hermes-agent/tests/gateway/test_gateway_inactivity_timeout.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

172 lines
5.7 KiB
Python

"""Tests for staged inactivity timeout in gateway agent runs.
Tests cover:
- Warning fires once when inactivity reaches gateway_timeout_warning threshold
- Warning does not fire when gateway_timeout is 0 (unlimited)
- Warning fires only once per run, not on every poll
- Full timeout still fires at gateway_timeout threshold
- Warning respects HERMES_AGENT_TIMEOUT_WARNING env var
- Warning disabled when gateway_timeout_warning is 0
"""
import concurrent.futures
import os
import sys
import time
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
class FakeAgent:
"""Mock agent with controllable activity summary for timeout tests."""
def __init__(self, idle_seconds=0.0, activity_desc="tool_call",
current_tool=None, api_call_count=5, max_iterations=90):
self._idle_seconds = idle_seconds
self._activity_desc = activity_desc
self._current_tool = current_tool
self._api_call_count = api_call_count
self._max_iterations = max_iterations
self._interrupted = False
self._interrupt_msg = None
def get_activity_summary(self):
return {
"last_activity_ts": time.time() - self._idle_seconds,
"last_activity_desc": self._activity_desc,
"seconds_since_activity": self._idle_seconds,
"current_tool": self._current_tool,
"api_call_count": self._api_call_count,
"max_iterations": self._max_iterations,
}
def interrupt(self, msg):
self._interrupted = True
self._interrupt_msg = msg
def run_conversation(self, prompt):
return {"final_response": "Done", "messages": []}
class SlowFakeAgent(FakeAgent):
"""Agent that runs for a while, then goes idle."""
def __init__(self, run_duration=0.5, idle_after=None, **kwargs):
super().__init__(**kwargs)
self._run_duration = run_duration
self._idle_after = idle_after
self._start_time = None
def get_activity_summary(self):
summary = super().get_activity_summary()
if self._idle_after is not None and self._start_time:
elapsed = time.time() - self._start_time
if elapsed > self._idle_after:
idle_time = elapsed - self._idle_after
summary["seconds_since_activity"] = idle_time
summary["last_activity_desc"] = "api_call_streaming"
else:
summary["seconds_since_activity"] = 0.0
return summary
def run_conversation(self, prompt):
self._start_time = time.time()
time.sleep(self._run_duration)
return {"final_response": "Completed after work", "messages": []}
class TestStagedInactivityWarning:
"""Test the staged inactivity warning before full timeout."""
def test_warning_fires_once_before_timeout(self):
"""Warning fires when inactivity reaches warning threshold."""
agent = SlowFakeAgent(
run_duration=0.6,
idle_after=0.05,
activity_desc="api_call_streaming",
)
_agent_timeout = 20.0
_agent_warning = 0.15
_POLL_INTERVAL = 0.05
pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
future = pool.submit(agent.run_conversation, "test prompt")
_inactivity_timeout = False
_warning_fired = False
_warning_send_count = 0
while True:
done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
if done:
result = future.result()
break
_idle_secs = 0.0
if hasattr(agent, "get_activity_summary"):
try:
_act = agent.get_activity_summary()
_idle_secs = _act.get("seconds_since_activity", 0.0)
except Exception:
pass
if (not _warning_fired and _agent_warning > 0
and _idle_secs >= _agent_warning):
_warning_fired = True
_warning_send_count += 1
if _idle_secs >= _agent_timeout:
_inactivity_timeout = True
break
pool.shutdown(wait=False, cancel_futures=True)
assert _warning_fired
assert _warning_send_count == 1
assert not _inactivity_timeout
def test_full_timeout_still_fires_after_warning(self):
"""Full timeout fires even after warning was sent."""
agent = SlowFakeAgent(
run_duration=5.0,
idle_after=0.05,
activity_desc="waiting for provider response (streaming)",
)
_agent_timeout = 0.4
_agent_warning = 0.15
_POLL_INTERVAL = 0.05
pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
future = pool.submit(agent.run_conversation, "test")
_inactivity_timeout = False
_warning_fired = False
while True:
done, _ = concurrent.futures.wait({future}, timeout=_POLL_INTERVAL)
if done:
future.result()
break
_idle_secs = 0.0
if hasattr(agent, "get_activity_summary"):
try:
_act = agent.get_activity_summary()
_idle_secs = _act.get("seconds_since_activity", 0.0)
except Exception:
pass
if (not _warning_fired and _agent_warning > 0
and _idle_secs >= _agent_warning):
_warning_fired = True
if _idle_secs >= _agent_timeout:
_inactivity_timeout = True
break
pool.shutdown(wait=False, cancel_futures=True)
assert _warning_fired
assert _inactivity_timeout