ktx/packages/cli/test/demo-assets.test.ts

167 lines
6.8 KiB
TypeScript
Raw Permalink Normal View History

import { access, readFile, rm, stat } from 'node:fs/promises';
2026-05-10 23:12:26 +02:00
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { fileURLToPath } from 'node:url';
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
import { afterEach, describe, expect, it, vi } from 'vitest';
2026-05-10 23:12:26 +02:00
import {
DEMO_ADAPTER,
DEMO_CONNECTION_ID,
DEMO_REPLAY_FILE,
defaultDemoProjectDir,
ensureDemoProject,
ensureSeededDemoProject,
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
} from '../src/demo-assets.js';
2026-05-10 23:12:26 +02:00
const packagedDemoSource = 'packaged-orbit-demo';
function packagedDemoAssetPath(relativePath: string): string {
return fileURLToPath(new URL(`../assets/demo/orbit/${relativePath}`, import.meta.url));
}
async function readPackagedJson<T>(relativePath: string): Promise<T> {
return JSON.parse(await readFile(packagedDemoAssetPath(relativePath), 'utf-8')) as T;
}
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
function makeIo() {
let stderr = '';
return {
stdout: {
isTTY: true,
write() {},
},
stderr: {
write(chunk: string) {
stderr += chunk;
},
},
stderrText: () => stderr,
};
}
2026-05-10 23:12:26 +02:00
describe('demo assets', () => {
2026-05-10 23:51:24 +02:00
const projectDir = join(tmpdir(), `ktx-demo-assets-${process.pid}`);
2026-05-10 23:12:26 +02:00
afterEach(async () => {
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
vi.unstubAllEnvs();
2026-05-10 23:12:26 +02:00
await rm(projectDir, { recursive: true, force: true });
});
it('resolves the default demo root under the OS temp directory', () => {
const dir = defaultDemoProjectDir();
2026-05-10 23:51:24 +02:00
expect(dir.startsWith(join(tmpdir(), 'ktx-demo-'))).toBe(true);
expect(dir).toMatch(/ktx-demo-[a-f0-9]{8}$/);
2026-05-10 23:12:26 +02:00
});
it('exports the packaged Orbit demo identity', () => {
expect(DEMO_CONNECTION_ID).toBe('orbit_demo');
expect(DEMO_ADAPTER).toBe('live-database');
expect(DEMO_REPLAY_FILE).toBe('replay.memory-flow.v1.json');
});
it('ships the seeded demo bundle required by the May 6 PRD', async () => {
const manifest = await readPackagedJson<{
demoAssetSchemaVersion: number;
mode: string;
source: string;
sources: {
warehouse: { tables: number; rowCounts: Record<string, number> };
dbt: { models: number; sourceTables: number };
bi: { explores: number; dashboards: number };
notion: { pages: number };
};
name: string;
displayName: string;
generated: {
semanticLayer: { path: string; sourceCount: number };
knowledge: { pageCount: number };
links: { linkCount: number };
};
}>('manifest.json');
expect(manifest).toMatchObject({
demoAssetSchemaVersion: 2,
name: 'orbit',
displayName: 'Orbit Demo',
mode: 'seeded',
source: packagedDemoSource,
});
expect(manifest.sources.warehouse.tables).toBeGreaterThanOrEqual(5);
expect(manifest.sources.warehouse.tables).toBeLessThanOrEqual(10);
expect(Object.keys(manifest.sources.warehouse.rowCounts).sort()).toEqual([
'accounts',
'arr_movements',
'contracts',
'invoices',
'plans',
'purchase_requests',
'support_tickets',
'users',
]);
expect(manifest.sources.dbt.models).toBeGreaterThanOrEqual(3);
expect(manifest.sources.dbt.models).toBeLessThanOrEqual(6);
expect(manifest.sources.bi.explores).toBeGreaterThanOrEqual(2);
expect(manifest.sources.bi.dashboards).toBeGreaterThanOrEqual(2);
expect(manifest.sources.notion.pages).toBeGreaterThanOrEqual(5);
expect(manifest.generated.semanticLayer.sourceCount).toBeGreaterThanOrEqual(40);
expect(manifest.generated.knowledge.pageCount).toBeGreaterThanOrEqual(20);
2026-05-10 23:12:26 +02:00
expect(manifest.generated.links.linkCount).toBeGreaterThanOrEqual(10);
const dbStat = await stat(packagedDemoAssetPath('demo.db'));
expect(dbStat.size).toBeGreaterThan(0);
expect(dbStat.size).toBeLessThan(10 * 1024 * 1024);
await expect(access(packagedDemoAssetPath('semantic-layer/dbt-main/mart_arr_daily.yaml'))).resolves.toBeUndefined();
await expect(access(packagedDemoAssetPath('semantic-layer/postgres-warehouse/mart_account_activity.yaml'))).resolves.toBeUndefined();
await expect(access(packagedDemoAssetPath('wiki/global/orbit-company-overview.md'))).resolves.toBeUndefined();
2026-05-10 23:12:26 +02:00
