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

Files

T

Azure SRE Agent 70c88d2150 docs: clarify checkpoint storage security model and deserialization trust boundaries

Add Security Model documentation sections to the checkpoint encoding and
Azure Functions serialization modules explaining:
- Checkpoint storage is a trusted data source requiring access controls
- The RestrictedUnpickler allowlist is defense-in-depth, not a security boundary
- Developer responsibilities for securing storage backends
- Guidance on using allowed_types and strip_pickle_markers

Co-authored-by: Azure SRE Agent <noreply@microsoft.com>

70c88d2150 · 2026-06-03 01:01:00 +00:00

History

agent_framework_azurefunctions

docs: clarify checkpoint storage security model and deserialization trust boundaries

2026-06-03 01:01:00 +00:00

tests

Fix integration test worker crashes in Azure Functions on Py3.13 (#4260 )

2026-06-01 09:18:26 +00:00

AGENTS.md

.NET: Python: Add AGENTS.md files and update coding standards (#3644 )

2026-02-05 10:27:46 +00:00

LICENSE

.NET: Python: Azure Functions feature branch (#1916 )

2025-11-13 02:00:53 +00:00

pyproject.toml

Python: bump package versions for 1.6.0 release (#6017 )

2026-05-22 01:59:20 +00:00

README.md

.NET: Python: Azure Functions feature branch (#1916 )

2025-11-13 02:00:53 +00:00

README.md

Get Started with Microsoft Agent Framework Durable Functions

Please install this package via pip:

pip install agent-framework-azurefunctions --pre

Durable Agent Extension

The durable agent extension lets you host Microsoft Agent Framework agents on Azure Durable Functions so they can persist state, replay conversation history, and recover from failures automatically.

Basic Usage Example

See the durable functions integration sample in the repository to learn how to:

from agent_framework.azure import AgentFunctionApp

_app = AgentFunctionApp()

Register agents with AgentFunctionApp
Post messages using the generated /api/agents/{agent_name}/run endpoint

For more details, review the Python README and the samples directory.