Independent read-only review of c56f852..2d29966 (2026-10-08), each defect reproduced by the reviewer; each new test fails on that code. - test-lock green ran ANY allowlisted command: `green --cmd "git status"` marked a red step green and the stop guard let it stop. The lock now stores the step's test command (`lock --cmd`); `green` runs only that one (a different --cmd, or a lock without one, exits 2). trekexecute D1 calls `green` with no command, which also removes the quoting hazard. - plan-gate --accept-open worked at round 1 and passed the gate; it now refuses while rounds are left. - findings-schema --repo-root swallowed a following flag, or took a root that does not exist, and silently skipped the line check: exit 2. - brief-review-stamp hashed only the body, so a changed `framing` or `research_topics` stayed "current"; it now covers the reviewed frontmatter too (only the post-review stamps are left out). - red-proof red_kind read an assertion message naming SyntaxError as a load error; the signatures are now specific. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
122 lines
6.9 KiB
JavaScript
122 lines
6.9 KiB
JavaScript
// tests/lib/independent-review-fixes.test.mjs
|
|
// Findings of the independent review of c56f852..2d29966 (2026-10-08), each
|
|
// verified by the reviewer by running it; each test fails on that code.
|
|
|
|
import { test } from 'node:test';
|
|
import { strict as assert } from 'node:assert';
|
|
import { spawnSync } from 'node:child_process';
|
|
import { mkdtempSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
|
|
import { join, dirname } from 'node:path';
|
|
import { tmpdir } from 'node:os';
|
|
import { fileURLToPath } from 'node:url';
|
|
import { runHook } from '../helpers/hook-helper.mjs';
|
|
import { makeRepo, parseJsonOut } from '../hooks/guard-helpers.mjs';
|
|
import { recordVerdict, planHash, acceptOpen, gatePlan } from '../../lib/validators/plan-gate.mjs';
|
|
import { stampBriefReview, checkBriefReview } from '../../lib/validators/brief-review-stamp.mjs';
|
|
import { stampIntentApproval } from '../../lib/validators/intent-approval.mjs';
|
|
import { buildPlan } from '../helpers/plan-v18-builder.mjs';
|
|
|
|
const HERE = dirname(fileURLToPath(import.meta.url));
|
|
const ROOT = join(HERE, '..', '..');
|
|
const LOCK = join(ROOT, 'lib', 'util', 'test-lock.mjs');
|
|
const STOP = join(ROOT, 'hooks', 'scripts', 'stop-test-lock.mjs');
|
|
const SESS = `sess-review-${process.pid}-${Date.now()}`;
|
|
|
|
// --- 1 + 5: the green mark runs the step's OWN test command, stored at lock time
|
|
|
|
function lockRepo(withCmd) {
|
|
const repo = makeRepo('main');
|
|
mkdirSync(join(repo, 'tests'), { recursive: true });
|
|
writeFileSync(join(repo, 'tests', 'a.test.mjs'), "import { test } from 'node:test';\nimport assert from 'node:assert';\ntest('a', () => assert.equal(1, 2));\n");
|
|
const args = ['lock', '--files', 'tests/a.test.mjs', '--step', '1'];
|
|
if (withCmd) args.push('--cmd', 'node --test tests/a.test.mjs');
|
|
const r = spawnSync(process.execPath, [LOCK, ...args], { cwd: repo, encoding: 'utf8', env: { ...process.env, CLAUDE_CODE_SESSION_ID: SESS } });
|
|
assert.equal(r.status, 0, r.stderr);
|
|
return repo;
|
|
}
|
|
const lockCli = (repo, args) => spawnSync(process.execPath, [LOCK, ...args], { cwd: repo, encoding: 'utf8', env: { ...process.env, CLAUDE_CODE_SESSION_ID: SESS } });
|
|
|
|
test('green: another allowed command (git status) can never mark a red step green', async () => {
|
|
const repo = lockRepo(true);
|
|
assert.notEqual(lockCli(repo, ['green', '--cmd', 'git status']).status, 0);
|
|
assert.equal(lockCli(repo, ['green']).status, 1, 'the stored test command is red');
|
|
assert.equal(JSON.parse(lockCli(repo, ['status']).stdout).green_at, null);
|
|
const stop = await runHook(STOP, { hook_event_name: 'Stop', session_id: SESS, cwd: repo, stop_hook_active: false });
|
|
assert.equal(parseJsonOut(stop.stdout)?.decision, 'block');
|
|
});
|
|
|
|
test('green: a lock that names no test command is never marked green (exit 2)', () => {
|
|
const repo = lockRepo(false);
|
|
assert.equal(lockCli(repo, ['green', '--cmd', 'node --test tests/a.test.mjs']).status, 2);
|
|
});
|
|
|
|
test('green without --cmd runs the stored command; status shows it', () => {
