ktx/packages/cli/test/context/sql-analysis/http-sql-analysis-port.test.ts

179 lines
5.9 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, it, vi } 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 { createHttpSqlAnalysisPort } from '../../../src/context/sql-analysis/http-sql-analysis-port.js';
2026-05-10 23:12:26 +02:00
describe('createHttpSqlAnalysisPort', () => {
it('calls the SQL-analysis fingerprint endpoint and maps snake_case response fields', async () => {
2026-05-10 23:12:26 +02:00
const requestJson = vi.fn(async () => ({
fingerprint: 'fingerprint-template',
normalized_sql: 'SELECT * FROM analytics.orders WHERE status = ?',
tables_touched: ['analytics.orders'],
literal_slots: [{ position: 1, type: 'string', example_value: 'paid' }],
}));
const port = createHttpSqlAnalysisPort({ baseUrl: 'http://python.test', requestJson });
await expect(
port.analyzeForFingerprint("SELECT * FROM analytics.orders WHERE status = 'paid'", 'postgres'),
).resolves.toEqual({
fingerprint: 'fingerprint-template',
normalizedSql: 'SELECT * FROM analytics.orders WHERE status = ?',
tablesTouched: ['analytics.orders'],
literalSlots: [{ position: 1, type: 'string', exampleValue: 'paid' }],
});
expect(requestJson).toHaveBeenCalledWith('/api/sql/analyze-for-fingerprint', {
sql: "SELECT * FROM analytics.orders WHERE status = 'paid'",
dialect: 'postgres',
});
});
it('preserves SQL-analysis parse errors in the mapped result', async () => {
2026-05-10 23:12:26 +02:00
const requestJson = vi.fn(async () => ({
fingerprint: '',
normalized_sql: '',
tables_touched: [],
literal_slots: [],
error: 'Invalid expression / Unexpected token',
}));
const port = createHttpSqlAnalysisPort({ baseUrl: 'http://python.test', requestJson });
await expect(port.analyzeForFingerprint('SELECT * FROM WHERE', 'postgres')).resolves.toEqual({
fingerprint: '',
normalizedSql: '',
tablesTouched: [],
literalSlots: [],
error: 'Invalid expression / Unexpected token',
});
});
2026-05-11 17:03:22 +02:00
it('calls the SQL batch endpoint and maps snake_case response fields into a Map', async () => {
const requestJson = vi.fn(async () => ({
results: {
orders: {
tables_touched: ['public.orders', 'public.customers'],
columns_by_clause: {
select: ['status'],
where: ['created_at'],
join: ['customer_id', 'id'],
},
error: null,
},
broken: {
tables_touched: [],
columns_by_clause: {},
error: 'Invalid expression / Unexpected token',
},
},
}));
const port = createHttpSqlAnalysisPort({ baseUrl: 'http://python.test', requestJson });
await expect(
port.analyzeBatch(
[
{ id: 'orders', sql: 'select status from public.orders' },
{ id: 'broken', sql: 'select * from where' },
],
'postgres',
),
).resolves.toEqual(
new Map([
[
'orders',
{
tablesTouched: ['public.orders', 'public.customers'],
columnsByClause: {
select: ['status'],
where: ['created_at'],
join: ['customer_id', 'id'],
},
error: null,
},
],
[
'broken',
{
tablesTouched: [],
columnsByClause: {},
error: 'Invalid expression / Unexpected token',
},
],
]),
);
expect(requestJson).toHaveBeenCalledWith('/sql/analyze-batch', {
dialect: 'postgres',
items: [
{ id: 'orders', sql: 'select status from public.orders' },
{ id: 'broken', sql: 'select * from where' },
],
});
});
feat(mcp):added MCP server (#97) * docs(specs): design research-agent MCP tools and ktx mcp daemon Adds the 2026-05-14 design spec for exposing four new MCP tools (discover_data, entity_details, dictionary_search, sql_execution), shipping a ktx-research skill, and introducing an HTTP-only ktx mcp daemon so external agents can use KTX as a research-capable context layer. * Refine research-agent MCP tools spec after adversarial review iteration 1 * Refine research-agent MCP tools spec after adversarial review iteration 2 * Refine research-agent MCP tools spec after adversarial review iteration 3 * Refine spec: drop connectionName compat carve-out and ground summary/snippet provenance