siftlode/backend/app/scheduler.py

"""Background scheduler: free RSS detection, enrichment of new videos, and quota-aware
recent-first / deep backfill. Runs inside the API process (single worker)."""
import logging
import threading
from datetime import datetime, timezone

from apscheduler.schedulers.background import BackgroundScheduler
from sqlalchemy import select

from app import quota
from app.config import settings
from app.db import SessionLocal
from app.models import SchedulerSetting
from app.state import is_sync_paused
from app.sync.autotag import run_autotag_all
from app.sync.playlists import sync_all_playlists
from app.sync.runner import (
    run_deep_backfill,
    run_enrich,
    run_recent_backfill,
    run_rss_poll,
    run_shorts,
    run_subscription_resync,
)

logger = logging.getLogger("subfeed.scheduler")

_scheduler: BackgroundScheduler | None = None

# Per-job run activity, kept in-memory for the admin Scheduler dashboard to read (the
# scheduler lives in the same single-worker process as the API, so a request can read it
# directly). Ephemeral by design — it reflects "what the scheduler is doing right now and
# how the last runs went" since this process started; durable history isn't the goal here.
_activity: dict[str, dict] = {}
_activity_lock = threading.Lock()

# Each interval job's env/config default period (minutes). The admin can override any of
# these at runtime (stored in scheduler_settings, applied live); see load_intervals.
JOB_INTERVALS: dict[str, int] = {
    "rss_poll": settings.rss_poll_minutes,
    "enrich": settings.enrich_interval_minutes,
    "backfill": settings.backfill_interval_minutes,
    "autotag": settings.autotag_interval_minutes,
    "shorts": settings.shorts_probe_interval_minutes,
    "subscriptions": settings.subscriptions_resync_minutes,
    "playlist_sync": settings.playlist_sync_minutes,
}

# Sane bounds for an admin-set interval (minutes).
MIN_INTERVAL = 1
MAX_INTERVAL = 1440  # one day


def load_intervals(db) -> dict[str, int]:
    """Effective per-job intervals: the env/config defaults overlaid with any admin overrides
    saved in scheduler_settings."""
    iv = dict(JOB_INTERVALS)
    for row in db.execute(select(SchedulerSetting)).scalars():
        if row.job_id in iv and row.interval_minutes:
            iv[row.job_id] = row.interval_minutes
    return iv


def apply_interval(db, job_id: str, minutes: int) -> int:
    """Persist a job's interval override and reschedule the live job immediately (if the
    scheduler runs in this process). Returns the applied value."""
    if job_id not in JOB_INTERVALS:
        raise KeyError(job_id)
    minutes = max(MIN_INTERVAL, min(MAX_INTERVAL, int(minutes)))
    row = db.get(SchedulerSetting, job_id)
    if row is None:
        db.add(SchedulerSetting(job_id=job_id, interval_minutes=minutes))
    else:
        row.interval_minutes = minutes
    db.commit()
    if _scheduler is not None and _scheduler.get_job(job_id) is not None:
        _scheduler.reschedule_job(job_id, trigger="interval", minutes=minutes)
        logger.info("rescheduled job %s to every %s min", job_id, minutes)
    return minutes


def _now_iso() -> str:
    return datetime.now(timezone.utc).isoformat()


def _record(name: str, **fields) -> None:
    with _activity_lock:
        _activity.setdefault(name, {}).update(fields)


def _job(name: str, fn) -> None:
    db = SessionLocal()
    _record(name, running=True, last_started=_now_iso(), last_error=None)
    try:
        if is_sync_paused(db):
            logger.info("job %s skipped (sync paused)", name)
            _record(name, running=False, status="skipped", last_finished=_now_iso(),
                     last_result="paused")
            return
        result = fn(db)
        logger.info("job %s -> %s", name, result)
        _record(name, running=False, status="ok", last_finished=_now_iso(),
                last_result=_summarize(result))
    except Exception as exc:
        db.rollback()
        logger.exception("job %s failed", name)
        _record(name, running=False, status="error", last_finished=_now_iso(),
                last_error=str(exc) or exc.__class__.__name__)
    finally:
        db.close()


