### Prerequisites - [x] I am running the latest code. Mention the version if possible as well. - [x] I carefully followed the [README.md](https://github.com/ggml-org/llama.cpp/blob/master/README.md). - [x] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed). - [x] I reviewed the [Discussions](https://github.com/ggml-org/llama.cpp/discussions), and have a new and useful enhancement to share. ### Feature Description Currently, if the UI got an error while it's generating the text, it will throw away the generating message. The most simple way to test is to Ctrl+C to kill the server while it's generating a response. The expected behavior is to show a meaningful error like what they do on chatgpt <img width="680" alt="Image" src="https://github.com/user-attachments/assets/a3734cef-3e47-4fda-b12b-231f74bdf43f" /> ### Motivation N/A ### Possible Implementation _No response_