Support typed content in contextual prompt fragments (#54776)

## Why

Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.

## What changed

- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.

## Testing

Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.

GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1

codex-rs/core/src/session/tests.rs

@@ -10952,10 +10952,9 @@ async fn build_initial_context_adds_multi_agent_v2_subagent_usage_hint_as_develo
 
     let developer_messages = developer_message_texts(&initial_context);
     assert!(
-        developer_messages
-            .iter()
-            .flatten()
-            .any(|text| text.contains("<context_window>\nAgent name: /root/worker\n")),
+        developer_messages.iter().any(|message| message
+            .concat()
+            .contains("<context_window>\nAgent name: /root/worker\n")),
         "expected subagent context window to include its canonical name, got {developer_messages:?}"
     );
     assert!(

codex-rs/core/src/session/turn.rs

@@ -2162,7 +2162,10 @@ pub(super) fn realtime_text_for_event(msg: &EventMsg) -> Option<RealtimeEventTex
             ) =>
         {
             Some(RealtimeEventText::Handoff(
-                UserVerificationNotice.render(),
+                UserVerificationNotice
+                    .render()
+                    .into_text()
+                    .unwrap_or_default(),
                 None,
             ))
         }

codex-rs/core/src/session/turn_input.rs

@@ -957,7 +957,7 @@ async fn pending_turn_input(
                 let mut messages = SenderUserMessages {
                     receiver_turn_id: turn_id.to_owned(),
                     receiver_message_id: fragment.delivery.clone(),
-                    text: fragment.render(),
+                    text: fragment.render().into_text().unwrap_or_default(),
                 };
                 messages.bound();
                 Some(CodexHarnessMetadata {