iterative▌

Progressive context refinement loop for multi-agent workflows solving the subagent context problem. \n \n Four-phase cycle (dispatch, evaluate, refine, loop) that iteratively narrows retrieval to high-relevance files, capping at 3 iterations to balance token usage and context quality \n Scores retrieved files on a 0–1 relevance scale and explicitly identifies missing context gaps to drive the next refinement cycle \n Learns codebase terminology and patterns during the first cycle, improving subs