voyage/lib/util/park-attempt-files.mjs

#!/usr/bin/env node
// lib/util/park-attempt-files.mjs
// A step sent back to the plan (`fix_rounds` 4) is reverted with its new files
// left on disk, untracked: nothing the step made is deleted. On --resume the
// re-planned step is built fresh, but the stale files were still there, and in
// voyage-lekerepo trial 5 (finding 4) an old tests/batch.sh holding the
// rejected line would have passed Verify, the manifest and the success
// criterion. Only the plan critic caught it.
//
// Before the fresh build the executor parks them: every file the attempt
// created (a `new file mode` entry in step-{N}-upward.diff) that is still
// untracked on disk moves to <git dir>/voyage/parked/step-<N>-attempt-<k>/
// under its own path. The git dir, like the test lock's, is outside the work
// tree, so a parked file never comes back as a new file of the next build.
// Moved, never deleted, and never over a file already parked there.
//
// Usage:
//   node lib/util/park-attempt-files.mjs --diff <step-N-upward.diff> --step <N> --attempt <k> [--cwd <repo>]
// Prints {"parked": [paths], "kept": [{"path", "reason", "blocking"}], "to": dir}.
// Exit: 0 = no file the attempt made is left in the tree; 1 = one still is
// (a header it could not read, a move that failed, a target already taken):
// the run stops; 2 = could not run (bad usage, unreadable diff, not a
// repository). Neither 1 nor 2 is ever "the tree is clean".

import { readFileSync, mkdirSync, renameSync, lstatSync } from 'node:fs';
import { join, dirname, resolve, relative, isAbsolute } from 'node:path';
import { spawnSync } from 'node:child_process';
import { isMain } from './is-main.mjs';

/**
 * What a unified git diff creates: `paths` read from a `diff --git a/X b/X`
 * header followed by `new file mode`, and `unread`, the raw headers of new
 * files whose header is not that form (another prefix, a quoted path).
 */
export function newFilesInDiff(diffText) {
  const paths = [];
  const unread = [];
  let header = null;
  for (const line of String(diffText).split('\n')) {
    if (line.startsWith('diff --git ')) {
      header = line;
      continue;
    }
    if (header !== null && /^new file mode \d+$/.test(line)) {
      // Both names are the same for a new file, so a space in it is read too.
      const m = header.match(/^diff --git a\/(.+) b\/\1$/);
      if (m) paths.push(m[1]);
      else unread.push(header);
      header = null;
    }
  }
  return { paths, unread };
}

function lexists(abs) {
  try {
    lstatSync(abs);
    return true;
  } catch {
    return false;
  }
}

/**
 * @param {{ diffText: string, step: string|number, attempt: string|number, cwd?: string }} args
 * @returns {{ parked: string[], kept: Array<{path: string, reason: string, blocking: boolean}>, to: string }}
 */
export function parkAttemptFiles({ diffText, step, attempt, cwd = process.cwd() }) {
  const root = resolve(cwd);
  const gitDir = spawnSync('git', ['rev-parse', '--absolute-git-dir'], { cwd: root, encoding: 'utf8' }).stdout.trim();
  const to = join(gitDir, 'voyage', 'parked', `step-${step}-attempt-${attempt}`);
  const trackedPaths = new Set(
    spawnSync('git', ['ls-files', '-z'], { cwd: root, encoding: 'utf8' }).stdout.split('\0').filter(Boolean),
  );
  const { paths, unread } = newFilesInDiff(diffText);
  const parked = [];
  const kept = unread.map((h) => ({ path: h, reason: 'diff header not read: move this file out by hand', blocking: true }));
  for (const path of paths) {
    const abs = resolve(root, path);
    const rel = relative(root, abs);
    if (isAbsolute(path) || rel === '' || rel.startsWith('..') || isAbsolute(rel) || rel.split(/[\\/]/)[0] === '.git') {
      kept.push({ path, reason: 'outside the repository: refused', blocking: false });
      continue;
    }
    if (!lexists(abs)) {
      kept.push({ path, reason: 'not on disk: nothing to park', blocking: false });
      continue;
    }
    if (trackedPaths.has(rel.split('\\').join('/'))) {
      kept.push({ path, reason: 'tracked since the attempt: not the executor\'s to move', blocking: false });
      continue;
    }
    const target = join(to, rel);
    if (lexists(target)) {
      kept.push({ path, reason: `already parked at ${target}: never overwritten, move it by hand`, blocking: true });
      continue;
    }
    try {
      mkdirSync(dirname(target), { recursive: true });
      renameSync(abs, target);
      parked.push(rel);
    } catch (e) {
      kept.push({ path, reason: `could not move: ${e.message}`, blocking: true });
    }
  }
  return { parked, kept, to };
}

if (isMain(import.meta.url)) {
  const argv = process.argv.slice(2);
  const opt = (name) => {
    const i = argv.indexOf(name);
    return i === -1 ? undefined : argv[i + 1];
  };
  const diff = opt('--diff');
  const step = opt('--step');
  const attempt = opt('--attempt');
  const cwd = opt('--cwd') ?? process.cwd();
  if (!diff || !/^[0-9]+$/.test(step ?? '') || !/^[0-9]+$/.test(attempt ?? '')) {
    process.stderr.write('Usage: park-attempt-files.mjs --diff <step-N-upward.diff> --step <N> --attempt <k> [--cwd <repo>]\n');
    process.exit(2);
  }
  let diffText;
  try {
    diffText = readFileSync(diff, 'utf8');
  } catch (e) {
    process.stderr.write(`park-attempt-files: cannot read ${diff}: ${e.message}\n`);
    process.exit(2);
  }
  if (spawnSync('git', ['rev-parse', '--git-dir'], { cwd, encoding: 'utf8' }).status !== 0) {
    process.stderr.write(`park-attempt-files: ${cwd} is not a git repository\n`);
    process.exit(2);
  }
  const result = parkAttemptFiles({ diffText, step, attempt, cwd });
  process.stdout.write(JSON.stringify(result, null, 2) + '\n');
  process.exit(result.kept.some((k) => k.blocking) ? 1 : 0);
}