Function parse_user_message_image_refs 

pub fn parse_user_message_image_refs(content: &str) -> (String, Vec<String>)

Split user-role content for image lifting: a prompt-mode tool carrier contributes only its declared image attachment lines (the body is never scanned, and non-image attachment lines stay in the text); every other user message lifts text markers exactly as before.

Provider adapters that resolve user content into image parts call this instead of parse_image_markers so a carrier body containing literal marker syntax cannot smuggle an unintended image into the request.