jobhunt-platform/apps/api/app/scheduler.py

"""APScheduler integration: daily fetch + batch score + imap poll + digest.

Starts during app lifespan when SCHEDULER_ENABLED=true (default false).
Jobs:
  - daily_fetch_score at 07:00: fetch postings + batch score
  - daily_digest at 07:30: send daily digest notification
  - imap_poll every 15 min: poll inbox for new emails (gated by EMAIL_WATCH_ENABLED)
"""

from __future__ import annotations

import logging
import os

logger = logging.getLogger(__name__)

_scheduler = None


def is_scheduler_enabled() -> bool:
    """Check if the scheduler is enabled via env."""
    return os.environ.get("SCHEDULER_ENABLED", "false").lower() in (
        "true",
        "1",
        "yes",
    )


def is_email_watch_enabled() -> bool:
    """Check if email watch is enabled via env."""
    return os.environ.get("EMAIL_WATCH_ENABLED", "false").lower() in (
        "true",
        "1",
        "yes",
    )


async def _daily_fetch_and_score() -> None:
    """Daily job: fetch postings and batch-score pending applications."""
    logger.info("Scheduler: running daily fetch + batch score")
    try:
        # Import here to avoid circular imports
        from app.main import _fetch_and_create_postings, _batch_score_internal

        # Fetch default query
        fetch_result = _fetch_and_create_postings(
            query="developer",
            region="Skane lan",
        )
        logger.info(
            "Scheduler: fetched %s new, %s dupes",
            fetch_result.get("new", 0),
            fetch_result.get("dupes", 0),
        )

        # Batch score all discovered applications
        from app.db import repo_app
        apps = repo_app.list_applications()
        discovered_ids = [
            a["id"] for a in apps if a["state"] == "discovered"
        ]
        if discovered_ids:
            results = _batch_score_internal(discovered_ids)
            logger.info(
                "Scheduler: batch-scored %s applications", len(results)
            )
    except Exception:
        logger.exception("Scheduler: daily job failed")


async def _daily_digest() -> None:
    """Daily digest: build /today payload text and send notification."""
    logger.info("Scheduler: running daily digest")
    try:
        from app.notify import send_notification
        from app.db import repo_app

        digest_apps = repo_app.get_digest(limit=20)
        nudge_apps = repo_app.get_nudge_applications()
        pending = repo_app.count_pending_approvals()

        lines: list[str] = []
        lines.append("Daily Digest")
        lines.append(f"Scored applications: {len(digest_apps)}")
        if digest_apps:
            lines.append("")
            lines.append("Top opportunities:")
            for item in digest_apps[:5]:
                score = item.get("score")
                score_str = f" (score: {int(score)})" if score else ""
                lines.append(
                    f"  - {item.get('title', '?')} at {item.get('company', '?')}{score_str}"
                )

        if nudge_apps:
            lines.append("")
            lines.append(f"Follow-up nudges: {len(nudge_apps)}")
            for n in nudge_apps[:5]:
                lines.append(
                    f"  - {n.get('title', '?')} at {n.get('company', '?')}"
                    f" ({n.get('days_since_sent', 0)} days since sent)"
                )

        if pending:
            lines.append("")
            lines.append(f"Pending approvals: {pending}")

        text = "\n".join(lines)
        send_notification("daily_digest", text, {
            "digest_count": len(digest_apps),
            "nudge_count": len(nudge_apps),
            "pending_approvals": pending,
        })
        logger.info("Scheduler: daily digest sent")
    except Exception:
        logger.exception("Scheduler: daily digest failed")


async def _imap_poll() -> None:
    """IMAP poll job: check for new emails and create suggestions."""
    if not is_email_watch_enabled():
        return
    logger.info("Scheduler: running imap poll")
    try:
        from app.imap_watch import poll_inbox
        created = poll_inbox()
        logger.info("Scheduler: imap poll created %s suggestions", len(created))
    except Exception:
        logger.exception("Scheduler: imap poll failed")


def start_scheduler() -> None:
    """Start the APScheduler if enabled."""
    global _scheduler
    if not is_scheduler_enabled():
        logger.info("Scheduler disabled (SCHEDULER_ENABLED != true)")
        return

    try:
        from apscheduler.schedulers.asyncio import AsyncIOScheduler
        from apscheduler.triggers.cron import CronTrigger
        from apscheduler.triggers.interval import IntervalTrigger
    except ImportError:
        logger.warning(
            "APScheduler not installed; scheduler will not start."
        )
        return

    _scheduler = AsyncIOScheduler()
    _scheduler.add_job(
        _daily_fetch_and_score,
        CronTrigger(hour=7, minute=0),
        id="daily_fetch_score",
        replace_existing=True,
    )
    _scheduler.add_job(
        _daily_digest,
        CronTrigger(hour=7, minute=30),
        id="daily_digest",
        replace_existing=True,
    )
    _scheduler.add_job(
        _imap_poll,
        IntervalTrigger(minutes=15),
        id="imap_poll",
        replace_existing=True,
    )
    _scheduler.start()
    logger.info("Scheduler started: daily fetch+score at 07:00, digest at 07:30, imap poll every 15 min")


def stop_scheduler() -> None:
    """Stop the scheduler if running."""
    global _scheduler
    if _scheduler is not None:
        _scheduler.shutdown(wait=False)
        _scheduler = None
        logger.info("Scheduler stopped")