Connect a model for New Vegas work

You pick the model that runs your agent. The Test button checks the connection and shows the context window size. In Ask first mode, you review the plan before the agent changes files.

Choose your model provider

Cloud AI provider

You enter a standard API endpoint to use a cloud model. The prompt travels to that provider, so your file text leaves your PC.

Local PC model

With a local model, nothing leaves the PC.

Built-in model

The agent uses a built-in model ready to use without your own endpoint.

Check your connection

Press the Test button to verify your chosen model. The agent sends a small request and measures the response time. It also displays the context window size available for your prompt. This helps you decide if the model can handle your large mod lists.

Select the right model size

Use the run_on_model tool for complex logic or large refactors. A smaller model works well for simple edits to INI files. You can use the run_on_model tool to send a hard step to a larger model when the work gets difficult.

Quality varies between models and prompts. Always review the diff before accepting changes. Use Ask first to pause before actions that change files. This ensures you see exactly what the agent modifies in your New Vegas working folder.