Initial commit

backend/app/models/__init__.py

@@ -0,0 +1,6 @@
+"""Model exports for ORM metadata discovery."""
+
+from app.models.document import Document, DocumentStatus
+from app.models.processing_log import ProcessingLogEntry
+
+__all__ = ["Document", "DocumentStatus", "ProcessingLogEntry"]

backend/app/models/document.py

@@ -0,0 +1,65 @@
+"""Data model representing a stored and processed document."""
+
+import uuid
+from datetime import UTC, datetime
+from enum import Enum
+
+from sqlalchemy import Boolean, DateTime, Enum as SqlEnum, ForeignKey, Integer, String, Text
+from sqlalchemy.dialects.postgresql import ARRAY, JSONB, UUID
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.db.base import Base
+
+
+class DocumentStatus(str, Enum):
+    """Enumerates processing states for uploaded documents."""
+
+    QUEUED = "queued"
+    PROCESSED = "processed"
+    UNSUPPORTED = "unsupported"
+    ERROR = "error"
+    TRASHED = "trashed"
+
+
+class Document(Base):
+    """Stores file identity, storage paths, extracted content, and classification metadata."""
+
+    __tablename__ = "documents"
+
+    id: Mapped[uuid.UUID] = mapped_column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
+    original_filename: Mapped[str] = mapped_column(String(512), nullable=False)
+    source_relative_path: Mapped[str] = mapped_column(String(1024), nullable=False, default="")
+    stored_relative_path: Mapped[str] = mapped_column(String(1024), nullable=False)
+    mime_type: Mapped[str] = mapped_column(String(255), nullable=False, default="application/octet-stream")
+    extension: Mapped[str] = mapped_column(String(32), nullable=False, default="")
+    sha256: Mapped[str] = mapped_column(String(128), nullable=False)
+    size_bytes: Mapped[int] = mapped_column(Integer, nullable=False)
+    logical_path: Mapped[str] = mapped_column(String(1024), nullable=False, default="Inbox")
+    suggested_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
+    tags: Mapped[list[str]] = mapped_column(ARRAY(String), nullable=False, default=list)
+    suggested_tags: Mapped[list[str]] = mapped_column(ARRAY(String), nullable=False, default=list)
+    metadata_json: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict)
+    extracted_text: Mapped[str] = mapped_column(Text, nullable=False, default="")
+    image_text_type: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    handwriting_style_id: Mapped[str | None] = mapped_column(String(64), nullable=True, index=True)
+    status: Mapped[DocumentStatus] = mapped_column(SqlEnum(DocumentStatus), nullable=False, default=DocumentStatus.QUEUED)
+    preview_available: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
+    archived_member_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
+    is_archive_member: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
+    parent_document_id: Mapped[uuid.UUID | None] = mapped_column(UUID(as_uuid=True), ForeignKey("documents.id"), nullable=True)
+    replaces_document_id: Mapped[uuid.UUID | None] = mapped_column(UUID(as_uuid=True), ForeignKey("documents.id"), nullable=True)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
+    processed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True),
+        nullable=False,
+        default=lambda: datetime.now(UTC),
+        onupdate=lambda: datetime.now(UTC),
+    )
+
+    parent_document: Mapped["Document | None"] = relationship(
+        "Document",
+        remote_side="Document.id",
+        foreign_keys=[parent_document_id],
+        post_update=True,
+    )

backend/app/models/processing_log.py

@@ -0,0 +1,33 @@
+"""Data model representing one persisted processing pipeline log entry."""
+
+import uuid
+from datetime import UTC, datetime
+
+from sqlalchemy import BigInteger, DateTime, ForeignKey, String, Text
+from sqlalchemy.dialects.postgresql import JSONB, UUID
+from sqlalchemy.orm import Mapped, mapped_column
+
+from app.db.base import Base
+
+
+class ProcessingLogEntry(Base):
+    """Stores a timestamped processing event with optional model prompt and response text."""
+
+    __tablename__ = "processing_logs"
+
+    id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False, default=lambda: datetime.now(UTC))
+    level: Mapped[str] = mapped_column(String(16), nullable=False, default="info")
+    stage: Mapped[str] = mapped_column(String(64), nullable=False)
+    event: Mapped[str] = mapped_column(String(256), nullable=False)
+    document_id: Mapped[uuid.UUID | None] = mapped_column(
+        UUID(as_uuid=True),
+        ForeignKey("documents.id", ondelete="SET NULL"),
+        nullable=True,
+    )
+    document_filename: Mapped[str | None] = mapped_column(String(512), nullable=True)
+    provider_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
+    model_name: Mapped[str | None] = mapped_column(String(256), nullable=True)
+    prompt_text: Mapped[str | None] = mapped_column(Text, nullable=True)
+    response_text: Mapped[str | None] = mapped_column(Text, nullable=True)
+    payload_json: Mapped[dict] = mapped_column(JSONB, nullable=False, default=dict)