mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-10 08:05:14 +02:00
* 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
131 lines
5.7 KiB
TypeScript
131 lines
5.7 KiB
TypeScript
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
|
import type { WarehouseCatalogService } from '../../../../../src/context/scan/warehouse-catalog.js';
|
|
import type { BaseTool, ToolContext } from '../../../../../src/context/tools/base-tool.js';
|
|
import { DiscoverDataTool } from '../../../../../src/context/ingest/tools/warehouse-verification/discover-data.tool.js';
|
|
|
|
describe('DiscoverDataTool', () => {
|
|
const wikiSearchTool = { call: vi.fn() } as unknown as BaseTool & { call: ReturnType<typeof vi.fn> };
|
|
const slDiscoverTool = { call: vi.fn() } as unknown as BaseTool & { call: ReturnType<typeof vi.fn> };
|
|
const catalog = { searchByName: vi.fn() } as unknown as WarehouseCatalogService & {
|
|
searchByName: ReturnType<typeof vi.fn>;
|
|
};
|
|
const context: ToolContext = {
|
|
sourceId: 'ingest',
|
|
messageId: 'm1',
|
|
userId: 'system',
|
|
session: { allowedConnectionNames: new Set(['warehouse']) } as any,
|
|
};
|
|
const tool = new DiscoverDataTool({
|
|
wikiSearchTool,
|
|
slDiscoverTool,
|
|
catalogFactory: () => catalog,
|
|
});
|
|
|
|
beforeEach(() => {
|
|
wikiSearchTool.call.mockReset();
|
|
slDiscoverTool.call.mockReset();
|
|
catalog.searchByName.mockReset();
|
|
wikiSearchTool.call.mockResolvedValue({
|
|
markdown: '- orders wiki',
|
|
structured: { totalFound: 1, results: [{ key: 'orders' }] },
|
|
});
|
|
slDiscoverTool.call.mockResolvedValue({
|
|
markdown: '- orders source',
|
|
structured: { totalSources: 1, sources: [{ sourceName: 'orders' }] },
|
|
});
|
|
catalog.searchByName.mockResolvedValue([
|
|
{
|
|
kind: 'table',
|
|
connectionId: 'warehouse',
|
|
ref: { catalog: null, db: 'public', name: 'orders' },
|
|
display: 'public.orders',
|
|
matchedOn: 'name',
|
|
},
|
|
]);
|
|
});
|
|
|
|
it('groups wiki, semantic layer, and raw schema hits with routing hints', async () => {
|
|
const result = await tool.call({ query: 'orders', connectionId: 'warehouse', limit: 5 }, context);
|
|
|
|
expect(result.markdown).toContain('## Wiki Pages');
|
|
expect(result.markdown).toContain('use `wiki_read(blockKey)` for full content');
|
|
expect(result.markdown).toContain('## Semantic Layer Sources');
|
|
expect(result.markdown).toContain('use `sl_read_source(sourceName)` for the YAML');
|
|
expect(result.markdown).toContain('## Raw Warehouse Schema');
|
|
expect(result.markdown).toContain('use `entity_details({connectionId, targets: [{display}]})`');
|
|
expect(result.structured.raw?.hits).toHaveLength(1);
|
|
});
|
|
|
|
it('includes connectionId on raw schema hits so entity_details can follow up', async () => {
|
|
const multiConnectionContext: ToolContext = {
|
|
...context,
|
|
session: { allowedConnectionNames: new Set(['warehouse', 'analytics']) } as any,
|
|
};
|
|
catalog.searchByName.mockImplementation(async (connectionId: string, query: string) => [
|
|
{
|
|
kind: 'table',
|
|
connectionId,
|
|
ref: { catalog: null, db: 'public', name: `${connectionId}_${query}` },
|
|
display: `public.${connectionId}_${query}`,
|
|
matchedOn: 'name',
|
|
},
|
|
]);
|
|
|
|
const result = await tool.call({ query: 'orders', limit: 10 }, multiConnectionContext);
|
|
|
|
expect(catalog.searchByName).toHaveBeenCalledWith('analytics', 'orders', 10);
|
|
expect(catalog.searchByName).toHaveBeenCalledWith('warehouse', 'orders', 10);
|
|
expect(result.markdown).toContain('connectionId=analytics');
|
|
expect(result.markdown).toContain('connectionId=warehouse');
|
|
expect(result.markdown).toContain(
|
|
'entity_details({connectionId: "analytics", targets: [{display: "public.analytics_orders"}]})',
|
|
);
|
|
expect(result.structured.raw?.hits.map((hit) => hit.connectionId)).toEqual(['analytics', 'warehouse']);
|
|
});
|
|
|
|
it('refuses explicit out-of-scope connection names', async () => {
|
|
const result = await tool.call({ query: 'orders', connectionId: 'billing' }, context);
|
|
|
|
expect(result.markdown).toContain('Connection "billing" is not available to this ingest stage.');
|
|
expect(result.structured).toEqual({ wiki: null, sl: null, raw: null });
|
|
expect(wikiSearchTool.call).not.toHaveBeenCalled();
|
|
expect(slDiscoverTool.call).not.toHaveBeenCalled();
|
|
expect(catalog.searchByName).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('delegates sourceName inspect mode to sl_discover only', async () => {
|
|
slDiscoverTool.call.mockResolvedValueOnce({
|
|
markdown: 'source detail',
|
|
structured: { sourceName: 'orders' },
|
|
});
|
|
|
|
const result = await tool.call({ sourceName: 'orders', connectionId: 'warehouse' }, context);
|
|
|
|
expect(slDiscoverTool.call).toHaveBeenCalledWith({ sourceName: 'orders', connectionId: 'warehouse' }, context);
|
|
expect(wikiSearchTool.call).not.toHaveBeenCalled();
|
|
expect(catalog.searchByName).not.toHaveBeenCalled();
|
|
expect(result.markdown).toContain('source detail');
|
|
});
|
|
|
|
it('returns the empty-state message when all sections are empty', async () => {
|
|
wikiSearchTool.call.mockResolvedValueOnce({ markdown: '', structured: { totalFound: 0, results: [] } });
|
|
slDiscoverTool.call.mockResolvedValueOnce({ markdown: '', structured: { totalSources: 0, sources: [] } });
|
|
catalog.searchByName.mockResolvedValueOnce([]);
|
|
|
|
const result = await tool.call({ query: 'customer source', connectionId: 'warehouse' }, context);
|
|
|
|
expect(result.markdown).toContain('No matches for "customer source" across wiki, semantic layer, or raw warehouse schema.');
|
|
});
|
|
|
|
it('uses connectionId as the optional connection filter', () => {
|
|
const legacyConnectionField = ['connection', 'Name'].join('');
|
|
|
|
expect(tool.parseInput({ query: 'orders', connectionId: 'warehouse', limit: 5 })).toEqual({
|
|
query: 'orders',
|
|
connectionId: 'warehouse',
|
|
limit: 5,
|
|
});
|
|
|
|
expect(() => tool.parseInput({ query: 'orders', [legacyConnectionField]: 'warehouse', limit: 5 })).toThrow();
|
|
});
|
|
});
|