修复多个问题

backend/app/models.py

@@ -1,7 +1,7 @@
 from datetime import datetime, timedelta
 
-from sqlalchemy import DateTime, Integer, String
-from sqlalchemy.orm import Mapped, mapped_column, Session
+from sqlalchemy import DateTime, Integer, String, and_, or_
+from sqlalchemy.orm import Mapped, Session, mapped_column
 
 from app.database import Base
 
@@ -11,20 +11,57 @@ class HTMLFile(Base):
 
     id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
     unique_id: Mapped[str] = mapped_column(
-        String(32), unique=True, index=True, nullable=False
+        String(32),
+        unique=True,
+        index=True,
+        nullable=False,
     )
     filename: Mapped[str] = mapped_column(String(255), nullable=False)
+    title: Mapped[str | None] = mapped_column(String(120), nullable=True)
+    source: Mapped[str | None] = mapped_column(String(80), nullable=True)
+    request_id: Mapped[str | None] = mapped_column(String(120), nullable=True)
+    size_bytes: Mapped[int | None] = mapped_column(Integer, nullable=True)
     created_at: Mapped[datetime] = mapped_column(
-        DateTime, default=datetime.utcnow, nullable=False
+        DateTime,
+        default=datetime.utcnow,
+        nullable=False,
+    )
+    expires_at: Mapped[datetime | None] = mapped_column(
+        DateTime,
+        nullable=True,
+        index=True,
     )
     updated_at: Mapped[datetime] = mapped_column(
-        DateTime, default=datetime.utcnow, onupdate=datetime.utcnow, nullable=False
+        DateTime,
+        default=datetime.utcnow,
+        onupdate=datetime.utcnow,
+        nullable=False,
     )
 
     @classmethod
-    def delete_expired_records(cls, db: Session, days: int = 5) -> int:
-        """删除超过指定天数的记录"""
-        cutoff_date = datetime.utcnow() - timedelta(days=days)
-        deleted = db.query(cls).filter(cls.created_at < cutoff_date).delete()
-        db.commit()
-        return deleted
+    def list_expired_records(
+        cls,
+        db: Session,
+        default_retention_days: int,
+    ) -> list["HTMLFile"]:
+        now = datetime.utcnow()
+        fallback_cutoff = now - timedelta(days=default_retention_days)
+        return (
+            db.query(cls)
+            .filter(
+                or_(
+                    cls.expires_at < now,
+                    and_(
+                        cls.expires_at.is_(None),
+                        cls.created_at < fallback_cutoff,
+                    ),
+                )
+            )
+            .all()
+        )
+
+    def resolved_expires_at(self, default_retention_days: int) -> datetime:
+        if self.expires_at is not None:
+            return self.expires_at
+
+        return self.created_at + timedelta(days=default_retention_days)