Add support to Google Gemini 2.5 Pro Image Input

[pidgeon777]

It seems that with Google Gemini 2.5 Pro it is possible to specify images as input:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
  "model": "google/gemini-2.5-pro-exp-03-25:free",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
          }
        }
      ]
    }
  ]
  
}'

How could this functionality be supported in codecompanion.nvim? I suppose that's the same model currently provided by GitHub Copilot, OpenRouter and Google itself.

[olimorris]

I covered my plan for image support in #1208. And I would plan to support all of the main adapters.