inspector/scripts/lib/announced-child.test.mjs
cliffhall 9cade95fd0 test(scripts): kill the probe child on every path; document the helper
Two review findings from round 2, both correct.

1. The regression suite killed its child only after the assertions. If
   `assert.rejects` or either assertion failed, execution never reached the
   kill, leaving a 60-second child attached to the runner — a suite guarding a
   process leak would leak one itself, precisely on the run where the
   regression had come back. Teardown is now registered from `onSpawn` via
   `t.after`, so it runs on every path out of every case. That is the helper's
   own ownership rule applied to the tests; killing an already-exited child is
   a no-op, so the early-exit cases pay nothing for it.

2. Document the new shared helper, per the maintenance rules. AGENTS.md's
   scripts/lib tree entry now carries announced-child.mjs and what its contract
   buys, and the smoke:web:app paragraph records why the spawn/readiness step
   moved out of the smoke (same reason teardownWebServer left prod-web-server's
   stop()). README's test:scripts row names the new suite alongside
   resolve-node-bin's.

Not mirrored into .github/copilot-instructions.md: that file is a distillation
of the rules a reviewer cites against a diff, and deliberately excludes the
project-structure tree and tooling inventory.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013hzwzS8UvBsr4yZm7o7sev
Signed-off-by: cliffhall <cliff@futurescale.com>
2026-08-23 12:48:53 -04:00

139 lines
4.6 KiB
JavaScript

/**
* Tests for the spawn/readiness ownership helper (#2000).
*
* The invariant under test is the one a smoke script can never check itself:
* a child that stays alive *through* the readiness timeout must still be
* reachable by the caller's teardown. `smoke:web:app`'s happy path always gets
* the announcement, so a regression here would be silent in `npm run ci` and
* would surface only as a stray process holding a port on a later run.
*
* Every case drives a real `node -e` child rather than a spy, so the assertion
* is about a real process being killable, not about a mock's call log.
*/
import test from "node:test";
import assert from "node:assert/strict";
import { startAnnouncedChild } from "./announced-child.mjs";
/** Wait for a real child to exit (or resolve immediately if it already has). */
function waitForExit(child) {
if (child.exitCode !== null || child.signalCode !== null)
return Promise.resolve();
return new Promise((resolve) => child.once("close", resolve));
}
/**
* Build an `onSpawn` that registers teardown the moment the child exists, so it
* is killed on every path out of the test — a failed assertion included.
*
* This is the helper's own ownership rule applied to the suite: killing only on
* the success path would leak a 60-second child into the runner precisely when
* the regression being guarded has come back, which is the one run where a leak
* matters most. Killing an already-exited child is a no-op, so the early-exit
* cases pay nothing for it.
*/
function killOnTeardown(t, capture = () => {}) {
return (child) => {
capture(child);
t.after(async () => {
child.kill("SIGKILL");
await waitForExit(child);
});
};
}
test("hands the child to onSpawn before waiting, and returns the match", async (t) => {
let seen = null;
const { child, match } = await startAnnouncedChild({
command: process.execPath,
args: ["-e", 'console.error("listening at http://127.0.0.1:9999")'],
pattern: /listening at (http:\/\/\S+)/i,
onSpawn: killOnTeardown(t, (c) => (seen = c)),
what: "probe",
timeoutMs: 10_000,
pollMs: 25,
});
assert.equal(seen, child, "onSpawn got the child that was returned");
assert.equal(match[1], "http://127.0.0.1:9999");
});
test("scans stdout as well as stderr", async (t) => {
const { match } = await startAnnouncedChild({
command: process.execPath,
args: ["-e", 'console.log("ready on 4242")'],
pattern: /ready on (\d+)/,
onSpawn: killOnTeardown(t),
what: "probe",
timeoutMs: 10_000,
pollMs: 25,
});
assert.equal(match[1], "4242");
});
test("a non-announcing child is still reachable and killable after the timeout", async (t) => {
// The regression: a child that is alive but never announces. The throw must
// not be the only thing that happens — the caller must already hold the
// handle, or `process.exit(1)` leaves this running.
let published = null;
await assert.rejects(
startAnnouncedChild({
// Sleeps well past the budget and prints nothing matching.
command: process.execPath,
args: ["-e", "setTimeout(() => {}, 60000)"],
pattern: /never going to match/,
onSpawn: killOnTeardown(t, (c) => (published = c)),
what: "probe",
timeoutMs: 300,
pollMs: 25,
}),
/probe did not start within/,
);
assert.ok(published, "the child was published before the readiness wait");
assert.equal(
published.exitCode,
null,
"and it is still alive, as in the bug",
);
published.kill("SIGKILL");
await waitForExit(published);
assert.ok(
published.exitCode !== null || published.signalCode !== null,
"teardown could actually stop it",
);
});
test("reports a child that exits before announcing, with its output", async (t) => {
let published = null;
await assert.rejects(
startAnnouncedChild({
command: process.execPath,
args: ["-e", 'console.error("boom: bad config"); process.exit(3)'],
pattern: /never going to match/,
onSpawn: killOnTeardown(t, (c) => (published = c)),
what: "probe",
timeoutMs: 10_000,
pollMs: 25,
}),
(err) =>
/probe exited early/.test(err.message) &&
/boom: bad config/.test(err.message),
);
assert.ok(published, "published even on the early-exit path");
});
test("reports a spawn failure rather than throwing it uncaught", async (t) => {
await assert.rejects(
startAnnouncedChild({
command: "definitely-not-an-executable-2000",
args: [],
pattern: /never/,
onSpawn: killOnTeardown(t),
what: "probe",
timeoutMs: 10_000,
pollMs: 25,
}),
/could not spawn the probe:/,
);
});