-
Notifications
You must be signed in to change notification settings - Fork 28
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
Fetch failed with status 404 body {"message": "Not Found"... #24
Comments
gh copilot is given to me via student pack, provided by my university. could this be the issue? |
it works with the openAI key, but I still need to use copilot (specially since it says it's the recommended model in the readme) |
thank you for this project. it works very well. Although I have yet to figure how to get the copilot one working. |
It's strange that a university encourages use of Copilot. Do your credentials work with the VSCode plugin do you know? |
It's called Github Student Developer Pack and it contains a lot of other things. I think some student's learning process will be enhanced with it while others will learn less, so a mixed bag
Yes, I've been using copilot with all it's features, including copilot chat, and "fix with copilot" in vscode My guess is that the api is closed for people that get copilot for free, so that they can't give it to others, maybe? |
You said you can view the code actions successfully in the OP though. So are you getting the completions at first? The request that's failing is to do with refreshing the token so it might be that auth step which is done differently for your case. |
I mean that I can see the code actions options (as in "improve code", "resolve diagnostics", etc) , but when I click any of them, I get the error described in OP. and that error is the same whether it is a code action, or a completion on insert mode (like when you hit space bar) |
I am getting a very similar error when trying to use the openai handler with perplexities pplx api, which is openai compatible, so I figured it would work. Problem is the log is kinda not as helpful as I would like. Nowhere in the log does it show the full endpoint url, so I have no idea if it is simply misconfigured, or truly broken. Is there a way to increase the log verbosity? |
helix-editor version
helix 23.10 (83f09ecb)
helix-gpt version
0.27
Describe the bug
I can view the code actions successfully but when I pick one, I get the following error (I manually copied helix's diagnostic):
helix-gpt logs
Helix GPT output logs. Pass
--logFile /app/helix-gpt.log
to save them.helix logs
The text was updated successfully, but these errors were encountered: