Split out `openai-gpt` gpts into different agents

[StevenBucher98]

Summary of the new feature / enhancement

As a user I want to switch between different openAI compatible AI providers in a similiar way that I switch between agents using the @ sign. It is confusing to treat them as different "GPTs" under the "openAI" agent especially if I call a different provider entirely like Google Gemini or DeepSeek.

Proposed technical implementation details (optional)

Ability to switch to different GPTs via the @ sign. For example if I have the following GPTs configured

{
    "GPTs": [
        {
          "Name": "deepseek",
          "Description": "A GPT instance using DeepSeek v3.",
          "Endpoint": "https://api.deepseek.com",
          "ModelName": "deepseek-chat",
          "Key": "<your-deepseek-api-key>",
          "SystemPrompt": "You are a helpful assistant."
        },

        {
          "Name": "gemini",
          "Description": "A GPT instance using Google Gemini.",
          "Endpoint": "https://generativelanguage.googleapis.com/v1beta/openai/",
          "ModelName": "gemini-1.5-flash",
          "Key": "<your-gemini-api-key>",
          "SystemPrompt": "You are a helpful assistant."
        }
    ]

    "Active": "deepseek"
}

It is unclear to users unfamiliar with the concept of GPTs to have to do @OpenAI-GPT agent and then /gpt use gemini to switch between these different providers. It may make more sense to do @gemini or @deepseek so user has a more clear indicator of what the currently called GPT is in the prompt rather than just at the beginning.

I'd also be open to using some kind of dot notation like @openai.gemini but personally feel typical user is not going to be familiar with GPTs. Open to discussion on this, I think I rather the @ notation.