feat: separate contents, abstract and body evidence

backend/wisegrade/models.py

@@ -176,6 +176,14 @@ class KnowledgePage(Base):
     page = Column(Integer, primary_key=True)
     text = Column(Text, nullable=False, default="")
     image_path = Column(String(1200), nullable=True)  # Relative to processed_path.
+    # Page-level classification: cover, abstract, toc, body, references or unknown.
+    page_type = Column(String(20), nullable=False, default="unknown", server_default="unknown")
+    mixed = Column(Boolean, nullable=False, default=False, server_default="false")
+    section = Column(String(500), default="")
+    chapter = Column(String(500), default="")
+    confidence = Column(Float, nullable=True)
+    # Bounded classifier evidence: which signals decided the type, kept for audit.
+    classification = Column(JSON, default=dict, nullable=False)
 
 
 class KnowledgeChunk(Base):
@@ -187,6 +195,9 @@ class KnowledgeChunk(Base):
     document_type = Column(String(80), nullable=False)
     page = Column(Integer, nullable=False)
     section = Column(String(500), default="")
+    chapter = Column(String(500), default="")
+    page_type = Column(String(20), nullable=False, default="unknown", server_default="unknown")
+    block_type = Column(String(20), nullable=False, default="body", server_default="body")
     text = Column(Text, nullable=False)
     embedding = Column(Embedding, nullable=True)
 
@@ -225,6 +236,9 @@ class CriterionScore(Base):
     suggestion = Column(Text, default="")
     status = Column(String(40), default="pending")
     error = Column(Text, default="")
+    #: Content targets that still lacked body evidence, with the search that was run.
+    #: Kept after teacher review so the original retrieval problem stays auditable.
+    evidence_gaps = Column(JSON, default=list)
     __table_args__ = (UniqueConstraint("batch_id", "project_id", "criterion_id"),)
 
     @property
@@ -241,6 +255,14 @@ class ScoreEvidence(Base):
     page = Column(Integer, nullable=False)
     quote = Column(Text, nullable=False)
     image_path = Column(String(1200), nullable=True)
+    # Which required-evidence target this quotation is offered to support.
+    target_id = Column(String(50), default="", server_default="")
+    target_label = Column(String(300), default="", server_default="")
+    # Page type of the source passage, and its role in the judgement.
+    page_type = Column(String(20), default="unknown", server_default="unknown")
+    source_role = Column(String(20), default="content", server_default="content")
+    # True when the quotation was written before this retrieval policy existed.
+    historical = Column(Boolean, default=False, nullable=False, server_default="false")
 
 
 class TeacherRevision(Base):