sebrief/tests/test_daemon.py

"""Daemon tests with a fake scheduler (captures add_job) and a fake weekly clock."""

from __future__ import annotations

import signal
from datetime import datetime, timedelta
from zoneinfo import ZoneInfo

import pytest
from _fakes import NOW, WEEK, FakeClock, FakeDeliverer, FakeStore
from apscheduler.events import EVENT_JOB_MISSED, JobExecutionEvent
from apscheduler.schedulers import SchedulerNotRunningError
from apscheduler.triggers.date import DateTrigger
from apscheduler.triggers.interval import IntervalTrigger

from sebrief import daemon as daemon_mod
from sebrief.config import Settings
from sebrief.daemon import DIGEST_JOB_ID, HEARTBEAT_JOB_ID, RECOVERY_JOB_ID, Daemon

KST = ZoneInfo("Asia/Seoul")
NEXT_RUN = ("2026-W37", datetime(2026, 9, 14, 7, 0, tzinfo=KST))


class FakeScheduler:
    def __init__(self):
        self.jobs: dict[str, dict] = {}
        self.add_calls: list[dict] = []
        self.shutdown_calls: list[bool] = []
        self.listeners: list[tuple[object, int | None]] = []

    def add_listener(self, callback, mask=None):
        self.listeners.append((callback, mask))

    def add_job(self, func, trigger=None, **kwargs):
        entry = {"func": func, "trigger": trigger, **kwargs}
        self.add_calls.append(entry)
        self.jobs[kwargs.get("id", func.__name__)] = entry
        return entry

    def shutdown(self, wait=True):
        self.shutdown_calls.append(wait)


class RunRecorder:
    def __init__(self, fail: bool = False):
        self.weeks: list[str] = []
        self.fail = fail

    def __call__(self, week: str):
        self.weeks.append(week)
        if self.fail:
            raise RuntimeError("pipeline exploded")


def make_settings(tmp_path, **overrides) -> Settings:
    values = {"SEBRIEF_DATA_DIR": str(tmp_path / "data"), "SEBRIEF_LOG_DIR": str(tmp_path / "logs")}
    values.update(overrides)
    return Settings(_env_file=None, **values)


def make_daemon(tmp_path, *, clock=None, store=None, run_fn=None, settings=None, deliverer=None):
    scheduler = FakeScheduler()
    clock = clock or FakeClock(next_run=NEXT_RUN)
    store = store or FakeStore()
    run_fn = run_fn or RunRecorder()
    deliverer = deliverer or FakeDeliverer("file")
    d = Daemon(
        settings or make_settings(tmp_path),
        scheduler=scheduler,
        clock=clock,
        store=store,
        run_fn=run_fn,
        now_fn=lambda: NOW,
        deliverers_fn=lambda s: [deliverer],
    )
    return d, scheduler, clock, store, run_fn, deliverer


# -------------------------------------------------------------------------------- scheduling
def test_schedule_next_schedules_one_shot_job(tmp_path):
    d, scheduler, *_ = make_daemon(tmp_path)
    assert d.schedule_next() == NEXT_RUN
    job = scheduler.jobs[DIGEST_JOB_ID]
    assert isinstance(job["trigger"], DateTrigger)
    assert job["trigger"].run_date == NEXT_RUN[1]
    assert job["args"] == [NEXT_RUN[0], NEXT_RUN[1]]
    assert job["replace_existing"] is True
    # None: a late (sleep/wake) job must still FIRE so it can reschedule itself
    assert job["misfire_grace_time"] is None


def test_schedule_next_survives_clock_error(tmp_path):
    class BrokenClock(FakeClock):
        def next_run(self, now):
            raise RuntimeError("clock broken")

    d, scheduler, *_ = make_daemon(tmp_path, clock=BrokenClock())
    assert d.schedule_next() is None
    assert DIGEST_JOB_ID not in scheduler.jobs
    d.clock = FakeClock(next_run=NEXT_RUN)
    d._heartbeat_job()  # heartbeat retries scheduling
    assert DIGEST_JOB_ID in scheduler.jobs


