Invalid models shown when switching providers

[angiejones]

I was using OpenAI then wanted to switch to Gemini. When prompted for the model from my new provider, configure gives the model from the current provider. Seems it's pulling this from `/.config/goose/config.yaml as opposed to pulling the appropriate models for the selected provider.

┌   goose-configure 
│
◇  What would you like to configure?
│  Configure Providers 
│
◇  Which model provider should we use?
│  Google Gemini 
│
●  GOOGLE_API_KEY is already configured
│  
◇  Would you like to update this value?
│  No 
│
◆  Enter a model from that provider:
│  gpt-4o (default)
└  

Here's an example when going from Gemini to Ollama

┌   goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Ollama
│
◇ Enter a model from that provider:
│ gemini-2.0-flash-exp
│
◐ Checking your configuration...                                                   ExecutionError("error sending request for url (http://localhost:11434/v1/chat/completions)")
◇ We could not connect!
│
└ The provider configuration was invalid

[angiejones]

Note, that I am able to type the correct model but I would have to know its name. A bit difficult when it's something like gemini-2.0-flash-exp