fix: Resolve o3-pro response parsing and test execution issues

- Fix lint errors: trailing whitespace and deprecated typing imports
- Update test mock for o3-pro response format (output.content[] → output_text)
- Implement robust test isolation with monkeypatch fixture
- Clear provider registry cache to prevent test interference
- Ensure o3-pro tests pass in both individual and full suite execution

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

tests/test_openai_provider.py

@@ -230,10 +230,8 @@ class TestOpenAIProvider:
         mock_openai_class.return_value = mock_client
 
         mock_response = MagicMock()
-        mock_response.output = MagicMock()
-        mock_response.output.content = [MagicMock()]
-        mock_response.output.content[0].type = "output_text"
-        mock_response.output.content[0].text = "4"
+        # New o3-pro format: direct output_text field
+        mock_response.output_text = "4"
         mock_response.model = "o3-pro-2025-06-10"
         mock_response.id = "test-id"
         mock_response.created_at = 1234567890