Refine data management and collection workflows

backend/app/models/data_snapshot.py

@@ -0,0 +1,26 @@
+from sqlalchemy import Boolean, Column, DateTime, ForeignKey, Integer, JSON, String
+from sqlalchemy.sql import func
+
+from app.db.session import Base
+
+
+class DataSnapshot(Base):
+    __tablename__ = "data_snapshots"
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    datasource_id = Column(Integer, nullable=False, index=True)
+    task_id = Column(Integer, ForeignKey("collection_tasks.id"), nullable=True, index=True)
+    source = Column(String(100), nullable=False, index=True)
+    snapshot_key = Column(String(100), nullable=True, index=True)
+    reference_date = Column(DateTime(timezone=True), nullable=True)
+    started_at = Column(DateTime(timezone=True), server_default=func.now())
+    completed_at = Column(DateTime(timezone=True), nullable=True)
+    record_count = Column(Integer, default=0)
+    status = Column(String(20), nullable=False, default="running")
+    is_current = Column(Boolean, default=True, index=True)
+    parent_snapshot_id = Column(Integer, ForeignKey("data_snapshots.id"), nullable=True, index=True)
+    summary = Column(JSON, default={})
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+
+    def __repr__(self):
+        return f"<DataSnapshot {self.id}: {self.source}/{self.status}>"