Add project and organization foreign keys to async Job model

backend/app/alembic/versions/043_add_project_org_to_job_table.py

@@ -0,0 +1,92 @@
+"""Add project_id and organization_id to job table
+
+Revision ID: 043
+Revises: 042
+Create Date: 2026-02-04 14:39:00.000000
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "043"
+down_revision = "042"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Add organization_id column
+    op.add_column(
+        "job",
+        sa.Column(
+            "organization_id",
+            sa.Integer(),
+            nullable=False,
+            comment="Reference to the organization",
+        ),
+    )
+
+    # Add project_id column
+    op.add_column(
+        "job",
+        sa.Column(
+            "project_id",
+            sa.Integer(),
+            nullable=False,
+            comment="Reference to the project",
+        ),
+    )
+
+    # Create foreign key constraints
+    op.create_foreign_key(
+        "fk_job_organization_id",
+        "job",
+        "organization",
+        ["organization_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.create_foreign_key(
+        "fk_job_project_id",
+        "job",
+        "project",
+        ["project_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    # Create indexes
+    op.create_index(
+        "ix_job_organization_id",
+        "job",
+        ["organization_id"],
+        unique=False,
+    )
+
+    op.create_index(
+        "ix_job_project_id",
+        "job",
+        ["project_id"],
+        unique=False,
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Drop indexes
+    op.drop_index("ix_job_project_id", table_name="job")
+    op.drop_index("ix_job_organization_id", table_name="job")
+
+    # Drop foreign key constraints
+    op.drop_constraint("fk_job_project_id", "job", type_="foreignkey")
+    op.drop_constraint("fk_job_organization_id", "job", type_="foreignkey")
+
+    # Drop columns
+    op.drop_column("job", "project_id")
+    op.drop_column("job", "organization_id")
+    # ### end Alembic commands ###

backend/app/api/docs/documents/upload.md

@@ -4,6 +4,12 @@ Upload a document to Kaapi.
 - If a target format is specified, a transformation job will also be created to transform document into target format in the background. The response will include both the uploaded document details and information about the transformation job.
 - If a callback URL is provided, you will receive a notification at that URL once the document transformation job is completed.
 
+### File Size Restrictions
+
+- **Maximum file size**: 50MB (configurable via `MAX_DOCUMENT_UPLOAD_SIZE_MB` environment variable)
+- Files exceeding the size limit will be rejected with a 413 (Payload Too Large) error
+- Empty files will be rejected with a 422 (Unprocessable Entity) error
+
 ### Supported Transformations
 
 The following (source_format → target_format) transformations are supported:

backend/app/api/routes/documents.py

@@ -34,6 +34,7 @@
     build_document_schema,
     build_document_schemas,
 )
+from app.services.documents.validators import validate_document_file
 from app.utils import (
     APIResponse,
     get_openai_client,
@@ -123,6 +124,9 @@ async def upload_doc(
     if callback_url:
         validate_callback_url(callback_url)
 
+    # Validate file size before uploading to S3
+    await validate_document_file(src)
+
     source_format, actual_transformer = pre_transform_validation(
         src_filename=src.filename,
         target_format=target_format,

backend/app/api/routes/login.py

@@ -83,7 +83,7 @@ def recover_password(email: str, session: SessionDep) -> Message:
     return Message(message="Password recovery email sent")
 
 
-@router.post("/reset-password/", include_in_schema=False)
+@router.post("/reset-password", include_in_schema=False)
 def reset_password(session: SessionDep, body: NewPassword) -> Message:
     """
     Reset password

backend/app/api/routes/private.py

@@ -20,7 +20,7 @@ class PrivateUserCreate(BaseModel):
     is_verified: bool = False
 
 
-@router.post("/users/", response_model=UserPublic, include_in_schema=False)
+@router.post("/users", response_model=UserPublic, include_in_schema=False)
 def create_user(user_in: PrivateUserCreate, session: SessionDep) -> Any:
     """
     Create a new user.

backend/app/api/routes/utils.py

@@ -27,6 +27,6 @@ def test_email(email_to: EmailStr) -> Message:
     return Message(message="Test email sent")
 
 
-@router.get("/health/", include_in_schema=False)
+@router.get("/health", include_in_schema=False)
 async def health_check() -> bool:
     return True

backend/app/core/config.py

@@ -123,6 +123,9 @@ def AWS_S3_BUCKET(self) -> str:
     CALLBACK_CONNECT_TIMEOUT: int = 3
     CALLBACK_READ_TIMEOUT: int = 10
 
+    # Document upload size limit (in MB)
+    MAX_DOCUMENT_UPLOAD_SIZE_MB: int = 50
+
     @computed_field  # type: ignore[prop-decorator]
     @property
     def COMPUTED_CELERY_WORKER_CONCURRENCY(self) -> int:

backend/app/crud/jobs.py

@@ -12,9 +12,17 @@ class JobCrud:
     def __init__(self, session: Session):
         self.session = session
 
