-
Notifications
You must be signed in to change notification settings - Fork 35
FEATURE: forum researcher persona for deep research #1313
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
Conversation
a10d1e9
to
84e9286
Compare
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.
Changes look good. The CancelManager
is a very nice improvement.
Something I have mixed feelings about is where the object is istantiated. I'd prefer it to bubble from the bottom like before this change, but we'd need a better completion response abstraction to properly support that, so not pushing for that right now.
I actually regret bubbling it from the block cause it forces you to keep repeating it which is a bit confusing. Plus if you are waiting a minute for the first few bytes from the LLM you need to bubble it right away which means you say "here is no text, but in case you need to cancel you can use this" having it passed in gives us so much more consistency (now that endpoint/base and open ai image generation both share the pattern) |
This commit introduces a new Forum Researcher persona specialized in deep forum content analysis along with comprehensive improvements to our AI infrastructure.
Key additions:
Infrastructure improvements:
Other improvements:
default_enabled
flag to control which personas are enabled by defaultThis change makes our AI platform more stable while adding powerful research capabilities that can analyze forum trends and surface relevant content.