"LLM" as well, because coding agents are already more than just an LLM. There is very useful context management around it, and tool calling, and ability to run tests/programs, etc. Though they are LLM-based systems, they are not LLMs.
This rapidly gets philosophical. If I use tools am I not handling the codebase? Are we classing LLM as tool or user in this scenario?
Indeed. If the LLM calls a chess engine tool behind the scenes, it would be able to play excellent chess as well.