feat(compute): 补齐媒体生成 provider 能力声明（Seedream/Seedance/快乐马） (#34)

- volcengine：services 增 image_gen/video_gen；新增 doubao-seedream-4-0-250828（真 img2img/多图融合）与 doubao-seedance-2-0-260128（多素材视频）模型
- dashscope：新增快乐马 happyhorse-1.0-t2v/i2v/r2v 视频模型
- service-map：默认 image_gen→minimax/image-01、video_gen→minimax/MiniMax-Hailuo-2.3（指向已有内置工具适配器的后端）

使算力配置 UI 能展示这些 provider 的图像/视频能力标签与模型，用户填 key 时即可显式知晓其用途。

compute/service-map.json

@@ -40,12 +40,12 @@
     "providerId": "provider-openai-001"
   },
   "image_gen": {
-    "modelName": "dall-e-3",
-    "providerId": "provider-openai-001"
+    "modelName": "image-01",
+    "providerId": "provider-minimax-001"
   },
   "video_gen": {
-    "modelName": "kling-v2",
-    "providerId": "provider-kling-001"
+    "modelName": "MiniMax-Hailuo-2.3",
+    "providerId": "provider-minimax-001"
   },
   "omni": {
     "modelName": "gpt-4o-realtime",