[env] fix: Improve License Check Hook Flexibility

.github/workflows/sanity.yml

@@ -12,7 +12,7 @@
 # - `special_sanity`: a suite of quick sanity tests
 # - `special_standalone`: a set of test that are designed to run in dedicated environments
 
-# Accelerators for tests 
+# Accelerators for tests
 # - By default tests are run with GPU available, except for the ones under `special_npu`, and any test script whose name ends with `on_cpu.py`.
 # - For test scripts with `on_cpu.py` name suffix would be tested on CPU resources in linux environment.
 
@@ -78,7 +78,7 @@ jobs:
           pytest -s -x tests/special_sanity
       - name: Run license test
         run: |
-          python3 tests/special_sanity/check_license.py --directory .
+          python3 tests/special_sanity/check_license.py --directories .
       - name: Assert naming convention
         run: |
           if grep -rIn --exclude-dir=.git --exclude-dir=.github --exclude-dir=venv --exclude-dir=__pycache__ 'veRL' .; then

.pre-commit-config.yaml

@@ -32,6 +32,6 @@ repos:
     hooks:
       - id: check-license
         name: Check license
-        entry: python3 tests/special_sanity/check_license.py --directory .
+        entry: python3 tests/special_sanity/check_license.py --directories examples recipe scripts tests verl setup.py
         language: python
         pass_filenames: false

tests/special_sanity/check_license.py

@@ -37,11 +37,19 @@
 
 if __name__ == "__main__":
     parser = ArgumentParser()
-    parser.add_argument("--directory", "-d", required=True, type=str)
+    parser.add_argument(
+        "--directories",
+        "-d",
+        required=True,
+        type=Path,
+        nargs="+",
+        help="List of directories to check for license headers",
+    )
     args = parser.parse_args()
-    directory_in_str = args.directory
 
-    pathlist = Path(directory_in_str).glob("**/*.py")
+    # Collect all Python files from specified directories
+    pathlist = set(path for directory in args.directories for path in directory.glob("**/*.py"))
+
     for path in pathlist:
         # because path is object not string
         path_in_str = str(path.absolute())