voyage/tests/hooks/test-lock-green.test.mjs
Kjell Tore Guttormsen 29b4ac91b3
fix: round 7 of the release review of 6.3.0, for 6.3.1
Round 7 (516dffa..45aa9e1, WARN: 12 MAJOR, 0 BLOCKER) and the fence defect
found while writing its review.md. Each fix began with a test that failed on
0f400d3 (v6.3.0); suite 2208 (2206/0/2), 14 tests more.

- Tests-only (operator 2026-10-11): the plan's Files: alone decides, and the
  text says so (red-proof, trekexecute Sub-step B, step-implementer,
  HANDOVER-CONTRACTS). red-proof no longer reads the step's diff, so a change
  already in the tree when the step began no longer counts against it, and a
  plan placed outside .claude/ reads the same. The round-6 test that had the
  diff overrule the plan is rewritten to the new rule.
- The Files: reader keeps a plain file beside a backticked path
  (", Dockerfile", "the CLI entry src/cli.mjs", "and Makefile"). Measured on
  the 520 Files: fields in 182 plans: no field reads differently.
- Red proof reports a command its timeout killed as killed after the timeout,
  not "could not start"; the release check tells a timeout from output past
  its buffer and from another signal. One reading of a stop
  (criteria-runner stoppedBy) for red proof, the criteria runner and the
  release check.
- A trailing `# comment` is dropped in a backticked check too, and in a
  command passed as written, so the words screened are the words run.
- The release check reads a relative --review in --repo.
- The 15-minute timeout is defined once (criteria-runner.mjs).
- The findings check reads each cited file once per validation.
- One isMain helper (lib/util/is-main.mjs) for every CLI: the 31 copies of
  the realpath guard and the 20 modules still on the file:// guard, which
  exited 0 having done nothing under a symlink or a path with a space.
- The Bash guard writes its no-one-to-ask refusal once, on a direct condition.
- The findings check ends a ```json block only at a fence on its own line, so
  three backticks inside a JSON string no longer end it (also in 6.2.0).
- Brief-conformance notes: a test for test-lock green on exit 127 (it
  passed at once; it fails when 127 is read as could-not-run); the prose now
  names the git revision `@~1` as the one leading-@ exception.

Not changed: the example plan's steps 1-2 keep their tests-only warning
(operator decision 2026-10-09; the r5 test records it). Brief note 4 (a
Regression: whose runner is not installed goes to the fix rounds) is a
routing question for the operator.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 09:11:57 +02:00

