mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
71 lines
3 KiB
Python
71 lines
3 KiB
Python
"""Tests for the shared httpx.Limits helper that all long-lived platform
|
|
adapters use to tighten their keep-alive pool.
|
|
|
|
Context: #18451 — on macOS behind Cloudflare Warp, httpx's default
|
|
keepalive_expiry=5s let idle CLOSE_WAIT sockets accumulate across
|
|
multiple long-lived gateway adapters (QQ Bot, Feishu, WeCom, DingTalk,
|
|
Signal, BlueBubbles, WeCom-callback) until the process hit the default
|
|
256 fd limit. These tests just verify the helper returns sensibly
|
|
tuned limits and respects env-var overrides; the actual fd-pressure
|
|
behaviour is only observable at runtime under load.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clear_env(monkeypatch):
|
|
monkeypatch.delenv("HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY", raising=False)
|
|
monkeypatch.delenv("HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE", raising=False)
|
|
|
|
|
|
def test_returns_none_when_httpx_unavailable(monkeypatch):
|
|
"""If httpx can't be imported, the helper returns None so callers
|
|
fall back to httpx's built-in Limits default without raising."""
|
|
import gateway.platforms._http_client_limits as mod
|
|
monkeypatch.setattr(mod, "httpx", None)
|
|
assert mod.platform_httpx_limits() is None
|
|
|
|
|
|
def test_env_override_rejects_garbage(monkeypatch):
|
|
"""Malformed env values fall back to defaults rather than raising."""
|
|
monkeypatch.setenv("HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY", "not-a-number")
|
|
monkeypatch.setenv("HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE", "-3")
|
|
from gateway.platforms._http_client_limits import platform_httpx_limits
|
|
limits = platform_httpx_limits()
|
|
# Non-positive / non-numeric → fell back to defaults (not the override values)
|
|
assert limits.keepalive_expiry is not None and limits.keepalive_expiry > 0
|
|
assert limits.max_keepalive_connections is not None
|
|
assert limits.max_keepalive_connections > 0
|
|
|
|
|
|
class TestWhatsappTypingLeakFix:
|
|
"""#18451 — whatsapp.send_typing previously used a bare
|
|
`await self._http_session.post(...)` which leaked the aiohttp
|
|
response object until GC, holding its TCP socket in CLOSE_WAIT.
|
|
Must now wrap the call in `async with` so the response is
|
|
released immediately when the call returns.
|
|
|
|
We verify by inspecting the source text rather than exercising
|
|
the coroutine — the test suite would otherwise need a live
|
|
aiohttp server, and the contract we care about is structural.
|
|
"""
|
|
|
|
def test_bare_await_removed(self):
|
|
import inspect
|
|
import plugins.platforms.whatsapp.adapter as mod
|
|
|
|
src = inspect.getsource(mod.WhatsAppAdapter.send_typing)
|
|
# The fix must be structural: the post() call is inside an
|
|
# `async with`, not a bare `await`.
|
|
assert "async with self._http_session.post(" in src, (
|
|
"send_typing must wrap self._http_session.post(...) in "
|
|
"`async with` to release the aiohttp response socket "
|
|
"(#18451). Otherwise the response sits in CLOSE_WAIT "
|
|
"until GC."
|
|
)
|
|
# The old bare-await form must be gone.
|
|
assert "await self._http_session.post(" not in src
|