Python: Read and write chat history files as UTF-8

python/semantic_kernel/contents/chat_history.py

@@ -414,26 +414,29 @@ def store_chat_history_to_file(self, file_path: str) -> None:
         """Stores the serialized ChatHistory to a file.
 
         Uses mode "w" which means the file is created if it does not exist and gets truncated if it does.
+        The file is always written as UTF-8, so that histories with non-ASCII content can be stored
+        and reloaded on platforms whose locale encoding is not UTF-8.
 
         Args:
             file_path: The path to the file where the serialized data will be stored.
         """
         json_str = self.serialize()
-        with open(file_path, "w") as local_file:
+        with open(file_path, "w", encoding="utf-8") as local_file:
             local_file.write(json_str)
 
     @classmethod
     def load_chat_history_from_file(cls: type[_T], file_path: str) -> _T:
         """Loads the ChatHistory from a file.
 
         Uses mode "r" which means it can only be read if it exists.
+        The file is always read as UTF-8, matching what store_chat_history_to_file writes.
 
         Args:
             file_path: The path to the file from which to load the ChatHistory.
 
         Returns:
             ChatHistory: The deserialized ChatHistory instance.
         """
-        with open(file_path) as file:
+        with open(file_path, encoding="utf-8") as file:
             json_str = file.read()
         return cls.restore_chat_history(json_str)

python/tests/unit/contents/test_chat_history.py

@@ -612,6 +612,24 @@ def test_to_from_file(chat_history: ChatHistory, tmp_path):
     assert chat_history_2.messages[4] == chat_history.messages[4]
 
 
+def test_to_from_file_non_ascii(chat_history: ChatHistory, tmp_path):
+    """Chat histories with non-ASCII content should round-trip on any platform.
+
+    The file is always written and read as UTF-8, so the round-trip does not depend on the
+    locale encoding of the machine (which is not UTF-8 on Windows).
+    """
+    chat_history.add_user_message("你好，今天天气怎么样？")
+    chat_history.add_assistant_message("À Paris, il fait beau ☀️")
+
+    file_path = tmp_path / "chat_history.json"
+    chat_history.store_chat_history_to_file(file_path)
+
+    assert "你好" in file_path.read_text(encoding="utf-8")
+
+    chat_history_2 = ChatHistory.load_chat_history_from_file(file_path)
+    assert chat_history_2.messages == chat_history.messages
+
+
 def test_from_rendered_prompt_preserves_html_p_tag():
     """HTML <p> tags in prompts should be preserved as text, not treated as template tags.