def test_start_schedules_digest_and_heartbeat(tmp_path):
    d, scheduler, *_ = make_daemon(tmp_path)
    d.start()
    assert set(scheduler.jobs) == {DIGEST_JOB_ID, HEARTBEAT_JOB_ID}
    hb = scheduler.jobs[HEARTBEAT_JOB_ID]
    assert isinstance(hb["trigger"], IntervalTrigger)
    assert hb["trigger"].interval.total_seconds() == 3600
    assert (d._on_job_missed, EVENT_JOB_MISSED) in scheduler.listeners


# ---------------------------------------------------------------------------------- catch-up
def test_catchup_runs_when_candidate_and_not_yet_digested(tmp_path):
    clock = FakeClock(catchup=WEEK, next_run=NEXT_RUN)
    d, _scheduler, clock, _store, run_fn, _ = make_daemon(tmp_path, clock=clock)
    assert d.run_catchup() is True
    assert run_fn.weeks == [WEEK]
    assert clock.calls[0] == ("catchup_candidate", (NOW, 72))


def test_catchup_skipped_when_digest_exists(tmp_path):
    store = FakeStore()
    store.digests[WEEK] = object()
    d, _s, _c, _st, run_fn, _ = make_daemon(tmp_path, clock=FakeClock(catchup=WEEK), store=store)
    assert d.run_catchup() is False
    assert run_fn.weeks == []


def test_catchup_skipped_without_candidate(tmp_path):
    d, _s, _c, _st, run_fn, _ = make_daemon(tmp_path)
    assert d.run_catchup() is False
    assert run_fn.weeks == []


def test_catchup_failure_is_logged_and_start_continues(tmp_path):
    d, scheduler, _c, _st, run_fn, deliverer = make_daemon(
        tmp_path, clock=FakeClock(catchup=WEEK, next_run=NEXT_RUN), run_fn=RunRecorder(fail=True)
    )
    d.start()  # must not raise
    assert run_fn.weeks == [WEEK]
    assert DIGEST_JOB_ID in scheduler.jobs
    assert deliverer.errors and "catch-up" in deliverer.errors[0][0]


def test_catchup_window_comes_from_settings(tmp_path):
    settings = make_settings(tmp_path, SEBRIEF_CATCHUP_WINDOW_HOURS="24")
    d, _s, clock, *_ = make_daemon(tmp_path, settings=settings)
    d.run_catchup()
    assert clock.calls[0] == ("catchup_candidate", (NOW, 24))


# -------------------------------------------------------------------------------------- job
def test_job_runs_pipeline_and_reschedules(tmp_path):
    d, scheduler, clock, _st, run_fn, deliverer = make_daemon(tmp_path)
    d.schedule_next()
    job = scheduler.jobs[DIGEST_JOB_ID]
    clock._next_run = ("2026-W38", datetime(2026, 9, 21, 7, 0, tzinfo=KST))

    job["func"](*job["args"])

    assert run_fn.weeks == [NEXT_RUN[0]]
    assert scheduler.jobs[DIGEST_JOB_ID]["args"] == ["2026-W38", clock._next_run[1]]
    assert d.next_run == clock._next_run
    assert deliverer.errors == []


def test_job_exception_notifies_and_still_reschedules(tmp_path):
    d, scheduler, _clock, _st, run_fn, deliverer = make_daemon(tmp_path, run_fn=RunRecorder(fail=True))
    d.schedule_next()
    job = scheduler.jobs[DIGEST_JOB_ID]
    job["func"](*job["args"])  # must not raise
    assert run_fn.weeks == [NEXT_RUN[0]]
    assert scheduler.jobs[DIGEST_JOB_ID]["trigger"].run_date == NEXT_RUN[1]
    subject, detail = deliverer.errors[0]
    assert "다이제스트 실패" in subject and "pipeline exploded" in detail


