mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Bryan Ostdiek d18ce24bf8 Python: feat(mcp): add full _meta field support for CallToolResult objects (#2286 )

* 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>

d18ce24bf8 · 2025-11-21 08:43:24 +00:00

History

a2a

Python: Fix AI Search Tool Sample and improve AI Search Exceptions (#1206 )

2025-10-10 18:46:57 +00:00

anthropic

Python: Anthropic foundry (#2302 )

2025-11-18 16:03:40 +00:00

azure_ai

Python: Feature/azure ai search agentic rag (search as separate package) (#2328 )

2025-11-20 22:34:46 +00:00

azure_ai_agent

Python: Updated documentation for Azure AI (#2280 )

2025-11-17 19:14:07 +00:00

azure_openai

Python: Added an Azure OpenAI Responses API Hosted MCP sample (#2108 )

2025-11-13 22:44:49 +00:00

copilotstudio

Agents + Chat Client Samples Doctsring Updates (#1028 )

2025-10-01 07:18:53 +00:00

custom

Agents + Chat Client Samples Doctsring Updates (#1028 )

2025-10-01 07:18:53 +00:00

ollama

Python: Clean up imports (#2318 )

2025-11-19 23:41:01 +00:00

openai

Python: feat(mcp): add full _meta field support for CallToolResult objects (#2286 )

2025-11-21 08:43:24 +00:00

resources

Python: Foundry Agent Completeness (#954 )

2025-10-01 13:38:51 +00:00

README.md

Python: Updated documentation for Azure AI (#2280 )

2025-11-17 19:14:07 +00:00

README.md

Agent Examples

This folder contains examples demonstrating how to create and use agents with different chat clients from the Agent Framework. Each sub-folder focuses on a specific provider and client type, showing various capabilities like function tools, code interpreter, thread management, structured outputs, image processing, web search, Model Context Protocol (MCP) integration, and more.

Examples by Provider

Azure AI Foundry Examples

Folder	Description
`azure_ai_agent/`	Create agents using Azure AI Agent Service (based on `azure-ai-agents` V1 package) including function tools, code interpreter, MCP integration, thread management, and more.
`azure_ai/`	Create agents using Azure AI Agent Service (based on `azure-ai-projects` V2 package) including function tools, code interpreter, MCP integration, thread management, and more.

Microsoft Copilot Studio Examples

Folder	Description
`copilotstudio/`	Create agents using Microsoft Copilot Studio with streaming and non-streaming responses, authentication handling, and explicit configuration options

Azure OpenAI Examples

Folder	Description
`azure_openai/`	Create agents using Azure OpenAI APIs with multiple client types (Assistants, Chat, and Responses clients) supporting function tools, code interpreter, thread management, and more

OpenAI Examples

Folder	Description
`openai/`	Create agents using OpenAI APIs with comprehensive examples including Assistants, Chat, and Responses clients featuring function tools, code interpreter, file search, web search, MCP integration, image analysis/generation, structured outputs, reasoning, and thread management

Anthropic Examples

Folder	Description
`anthropic/`	Create agents using Anthropic models through OpenAI Chat Client configuration, demonstrating tool calling capabilities

Custom Implementation Examples

Folder	Description
`custom/`	Create custom agents and chat clients by extending the base framework classes, showing complete control over agent behavior and backend integration