Max context tokens parameter in Claude model errors

[superphao4]

What happened?

I am using the Claude model with customized Max Context Tokens parameter, and I received the following error:

"Something went wrong. Here's the specific error message we encountered: Operation failed after 3 attempts: 400 {"type":"error","error":{"type":"invalid_request_error","message":"messages: at least one message is required"}}."

Version Information

docker ghcr.io/danny-avila/librechat:v0.7.8

Steps to Reproduce

1. Go to new Chat, use Claude3.7 model
2. Custom parameter with any value, in my case i'm config with value 8000
3. Send any message

What browsers are you seeing the problem on?

No response

Relevant log output

"Something went wrong. Here's the specific error message we encountered: Operation failed after 3 attempts: 400 {"type":"error","error":{"type":"invalid_request_error","message":"messages: at least one message is required"}}."

With thinking:
Something went wrong. Here's the specific error message we encountered: Operation failed after 3 attempts: 400 {"type":"error","error":{"type":"invalid_request_error","message":"thinking.enabled.budget_tokens: Input should be greater than or equal to 1024"}}

Screenshots

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

This happens because the "system" value for max output tokens is reserved at about 8000 tokens. You would need to adjust that if you want "max output tokens" to be 8000: