Adds support for Ollama as a provider (requires Ollama server to be configured and running).

Prompts for URL when chosen or used as a provider and one is not configured.

Shows messaging when no models are installed.

To use:

1. Download Ollama: https://ollama.com/download
2. Install a model from the library: https://ollama.com/library (note: you can use any terminal and write, for example, ollama run llama3.3 if Ollama is installed and configured)
3. Be sure Ollama is running, then use the "switch AI model" flow and choose Ollama, then put in your server URL (default is http://localhost:11434 if you're running it locally.
4. Your installed models should show up in a list. Choose one and you're good to go.

Closes #3311