Allow using 3rd party AI services that are compatible with OpenAI API format in the openai-gpt agent

[daxian-dbw]

PR Summary

Add support for users to user an AI endpoint whose API is compatible with OpenAI API format.

1. Azure OpenAI
   It requires the endpoint, deployment name, and the model name.

2. Public OpenAI
   It requires the model name. No endpoint, no deployment name.

3. OpenAI-compatible AI endpoint
   It requires the endpoint and model name. No deployment name.

CompatibleThirdParty is added as a new EndpointType member.

Many LLM tools can setup local or remote API endpoint that is compatible with OpenAI API format for users to call a model hosted by the tool, such as Ollama, LM Studio, LocalAI. The DeepSeek v3 and Google Gemini also provide OpenAI compatibility for their API endpoints.

To add an GPT targeting DeepSeek or Google Gemini, add the following to the openai.agent.json file:

{
    "GPTs": [
        {
          "Name": "gpt-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": "gpt-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": "gpt-deepseek"
}

[daxian-dbw]

@StevenBucher98 FYI