[Feature Request] Auto-discover available models from custom providers

[MoooJianG]

Preflight Checklist

• I have read the Contributing Guidelines for this project.
• I agree to follow the Code of Conduct that this project adheres to.
• I have searched the issue tracker for a feature request that matches the one I want to file, without success.

Problem/Usecase Description

Feature Description

When configuring a custom AI provider, it would be helpful to automatically fetch and display available models from the provider's API.

Current Behavior

Users must manually type the model ID, which requires looking up documentation.

Benefits

• Reduces configuration errors
• Improves user experience
• Works with any OpenAI-compatible API

Proposed Solution

1. Add a "Fetch Models" button next to the API endpoint field
2. Call the provider's /v1/models endpoint to get available models
3. Display models in a searchable dropdown
4. Allow users to select from the list instead of typing manually

Feature Type

New functionality

Additional Context

Most OpenAI-compatible providers (Ollama, OpenRouter, etc.) support the /v1/models endpoint.

Contribution

• I'd be willing to implement this feature
• I'd be willing to test this feature once implemented
• I can provide additional details or clarification if needed