zlacker

>>embedd+(OP)
How did you handle the context window for 20k lines? I assume you aren't feeding the whole codebase in every time given the API costs. I've struggled to keep agents coherent on larger projects without blowing the budget, so I'm curious if you used a specific scoping strategy here.

>>storys+jC1
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.

>>nurett+MJ1
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.

>>storys+J72
If you don't trigger the discovery agents, claude cli uses a search tool and greps 50-100 lines at a go. If discovery is triggered, claude sends multiple agents to the code with different tasks which return with overall architecture notes.