openai.error.InvalidRequestError, requested too many tokens

[chrismarquardt]

Worked great the other day, now I'm getting this, no matter the command:

openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens, however you requested 6365 tokens (6109 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.

[github-actions]

Message that will be displayed on users' first issue

[JoelKronander]

Hi @chrismarquardt

Sorry about that it seems your prompt got very long. Are you using the latest version terminal-copilot 1.0.7?

Could you run with the -v flag to see the prompt that gets sent to openai to help us debug?

[rafpaf]

I ran into this problem when using copilot in a directory that contained a lot of hidden files. Once I deleted the files the problem went away.

[2mawi2]

Yes directory_list = os.listdir() currently has no limits. If you have a lot of directories and files. We could add a max limit to the directory context.

[2mawi2]

Implemented in #44