diff --git a/src/codegen/git/repo_operator/repo_operator.py b/src/codegen/git/repo_operator/repo_operator.py
index dd00d7e42..6f13bec43 100644
--- a/src/codegen/git/repo_operator/repo_operator.py
+++ b/src/codegen/git/repo_operator/repo_operator.py
@@ -634,7 +634,7 @@ def iter_files(
                     content = self.get_file(filepath)
                     yield rel_filepath, content
                 except Exception as e:
-                    print(f"Error reading file {filepath}: {e}")
+                    logger.warning(f"Error reading file {filepath}: {e}")
 
     def list_files(self, subdirs: list[str] | None = None, extensions: list[str] | None = None) -> list[str]:
         """List files matching subdirs + extensions in a repo.
diff --git a/src/codegen/git/utils/language.py b/src/codegen/git/utils/language.py
index 6868b02dc..cc2742893 100644
--- a/src/codegen/git/utils/language.py
+++ b/src/codegen/git/utils/language.py
@@ -109,6 +109,7 @@ def _determine_language_by_git_file_count(folder_path: str) -> ProgrammingLangua
     """
     from codegen.git.repo_operator.repo_operator import RepoOperator
     from codegen.git.schemas.repo_config import RepoConfig
+    from codegen.sdk.codebase.codebase_context import GLOBAL_FILE_IGNORE_LIST
     from codegen.sdk.python import PyFile
     from codegen.sdk.typescript.file import TSFile
 
@@ -132,7 +133,7 @@ def _determine_language_by_git_file_count(folder_path: str) -> ProgrammingLangua
     repo_operator = RepoOperator(repo_config=repo_config)
 
     # Walk through the directory
-    for rel_path, _ in repo_operator.iter_files(subdirs=[base_path] if base_path else None):
+    for rel_path, _ in repo_operator.iter_files(subdirs=[base_path] if base_path else None, ignore_list=GLOBAL_FILE_IGNORE_LIST):
         # Convert to Path object
         file_path = Path(git_root) / Path(rel_path)
 
diff --git a/src/codegen/sdk/codebase/codebase_context.py b/src/codegen/sdk/codebase/codebase_context.py
index c4337683d..16118bc96 100644
--- a/src/codegen/sdk/codebase/codebase_context.py
+++ b/src/codegen/sdk/codebase/codebase_context.py
@@ -55,7 +55,16 @@
 
 
 # src/vs/platform/contextview/browser/contextMenuService.ts is ignored as there is a parsing error with tree-sitter
-GLOBAL_FILE_IGNORE_LIST = [".git/*", ".yarn/releases/*", ".*/tests/static/chunk-.*.js", ".*/ace/.*.js", "src/vs/platform/contextview/browser/contextMenuService.ts"]
+GLOBAL_FILE_IGNORE_LIST = [
+    ".git/*",
+    "*/.git/*",
+    "node_modules/*",
+    "*/node_modules/*",
+    ".yarn/releases/*",
+    ".*/tests/static/chunk-.*.js",
+    ".*/ace/.*.js",
+    "src/vs/platform/contextview/browser/contextMenuService.ts",
+]
 
 
 @unique