From 73bbbde01dcdf5da4bca9fa57be44a5cd8ebd60d Mon Sep 17 00:00:00 2001
From: kubi <140750+kubi-dev@users.noreply.github.com>
Date: Sat, 18 Jul 2026 01:32:48 +0700
Subject: [PATCH] fix frontmatter scans to respect git excludes (#2462)

---
 src/commands/frontmatter.ts          |  8 ++++
 src/core/brain-writer.ts             | 15 ++++++-
 src/core/git-visible-files.ts        | 59 ++++++++++++++++++++++++++++
 test/brain-writer-walk-prune.test.ts | 46 +++++++++++++++++++++-
 4 files changed, 125 insertions(+), 3 deletions(-)
 create mode 100644 src/core/git-visible-files.ts

diff --git a/src/commands/frontmatter.ts b/src/commands/frontmatter.ts
index 4e5295a9d..951e35905 100644
--- a/src/commands/frontmatter.ts
+++ b/src/commands/frontmatter.ts
@@ -30,6 +30,7 @@ import {
   type AuditReport,
   type AuditFix,
 } from '../core/brain-writer.ts';
+import { collectGitVisibleFiles } from '../core/git-visible-files.ts';
 import { isSyncable, pruneDir, slugifyPath } from '../core/sync.ts';
 
 export async function runFrontmatter(args: string[]): Promise<void> {
@@ -272,6 +273,13 @@ export function collectFiles(
   if (st.isFile()) {
     return [target];
   }
+
+  const gitFiles = collectGitVisibleFiles(target, (rel) => isSyncable(rel, { strategy: 'markdown' }));
+  if (gitFiles) {
+    if (visitDir) visitDir(target);
+    return gitFiles;
+  }
+
   const out: string[] = [];
   const stack = [target];
   if (visitDir) visitDir(target);
diff --git a/src/core/brain-writer.ts b/src/core/brain-writer.ts
index ad17f41b9..a65e6864b 100644
--- a/src/core/brain-writer.ts
+++ b/src/core/brain-writer.ts
@@ -22,6 +22,7 @@ import { join, relative, resolve, dirname, basename, isAbsolute } from 'path';
 import type { BrainEngine } from './engine.ts';
 import type { ProgressReporter } from './progress.ts';
 import { gbrainPath } from './config.ts';
+import { collectGitVisibleFiles } from './git-visible-files.ts';
 import {
   parseMarkdown,
   type ParseValidationCode,
@@ -579,7 +580,7 @@ function scanOneSource(
   let ignoredMissingOpen = 0;
   let interrupted = false;
 
-  walkDir(rootResolved, (absPath) => {
+  const visitFile = (absPath: string): boolean | void => {
     // Per-file deadline + abort gate. Deadline is the load-bearing
     // wall-clock bound (sync I/O blocks the event loop so timer-based
     // AbortSignal.timeout can't fire mid-walk — codex C1).
@@ -625,7 +626,17 @@ function scanOneSource(
       opts.onProgress.tick(50);
     }
     return true;
-  }, opts.visitDir);
+  };
+
+  const gitFiles = collectGitVisibleFiles(rootResolved, (rel) => isSyncable(rel, { strategy: 'markdown' }));
+  if (gitFiles) {
+    if (opts.visitDir) opts.visitDir(rootResolved);
+    for (const absPath of gitFiles) {
+      if (visitFile(absPath) === false) break;
+    }
+  } else {
+    walkDir(rootResolved, visitFile, opts.visitDir);
+  }
 
