Massprice/scheduler.py
Barely Removable 0f336b3d0c
All checks were successful
Deploy / deploy (push) Successful in 22s
Fix crash-loop: CronTrigger resolves its own timezone independent of the scheduler's
The America/Phoenix TZ fix earlier only passed timezone= to
BackgroundScheduler's constructor. That wasn't enough: APScheduler's
CronTrigger independently calls tzlocal's get_localzone() in its own
__init__ when not given an explicit timezone, regardless of what the
scheduler itself is configured with. This never surfaced in testing
because schedules.json was always empty — the rebuild_jobs() loop that
constructs CronTrigger never executed. It crashed for real once a real
schedule existed (confirmed live: the already-configured "Pokemon
Singles >10" 4x/day schedule crash-looped the container on every boot).
Fixed by passing the same resolved timezone to every CronTrigger call.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01H6TgffxTvYhqxykAbVQg2v
2026-08-31 20:25:25 -07:00

101 lines
3.3 KiB
Python

"""In-process cron scheduling for rule runs.
A single background worker thread owns every Playwright run — both
APScheduler-triggered runs and manual "Run Now" clicks are pushed onto
one queue.Queue so exactly one browser session is ever active at a time.
This must run in exactly one process; see gunicorn.conf.py's workers=1.
"""
import logging
import os
import queue
import threading
import pytz
from apscheduler.schedulers.background import BackgroundScheduler
from apscheduler.triggers.cron import CronTrigger
import automation
import storage
logger = logging.getLogger("massprice.scheduler")
_work_queue: "queue.Queue" = queue.Queue()
# Resolved once and reused everywhere a timezone is needed. Must be
# passed explicitly at construction time, never left to be inferred —
# both BackgroundScheduler AND CronTrigger independently call tzlocal's
# get_localzone() in their own __init__ if not given one, which fails
# inside this container image for an arbitrary $TZ (no zoneinfo/tzdata
# wiring). Passing it to the scheduler alone is NOT enough — a
# CronTrigger built without its own explicit timezone still resolves
# get_localzone() itself, regardless of what the scheduler is configured
# with, and crashes the same way. Every CronTrigger(...) below must pass
# timezone=_TZ explicitly.
_TZ = pytz.timezone(os.environ.get("TZ", "UTC"))
_scheduler = BackgroundScheduler(timezone=_TZ)
_started = False
VALID_DAYS = ["mon", "tue", "wed", "thu", "fri", "sat", "sun"]
def _worker_loop():
while True:
rule_id, rule_name = _work_queue.get()
try:
automation.run_rule(rule_id, rule_name)
except Exception:
logger.exception("Unhandled error running rule %s", rule_id)
finally:
_work_queue.task_done()
def enqueue_run(rule_id, rule_name=None):
_work_queue.put((rule_id, rule_name))
def _job_id(rule_id, index):
return f"rule-{rule_id}-{index}"
def rebuild_jobs():
"""Clear and re-add every APScheduler job from schedules.json."""
for job in _scheduler.get_jobs():
job.remove()
schedules = storage.load("schedules.json", {})
for rule_id, rule in schedules.items():
if not rule.get("enabled", True):
continue
for idx, entry in enumerate(rule.get("schedules", [])):
days = [d for d in entry.get("days", []) if d in VALID_DAYS]
time_str = entry.get("time")
if not days or not time_str:
continue
hour, minute = time_str.split(":")
trigger = CronTrigger(
day_of_week=",".join(days),
hour=int(hour),
minute=int(minute),
timezone=_TZ,
)
_scheduler.add_job(
enqueue_run,
trigger=trigger,
args=[rule_id, rule.get("name")],
id=_job_id(rule_id, idx),
replace_existing=True,
misfire_grace_time=300,
)
logger.info("Rebuilt %d scheduled job(s)", len(_scheduler.get_jobs()))
def start(tz=None):
# tz is accepted for backwards-compat call sites but is a no-op now
# that timezone is fixed at construction time above.
global _started
if _started:
return
rebuild_jobs()
_scheduler.start()
threading.Thread(target=_worker_loop, daemon=True).start()
_started = True