mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
55 lines
2.7 KiB
Python
55 lines
2.7 KiB
Python
"""Tests for cronjob action='run' immediate execution (#41037).
|
|
|
|
Before this fix, `cronjob(action='run')` only set next_run_at=now and returned
|
|
success, relying on the scheduler ticker to actually run the job. With no
|
|
gateway/ticker active (e.g. a CLI-only Windows setup) the job never executed and
|
|
last_run_at stayed null forever. Now action='run' claims the job (at-most-once,
|
|
blocking a concurrent tick) and fires it inline via the shared run_one_job body.
|
|
"""
|
|
import json
|
|
from unittest.mock import patch
|
|
|
|
from tools.cronjob_tools import cronjob, _execute_job_now
|
|
|
|
|
|
_JOB = {"id": "job-run-1", "name": "manual run", "prompt": "hi",
|
|
"schedule": {"kind": "cron", "expr": "0 9 * * *"}}
|
|
|
|
|
|
class TestCronjobRunExecutesImmediately:
|
|
def test_run_action_claims_and_fires_via_run_one_job(self):
|
|
"""action='run' must claim the job then fire it through run_one_job."""
|
|
ran = {"job": "after-run", "last_status": "ok", "last_error": None}
|
|
with patch("tools.cronjob_tools.resolve_job_ref", return_value=dict(_JOB)), \
|
|
patch("tools.cronjob_tools.claim_job_for_fire", return_value=True) as m_claim, \
|
|
patch("cron.scheduler.run_one_job", return_value=True) as m_run, \
|
|
patch("tools.cronjob_tools.get_job", return_value=ran):
|
|
out = json.loads(cronjob(action="run", job_id="job-run-1"))
|
|
|
|
assert out["success"] is True
|
|
assert out["job"]["executed"] is True
|
|
assert out["job"]["execution_success"] is True
|
|
m_claim.assert_called_once_with("job-run-1") # at-most-once claim taken
|
|
m_run.assert_called_once() # fired via the shared body
|
|
|
|
|
|
def test_execute_job_now_bails_without_claim(self):
|
|
"""_execute_job_now never calls run_one_job when the claim is lost."""
|
|
with patch("tools.cronjob_tools.claim_job_for_fire", return_value=False), \
|
|
patch("cron.scheduler.run_one_job") as m_run:
|
|
res = _execute_job_now(dict(_JOB))
|
|
assert res["claimed"] is False
|
|
assert res["success"] is False
|
|
m_run.assert_not_called()
|
|
|
|
def test_execute_job_now_marks_failure_on_exception(self):
|
|
"""An exception during fire is captured, marked failed, not propagated."""
|
|
with patch("tools.cronjob_tools.claim_job_for_fire", return_value=True), \
|
|
patch("cron.scheduler.run_one_job", side_effect=RuntimeError("boom")), \
|
|
patch("tools.cronjob_tools.mark_job_run") as m_mark, \
|
|
patch("tools.cronjob_tools.get_job", return_value=dict(_JOB)):
|
|
res = _execute_job_now(dict(_JOB))
|
|
assert res["claimed"] is True
|
|
assert res["success"] is False
|
|
assert "boom" in res["error"]
|
|
m_mark.assert_called_once()
|