[prompts] Better user_instructions handling (#1836)

## Summary
Our recent change in #1737 can sometimes lead to the model confusing
AGENTS.md context as part of the message. But a little prompting and
formatting can help fix this!

## Testing
- Ran locally with a few different prompts to verify the model
behaves well.
- Updated unit tests

codex-rs/core/tests/client.rs

@@ -376,7 +376,13 @@ async fn includes_user_instructions_message_in_request() {
         request_body["input"][0]["content"][0]["text"]
             .as_str()
             .unwrap()
-            .starts_with("be nice")
+            .starts_with("<user_instructions>\n\nbe nice")
+    );
+    assert!(
+        request_body["input"][0]["content"][0]["text"]
+            .as_str()
+            .unwrap()
+            .ends_with("</user_instructions>")
     );
 }