osint-dashboard/news/summerizer/run_news_summarizer.py

#!/usr/bin/env python3
"""Scheduler loop for the news summarizer — hourly summarize at minute :05.

Replaces the k8s CronJob (`5 * * * *`) with an in-compose loop. Runs once on
boot (catches up on any articles scraped since the last summary), then fires
at each :NEWS_SUMMARIZE_MINUTE wall-clock boundary.

The loop is serial, so a slow LLM pass never overlaps the next run.

Env (all optional, 12-factor):
  NEWS_SUMMARIZE_MINUTE        minute of the hour to fire (default 5)
  NEWS_SUMMARIZE_RUN_ON_START  "1" to summarize once immediately on boot (default 1)
  NOUS_API_KEY                 optional in env; Keys UI / api_keys also works
"""

from __future__ import annotations

import datetime
import logging
import os
import subprocess
import sys
import time

logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
logger = logging.getLogger("news.summarizer.scheduler")

MINUTE = int(os.getenv("NEWS_SUMMARIZE_MINUTE", "5"))
RUN_ON_START = os.getenv("NEWS_SUMMARIZE_RUN_ON_START", "1").lower() in ("1", "true", "yes")


def seconds_until_next(minute: int) -> float:
    """Seconds until the next occurrence of ``minute`` past the hour (local time)."""
    now = datetime.datetime.now()
    nxt = now.replace(minute=minute, second=0, microsecond=0) + datetime.timedelta(hours=1)
    return (nxt - now).total_seconds()


def run_summarize() -> None:
    logger.info("summarize starting at %s", datetime.datetime.now().isoformat(timespec="seconds"))
    try:
        proc = subprocess.run([sys.executable, "summarizer.py"], cwd="/app")
        logger.info("summarize finished rc=%s", proc.returncode)
    except Exception:  # noqa: BLE001 — keep the loop alive across failures
        logger.exception("summarize failed")


def main() -> None:
    if not os.getenv("NOUS_API_KEY", "").strip():
        logger.warning(
            "NOUS_API_KEY unset in env — will read api_keys on each run; idle if both empty"
        )
    logger.info(
        "news summarizer loop starting (minute=%s, run_on_start=%s)",
        MINUTE, RUN_ON_START,
    )
    if RUN_ON_START:
        run_summarize()
    while True:
        delay = seconds_until_next(MINUTE)
        logger.info("next summarize at :%02d (in %.0fs)", MINUTE, delay)
        time.sleep(delay)
        run_summarize()


if __name__ == "__main__":
    sys.exit(main())