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

156 lines
4.7 KiB
TypeScript
Raw Permalink Normal View History

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 { mkdtemp, readFile, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import { createGlobalExceptionReporter, type KtxCliIo } from '../../src/cli-runtime.js';
Make telemetry reliable across interrupts and headless installs Three reliability gaps surfaced while auditing why PostHog numbers were untrustworthy: 1. Interrupted commands lost their events. capture() is fire-and-forget and the only flush guarantee lived in a finally block, which SIGINT/SIGTERM skip — so Ctrl-C'ing a long ingest or an MCP client killing 'ktx mcp stdio' dropped the command event and any queued events. Add SIGINT/SIGTERM handlers (real-process entry only; never under test/programmatic io) that mark the active command span aborted, emit it, drain the emitter, then exit. Idempotent with the normal finally path via the single-consume command span. 2. Headless-first installs were invisible. loadTelemetryIdentity refused to mint an installId unless stdout was a TTY, so a machine whose first run was an IDE-launched MCP server or a script emitted nothing, ever. Mint on first run regardless of surface (still honoring CI/DO_NOT_TRACK/KTX_TELEMETRY_DISABLED), writing the one-time notice to stderr — safe under the MCP stdio protocol, which reserves stdout. Drop the now-unused stdoutIsTTY option. 3. No guard against silent emit regressions (the 0.7.0 scan_completed blackout). Add tests: the shared executePublicIngestTarget chokepoint emits exactly one ingest_completed on success and on the preflight-failure branch, and a database target invokes the scan that emits scan_completed; plus coverage for the aborted-flush helper. Identity is unchanged otherwise: every event still attributes to the installId in ~/.ktx/telemetry.json. No event/field changes, so Node<->Python schema parity is untouched. Docs updated to reflect first-run-on-any-surface activation.
2026-06-02 23:19:37 +02:00
import { beginCommandSpan, emitAbortedCommandAndShutdown, emitTelemetryEvent } from '../../src/telemetry/index.js';
import { resetCommandSpan } from '../../src/telemetry/command-hook.js';
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
function makeIo(): { io: KtxCliIo; stderr: () => string } {
let stderr = '';
return {
io: {
stdout: {
isTTY: true,
write: () => {},
},
stderr: {
write: (chunk) => {
stderr += chunk;
},
},
},
stderr: () => stderr,
};
}
describe('emitTelemetryEvent', () => {
let homeDir: string;
beforeEach(async () => {
homeDir = await mkdtemp(join(tmpdir(), 'ktx-telemetry-index-'));
vi.stubEnv('HOME', homeDir);
});
afterEach(async () => {
vi.unstubAllEnvs();
await rm(homeDir, { recursive: true, force: true });
});
it('prints debug telemetry when live telemetry is disabled without creating an identity file', async () => {
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('KTX_TELEMETRY_DISABLED', '1');
vi.stubEnv('DO_NOT_TRACK', '1');
const testIo = makeIo();
const projectDir = join(homeDir, 'private-project');
await emitTelemetryEvent({
name: 'connection_added',
projectDir,
io: testIo.io,
packageInfo: { name: '@kaelio/ktx', version: '0.0.0-test' },
fields: {
driver: 'sqlite',
isDemoConnection: false,
},
});
expect(testIo.stderr()).toContain('[telemetry]');
expect(testIo.stderr()).toContain('"event":"connection_added"');
expect(testIo.stderr()).not.toContain(projectDir);
await expect(readFile(join(homeDir, '.ktx', 'telemetry.json'), 'utf-8')).rejects.toThrow();
});
});
Make telemetry reliable across interrupts and headless installs Three reliability gaps surfaced while auditing why PostHog numbers were untrustworthy: 1. Interrupted commands lost their events. capture() is fire-and-forget and the only flush guarantee lived in a finally block, which SIGINT/SIGTERM skip — so Ctrl-C'ing a long ingest or an MCP client killing 'ktx mcp stdio' dropped the command event and any queued events. Add SIGINT/SIGTERM handlers (real-process entry only; never under test/programmatic io) that mark the active command span aborted, emit it, drain the emitter, then exit. Idempotent with the normal finally path via the single-consume command span. 2. Headless-first installs were invisible. loadTelemetryIdentity refused to mint an installId unless stdout was a TTY, so a machine whose first run was an IDE-launched MCP server or a script emitted nothing, ever. Mint on first run regardless of surface (still honoring CI/DO_NOT_TRACK/KTX_TELEMETRY_DISABLED), writing the one-time notice to stderr — safe under the MCP stdio protocol, which reserves stdout. Drop the now-unused stdoutIsTTY option. 3. No guard against silent emit regressions (the 0.7.0 scan_completed blackout). Add tests: the shared executePublicIngestTarget chokepoint emits exactly one ingest_completed on success and on the preflight-failure branch, and a database target invokes the scan that emits scan_completed; plus coverage for the aborted-flush helper. Identity is unchanged otherwise: every event still attributes to the installId in ~/.ktx/telemetry.json. No event/field changes, so Node<->Python schema parity is untouched. Docs updated to reflect first-run-on-any-surface activation.
