fix: add ensure_ascii=False to json.dumps for correct Unicode output

[KatHaruto]

Set ensure_ascii=False in json.dumps(...) to allow proper Unicode character output (e.g., Japanese).

Without this, non-ASCII characters are escaped (e.g., 日本語 → \u65e5\u672c\u8a9e), which makes logs or exports harder to read.

[seratch]

Thanks for the suggestion! You’re absolutely right. Non-English text in debug logs isn’t very developer-friendly at the moment. Generally speaking, as long as all input text data is UTF-8 encoded, this shouldn’t introduce any issues. In particular, the changes to the debug logging should be safe.

That said, the changes in the following files could potentially affect behavior (though I think it’s unlikely). Still, it would be good to test with a few patterns just to be sure:

• src/agents/models/chatcmpl_converter.py
• src/agents/mcp/util.py

Also, the CI tests detect an issue with older Python versions. Could you resolve it?