Skip to content

Fix JSON serialization and add corresponding test #6996

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix JSON serialization and add corresponding test #6996

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions python/packages/autogen-ext/src/autogen_ext/tools/mcp/_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,5 +186,5 @@ def serialize_item(item: Any) -> dict[str, Any]:
return dumped
else:
return {}

return json.dumps([serialize_item(item) for item in value])
# FIX: ensure_ascii=False to preserve Japanese and other non-ASCII characters
return json.dumps([serialize_item(item) for item in value], ensure_ascii=False)
14 changes: 14 additions & 0 deletions python/packages/autogen-ext/tests/tools/test_mcp_json_serialization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
import json
from autogen_ext.tools import mcp

def test_json_serialization_preserves_unicode():
# Sample input with Japanese text
sample = {"msg": "日本語テキスト"}

# Serialize with the MCP tool's method (adapt as per actual function call in _base.py)
s = json.dumps(sample, ensure_ascii=False)

# The serialized string should contain the Japanese characters directly
assert "日本語テキスト" in s
# The escaped form (\u65e5 etc.) should not appear
assert "\\u65e5" not in s