Add audio variants to user input protocols (#33923)

## What changed

- Add remote and local audio variants to core and app-server user inputs, including generated JSON and TypeScript schemas.
- Preserve audio fields when converting app-server inputs and response content into thread items.
- Keep unsupported audio out of model requests, TUI rendering, text extraction, and truncated tool output, using explicit text placeholders where audio is submitted as a model input.

## Testing

- Cover app-server media conversion, unsupported-input placeholders, TUI omission, and tool-output truncation.

GitOrigin-RevId: 16152bf3af674575ce569764a8b472e032e7569d

codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__live_app_server_user_message_omits_unsupported_media.snap

@@ -0,0 +1,6 @@
+---
+source: tui/src/chatwidget/tests/app_server.rs
+expression: "lines_to_single_string(&inserted[0])"
+---
+
+› Please inspect the attachments.

codex-rs/tui/src/chatwidget/tests/app_server.rs

@@ -538,6 +538,43 @@ async fn live_app_server_user_message_item_completed_does_not_duplicate_rendered
     assert!(drain_insert_history(&mut rx).is_empty());
 }
 
+#[tokio::test]
+async fn live_app_server_user_message_omits_unsupported_media() {
+    let (mut chat, mut rx, _op_rx) = make_chatwidget_manual(/*model_override*/ None).await;
+
+    chat.handle_server_notification(
+        ServerNotification::ItemCompleted(ItemCompletedNotification {
+            thread_id: "thread-1".to_string(),
+            turn_id: "turn-1".to_string(),
+            completed_at_ms: 0,
+            item: AppServerThreadItem::UserMessage {
+                id: "user-1".to_string(),
+                client_id: None,
+                content: vec![
+                    AppServerUserInput::Text {
+                        text: "Please inspect the attachments.".to_string(),
+                        text_elements: Vec::new(),
+                    },
+                    AppServerUserInput::Audio {
+                        url: "https://example.com/one.wav".to_string(),
+                    },
+                    AppServerUserInput::LocalAudio {
+                        path: test_path_buf("/tmp/two.wav"),
+                    },
+                ],
+            },
+        }),
+        /*replay_kind*/ None,
+    );
+
+    let inserted = drain_insert_history(&mut rx);
+    assert_eq!(inserted.len(), 1);
+    assert_chatwidget_snapshot!(
+        "live_app_server_user_message_omits_unsupported_media",
+        lines_to_single_string(&inserted[0]),
+    );
+}
+
 #[tokio::test]
 async fn live_app_server_turn_completed_clears_working_status_after_answer_item() {
     let (mut chat, mut rx, _op_rx) = make_chatwidget_manual(/*model_override*/ None).await;

codex-rs/tui/src/chatwidget/user_messages.rs

@@ -589,7 +589,11 @@ pub(crate) fn mention_bindings_from_user_inputs(
                     path: path.clone(),
                 })
             }
-            UserInput::Text { .. } | UserInput::Image { .. } | UserInput::LocalImage { .. } => None,
+            UserInput::Text { .. }
+            | UserInput::Image { .. }
+            | UserInput::LocalImage { .. }
+            | UserInput::Audio { .. }
+            | UserInput::LocalAudio { .. } => None,
         })
         .collect();
     mention_bindings.sort_by_key(|binding| {
@@ -655,7 +659,10 @@ impl ChatWidget {
             match item {
                 UserInput::Text { text, .. } => message.push_str(text),
                 UserInput::Image { .. } | UserInput::LocalImage { .. } => image_count += 1,
-                UserInput::Skill { .. } | UserInput::Mention { .. } => {}
+                UserInput::Audio { .. }
+                | UserInput::LocalAudio { .. }
+                | UserInput::Skill { .. }
+                | UserInput::Mention { .. } => {}
             }
         }
 
@@ -666,6 +673,12 @@ impl ChatWidget {
     }
 
     pub(crate) fn user_message_display_from_inputs(items: &[UserInput]) -> UserMessageDisplay {
+        if items
+            .iter()
+            .any(|item| matches!(item, UserInput::Audio { .. } | UserInput::LocalAudio { .. }))
+        {
+            tracing::warn!("audio user inputs are not supported by the TUI and will be omitted");
+        }
         let mut message = String::new();
         let mut remote_image_urls = Vec::new();
         let mut local_images = Vec::new();
@@ -694,7 +707,10 @@ impl ChatWidget {
                 ),
                 UserInput::Image { url, .. } => remote_image_urls.push(url.clone()),
                 UserInput::LocalImage { path, .. } => local_images.push(path.clone()),
-                UserInput::Skill { .. } | UserInput::Mention { .. } => {}
+                UserInput::Audio { .. }
+                | UserInput::LocalAudio { .. }
+                | UserInput::Skill { .. }
+                | UserInput::Mention { .. } => {}
             }
         }