fix(docling): align volume mount with HF default cache path

Build preloads models to /root/.cache/huggingface (HF default).
Volume must mount there too, not a separate /models path.
Remove HF_HOME env override to keep paths consistent.

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

docker-compose.yml

@@ -256,12 +256,10 @@ services:
       dockerfile: Dockerfile
     container_name: iconsulting-docling
     restart: unless-stopped
-    environment:
-      HF_HOME: /models/huggingface
     ports:
       - "3007:3007"
     volumes:
-      - docling_models:/models
+      - docling_models:/root/.cache/huggingface
     healthcheck:
       test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3007/health')"]
       interval: 30s

packages/services/docling-service/Dockerfile

@@ -13,9 +13,8 @@ RUN pip install --no-cache-dir -r requirements.txt
 COPY app/ ./app/
 COPY scripts/ ./scripts/
 
-# 模型缓存目录（运行时通过 Docker volume 持久化到 /models）
-# 构建时预下载到镜像默认路径；运行时 HF_HOME=/models/huggingface 由 volume 接管
-ENV HF_HOME=/root/.cache/huggingface
+# 构建时预下载模型到 /root/.cache/huggingface（HF 默认路径）
+# 运行时通过 Docker volume 持久化该目录，首次启动从镜像初始化 volume
 RUN python scripts/preload_models.py || echo "Model preload skipped (will download on first request)"
 
 EXPOSE 3007