[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/src/chat_completions.rs

@@ -40,7 +40,7 @@ pub(crate) async fn stream_chat_completions(
     let full_instructions = prompt.get_full_instructions(model);
     messages.push(json!({"role": "system", "content": full_instructions}));
 
-    if let Some(instr) = &prompt.user_instructions {
+    if let Some(instr) = &prompt.get_formatted_user_instructions() {
         messages.push(json!({"role": "user", "content": instr}));
     }