def _summarize(result) -> str | None:
    """Compact one-line rendering of a job's return value for the dashboard."""
    if result is None:
        return None
    if isinstance(result, dict):
        return ", ".join(f"{k}={v}" for k, v in result.items()) or None
    return str(result)


def scheduler_snapshot() -> dict:
    """What the scheduler is doing, for the admin dashboard. `running_here` is False in
    environments where the scheduler is disabled (e.g. local dev shares the prod-ish DB but
    runs no scheduler), so the UI can say so while still showing DB-derived queue/quota."""
    running_here = _scheduler is not None
    next_runs: dict[str, str | None] = {}
    live_intervals: dict[str, int] = {}
    if _scheduler is not None:
        for job in _scheduler.get_jobs():
            nr = getattr(job, "next_run_time", None)
            next_runs[job.id] = nr.astimezone(timezone.utc).isoformat() if nr else None
            iv = getattr(job.trigger, "interval", None)
            if iv is not None:
                live_intervals[job.id] = round(iv.total_seconds() / 60)
    with _activity_lock:
        acts = {k: dict(v) for k, v in _activity.items()}
    jobs = []
    for job_id, default_interval in JOB_INTERVALS.items():
        a = acts.get(job_id, {})
        jobs.append(
            {
                "id": job_id,
                "interval_minutes": live_intervals.get(job_id, default_interval),
                "next_run": next_runs.get(job_id),
                "running": a.get("running", False),
                "status": a.get("status"),
                "last_started": a.get("last_started"),
                "last_finished": a.get("last_finished"),
                "last_result": a.get("last_result"),
                "last_error": a.get("last_error"),
            }
        )
    return {"running_here": running_here, "enabled": settings.scheduler_enabled, "jobs": jobs}


def _rss_job() -> None:
    _job("rss_poll", lambda db: run_rss_poll(db))


def _enrich_job() -> None:
    def work(db):
        with quota.attribute(None, "enrich"):
            return run_enrich(db)

    _job("enrich", work)


def _backfill_job() -> None:
    # Recent-first for not-yet-synced channels, then deep backfill for the rest. All
    # background spend is attributed to the system (no actor), split by action.
    def work(db):
        with quota.attribute(None, "backfill_recent"):
            recent = run_recent_backfill(db, max_channels=25)
        with quota.attribute(None, "backfill_deep"):
            deep = run_deep_backfill(db, max_channels=10)
        return {"recent": recent, "deep": deep}

    _job("backfill", work)


def _autotag_job() -> None:
    _job("autotag", lambda db: run_autotag_all(db, only_missing=True))


def _shorts_job() -> None:
    _job("shorts", run_shorts)


def _subscriptions_job() -> None:
    def work(db):
        with quota.attribute(None, "subscription_resync"):
            return run_subscription_resync(db)

    _job("subscriptions", work)


def _playlist_sync_job() -> None:
    # Mirror each read-scope user's YouTube playlists; per-user quota attribution is
    # handled inside sync_all_playlists.
    _job("playlist_sync", sync_all_playlists)


def start_scheduler() -> None:
    global _scheduler
    if not settings.scheduler_enabled or _scheduler is not None:
        return
    # Effective intervals = env defaults overlaid with any admin overrides from the DB.
    db = SessionLocal()
    try:
        iv = load_intervals(db)
    finally:
        db.close()
    fns = {
        "rss_poll": _rss_job,
        "enrich": _enrich_job,
        "backfill": _backfill_job,
        "autotag": _autotag_job,
        "shorts": _shorts_job,
        "subscriptions": _subscriptions_job,
        "playlist_sync": _playlist_sync_job,
    }
    scheduler = BackgroundScheduler(timezone="UTC")
    for job_id, fn in fns.items():
        scheduler.add_job(fn, "interval", minutes=iv[job_id], id=job_id)
    scheduler.start()
    _scheduler = scheduler
    logger.info("scheduler started")


def shutdown_scheduler() -> None:
    global _scheduler
    if _scheduler is not None:
        _scheduler.shutdown(wait=False)
        _scheduler = None