hermes-agent/tests/cron/test_parallel_pool.py
Teknium 6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):

- DELETE: source-reading tests (read_text/getsource on prod files),
  change-detector tests (exact catalog counts, model-name snapshots,
  config version literals), mock-echo tests (assert a mock returns what
  it was told), assertion-free/trivial tests, near-duplicate
  parametrizations (boundaries + one representative kept), async/sync
  twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
  alternation invariants, prompt-caching/deterministic-call-id
  invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
  redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
  models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
  tests performed on every session create — test_server.py 147s → 3.4s,
  and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
  compression_concurrent_fork, etc.); no wall-clock assertion tightened.

Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
2026-07-29 13:10:23 -07:00

182 lines
6.3 KiB
Python

"""Tests for the persistent parallel pool and running-job guard in cron/scheduler.py.
These verify the fix for the tick-blocking issue where as_completed(timeout=600)
prevented the ticker thread from firing, causing all other jobs to be fast-forwarded.
"""
import concurrent.futures
import threading
import time
from unittest.mock import patch
import pytest
class TestPersistentPool:
"""_get_parallel_pool returns a persistent ThreadPoolExecutor."""
def test_pool_is_reused(self, monkeypatch):
"""Same pool instance returned when max_workers doesn't change."""
import cron.scheduler as sched
# Reset module state.
sched._parallel_pool = None
sched._parallel_pool_max_workers = None
pool1 = sched._get_parallel_pool(4)
pool2 = sched._get_parallel_pool(4)
assert pool1 is pool2
# Cleanup.
sched._shutdown_parallel_pool()
def test_shutdown_clears_pool(self, monkeypatch):
"""_shutdown_parallel_pool resets state."""
import cron.scheduler as sched
sched._parallel_pool = None
sched._parallel_pool_max_workers = None
sched._get_parallel_pool(2)
sched._shutdown_parallel_pool()
assert sched._parallel_pool is None
assert sched._parallel_pool_max_workers is None
class TestRunningJobGuard:
"""_running_job_ids prevents double-dispatch of active jobs."""
def test_running_set_prevents_double_dispatch(self, tmp_path, monkeypatch):
"""A job already in _running_job_ids is skipped on the next tick."""
import cron.scheduler as sched
# Reset state.
sched._parallel_pool = None
sched._parallel_pool_max_workers = None
sched._running_job_ids.clear()
job = {
"id": "guard-job",
"name": "guard-test",
"prompt": "test",
"schedule": "every 5m",
"enabled": True,
"next_run_at": "2020-01-01T00:00:00",
"deliver": "local",
}
# Simulate the job already running.
sched._running_job_ids.add("guard-job")
dispatched = []
monkeypatch.setattr(sched, "get_due_jobs", lambda: [job])
monkeypatch.setattr(sched, "advance_next_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "run_job", lambda j, **_kw: dispatched.append(j["id"]) or (True, "out", "resp", None))
monkeypatch.setattr(sched, "save_job_output", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "mark_job_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "_deliver_result", lambda *_a, **_kw: None)
n = sched.tick(verbose=False)
assert n == 0 # skipped, not dispatched
assert dispatched == []
sched._running_job_ids.discard("guard-job")
sched._shutdown_parallel_pool()
class TestSyncMode:
"""tick() blocks by default (sync=True); tick(sync=False) returns immediately."""
def test_sync_true_blocks_and_returns_correct_count(self, tmp_path, monkeypatch):
"""sync=True waits for jobs and returns actual results."""
import cron.scheduler as sched
sched._parallel_pool = None
sched._parallel_pool_max_workers = None
sched._running_job_ids.clear()
jobs = [
{"id": f"job-{i}", "name": f"Job {i}", "prompt": "test",
"schedule": "every 5m", "enabled": True,
"next_run_at": "2020-01-01T00:00:00", "deliver": "local"}
for i in range(3)
]
monkeypatch.setattr(sched, "get_due_jobs", lambda: jobs)
monkeypatch.setattr(sched, "advance_next_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "run_job", lambda j, **_kw: (True, "out", "resp", None))
monkeypatch.setattr(sched, "save_job_output", lambda *_a, **_kw: "/tmp/out")
monkeypatch.setattr(sched, "mark_job_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "_deliver_result", lambda *_a, **_kw: None)
n = sched.tick(verbose=False)
assert n == 3
sched._shutdown_parallel_pool()
class TestSequentialPool:
"""Sequential (workdir) jobs use the persistent cron-seq pool.
Verifies the follow-up fix: env-mutating jobs no longer run inline
in the ticker thread, so a long workdir job can't starve the
schedule the same way the parallel path used to.
"""
def test_sequential_job_does_not_block_ticker(self, tmp_path, monkeypatch):
"""sync=False returns immediately even when a workdir job is slow."""
import cron.scheduler as sched
sched._parallel_pool = None
sched._parallel_pool_max_workers = None
sched._sequential_pool = None
sched._running_job_ids.clear()
job = {
"id": "slow-workdir",
"name": "slow-workdir",
"prompt": "test",
"schedule": "every 5m",
"enabled": True,
"next_run_at": "2020-01-01T00:00:00",
"deliver": "local",
"workdir": str(tmp_path), # makes it sequential
}
barrier = threading.Barrier(2, timeout=5)
def slow_run(j, *, defer_agent_teardown=None):
barrier.wait()
return True, "out", "resp", None
monkeypatch.setattr(sched, "get_due_jobs", lambda: [job])
monkeypatch.setattr(sched, "advance_next_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "run_job", slow_run)
monkeypatch.setattr(sched, "save_job_output", lambda *_a, **_kw: "/tmp/out")
monkeypatch.setattr(sched, "mark_job_run", lambda *_a, **_kw: None)
monkeypatch.setattr(sched, "_deliver_result", lambda *_a, **_kw: None)
start = time.monotonic()
n = sched.tick(verbose=False, sync=False)
elapsed = time.monotonic() - start
assert n == 1 # optimistic count
assert elapsed < 1.0 # did NOT block on the slow workdir job
barrier.wait()
time.sleep(0.1)
sched._shutdown_parallel_pool()
def test_get_sequential_pool_is_persistent(self):
"""_get_sequential_pool returns the same single-thread pool."""
import cron.scheduler as sched
sched._sequential_pool = None
pool1 = sched._get_sequential_pool()
pool2 = sched._get_sequential_pool()
assert pool1 is pool2
sched._shutdown_parallel_pool()
assert sched._sequential_pool is None