-
Notifications
You must be signed in to change notification settings - Fork 116
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
Auto Fill mode should be respected #302
Comments
I don't think this is possible, auto-fill only works when running You can fill text in gptel's post-response hook: (add-hook 'gptel-post-response-functions 'fill-region) Or, conditioned on (add-hook 'gptel-post-response-functions
(lambda (beg end)
(when auto-fill-function
(fill-region beg end)))) |
I see, thank you for the work around. |
Due to the way text properties are handled by gptel, you may get errors with some LLMs when continuing a conversation after filling text. If you get errors as a result of filling text please reopen this issue. |
Thought this was working pretty well at first, but then noticed it messes up source block formatting. (add-hook 'gptel-post-response-functions
(lambda (beg end)
(when auto-fill-function
(fill-region beg end)))) I ended up just going with soft-wrapping |
It would be nice if the response insertion behaved the same as ordinary interactive insertion so that inserting a space at a column beyond current-fill-column automatically breaks the line at a previous space when Auto Fill mode is enabled. Long lines in the response are currently inserted as-is.
The text was updated successfully, but these errors were encountered: