ktx/packages/cli/test/context/ingest/tools/read-raw-file.tool.test.ts

70 lines
2.9 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
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';
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 { createReadRawFileTool } from '../../../../src/context/ingest/tools/read-raw-file.tool.js';
2026-05-10 23:12:26 +02:00
describe('read_raw_file tool', () => {
let stagedDir: string;
beforeEach(async () => {
stagedDir = await mkdtemp(join(tmpdir(), 'readraw-'));
await mkdir(join(stagedDir, 'views'), { recursive: true });
await writeFile(join(stagedDir, 'views', 'a.yml'), 'line1\nline2\nline3\n', 'utf-8');
await writeFile(join(stagedDir, 'peer.yml'), 'secret', 'utf-8');
});
afterEach(async () => rm(stagedDir, { recursive: true, force: true }));
it('returns content for an allowed path', async () => {
const tool = createReadRawFileTool({ stagedDir, allowedPaths: new Set(['views/a.yml']) });
const result = await (tool.execute as (...args: unknown[]) => unknown)(
{ path: 'views/a.yml' },
{ toolCallId: 't1', messages: [] },
);
expect(result).toContain('line1');
expect(result).toContain('line2');
});
it('refuses to return oversized files and directs callers to read spans', async () => {
await writeFile(join(stagedDir, 'views', 'huge.yml'), `${'x'.repeat(160_000)}\n`, 'utf-8');
const tool = createReadRawFileTool({ stagedDir, allowedPaths: new Set(['views/huge.yml']) });
const result = await (tool.execute as (...args: unknown[]) => unknown)(
{ path: 'views/huge.yml' },
{ toolCallId: 't1', messages: [] },
);
expect(result).toMatch(/too large/i);
expect(result).toMatch(/read_raw_span/i);
expect(String(result).length).toBeLessThan(1000);
});
it('rejects a path not in the allow-list', async () => {
const tool = createReadRawFileTool({ stagedDir, allowedPaths: new Set(['views/a.yml']) });
const result = await (tool.execute as (...args: unknown[]) => unknown)(
{ path: 'peer.yml' },
{ toolCallId: 't1', messages: [] },
);
expect(result).toMatch(/not accessible/i);
expect(result).not.toContain('secret');
});
it('rejects directory traversal attempts', async () => {
const tool = createReadRawFileTool({ stagedDir, allowedPaths: new Set(['views/a.yml']) });
const result = await (tool.execute as (...args: unknown[]) => unknown)(
{ path: '../outside.yml' },
{ toolCallId: 't1', messages: [] },
);
expect(result).toMatch(/not accessible/i);
});
it('returns a clear error when the file is missing despite being allowed', async () => {
const tool = createReadRawFileTool({ stagedDir, allowedPaths: new Set(['views/missing.yml']) });
const result = await (tool.execute as (...args: unknown[]) => unknown)(
{ path: 'views/missing.yml' },
{ toolCallId: 't1', messages: [] },
);
expect(result).toMatch(/not found/i);
});
});