feat(vision): 实现 mingxi-vision 推理服务核心功能

- engine/defect_classes: HRIPCB 6类缺陷定义 + 4类扩展 + severity排序
- engine/base: DefectBox / DetectResult 数据类 + BaseInferenceEngine 抽象基类
- engine/ultralytics_adapter: YOLOv8 .pt 推理适配器 + warmup
- engine/annotator: 按 severity 着色的标注图生成 + base64 编码
- engine/loader: 单例管理 + asyncio.Lock 推理串行化 + 热重载支持
- config: Pydantic v1 BaseSettings，读取 .env
- schema: DetectResponse / HealthResponse / ReloadRequest 等响应模型
- api/detect: POST /api/detect，内存读图，推理锁保护
- api/health: GET /api/health
- api/model: POST /api/model/reload 热重载接口
- main: FastAPI lifespan 启动加载模型

测试通过：/api/health 200，/api/detect 空图返回 pass，标注图 base64 正常

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

mingxi-vision/schema.py

@@ -0,0 +1,42 @@
+from typing import List, Optional
+from pydantic import BaseModel  # pydantic v1
+
+
+class DefectBoxSchema(BaseModel):
+    class_id: int
+    class_name: str
+    class_name_zh: str
+    confidence: float
+    severity: str
+    box_xyxy: List[float]
+
+
+class DetectResponse(BaseModel):
+    task_id: str
+    verdict: str                        # pass | fail
+    defect_count: int
+    max_severity: str
+    avg_confidence: float
+    duration_ms: float
+    image_width: int
+    image_height: int
+    model_version: str
+    defects: List[DefectBoxSchema]
+    annotated_image_base64: Optional[str] = None
+
+
+class ReloadRequest(BaseModel):
+    model_path: str
+    runtime: str = "ultralytics"
+
+
+class ReloadResponse(BaseModel):
+    status: str
+    model_version: str
+
+
+class HealthResponse(BaseModel):
+    status: str
+    model_version: str
+    runtime: str
+    device: str