@runt/ai: Process images

[rgbkrk]

Image outputs should get folded into the conversation for AI usage. Example code:

response = client.responses.create(
    model="gpt-4.1",
    input=[
        {
            "role": "user",
            "content": [
                { "type": "input_text", "text": "what's in this image?" },
                {
                    "type": "input_image",
                    "image_url": f"data:image/jpeg;base64,{base64_image}",
                },
            ],
        }
    ],
)