|
|
const repo = lockRepo(true);
|
|
writeFileSync(join(repo, 'tests', 'a.test.mjs'), "import { test } from 'node:test';\ntest('a', () => {});\n");
|
|
assert.equal(lockCli(repo, ['green']).status, 0);
|
|
assert.equal(JSON.parse(lockCli(repo, ['status']).stdout).cmd, 'node --test tests/a.test.mjs');
|
|
});
|
|
|
|
test('prose: the helper locks with --cmd, and D1 calls green without re-quoting the command', () => {
|
|
assert.match(readFileSync(join(ROOT, 'agents', 'step-implementer.md'), 'utf8'), /test-lock\.mjs lock --files <test files> --step \{step\} --cmd "\{Verify command\}"/);
|
|
const ex = readFileSync(join(ROOT, 'commands', 'trekexecute.md'), 'utf8');
|
|
assert.match(ex, /test-lock\.mjs green`?\n/);
|
|
assert.doesNotMatch(ex, /test-lock\.mjs green --cmd/);
|
|
});
|
|
|
|
// --- 2: --accept-open only after the last round -------------------------------
|
|
|
|
const BOTH = [{ agent: 'plan-critic', present: true }, { agent: 'scope-guardian', present: true }];
|
|
test('--accept-open refuses while rounds are left: revise instead', () => {
|
|
const t = buildPlan();
|
|
const r = recordVerdict(t, { findings: [{ id: 'm', severity: 'major', text: 'weak test' }], sources: BOTH }, { reviewed: planHash(t) });
|
|
const a = acceptOpen(r.text);
|
|
assert.equal(a.code, 1);
|
|
assert.match(a.message, /round\(s\) left/);
|
|
assert.equal(gatePlan(r.text).code, 1);
|
|
});
|
|
|
|
// --- 3: --repo-root never swallows a flag or accepts a missing root ----------
|
|
|
|
test('findings-schema: --repo-root followed by a flag, or naming no directory, is a usage error (exit 2)', () => {
|
|
const dir = mkdtempSync(join(tmpdir(), 'voyage-root-'));
|
|
try {
|
|
const out = join(dir, 'r.md');
|
|
writeFileSync(out, '```json\n{"reviewer":"x","findings":[]}\n```\n');
|
|
const cli = (...a) => spawnSync(process.execPath, [join(ROOT, 'lib', 'review', 'findings-schema.mjs'), ...a], { encoding: 'utf8' });
|
|
assert.equal(cli('--repo-root', '--json', out).status, 2);
|
|
assert.equal(cli('--repo-root', join(dir, 'nope'), out).status, 2);
|
|
assert.equal(cli('--repo-root', dir, out).status, 0);
|
|
} finally {
|
|
rmSync(dir, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
// --- 4: the stamp covers the frontmatter the reviewer judges -----------------
|
|
|
|
const BRIEF = ['---', 'type: trekbrief', 'framing: preserve', 'research_topics: 2', '---', '', '## Intent', '', 'Why.', '', '## Goal', '', 'What.', ''].join('\n');
|
|
|
|
test('brief stamp: changing framing or research_topics after the review makes it stale', () => {
|
|
const s = stampBriefReview(BRIEF).text;
|
|
assert.equal(checkBriefReview(s.replace('framing: preserve', 'framing: replace')).state, 'stale');
|
|
assert.equal(checkBriefReview(s.replace('research_topics: 2', 'research_topics: 0')).state, 'stale');
|
|
assert.equal(checkBriefReview(stampIntentApproval(s).text).state, 'current', 'the intent stamp still keeps it current');
|
|
});
|
|
|
|
// --- 6: red_kind does not read an assertion message as a load error ----------
|
|
|
|
test('red proof: a named test whose assertion mentions SyntaxError is a test-failure', async () => {
|
|
const { proveRed } = await import('../../lib/verification/red-proof.mjs');
|
|
const repo = makeRepo('main');
|
|
mkdirSync(join(repo, 'lib'));
|
|
writeFileSync(join(repo, 'lib', 'p.mjs'), 'export function parse(s) { return s; }\n');
|
|
spawnSync('git', ['add', 'lib/p.mjs'], { cwd: repo });
|
|
spawnSync('git', ['commit', '-q', '-m', 'base'], { cwd: repo });
|
|
const base = spawnSync('git', ['rev-parse', 'HEAD'], { cwd: repo, encoding: 'utf8' }).stdout.trim();
|
|
mkdirSync(join(repo, 'tests'));
|
|
writeFileSync(join(repo, 'tests', 'p.test.mjs'), "import { test } from 'node:test';\nimport assert from 'node:assert';\nimport { parse } from '../lib/p.mjs';\ntest('throws on bad input', () => { assert.throws(() => parse('{'), SyntaxError); });\n");
|
|
writeFileSync(join(repo, 'lib', 'p.mjs'), 'export function parse(s) { return JSON.parse(s); }\n');
|
|
const r = proveRed({ cwd: repo, base, cmd: 'node --test tests/p.test.mjs', tests: ['tests/p.test.mjs'] });
|
|
assert.equal(r.status, 'proven', JSON.stringify(r).slice(0, 400));
|
|
assert.equal(r.red_kind, 'test-failure');
|
|
});
|