mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Giles Odigwe
6b47cdbf52
* Python: Fix broken samples for GitHub Copilot, declarative, and Responses API - Add missing on_permission_request handler to github_copilot_basic and github_copilot_with_session samples (required by copilot SDK) - Increase timeout for remote MCP query in github_copilot_with_mcp sample - Soften session isolation claim in github_copilot_with_session sample - Fix inline_yaml sample: pass project_endpoint via client_kwargs instead of relying on YAML connection block (AzureAIClient expects project_endpoint, not endpoint) - Handle raw JSON schemas in Responses client _convert_response_format so declarative outputSchema works with the Responses API Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Improve raw JSON schema detection heuristic and add tests - Broaden raw schema detection to handle anyOf, oneOf, allOf, $ref, $defs keywords and JSON Schema primitive types, not just 'properties' - Apply same raw schema handling to azure-ai _shared.py for consistency - Add unit tests for both openai and azure-ai response_format conversion Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
6b47cdbf52
ยท
2026-03-27 16:27:19 +00:00
History
Get Started with Microsoft Agent Framework Azure AI
Please install this package via pip:
pip install agent-framework-azure-ai --pre
Foundry Memory Context Provider
The Foundry Memory context provider enables semantic memory capabilities for your agents using Azure AI Foundry Memory Store. It automatically:
- Retrieves static (user profile) memories on first run
- Searches for contextual memories based on conversation
- Updates the memory store with new conversation messages
Basic Usage Example
See the Foundry Memory example which demonstrates:
- Creating a memory store using Azure AI Projects client
- Setting up an agent with FoundryMemoryProvider
- Teaching the agent user preferences
- Retrieving information using remembered context across conversations
- Automatic memory updates with configurable delays
and see the README for more information.