voyage/lib/verification/plan-scope-sweep.mjs

// lib/verification/plan-scope-sweep.mjs
// K6 — the sweep for files the plan does not name.
//
//   node plan-scope-sweep.mjs --plan <plan.md> --base <ref> [--repo <dir>] [--process <path|glob>]...
//     0 = every changed file is named by the plan or is a process file
//     1 = deviation: changed files outside the plan (listed in `outside`)
//     2 = could not run (not a git repo, unknown ref, plan missing or without steps)
//   JSON on stdout: {code, status, base, merge_base, changed, outside, planned, process}
//
// changed  = `git diff --name-only --no-renames <merge-base>` (committed AND
//            uncommitted tracked changes) + untracked, non-ignored files
// planned  = every step's `Files:` paths, its `Test first:` File, and its
//            manifest `expected_paths`
// process  = PROCESS_FILES (the plan itself, its project directory, Voyage's
//            own planning areas) + any `--process` entries
// outside  = changed − planned − process. It must be empty.
//
// A deviation is allowed only when the plan names the file in the same
// commit: the sweep reads the plan from the working tree, so adding the path
// to the step's `Files:` is what clears it.
//
// `--repo` defaults to the current directory. Paths in the plan are relative
// to the repository root (git top level), as git reports changed files.
// Paths in a plan may end in `/` (a directory) or use `*` / `**` globs; a glob
// must start with a fixed directory (`src/**` is fine, `**/*` would plan the
// whole repo and is ignored and reported in `ignored`). git output is read
// NUL-separated (-z), so non-ASCII names and spaces arrive unquoted.
//
// Borrowed: the sweep for files outside the plan from ai-native-sdlc (MIT).
// Voyage before this checked only each step's expected and forbidden paths.

import { readFileSync, existsSync, realpathSync } from 'node:fs';
import { spawnSync } from 'node:child_process';
import { resolve, relative, dirname, isAbsolute, sep } from 'node:path';
import { fileURLToPath } from 'node:url';
import { sliceSteps, parseStepFields, fieldPaths } from '../parsers/plan-schema.mjs';
import { parseManifest } from '../parsers/manifest-yaml.mjs';

// Files Voyage's own process writes while planning and executing.
export const PROCESS_FILES = Object.freeze([
  '.claude/projects/**',
  '.claude/plans/**',
  '.claude/trekplan-sessions/**',
]);

const BACKTICK_SPAN = /`([^`\n]+)`/g;
// A backticked path in `Test first:` (spaces allowed: `docs/my file.md`).
const looksLikeTickedPath = s => /[./]/.test(s) && !/^https?:/.test(s) && !s.startsWith('-') && s.trim() === s;

function pathsIn(text) {
  const out = [];
  for (const m of text.matchAll(BACKTICK_SPAN)) if (looksLikeTickedPath(m[1])) out.push(m[1]);
  return out;
}

const norm = p => p.replace(/\\/g, '/').replace(/^\.\//, '');

/** Every path the plan names: Files, Test first File, manifest expected_paths. */
export function plannedPaths(planText) {
  const out = new Set();
  for (const s of sliceSteps(planText)) {
    const f = parseStepFields(s.body);
    const files = f.get('Files');
    // One reader with the tests-only check (plan-schema.mjs fieldPaths):
    // backticked spans as written, else every path-like word.
    if (files) for (const p of fieldPaths(files.text)) out.add(norm(p));
    const tf = f.get('Test first');
    if (tf) {
      for (const line of tf.text.split('\n')) {
        if (/\bFile:/i.test(line)) for (const p of pathsIn(line)) out.add(norm(p));
      }
    }
    const man = parseManifest(s.body);
    for (const p of man?.parsed?.expected_paths ?? []) {
      if (typeof p === 'string') out.add(norm(p));
    }
  }
  return [...out].sort();
}

function globToRegExp(glob) {
  let re = '';
  for (let i = 0; i < glob.length; i++) {
    const c = glob[i];
    if (c === '*' && glob[i + 1] === '*') { re += '.*'; i++; if (glob[i + 1] === '/') i++; }
    else if (c === '*') re += '[^/]*';
    else if (c === '?') re += '[^/]';
    else re += c.replace(/[.+^${}()|[\]\\]/g, '\\$&');
  }
  return new RegExp(`^${re}$`);
}

