ktx/packages/cli/test/context/ingest/final-gate-repair.test.ts
Andrey Avtomonov 56985b7e09
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

136 lines
5 KiB
TypeScript

import { mkdir, mkdtemp, readFile, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { describe, expect, it, vi } from 'vitest';
import { finalGateRepairPaths, repairFinalGateFailure } from '../../../src/context/ingest/final-gate-repair.js';
import { FileIngestTraceWriter } from '../../../src/context/ingest/ingest-trace.js';
async function makeHarness() {
const root = await mkdtemp(join(tmpdir(), 'ktx-final-gate-repair-'));
const workdir = join(root, 'workdir');
await mkdir(join(workdir, 'wiki/global'), { recursive: true });
await mkdir(join(workdir, 'semantic-layer/warehouse'), { recursive: true });
await writeFile(
join(workdir, 'wiki/global/account-segments.md'),
'---\nsummary: Account segments\nusage_mode: auto\n---\n\nARR uses `mart_account_segments.total_contract_arr_cents`.\n',
'utf-8',
);
await writeFile(
join(workdir, 'semantic-layer/warehouse/mart_account_segments.yaml'),
'name: mart_account_segments\ncolumns: [{name: account_id, type: string}]\njoins: []\nmeasures:\n - name: total_contract_arr\n expr: sum(contract_arr)\n',
'utf-8',
);
const trace = new FileIngestTraceWriter({
tracePath: join(root, 'trace.jsonl'),
jobId: 'job-1',
connectionId: 'warehouse',
sourceKey: 'metabase',
runId: 'run-1',
syncId: 'sync-1',
level: 'trace',
});
return { root, workdir, trace };
}
describe('finalGateRepairPaths', () => {
it('derives sorted wiki and semantic-layer file paths', () => {
expect(
finalGateRepairPaths({
changedWikiPageKeys: ['account-segments', 'overview', 'account-segments'],
touchedSlSources: [
{ connectionId: 'warehouse', sourceName: 'mart_account_segments' },
{ connectionId: 'warehouse', sourceName: 'orders' },
{ connectionId: 'warehouse', sourceName: 'orders' },
],
}),
).toEqual([
'semantic-layer/warehouse/mart_account_segments.yaml',
'semantic-layer/warehouse/orders.yaml',
'wiki/global/account-segments.md',
'wiki/global/overview.md',
]);
});
});
describe('repairFinalGateFailure', () => {
it('lets the repair agent read gate errors and edit only allowed files', async () => {
const { workdir, trace } = await makeHarness();
const agentRunner = {
runLoop: vi.fn(async (params: any) => {
const error = await params.toolSet.read_gate_error.execute({});
expect(error.markdown).toContain('total_contract_arr_cents');
const page = await params.toolSet.read_repair_file.execute({
path: 'wiki/global/account-segments.md',
});
expect(page.markdown).toContain('total_contract_arr_cents');
await expect(
params.toolSet.write_repair_file.execute({
path: 'wiki/global/other.md',
content: 'not allowed',
}),
).rejects.toThrow(/gate repair path not allowed/);
await params.toolSet.write_repair_file.execute({
path: 'wiki/global/account-segments.md',
content: page.markdown.replace('total_contract_arr_cents', 'total_contract_arr'),
});
return { stopReason: 'natural' as const };
}),
};
const result = await repairFinalGateFailure({
agentRunner,
workdir,
gateError:
'final artifact gates failed:\naccount-segments: unknown semantic-layer entity mart_account_segments.total_contract_arr_cents',
allowedPaths: ['wiki/global/account-segments.md'],
trace,
repairKind: 'final_artifact_gate',
maxAttempts: 1,
stepBudget: 8,
});
expect(result).toEqual({
status: 'repaired',
attempts: 1,
changedPaths: ['wiki/global/account-segments.md'],
});
await expect(readFile(join(workdir, 'wiki/global/account-segments.md'), 'utf-8')).resolves.toContain(
'total_contract_arr',
);
await expect(readFile(trace.tracePath, 'utf-8')).resolves.toContain('gate_repair_repaired');
expect(agentRunner.runLoop).toHaveBeenCalledWith(
expect.objectContaining({
modelRole: 'repair',
stepBudget: 8,
telemetryTags: expect.objectContaining({
operationName: 'ingest-isolated-diff-gate-repair',
repairKind: 'final_artifact_gate',
}),
}),
);
});
it('returns failed when the repair agent edits no allowed file', async () => {
const { workdir, trace } = await makeHarness();
const result = await repairFinalGateFailure({
agentRunner: { runLoop: vi.fn(async () => ({ stopReason: 'natural' as const })) },
workdir,
gateError: 'final artifact gates failed:\naccount-segments: unknown semantic-layer entity',
allowedPaths: ['wiki/global/account-segments.md'],
trace,
repairKind: 'final_artifact_gate',
maxAttempts: 1,
stepBudget: 8,
});
expect(result).toEqual({
status: 'failed',
attempts: 1,
reason: 'gate repair completed without editing an allowed path',
});
await expect(readFile(trace.tracePath, 'utf-8')).resolves.toContain('gate_repair_failed');
});
});