mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
85 lines
3.5 KiB
Python
85 lines
3.5 KiB
Python
"""Regression tests for browser session cleanup and screenshot recovery."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
class TestScreenshotPathRecovery:
|
|
def test_extracts_standard_absolute_path(self):
|
|
from tools.browser_tool import _extract_screenshot_path_from_text
|
|
|
|
assert (
|
|
_extract_screenshot_path_from_text("Screenshot saved to /tmp/foo.png")
|
|
== "/tmp/foo.png"
|
|
)
|
|
|
|
def test_extracts_quoted_absolute_path(self):
|
|
from tools.browser_tool import _extract_screenshot_path_from_text
|
|
|
|
assert (
|
|
_extract_screenshot_path_from_text(
|
|
"Screenshot saved to '/Users/david/.hermes/browser_screenshots/shot.png'"
|
|
)
|
|
== "/Users/david/.hermes/browser_screenshots/shot.png"
|
|
)
|
|
|
|
|
|
class TestBrowserCleanup:
|
|
def setup_method(self):
|
|
from tools import browser_tool
|
|
|
|
self.browser_tool = browser_tool
|
|
self.orig_active_sessions = browser_tool._active_sessions.copy()
|
|
self.orig_session_last_activity = browser_tool._session_last_activity.copy()
|
|
self.orig_recording_sessions = browser_tool._recording_sessions.copy()
|
|
self.orig_cleanup_done = browser_tool._cleanup_done
|
|
|
|
def teardown_method(self):
|
|
self.browser_tool._active_sessions.clear()
|
|
self.browser_tool._active_sessions.update(self.orig_active_sessions)
|
|
self.browser_tool._session_last_activity.clear()
|
|
self.browser_tool._session_last_activity.update(self.orig_session_last_activity)
|
|
self.browser_tool._recording_sessions.clear()
|
|
self.browser_tool._recording_sessions.update(self.orig_recording_sessions)
|
|
self.browser_tool._cleanup_done = self.orig_cleanup_done
|
|
|
|
def test_cleanup_browser_clears_tracking_state(self):
|
|
browser_tool = self.browser_tool
|
|
browser_tool._active_sessions["task-1"] = {
|
|
"session_name": "sess-1",
|
|
"bb_session_id": None,
|
|
}
|
|
browser_tool._session_last_activity["task-1"] = 123.0
|
|
|
|
with (
|
|
patch("tools.browser_tool._maybe_stop_recording") as mock_stop,
|
|
patch(
|
|
"tools.browser_tool._run_browser_command",
|
|
return_value={"success": True},
|
|
) as mock_run,
|
|
patch("tools.browser_tool.os.path.exists", return_value=False),
|
|
):
|
|
browser_tool.cleanup_browser("task-1")
|
|
|
|
assert "task-1" not in browser_tool._active_sessions
|
|
assert "task-1" not in browser_tool._session_last_activity
|
|
mock_stop.assert_called_once_with("task-1")
|
|
mock_run.assert_called_once_with("task-1", "close", [], timeout=10)
|
|
|
|
|
|
def test_emergency_cleanup_clears_all_tracking_state(self):
|
|
browser_tool = self.browser_tool
|
|
browser_tool._cleanup_done = False
|
|
browser_tool._active_sessions["task-1"] = {"session_name": "sess-1"}
|
|
browser_tool._active_sessions["task-2"] = {"session_name": "sess-2"}
|
|
browser_tool._session_last_activity["task-1"] = 1.0
|
|
browser_tool._session_last_activity["task-2"] = 2.0
|
|
browser_tool._recording_sessions.update({"task-1", "task-2"})
|
|
|
|
with patch("tools.browser_tool.cleanup_all_browsers") as mock_cleanup_all:
|
|
browser_tool._emergency_cleanup_all_sessions()
|
|
|
|
mock_cleanup_all.assert_called_once_with()
|
|
assert browser_tool._active_sessions == {}
|
|
assert browser_tool._session_last_activity == {}
|
|
assert browser_tool._recording_sessions == set()
|
|
assert browser_tool._cleanup_done is True
|