fix:批量修复了一些问题

src/api/deps.py

@@ -167,6 +167,12 @@ class _RateLimiter:
         self._hits[key] = timestamps
         return True
 
+    def remaining(self, key: str) -> int:
+        """当前窗口内剩余可用次数。"""
+        now = time.time()
+        timestamps = [t for t in self._hits.get(key, []) if t > now - self.window_seconds]
+        return max(0, self.max_requests - len(timestamps))
+
 
 # 全局限流实例: /api/v1/predict 每分钟 10 次
 _predict_limiter = _RateLimiter(max_requests=10, window_seconds=60)