Fix UnicodeDecodeError when running crewai create crew on Windows (issue #2715)

Co-Authored-By: Joe Moura <joao@crewai.com>

src/crewai/cli/create_flow.py

@@ -28,7 +28,7 @@ def create_flow(name):
     (project_root / "tests").mkdir(exist_ok=True)
 
     # Create .env file
-    with open(project_root / ".env", "w") as file:
+    with open(project_root / ".env", "w", encoding="utf-8") as file:
         file.write("OPENAI_API_KEY=YOUR_API_KEY")
 
     package_dir = Path(__file__).parent
@@ -58,7 +58,7 @@ def create_flow(name):
         content = content.replace("{{flow_name}}", class_name)
         content = content.replace("{{folder_name}}", folder_name)
 
-        with open(dst_file, "w") as file:
+        with open(dst_file, "w", encoding="utf-8") as file:
             file.write(content)
 
     # Copy and process root template files

src/crewai/cli/provider.py

@@ -147,7 +147,7 @@ def read_cache_file(cache_file):
     - dict or None: The JSON content of the cache file or None if the JSON is invalid.
     """
     try:
-        with open(cache_file, "r") as f:
+        with open(cache_file, "r", encoding="utf-8") as f:
             return json.load(f)
     except json.JSONDecodeError:
         return None
@@ -167,7 +167,7 @@ def fetch_provider_data(cache_file):
         response = requests.get(JSON_URL, stream=True, timeout=60)
         response.raise_for_status()
         data = download_data(response)
-        with open(cache_file, "w") as f:
+        with open(cache_file, "w", encoding="utf-8") as f:
             json.dump(data, f)
         return data
     except requests.RequestException as e:

src/crewai/cli/utils.py

@@ -18,7 +18,7 @@ console = Console()
 
 def copy_template(src, dst, name, class_name, folder_name):
     """Copy a file from src to dst."""
-    with open(src, "r") as file:
+    with open(src, "r", encoding="utf-8") as file:
         content = file.read()
 
     # Interpolate the content
@@ -27,7 +27,7 @@ def copy_template(src, dst, name, class_name, folder_name):
     content = content.replace("{{folder_name}}", folder_name)
 
     # Write the interpolated content to the new file
-    with open(dst, "w") as file:
+    with open(dst, "w", encoding="utf-8") as file:
         file.write(content)
 
     click.secho(f"  - Created {dst}", fg="green")
@@ -78,7 +78,7 @@ def _get_project_attribute(
     attribute = None
 
     try:
-        with open(pyproject_path, "r") as f:
+        with open(pyproject_path, "r", encoding="utf-8") as f:
             pyproject_content = parse_toml(f.read())
 
         dependencies = (
@@ -119,7 +119,7 @@ def fetch_and_json_env_file(env_file_path: str = ".env") -> dict:
     """Fetch the environment variables from a .env file and return them as a dictionary."""
     try:
         # Read the .env file
-        with open(env_file_path, "r") as f:
+        with open(env_file_path, "r", encoding="utf-8") as f:
             env_content = f.read()
 
         # Parse the .env file content to a dictionary
@@ -158,9 +158,9 @@ def tree_find_and_replace(directory, find, replace):
         for filename in files:
             filepath = os.path.join(path, filename)
 
-            with open(filepath, "r") as file:
+            with open(filepath, "r", encoding="utf-8") as file:
                 contents = file.read()
-            with open(filepath, "w") as file:
+            with open(filepath, "w", encoding="utf-8") as file:
                 file.write(contents.replace(find, replace))
 
             if find in filename:
@@ -189,7 +189,7 @@ def load_env_vars(folder_path):
     env_file_path = folder_path / ".env"
     env_vars = {}
     if env_file_path.exists():
-        with open(env_file_path, "r") as file:
+        with open(env_file_path, "r", encoding="utf-8") as file:
             for line in file:
                 key, _, value = line.strip().partition("=")
                 if key and value:
@@ -244,6 +244,6 @@ def write_env_file(folder_path, env_vars):
     - env_vars (dict): A dictionary of environment variables to write.
     """
     env_file_path = folder_path / ".env"
-    with open(env_file_path, "w") as file:
+    with open(env_file_path, "w", encoding="utf-8") as file:
         for key, value in env_vars.items():
             file.write(f"{key}={value}\n")

