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/context/memory.rs

@@ -1,7 +1,9 @@
 //! Typed, bounded v2 memory context.
 
 use super::ContextualUserFragment;
+use codex_protocol::models::ContentItem;
 use codex_protocol::models::ContentItemKind;
+use codex_protocol::models::input_text;
 use codex_utils_output_truncation::TruncationPolicy;
 use codex_utils_output_truncation::truncate_text;
 
@@ -38,8 +40,8 @@ impl ContextualUserFragment for MemoryContextFragment {
     fn type_markers() -> (&'static str, &'static str) {
         ("", "")
     }
-    fn body(&self) -> String {
+    fn body(&self) -> ContentItem {
         let (Self::ReadInstructions(text) | Self::ExtractionEvidence(text)) = self;
-        truncate_text(text, TruncationPolicy::Bytes(8_900))
+        input_text(truncate_text(text, TruncationPolicy::Bytes(8_900)))
     }
 }