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/core/src/agent/control.rs

@@ -213,6 +213,7 @@ impl LocalAgentControl {
             .await;
         let completed_at_ms = now_unix_timestamp_ms();
         let completed = ItemCompletedEvent {
+            content_token_count: None,
             thread_id,
             turn_id: turn_id.clone(),
             item,

codex-rs/core/src/agent/control_tests.rs

@@ -2435,6 +2435,7 @@ async fn spawn_agent_fork_from_paginated_parent_uses_model_context_prefix(
                 internal_chat_message_metadata_passthrough: None,
             }),
             RolloutItem::EventMsg(EventMsg::ItemCompleted(ItemCompletedEvent {
+                content_token_count: None,
                 thread_id: parent_thread_id,
                 turn_id: "parent-turn".to_string(),
                 item: TurnItem::UserMessage(UserMessageItem {