Refactor backend into a reliable modular monolith

backend/migrations/env.py

@@ -1,17 +1,23 @@
 import asyncio
 from logging.config import fileConfig
+
+from alembic import context
 from sqlalchemy import pool
 from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import async_engine_from_config
-from alembic import context
-from src.service import DB_URL
+
+from src.core.config import get_db_url
 from src.models import Base
-import src.models
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
 config = context.config
-config.set_main_option('sqlalchemy.url', DB_URL)
+database_url = get_db_url().render_as_string(hide_password=False)
+
+config.set_main_option(
+    "sqlalchemy.url",
+    database_url.replace("%", "%%"),
+)
 
 # Interpret the config file for Python logging.
 # This line sets up loggers basically.

backend/migrations/versions/0d6439d2e79f_init.py

@@ -1,58 +1,78 @@
 """init
 
 Revision ID: 0d6439d2e79f
-Revises: 
+Revises:
 Create Date: 2026-04-03 16:26:49.885174
 
 """
-from typing import Sequence, Union
 
-from alembic import op
-import sqlalchemy as sa
+from collections.abc import Sequence
 
+import sqlalchemy as sa
+from alembic import op
 
 # revision identifiers, used by Alembic.
-revision: str = '0d6439d2e79f'
-down_revision: Union[str, Sequence[str], None] = None
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
+revision: str = "0d6439d2e79f"
+down_revision: str | Sequence[str] | None = None
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
 
 
 def upgrade() -> None:
     """Upgrade schema."""
     # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table('files',
-    sa.Column('id', sa.String(length=36), nullable=False),
-    sa.Column('title', sa.String(length=255), nullable=False),
-    sa.Column('original_name', sa.String(length=255), nullable=False),
-    sa.Column('stored_name', sa.String(length=255), nullable=False),
-    sa.Column('mime_type', sa.String(length=255), nullable=False),
-    sa.Column('size', sa.Integer(), nullable=False),
-    sa.Column('processing_status', sa.String(length=50), nullable=False),
-    sa.Column('scan_status', sa.String(length=50), nullable=True),
-    sa.Column('scan_details', sa.String(length=500), nullable=True),
-    sa.Column('metadata_json', sa.JSON(), nullable=True),
-    sa.Column('requires_attention', sa.Boolean(), nullable=False),
-    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
-    sa.Column('updated_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('stored_name')
+    op.create_table(
+        "files",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("title", sa.String(length=255), nullable=False),
+        sa.Column("original_name", sa.String(length=255), nullable=False),
+        sa.Column("stored_name", sa.String(length=255), nullable=False),
+        sa.Column("mime_type", sa.String(length=255), nullable=False),
+        sa.Column("size", sa.Integer(), nullable=False),
+        sa.Column("processing_status", sa.String(length=50), nullable=False),
+        sa.Column("scan_status", sa.String(length=50), nullable=True),
+        sa.Column("scan_details", sa.String(length=500), nullable=True),
+        sa.Column("metadata_json", sa.JSON(), nullable=True),
+        sa.Column("requires_attention", sa.Boolean(), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("stored_name"),
     )
-    op.create_table('alerts',
-    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
-    sa.Column('file_id', sa.String(length=36), nullable=False),
-    sa.Column('level', sa.String(length=50), nullable=False),
-    sa.Column('message', sa.String(length=500), nullable=False),
-    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
-    sa.ForeignKeyConstraint(['file_id'], ['files.id'], ),
-    sa.PrimaryKeyConstraint('id')
+    op.create_table(
+        "alerts",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("file_id", sa.String(length=36), nullable=False),
+        sa.Column("level", sa.String(length=50), nullable=False),
+        sa.Column("message", sa.String(length=500), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["file_id"],
+            ["files.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
     )
     # ### end Alembic commands ###
 
 
 def downgrade() -> None:
     """Downgrade schema."""
     # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_table('alerts')
-    op.drop_table('files')
+    op.drop_table("alerts")
+    op.drop_table("files")
     # ### end Alembic commands ###

backend/migrations/versions/72bd615f6afe_cascade_alerts_when_file_is_deleted.py

@@ -0,0 +1,35 @@
+"""cascade alerts when file is deleted
+
+Revision ID: 72bd615f6afe
+Revises: 0d6439d2e79f
+Create Date: 2026-07-12 09:13:18.689868
+
+"""
+
+from collections.abc import Sequence
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "72bd615f6afe"
+down_revision: str | Sequence[str] | None = "0d6439d2e79f"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint(op.f("alerts_file_id_fkey"), "alerts", type_="foreignkey")
+    op.create_foreign_key(
+        "alerts_file_id_fkey", "alerts", "files", ["file_id"], ["id"], ondelete="CASCADE"
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint("alerts_file_id_fkey", "alerts", type_="foreignkey")
+    op.create_foreign_key(op.f("alerts_file_id_fkey"), "alerts", "files", ["file_id"], ["id"])
+    # ### end Alembic commands ###

