d48cda4081
CI / Test (ubuntu-latest, Node 18.x, bun) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, npm) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, pnpm) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 18.x, yarn) (push) Failing after 15m1s
CI / Test (ubuntu-latest, Node 20.x, bun) (push) Failing after 17m13s
CI / Test (ubuntu-latest, Node 20.x, npm) (push) Failing after 18m42s
CI / Test (ubuntu-latest, Node 20.x, pnpm) (push) Failing after 15m0s
CI / Test (ubuntu-latest, Node 20.x, yarn) (push) Failing after 49m44s
CI / Test (ubuntu-latest, Node 22.x, bun) (push) Failing after 51m55s
CI / Test (ubuntu-latest, Node 22.x, pnpm) (push) Failing after 21m57s
CI / Test (ubuntu-latest, Node 22.x, npm) (push) Failing after 37m39s
CI / Test (ubuntu-latest, Node 22.x, yarn) (push) Failing after 34m7s
CI / Validate Components (push) Failing after 37m15s
CI / Python Tests (push) Failing after 10m1s
CI / Security Scan (push) Failing after 10m1s
CI / Lint (push) Failing after 17m12s
CI / Coverage (push) Failing after 20m19s
CI / Test (macos-latest, Node 18.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, yarn) (push) Has been cancelled
204 lines
6.7 KiB
JavaScript
204 lines
6.7 KiB
JavaScript
/**
|
|
* Regression tests for #2090: "Stop hook error: JSON validation failed".
|
|
*
|
|
* Stop hooks follow the ECC pass-through convention (echo stdin on stdout).
|
|
* The Stop payload carries `last_assistant_message`, which can be large; any
|
|
* hook that caps stdin and echoes the capped string emits a JSON document cut
|
|
* mid-stream, which the harness reports as a Stop hook JSON validation
|
|
* failure. Worst offender: cost-tracker capped stdin at 64KB, so any Stop
|
|
* payload with a >64KB final assistant message broke the whole Stop chain.
|
|
*
|
|
* Contract under test: for every Stop hook, stdout is either empty or valid
|
|
* JSON, and the exit code is 0 — for realistic large payloads and for
|
|
* oversized (>1MB) payloads, via the production runner and via direct
|
|
* invocation.
|
|
*/
|
|
|
|
'use strict';
|
|
|
|
const assert = require('assert');
|
|
const fs = require('fs');
|
|
const os = require('os');
|
|
const path = require('path');
|
|
const { spawnSync } = require('child_process');
|
|
|
|
const repoRoot = path.join(__dirname, '..', '..');
|
|
const runner = path.join(repoRoot, 'scripts', 'hooks', 'run-with-flags.js');
|
|
|
|
const MAX_STDIN = 1024 * 1024;
|
|
|
|
const workDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-stop-stdout-')); // non-git cwd
|
|
const dataHome = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-stop-data-'));
|
|
|
|
function test(name, fn) {
|
|
try {
|
|
fn();
|
|
console.log(` ✓ ${name}`);
|
|
return true;
|
|
} catch (error) {
|
|
console.log(` ✗ ${name}`);
|
|
console.log(` Error: ${error.message}`);
|
|
return false;
|
|
}
|
|
}
|
|
|
|
function stopPayload(messageBytes) {
|
|
return JSON.stringify({
|
|
session_id: `stop-stdout-test-${process.pid}`,
|
|
transcript_path: path.join(workDir, 'missing-transcript.jsonl'),
|
|
cwd: workDir,
|
|
hook_event_name: 'Stop',
|
|
stop_hook_active: false,
|
|
last_assistant_message: 'm'.repeat(messageBytes)
|
|
});
|
|
}
|
|
|
|
function hookEnv() {
|
|
const env = {
|
|
...process.env,
|
|
ECC_HOOK_PROFILE: 'standard',
|
|
ECC_AGENT_DATA_HOME: dataHome,
|
|
CLAUDE_SESSION_ID: `stop-stdout-test-${process.pid}`
|
|
};
|
|
delete env.ECC_GATEGUARD;
|
|
delete env.ECC_DISABLED_HOOKS;
|
|
return env;
|
|
}
|
|
|
|
function runViaRunner(hookId, script, input) {
|
|
return spawnSync('node', [runner, hookId, script, 'minimal,standard,strict'], {
|
|
input,
|
|
encoding: 'utf8',
|
|
cwd: workDir,
|
|
env: hookEnv(),
|
|
timeout: 60000,
|
|
maxBuffer: 16 * 1024 * 1024,
|
|
stdio: ['pipe', 'pipe', 'pipe']
|
|
});
|
|
}
|
|
|
|
function runDirect(script, input) {
|
|
return spawnSync('node', [path.join(repoRoot, script)], {
|
|
input,
|
|
encoding: 'utf8',
|
|
cwd: workDir,
|
|
env: hookEnv(),
|
|
timeout: 60000,
|
|
maxBuffer: 16 * 1024 * 1024,
|
|
stdio: ['pipe', 'pipe', 'pipe']
|
|
});
|
|
}
|
|
|
|
function assertStdoutContract(result, label) {
|
|
assert.strictEqual(result.status, 0, `${label}: expected exit 0, got ${result.status}: ${result.stderr}`);
|
|
if (result.stdout.length > 0) {
|
|
try {
|
|
JSON.parse(result.stdout);
|
|
} catch (err) {
|
|
assert.fail(`${label}: stdout is non-empty but not valid JSON (${err.message}); first 120 chars: ${result.stdout.slice(0, 120)}`);
|
|
}
|
|
}
|
|
}
|
|
|
|
// All registered Stop hooks (hooks/hooks.json).