per kind * feat(daemon): validate read-only SQL with sqlglot * feat(context): expose read-only SQL validation port * feat(context): register MCP sql execution tool * feat(context): execute MCP SQL through validated connector path * test(context): update SQL analysis port fixtures * docs: add research-agent MCP sql execution foundation plan * feat(context): add scan-backed entity details service * feat(context): register MCP entity details tool * feat(context): expose local MCP entity details * test(context): align entity details scan fixtures * docs: add research-agent MCP entity_details plan * feat(context): add dictionary search service * feat(context): register MCP dictionary search tool * feat(context): expose local MCP dictionary search * docs: add research-agent MCP dictionary_search plan * feat: add MCP discover data service * feat: expose discover data MCP tool * feat: wire local discover data MCP port * docs: add research-agent MCP discover_data plan * feat(cli): add mcp http security helpers * feat(cli): host mcp over streamable http * feat(cli): manage mcp daemon lifecycle * feat(cli): add ktx mcp commands * fix(cli): stabilize mcp daemon verification * docs: add research-agent MCP http daemon plan * feat(cli): install KTX research skill * feat(cli): configure MCP clients in setup agents * feat(cli): support Claude local MCP setup scope * docs: add research-agent MCP setup-agents plan * refactor(context): use connectionId in warehouse verification tools * docs(context): update ingest verification prompts for connectionId * docs: add research-agent MCP ingest contract convergence plan * chore: build runtime artifacts in conductor setup --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-15 02:35:09 +02:00
it('maps read-only SQL validation responses', async () => {
const requests: Array<{ path: string; payload: Record<string, unknown> }> = [];
const port = createHttpSqlAnalysisPort({
baseUrl: 'http://127.0.0.1:8765',
requestJson: async (path, payload) => {
requests.push({ path, payload });
return { ok: false, error: 'SQL contains read/write operation: Insert' };
},
});
await expect(
port.validateReadOnly('with x as (insert into t values (1)) select * from x', 'postgres'),
).resolves.toEqual({
ok: false,
error: 'SQL contains read/write operation: Insert',
});
expect(requests).toEqual([
{
path: '/sql/validate-read-only',
payload: {
dialect: 'postgres',
sql: 'with x as (insert into t values (1)) select * from x',
},
},
]);
});
it('rejects malformed read-only validation responses', async () => {
const port = createHttpSqlAnalysisPort({
baseUrl: 'http://127.0.0.1:8765',
requestJson: async () => ({ ok: 'yes' }),
});
await expect(port.validateReadOnly('select 1', 'postgres')).rejects.toThrow(
'sql analysis response is missing boolean field ok',
);
});
2026-05-11 17:03:22 +02:00
it('rejects malformed SQL batch responses instead of inventing defaults', async () => {
const requestJson = vi.fn(async () => ({
results: {
orders: {
tables_touched: ['public.orders'],
columns_by_clause: { select: ['status'], where: [42] },
error: null,
},
},
}));
const port = createHttpSqlAnalysisPort({ baseUrl: 'http://python.test', requestJson });
await expect(port.analyzeBatch([{ id: 'orders', sql: 'select status from public.orders' }], 'postgres')).rejects
.toThrow('sql analysis response is missing string[] field columns_by_clause.where');
});
2026-05-10 23:12:26 +02:00
it('rejects malformed daemon responses instead of inventing defaults', async () => {
const requestJson = vi.fn(async () => ({
fingerprint: 'abc',
normalized_sql: 'SELECT ?',
tables_touched: 'orders',
literal_slots: [],
}));
const port = createHttpSqlAnalysisPort({ baseUrl: 'http://python.test', requestJson });
await expect(port.analyzeForFingerprint('SELECT 1', 'postgres')).rejects.toThrow(
'sql analysis response is missing string[] field tables_touched',
);
});
});