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.
88 lines
3.2 KiB
Python
88 lines
3.2 KiB
Python
"""Regression tests: failed-connect path must call adapter.disconnect().
|
|
|
|
When adapter.connect() returns False or raises, the adapter may have
|
|
allocated resources (aiohttp.ClientSession, poll tasks, child
|
|
subprocesses) before giving up. Without a defensive disconnect() call
|
|
these leak and surface as "Unclosed client session" warnings at
|
|
process exit (seen on the 2026-04-18 18:08:16 gateway restart).
|
|
|
|
The fix: gateway/run.py wraps each adapter connect() with a safety-net
|
|
call to _safe_adapter_disconnect() in the failure branches.
|
|
"""
|
|
|
|
import asyncio
|
|
import logging
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from gateway.config import Platform
|
|
from gateway.run import GatewayRunner
|
|
|
|
|
|
@pytest.fixture
|
|
def bare_runner():
|
|
"""A GatewayRunner shell that only needs to support _safe_adapter_disconnect."""
|
|
return object.__new__(GatewayRunner)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_safe_disconnect_times_out_and_continues(bare_runner, monkeypatch, caplog):
|
|
"""A wedged adapter disconnect must not block gateway shutdown."""
|
|
monkeypatch.setenv("HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT", "0.001")
|
|
adapter = MagicMock()
|
|
|
|
async def hang():
|
|
await asyncio.sleep(0.2)
|
|
|
|
adapter.disconnect = AsyncMock(side_effect=hang)
|
|
|
|
with caplog.at_level(logging.WARNING, logger="gateway.run"):
|
|
await bare_runner._safe_adapter_disconnect(adapter, Platform.FEISHU)
|
|
|
|
adapter.disconnect.assert_awaited_once()
|
|
assert "Timed out after 0.0s while disconnecting feishu adapter" in caplog.text
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_safe_disconnect_detaches_cancellation_swallowing_disconnect(
|
|
bare_runner, monkeypatch, caplog
|
|
):
|
|
"""A disconnect that catches cancellation cannot block fatal recovery.
|
|
|
|
``asyncio.wait_for`` cancels its child at the deadline but then waits for
|
|
it to finish. A half-closed transport can catch that cancellation while
|
|
unwinding, so the runner must detach the old close task and continue to the
|
|
reconnect queue instead of waiting indefinitely.
|
|
"""
|
|
monkeypatch.setenv("HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT", "0.01")
|
|
adapter = MagicMock()
|
|
started = asyncio.Event()
|
|
release = asyncio.Event()
|
|
finished = asyncio.Event()
|
|
|
|
async def swallow_cancellation():
|
|
started.set()
|
|
while not release.is_set():
|
|
try:
|
|
await release.wait()
|
|
except asyncio.CancelledError:
|
|
continue
|
|
finished.set()
|
|
|
|
adapter.disconnect = AsyncMock(side_effect=swallow_cancellation)
|
|
operation = asyncio.create_task(
|
|
bare_runner._safe_adapter_disconnect(adapter, Platform.FEISHU)
|
|
)
|
|
await started.wait()
|
|
done, _pending = await asyncio.wait({operation}, timeout=0.2)
|
|
try:
|
|
assert operation in done
|
|
assert "Timed out after 0.0s while disconnecting feishu adapter" in caplog.text
|
|
finally:
|
|
# The implementation must detach rather than abandon the old task.
|
|
# Release it here so this test leaves no cancellation-swallowing task
|
|
# behind when it runs against the pre-fix implementation.
|
|
release.set()
|
|
await asyncio.wait({operation}, timeout=0.2)
|
|
await asyncio.wait_for(finished.wait(), timeout=0.2)
|