Problem/Motivation
Currently we do not match the error message from LiteLLM, because we inherit the OpenAI chat method.
We should copy and fix the error messages that trigger AiQuotaException.
This is not nice way of extending it, but this is fixed in 1.2.0.
Steps to reproduce
Reach the quota
You still get a generic error
Proposed resolution
Copy the chat method.
Just change the part of the error message.
Issue fork ai_provider_litellm-3550977
Show commands
Start within a Git clone of the project using the version control instructions.
Or, if you do not have SSH keys set up on git.drupalcode.org:
Comments
Comment #3
marcus_johansson commentedComment #4
dan2k3k4 commentedComment #5
dan2k3k4 commentedCode reviewed, looks good to me
Comment #7
dan2k3k4 commentedComment #9
dan2k3k4 commented