[功能]: 利用对几何信息的支持进行调度,以阻止重复出现的"无声 AABB"错误类

What: A small geometry-aware dispatch layer so detection ops use the geometry each detection actually carries (mask / OBB / box) instead of silently falling back to the axis-aligned xyxy.

Why: Several recent fixes are the same bug in different functions: code grabs detections.xyxy and forgets the real geometry lives in data["xyxyxyxy"] (OBB) or mask. Because xyxy is always present, the wrong answer is the silent default:

• Detections.area returned the AABB area, not the rotated body (#2306)
• with_nms / with_nmm dropped crossed OBBs via AABB IoU (#2303)
• as_yolo dropped OBB rotation on export (#2289)
• roboflow/inference: consensus IoU, and stitch / crop corner shifts (https://GitHub.com/roboflow/inference/pull/2420, https://GitHub.com/roboflow/inference/pull/2427, https://GitHub.com/roboflow/inference/pull/2430)

Same root cause each time: Detections holds several geometries at once and xyxy is just a derived envelope, so every consumer re-implements "which geometry is the real one?" and forgetting it fails silently. The next geometry-aware function will hit it again.