feat(digest): Phase 4 Global News Digest (cluster-level batch summarization)

7일 rolling window 뉴스를 country × topic 2-level로 묶어 매일 04:00 KST 배치 생성.
search 파이프라인 미사용. documents → clustering → cluster-level LLM summarization → digest.

핵심 결정:
- adaptive threshold (0.75/0.78/0.80) + EMA centroid (α=0.7) + time-decay (λ=ln(2)/3)
- min_articles=3, max_topics=10/country, top-5 MMR diversity, ai_summary[:300] truncate
- cluster-level LLM only, drop금지 fallback (topic_label="주요 뉴스 묶음" + top member ai_summary[:200])
- importance_score country별 0~1 normalize + raw_weight_sum 별도 보존, max(score, 0.01) floor
- per-call timeout 25s + pipeline hard cap 600s
- DELETE+INSERT idempotent (UNIQUE digest_date), AIClient._call_chat 직접 호출 (client.py 수정 없음)

신규:
- migrations/101_global_digests.sql (2테이블 정규화)
- app/models/digest.py (GlobalDigest + DigestTopic ORM)
- app/services/digest/{loader,clustering,selection,summarizer,pipeline}.py
- app/workers/digest_worker.py (PIPELINE_HARD_CAP + CLI 진입점)
- app/api/digest.py (/latest, ?date|country, /regenerate, inline Pydantic)
- app/prompts/digest_topic.txt (JSON-only + 절대 금지 블록)

main.py 4줄: import 2 + scheduler add_job 1 + include_router 1.
plan: ~/.claude/plans/quiet-herding-tome.md

app/models/digest.py

@@ -0,0 +1,87 @@
+"""global_digests + digest_topics 테이블 ORM (Phase 4)"""
+
+from datetime import date, datetime
+
+from sqlalchemy import (
+    BigInteger,
+    Boolean,
+    Date,
+    DateTime,
+    Float,
+    ForeignKey,
+    Integer,
+    String,
+    Text,
+)
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from core.database import Base
+
+
+class GlobalDigest(Base):
+    """하루 단위 digest run 메타데이터"""
+
+    __tablename__ = "global_digests"
+
+    id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
+    digest_date: Mapped[date] = mapped_column(Date, nullable=False, unique=True)
+    window_start: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
+    window_end: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
+    decay_lambda: Mapped[float] = mapped_column(Float, nullable=False)
+
+    total_articles: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    total_countries: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    total_topics: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+
+    generation_ms: Mapped[int | None] = mapped_column(Integer)
+    llm_calls: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    llm_failures: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    status: Mapped[str] = mapped_column(String(20), nullable=False, default="success")
+
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=datetime.now
+    )
+
+    topics: Mapped[list["DigestTopic"]] = relationship(
+        back_populates="digest",
+        cascade="all, delete-orphan",
+        order_by="DigestTopic.country, DigestTopic.topic_rank",
+    )
+
+
+class DigestTopic(Base):
+    """country × topic 단위 cluster 결과"""
+
+    __tablename__ = "digest_topics"
+
+    id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
+    digest_id: Mapped[int] = mapped_column(
+        BigInteger,
+        ForeignKey("global_digests.id", ondelete="CASCADE"),
+        nullable=False,
+    )
+
+    country: Mapped[str] = mapped_column(String(10), nullable=False)
+    topic_rank: Mapped[int] = mapped_column(Integer, nullable=False)
+
+    topic_label: Mapped[str] = mapped_column(Text, nullable=False)
+    summary: Mapped[str] = mapped_column(Text, nullable=False)
+
+    article_ids: Mapped[list] = mapped_column(JSONB, nullable=False)
+    article_count: Mapped[int] = mapped_column(Integer, nullable=False)
+
+    importance_score: Mapped[float] = mapped_column(Float, nullable=False)
+    raw_weight_sum: Mapped[float] = mapped_column(Float, nullable=False)
+
+    centroid_sample: Mapped[dict | None] = mapped_column(JSONB)
+    llm_model: Mapped[str | None] = mapped_column(String(100))
+    llm_fallback_used: Mapped[bool] = mapped_column(
+        Boolean, nullable=False, default=False
+    )
+
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=datetime.now
+    )
+
+    digest: Mapped["GlobalDigest"] = relationship(back_populates="topics")