feat(commentary): 双 provider 评论 — Angel(Agnes) + 美团大模型(LongCat)

- 新增 articles.commentary_meituan{_status,_model,_error} 4 列 + commentary_engine
- LlmSetting 加 meituan_api_key/base_url/chat_model/interval_sec/enabled/commentary_prompt
- 新 app/services/llm/providers.py 工厂,支持多 provider 客户端
- enrichment 流程改为 commentary_angel + commentary_meituan 并行(asyncio.gather),
  任一 provider 失败不影响另一个
- enrichment_loop 状态判定:任一 provider 状态不是 ok 都视为待 enrich
- alembic 0004_dual_commentary 迁移
- 前端 Feed 卡片 + ArticleDetail 详情页各加一条'美团评论'卡
- AdminLlmSettings 加美团 provider 配置卡(独立 api_key 编辑器,不回显明文)
- LlmSettingOut.meituan_api_key_set (bool) 替代直接回传 key
- 默认 URL https://api.longcat.chat/openai/v1 / 默认模型 LongCat-2.0-Preview

backend/app/models/article.py

@@ -71,16 +71,24 @@ class Article(Base):
     image_ai_status: Mapped[str] = mapped_column(
         String(16), default="n/a", nullable=False
     )
+    # === 双 provider 评论(Angel = 原 commentary,美团 = LongCat)===
     commentary_status: Mapped[str] = mapped_column(
         String(16), default="n/a", nullable=False
     )
+    commentary_engine: Mapped[str | None] = mapped_column(String(32))  # angel / meituan / 多 provider 拼接
+    commentary_meituan_status: Mapped[str] = mapped_column(
+        String(16), default="n/a", nullable=False
+    )
+    commentary_meituan_model: Mapped[str | None] = mapped_column(String(64))
+    commentary_meituan_error: Mapped[str | None] = mapped_column(Text)
 
     # === LLM 增强内容 ===
     image_ai_url: Mapped[str | None] = mapped_column(Text)  # AI 生成的插图
 
     # === ML 字段(预留,MVP 全 null)===
     category: Mapped[str | None] = mapped_column(String(32), index=True)
-    commentary: Mapped[str | None] = mapped_column(Text)
+    commentary: Mapped[str | None] = mapped_column(Text)  # Angel 评论
+    commentary_meituan: Mapped[str | None] = mapped_column(Text)  # 美团评论
     entities: Mapped[dict | None] = mapped_column(JSONB)
     sentiment: Mapped[float | None] = mapped_column(Float)
     topic_id: Mapped[str | None] = mapped_column(String(64), index=True)