109 lines
5.5 KiB
JavaScript

// tests/hooks/test-lock-green.test.mjs
// The test lock's green mark (operator decision 2026-10-08, voyage-lekerepo
// trial point 7). The stop guard blocked Stop three times while the executor
// waited for the controller in the background, though the step's test was
// already green. Now:
// - `test-lock.mjs green --cmd "<Verify>"` RUNS the step's test command and
// marks the lock "seen green" only on exit 0 (a command proves it, never a
// word);
// - the stop guard lets a green-marked lock stop; the write guard still
// refuses the locked files — the lock still protects the test;
// - `test-lock.mjs pending` clears the mark when a fix round starts.
import { test } from 'node:test';
import { strict as assert } from 'node:assert';
import { spawnSync } from 'node:child_process';
import { writeFileSync, mkdirSync, readFileSync } from 'node:fs';
import { join } from 'node:path';
import { runHook } from '../helpers/hook-helper.mjs';
import { ROOT, makeRepo, parseJsonOut } from './guard-helpers.mjs';
const CLI = join(ROOT, 'lib', 'util', 'test-lock.mjs');
const STOP = join(ROOT, 'hooks', 'scripts', 'stop-test-lock.mjs');
const PRE_WRITE = join(ROOT, 'hooks', 'scripts', 'pre-write-executor.mjs');
const SESS = `sess-green-${process.pid}-${Date.now()}`;
const CMD = 'node --test tests/step.test.mjs';
function cli(repo, args) {
const r = spawnSync(process.execPath, [CLI, ...args], { cwd: repo, encoding: 'utf8', env: { ...process.env, CLAUDE_CODE_SESSION_ID: SESS } });
return { code: r.status, stdout: r.stdout, stderr: r.stderr };
}
function lockedRepo(testBody) {
const repo = makeRepo('main');
mkdirSync(join(repo, 'tests'), { recursive: true });
writeFileSync(join(repo, 'tests', 'step.test.mjs'), [
"import { test } from 'node:test';",
"import { strict as assert } from 'node:assert';",
`test('step', () => { ${testBody} });`,
'',
].join('\n'));
assert.equal(cli(repo, ['lock', '--files', 'tests/step.test.mjs', '--step', '3', '--cmd', CMD]).code, 0);
return repo;
}
const stop = (repo) => ({ hook_event_name: 'Stop', session_id: SESS, cwd: repo, stop_hook_active: false });
const edit = (file_path) => ({ hook_event_name: 'PreToolUse', tool_name: 'Edit', tool_input: { file_path, old_string: 'x', new_string: 'z' } });
test('green: the step\'s test passes -> the lock is marked green, Stop goes through, the test file stays locked', async () => {
const repo = lockedRepo('assert.equal(1, 1);');
const g = cli(repo, ['green', '--cmd', CMD]);
assert.equal(g.code, 0, g.stderr);
assert.ok(JSON.parse(cli(repo, ['status']).stdout).green_at, 'status shows green_at');
assert.equal(parseJsonOut((await runHook(STOP, stop(repo))).stdout), null, 'a green lock does not block Stop');
const w = await runHook(PRE_WRITE, edit(join(repo, 'tests', 'step.test.mjs')));
assert.equal(w.code, 2, 'the test file is still locked against edits');
});
test('green: the test fails -> exit 1, no mark, Stop is still refused', async () => {
const repo = lockedRepo('assert.equal(1, 2);');
assert.equal(cli(repo, ['green', '--cmd', CMD]).code, 1);
assert.equal(JSON.parse(cli(repo, ['status']).stdout).green_at, null);
assert.equal(parseJsonOut((await runHook(STOP, stop(repo))).stdout)?.decision, 'block');
});
test('green: a --cmd that is not the stored test command is never run -> exit 2, no mark', () => {
const repo = lockedRepo('assert.equal(1, 1);');
const g = cli(repo, ['green', '--cmd', 'echo ok']);
assert.equal(g.code, 2, g.stderr);
assert.equal(JSON.parse(cli(repo, ['status']).stdout).green_at, null);
});
test('green: no lock to mark -> exit 1', () => {
const repo = makeRepo('main');
assert.equal(cli(repo, ['green', '--cmd', CMD]).code, 1);
});
test('pending: a fix round clears the mark, and Stop is refused again', async () => {
const repo = lockedRepo('assert.equal(1, 1);');
assert.equal(cli(repo, ['green', '--cmd', CMD]).code, 0);
assert.equal(cli(repo, ['pending']).code, 0);
assert.equal(JSON.parse(cli(repo, ['status']).stdout).green_at, null);
assert.equal(parseJsonOut((await runHook(STOP, stop(repo))).stdout)?.decision, 'block');
});
test('re-lock of the same step starts without a mark', () => {
const repo = lockedRepo('assert.equal(1, 1);');
assert.equal(cli(repo, ['green', '--cmd', CMD]).code, 0);
assert.equal(cli(repo, ['lock', '--files', 'tests/step.test.mjs', '--step', '3', '--cmd', CMD]).code, 0);
assert.equal(JSON.parse(cli(repo, ['status']).stdout).green_at, null);
});
test('trekexecute: D1 marks the lock green through the command, a fix round marks it pending', () => {
const md = readFileSync(join(ROOT, 'commands', 'trekexecute.md'), 'utf8');
assert.match(md, /test-lock\.mjs green\n/);
assert.match(md, /test-lock\.mjs lock --files \{test files\} --step \{N\} --cmd "\{Verify command\}"/);
assert.match(md, /test-lock\.mjs pending/);
});
test('green: exit 127 from the test program itself is a red -> exit 1, no mark (release review of 6.3.0, round 7)', () => {
const repo = makeRepo('main');
mkdirSync(join(repo, 'tests'), { recursive: true });
// The tool the step builds is not there yet: bash runs, and exits 127 for it.
writeFileSync(join(repo, 'tests', 'e2e.sh'), './bin/tool\n');
const cmd = 'bash tests/e2e.sh';
assert.equal(cli(repo, ['lock', '--files', 'tests/e2e.sh', '--step', '3', '--cmd', cmd]).code, 0);
const g = cli(repo, ['green', '--cmd', cmd]);
assert.equal(g.code, 1, g.stderr);
assert.match(g.stderr, /exited 127/);
assert.equal(JSON.parse(cli(repo, ['status']).stdout).green_at, null);
});