Function findNestedGitRepos

src/extraction/index.ts:410–447

* Find git repositories nested under `absDir` (inclusive), shallow bounded BFS. * Stops descending at each repo root found — contents belong to that repo's own * enumeration. Skips default-ignored dirs (`node_modules` can contain `.git` * from npm git-dependencies — that never makes it project co

(absDir: string, relPrefix: string)

 * data dirs. Depth- and entry-capped so a huge ignored tree can't stall the scan.
 */
function findNestedGitRepos(absDir: string, relPrefix: string): string[] {
  const found: string[] = [];
  const defaults = defaultsOnlyIgnore();
  const queue: Array<{ abs: string; rel: string; depth: number }> = [
    { abs: absDir, rel: relPrefix, depth: 0 },
  ];
  let examined = 0;
  while (queue.length > 0) {
    const { abs, rel, depth } = queue.shift()!;
    if (++examined > EMBEDDED_REPO_SEARCH_ENTRIES) {
      logDebug('Embedded-repo search entry cap hit — deeper repos (if any) not discovered', { under: relPrefix });
      break;
    }
    const cls = classifyGitDir(abs);
    if (cls === 'worktree') {
      continue; // a git worktree duplicates an already-indexed repo (#848) — skip
    }
    if (cls === 'embedded') {
      found.push(rel);
      continue; // its own git handles everything below
    }
    if (depth >= EMBEDDED_REPO_SEARCH_DEPTH) continue;
    let entries: fs.Dirent[];
    try {
      entries = fs.readdirSync(abs, { withFileTypes: true });
    } catch {
      continue;
    }
    for (const entry of entries) {
      if (!entry.isDirectory()) continue;
      if (entry.name === '.git' || isCodeGraphDataDir(entry.name)) continue;
      const childRel = rel + entry.name + '/';
      if (defaults.ignores(childRel)) continue;
      queue.push({ abs: path.join(abs, entry.name), rel: childRel, depth: depth + 1 });
    }
  }
  return found;
}

/**
 * Workspace-scope ignore matcher. Ordinary paths get the root's matcher