Evaluation UI: Model Config

Is your feature request related to a problem?

The current evaluation config only supports basic options: model name, vector store ID, and system prompt. However, different models have different configuration parameters—newer models support reasoning and verbosity, while older models use temperature and top_p.
This limits our ability to properly evaluate models with their optimal settings.

Describe the solution you'd like

Add support for model-specific configuration options in the evaluation config:

• Newer models: reasoning, verbosity
• Older models: temperature, top_p, max_tokens

This would:

• Allow evaluations with model-appropriate parameters
• Enable testing different config combinations (e.g., high vs low temperature)

No files or tests are named. Start by locating the evaluation configuration UI and the code that builds model configuration, then trace how the current model name, vector store ID, and system prompt are handled. Done means model-specific reasoning, verbosity, temperature, top_p, and max_tokens options can be configured for evaluations, including different combinations.