|
|
const STOP_HOOKS = [
|
|
['stop:format-typecheck', 'scripts/hooks/stop-format-typecheck.js'],
|
|
['stop:check-console-log', 'scripts/hooks/check-console-log.js'],
|
|
['stop:session-end', 'scripts/hooks/session-end.js'],
|
|
['stop:evaluate-session', 'scripts/hooks/evaluate-session.js'],
|
|
['stop:cost-tracker', 'scripts/hooks/cost-tracker.js']
|
|
// stop:desktop-notify is excluded from the valid-payload run because a
|
|
// successful run() fires a real OS notification; its truncation path is
|
|
// covered separately below (run() bails on JSON.parse before notifying).
|
|
];
|
|
|
|
// Direct-invocation legacy paths that echo stdin.
|
|
const ECHOING_STOP_HOOKS = [
|
|
'scripts/hooks/stop-format-typecheck.js',
|
|
'scripts/hooks/check-console-log.js',
|
|
'scripts/hooks/cost-tracker.js',
|
|
'scripts/hooks/desktop-notify.js'
|
|
];
|
|
|
|
console.log('\nStop hook stdout contract tests (#2090):');
|
|
|
|
let passed = 0;
|
|
let failed = 0;
|
|
|
|
// A 100KB last_assistant_message is a realistic long-session Stop payload.
|
|
// Before the fix, cost-tracker echoed it cut at 64KB through the production
|
|
// runner path, making the harness report "JSON validation failed".
|
|
const realisticPayload = stopPayload(100 * 1024);
|
|
|
|
for (const [hookId, script] of STOP_HOOKS) {
|
|
if (
|
|
test(`${hookId} via runner keeps stdout valid for a 100KB Stop payload`, () => {
|
|
const result = runViaRunner(hookId, script, realisticPayload);
|
|
assertStdoutContract(result, hookId);
|
|
if (result.stdout.length > 0) {
|
|
assert.strictEqual(result.stdout, realisticPayload, `${hookId}: pass-through must echo the payload uncut`);
|
|
}
|
|
})
|
|
)
|
|
passed++;
|
|
else failed++;
|
|
}
|
|
|
|
const oversizedPayload = stopPayload(MAX_STDIN + 64 * 1024);
|
|
|
|
for (const [hookId, script] of [...STOP_HOOKS, ['stop:desktop-notify', 'scripts/hooks/desktop-notify.js']]) {
|
|
if (
|
|
test(`${hookId} via runner fails open on a >1MB Stop payload`, () => {
|
|
const result = runViaRunner(hookId, script, oversizedPayload);
|
|
assert.strictEqual(result.status, 0, `${hookId}: expected exit 0, got ${result.status}: ${result.stderr}`);
|
|
assert.strictEqual(result.stdout, '', `${hookId}: oversized payloads must not be echoed`);
|
|
})
|
|
)
|
|
passed++;
|
|
else failed++;
|
|
}
|
|
|
|
for (const script of ECHOING_STOP_HOOKS) {
|
|
if (
|
|
test(`${path.basename(script)} invoked directly never echoes truncated stdin`, () => {
|
|
const result = runDirect(script, oversizedPayload);
|
|
assert.strictEqual(result.status, 0, `${script}: expected exit 0, got ${result.status}: ${result.stderr}`);
|
|
assert.strictEqual(result.stdout, '', `${script}: truncated stdin must not be echoed`);
|
|
})
|
|
)
|
|
passed++;
|
|
else failed++;
|
|
}
|
|
|
|
if (
|
|
test('check-console-log invoked directly echoes a sub-cap >64KB payload uncut', () => {
|
|
const result = runDirect('scripts/hooks/check-console-log.js', realisticPayload);
|
|
assert.strictEqual(result.status, 0);
|
|
assert.strictEqual(result.stdout, realisticPayload, 'pass-through must not be cut at the pipe buffer');
|
|
JSON.parse(result.stdout);
|
|
})
|
|
)
|
|
passed++;
|
|
else failed++;
|
|
|
|
if (
|
|
test('cost-tracker invoked directly echoes a sub-cap >64KB payload uncut', () => {
|
|
const result = runDirect('scripts/hooks/cost-tracker.js', realisticPayload);
|
|
assert.strictEqual(result.status, 0);
|
|
assert.strictEqual(result.stdout, realisticPayload, 'the old 64KB cap must not cut realistic Stop payloads');
|
|
JSON.parse(result.stdout);
|
|
})
|
|
)
|
|
passed++;
|
|
else failed++;
|
|
|
|
try {
|
|
fs.rmSync(workDir, { recursive: true, force: true });
|
|
fs.rmSync(dataHome, { recursive: true, force: true });
|
|
} catch {
|
|
/* best-effort cleanup */
|
|
}
|
|
|
|
console.log(`\n ${passed} passed, ${failed} failed\n`);
|
|
process.exit(failed > 0 ? 1 : 0);
|