Score range fix (0, 1)

inference.py

@@ -53,6 +53,7 @@ def log_step(step: int, action: str, reward: float, done: bool, error: Optional[
     )
 
 def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
+    score = max(0.01, min(0.99, float(score)))
     rewards_str = ",".join(f"{r:.2f}" for r in rewards)
     print(f"[END] success={str(success).lower()} steps={steps} score={score:.2f} rewards={rewards_str}", flush=True)