2026-06-02 23:19:37 +02:00
describe('emitAbortedCommandAndShutdown', () => {
let homeDir: string;
beforeEach(async () => {
homeDir = await mkdtemp(join(tmpdir(), 'ktx-telemetry-abort-'));
vi.stubEnv('HOME', homeDir);
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('CI', '');
vi.stubEnv('KTX_TELEMETRY_DISABLED', '');
vi.stubEnv('DO_NOT_TRACK', '');
resetCommandSpan();
});
afterEach(async () => {
resetCommandSpan();
vi.unstubAllEnvs();
await rm(homeDir, { recursive: true, force: true });
});
it('flushes the active command span as aborted (the signal path)', async () => {
const testIo = makeIo();
beginCommandSpan({
commandPath: ['ktx', 'ingest'],
flagsPresent: {},
hasProject: true,
attachProjectGroup: false,
startedAt: performance.now(),
});
await emitAbortedCommandAndShutdown({
packageInfo: { name: '@kaelio/ktx', version: '0.0.0-test' },
io: testIo.io,
});
expect(testIo.stderr()).toContain('"event":"command"');
expect(testIo.stderr()).toContain('"outcome":"aborted"');
expect(testIo.stderr()).toContain('"commandPath":["ktx","ingest"]');
});
it('is idempotent: a second call (or no active span) emits nothing', async () => {
const testIo = makeIo();
beginCommandSpan({
commandPath: ['ktx', 'ingest'],
flagsPresent: {},
hasProject: true,
attachProjectGroup: false,
startedAt: performance.now(),
});
const pkg = { name: '@kaelio/ktx', version: '0.0.0-test' };
await emitAbortedCommandAndShutdown({ packageInfo: pkg, io: testIo.io });
const secondIo = makeIo();
await emitAbortedCommandAndShutdown({ packageInfo: pkg, io: secondIo.io });
expect(secondIo.stderr()).not.toContain('"event":"command"');
});
});
describe('global exception reporting contract', () => {
let homeDir: string;
beforeEach(async () => {
homeDir = await mkdtemp(join(tmpdir(), 'ktx-telemetry-global-exception-'));
vi.stubEnv('HOME', homeDir);
vi.stubEnv('KTX_TELEMETRY_DEBUG', '1');
vi.stubEnv('KTX_TELEMETRY_DISABLED', '1');
vi.stubEnv('DO_NOT_TRACK', '');
vi.stubEnv('CI', '');
});
afterEach(async () => {
vi.unstubAllEnvs();
await rm(homeDir, { recursive: true, force: true });
});
it('reports uncaughtException through the fatal debug payload', async () => {
const testIo = makeIo();
const report = createGlobalExceptionReporter(testIo.io, {
name: '@kaelio/ktx',
version: '0.0.0-test',
});
await report('uncaughtException', new Error('global boom'));
expect(testIo.stderr()).toContain('[telemetry-exception]');
expect(testIo.stderr()).toContain('"source":"uncaughtException"');
expect(testIo.stderr()).toContain('"handled":false');
expect(testIo.stderr()).toContain('"fatal":true');
});
});