Fix SSE route dependency and align architecture docs

backend/app/domain/documents/__init__.py

@@ -0,0 +1,17 @@
+"""Initialize the app.domain.documents package."""
+
+from .models import Chunk, Document, DocumentStatus, ParsedDocument
+from .ports import ChunkBuilder, DocumentBinaryStore, DocumentParser, DocumentRepository
+# Keep package boundaries explicit so backend imports stay predictable.
+
+
+__all__ = [
+    "Chunk",
+    "Document",
+    "DocumentStatus",
+    "ParsedDocument",
+    "ChunkBuilder",
+    "DocumentBinaryStore",
+    "DocumentParser",
+    "DocumentRepository",
+]

backend/app/domain/documents/models.py

@@ -0,0 +1,77 @@
+"""Define domain models for documents."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from datetime import UTC, datetime
+from enum import Enum
+from typing import Any
+# Keep module behavior explicit so the backend flow stays easy to audit.
+
+
+def utcnow() -> datetime:
+    return datetime.now(UTC)
+
+
+
+class DocumentStatus(str, Enum):
+    """Define the Document Status enumeration."""
+    PENDING = "pending"
+    STORED = "stored"
+    PARSED = "parsed"
+    INDEXED = "indexed"
+    FAILED = "failed"
+
+
+@dataclass
+class Document:
+    """Represent the Document type."""
+    doc_id: str
+    doc_name: str
+    file_name: str
+    object_name: str
+    content_type: str
+    size_bytes: int
+    status: DocumentStatus = DocumentStatus.PENDING
+    regulation_type: str = ""
+    version: str = ""
+    summary: str = ""
+    summary_latency_ms: int = 0
+    chunk_count: int = 0
+    parser_name: str = ""
+    index_name: str = ""
+    error_message: str = ""
+    created_at: datetime = field(default_factory=utcnow)
+    updated_at: datetime = field(default_factory=utcnow)
+    metadata: dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class ParsedDocument:
+    """Represent the Parsed Document type."""
+    doc_id: str
+    doc_name: str
+    structure_nodes: list[dict[str, Any]]
+    semantic_blocks: list[dict[str, Any]]
+    vector_chunks: list[dict[str, Any]]
+    parser_name: str
+    raw_text: str = ""
+    metadata: dict[str, Any] = field(default_factory=dict)
+
+
+@dataclass
+class Chunk:
+    """Represent the Chunk type."""
+    chunk_id: str
+    doc_id: str
+    doc_name: str
+    content: str
+    embedding_text: str
+    section_title: str = ""
+    section_path: list[str] = field(default_factory=list)
+    page_number: int = 0
+    regulation_type: str = ""
+    version: str = ""
+    semantic_id: str = ""
+    block_type: str = ""
+    metadata: dict[str, Any] = field(default_factory=dict)

backend/app/domain/documents/ports.py

@@ -0,0 +1,96 @@
+"""Define domain ports for documents."""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+from .models import Chunk, Document, DocumentStatus, ParsedDocument
+# Keep domain contracts explicit so adapters can swap implementations cleanly.
+
+
+
+class DocumentRepository(ABC):
+    """Provide the Document Repository repository implementation."""
+    @abstractmethod
+    def create(self, document: Document) -> Document:
+        """Handle create for the Document Repository instance."""
+        pass
+
+    @abstractmethod
+    def update(self, document: Document) -> Document:
+        """Handle update for the Document Repository instance."""
+        pass
+
+    @abstractmethod
+    def get(self, doc_id: str) -> Document | None:
+        """Handle get for the Document Repository instance."""
+        pass
+
+    @abstractmethod
+    def list(self, limit: int | None = None) -> list[Document]:
+        """Handle list for the Document Repository instance."""
+        pass
+
+    @abstractmethod
+    def update_status(
+        self,
+        doc_id: str,
+        status: DocumentStatus,
+        *,
+        error_message: str = "",
+        chunk_count: int | None = None,
+        summary: str | None = None,
+        summary_latency_ms: int | None = None,
+        parser_name: str | None = None,
+        index_name: str | None = None,
+        metadata: dict | None = None,
+    ) -> Document | None:
+        """Update status for the Document Repository instance."""
+        pass
+
+
+class DocumentBinaryStore(ABC):
+    """Provide the Document Binary Store store implementation."""
+    @abstractmethod
+    def save(
+        self,
+        *,
+        object_name: str,
+        data: bytes,
+        content_type: str,
+        metadata: dict[str, str] | None = None,
+    ) -> None:
+        """Handle save for the Document Binary Store instance."""
+        pass
+
+    @abstractmethod
+    def read(self, object_name: str) -> bytes:
+        """Handle read for the Document Binary Store instance."""
+        pass
+
+    @abstractmethod
+    def delete(self, object_name: str) -> None:
+        """Handle delete for the Document Binary Store instance."""
+        pass
+
+
+class DocumentParser(ABC):
+    """Provide the Document Parser parser."""
+    @abstractmethod
+    def parse(self, *, file_path: str, doc_id: str, doc_name: str) -> ParsedDocument:
+        """Handle parse for the Document Parser instance."""
+        pass
+
+
+class ChunkBuilder(ABC):
+    """Provide the Chunk Builder builder."""
+    @abstractmethod
+    def build(
+        self,
+        *,
+        parsed_document: ParsedDocument,
+        regulation_type: str,
+        version: str,
+    ) -> list[Chunk]:
+        """Handle build for the Chunk Builder instance."""
+        pass