feat: 뉴스 전용 페이지 + 분류 격리 + 읽음 상태

- /news 전용 페이지: 신문사 필터, 읽지않음 필터, 시간순 리스트, 미리보기
- 뉴스 분류 격리: ai_domain='News', classify 제거, embed만 등록
- is_read: 클릭 시 자동 읽음, 전체 읽음 API
- documents 목록에서 뉴스 제외 (source_channel != 'news')
- nav에 뉴스 링크 추가
- GET /api/news/articles, POST /api/news/mark-all-read

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/api/documents.py

@@ -43,6 +43,7 @@ class DocumentResponse(BaseModel):
     derived_path: str | None
     original_format: str | None
     conversion_status: str | None
+    is_read: bool | None
     review_status: str | None
     edit_url: str | None
     preview_status: str | None
@@ -146,8 +147,8 @@ async def list_documents(
     source: str | None = None,
     format: str | None = None,
 ):
-    """문서 목록 조회 (페이지네이션 + 필터)"""
-    query = select(Document).where(Document.deleted_at == None)
+    """문서 목록 조회 (페이지네이션 + 필터, 뉴스 제외)"""
+    query = select(Document).where(Document.deleted_at == None, Document.source_channel != "news")
 
     if domain:
         # prefix 매칭: Industrial_Safety 클릭 시 하위 전부 포함

app/api/news.py

@@ -98,6 +98,62 @@ async def delete_source(
     return {"message": f"소스 {source_id} 삭제됨"}
 
 
+@router.get("/articles")
+async def list_articles(
+    user: Annotated[User, Depends(get_current_user)],
+    session: Annotated[AsyncSession, Depends(get_session)],
+    source: str | None = None,
+    unread_only: bool = False,
+    page: int = 1,
+    page_size: int = 30,
+):
+    """뉴스 기사 목록"""
+    from sqlalchemy import func
+    from models.document import Document
+
+    query = select(Document).where(
+        Document.source_channel == "news",
+        Document.deleted_at == None,
+    )
+    if source:
+        query = query.where(Document.ai_sub_group == source)
+    if unread_only:
+        query = query.where(Document.is_read == False)
+
+    count_q = select(func.count()).select_from(query.subquery())
+    total = (await session.execute(count_q)).scalar()
+
+    query = query.order_by(Document.is_read.asc(), Document.created_at.desc())
+    query = query.offset((page - 1) * page_size).limit(page_size)
+    result = await session.execute(query)
+    items = result.scalars().all()
+
+    from api.documents import DocumentResponse
+    return {
+        "items": [DocumentResponse.model_validate(doc) for doc in items],
+        "total": total,
+        "page": page,
+    }
+
+
+@router.post("/mark-all-read")
+async def mark_all_read(
+    user: Annotated[User, Depends(get_current_user)],
+    session: Annotated[AsyncSession, Depends(get_session)],
+):
+    """전체 읽음 처리"""
+    from sqlalchemy import update
+    from models.document import Document
+
+    result = await session.execute(
+        update(Document)
+        .where(Document.source_channel == "news", Document.is_read == False)
+        .values(is_read=True)
+    )
+    await session.commit()
+    return {"marked": result.rowcount}
+
+
 @router.post("/collect")
 async def trigger_collect(
     user: Annotated[User, Depends(get_current_user)],

app/models/document.py

@@ -3,7 +3,7 @@
 from datetime import datetime
 
 from pgvector.sqlalchemy import Vector
-from sqlalchemy import BigInteger, DateTime, Enum, String, Text
+from sqlalchemy import BigInteger, Boolean, DateTime, Enum, String, Text
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.orm import Mapped, mapped_column
 
@@ -55,6 +55,9 @@ class Document(Base):
     original_format: Mapped[str | None] = mapped_column(String(20))
     conversion_status: Mapped[str | None] = mapped_column(String(20), default="none")
 
+    # 읽음 상태 (뉴스용)
+    is_read: Mapped[bool | None] = mapped_column(Boolean, default=False)
+
     # 승인/삭제
     review_status: Mapped[str | None] = mapped_column(String(20), default="pending")
     deleted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))

app/workers/news_collector.py

@@ -139,6 +139,7 @@ async def _fetch_rss(session, source: NewsSource) -> int:
             continue
 
         category = _normalize_category(source.category or "")
+        source_short = source.name.split(" ")[0]  # "경향신문 문화" → "경향신문"
 
         doc = Document(
             file_path=f"news/{source.name}/{article_id}",
@@ -154,14 +155,14 @@ async def _fetch_rss(session, source: NewsSource) -> int:
             data_origin="external",
             edit_url=link,
             review_status="approved",
+            ai_domain="News",
+            ai_sub_group=source_short,
+            ai_tags=[f"News/{source_short}/{category}"],
         )
         session.add(doc)
         await session.flush()
 
-        # classify + embed 큐 등록 (extract 불필요)
-        session.add(ProcessingQueue(document_id=doc.id, stage="classify", status="pending"))
-
-        # 30일 이내만 embed
+        # embed만 등록 (classify 불필요 — 소스/분야 이미 확정)
         days_old = (datetime.now(timezone.utc) - pub_dt).days
         if days_old <= 30:
             session.add(ProcessingQueue(document_id=doc.id, stage="embed", status="pending"))
@@ -219,6 +220,7 @@ async def _fetch_api(session, source: NewsSource) -> int:
             continue
 
         category = _normalize_category(article.get("section", source.category or ""))
+        source_short = source.name.split(" ")[0]
 
         doc = Document(
             file_path=f"news/{source.name}/{article_id}",
@@ -234,12 +236,13 @@ async def _fetch_api(session, source: NewsSource) -> int:
             data_origin="external",
             edit_url=link,
             review_status="approved",
+            ai_domain="News",
+            ai_sub_group=source_short,
+            ai_tags=[f"News/{source_short}/{category}"],
         )
         session.add(doc)
         await session.flush()
 
-        session.add(ProcessingQueue(document_id=doc.id, stage="classify", status="pending"))
-
         days_old = (datetime.now(timezone.utc) - pub_dt).days
         if days_old <= 30:
             session.add(ProcessingQueue(document_id=doc.id, stage="embed", status="pending"))