-
Notifications
You must be signed in to change notification settings - Fork 29
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
FEATURE: Add persona-based replies and whisper support to LLM triage #1170
Conversation
raise ArgumentError, "llm_triage: no action specified!" | ||
end | ||
|
||
if action == :edit && category_id.blank? && tags.blank? && flag_post.blank? && | ||
hide_topic.blank? | ||
return |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not sure if this should raise the same argumenterror as above.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think this is correct, cause I am fine with not forcing busywork if people forgot to select "created" from the action type. it is so easy to miss
description: "#{persona.name} (#{persona.user.username})", | ||
} | ||
end | ||
def self.available_persona_choices(require_user: true, require_default_llm: true) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This may return an empty array? Not sure if we can disable the script if this resolves to []
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sadly automation is missing a lot of stuff here 😢 there is also a bunch of inter key dependencies, we only want to show option A if B is selected and stuff like that. automation does need a bunch of tlc
This PR enhances the LLM triage automation with several important improvements:
This allows for more dynamic and context-aware responses in automated workflows, with better control over visibility and attribution.