Model/backend/app/documents/router.py
Khalim Conn-Kowlessar 9ec7987e97 PR review: best-effort read path, true per-member streaming, race-safe 409, local email 🟩
Addresses PR #1498 review:
- A per-file read failure (missing/deleted object, or a bucket the role can't
  reach) is now a SkippedDocument(reason=unreadable), not a whole-run abort;
  an all-unreadable selection still fails (no empty package). Best-effort on
  the read path (ADR-0060).
- Each ZIP member is streamed to a temp file (S3DocumentDownloader.download,
  boto download_file) and added from disk, so a single multi-GB member never
  hits the heap — the 'never held whole in memory' claim is now true.
- The 409 double-submit guard is DB-arbitrated: the sub_task insert is
  conditional on the task having none, so a race creates only one.
- Local env gets a placeholder recipient email so the route is exercisable.
- PackageEntry carries landlord_property_id so a read failure can be reported.
- TODO noting the UploadedFile.s3_upload_timestamp typing fix.
Two new tests: per-file read failure skips-and-reports; address fallback flows
to the folder name.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-08 11:08:46 +00:00

156 lines
5.5 KiB
Python

"""Bulk Document Download trigger: POST /v1/documents/bulk-download (ADR-0060).
Resolves the authenticated requester's email, resolves + caps the property
selection, pins the recipe onto a single pre-created sub_task under the
app-owned task, and enqueues one message to the bulk_document_download worker.
Never assembles the package synchronously — the worker emails the link.
"""
import json
from collections.abc import Callable, Iterator
from typing import Any, cast
from uuid import uuid4
import boto3
from fastapi import APIRouter, Depends, HTTPException
from sqlmodel import Session
from backend.app.config import get_settings
from backend.app.db.connection import db_engine
from backend.app.dependencies import validate_jwt_token, validate_token
from backend.app.documents.download_tasks import DocumentDownloadTasks
from backend.app.documents.schemas import BulkDownloadRequest
# The selection cap (ADR-0060) — rejected at the trigger so an oversized request
# never reaches the worker. A conservative, tunable starting value.
MAX_PROPERTIES = 500
MessageSender = Callable[[str], None]
def get_session() -> Iterator[Session]:
with Session(db_engine) as session:
yield session
def get_message_sender() -> MessageSender:
settings = get_settings()
client: Any = cast(Any, boto3.client("sqs", settings.AWS_DEFAULT_REGION)) # pyright: ignore[reportUnknownMemberType]
queue_url = settings.BULK_DOCUMENT_DOWNLOAD_SQS_URL
def send(body: str) -> None:
client.send_message(QueueUrl=queue_url, MessageBody=body)
return send
def get_requesting_user_email(user: Any = Depends(validate_jwt_token)) -> str:
"""The authenticated requester's email — the Download Package recipient.
ADR-0059: the route resolves the user (JWT ``dbId`` -> ``UserModel``) rather
than only gating the token, and threads the email into the job."""
email: Any = getattr(user, "email", None)
if email is None and isinstance(user, dict):
email = cast(dict[str, Any], user).get("email")
if not email and get_settings().ENVIRONMENT == "local":
# Local `get_user` returns a dummy dict with no email; a placeholder lets
# the route be exercised end-to-end on a dev machine (email is a no-op
# locally anyway).
email = "local-dev@example.com"
if not email:
raise HTTPException(
status_code=400,
detail="Could not determine the requesting user's email address.",
)
return str(email)
router = APIRouter(
prefix="/documents",
tags=["documents"],
dependencies=[Depends(validate_token)],
)
@router.post("/bulk-download", status_code=202)
async def bulk_download(
body: BulkDownloadRequest,
session: Session = Depends(get_session),
send_message: MessageSender = Depends(get_message_sender),
recipient_email: str = Depends(get_requesting_user_email),
) -> dict[str, str]:
tasks = DocumentDownloadTasks(session)
if tasks.already_distributed(body.task_id):
raise HTTPException(
status_code=409,
detail=(
f"Task {body.task_id} already has a sub_task — a download has "
"already been started for it."
),
)
config = tasks.read_selection_config(body.task_id)
portfolio_id = config.get("portfolio_id")
property_ids = config.get("property_ids")
select_all = bool(config.get("select_all", False))
if not isinstance(portfolio_id, int):
raise HTTPException(
status_code=400,
detail="task.inputs is missing an integer portfolio_id.",
)
if not select_all and not property_ids:
raise HTTPException(
status_code=400,
detail="task.inputs must provide property_ids or set select_all.",
)
property_count, landlord_property_ids = tasks.resolve_selection(
portfolio_id, property_ids, select_all
)
if property_count == 0:
raise HTTPException(
status_code=400,
detail=(
f"The selection resolves to no properties in portfolio "
f"{portfolio_id}."
),
)
if property_count > MAX_PROPERTIES:
raise HTTPException(
status_code=400,
detail=(
f"The selection has {property_count} properties, over the "
f"{MAX_PROPERTIES} limit — narrow your selection."
),
)
if not landlord_property_ids:
raise HTTPException(
status_code=400,
detail=(
"None of the selected properties have a landlord_property_id, "
"so no documents can be matched."
),
)
subtask_id = uuid4()
recipe = {
"landlord_property_ids": landlord_property_ids,
"recipient_email": recipient_email,
"package_name": f"portfolio-{portfolio_id}-{body.task_id}",
}
created = tasks.create_download_subtask(body.task_id, subtask_id, recipe)
if not created:
# Lost a double-submit race — another request already created the
# sub_task. The DB arbitrated; don't enqueue a second job.
raise HTTPException(
status_code=409,
detail=(
f"Task {body.task_id} already has a sub_task — a download has "
"already been started for it."
),
)
send_message(
json.dumps({"task_id": str(body.task_id), "subtask_id": str(subtask_id)})
)
return {"message": "Bulk document download started"}