You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using langraph react sdk on frontend and langraph server to run a react agent.
The intermediate tool messages are streamed and are rendered as new messages the message array goes to size 50 and then the final response is sent the backend sends new message array with 12 messages.
On frontend what happens is user sees bunch of Ai responses and they just vanish when the React agent is done.
Now i understand why these messages are removed they help manage context size. I agree. But can i identify them somehow on frontend and not render them as messages but as thinking state?
I tried 4-5 approaches, there are complex ways to do this but seems overkill. Maybe there is a better way.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I am using langraph react sdk on frontend and langraph server to run a react agent.
The intermediate tool messages are streamed and are rendered as new messages the message array goes to size 50 and then the final response is sent the backend sends new message array with 12 messages.
On frontend what happens is user sees bunch of Ai responses and they just vanish when the React agent is done.
Now i understand why these messages are removed they help manage context size. I agree. But can i identify them somehow on frontend and not render them as messages but as thinking state?
I tried 4-5 approaches, there are complex ways to do this but seems overkill. Maybe there is a better way.
Beta Was this translation helpful? Give feedback.
All reactions