Files
library-desk/tests/test_job_plumbing.py
T
jpmschweitzerandClaude Fable 5 0b346d3a57 feat: add job cleanup loop, Scheduler task definitions, and registrar
- job_cleanup_loop (src/jobs/job_manager.py): hourly in-process pass over
  JobManager.cleanup_expired_jobs, started at app startup and cancelled
  at shutdown; Redis job payloads auto-expire but set memberships do not.
- docs/scheduler-tasks.md: the four production Scheduler task payloads
  for the deploy checklist - nightly integrity check 04:30, weekly
  quality report Sunday 03:00 (day_of_week=6, 0=Monday), daily Paperless
  orphan-cleanup 05:00 hitting the existing
  /maintenance/cleanup/paperless?user=jpmschweitzer&dry_run=false
  endpoint, and disabling test_example_task - with exact HTTP bodies
  (explicit user=jpmschweitzer, Authorization: Bearer ${LIBRARY_API_KEY}
  placeholder).
- scripts/register_scheduler_tasks.py: reads SCHEDULER_URL from env,
  DRY-RUN BY DEFAULT (prints the exact payloads, provably contacts
  nothing), --execute gated and requiring LIBRARY_API_KEY to fill the
  placeholder. NOT executed - definitions delivered for the deploy
  checklist only.

9 new offline tests (loop passes/error-resilience/cancellation, payload
schedules, explicit production user, placeholder, dry-run default).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L
2026-07-14 12:30:27 +02:00

122 lines
4.6 KiB
Python

"""
Offline unit tests for job + Scheduler task plumbing (Phase C item 5).
Covers:
- job_cleanup_loop: invokes cleanup_expired_jobs per pass, survives
transient errors, honors cancellation
- register_scheduler_tasks.py: dry-run default, payload contents
(explicit production user, auth placeholder, schedules)
"""
import asyncio
from unittest.mock import AsyncMock
import pytest
from src.jobs.job_manager import job_cleanup_loop
class TestJobCleanupLoop:
@pytest.mark.asyncio
async def test_invokes_cleanup_each_pass(self):
manager = AsyncMock()
passes = await job_cleanup_loop(manager, interval_seconds=0, max_iterations=3)
assert passes == 3
assert manager.cleanup_expired_jobs.await_count == 3
@pytest.mark.asyncio
async def test_transient_error_does_not_kill_loop(self):
manager = AsyncMock()
manager.cleanup_expired_jobs = AsyncMock(
side_effect=[RuntimeError("redis hiccup"), None]
)
passes = await job_cleanup_loop(manager, interval_seconds=0, max_iterations=2)
assert passes == 2
assert manager.cleanup_expired_jobs.await_count == 2
@pytest.mark.asyncio
async def test_cancellation_stops_loop(self):
manager = AsyncMock()
task = asyncio.create_task(job_cleanup_loop(manager, interval_seconds=60))
await asyncio.sleep(0) # let it start sleeping
task.cancel()
with pytest.raises(asyncio.CancelledError):
await task
class TestSchedulerTaskDefinitions:
def _load_module(self):
import importlib
return importlib.import_module("scripts.register_scheduler_tasks")
def test_four_production_payloads_defined(self):
mod = self._load_module()
names = {t["task_name"] for t in mod.TASKS}
assert names == {
"library_integrity_check",
"library_quality_report",
"library_paperless_orphan_cleanup",
}
updates = {u["task_name"]: u["updates"] for u in mod.TASK_UPDATES}
assert updates == {"test_example_task": {"enabled": False}}
def test_schedules(self):
mod = self._load_module()
by_name = {t["task_name"]: t for t in mod.TASKS}
integrity = by_name["library_integrity_check"]
assert (integrity["hour"], integrity["minute"], integrity["day_of_week"]) == (4, 30, -1)
quality = by_name["library_quality_report"]
# Sunday 03:00 (Scheduler: 0 = Monday .. 6 = Sunday)
assert (quality["hour"], quality["minute"], quality["day_of_week"]) == (3, 0, 6)
paperless = by_name["library_paperless_orphan_cleanup"]
assert (paperless["hour"], paperless["minute"], paperless["day_of_week"]) == (5, 0, -1)
def test_payloads_use_explicit_production_user_and_placeholder(self):
mod = self._load_module()
for task in mod.TASKS:
config = task["config"]
auth = config["headers"]["Authorization"]
assert auth == f"Bearer {mod.API_KEY_PLACEHOLDER}"
# Explicit production tenant in body or query string (Phase B)
body_user = config.get("body", {}).get("user")
assert body_user == "jpmschweitzer" or "user=jpmschweitzer" in config["url"]
def test_paperless_task_hits_existing_endpoint(self):
mod = self._load_module()
task = next(t for t in mod.TASKS
if t["task_name"] == "library_paperless_orphan_cleanup")
assert "/maintenance/cleanup/paperless" in task["config"]["url"]
assert "dry_run=false" in task["config"]["url"]
def test_substitute_api_key_replaces_placeholder_without_mutating(self):
mod = self._load_module()
original = mod.TASKS[0]
resolved = mod.substitute_api_key(original, "sekret")
assert resolved["config"]["headers"]["Authorization"] == "Bearer sekret"
# The module-level definition keeps the placeholder
assert mod.API_KEY_PLACEHOLDER in original["config"]["headers"]["Authorization"]
def test_dry_run_is_default_and_sends_nothing(self, capsys, monkeypatch):
mod = self._load_module()
monkeypatch.setattr("sys.argv", ["register_scheduler_tasks.py"])
monkeypatch.setenv("SCHEDULER_URL", "http://scheduler.test:8090")
def _boom(*args, **kwargs): # any HTTP client construction = failure
raise AssertionError("dry-run must not contact the Scheduler")
monkeypatch.setattr(mod.httpx, "Client", _boom)
assert mod.main() == 0
out = capsys.readouterr().out
assert "DRY RUN" in out
assert "library_integrity_check" in out
assert mod.API_KEY_PLACEHOLDER in out # placeholder, never a real key