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

Files

T

Eduard van Valkenburg 10d10364a9 Python: [BREAKING] cleanup of thread API and serialization (#893 )

* cleanup of threads and serialization

* fix for sliding window

* fix redis test

* updated from comments

* updated context provider and threads

* updated lock

* add asyncio default

* fix redis tests

* fix tests

* fix tests

* renamed to invoking

* fixed tests

* fix for instructions

10d10364a9 · 2025-09-29 16:22:34 +00:00

History

custom_chat_message_store_thread.py

Python: [BREAKING] cleanup of thread API and serialization (#893 )

2025-09-29 16:22:34 +00:00

README.md

Python: add RedisContextProvider (#716 )

2025-09-23 00:36:27 +00:00

redis_chat_message_store_thread.py

Python: [BREAKING] cleanup of thread API and serialization (#893 )

2025-09-29 16:22:34 +00:00

suspend_resume_thread.py

Python: Samples Integration Tests (#615 )

2025-09-08 23:45:51 +00:00

README.md

Thread Management Examples

This folder contains examples demonstrating different ways to manage conversation threads and chat message stores with the Agent Framework.

Examples

File	Description
`custom_chat_message_store_thread.py`	Demonstrates how to implement a custom `ChatMessageStore` for persisting conversation history. Shows how to create a custom store with serialization/deserialization capabilities and integrate it with agents for thread management across multiple sessions.
`suspend_resume_thread.py`	Shows how to suspend and resume conversation threads, allowing you to save the state of a conversation and continue it later. This is useful for long-running conversations or when you need to persist conversation state across application restarts.
`redis_chat_message_store_thread.py`	Comprehensive examples of using the Redis-backed `RedisChatMessageStore` for persistent conversation storage. Covers basic usage, user session management, conversation persistence across app restarts, thread serialization, and automatic message trimming. Requires Redis server and demonstrates production-ready patterns for scalable chat applications.