   if (opts.onProgress) {
     opts.onProgress.heartbeat(`scanned ${scanned} pages in ${sourceId}`);
diff --git a/src/core/git-visible-files.ts b/src/core/git-visible-files.ts
new file mode 100644
index 000000000..441147523
--- /dev/null
+++ b/src/core/git-visible-files.ts
@@ -0,0 +1,59 @@
+import { execFileSync } from 'child_process';
+import { lstatSync } from 'fs';
+import { join } from 'path';
+
+/**
+ * Return files visible to git from `dir`, respecting .gitignore,
+ * .git/info/exclude, and global git excludes. Returns null when `dir` is not
+ * inside a git work tree or git is unavailable, so callers can keep their
+ * existing filesystem-walk fallback.
+ */
+export function collectGitVisibleFiles(
+  dir: string,
+  acceptRelPath: (relPath: string) => boolean,
+): string[] | null {
+  let stdout: string;
+  try {
+    stdout = execFileSync(
+      'git',
+      ['-C', dir, 'ls-files', '--cached', '--others', '--exclude-standard', '-z'],
+      { encoding: 'utf8', maxBuffer: 512 * 1024 * 1024, stdio: ['ignore', 'pipe', 'ignore'] },
+    );
+  } catch {
+    return null;
+  }
+
+  const ignoredTracked = new Set<string>();
+  try {
+    const ignoredStdout = execFileSync(
+      'git',
+      ['-C', dir, 'ls-files', '-ci', '--exclude-standard', '-z'],
+      { encoding: 'utf8', maxBuffer: 512 * 1024 * 1024, stdio: ['ignore', 'pipe', 'ignore'] },
+    );
+    for (const rel of ignoredStdout.split('\0')) {
+      if (rel) ignoredTracked.add(rel);
+    }
+  } catch {
+    // Best effort: older Git or unusual worktrees still get the standard list.
+  }
+
+  const files: string[] = [];
+  for (const rel of stdout.split('\0')) {
+    if (!rel) continue;
+    if (ignoredTracked.has(rel)) continue;
+    const normalizedRel = rel.replace(/\\/g, '/');
+    if (!acceptRelPath(normalizedRel)) continue;
+
+    const full = join(dir, rel);
+    let st: ReturnType<typeof lstatSync>;
+    try {
+      st = lstatSync(full);
+    } catch {
+      continue;
+    }
+    if (st.isSymbolicLink() || !st.isFile()) continue;
+    files.push(full);
+  }
+
+  return files.sort();
+}
diff --git a/test/brain-writer-walk-prune.test.ts b/test/brain-writer-walk-prune.test.ts
index 4e668f063..1cd3540a0 100644
--- a/test/brain-writer-walk-prune.test.ts
+++ b/test/brain-writer-walk-prune.test.ts
@@ -19,9 +19,10 @@
  */
 import { describe, expect, test, beforeAll, afterAll } from 'bun:test';
 import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'fs';
+import { execFileSync } from 'child_process';
 import { join } from 'path';
 import { tmpdir } from 'os';
-import { walkDir } from '../src/core/brain-writer.ts';
+import { scanBrainSources, walkDir } from '../src/core/brain-writer.ts';
 import { collectFiles } from '../src/commands/frontmatter.ts';
 
 let root: string;
@@ -148,3 +149,46 @@ describe('collectFiles (frontmatter.ts) — descent-time pruning parity', () =>
     expect(files).toEqual([target]);
   });
 });
+
+describe('frontmatter walkers — git-visible file parity', () => {
+  test('collectFiles respects .git/info/exclude like sync/import', () => {
+    const repo = mkdtempSync(join(tmpdir(), 'frontmatter-git-visible-'));
+    try {
+      execFileSync('git', ['init'], { cwd: repo, stdio: 'ignore' });
+      mkdirSync(join(repo, 'people'), { recursive: true });
+      mkdirSync(join(repo, 'local-skills'), { recursive: true });
+      writeFileSync(join(repo, '.git', 'info', 'exclude'), 'local-skills/\n');
+      writeFileSync(join(repo, 'people', 'alice.md'), '---\ntitle: Alice\n---\n\nbody\n');
+      writeFileSync(join(repo, 'local-skills', 'SKILL.md'), '---\nname: bad\n# malformed frontmatter\n');
+
+      const files = collectFiles(repo).map((f) => f.replace(repo + '/', ''));
+      expect(files).toContain('people/alice.md');
+      expect(files).not.toContain('local-skills/SKILL.md');
+    } finally {
+      rmSync(repo, { recursive: true, force: true });
+    }
+  });
+
+  test('scanBrainSources ignores git-excluded malformed markdown', async () => {
+    const repo = mkdtempSync(join(tmpdir(), 'frontmatter-audit-git-visible-'));
+    try {
+      execFileSync('git', ['init'], { cwd: repo, stdio: 'ignore' });
+      mkdirSync(join(repo, 'people'), { recursive: true });
+      mkdirSync(join(repo, 'local-skills'), { recursive: true });
+      writeFileSync(join(repo, '.git', 'info', 'exclude'), 'local-skills/\n');
+      writeFileSync(join(repo, 'people', 'alice.md'), '---\ntitle: Alice\n---\n\nbody\n');
+      writeFileSync(join(repo, 'local-skills', 'SKILL.md'), '---\nname: bad\n# malformed frontmatter\n');
+
+      const engine = {
+        executeRaw: async () => [{ id: 'repo', local_path: repo }],
+      } as any;
+      const report = await scanBrainSources(engine, { sourceId: 'repo' });
+
+      expect(report.total).toBe(0);
+      expect(report.per_source[0].files_scanned).toBe(1);
+      expect(report.per_source[0].sample).toEqual([]);
+    } finally {
+      rmSync(repo, { recursive: true, force: true });
+    }
+  });
+});