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.
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
"""Tests for stuck-session loop detection (#7536).
|
|
|
|
When a session is active across 3+ consecutive gateway restarts (the agent
|
|
gets stuck, gateway restarts, same session gets stuck again), the session
|
|
is auto-suspended on startup so the user gets a clean slate.
|
|
"""
|
|
|
|
import json
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
from tests.gateway.restart_test_helpers import make_restart_runner
|
|
|
|
|
|
@pytest.fixture
|
|
def runner_with_home(tmp_path, monkeypatch):
|
|
"""Create a runner with a writable HERMES_HOME."""
|
|
monkeypatch.setattr("gateway.run._hermes_home", tmp_path)
|
|
runner, adapter = make_restart_runner()
|
|
return runner, tmp_path
|
|
|
|
|
|
class TestStuckLoopDetection:
|
|
|
|
def test_increment_creates_file(self, runner_with_home):
|
|
runner, home = runner_with_home
|
|
runner._increment_restart_failure_counts({"session:a", "session:b"})
|
|
path = home / runner._STUCK_LOOP_FILE
|
|
assert path.exists()
|
|
counts = json.loads(path.read_text())
|
|
assert counts["session:a"] == 1
|
|
assert counts["session:b"] == 1
|
|
|
|
|
|
def test_suspend_at_threshold(self, runner_with_home):
|
|
runner, home = runner_with_home
|
|
# Simulate 3 restarts with session:a active each time
|
|
for _ in range(3):
|
|
runner._increment_restart_failure_counts({"session:a"})
|
|
|
|
# Create a mock session entry
|
|
mock_entry = MagicMock()
|
|
mock_entry.suspended = False
|
|
runner.session_store._entries = {"session:a": mock_entry}
|
|
runner.session_store._save = MagicMock()
|
|
|
|
suspended = runner._suspend_stuck_loop_sessions()
|
|
assert suspended == 1
|
|
assert mock_entry.suspended is True
|
|
|
|
def test_no_suspend_below_threshold(self, runner_with_home):
|
|
runner, home = runner_with_home
|
|
runner._increment_restart_failure_counts({"session:a"})
|
|
runner._increment_restart_failure_counts({"session:a"})
|
|
# Only 2 restarts — below threshold of 3
|
|
|
|
mock_entry = MagicMock()
|
|
mock_entry.suspended = False
|
|
runner.session_store._entries = {"session:a": mock_entry}
|
|
|
|
suspended = runner._suspend_stuck_loop_sessions()
|
|
assert suspended == 0
|
|
assert mock_entry.suspended is False
|
|
|
|
|