fix: OCI vision requests fail — image_url not converted to camelCase

[fede-kamel]

Bug

OciClientV2.chat() with image content returns 400 from OCI Generative AI when using Command A Vision:

status_code: 400, body: {'message': 'Please pass in correct format of request.'}

Root Cause

OCI Generative AI expects camelCase field names. The SDK transforms message roles and content types but passes image_url through as-is instead of converting it to imageUrl.

SDK sends:

{"type": "IMAGE_URL", "image_url": {"url": "data:image/png;base64,..."}}

OCI expects:

{"type": "IMAGE_URL", "imageUrl": {"url": "data:image/png;base64,..."}}

Impact

All vision requests via OciClientV2 with inline images are broken.

Reproduction

response = client.chat(
    model="command-a-vision",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What color is this image?"},
            {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}},
        ],
    }],
)