feat(接口2): 移植head3d发际线管线 + 接口2实现方案文档

- 从head3d复制发际线检测管线到 hairline/ 包：MediaPipe Tasks + SegFormer分割
  + 17锚点射线检测 + 502点mesh(face_ext.obj)+UV
- 复制模型：face_landmarker.task(3.7MB)、SegFormer config/preprocessor
  (model.safetensors 340MB 单独下载中)
- 新增 docs/接口2-C端生发-技术实现方案.md：第一步=发际线曲线叠加预览图，
  新增gender必填参数，按性别贴图数量输出(female5/male4)，hairline_type英文key，
  服务端cv2逐三角形warp渲染器(head3d只有浏览器端Three.js渲染)
- 接口文档.md 接口2章节同步：gender参数、输出语义、错误码说明
- hairline_texture/ 9张发际线贴图入库

hairline/face_parsing.py

@@ -0,0 +1,42 @@
+"""Face parsing via HuggingFace SegFormer (jonathandinu/face-parsing).
+
+First call downloads ~150 MB of weights into the HF cache.
+"""
+from __future__ import annotations
+import numpy as np
+from typing import TYPE_CHECKING
+
+from . import constants as C
+
+if TYPE_CHECKING:  # avoid hard import at module load
+    pass
+
+
+class FaceParser:
+    """Wraps a SegFormer face-parsing model and returns a (H, W) int label map."""
+
+    def __init__(self, device: str | None = None):
+        import torch
+        from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
+
+        self.device = device or ("cuda" if torch.cuda.is_available() else "cpu")
+        self.processor = SegformerImageProcessor.from_pretrained(C.HF_FACE_PARSER_MODEL)
+        self.model = SegformerForSemanticSegmentation.from_pretrained(C.HF_FACE_PARSER_MODEL)
+        self.model.to(self.device).eval()
+        self._torch = torch
+
+    def parse(self, image_rgb: np.ndarray) -> np.ndarray:
+        """image_rgb: (H, W, 3) uint8. Returns (H, W) int64 of class indices."""
+        from PIL import Image
+
+        H, W = image_rgb.shape[:2]
+        pil = Image.fromarray(image_rgb)
+        inputs = self.processor(images=pil, return_tensors="pt").to(self.device)
+        with self._torch.no_grad():
+            logits = self.model(**inputs).logits  # (1, C, h, w)
+        # Upsample to original resolution
+        up = self._torch.nn.functional.interpolate(
+            logits, size=(H, W), mode="bilinear", align_corners=False
+        )
+        labels = up.argmax(dim=1).squeeze(0).to("cpu").numpy().astype(np.int32)
+        return labels