@pytest.mark.parametrize(("lateness_h", "expect_run"), [(0, True), (48, True), (72, False), (100, False)])
def test_late_job_honours_catchup_window(tmp_path, lateness_h, expect_run):
    d, scheduler, _c, _st, run_fn, deliverer = make_daemon(tmp_path)
    run_at = NOW - timedelta(hours=lateness_h)

    d._digest_job(WEEK, run_at)

    assert (run_fn.weeks == [WEEK]) is expect_run
    assert scheduler.jobs[DIGEST_JOB_ID]["trigger"].run_date == NEXT_RUN[1]  # always rescheduled
    assert deliverer.errors == []


# --------------------------------------------------------------------------- heartbeat / missed
def test_heartbeat_recovers_dropped_job_inside_window(tmp_path):
    now = {"t": NOW}
    d, scheduler, clock, _st, run_fn, _ = make_daemon(tmp_path)
    d.now_fn = lambda: now["t"]
    d.schedule_next()
    del scheduler.jobs[DIGEST_JOB_ID]  # what APScheduler does when it drops a misfired job
    now["t"] = NEXT_RUN[1] + timedelta(hours=2)
    clock.catchup = NEXT_RUN[0]

    d._heartbeat_job()

    assert run_fn.weeks == [NEXT_RUN[0]]
    assert DIGEST_JOB_ID in scheduler.jobs


def test_heartbeat_leaves_schedule_alone_when_run_is_imminent(tmp_path):
    now = {"t": NOW}
    d, scheduler, _c, _st, run_fn, _ = make_daemon(tmp_path)
    d.now_fn = lambda: now["t"]
    d.schedule_next()
    for delta in (timedelta(minutes=-30), timedelta(0), timedelta(minutes=2)):
        now["t"] = NEXT_RUN[1] + delta
        d._heartbeat_job()
    assert len(scheduler.add_calls) == 1 and run_fn.weeks == []


def test_heartbeat_does_not_run_while_digest_in_progress(tmp_path):
    now = {"t": NOW}
    d, scheduler, clock, _st, run_fn, _ = make_daemon(tmp_path)
    d.now_fn = lambda: now["t"]
    d.schedule_next()
    now["t"] = NEXT_RUN[1] + timedelta(hours=1)
    clock.catchup = NEXT_RUN[0]
    with d._run_lock:  # a digest is running on another executor thread
        d._heartbeat_job()
    assert run_fn.weeks == []  # no concurrent second run
    assert DIGEST_JOB_ID in scheduler.jobs  # but re-armed


def test_on_job_missed_queues_recovery_under_a_different_id(tmp_path):
    d, scheduler, clock, _st, run_fn, _ = make_daemon(tmp_path)
    d.start()
    del scheduler.jobs[DIGEST_JOB_ID]
    clock.catchup = NEXT_RUN[0]

    d._on_job_missed(JobExecutionEvent(EVENT_JOB_MISSED, DIGEST_JOB_ID, "default", NEXT_RUN[1]))

    assert scheduler.add_calls[-1]["id"] == RECOVERY_JOB_ID
    recovery = scheduler.jobs[RECOVERY_JOB_ID]
    assert isinstance(recovery["trigger"], DateTrigger) and recovery["misfire_grace_time"] is None
    recovery["func"]()
    assert run_fn.weeks == [NEXT_RUN[0]]
    assert DIGEST_JOB_ID in scheduler.jobs

    n_calls = len(scheduler.add_calls)
    d._on_job_missed(JobExecutionEvent(EVENT_JOB_MISSED, HEARTBEAT_JOB_ID, "default", NEXT_RUN[1]))
    assert len(scheduler.add_calls) == n_calls  # other jobs are ignored


