It is too easy to jailbreak the models with prefill, which was probably the reason why it was removed. But I like that this pushes people towards open source models. llama.cpp supports prefill and even GBNF grammars [1], which is useful if you are working with a custom programming language for example.

[1] https://github.com/ggml-org/llama.cpp/blob/master/grammars/R...