Wrap Image UserInput in <image> tags as well

codex-rs/core/src/event_mapping.rs

@@ -9,6 +9,8 @@ use codex_protocol::models::ReasoningItemContent;
 use codex_protocol::models::ReasoningItemReasoningSummary;
 use codex_protocol::models::ResponseItem;
 use codex_protocol::models::WebSearchAction;
+use codex_protocol::models::is_image_close_tag_text;
+use codex_protocol::models::is_image_open_tag_text;
 use codex_protocol::models::is_local_image_close_tag_text;
 use codex_protocol::models::is_local_image_open_tag_text;
 use codex_protocol::user_input::UserInput;
@@ -37,10 +39,10 @@ fn parse_user_message(message: &[ContentItem]) -> Option<UserMessageItem> {
     for (idx, content_item) in message.iter().enumerate() {
         match content_item {
             ContentItem::InputText { text } => {
-                if is_local_image_open_tag_text(text)
+                if (is_local_image_open_tag_text(text) || is_image_open_tag_text(text))
                     && (matches!(message.get(idx + 1), Some(ContentItem::InputImage { .. })))
                     || (idx > 0
-                        && is_local_image_close_tag_text(text)
+                        && (is_local_image_close_tag_text(text) || is_image_close_tag_text(text))
                         && matches!(message.get(idx - 1), Some(ContentItem::InputImage { .. })))
                 {
                     continue;
@@ -224,6 +226,43 @@ mod tests {
         }
     }
 
+    #[test]
+    fn skips_unnamed_image_label_text() {
+        let image_url = "data:image/png;base64,abc".to_string();
+        let label = codex_protocol::models::image_open_tag_text();
+        let user_text = "Please review this image.".to_string();
+
+        let item = ResponseItem::Message {
+            id: None,
+            role: "user".to_string(),
+            content: vec![
+                ContentItem::InputText { text: label },
+                ContentItem::InputImage {
+                    image_url: image_url.clone(),
+                },
+                ContentItem::InputText {
+                    text: codex_protocol::models::image_close_tag_text(),
+                },
+                ContentItem::InputText {
+                    text: user_text.clone(),
+                },
+            ],
+        };
+
+        let turn_item = parse_turn_item(&item).expect("expected user message turn item");
+
+        match turn_item {
+            TurnItem::UserMessage(user) => {
+                let expected_content = vec![
+                    UserInput::Image { image_url },
+                    UserInput::Text { text: user_text },
+                ];
+                assert_eq!(user.content, expected_content);
+            }
+            other => panic!("expected TurnItem::UserMessage, got {other:?}"),
+        }
+    }
+
     #[test]
     fn skips_user_instructions_and_env() {
         let items = vec![