Aurora-Core/app/workers/tasks.py

"""arq task functions. Thin wrappers around the ingestion runner so retry/
concurrency/observability behavior lives in arq's worker loop, not here.

Each task receives the `IngestionJob` row's id (created synchronously by the
enqueuing endpoint via `get_or_create_ingestion_job`, *not* generated here)
so status polling has a real, immediately-valid id to look up from the
moment the HTTP response comes back.
"""

from __future__ import annotations

import uuid
from typing import Any

from app.core.logging import get_logger
from app.services.ingestion.runner import (
    get_or_create_ingestion_job,
    get_series_season_numbers,
    run_movie_ingestion,
    run_person_ingestion,
    run_season_ingestion,
    run_series_ingestion,
)

logger = get_logger(__name__)


async def ingest_movie_task(ctx: dict[str, Any], job_id: str, external_id: str) -> str:
    movie_id = await run_movie_ingestion(uuid.UUID(job_id), external_id)
    return str(movie_id)


async def ingest_person_task(ctx: dict[str, Any], job_id: str, external_id: str) -> str:
    person_id = await run_person_ingestion(uuid.UUID(job_id), external_id)
    return str(person_id)


async def ingest_series_task(
    ctx: dict[str, Any], job_id: str, external_id: str, include_seasons: bool = False
) -> str:
    series_id = await run_series_ingestion(uuid.UUID(job_id), external_id)

    if include_seasons:
        # Fan out one ingest_season job per season this series has, using
        # the same arq connection this task is running on (arq hands every
        # job's ctx a "redis" entry precisely for chaining/fan-out like
        # this) — not a second, unrelated connection.
        redis = ctx["redis"]
        for season_number in await get_series_season_numbers(series_id):
            season_job_id = await get_or_create_ingestion_job(
                "season_sync", "season", f"{external_id}:{season_number}"
            )
            await redis.enqueue_job(
                "ingest_season_task", str(season_job_id), external_id, season_number
            )
        logger.info(
            "series_seasons_cascaded", series_id=str(series_id), external_id=external_id
        )

    return str(series_id)


async def ingest_season_task(
    ctx: dict[str, Any], job_id: str, series_external_id: str, season_number: int
) -> str:
    season_id = await run_season_ingestion(uuid.UUID(job_id), series_external_id, season_number)
    return str(season_id)