await expect(access(packagedDemoAssetPath('links/provenance.json'))).resolves.toBeUndefined();
await expect(access(packagedDemoAssetPath('reports/seeded-demo-report.json'))).resolves.toBeUndefined();
});
it('initializes a flat demo project without writing literal credentials', async () => {
const result = await ensureDemoProject({ projectDir, force: false });
expect(result.projectDir).toBe(projectDir);
await expect(access(join(projectDir, 'demo.db'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'state.sqlite'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'reports'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'semantic-layer'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'wiki'))).resolves.toBeUndefined();
2026-05-10 23:12:26 +02:00
await expect(access(join(projectDir, 'replays', 'replay.memory-flow.v1.json'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'raw-sources'))).resolves.toBeUndefined();
await expect(access(join(projectDir, '_schema'))).rejects.toMatchObject({ code: 'ENOENT' });
2026-05-10 23:51:24 +02:00
const config = await readFile(join(projectDir, 'ktx.yaml'), 'utf-8');
2026-05-10 23:12:26 +02:00
expect(config).toContain('backend: anthropic');
expect(config).toContain('api_key: env:ANTHROPIC_API_KEY');
expect(config).not.toContain('sk-ant-');
});
it('rejects an existing demo project unless force is set', async () => {
await ensureDemoProject({ projectDir, force: false });
await expect(ensureDemoProject({ projectDir, force: false })).rejects.toThrow('Demo project already exists');
await expect(ensureDemoProject({ projectDir, force: true })).resolves.toMatchObject({ projectDir });
});
feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205) * feat: add telemetry phase 1 * feat: add node telemetry event catalog * feat: add telemetry event helpers * feat: emit setup and connection telemetry * feat: emit connection and stack telemetry * feat: emit ingest and scan telemetry * feat: emit query telemetry * feat: emit sampled mcp telemetry * docs: expand telemetry event catalog * feat: add telemetry schema sync artifact * feat: pass telemetry project id to semantic daemon * feat: add daemon telemetry foundation * feat: emit semantic daemon telemetry * feat: emit daemon lifecycle telemetry * docs: document full telemetry event catalog * feat(telemetry): dim first-run notice * feat(telemetry): show first-run notice before command output * feat(telemetry): wire ktx PostHog project for live ingestion * docs(telemetry): drop posthog project name and host from storage section * docs(telemetry): trim to general overview and disclaimer * docs(agents): add short telemetry guidelines * feat(telemetry): enable posthog geoip enrichment * docs(telemetry): drop ip-geoip note from public overview * refactor(telemetry): drop no-op groupIdentify, rely on capture groups field * fix(telemetry): respect CI kill switch in python daemon identity * fix(sql): route table-count analysis to existing analyze-batch endpoint * fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander * fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check * fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests * fix(telemetry): unset CI kill switch in cli-program-telemetry tests
2026-05-22 18:18:47 +02:00
it('emits debug telemetry when the demo connection is created', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
const io = makeIo();
await ensureDemoProject({ projectDir, force: false, io, cliVersion: '0.2.0' });
expect(io.stderrText()).toContain('"event":"connection_added"');
expect(io.stderrText()).toContain('"driver":"sqlite"');
expect(io.stderrText()).toContain('"isDemoConnection":true');
expect(io.stderrText()).not.toContain(projectDir);
});
it('copies the seeded project assets used by the setup wizard tour', async () => {
await ensureSeededDemoProject({ projectDir, force: false });
2026-05-10 23:12:26 +02:00
await expect(access(join(projectDir, 'semantic-layer', 'dbt-main', 'mart_arr_daily.yaml'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'wiki', 'global', 'orbit-company-overview.md'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'links', 'provenance.json'))).resolves.toBeUndefined();
await expect(access(join(projectDir, 'reports', 'seeded-demo-report.json'))).resolves.toBeUndefined();
2026-05-10 23:12:26 +02:00
});
});