fix(edge): 修复 batch 推理超过 MAX_BATCH_SIZE 导致缓冲区溢出

队列中 ROI 数量超过 8 时（多摄像头多 ROI 绑定场景），
一次性送入 TensorRT 引擎导致 np.copyto 溢出。
改为按 max_batch_size 分块推理。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

main.py

@@ -562,26 +562,30 @@ class EdgeInferenceService:
             self._logger.error(f"处理帧失败 {camera_id}: {e}")
     
     def _batch_process_rois(self):
-        """批量处理 ROI - 真正的 batch 推理"""
+        """批量处理 ROI - 真正的 batch 推理（按 max_batch_size 分块）"""
         with self._batch_lock:
             roi_items = self._batch_roi_queue
             if not roi_items:
                 return
             self._batch_roi_queue = []
 
+        engine = self._engine_manager.get_engine("default")
+        if engine is None:
+            return
+
+        # 按 max_batch_size 分块处理
+        for chunk_start in range(0, len(roi_items), self._max_batch_size):
+            chunk = roi_items[chunk_start:chunk_start + self._max_batch_size]
+
             try:
-            images = [item[4] for item in roi_items]
-            scale_infos = [item[5] for item in roi_items]
+                images = [item[4] for item in chunk]
+                scale_infos = [item[5] for item in chunk]
 
                 # 真正的 batch: 将所有 ROI 裁剪图拼成 [N,3,H,W] 一次推理
                 batch_data, _ = self._preprocessor._batch_preprocessor.preprocess_batch(
                     images
                 )
 
-            engine = self._engine_manager.get_engine("default")
-            if engine is None:
-                return
-
                 # 一次性推理整个 batch
                 outputs, inference_time_ms = engine.infer(batch_data)
 
@@ -593,7 +597,7 @@ class EdgeInferenceService:
                     shapes = [o.shape if hasattr(o, 'shape') else type(o) for o in outputs]
                     self._logger.debug(f"[推理诊断] batch_data shape={batch_data.shape}, outputs={shapes}, 耗时={inference_time_ms:.1f}ms")
 
-            batch_size = len(roi_items)
+                batch_size = len(chunk)
                 batch_results = self._postprocessor.batch_process_detections(
                     outputs,
                     batch_size,
@@ -603,7 +607,7 @@ class EdgeInferenceService:
                 total_detections = sum(len(r[0]) for r in batch_results)
                 self._logger.debug(f"[推理] batch_size={batch_size}, 总检测数={total_detections}, conf_thresh={self._settings.inference.conf_threshold}")
 
-            for idx, (camera_id, roi, bind, frame, _, scale_info) in enumerate(roi_items):
+                for idx, (camera_id, roi, bind, frame, _, scale_info) in enumerate(chunk):
                     boxes, scores, class_ids = batch_results[idx]
 
                     # 无论是否检测到目标都要调用算法（离岗检测需要"无人"信号）