NixReaperandClaude Sonnet 5
669034896a
CI / lint (push) Canceled after 0s
CI / typecheck (push) Canceled after 0s
CI / unit-tests (push) Canceled after 0s
CI / integration-tests (push) Canceled after 0s
CI / container-build (push) Canceled after 0s
CI / dependency-audit (push) Canceled after 0s
POST /api/v1/admin/ingest/movie returned arq's own internal queue
job id, but GET /api/v1/admin/ingest/jobs/{job_id} looked up our
IngestionJob DB row by its own UUID -- a completely different id that
didn't even exist yet at enqueue time (the row was only created once
the worker picked up the task). Every status poll 404'd.
Fix: create the IngestionJob row synchronously in the enqueue endpoint
(reusing the existing idempotency-key logic, so repeat enqueues for
the same tmdb_id reuse the same row rather than creating duplicates),
pass its real id into the arq task, and have the worker update that
row instead of creating a new one.
Found by actually running the milestone end-to-end: enqueue a real
TMDb ingestion, then poll its status.
Co-Authored-By: Claude Sonnet 5 <[email protected]>
101 lines
3.3 KiB
Python
101 lines
3.3 KiB
Python
"""Administrative/provider endpoints (section 17): trigger ingestion and
|
|
check job status. Separately protected by an admin API key — never mounted
|
|
on the public read path.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import uuid
|
|
|
|
from arq import ArqRedis
|
|
from fastapi import APIRouter, Depends, HTTPException, status
|
|
from pydantic import BaseModel
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.api.deps import not_found
|
|
from app.core.database import get_db
|
|
from app.core.queue import get_queue
|
|
from app.core.security import require_admin_api_key
|
|
from app.repositories.provider_repository import get_ingestion_job
|
|
from app.services.ingestion.runner import get_or_create_ingestion_job
|
|
|
|
router = APIRouter(
|
|
prefix="/admin",
|
|
tags=["admin"],
|
|
dependencies=[Depends(require_admin_api_key)],
|
|
)
|
|
|
|
|
|
class IngestMovieRequest(BaseModel):
|
|
tmdb_id: str
|
|
|
|
|
|
class IngestPersonRequest(BaseModel):
|
|
tmdb_id: str
|
|
|
|
|
|
class IngestionEnqueuedOut(BaseModel):
|
|
job_id: str
|
|
arq_job_id: str
|
|
status: str = "enqueued"
|
|
|
|
|
|
class IngestionJobOut(BaseModel):
|
|
id: str
|
|
job_type: str
|
|
entity_type: str | None
|
|
external_id: str | None
|
|
status: str
|
|
attempts: int
|
|
error: str | None
|
|
result_aurora_id: str | None
|
|
|
|
|
|
@router.post("/ingest/movie", response_model=IngestionEnqueuedOut)
|
|
async def enqueue_movie_ingestion(
|
|
body: IngestMovieRequest, queue: ArqRedis = Depends(get_queue)
|
|
) -> IngestionEnqueuedOut:
|
|
# Created synchronously (and idempotently — same tmdb_id reuses the same
|
|
# row) so the response's job_id is immediately valid against
|
|
# GET /ingest/jobs/{job_id}. arq's own job id is a separate, unrelated
|
|
# identifier used only for queue bookkeeping.
|
|
job_id = await get_or_create_ingestion_job("movie_sync", "movie", body.tmdb_id)
|
|
arq_job = await queue.enqueue_job("ingest_movie_task", str(job_id), body.tmdb_id)
|
|
if arq_job is None:
|
|
raise HTTPException(
|
|
status.HTTP_503_SERVICE_UNAVAILABLE, "Could not enqueue ingestion job (queue busy)."
|
|
)
|
|
return IngestionEnqueuedOut(job_id=str(job_id), arq_job_id=arq_job.job_id)
|
|
|
|
|
|
@router.post("/ingest/person", response_model=IngestionEnqueuedOut)
|
|
async def enqueue_person_ingestion(
|
|
body: IngestPersonRequest, queue: ArqRedis = Depends(get_queue)
|
|
) -> IngestionEnqueuedOut:
|
|
job_id = await get_or_create_ingestion_job("person_sync", "person", body.tmdb_id)
|
|
arq_job = await queue.enqueue_job("ingest_person_task", str(job_id), body.tmdb_id)
|
|
if arq_job is None:
|
|
raise HTTPException(
|
|
status.HTTP_503_SERVICE_UNAVAILABLE, "Could not enqueue ingestion job (queue busy)."
|
|
)
|
|
return IngestionEnqueuedOut(job_id=str(job_id), arq_job_id=arq_job.job_id)
|
|
|
|
|
|
@router.get("/ingest/jobs/{job_id}", response_model=IngestionJobOut)
|
|
async def get_ingestion_job_status(
|
|
job_id: uuid.UUID, session: AsyncSession = Depends(get_db)
|
|
) -> IngestionJobOut:
|
|
job = await get_ingestion_job(session, job_id)
|
|
if job is None:
|
|
raise not_found("ingestion_job", str(job_id))
|
|
return IngestionJobOut(
|
|
id=str(job.id),
|
|
job_type=job.job_type,
|
|
entity_type=job.entity_type,
|
|
external_id=job.external_id,
|
|
status=job.status.value,
|
|
attempts=job.attempts,
|
|
error=job.error,
|
|
result_aurora_id=str(job.result_aurora_id) if job.result_aurora_id else None,
|
|
)
|