# --------------------------------------------------------------------------------- shutdown
def test_signal_handler_shuts_scheduler_down(tmp_path):
    d, scheduler, *_ = make_daemon(tmp_path)
    old_term, old_int = signal.getsignal(signal.SIGTERM), signal.getsignal(signal.SIGINT)
    try:
        d.install_signal_handlers()
        handler = signal.getsignal(signal.SIGTERM)
        assert callable(handler) and handler is not old_term
        handler(signal.SIGTERM, None)
    finally:
        signal.signal(signal.SIGTERM, old_term)
        signal.signal(signal.SIGINT, old_int)
    assert scheduler.shutdown_calls == [False]


def test_signal_during_catchup_unwinds_when_scheduler_not_running(tmp_path):
    class NotStarted(FakeScheduler):
        def shutdown(self, wait=True):
            super().shutdown(wait)
            raise SchedulerNotRunningError

    d, *_ = make_daemon(tmp_path)
    d.scheduler = NotStarted()
    old_term, old_int = signal.getsignal(signal.SIGTERM), signal.getsignal(signal.SIGINT)
    try:
        d.install_signal_handlers()
        handler = signal.getsignal(signal.SIGTERM)
        with pytest.raises(KeyboardInterrupt):
            handler(signal.SIGTERM, None)
    finally:
        signal.signal(signal.SIGTERM, old_term)
        signal.signal(signal.SIGINT, old_int)
    assert d.stop_requested is True


def test_shutdown_during_catchup_prevents_scheduling(tmp_path):
    class NotStarted(FakeScheduler):
        def shutdown(self, wait=True):
            super().shutdown(wait)
            raise SchedulerNotRunningError

    holder: dict = {}

    def run_fn(week):
        holder["d"].shutdown()

    d, *_ = make_daemon(tmp_path, clock=FakeClock(catchup=WEEK, next_run=NEXT_RUN), run_fn=run_fn)
    d.scheduler = NotStarted()
    holder["d"] = d
    d.start()
    assert d.stop_requested is True
    assert d.scheduler.jobs == {}  # nothing scheduled; run_daemon skips scheduler.start()


# ------------------------------------------------------------------------------- run_daemon
def test_run_daemon_wires_real_parts_and_blocks_on_scheduler(monkeypatch, tmp_path):
    started = {}
    fake_store = FakeStore()

    class FakeBlocking(FakeScheduler):
        def __init__(self, timezone=None):
            super().__init__()
            started["timezone"] = timezone

        def start(self, paused=False):
            started["started"] = True
            raise KeyboardInterrupt  # simulate Ctrl-C ending the blocking loop

    monkeypatch.setattr(daemon_mod, "BlockingScheduler", FakeBlocking)
    monkeypatch.setattr(daemon_mod, "WeeklyClock", lambda wd, t: FakeClock(next_run=NEXT_RUN))
    monkeypatch.setattr(daemon_mod, "Store", lambda path: fake_store)
    monkeypatch.setattr(daemon_mod.signal, "signal", lambda *a, **k: None)

    daemon_mod.run_daemon(make_settings(tmp_path))

    assert started["started"] is True
    assert str(started["timezone"]) == "Asia/Seoul"
    assert fake_store.closed is True


def test_run_lock_serialises_catchup_and_job(tmp_path):
    seen = {}
    d, *_ = make_daemon(tmp_path)

    def run_fn(week):
        seen["locked"] = d._run_lock.locked()

    d.run_fn = run_fn
    d._digest_job(WEEK, NOW)
    assert seen["locked"] is True


def test_notify_error_failures_are_swallowed(tmp_path):
    class Exploding(FakeDeliverer):
        def notify_error(self, subject, detail):
            raise RuntimeError("channel down")

    d, *_ = make_daemon(tmp_path, run_fn=RunRecorder(fail=True), deliverer=Exploding("x"))
    d._digest_job(WEEK)  # must not raise

    d.deliverers_fn = lambda s: (_ for _ in ()).throw(RuntimeError("cannot build"))
    d._digest_job(WEEK)  # must not raise either