ktx/packages/cli/src/sql.test.ts

297 lines
8.8 KiB
TypeScript
Raw Normal View History

import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
import { initKtxProject } from './context/project/project.js';
import { parseKtxProjectConfig, serializeKtxProjectConfig } from './context/project/config.js';
import type { KtxScanConnector } from './context/scan/types.js';
import type { SqlAnalysisPort } from './context/sql-analysis/ports.js';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { runKtxSql } from './sql.js';
function makeIo() {
let stdout = '';
let stderr = '';
return {
io: {
stdout: {
write: (chunk: string) => {
stdout += chunk;
},
},
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stdout: () => stdout,
stderr: () => stderr,
};
}
function makeSqlAnalysis(result: Awaited<ReturnType<SqlAnalysisPort['validateReadOnly']>>): SqlAnalysisPort {
return {
analyzeForFingerprint: vi.fn(),
analyzeBatch: vi.fn(),
validateReadOnly: vi.fn(async () => result),
};
}
function makeConnector(overrides: Partial<KtxScanConnector> = {}): KtxScanConnector {
return {
id: 'sqlite:warehouse',
driver: 'sqlite',
capabilities: {
structuralIntrospection: true,
tableSampling: true,
columnSampling: true,
columnStats: true,
readOnlySql: true,
nestedAnalysis: false,
eventStreamDiscovery: false,
formalForeignKeys: true,
estimatedRowCounts: true,
},
introspect: vi.fn(),
executeReadOnly: vi.fn(async () => ({
headers: ['id', 'status'],
headerTypes: ['integer', 'text'],
rows: [
[1, 'paid'],
[2, 'open'],
],
totalRows: 2,
rowCount: 2,
})),
cleanup: vi.fn(async () => undefined),
...overrides,
};
}
describe('runKtxSql', () => {
let tempDir: string;
beforeEach(async () => {
tempDir = await mkdtemp(join(tmpdir(), 'ktx-cli-sql-'));
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
async function writeConnections(
projectDir: string,
connections: ReturnType<typeof parseKtxProjectConfig>['connections'],
): Promise<void> {
const config = parseKtxProjectConfig(await readFile(join(projectDir, 'ktx.yaml'), 'utf-8'));
await writeFile(join(projectDir, 'ktx.yaml'), serializeKtxProjectConfig({ ...config, connections }), 'utf-8');
}
it('validates SQL, executes through the scan connector, and prints a pretty table', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const sqlAnalysis = makeSqlAnalysis({ ok: true, error: null });
const connector = makeConnector();
const createScanConnector = vi.fn(async () => connector);
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id, status from orders',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => sqlAnalysis,
createScanConnector,
},
),
).resolves.toBe(0);
expect(sqlAnalysis.validateReadOnly).toHaveBeenCalledWith('select id, status from orders', 'sqlite');
expect(createScanConnector).toHaveBeenCalledWith(expect.objectContaining({ projectDir }), 'warehouse');
expect(connector.executeReadOnly).toHaveBeenCalledWith(
{ connectionId: 'warehouse', sql: 'select id, status from orders', maxRows: 1000 },
{ runId: 'cli-sql' },
);
expect(connector.cleanup).toHaveBeenCalledTimes(1);
expect(io.stdout()).toContain('id status');
expect(io.stdout()).toContain('1 paid');
expect(io.stdout()).toContain('2 open');
expect(io.stdout()).toContain('2 rows');
expect(io.stderr()).toBe('');
});
it('prints JSON output', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id from orders',
maxRows: 10,
output: undefined,
json: true,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => makeConnector()),
},
),
).resolves.toBe(0);
expect(JSON.parse(io.stdout())).toEqual({
connectionId: 'warehouse',
headers: ['id', 'status'],
headerTypes: ['integer', 'text'],
rows: [
[1, 'paid'],
[2, 'open'],
],
rowCount: 2,
});
});
it('prints plain TSV output', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select id from orders',
maxRows: 10,
output: 'plain',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => makeConnector()),
},
),
).resolves.toBe(0);
expect(io.stdout()).toBe('id\tstatus\n1\tpaid\n2\topen\n');
expect(io.stderr()).toBe('');
});
it('rejects non-read-only SQL before executing connector SQL', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const connector = makeConnector();
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'delete from orders',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: false, error: 'SQL contains read/write operation: Delete' }),
createScanConnector: vi.fn(async () => connector),
},
),
).resolves.toBe(1);
expect(connector.executeReadOnly).not.toHaveBeenCalled();
expect(connector.cleanup).not.toHaveBeenCalled();
expect(io.stderr()).toContain('SQL contains read/write operation: Delete');
});
it('rejects missing connections', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select 1',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
},
),
).resolves.toBe(1);
expect(io.stderr()).toContain('Connection "warehouse" is not configured in ktx.yaml');
});
it('rejects connectors without read-only SQL support and still cleans up', async () => {
const projectDir = join(tempDir, 'project');
await initKtxProject({ projectDir });
await writeConnections(projectDir, { warehouse: { driver: 'sqlite', path: 'warehouse.db' } });
const connector = makeConnector({
capabilities: {
...makeConnector().capabilities,
readOnlySql: false,
},
});
const io = makeIo();
await expect(
runKtxSql(
{
command: 'execute',
projectDir,
connectionId: 'warehouse',
sql: 'select 1',
maxRows: 1000,
output: 'pretty',
json: false,
cliVersion: '0.0.0-test',
},
io.io,
{
createSqlAnalysis: () => makeSqlAnalysis({ ok: true, error: null }),
createScanConnector: vi.fn(async () => connector),
},
),
).resolves.toBe(1);
expect(connector.executeReadOnly).not.toHaveBeenCalled();
expect(connector.cleanup).toHaveBeenCalledTimes(1);
expect(io.stderr()).toContain('Connection "warehouse" does not support read-only SQL execution.');
});
});