backend/migrations/versions/daaf09d6664b_add_query_indexes.py

@@ -0,0 +1,34 @@
+"""add query indexes
+
+Revision ID: daaf09d6664b
+Revises: 72bd615f6afe
+Create Date: 2026-07-13 17:11:48.206886
+
+"""
+from collections.abc import Sequence
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = 'daaf09d6664b'
+down_revision: str | Sequence[str] | None = '72bd615f6afe'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_index('ix_alerts_created_at', 'alerts', ['created_at'], unique=False)
+    op.create_index('ix_alerts_file_id', 'alerts', ['file_id'], unique=False)
+    op.create_index('ix_files_created_at', 'files', ['created_at'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index('ix_files_created_at', table_name='files')
+    op.drop_index('ix_alerts_file_id', table_name='alerts')
+    op.drop_index('ix_alerts_created_at', table_name='alerts')
+    # ### end Alembic commands ###

backend/pyproject.toml

@@ -9,8 +9,39 @@ dependencies = [
     "asyncpg>=0.30.0",
     "celery[redis]>=5.6.3",
     "fastapi>=0.135.3",
+    "greenlet>=3.3.2",
     "pydantic>=2.12.5",
     "python-multipart>=0.0.20",
     "sqlalchemy>=2.0.48",
     "uvicorn>=0.42.0",
 ]
+
+[dependency-groups]
+dev = [
+    "httpx>=0.28.1",
+    "pytest>=9.1.1",
+    "pytest-asyncio>=1.4.0",
+    "ruff>=0.15.21",
+]
+
+[tool.ruff]
+target-version = "py314"
+line-length = 100
+
+[tool.ruff.lint]
+select = [
+  "E",   # style errors
+  "F",   # Pyflakes
+  "I",   # import sorting
+  "B",   # likely bugs
+  "UP",  # modern Python syntax
+  "ASYNC",
+]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+pythonpath = ["."]

backend/src/alerts/repository.py

@@ -0,0 +1,24 @@
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio.session import AsyncSession
+
+from src.models import Alert
+
+
+class AlertRepository:
+    def __init__(self, session: AsyncSession):
+        self.session = session
+
+    async def list_ordered(self) -> list[Alert]:
+        result = await self.session.execute(
+            select(Alert).order_by(Alert.created_at.desc())
+        )
+        return list(result.scalars().all())
+
+    async def get_for_file(self, file_id: str) -> Alert | None:
+        result = await self.session.execute(
+            select(Alert).where(Alert.file_id == file_id).limit(1)
+        )
+        return result.scalar_one_or_none()
+
+    def add(self, alert: Alert) -> None:
+        self.session.add(alert)

backend/src/api/alerts.py

@@ -0,0 +1,16 @@
+from typing import Annotated
+
+from fastapi import APIRouter, Depends
+
+from src.alerts.repository import AlertRepository
+from src.api.deps import get_alert_repository
+from src.schemas import AlertItem
+
+router = APIRouter(prefix="/alerts", tags=["alerts"])
+
+
+@router.get("", response_model=list[AlertItem])
+async def list_alerts_view(
+    repository: Annotated[AlertRepository, Depends(get_alert_repository)],
+):
+    return await repository.list_ordered()

backend/src/api/deps.py

@@ -0,0 +1,27 @@
+from typing import Annotated
+
+from fastapi import Depends
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from src.alerts.repository import AlertRepository
+from src.core.config import STORAGE_DIR
+from src.core.database import get_session
+from src.files.repository import FileRepository
+from src.files.service import FileService
+from src.files.storage import FileStorage
+
+
+def get_file_service(
+    session: Annotated[AsyncSession, Depends(get_session)],
+) -> FileService:
+    return FileService(
+        session=session,
+        repository=FileRepository(session),
+        storage=FileStorage(STORAGE_DIR),
+    )
+
+
+def get_alert_repository(
+    session: Annotated[AsyncSession, Depends(get_session)],
+) -> AlertRepository:
+    return AlertRepository(session)

backend/src/api/files.py

@@ -0,0 +1,68 @@
+from typing import Annotated
+
+from fastapi import APIRouter, Depends, File, Form, UploadFile
+from fastapi.responses import FileResponse
+
+from src.api.deps import get_file_service
+from src.files.service import FileService
+from src.processing.tasks import enqueue_file_processing
+from src.schemas import FileItem, FileUpdate
+
+router = APIRouter(prefix="/files", tags=["files"])
+
+
+@router.get("", response_model=list[FileItem])
+async def list_files_view(
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    return await service.list_files()
+
+
+@router.get("/{file_id}", response_model=FileItem)
+async def get_file_view(
+    file_id: str,
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    return await service.get_file(file_id)
+
+
+@router.patch("/{file_id}", response_model=FileItem)
+async def update_file_view(
+    file_id: str,
+    payload: FileUpdate,
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    return await service.update_file(file_id=file_id, title=payload.title)
+
+
+@router.post("", response_model=FileItem, status_code=201)
+async def create_file_view(
+    title: Annotated[str, Form(...)],
+    file: Annotated[UploadFile, File(...)],
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    file_item = await service.create_file(title=title, upload_file=file)
+    enqueue_file_processing(str(file_item.id))
+    return file_item
+
+
+@router.get("/{file_id}/download")
+async def download_file(
+    file_id: str,
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    file_item, stored_path = await service.get_file_path(file_id)
+
+    return FileResponse(
+        path=stored_path,
+        media_type=file_item.mime_type,
+        filename=file_item.original_name,
+    )
+
+
+@router.delete("/{file_id}", status_code=204)
+async def delete_file_view(
+    file_id: str,
+    service: Annotated[FileService, Depends(get_file_service)],
+):
+    await service.delete_file(file_id)