Skip to content
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

Chat history is forced into the Memory Agent Prompt #989

Open
lucagobbi opened this issue Dec 14, 2024 · 0 comments
Open

Chat history is forced into the Memory Agent Prompt #989

lucagobbi opened this issue Dec 14, 2024 · 0 comments

Comments

@lucagobbi
Copy link
Collaborator

lucagobbi commented Dec 14, 2024

Since the agents refactor, Memory Agent is forcing chat history to be inserted in the agent prompt:

*(stray.langchainfy_chat_history()),

while other variables can be overriden using the before_agent_starts hook. Chat history is not part of the agent prompt suffix anymore even if it is populated inside the default agent_input object (using stringify method instead of langchainify):

"chat_history": conversation_history_formatted_content, # TODOV2: take away

that value is not used and a comment says to take away in V2, why is that?

Imho chat_history should be considered at the same level as memories, tool outputs and other custom keys provided in the agent input. If a developer wants to override that using before_agent_starts hook should be able to do it for chat_history as well.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant