What specific problem does this solve?

Currently, AI provider configurations (like selected models for each mode) are saved globally across all VS Code workspaces. This means that when users work on different projects with different requirements, they have to manually reconfigure providers each time they switch workspaces.

For example:

• A user might want to use Claude for a TypeScript project (workspace A)
• But prefer GPT-4 for a Python project (workspace B)
• Currently, changing the provider in one workspace affects all others

This creates friction and reduces productivity when working on multiple projects simultaneously.

Proposed Solution

Implement per-workspace provider configuration that:

1. Saves provider settings (selected models, API keys if applicable) per workspace
2. Allows different modes to use different providers in different workspaces
3. Maintains backward compatibility with existing global settings
4. Provides an option to sync or copy settings between workspaces

Technical Considerations

• Store provider configurations in workspace-specific settings
• Add UI indicators showing which workspace's settings are active
• Provide migration path for existing users
• Ensure API keys remain secure (workspace-scoped vs global)

Additional Context

This would greatly improve the workflow for developers working on multiple projects with different AI requirements, making RooCode more flexible and user-friendly.

Request Checklist

• I've searched existing Issues and Discussions for duplicates
• This describes a specific problem with clear impact and context

Interested in implementing this feature?

• Yes, I'd like to help implement this feature
• This is a feature request only