-    def create(self, job_type: JobType, trace_id: str | None = None) -> Job:
+    def create(
+        self,
+        job_type: JobType,
+        project_id: int,
+        organization_id: int,
+        trace_id: str | None = None,
+    ) -> Job:
         new_job = Job(
             job_type=job_type,
+            project_id=project_id,
+            organization_id=organization_id,
             trace_id=trace_id,
         )
         self.session.add(new_job)

backend/app/models/job.py

@@ -1,11 +1,16 @@
 from datetime import datetime
 from enum import Enum
+from typing import TYPE_CHECKING, Optional
 from uuid import UUID, uuid4
 
-from sqlmodel import Field, SQLModel
+from sqlmodel import Field, Relationship, SQLModel
 
 from app.core.util import now
 
+if TYPE_CHECKING:
+    from .organization import Organization
+    from .project import Project
+
 
 class JobStatus(str, Enum):
     PENDING = "PENDING"
@@ -58,6 +63,22 @@ class Job(SQLModel, table=True):
         },
     )
 
+    # Foreign keys
+    organization_id: int = Field(
+        foreign_key="organization.id",
+        nullable=False,
+        ondelete="CASCADE",
+        index=True,
+        sa_column_kwargs={"comment": "Reference to the organization"},
+    )
+    project_id: int = Field(
+        foreign_key="project.id",
+        nullable=False,
+        ondelete="CASCADE",
+        index=True,
+        sa_column_kwargs={"comment": "Reference to the project"},
+    )
+
     # Timestamps
     created_at: datetime = Field(
         default_factory=now,
@@ -68,6 +89,10 @@ class Job(SQLModel, table=True):
         sa_column_kwargs={"comment": "Timestamp when the job was last updated"},
     )
 
+    # Relationships
+    organization: Optional["Organization"] = Relationship()
+    project: Optional["Project"] = Relationship()
+
 
 class JobUpdate(SQLModel):
     status: JobStatus | None = None

backend/app/services/documents/validators.py

@@ -0,0 +1,54 @@
+"""Validation utilities for document uploads."""
+
+import logging
+from pathlib import Path
+
+from fastapi import HTTPException, UploadFile
+
+from app.core.config import settings
+
+logger = logging.getLogger(__name__)
+
+# Maximum file size for document uploads (in bytes)
+# Default: 50 MB, configurable via settings
+MAX_DOCUMENT_SIZE = settings.MAX_DOCUMENT_UPLOAD_SIZE_MB * 1024 * 1024
+
+
+async def validate_document_file(file: UploadFile) -> int:
+    """
+    Validate document file size.
+
+    Args:
+        file: The uploaded file
+
+    Returns:
+        File size in bytes if valid
+
+    Raises:
+        HTTPException: If validation fails
+    """
+    if not file.filename:
+        raise HTTPException(
+            status_code=422,
+            detail="File must have a filename",
+        )
+
+    # Get file size by seeking to end
+    file.file.seek(0, 2)
+    file_size = file.file.tell()
+    file.file.seek(0)
+
+    if file_size > MAX_DOCUMENT_SIZE:
+        raise HTTPException(
+            status_code=413,
+            detail=f"File too large. Maximum size: {MAX_DOCUMENT_SIZE / (1024 * 1024):.0f}MB",
+        )
+
+    if file_size == 0:
+        raise HTTPException(
+            status_code=422,
+            detail="Empty file uploaded"
+        )
+
+    logger.info(f"Document file validated: {file.filename} ({file_size} bytes)")
+    return file_size

backend/app/services/llm/jobs.py

@@ -26,7 +26,12 @@ def start_job(
     """Create an LLM job and schedule Celery task."""
     trace_id = correlation_id.get() or "N/A"
     job_crud = JobCrud(session=db)
-    job = job_crud.create(job_type=JobType.LLM_API, trace_id=trace_id)
+    job = job_crud.create(
+        job_type=JobType.LLM_API,
+        project_id=project_id,
+        organization_id=organization_id,
+        trace_id=trace_id,
+    )
 
     try:
         task_id = start_high_priority_job(

backend/app/services/response/jobs.py

@@ -19,7 +19,12 @@ def start_job(
     """Create a response job and schedule Celery task."""
     trace_id = correlation_id.get() or "N/A"
     job_crud = JobCrud(session=db)
-    job = job_crud.create(job_type=JobType.RESPONSE, trace_id=trace_id)
+    job = job_crud.create(
+        job_type=JobType.RESPONSE,
+        project_id=project_id,
+        organization_id=organization_id,
+        trace_id=trace_id,
+    )
 
     try:
         task_id = start_high_priority_job(