Update GUI game debugging multiple-apps examples and eval

desktop_env/evaluators/metrics/__init__.py

@@ -123,7 +123,9 @@ from .vscode import (
     compare_answer,
     is_extension_installed,
     check_json_settings,
-    check_json_keybindings
+    check_json_keybindings,
+    check_python_file_by_test_suite,
+    check_python_file_by_gold_file
 )
 
 

desktop_env/evaluators/metrics/vscode.py

@@ -1,5 +1,7 @@
 import copy
+import importlib.util
 import json
+import sys
 from typing import Dict
 
 
@@ -133,9 +135,29 @@ def is_extension_installed(actual: str, rules: Dict, **options):
         raise NotImplementedError
 
 
-def check_python_file_by_test_suite(actual_file, test_suites, **options) -> float:
-    pass
+def check_python_file_by_test_suite(actual_files, test_file, **options) -> float:
+    """Check the python file by running the test suite in the given test file."""
+
+    test_function_name = options.get('test_function_name', 'test')
+    # Create a unique module name, it can be arbitrary but must be unique in the current runtime environment
+    module_name = 'dynamic_module'
+
+    # Load the module from the given file path
+    spec = importlib.util.spec_from_file_location(module_name, test_file)
+    module = importlib.util.module_from_spec(spec)
+    sys.modules[module_name] = module  # Add the loaded module to sys.modules
+    spec.loader.exec_module(module)  # Execute the module to make its content available
+
+    # Retrieve the function by name from the loaded module and execute it
+    test_function = getattr(module, test_function_name)
+    try:
+        if test_function():
+            return 1.0
+        else:
+            return 0.0
+    except Exception as e:
+        return 0.0
 
 
-def check_python_file_by_gold_file(actual_file, gold_file: str, **options) -> float:
+def check_python_file_by_gold_file(actual_files, gold_file: str, **options) -> float:
     pass