Problem
What problem does this solve?
在和模型交互的过程中，有些提问不是很好或者回答不是很好，怕之前的提问或者回答影响上下文，需要从上次提问重新组织问题。
Solution
How should it work?
增加会话回退或者分支，这样我就可以的重新展开策略思考。注意，memory也要进行分支。
Use Case
When would you use this?
Priority
-
High - Blocking issue -
Medium - Important improvement -
Low - Nice to have
Additional Info
(Optional: screenshots, examples, links)