tests/cli/test_create_crew.py

@@ -0,0 +1,77 @@
+import os
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch, MagicMock
+
+import click
+from click.testing import CliRunner
+
+from crewai.cli.cli import create
+from crewai.cli.create_crew import create_crew
+
+
+class TestCreateCrew(unittest.TestCase):
+    def setUp(self):
+        self.runner = CliRunner()
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.test_dir = Path(self.temp_dir.name)
+        
+    def tearDown(self):
+        self.temp_dir.cleanup()
+        
+    @patch("crewai.cli.create_crew.get_provider_data")
+    @patch("crewai.cli.create_crew.select_provider")
+    @patch("crewai.cli.create_crew.select_model")
+    @patch("crewai.cli.create_crew.write_env_file")
+    @patch("crewai.cli.create_crew.load_env_vars")
+    @patch("click.confirm")
+    def test_create_crew_handles_unicode(self, mock_confirm, mock_load_env, 
+                                         mock_write_env, mock_select_model, 
+                                         mock_select_provider, mock_get_provider_data):
+        """Test that create_crew command handles Unicode properly."""
+        mock_confirm.return_value = True
+        mock_load_env.return_value = {}
+        mock_get_provider_data.return_value = {"openai": ["gpt-4"]}
+        mock_select_provider.return_value = "openai"
+        mock_select_model.return_value = "gpt-4"
+        
+        templates_dir = Path("src/crewai/cli/templates/crew")
+        templates_dir.mkdir(parents=True, exist_ok=True)
+        
+        template_content = """
+        Hello {{name}}! Unicode test: 你好, こんにちは, Привет 🚀
+        Class: {{crew_name}}
+        Folder: {{folder_name}}
+        """
+        
+        (templates_dir / "tools").mkdir(exist_ok=True)
+        (templates_dir / "config").mkdir(exist_ok=True)
+        
+        for file_name in [".gitignore", "pyproject.toml", "README.md", "__init__.py", "main.py", "crew.py"]:
+            with open(templates_dir / file_name, "w", encoding="utf-8") as f:
+                f.write(template_content)
+                
+        (templates_dir / "knowledge").mkdir(exist_ok=True)
+        with open(templates_dir / "knowledge" / "user_preference.txt", "w", encoding="utf-8") as f:
+            f.write(template_content)
+            
+        for file_path in ["tools/custom_tool.py", "tools/__init__.py", "config/agents.yaml", "config/tasks.yaml"]:
+            (templates_dir / file_path).parent.mkdir(exist_ok=True, parents=True)
+            with open(templates_dir / file_path, "w", encoding="utf-8") as f:
+                f.write(template_content)
+        
+        with patch("crewai.cli.create_crew.Path") as mock_path:
+            mock_path.return_value = self.test_dir
+            mock_path.side_effect = lambda x: self.test_dir / x if isinstance(x, str) else x
+            
+            create_crew("test_crew", skip_provider=True)
+            
+        crew_dir = self.test_dir / "test_crew"
+        for root, _, files in os.walk(crew_dir):
+            for file in files:
+                file_path = os.path.join(root, file)
+                with open(file_path, "r", encoding="utf-8") as f:
+                    content = f.read()
+                    self.assertIn("你好", content, f"Unicode characters not preserved in {file_path}")
+                    self.assertIn("🚀", content, f"Emoji not preserved in {file_path}")

tests/cli/test_encoding.py

@@ -0,0 +1,84 @@
+import os
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from crewai.cli.utils import copy_template, load_env_vars, write_env_file, tree_find_and_replace
+from crewai.cli.provider import read_cache_file, fetch_provider_data
+
+
+class TestEncoding(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.test_dir = Path(self.temp_dir.name)
+        
+        self.unicode_content = "Hello Unicode: 你好, こんにちは, Привет, مرحبا, 안녕하세요 🚀"
+        self.src_file = self.test_dir / "src_file.txt"
+        self.dst_file = self.test_dir / "dst_file.txt"
+        
+        with open(self.src_file, "w", encoding="utf-8") as f:
+            f.write(self.unicode_content)
+            
+    def tearDown(self):
+        self.temp_dir.cleanup()
+        
+    def test_copy_template_handles_unicode(self):
+        """Test that copy_template handles Unicode characters properly."""
+        copy_template(
+            self.src_file, 
+            self.dst_file, 
+            "test_name", 
+            "TestClass", 
+            "test_folder"
+        )
+        
+        with open(self.dst_file, "r", encoding="utf-8") as f:
+            content = f.read()
+            
+        self.assertIn("你好", content)
+        self.assertIn("こんにちは", content)
+        self.assertIn("🚀", content)
+        
+    def test_env_vars_handle_unicode(self):
+        """Test that environment variable functions handle Unicode characters properly."""
+        test_env_path = self.test_dir / ".env"
+        test_env_vars = {
+            "KEY1": "Value with Unicode: 你好",
+            "KEY2": "More Unicode: こんにちは 🚀"
+        }
+        
+        write_env_file(self.test_dir, test_env_vars)
+        
+        loaded_vars = load_env_vars(self.test_dir)
+        
+        self.assertEqual(loaded_vars["KEY1"], "Value with Unicode: 你好")
+        self.assertEqual(loaded_vars["KEY2"], "More Unicode: こんにちは 🚀")
+        
+    def test_tree_find_and_replace_handles_unicode(self):
+        """Test that tree_find_and_replace handles Unicode characters properly."""
+        test_file = self.test_dir / "replace_test.txt"
+        with open(test_file, "w", encoding="utf-8") as f:
+            f.write("Replace this: PLACEHOLDER with Unicode: 你好")
+            
+        tree_find_and_replace(self.test_dir, "PLACEHOLDER", "🚀")
+        
+        with open(test_file, "r", encoding="utf-8") as f:
+            content = f.read()
+            
+        self.assertIn("Replace this: 🚀 with Unicode: 你好", content)
+        
+    @patch("crewai.cli.provider.requests.get")
+    def test_provider_functions_handle_unicode(self, mock_get):
+        """Test that provider data functions handle Unicode properly."""
+        mock_response = unittest.mock.Mock()
+        mock_response.iter_content.return_value = [self.unicode_content.encode("utf-8")]
+        mock_response.headers.get.return_value = str(len(self.unicode_content))
+        mock_get.return_value = mock_response
+        
+        cache_file = self.test_dir / "cache.json"
+        with open(cache_file, "w", encoding="utf-8") as f:
+            f.write('{"model": "Unicode test: 你好 🚀"}')
+            
+        cache_data = read_cache_file(cache_file)
+        self.assertEqual(cache_data["model"], "Unicode test: 你好 🚀")