Using the same local endpoint for multiple modes-? #144
Description
I've been trying to get llama-vscode working using one local model for all the different modes (chat, agent, tools, code completion etc) but have failed to work it out. There are some responses in this repo about using settings, but it's not clear to me which settings to use and what to put in them. Is there some documentation which could be added to the wiki to explain how to do it? Basically I want to spin up one local model (Qwen3-Coder) and use it for all the modes.