-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Description
Problem (one or two sentences)
Not knowing what model is primarily responsible for processing the current task. This has implications for cost and effectiveness.
Context (who is affected and when)
When I pick a mode , it abstracts the API provider, the prompts etc. That is fine.
The way we set models for modes is not intuitive and generates uncertainty in users - especially new users. So I may be using the 'Code' mode but I cannot easily see what model it is using (without going into settings/providers).
Desired behavior (conceptual, not technical)
I want the mode to have an explicit model setting, not something unintuitive like 'last model used'.
A way to pick the API and Model in the Modes editor is also important. The abstraction of using profiles is not particularly clear.
I think the separation is Settings/Providers is about picking what models you are enabling with keys.
Modes is about which models are you using for which specialised function.
Constraints / preferences (optional)
The explicit setting should be at the bottom of the chat, next to the mode picker , so that when I change modes I can see the provider + model it is set to and that puts the cost in the request in full context.
Request checklist
- I've searched existing Issues and Discussions for duplicates
- This describes a specific problem with clear context and impact
Roo Code Task Links (optional)
No response
Acceptance criteria (optional)
No response
Proposed approach (optional)
No response
Trade-offs / risks (optional)
No response