iterative-debugging-behavior

Block-by-block fix loop on BEHAVIOR-1K (R1 Pro, OmniGibson on Isaac Sim). The policy is grown one code block at a time against what the robot actually did, and what carries across seeds is a skill library, not a program. Use for the two R1 Pro pickup tasks; Stage 1 learns on seeds 26-35, Stage 2 evaluates on 1-25 with a frozen library.