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/protocol/src/models.rs

@@ -910,6 +910,21 @@ pub enum ContentItem {
     },
 }
 
+/// Constructs an input-text content item.
+pub fn input_text(text: impl Into<String>) -> ContentItem {
+    ContentItem::InputText { text: text.into() }
+}
+
+impl ContentItem {
+    /// Extracts text, returning `None` for non-text content.
+    pub fn into_text(self) -> Option<String> {
+        match self {
+            Self::InputText { text } | Self::OutputText { text, .. } => Some(text),
+            Self::InputImage { .. } | Self::InputAudio { .. } => None,
+        }
+    }
+}
+
 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema, TS)]
 #[serde(untagged)]
 #[ts(untagged)]
@@ -2251,6 +2266,20 @@ pub enum FunctionCallOutputContentItem {
     },
 }
 
+/// Converts message content to tool output, preserving media and image detail.
+/// Output text becomes input text without its sampling annotations or logprobs.
+impl From<ContentItem> for FunctionCallOutputContentItem {
+    fn from(item: ContentItem) -> Self {
+        match item {
+            ContentItem::InputText { text } | ContentItem::OutputText { text, .. } => {
+                Self::InputText { text }
+            }
+            ContentItem::InputImage { image, detail } => Self::InputImage { image, detail },
+            ContentItem::InputAudio { audio_url } => Self::InputAudio { audio_url },
+        }
+    }
+}
+
 /// Converts structured function-call output content into plain text for
 /// human-readable surfaces.
 ///