-
Notifications
You must be signed in to change notification settings - Fork 0
chore: isolate internal protos #670
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
base: main
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This one is a bit odd because both the internal and external servers run this service since it's needed for both internal tool calls (system & remote) and external tool exec runners (user-land and environment tools) There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Not strongly opinionated here, but maybe best to default to this being in |
Uh oh!
There was an error while loading. Please reload this page.
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 is the one larger made here to avoid externalizing an internal type, I can't find any space we are actually populating this field at the moment though
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'd argue this is internal only data and doesn't need to be exposed externally. externally we could include credits a thread used but I think this is not exactly the same as llm token usage.
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.
Agreed with @mycodecrafting, I think it's probably best to move back to
llm_response_types.proto