Files
codegraph/__tests__/startup-handshake.test.ts
T
c9f8c0ebaf fix(mcp): reap the server when its launcher is killed during startup (#1185) (#1199)
An MCP host that kills the launcher chain within the server's first ~100ms
while keeping the stdio pipes open (config probe, cancelled request, startup
timeout; Rust hosts that kill a child without dropping its stdio handles) left
the server orphaned: it booted already reparented to init, so the PPID
watchdog's "ppid changed" baseline was captured as 1 and could never fire, and
stdin never EOF'd. The process lingered — idle, ~30MB — until the host itself
exited, accumulating one per abandoned launch (the pile-up reported in #1185).
Reproduced on released 1.2.0/macOS: SIGKILL the launcher at +50ms → permanent
orphan; at +150ms the old late baseline had already run and reaped it.

Three-part fix:
- Capture process.ppid at the earliest line of the CLI entry (early-ppid.ts)
  and use it as every watchdog baseline, shrinking the blind window to the few
  ms before our first JS runs.
- Thread the real host pid down the bundled path: the npm shim and the
  standalone sh launcher set CODEGRAPH_HOST_PPID (an outer launcher's value
  wins), so the watchdog polls the host directly. Previously only the
  --liftoff-only relaunch set it, leaving the entire npm/standalone install
  base with hostPpid=null.
- Never-initialized backstop (startup-handshake.ts): a serve --mcp that
  receives no MCP traffic for CODEGRAPH_STARTUP_HANDSHAKE_TIMEOUT_MS (default
  15min, 0 disables) shuts down — the catch-all for a kill landing in the
  residual pre-JS window. Disarmed on the first byte, so a quiet-but-live
  session is never touched.

Also scrub CODEGRAPH_HOST_PPID from the detached daemon's env — it has no host,
and a stale pid must not leak into anything it spawns.

Validated end-to-end on the built bundle: the +50ms early-kill orphan is now
reaped while the host still holds the pipes open, and all six normal
lifecycle paths (clean close, SIGTERM/SIGKILL child, host exit/SIGKILL,
fd-holding adversarial host) stay clean. New coverage in
startup-handshake.test.ts, mcp-startup-orphan.test.ts, and npm-shim.test.ts.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 08:45:12 -05:00

109 lines
3.9 KiB
TypeScript

/**
* Never-initialized backstop + early ppid capture (#1185).
*
* The orphan these guard against: an MCP host kills the launcher chain within
* the server's first ~100ms and keeps the stdio pipes open. The server boots
* already reparented (ppid baseline reads 1 → the divergence watchdog is
* blind), stdin never EOFs, and pre-#1185 the process lived until the host
* itself exited. The backstop reaps any server that never receives a single
* byte of MCP traffic; early-ppid.ts shrinks the blind window itself.
*/
import { describe, it, expect } from 'vitest';
import { PassThrough } from 'stream';
import {
DEFAULT_STARTUP_HANDSHAKE_TIMEOUT_MS,
armStartupHandshakeTimeout,
parseStartupHandshakeTimeoutMs,
} from '../src/mcp/startup-handshake';
import { EARLY_PPID } from '../src/mcp/early-ppid';
const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));
describe('parseStartupHandshakeTimeoutMs', () => {
it('defaults when unset or empty', () => {
expect(parseStartupHandshakeTimeoutMs(undefined)).toBe(DEFAULT_STARTUP_HANDSHAKE_TIMEOUT_MS);
expect(parseStartupHandshakeTimeoutMs('')).toBe(DEFAULT_STARTUP_HANDSHAKE_TIMEOUT_MS);
});
it('defaults on non-numeric garbage', () => {
expect(parseStartupHandshakeTimeoutMs('abc')).toBe(DEFAULT_STARTUP_HANDSHAKE_TIMEOUT_MS);
expect(parseStartupHandshakeTimeoutMs('NaN')).toBe(DEFAULT_STARTUP_HANDSHAKE_TIMEOUT_MS);
});
it('treats 0 and negatives as disabled', () => {
expect(parseStartupHandshakeTimeoutMs('0')).toBe(0);
expect(parseStartupHandshakeTimeoutMs('-5')).toBe(0);
});
it('floors fractional values', () => {
expect(parseStartupHandshakeTimeoutMs('2500.7')).toBe(2500);
});
});
describe('armStartupHandshakeTimeout', () => {
it('fires exactly once when no data ever arrives', async () => {
const stream = new PassThrough();
let fired = 0;
armStartupHandshakeTimeout(() => { fired++; }, stream, 40);
await sleep(140);
expect(fired).toBe(1);
});
it('does not fire once any traffic arrives', async () => {
const stream = new PassThrough();
let fired = 0;
armStartupHandshakeTimeout(() => { fired++; }, stream, 40);
stream.write('{"jsonrpc":"2.0","id":1,"method":"initialize"}\n');
await sleep(140);
expect(fired).toBe(0);
});
it('a single early byte disarms it for good', async () => {
const stream = new PassThrough();
let fired = 0;
armStartupHandshakeTimeout(() => { fired++; }, stream, 40);
stream.write('x');
await sleep(140); // well past the 40ms window, with no further traffic
expect(fired).toBe(0);
});
it('the returned disarm function cancels it', async () => {
const stream = new PassThrough();
let fired = 0;
const disarm = armStartupHandshakeTimeout(() => { fired++; }, stream, 40);
disarm();
disarm(); // idempotent
await sleep(140);
expect(fired).toBe(0);
});
it('timeout 0 disables (env convention shared with CODEGRAPH_PPID_POLL_MS)', async () => {
const stream = new PassThrough();
let fired = 0;
const disarm = armStartupHandshakeTimeout(() => { fired++; }, stream, 0);
await sleep(80);
expect(fired).toBe(0);
disarm(); // still callable
});
it('does not steal data from the real consumer', async () => {
// The backstop attaches its own once('data') listener; the actual MCP
// consumer on the same stream must still see every byte.
const stream = new PassThrough();
let seen = '';
stream.on('data', (c: Buffer) => { seen += c.toString(); });
armStartupHandshakeTimeout(() => { /* no-op */ }, stream, 1000);
stream.write('hello');
stream.write(' world');
await sleep(20);
expect(seen).toBe('hello world');
});
});
describe('EARLY_PPID', () => {
it('captured a plausible parent pid at module load', () => {
expect(Number.isInteger(EARLY_PPID)).toBe(true);
expect(EARLY_PPID).toBeGreaterThan(0);
});
});