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.
141 lines
4.2 KiB
Python
141 lines
4.2 KiB
Python
"""Tests for the gateway loop-level transient-network-error safety net.
|
|
|
|
Issues #31066 / #31110: unhandled ``telegram.error.TimedOut`` (or peer
|
|
``NetworkError`` / ``httpx`` connection error) propagating to the
|
|
asyncio event loop killed the gateway process, taking down every
|
|
profile attached to the same runner. The safety net installed in
|
|
:func:`gateway.run.start_gateway` catches the transient crash class
|
|
and logs+swallows it; non-transient errors still surface.
|
|
|
|
These tests pin the classifier and the loop handler so the safety net
|
|
can't silently regress to swallowing every exception.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
|
|
import pytest
|
|
|
|
from gateway.run import (
|
|
_gateway_loop_exception_handler,
|
|
_is_transient_network_error,
|
|
)
|
|
|
|
|
|
# ----- Fake exception classes that mimic the real wire types ----------
|
|
# We avoid importing telegram / httpx here so the test runs in environments
|
|
# without those packages installed (the classifier matches on class name).
|
|
|
|
class TimedOut(Exception):
|
|
"""Stand-in for ``telegram.error.TimedOut``."""
|
|
|
|
|
|
class NetworkError(Exception):
|
|
"""Stand-in for ``telegram.error.NetworkError``."""
|
|
|
|
|
|
class ConnectError(Exception):
|
|
"""Stand-in for ``httpx.ConnectError``."""
|
|
|
|
|
|
class ReadTimeout(Exception):
|
|
"""Stand-in for ``httpx.ReadTimeout``."""
|
|
|
|
|
|
class PoolTimeout(Exception):
|
|
"""Stand-in for ``httpx.PoolTimeout``."""
|
|
|
|
|
|
class ClientConnectorError(Exception):
|
|
"""Stand-in for ``aiohttp.ClientConnectorError``."""
|
|
|
|
|
|
class SomeUnrelatedBug(Exception):
|
|
"""A non-transient error that should NOT be swallowed."""
|
|
|
|
|
|
# ---------------------------------------------------------------------
|
|
# Classifier
|
|
# ---------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"exc_cls",
|
|
[
|
|
TimedOut,
|
|
NetworkError,
|
|
ConnectError,
|
|
ReadTimeout,
|
|
PoolTimeout,
|
|
ClientConnectorError,
|
|
],
|
|
)
|
|
def test_transient_classifier_matches_known_network_errors(exc_cls):
|
|
"""Every well-known transient network exception class is classified."""
|
|
assert _is_transient_network_error(exc_cls("boom")) is True
|
|
|
|
|
|
# ---------------------------------------------------------------------
|
|
# Loop handler
|
|
# ---------------------------------------------------------------------
|
|
|
|
|
|
def test_handler_delegates_unknown_errors_to_default(monkeypatch):
|
|
"""A non-transient error is forwarded to ``loop.default_exception_handler``."""
|
|
loop = asyncio.new_event_loop()
|
|
try:
|
|
forwarded: list[dict] = []
|
|
|
|
def fake_default(ctx):
|
|
forwarded.append(ctx)
|
|
|
|
monkeypatch.setattr(loop, "default_exception_handler", fake_default)
|
|
|
|
context = {
|
|
"message": "Something else broke",
|
|
"exception": SomeUnrelatedBug("real bug"),
|
|
}
|
|
_gateway_loop_exception_handler(loop, context)
|
|
assert forwarded == [context]
|
|
finally:
|
|
loop.close()
|
|
|
|
|
|
# ---------------------------------------------------------------------
|
|
# End-to-end: task-level
|
|
# ---------------------------------------------------------------------
|
|
|
|
|
|
def test_unhandled_transient_error_in_task_does_not_propagate_to_loop():
|
|
"""Smoke test the wiring as a loop would actually use it.
|
|
|
|
Schedules a task that raises TimedOut and is never awaited. With the
|
|
handler installed, the loop completes normally and logs a warning
|
|
instead of dying. Without the handler, asyncio would emit
|
|
``Task exception was never retrieved`` and (depending on Python's
|
|
debug mode) potentially escalate.
|
|
"""
|
|
|
|
async def raiser():
|
|
raise TimedOut("upstream timeout")
|
|
|
|
async def main():
|
|
loop = asyncio.get_running_loop()
|
|
loop.set_exception_handler(_gateway_loop_exception_handler)
|
|
task = loop.create_task(raiser())
|
|
# Give the task a tick to run and raise.
|
|
await asyncio.sleep(0)
|
|
# Don't await ``task`` — let it become an unhandled-exception task.
|
|
del task
|
|
import gc
|
|
|
|
gc.collect()
|
|
await asyncio.sleep(0)
|
|
|
|
# If the safety net works, this returns cleanly. If not, the test
|
|
# would still pass (asyncio's default is a warning, not a crash) —
|
|
# the real assertion is that no unhandled exception escapes the
|
|
# ``run`` boundary.
|
|
asyncio.run(main())
|