ktx/packages/cli/test/telemetry/identity.test.ts

210 lines
6.1 KiB
TypeScript
Raw Permalink Normal View History

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 { mkdir, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join, resolve } from 'node:path';
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
import {
computeTelemetryProjectId,
loadTelemetryIdentity,
readExistingTelemetryProjectId,
TELEMETRY_NOTICE,
type TelemetryIdentityEnv,
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/telemetry/identity.js';
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(stdoutIsTTY = true) {
let stderr = '';
return {
io: {
stdout: { isTTY: stdoutIsTTY, write: () => {} },
stderr: {
write: (chunk: string) => {
stderr += chunk;
},
},
},
stderr: () => stderr,
};
}
describe('telemetry identity', () => {
let homeDir: string;
let env: TelemetryIdentityEnv;
beforeEach(async () => {
homeDir = await mkdtemp(join(tmpdir(), 'ktx-telemetry-home-'));
env = {};
});
afterEach(async () => {
await rm(homeDir, { recursive: true, force: true });
});
it('creates the telemetry file and one-line notice on first interactive enabled load', async () => {
const testIo = makeIo(true);
const identity = await loadTelemetryIdentity({
homeDir,
env,
stdoutIsTTY: true,
stderr: testIo.io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
});
expect(identity.enabled).toBe(true);
expect(identity.installId).toMatch(/^[0-9a-f-]{36}$/);
expect(identity.createdFile).toBe(true);
expect(identity.noticeShown).toBe(true);
expect(testIo.stderr()).toBe(`${TELEMETRY_NOTICE}\n`);
const stored = JSON.parse(await readFile(join(homeDir, '.ktx', 'telemetry.json'), 'utf-8')) as {
enabled: boolean;
noticeShownVersion: number;
};
expect(stored.enabled).toBe(true);
expect(stored.noticeShownVersion).toBe(1);
});
it('emits the notice without ANSI when NO_COLOR is set', async () => {
const testIo = makeIo(true);
await loadTelemetryIdentity({
homeDir,
env: { NO_COLOR: '1' },
stdoutIsTTY: true,
stderr: testIo.io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
});
expect(testIo.stderr()).toBe(`${TELEMETRY_NOTICE}\n`);
});
it('does not create a file when env disables telemetry', async () => {
const identity = await loadTelemetryIdentity({
homeDir,
env: { KTX_TELEMETRY_DISABLED: '1' },
stdoutIsTTY: true,
stderr: makeIo(true).io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
});
expect(identity.enabled).toBe(false);
await expect(readFile(join(homeDir, '.ktx', 'telemetry.json'), 'utf-8')).rejects.toThrow();
});
it('does not create a file for CI or non-TTY command invocations', async () => {
await expect(
loadTelemetryIdentity({
homeDir,
env: { CI: '1' },
stdoutIsTTY: true,
stderr: makeIo(true).io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
}),
).resolves.toMatchObject({ enabled: false, createdFile: false });
await expect(
loadTelemetryIdentity({
homeDir,
env: {},
stdoutIsTTY: false,
stderr: makeIo(false).io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
}),
).resolves.toMatchObject({ enabled: false, createdFile: false });
});
it('honors persistent enabled false', async () => {
await mkdir(join(homeDir, '.ktx'), { recursive: true });
await writeFile(
join(homeDir, '.ktx', 'telemetry.json'),
JSON.stringify(
{
installId: '00000000-0000-4000-8000-000000000000',
enabled: false,
noticeShownAt: '2026-05-22T14:33:02.000Z',
noticeShownVersion: 1,
createdAt: '2026-05-22T14:33:02.000Z',
},
null,
2,
) + '\n',
'utf-8',
);
await expect(
loadTelemetryIdentity({
homeDir,
env,
stdoutIsTTY: true,
stderr: makeIo(true).io.stderr,
now: () => new Date('2026-05-22T15:00:00.000Z'),
}),
).resolves.toMatchObject({
installId: '00000000-0000-4000-8000-000000000000',
enabled: false,
createdFile: false,
});
});
it('recreates a corrupted file instead of surfacing an error to users', async () => {
await mkdir(join(homeDir, '.ktx'), { recursive: true });
await writeFile(join(homeDir, '.ktx', 'telemetry.json'), '{bad json', 'utf-8');
const identity = await loadTelemetryIdentity({
homeDir,
env,
stdoutIsTTY: true,
stderr: makeIo(true).io.stderr,
now: () => new Date('2026-05-22T14:33:02.000Z'),
});
expect(identity.enabled).toBe(true);
expect(identity.createdFile).toBe(true);
});
it('derives a salted project hash without exposing the path', () => {
const projectDir = resolve('/tmp/acme-private-project');
const projectId = computeTelemetryProjectId('00000000-0000-4000-8000-000000000000', projectDir);
expect(projectId).toMatch(/^[a-f0-9]{64}$/);
expect(projectId).not.toContain('acme');
expect(computeTelemetryProjectId('00000000-0000-4000-8000-000000000000', projectDir)).toBe(projectId);
expect(computeTelemetryProjectId('11111111-1111-4111-8111-111111111111', projectDir)).not.toBe(projectId);
});
it('reads an existing project id for Python telemetry without creating identity', async () => {
await mkdir(join(homeDir, '.ktx'), { recursive: true });
await writeFile(
join(homeDir, '.ktx', 'telemetry.json'),
JSON.stringify(
{
installId: '00000000-0000-4000-8000-000000000000',
enabled: true,
noticeShownAt: '2026-05-22T14:33:02.000Z',
noticeShownVersion: 1,
createdAt: '2026-05-22T14:33:02.000Z',
},
null,
2,
) + '\n',
'utf-8',
);
await expect(
readExistingTelemetryProjectId({
homeDir,
projectDir: '/tmp/acme-private-project',
env: {},
}),
).resolves.toMatch(/^[a-f0-9]{64}$/);
await expect(
readExistingTelemetryProjectId({
homeDir,
projectDir: '/tmp/acme-private-project',
env: { KTX_TELEMETRY_DISABLED: '1' },
}),
).resolves.toBeUndefined();
});
});