mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-07 07:55:13 +02:00
56985b7e09
* 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
78 lines
2.8 KiB
TypeScript
78 lines
2.8 KiB
TypeScript
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
|
|
import { tmpdir } from 'node:os';
|
|
import { join } from 'node:path';
|
|
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
|
|
|
import { buildProjectStackSnapshotFields } from '../../src/telemetry/project-snapshot.js';
|
|
|
|
describe('buildProjectStackSnapshotFields', () => {
|
|
let projectDir: string;
|
|
|
|
beforeEach(async () => {
|
|
projectDir = await mkdtemp(join(tmpdir(), 'ktx-stack-snapshot-'));
|
|
});
|
|
|
|
afterEach(async () => {
|
|
await rm(projectDir, { recursive: true, force: true });
|
|
});
|
|
|
|
it('summarizes connectors and project capabilities without names or paths', async () => {
|
|
await mkdir(join(projectDir, 'semantic-layer', 'warehouse'), { recursive: true });
|
|
await mkdir(join(projectDir, 'wiki', 'global'), { recursive: true });
|
|
await writeFile(join(projectDir, 'semantic-layer', 'warehouse', 'orders.yaml'), 'name: orders\n');
|
|
await writeFile(join(projectDir, 'wiki', 'global', 'revenue.md'), '# Revenue\n');
|
|
await writeFile(join(projectDir, '.mcp.json'), '{"mcpServers":{"ktx":{}}}\n');
|
|
|
|
const fields = await buildProjectStackSnapshotFields({
|
|
projectDir,
|
|
config: {
|
|
connections: {
|
|
orbit_demo: { driver: 'sqlite', path: join(projectDir, 'demo.db') },
|
|
warehouse: { driver: 'postgres', readonly: true },
|
|
},
|
|
ingest: {
|
|
adapters: [],
|
|
embeddings: { backend: 'sentence-transformers', dimensions: 384 },
|
|
workUnits: { stepBudget: 40, maxConcurrency: 1, failureMode: 'continue' },
|
|
},
|
|
llm: { provider: { backend: 'none' }, models: {}, promptCaching: {} },
|
|
scan: {
|
|
enrichment: { mode: 'none' },
|
|
relationships: {
|
|
enabled: true,
|
|
llmProposals: true,
|
|
validationRequiredForManifest: true,
|
|
acceptThreshold: 0.85,
|
|
reviewThreshold: 0.55,
|
|
maxLlmTablesPerBatch: 40,
|
|
maxCandidatesPerColumn: 25,
|
|
profileSampleRows: 10000,
|
|
profileConcurrency: 4,
|
|
validationConcurrency: 4,
|
|
},
|
|
},
|
|
storage: {
|
|
state: 'sqlite',
|
|
search: 'sqlite-fts5',
|
|
git: { auto_commit: true, author: 'ktx <ktx@example.com>' },
|
|
},
|
|
agent: { run_research: { enabled: false, max_iterations: 20, default_toolset: [] } },
|
|
memory: { auto_commit: true },
|
|
},
|
|
});
|
|
|
|
expect(fields).toEqual({
|
|
connectors: [
|
|
{ driver: 'sqlite', isDemo: true },
|
|
{ driver: 'postgres', isDemo: false },
|
|
],
|
|
connectionCount: 2,
|
|
hasSl: true,
|
|
hasWiki: true,
|
|
hasMcp: true,
|
|
hasManagedRuntime: true,
|
|
});
|
|
expect(JSON.stringify(fields)).not.toContain(projectDir);
|
|
expect(JSON.stringify(fields)).not.toContain('warehouse');
|
|
});
|
|
});
|