames) {
|
|
|
|
|
const prompt = await prompts.loadPrompt(promptName);
|
|
|
|
|
expect(prompt.trim().length).toBeGreaterThan(100);
|
|
|
|
|
expect(prompt).not.toMatch(forbiddenProductPattern());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
await expect(prompts.loadPrompt('skills/page_triage_classifier')).resolves.toContain('# Page Triage Classifier');
|
|
|
|
|
await expect(prompts.loadPrompt('skills/light_extraction')).resolves.toContain('# Light Context Extraction');
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
it('packages historic-SQL table digest guidance from KTX assets', async () => {
|
2026-05-10 23:12:26 +02:00
|
|
|
const registry = new SkillsRegistryService({ skillsDir });
|
2026-05-11 18:48:31 +02:00
|
|
|
const skills = await registry.listSkills(['historic_sql_table_digest'], 'memory_agent');
|
2026-05-10 23:12:26 +02:00
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
expect(skills.map((skill) => skill.name)).toEqual(['historic_sql_table_digest']);
|
2026-05-10 23:12:26 +02:00
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
const body = await readFile(join(skills[0]!.path, 'SKILL.md'), 'utf-8');
|
|
|
|
|
expect(body).toContain('# Historic SQL Table Digest');
|
|
|
|
|
expect(body).toContain('tables/<schema>.<name>.json');
|
|
|
|
|
expect(body).toContain('tableUsageOutputSchema');
|
|
|
|
|
expect(body).toContain('emit_historic_sql_evidence');
|
|
|
|
|
expect(body).toContain('Do not call wiki_write');
|
|
|
|
|
expect(body).toContain('Do not call sl_write_source');
|
2026-05-10 23:12:26 +02:00
|
|
|
expect(body).not.toMatch(forbiddenProductPattern());
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
it('packages historic-SQL patterns guidance from KTX assets', async () => {
|
2026-05-10 23:12:26 +02:00
|
|
|
const registry = new SkillsRegistryService({ skillsDir });
|
2026-05-11 18:48:31 +02:00
|
|
|
const skills = await registry.listSkills(['historic_sql_patterns'], 'memory_agent');
|
2026-05-10 23:12:26 +02:00
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
expect(skills.map((skill) => skill.name)).toEqual(['historic_sql_patterns']);
|
2026-05-10 23:12:26 +02:00
|
|
|
|
2026-05-11 18:48:31 +02:00
|
|
|
const body = await readFile(join(skills[0]!.path, 'SKILL.md'), 'utf-8');
|
|
|
|
|
expect(body).toContain('# Historic SQL Patterns');
|
2026-05-11 20:21:39 +02:00
|
|
|
expect(body).toContain('patterns-input/part-0001.json');
|
2026-05-11 18:48:31 +02:00
|
|
|
expect(body).toContain('patternsArraySchema');
|
|
|
|
|
expect(body).toContain('emit_historic_sql_evidence');
|
|
|
|
|
expect(body).toContain('cross-table');
|
2026-05-10 23:12:26 +02:00
|
|
|
expect(body).not.toMatch(forbiddenProductPattern());
|
|
|
|
|
});
|
2026-05-13 13:43:23 +02:00
|
|
|
|
|
|
|
|
it('packages identifier verification prompt assets', async () => {
|
|
|
|
|
const shared = await readFile(join(skillsDir, '_shared', 'identifier-verification.md'), 'utf-8');
|
2026-05-15 02:35:09 +02:00
|
|
|
const legacyConnectionPrefix = ['connection', 'Name'].join('');
|
|
|
|
|
|
2026-05-13 13:43:23 +02:00
|
|
|
expect(shared).toContain('## Identifier Verification Protocol');
|
|
|
|
|
expect(shared).toContain('discover_data');
|
|
|
|
|
expect(shared).toContain('entity_details');
|
|
|
|
|
expect(shared).toContain('sql_execution');
|
2026-05-15 02:35:09 +02:00
|
|
|
expect(shared).toContain('sql_execution({connectionId, sql: "SELECT DISTINCT');
|
|
|
|
|
expect(shared).toContain('sql_execution({connectionId, sql: "SELECT 1 FROM');
|
|
|
|
|
expect(shared).not.toContain(`entity_details({${legacyConnectionPrefix}`);
|
|
|
|
|
expect(shared).not.toContain(`sql_execution({${legacyConnectionPrefix}`);
|
2026-05-13 13:43:23 +02:00
|
|
|
});
|
2026-05-10 23:12:26 +02:00
|
|
|
});
|