Finer-grained control of Gemini models

[HahaBill]

What specific problem does this solve?

This is the part of the large proposal #4483

This proposal aims to increase user control and cost management with using Gemini as an API provider.

Summary

We would improve Gemini support in Roo Code by adding:

• topP and topK
• maxOutputTokens -> if no progress is made
• URL context
• Grounding Research
• Token control
• contextLimit / maxContextWindow - still an ongoing disccusion

How should this be solved?

Missing Integrations and Parameters

• Enable URL context + Grounding research: Gemini URL Context Support #4274
• Max Output Tokens: Decouple Max Tokens from Max Thinking Tokens #3355
• topP and topK - https://ai.google.dev/gemini-api/docs/prompting-strategies

#### Token-related issues

- Cannot strategically decrease context limits (input tokens): https://github.com/RooCodeInc/Roo-~~Code/discussions/2422, #3009, #3717
=> This PR (#4360) particularly solved the issue related to intelligent context condensing for Gemini. However, this is still under the discussion to whether make those changes. Other use case would be strategically setting artificial maximum context window limit for cost management.

How will we know it works? (Acceptance Criteria)

Acceptance Criteria

Case 1: Changing parameters and configurations

1. Users click on the Roo Code's setting button
2. Users create new profile and select Gemini as an API provider
3. Users see several custom parameters and configurations such as topP, topK, maxOutputTokens, enable URL context, enable Grounding Research and context limit.
   But I cannot see new parameters or configurations :(

Case 2: Strategically setting context limit / max context window

1. Users click on the Roo Code's setting button
2. Users create new profile and select Gemini as an API provider
3. Users change context limit / mac context window to aligned with their specific token usage
4. When users do multiple requests and Roo Code intelligently condense the context to be below the set context limit / max context window. Optional: If it goes over the set context limit, it will want useres
   But I am losing a lot of money :(

Estimated effort and complexity

Size: Medium (1-2 week)
Reasoning: Adding parameters and tools to genai functions - should not be difficult, UI/UX should not be difficult since it will be in the configuration profile, setting context limit (currently max context window) is already in progress
Main Challenges: optimal UI/UX designs
Dependencies: No new dependencies

Technical considerations (optional but helpful)

No response

Trade-offs and risks (optional)

No response

Additional context (optional)

Note

This will be reviewed by Google Deepmind and further adjustment could be made. Furthermore, there are some duplicates but they seem to be inactive - those have to be verified.

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

Interested in implementing this?

• Yes, I'd like to help implement this feature

[hannesrudolph]

Sounds good @HahaBill. Hit me up on discord and we can discuss the specifics.

[HahaBill]

Created this PR: #4895

contextLimit can use functionality and implementation from this PR: #4360 for users to strategically set max context window. Better naming and description will be made.