[WIP] Add a --cli option to llama-server that also forks a linenoise.cpp based cli process on launch of llama-server (use existing linenoise.cpp in the repo). This forked process acts as a client that speaks to the /chat/completions API in llama-server. Ctrl...

[Copilot]

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

Original description:

Add a --cli option to llama-server that also forks a linenoise.cpp based cli process on launch of llama-server (use existing linenoise.cpp in the repo). This forked process acts as a client that speaks to the /chat/completions API in llama-server. Ctrl-D should terminate both processes when invoked in --cli mode. Ctrl-C should stop/interrupt the chatbot response when pressed so we can ask another query, when pressed while in the user prompt it remind the user Ctrl-D is to quit. Here is a reference implementation in python3 of what the forked --cli process should look like:

@ericcurtin/lm-chat/files/lm-chat.py

---

💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.