voyage/lib/verification/done-line.mjs

// lib/verification/done-line.mjs
// The done line (P9 (4)). A step is "done" only when this script has written
// its line, and it writes the line only when the test command exits 0:
//
//   DONE step <N>: `<command>` exit 0 at <HEAD sha> <ISO time>
//
// appended to the step's report file. Exit 0 = written, 1 = the command failed
// (nothing written), 2 = could not run (nothing written; never green): no
// --step, a command outside the test-runner allowlist, a command that cannot
// start (not installed) or was killed, a working tree that is not a git repo.
// With no shell, an exit 126/127 is the test program's own and a failure.
//
// `--check --step <N> --report <file> [--commit <sha>]`: exit 0 when the report
// carries a well-formed line for step N (at exactly that commit, with
// --commit), 1 when it does not. /trekexecute writes the line right after the
// step's checkpoint and checks it with --commit, so the line is bound to the
// commit the test passed on.
//
// Adapted from obra/superpowers@8ca22db (MIT, (c) 2025 Jesse Vincent),
// skills/executing-plans/scripts/task-done: the completion line is appended
// only when the test command exits 0.

import { appendFileSync, existsSync, readFileSync } from 'node:fs';
import { spawnSync } from 'node:child_process';
import { resolve } from 'node:path';
import { DEFAULT_TIMEOUT_MS, allowedCommand, runCommand, screenCommand, stoppedBy } from './criteria-runner.mjs';
import { repoRoot } from './red-proof.mjs';
import { isMain } from '../util/is-main.mjs';

export function doneLineRe(step, commit) {
  const sha = commit ? String(commit).replace(/[^0-9a-f]/g, '') : '[0-9a-f]{40}';
  return new RegExp(`^DONE step ${step}: \`.+\` exit 0 at ${sha} \\d{4}-\\d{2}-\\d{2}T\\S+$`, 'm');
}

/**
 * With `commit` (the step's checkpoint sha, full 40 hex), the line must name
 * exactly that commit. A regex cannot tell a typed line from a written one; the
 * commit binds the line to the state the test ran on (/trekexecute writes the
 * line right after the checkpoint, so HEAD is the step's own commit).
 */
export function hasDoneLine(reportPath, step, commit) {
  if (!existsSync(reportPath)) return false;
  return doneLineRe(step, commit).test(readFileSync(reportPath, 'utf8'));
}

/** @returns {{status: 'written'|'failed'|'not-run', reason: string, line?: string, exit?: number|null}} */
export function writeDoneLine({ cwd, step, cmd, report, timeoutMs = DEFAULT_TIMEOUT_MS }) {
  if (!/^\d+$/.test(String(step ?? ''))) return { status: 'not-run', reason: '--step must be a step number' };
  if (!report) return { status: 'not-run', reason: '--report is required' };
  // The plan's Verify command is relative to the repo root, as in red-proof.mjs.
  const dir = repoRoot(resolve(cwd ?? process.cwd()));
  if (!dir) return { status: 'not-run', reason: `${cwd ?? process.cwd()} is not inside a git repository` };
  const allowed = allowedCommand(cmd, { cwd: dir });
  if (!allowed.allowed) return { status: 'not-run', reason: `command not run: ${allowed.reason}` };
  const screen = screenCommand(cmd);
  if (!screen.allowed) return { status: 'not-run', reason: `command blocked: ${screen.rule}` };
  const head = spawnSync('git', ['rev-parse', '--verify', '--quiet', 'HEAD'], { cwd: dir, encoding: 'utf8' });
  if (head.status !== 0) return { status: 'not-run', reason: `no git HEAD in ${dir}` };
  // No shell: the words the screen checked are the words that run.
  const r = runCommand(cmd, { cwd: dir, timeoutMs });
  // A stop is read once, by stoppedBy (round 8).
  const stopped = stoppedBy(r, { timeoutMs });
  if (stopped) return { status: 'not-run', reason: `the command ${stopped.why}`, exit: r.status };
  if (r.status !== 0) return { status: 'failed', reason: `the test command exited ${r.status}`, exit: r.status };
  const line = `DONE step ${step}: \`${cmd}\` exit 0 at ${head.stdout.trim()} ${new Date().toISOString()}`;
  appendFileSync(report, `${line}\n`);
  return { status: 'written', reason: 'the test command exited 0', line, exit: 0 };
}

const USAGE =
  'usage: done-line.mjs --step <N> --cmd "<test command>" --report <file> [--cwd <dir>] [--json]\n' +
  '       done-line.mjs --check --step <N> --report <file> [--commit <sha>]';

export function main(argv) {
  const o = {};
  let check = false;
  let json = false;
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    if (a === '--step' && argv[i + 1]) o.step = argv[++i];
    else if (a === '--cmd' && argv[i + 1]) o.cmd = argv[++i];
    else if (a === '--report' && argv[i + 1]) o.report = resolve(argv[++i]);
    else if (a === '--cwd' && argv[i + 1]) o.cwd = resolve(argv[++i]);
    else if (a === '--timeout' && argv[i + 1]) o.timeoutMs = Number(argv[++i]);
    else if (a === '--check') check = true;
    else if (a === '--commit' && argv[i + 1]) o.commit = argv[++i];
    else if (a === '--json') json = true;
    else { process.stderr.write(`done-line: unknown argument ${a}\n${USAGE}\n`); return 2; }
  }
  if (check) {
    if (!/^\d+$/.test(String(o.step ?? '')) || !o.report) { process.stderr.write(`done-line: --check needs --step and --report\n${USAGE}\n`); return 2; }
    const ok = hasDoneLine(o.report, o.step, o.commit);
    process.stdout.write(json ? `${JSON.stringify({ step: Number(o.step), done: ok })}\n` : `step ${o.step}: ${ok ? 'DONE line present' : 'no DONE line - not done'}\n`);
    return ok ? 0 : 1;
  }
  let r;
  try { r = writeDoneLine(o); }
  catch (e) { r = { status: 'not-run', reason: `done-line crashed: ${e.message}` }; }
  process.stdout.write(json ? `${JSON.stringify(r)}\n` : `done line: ${r.status.toUpperCase()} - ${r.line ?? r.reason}\n`);
  return r.status === 'written' ? 0 : r.status === 'failed' ? 1 : 2;
}

if (isMain(import.meta.url)) process.exitCode = main(process.argv.slice(2));