Add opt-in season cascade to series ingestion
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

Ingesting a series only ever produced season stubs -- getting actual
episodes meant calling POST /admin/ingest/season once per season by
hand, which is exactly what manual end-to-end testing kept requiring
for every multi-season show.

POST /api/v1/admin/ingest/series now takes include_seasons (default
false, since a show can have dozens of seasons and that's dozens of
TMDb calls fired from one request). When true, ingest_series_task
fans out one ingest_season job per season once the series succeeds,
using arq's own ctx['redis'] connection for the job (the same pattern
arq's docs recommend for job chaining) rather than a second unrelated
connection. Each fanned-out season job still goes through
get_or_create_ingestion_job, so re-running a cascaded series ingestion
reuses the same season job rows instead of creating duplicates.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
This commit is contained in:
NixReaper
2026-09-05 02:03:25 -05:00
co-authored by Claude Sonnet 5
parent ec6b5bdd7d
commit b4d1e8f755
6 changed files with 148 additions and 6 deletions
+7 -1
View File
@@ -36,6 +36,12 @@ class IngestPersonRequest(BaseModel):
class IngestSeriesRequest(BaseModel):
tmdb_id: str
# When true, ingest_series_task also enqueues an ingest_season job for
# every season the series has, once the series itself finishes.
# Defaults to false: a show can have dozens of seasons, and cascading
# automatically means dozens of TMDb calls fired off from one request —
# opt in rather than surprise the caller with that.
include_seasons: bool = False
class IngestSeasonRequest(BaseModel):
@@ -120,7 +126,7 @@ async def enqueue_series_ingestion(
entity_type="series",
external_id=body.tmdb_id,
task_name="ingest_series_task",
task_args=(body.tmdb_id,),
task_args=(body.tmdb_id, body.include_seasons),
)
+12
View File
@@ -25,6 +25,7 @@ from app.repositories.provider_repository import (
mark_job_running,
mark_job_succeeded,
)
from app.repositories.tv_repository import get_seasons_for_series
from app.services.ingestion.movie_ingestion import ingest_movie
from app.services.ingestion.person_ingestion import ingest_person
from app.services.ingestion.series_ingestion import ingest_season, ingest_series
@@ -138,3 +139,14 @@ async def run_season_ingestion(
session, provider, series_external_id, season_number, ingestion_job_id=job_id
),
)
async def get_series_season_numbers(series_id: uuid.UUID) -> list[int]:
"""All season numbers a just-ingested series has, for cascading into
per-season ingestion jobs (see `app/workers/tasks.py:ingest_series_task`,
`include_seasons`). A short-lived session of its own since this runs
after `run_series_ingestion`'s own session has already closed."""
async with session_scope() as session:
seasons = await get_seasons_for_series(session, series_id)
return [season.season_number for season in seasons]
+23 -1
View File
@@ -14,6 +14,8 @@ 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,
@@ -33,8 +35,28 @@ async def ingest_person_task(ctx: dict[str, Any], job_id: str, external_id: str)
return str(person_id)
async def ingest_series_task(ctx: dict[str, Any], job_id: str, external_id: str) -> str:
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)