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/agent/control/spawn.rs

@@ -1106,7 +1106,7 @@ impl LocalAgentControl {
                 [parent_usage_hints.root, parent_usage_hints.subagent]
                     .into_iter()
                     .flatten()
-                    .map(|instructions| instructions.render())
+                    .map(|instructions| instructions.render().into_text().unwrap_or_default())
                     .collect()
             } else {
                 Vec::new()