* Fix MCP tool result serialization for list[TextContent]
When MCP tools return results containing list[TextContent], they were
incorrectly serialized to object repr strings like:
'[<agent_framework._types.TextContent object at 0x...>]'
This fix properly extracts text content from list items by:
1. Checking if items have a 'text' attribute (TextContent)
2. Using model_dump() for items that support it
3. Falling back to str() for other types
4. Joining single items as plain text, multiple items as JSON array
Fixes#2509
* Address PR review feedback for MCP tool result serialization
- Extract serialize_content_result() to shared _utils.py
- Fix logic: use texts[0] instead of join for single item
- Add type annotation: texts: list[str] = []
- Return empty string for empty list instead of '[]'
- Move import json to file top level
- Add comprehensive unit tests for serialization
* Address PR review feedback: fix type checking and double serialization
- Add isinstance(item.text, str) check to ensure text attribute is a string
- Fix double-serialization issue by keeping model_dump results as dicts
until final json.dumps (removes escaped JSON strings in arrays)
- Improve docstring with detailed return value documentation
- Add test for non-string text attribute handling
- Add tests for list type tool results in _events.py path
* Simplify PR: minimal changes to fix MCP tool result serialization
Addresses reviewer feedback about excessive refactoring:
- Reset _events.py to original structure
- Only add import and use serialize_content_result in one location
- All review comments addressed in serialize_content_result():
- Added isinstance(item.text, str) check
- Use model_dump(mode="json") to avoid double-serialization
- Improved docstring with explicit return value documentation
- Empty list returns "" instead of "[]"
* Refactor: Move MCP TextContent serialization to core prepare_function_call_results
Per reviewer feedback, moved the TextContent serialization logic from
ag-ui's serialize_content_result to the core package's
prepare_function_call_results function.
Changes:
- Added handling for objects with 'text' attribute (like MCP TextContent)
in _prepare_function_call_results_as_dumpable
- Removed serialize_content_result from ag-ui/_utils.py
- Updated _events.py and _message_adapters.py to use
prepare_function_call_results from core package
- Updated tests to match the core function's behavior
* Fix failing tests for prepare_function_call_results behavior
- test_tool_result_with_none: Update expected value to 'null' (JSON serialization of None)
- test_tool_result_with_model_dump_objects: Use Pydantic BaseModel instead of plain class
* Fix B903 linter error: Convert MockTextContent to dataclass
The ruff linter was reporting B903 (class could be dataclass or namedtuple)
for the MockTextContent test helper classes. This commit converts them to
dataclasses to satisfy the linter check.
* refactoring and unifying naming schemes of internal methods of chat clients
* set tool_choice to auto
* fix for mypy
* added note on naming and fix#2951
* fix responses
* fixes in azure ai agents client
* Correction of MCP image type conversion in _mcp.py
* Added a new overload to the init function of the DataContent() type of the Agent Framework, edited the test case to correctly test the usage of the data and uri fields while using DataContent()
* Fixed tests related to the changes of the DataContent type, added testing for both string and byte representations
* Added an example of using kwargs in ai_function
* Added thread object to ai_function kwargs
* Updated docs
* Small fix
* Added thread parameter filtering
* added more complete parsing for mcp tool arguments
* fixed mypy
* added nonlocal model counter, and some fixes
* fixes in naming logic
* extracted json parsing function, added parametrized test and checked coverage
* Add factory pattern to sequential orchestration builder
* Use temp list to avoid override
* Add sample and some other fixes
* Fix comments
* Small fix
* Update readme
* Support HITL for orchestration patterns
* Cleanup around naming
* Fix typing issues
* Clean up
* Naming clean up
* Updates to HITL to make it cleaner
* Rename human input hook to orchestration request info
* Clean up per PR feedback
* Provide way for HITL with magentic
* support tool call approvals and hitl stall replan
* human plan intervention sample
* Clean up
* Improve loging
* updates
* Add type annotations for AgentRunEvent and AgentRunUpdateEvent data attributes
* Fix unnecessary cast after typing improvement
* Mcp pkg update introduced type change. Fix it.
* update opentelemetry deps to 1.39.0 and use LogRecordExporter for type compatibility
* Standardize orchestration outputs as list of chatmessage. Add chat options to group chat prompt manager
* refactor group chat
* Improve group chat manager
* README Update
* Cleanup
* Add comment
* More cleanup
* Standardize termination condition for group chat
* Improvements on termination logic
* Fix tests
* Fix new line
* PR feedback
* Update ChatKit based on OpenAI type change
* Raise error if response format is not expected type
* Only one starting executor required. Add tests.
* Add magentic start executor test
* feat(mcp): add full _meta field support for CallToolResult objects
- Extract and preserve complete _meta field from MCP CallToolResult responses
- Merge metadata into additional_properties of converted content items
- Handle isError field for proper error state integration
- Support arbitrary metadata like token usage, costs, and performance metrics
- Maintain backward compatibility with existing tool execution workflows
- Add comprehensive test coverage for all metadata scenarios including edge cases
- Update documentation with metadata handling examples and patterns
Fixes protocol compliance violation where _meta fields were being dropped,
enables proper monitoring and cost tracking of MCP tool usage.
* Update python/packages/core/agent_framework/_mcp.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Clarify MCP _meta field test to use generic example metadata
- Updated test_mcp_call_tool_result_with_meta_arbitrary_data to use arbitrary metadata fields
- Added comments to emphasize that _meta structure is server-specific and not standardized
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Fixes#2219
Adds default=str to json.dumps() calls to handle non-JSON-serializable
types like datetime objects in tool function results.
Co-authored-by: kishikawa-hayato <84244732+HerBest-max@users.noreply.github.com>
Evan MattsonandGitHub
claude89757andGitHub
Eduard van ValkenburgandGitHub
Hao LuoandGitHub
Ege Ozan ÖzyedekandGitHub
Tao ChenandGitHub
Dmytro StrukandGitHub
Giles OdigweandGitHub