// A glob with no fixed directory in front (`*`, `**/*`, `*.js`) names no place.
export const unboundedGlob = p => /[*?]/.test(p) && /[*?]/.test(norm(p).split('/')[0]);

function matcher(patterns) {
  const exact = new Set();
  const dirs = [];
  const globs = [];
  for (const p of patterns.map(norm)) {
    if (p.endsWith('/')) dirs.push(p);
    else if (/[*?]/.test(p)) globs.push(globToRegExp(p));
    else exact.add(p);
  }
  return f => exact.has(f) || dirs.some(d => f.startsWith(d)) || globs.some(g => g.test(f));
}

function git(repo, args) {
  const r = spawnSync('git', ['-C', repo, ...args], { encoding: 'utf-8', maxBuffer: 64 * 1024 * 1024 });
  if (r.status !== 0) throw new Error(`git ${args[0]}: ${(r.stderr || r.error?.message || '').trim().split('\n')[0]}`);
  return r.stdout;
}

const nulList = out => out.split('\0').filter(Boolean);

/**
 * @returns {{code: 0|1|2, status: string, outside?: string[], changed?: string[], planned?: string[], reason?: string}}
 */
export function sweep({ plan, base, repo = process.cwd(), process: extra = [] }) {
  const repoAbs = resolve(repo);
  const planAbs = resolve(repoAbs, plan);
  if (!existsSync(planAbs)) return { code: 2, status: 'error', reason: `plan not found: ${plan}` };
  let top;
  let mergeBase;
  let changed;
  let planText;
  try {
    planText = readFileSync(planAbs, 'utf-8');
    top = git(repoAbs, ['rev-parse', '--show-toplevel']).trim();
    mergeBase = git(repoAbs, ['merge-base', base, 'HEAD']).trim();
    const tracked = nulList(git(top, ['diff', '--name-only', '--no-renames', '-z', mergeBase]));
    const untracked = nulList(git(top, ['ls-files', '--others', '--exclude-standard', '-z']));
    changed = [...new Set([...tracked, ...untracked])].sort();
  } catch (e) {
    return { code: 2, status: 'error', reason: e.message };
  }
  if (sliceSteps(planText).length === 0) return { code: 2, status: 'error', reason: `plan has no "### Step N:" steps: ${plan}` };
  const all = plannedPaths(planText);
  const ignored = all.filter(unboundedGlob);
  const planned = all.filter(p => !unboundedGlob(p));

  const planRel = norm(relative(realpathSync(top), realpathSync(planAbs)).split(sep).join('/'));
  const processList = [...PROCESS_FILES, planRel, ...extra];
  const planDir = dirname(planRel);
  if (planDir !== '.' && planDir.startsWith('.claude/')) processList.push(`${planDir}/`);

  const isPlanned = matcher(planned);
  const isProcess = matcher(processList);
  const outside = changed.filter(f => !isPlanned(f) && !isProcess(f));
  return {
    code: outside.length === 0 ? 0 : 1,
    status: outside.length === 0 ? 'clean' : 'deviation',
    base,
    merge_base: mergeBase,
    changed,
    outside,
    planned,
    ignored,
    process: processList,
  };
}

// ---- CLI --------------------------------------------------------------------

function isMain() {
  try {
    return realpathSync(process.argv[1]) === realpathSync(fileURLToPath(import.meta.url));
  } catch {
    return false;
  }
}

if (isMain()) {
  const argv = process.argv.slice(2);
  const o = { process: [] };
  let bad = null;
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    const v = argv[i + 1];
    if (['--plan', '--base', '--repo', '--process'].includes(a)) {
      if (v === undefined || v.startsWith('--')) { bad = bad ?? `${a} needs a value`; continue; }
      i++;
      if (a === '--plan') o.plan = v;
      else if (a === '--base') o.base = v;
      else if (a === '--repo') o.repo = v;
      else o.process.push(v);
    } else bad = bad ?? `unknown argument: ${a}`;
  }
  let result;
  if (bad || !o.plan || !o.base) {
    result = { code: 2, status: 'error', reason: bad ?? 'usage: plan-scope-sweep.mjs --plan <plan.md> --base <ref> [--repo <dir>] [--process <path|glob>]...' };
  } else {
    result = sweep(o);
  }
  process.stdout.write(JSON.stringify(result, null, 2) + '\n');
  if (result.code === 1) process.stderr.write(`plan-scope-sweep: ${result.outside.length} file(s) outside the plan:\n${result.outside.map(f => `  ${f}`).join('\n')}\n`);
  process.exit(result.code);
}