-
Notifications
You must be signed in to change notification settings - Fork 69
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
Not working on GitLab #34
Comments
Is the MR you tried it on public? I think the context/description of the MR might have been too big. The patches itself are truncated already but the description is not. |
@nickveenhof I tried on private...
this is the random repo I tested: |
It is not an issue of private vs public, here is a public PR/MR I tested on and get the same error as this issue:
I have tried it on a number of private PRs and they work fine up to a certain size.
From my understand of ChatGPT you'd want to count the number of token's in the message before sending and consider sending multiple messages to the Chat asking for it to wait for a certain command before responding. Then there will be an issue with the Chat only able to remember so many previous messages / tokens, but it ultimately means multiple api calls. |
You are getting this error because The assumption of a description is an issue as not all MR in GitLab will render a description textarea, so that is a bug |
Does this bug still exist in the latest dev version? We also just pushed out a new version to the chrome store |
I tried the extension on Gitlab's MR and I got the Error from OpenAI:
From looking at the payload of the request and also at the code itself, it seems that the tool does not capture the code well, it sends too many lines (not only code) in one single request
The text was updated successfully, but these errors were encountered: