rl: true per-token entropy bonus (maximize r + beta*H, explicit diversity knob, no KL)

maxact-fast: hardening fixes (6 bugs) + Dr.GRPO vllm-lens rl.py + sbatch; Probe = universal direction

maxact-fast: clean repo — DESIGN + pretraining pipeline (embed/cluster/probe-cache/build-data/pretrain), Dr. GRPO RL to follow