-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
no graceful recovery or helpful info on 500 internal server errors #598
Comments
Thanks for trying aider and filing this issue. This is a bug introduced with the recent integration of litellm. Thanks for reporting it! I've just pushed a fix. The change is available in the main branch. You can get it by installing the latest version from github:
If you have a chance to try it, let me know if it works better for you. |
I'm going to close this issue for now, but feel free to add a comment here and I will re-open or file a new issue any time. |
Issue
A few times in the past day working with v0.31.1 and v0.32.0 I have gotten unexplained 500 errors from OpenAI's API, and it crashes out of the whole aider process. it seems trivial that if the actual API suggest is to retry again, that this is an error aider should handle itself with a retry loop (including a backoff and a limit). I will check out version 0.33.0 and see if that improves.
Version and model info
aider --yes main.py
Newer version v0.33.0 is available. To upgrade, run:
C:\Users\vandersen\source\repos\SMWParser\design_tools\docx_splitter\env\Scripts\python.exe -m pip install --upgrade aider-chat
Aider v0.32.0
Models: gpt-4-1106-preview with udiff edit format, weak model gpt-3.5-turbo
Git repo: .git with 1 files
Repo-map: using 1024 tokens
Added main.py to the chat.
VSCode terminal detected, pretty output has been disabled.
Use /help to see in-chat commands, run with --help to see cmd line args
The text was updated successfully, but these errors were encountered: