feat: Implement automated keyword-based news pipeline scheduler

- Add multi-threaded keyword scheduler for periodic news collection
- Create Keyword Manager API for CRUD operations and monitoring
- Implement automatic pipeline triggering (RSS → Google → AI → Translation)
- Add thread status monitoring and dynamic keyword management
- Support priority-based execution and configurable intervals
- Add comprehensive scheduler documentation guide
- Default keywords: AI, 테크놀로지, 경제, 블록체인

🤖 Generated with [Claude Code](https://claude.ai/code)

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

services/pipeline/shared/models.py

@@ -40,6 +40,7 @@ class RSSItem(BaseModel):
     item_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
     title: str
     link: str
+    guid: Optional[str] = None  # RSS GUID for deduplication
     published: Optional[str] = None
     summary: Optional[str] = None
     source_feed: str
@@ -74,22 +75,54 @@ class ItemWithImage(BaseModel):
     image_url: str
     image_prompt: str
     
-class FinalArticle(BaseModel):
-    """최종 기사"""
-    article_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
-    job_id: str
-    keyword_id: str
-    keyword: str
+class Subtopic(BaseModel):
+    """기사 소주제"""
     title: str
-    content: str
+    content: List[str]  # 문단별 내용
+
+class Entities(BaseModel):
+    """개체명"""
+    people: List[str] = Field(default_factory=list)
+    organizations: List[str] = Field(default_factory=list)
+    groups: List[str] = Field(default_factory=list)
+    countries: List[str] = Field(default_factory=list)
+    events: List[str] = Field(default_factory=list)
+
+class NewsReference(BaseModel):
+    """뉴스 레퍼런스"""
+    title: str
+    link: str
+    source: str
+    published: Optional[str] = None
+
+class FinalArticle(BaseModel):
+    """최종 기사 - ai_writer_db.articles 스키마와 일치"""
+    news_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    title: str
+    created_at: str = Field(default_factory=lambda: datetime.now().isoformat())
     summary: str
-    source_items: List[ItemWithImage]
-    images: List[str]
+    subtopics: List[Subtopic] = Field(default_factory=list)
     categories: List[str] = Field(default_factory=list)
-    tags: List[str] = Field(default_factory=list)
-    created_at: datetime = Field(default_factory=datetime.now)
-    pipeline_stages: List[str]
-    processing_time: float  # seconds
+    entities: Entities = Field(default_factory=Entities)
+    source_keyword: str
+    source_count: int = 1
+    # 레퍼런스 뉴스 정보
+    references: List[NewsReference] = Field(default_factory=list)
+    # 파이프라인 관련 추가 필드
+    job_id: Optional[str] = None
+    keyword_id: Optional[str] = None
+    pipeline_stages: List[str] = Field(default_factory=list)
+    processing_time: Optional[float] = None
+    # 다국어 지원
+    language: str = 'ko'
+    ref_news_id: Optional[str] = None
+    # RSS 중복 체크용 GUID
+    rss_guid: Optional[str] = None
+    # 이미지 관련 필드
+    image_prompt: Optional[str] = None
+    images: List[str] = Field(default_factory=list)
+    # 번역 추적
+    translated_languages: List[str] = Field(default_factory=list)
     
 class TranslatedItem(BaseModel):
     """번역된 아이템"""
@@ -110,4 +143,17 @@ class QueueMessage(BaseModel):
     queue_name: str
     job: PipelineJob
     timestamp: datetime = Field(default_factory=datetime.now)
-    retry_count: int = 0
+    retry_count: int = 0
+class Keyword(BaseModel):
+    """스케줄러용 키워드 모델"""
+    keyword_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    keyword: str
+    interval_minutes: int = Field(default=60)  # 기본 1시간
+    is_active: bool = Field(default=True)
+    last_run: Optional[datetime] = None
+    next_run: Optional[datetime] = None
+    created_at: datetime = Field(default_factory=datetime.now)
+    updated_at: datetime = Field(default_factory=datetime.now)
+    rss_feeds: List[str] = Field(default_factory=list)  # 커스텀 RSS 피드
+    priority: int = Field(default=0)  # 우선순위 (높을수록 우선)
+    max_articles_per_run: int = Field(default=100)  # 실행당 최대 기사 수