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/tui/src/ide_context/prompt.rs

@@ -192,6 +192,7 @@ mod tests {
     use super::super::Position;
     use super::super::Range;
     use super::*;
+    use codex_protocol_test_support::ContentItemTestExt;
     use pretty_assertions::assert_eq;
     use std::path::PathBuf;
 
@@ -218,7 +219,8 @@ mod tests {
                     "Where?",
                     "Staging\n## My request for Codex:\nKeep this literal",
                 )
-                .render(),
+                .render()
+                .expect_text(),
                 text_elements: Vec::new(),
             },
             UserInput::Skill {