ktx/packages/cli/test/setup-runtime.test.ts

146 lines
4.2 KiB
TypeScript
Raw Permalink Normal View History

import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
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 { buildDefaultKtxProjectConfig, type KtxProjectConfig } from '../src/context/project/config.js';
import { readKtxSetupState } from '../src/context/project/setup-config.js';
import { afterEach, beforeEach, 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 { runKtxSetupRuntimeStep } from '../src/setup-runtime.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 projectConfig(config: KtxProjectConfig) {
return vi.fn(async () => ({ config }));
}
describe('runKtxSetupRuntimeStep', () => {
let tempDir: string;
beforeEach(async () => {
tempDir = await mkdtemp(join(tmpdir(), 'ktx-setup-runtime-'));
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('skips runtime setup when the project has no direct runtime requirements', async () => {
const io = makeIo();
const ensureRuntime = vi.fn();
await expect(
runKtxSetupRuntimeStep(
{
projectDir: tempDir,
inputMode: 'auto',
cliVersion: '0.2.0',
runtimeInstallPolicy: 'prompt',
},
io.io,
{
loadProject: projectConfig(buildDefaultKtxProjectConfig()),
ensureRuntime,
env: {},
},
),
).resolves.toMatchObject({ status: 'skipped' });
expect(ensureRuntime).not.toHaveBeenCalled();
expect((await readKtxSetupState(tempDir)).completed_steps).not.toContain('runtime');
expect(io.stdout()).toContain('Runtime setup skipped.');
});
it('fails fast when required runtime features cannot be installed in no-input mode', async () => {
const io = makeIo();
const ensureRuntime = vi.fn(async () => {
throw new Error('KTX Python runtime is required for this command. Run: ktx admin runtime install --yes');
});
await expect(
runKtxSetupRuntimeStep(
{
projectDir: tempDir,
inputMode: 'disabled',
cliVersion: '0.2.0',
runtimeInstallPolicy: 'never',
databaseIntrospectionFallback: true,
},
io.io,
{
loadProject: projectConfig(buildDefaultKtxProjectConfig()),
ensureRuntime,
env: {},
},
),
).resolves.toMatchObject({ status: 'failed' });
expect(ensureRuntime).toHaveBeenCalledWith(expect.objectContaining({ installPolicy: 'never' }));
expect((await readKtxSetupState(tempDir)).completed_steps).not.toContain('runtime');
expect(io.stderr()).toContain('ktx admin runtime install --yes');
});
refactor(release): drop release-policy.json runtime dep and next branch (#180) * chore: standardize daemon naming on "KTX daemon" Replace inconsistent names ("KTX Python daemon", "KTX local embeddings daemon", "KTX managed daemon", "Python daemon") with the single name "KTX daemon" in CLI output, errors, command descriptions, test assertions, smoke scripts, docs, AGENTS.md, issue templates, and codecov flags. The daemon is a portable compute server with endpoints for SQL analysis, semantic layer, LookML, database introspection, and embeddings; the previous labels misrepresented it as embeddings-only or exposed implementation details ("Python", "managed"). The "KTX Python runtime" concept (installed interpreter + packages) is deliberately left as-is — it is a separate concept from the daemon process. * refactor(release): drop release-policy.json runtime dep and next branch Strips the release-policy.json fallback from release-version.ts so the CLI reads its version straight from packages/cli/package.json. dev → 0.0.0-private, installed @kaelio/ktx → the real semver baked into the published package.json. KtxCliPackageInfo collapses to { name, version, contextPackageName }; /health no longer depends on version files surviving past a CI run. Replaces the dual-branch (main + next) semantic-release model with a single- branch model on main. rcs and stables interleave on the same branch via { name: 'main', prerelease: 'rc', channel: 'next' } / ['main']. Drops @semantic-release/git and @semantic-release/changelog (nothing is committed back to the repo on any channel) and the workflow's "Prepare next prerelease branch" step plus the KTX_PRERELEASE_BRANCH plumbing. The git tag plus the published npm artifact carry the version forward. Updates docs/release.md, removes the two now-unused devDeps, regenerates pnpm-lock.yaml. 611/611 @ktx/cli tests, 173/173 script tests, type-check, biome, knip all clean. * fix(release): don't throw on non-main branches at config-load time knip loads .releaserc.cjs on every PR run, where GITHUB_REF_NAME is the merge ref (e.g. 180/merge). The previous version of releaseBranches threw immediately when the branch wasn't main, which made knip fail to evaluate the config and then mis-flag @semantic-release/exec as an unused dep. semantic-release already refuses to publish when the current branch doesn't match a configured release branch, so the explicit throw was redundant. Drop it (and the unused currentBranch helper) and replace the "rejects releases from non-main" assertion with one that exercises a CI- shaped GITHUB_REF_NAME and confirms the config loads.
2026-05-20 13:53:14 +02:00
it('starts the KTX daemon for configured sentence-transformers embeddings', async () => {
const io = makeIo();
const ensureLocalEmbeddings = vi.fn(async () => ({
baseUrl: 'http://127.0.0.1:61234',
stdoutLog: join(tempDir, '.ktx', 'runtime', 'daemon.stdout.log'),
stderrLog: join(tempDir, '.ktx', 'runtime', 'daemon.stderr.log'),
}));
const config: KtxProjectConfig = {
...buildDefaultKtxProjectConfig(),
ingest: {
...buildDefaultKtxProjectConfig().ingest,
embeddings: {
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
sentenceTransformers: { base_url: '' },
},
},
};
await expect(
runKtxSetupRuntimeStep(
{
projectDir: tempDir,
inputMode: 'auto',
cliVersion: '0.2.0',
runtimeInstallPolicy: 'auto',
},
io.io,
{
loadProject: projectConfig(config),
ensureLocalEmbeddings,
env: {},
},
),
).resolves.toMatchObject({ status: 'ready' });
expect(ensureLocalEmbeddings).toHaveBeenCalledWith(
expect.objectContaining({
projectDir: tempDir,
installPolicy: 'auto',
}),
);
expect(io.stdout()).toContain('Runtime ready: yes (local embeddings)');
});
});