fix: preserve non-ASCII text in MCP JSON serialization (#6995)#7193
Open
ichbinlucaskim wants to merge 1 commit intomicrosoft:mainfrom
Open
fix: preserve non-ASCII text in MCP JSON serialization (#6995)#7193ichbinlucaskim wants to merge 1 commit intomicrosoft:mainfrom
ichbinlucaskim wants to merge 1 commit intomicrosoft:mainfrom
Conversation
## Summary This PR fixes MCP JSON serialization so that non-ASCII text (for example, Japanese) is preserved instead of being escaped as `\uXXXX`. ## Changes - Added an internal helper `_to_json_str` in `autogen_ext.tools.mcp._base` that calls `json.dumps(..., ensure_ascii=False, indent=indent)`. - Updated `McpToolAdapter.return_value_as_string` to use `_to_json_str` for serializing tool return values. - Updated `StreamElicitor.elicit` in `_host/_elicitation.py` to use `_to_json_str` when rendering the requested schema for the user. - Added `tests/tools/test_mcp_serialization.py` to verify that Japanese text is not escaped. ## Tests - `uv run pytest tests/tools/test_mcp_serialization.py` ✓ - `uv run pytest` for `autogen-ext` fails on optional integrations (`chromadb`, `mem0`, `redisvl`, `torch`, `ollama`, `semantic_kernel`, `graphrag`, `json_schema_to_pydantic`) that are not installed in my local environment, but the new MCP tests pass.
Author
|
@microsoft-github-policy-service agree |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR fixes MCP JSON serialization so that non-ASCII text (for example, Japanese) is preserved instead of being escaped as
\\uXXXX.Changes
_to_json_strinautogen_ext.tools.mcp._basethat callsjson.dumps(..., ensure_ascii=False, indent=indent).McpToolAdapter.return_value_as_stringto use_to_json_strfor serializing tool return values.StreamElicitor.elicitin_host/_elicitation.pyto use_to_json_strwhen rendering the requested schema for the user.tests/tools/test_mcp_serialization.pyto verify that Japanese text is not escaped.Tests
uv run pytest tests/tools/test_mcp_serialization.py✓uv run pytestforautogen-extreports import errors for optional integrations(
chromadb,mem0,redisvl,torch,ollama,semantic_kernel,graphrag,json_schema_to_pydantic) that are not installed in my local environment, but the new MCP serialization tests pass.