"""Timing + activation pilot: fresh client, exact full-run settings (32x8, 512 tok, K=128, lr 1e-4, 1 update/batch, lag 0),
CENTER=1 seed 0, 3 steps on held-out-of-schedule batches (seed 1000 order, never used by outcome arms)."""
import json, time, os
import rl_score_centering as rl
t0 = time.time()
tc, consumed = rl.train(int(os.environ.get("CENTER", 1)), 1000, int(os.environ.get("STEPS", 3)), "pilot_logs")
json.dump({"total_seconds": time.time() - t0, "consumed": consumed}, open("pilot_summary.json", "w"))
print("PILOT_DONE", time.time() - t0, flush=True)