GLM not supported?

[Kampouse]

Preflight Checklist

• I have read the Contributing Guidelines for this project.
• I agree to follow the Code of Conduct that this project adheres to.
• I have searched the issue tracker for a bug report that matches the one I want to file, without success.

Surf Version

latest

What operating system(s) are you using?

macOS

Operating System Version

macors

What arch are you using?

arm64 (including Apple Silicon)

Expected Behavior

work

Actual Behavior

i was trying to use the GLM model with you ai browser. I encounter some issue while trying to use it.
is there anyway that i can trace the ai api call?
or the issue i have encounter is related to the internal of it
thanks you.
nice browser!

i been able to use this model it other app such a zed 🤷‍♂️ is has the same shape as the gpt completion
context:
glm-4.6
https://api.z.ai/api/paas/v4/chat/completions

Additional Information

No response

[aavshr]

Hi, Surf should support all API endpoints that support the completions API. From the screenshot, seems like you're hitting rate limit issues.

Can you please provide more information on what your current limits are so that we can try to see if the llm requests are too aggressive? Also does this happen always or intermittently?

[Kampouse]

I kept the default limit in the configuration!

[aavshr]

What is the default limit? Is there, for instance, a maximum number of requests you can make in a minute or other similar limits that is part of your z.ai account?

[Kampouse]

in my editor i have it setup to 200k

would be nice to have better debugging experience within surf(trace the source error)
might try spin up the codebase and see what wrong

at least do some testing..