alt Hacker NewsYou don't load the entire project into the context. You let the agent work on a few 600-800 line files one feature at a time.
You don't load the entire project into the context. You let the agent work on a few 600-800 line files one feature at a time.
Right, but how does it know which files to pick? I'm curious if you're using a dependency graph or embeddings for that discovery step, since getting the agent to self-select the right scope is usually the main bottleneck.