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

Files

T

Eduard van Valkenburg dc9439a75a Python: [BREAKING] Fix #3613 chat/agent message typing alignment (#3920 )

* Fix #3613 message typing across chat and agents

* Address #3613 review feedback and sample input style

* refactor: use shared AgentRunMessages aliases (#3613)

* refactor: rename agent run input aliases for #3613

* samples: inline image content in run calls

* core: export AgentRunInputs from package init

* core: use explicit init re-exports without __all__

* updated logging and inits

* Fix core mypy export and samples XML note

* Remove AgentRunInputsOrNone and dedupe loggers

* Remove prepare_messages helper

* fix integration tests

dc9439a75a · 2026-02-16 15:27:25 +00:00

History

agent_framework_durabletask

Python: [BREAKING] Fix #3613 chat/agent message typing alignment (#3920 )

2026-02-16 15:27:25 +00:00

tests

Python: Fix streamed workflow agent continuation context by finalizing AgentExecutor streams (#3882 )

2026-02-12 22:45:46 +00:00

AGENTS.md

Python: [BREAKING] PR2 — Wire context provider pipeline, remove old types, update all consumers (#3850 )

2026-02-12 21:00:32 +00:00

LICENSE

Python: Merge durabletask changes into main (#3420 )

2026-01-27 21:08:05 +00:00

pyproject.toml

update package versions (#3902 )

2026-02-13 00:00:57 +00:00

README.md

Python: replace pre-commit with prek, add PEP 723 script deps, clean up dev dependencies (#3748 )

2026-02-09 17:51:01 +00:00

README.md

Get Started with Microsoft Agent Framework Durable Task

Please install this package via pip:

pip install agent-framework-durabletask --pre

Durable Task Integration

The durable task integration lets you host Microsoft Agent Framework agents using the Durable Task framework so they can persist state, replay conversation history, and recover from failures automatically.

Basic Usage Example

from durabletask.worker import TaskHubGrpcWorker
from agent_framework.azure import DurableAIAgentWorker

# Create the worker
with TaskHubGrpcWorker(...) as worker:

    # Register the agent worker wrapper
    agent_worker = DurableAIAgentWorker(worker)

    # Register the agent
    agent_worker.add_agent(my_agent)

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