-
Notifications
You must be signed in to change notification settings - Fork 62
feature: Memory Truncation (CG-10994) #838
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
jemeza-codegen
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Left a few comments, overall looks good!
jemeza-codegen
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good !
|
🎉 This PR is included in version 0.51.1 🎉 The release is available on GitHub release Your semantic-release bot 📦🚀 |
Truncates conversation history + summarizes in two instances
max_messageswhich is default set to 100max_input_tokens_for_model - 10000)Algorithm -> similar to OpenHands summarizer
(len(state[messages])) // 2)and leave the last N messages untouchedkeep_first_messages) until thetail.Misc
agent_configparam toCodeAgentif we want to play around with the max_messages, orkeep_first_messagespropertySample Trace (setting max_messages = 10) -> https://smith.langchain.com/public/60c0eef2-4e46-4506-86d7-9acd48b01cbe/r