Skip to content

Python packages 1.0.0b251007

Choose a tag to compare

View all tags
@eavanvalkenburg eavanvalkenburg released this 07 Oct 21:53
· 126 commits to main since this release
python-1.0.0b251007
8b73b5b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

The first release after we went public, lots of small fixes, some bigger pieces, the highlights:

  • Support for approval_modes on AIFunctions and MCP Tools
  • Setting up your agent as a MCP server

And two breaking changes:

  • Parameter naming and other fixes (#1255)
    • This includes moving the parameters that were: model all to model_id
    • Some updates to the names of parameters on agent.run to more clearly indicate how you can pass provider specific settings.
  • Introduce add_agent functionality and added output_response to AgentExecutor; agent streaming behavior to follow workflow invocation (#1184)

Added

  • Added method to expose agent as MCP server (#1248)
  • Add PDF file support to OpenAI content parser with filename mapping (#1121)
  • Sample on integration of Azure OpenAI Responses Client with a local MCP server (#1215)
  • Added approval_mode and allowed_tools to local MCP (#1203)
  • Introducing AI Function approval (#1131)
  • Add name and description to workflows (#1183)
  • Add Ollama example using OpenAIChatClient (#1100)
  • Add DevUI improvements with color scheme, linking, agent details, and token usage data (#1091)
  • Add semantic-kernel to agent-framework migration code samples (#1045)

Changed

  • [BREAKING] Parameter naming and other fixes (#1255)
  • [BREAKING] Introduce add_agent functionality and added output_response to AgentExecutor; agent streaming behavior to follow workflow invocation (#1184)
  • OpenAI Clients accepting api_key callback (#1139)
  • Updated docstrings (#1225)
  • Standardize docstrings: Use Keyword Args for Settings classes and add environment variable examples (#1202)
  • Update References to Agent2Agent protocol to use correct terminology (#1162)
  • Update getting started samples to reflect AF and update unit test (#1093)
  • Update Lab Installation instructions to install from source (#1051)
  • Update python DEV_SETUP to add brew-based uv installation (#1173)
  • Update docstrings of all files and add example code in public interfaces (#1107)
  • Clarifications on installing packages in README (#1036)
  • DevUI Fixes (#1035)
  • Packaging fixes: removed lab from dependencies, setup build/publish tasks, set homepage url (#1056)
  • Agents + Chat Client Samples Docstring Updates (#1028)
  • Python: Foundry Agent Completeness (#954)

Fixed

  • Ollama + azureai openapi samples fix (#1244)
  • Fix multimodal input sample: Document required environment variables and configuration options (#1088)
  • Fix Azure AI Getting Started samples: Improve documentation and code readability (#1089)
  • Fix a2a import (#1058)
  • Fix DevUI serialization and agent structured outputs (#1055)
  • Default DevUI workflows to string input when start node is auto-wrapped agent (#1143)
  • Add missing pre flags on pip packages (#1130)
Assets 2
Loading