Expose assistant content token counts in completion notifications (#59041)

## What changed

Add optional `contentTokenCount` metadata to `item/completed` notifications, carrying the producer-supplied token count for each completed assistant message in default and plan modes. Counts include any sampled footer and are `null` when unavailable.

Keep this telemetry separate from stored thread items and omit it from subsequent model requests. Update the protocol schemas and generated TypeScript and Python types.

## Testing

Add coverage for per-message counts, including zero, in default and plan modes; missing and malformed metadata; backward-compatible notification decoding; and exclusion from subsequent model requests.

GitOrigin-RevId: 35973037a42650fa2d7569da8e88cb81215cf971

codex-rs/thread-store/src/thread_metadata_sync.rs

@@ -538,6 +538,7 @@ mod tests {
                 thread_id,
                 vec![RolloutItem::EventMsg(EventMsg::ItemCompleted(
                     ItemCompletedEvent {
+                        content_token_count: None,
                         thread_id,
                         turn_id: "turn-1".to_string(),
                         item: TurnItem::UserMessage(UserMessageItem::new(&[UserInput::Text {
@@ -650,6 +651,7 @@ mod tests {
         let update = sync
             .observe_appended_items(&[RolloutItem::EventMsg(EventMsg::ItemCompleted(
                 ItemCompletedEvent {
+                    content_token_count: None,
                     thread_id,
                     turn_id: "turn-1".to_string(),
                     item: TurnItem::UserMessage(UserMessageItem::new(&[UserInput::Text {