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/user_shell_command.rs

@@ -1,5 +1,7 @@
 use codex_protocol::exec_output::ExecToolCallOutput;
 use codex_protocol::models::ResponseItem;
+#[cfg(test)]
+use codex_protocol_test_support::ContentItemTestExt;
 
 use crate::context::ContextualUserFragment;
 use crate::context::UserShellCommand;
@@ -24,7 +26,9 @@ pub fn format_user_shell_command_record(
     exec_output: &ExecToolCallOutput,
     turn_context: &TurnContext,
 ) -> String {
-    user_shell_command_fragment(command, exec_output, turn_context).render()
+    user_shell_command_fragment(command, exec_output, turn_context)
+        .render()
+        .expect_text()
 }
 
 pub fn user_shell_command_record_item(