You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Removing token counting via APIs - using local token counting - fix to rename the 'Enable reasoning' checkbox to a better option and function of 'Set Reasoning/Thinking Budget' for new Gemini models. Or come up with better UX to decrease confusion.
How will we know it works? (Acceptance Criteria)
Case 1: Set Thinking Budget
1. Users click on the Roo Code's setting button 2. Users create new profile and select Gemini as an API provider 3. Users selects newest Gemini 2.5 Pro Review 4. Instead of seeing Enable Reasoning, users see Set Thinking Budget But it is still confusing? Why do I have to enable reasoning if the new Gemini already has reasoning?
Case 2: Local Accurate Token Count
Users make an API request
Instead of sending another API request to get token count, it will be computed locally on user's machines
Users are happier because the waiting time is reduced :)
But I am waiting forever for the request...
Estimated effort and complexity
Size: Medium (1 week)
Reasoning: Minor UI/UX, token-counting should not be difficult
Main Challenges: token-counting libraries not working
Dependencies: maybe more optimal token-counting libraries, could have some dependencies with this: #4375
Technical considerations (optional but helpful)
No response
Trade-offs and risks (optional)
No response
Additional context (optional)
No response
Proposal checklist
I've searched existing Issues and Discussions for duplicates
This is a specific, actionable proposal with clear problem and solution
I've included concrete acceptance criteria
I understand this needs approval before implementation begins
What specific problem does this solve?
This is the part of the large proposal #4483
This proposal aims to improve user experience with using Gemini as an API provider in to Roo Code.
Summary
- Thinking cannot be turned off in new Gemini models, which leads to confusion: https://github.com/RooCodeInc/Roo-Code/discussions/4407How should this be solved?
Increase Experience with Gemini
- fix to rename the 'Enable reasoning' checkbox to a better option and function of 'Set Reasoning/Thinking Budget' for new Gemini models. Or come up with better UX to decrease confusion.How will we know it works? (Acceptance Criteria)
Case 1: Set Thinking Budget1. Users click on the Roo Code's setting button2. Users create new profile and select Gemini as an API provider3. Users selects newest Gemini 2.5 Pro Review4. Instead of seeing Enable Reasoning, users see Set Thinking BudgetBut it is still confusing? Why do I have to enable reasoning if the new Gemini already has reasoning?Case 2: Local Accurate Token Count
But I am waiting forever for the request...
Estimated effort and complexity
Size: Medium (1 week)
Reasoning: Minor UI/UX, token-counting should not be difficult
Main Challenges: token-counting libraries not working
Dependencies: maybe more optimal token-counting libraries, could have some dependencies with this: #4375
Technical considerations (optional but helpful)
No response
Trade-offs and risks (optional)
No response
Additional context (optional)
No response
Proposal checklist
Interested in implementing this?