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.
69 lines
2.3 KiB
Python
69 lines
2.3 KiB
Python
"""Tests for gateway.memory_monitor — periodic process memory logging.
|
|
|
|
Ported from cline/cline#10343. The module logs a structured
|
|
``[MEMORY] rss=...MB ...`` line periodically so long-running gateway
|
|
leaks show up as a time series in agent.log / gateway.log.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import time
|
|
|
|
import pytest
|
|
|
|
from gateway import memory_monitor as mm
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _ensure_monitor_stopped():
|
|
"""Every test starts from a clean state and leaves one behind."""
|
|
mm.stop_memory_monitoring(timeout=1.0)
|
|
yield
|
|
mm.stop_memory_monitoring(timeout=1.0)
|
|
|
|
|
|
def test_log_memory_usage_has_grep_friendly_format(caplog):
|
|
caplog.set_level(logging.INFO, logger="gateway.memory_monitor")
|
|
mm.log_memory_usage()
|
|
msg = caplog.records[-1].getMessage()
|
|
# Grep-friendly contract: line starts with [MEMORY] and carries RSS
|
|
# (or 'unavailable'), GC counts, thread count, uptime.
|
|
assert msg.startswith("[MEMORY]"), msg
|
|
assert "rss=" in msg
|
|
assert "gc=" in msg
|
|
assert "threads=" in msg
|
|
assert "uptime=" in msg
|
|
|
|
|
|
def test_start_logs_baseline_and_returns_true(caplog):
|
|
caplog.set_level(logging.INFO, logger="gateway.memory_monitor")
|
|
# Large interval so the background timer never fires during the test —
|
|
# we're only checking the synchronous baseline behavior here.
|
|
started = mm.start_memory_monitoring(interval_seconds=3600.0)
|
|
assert started is True
|
|
assert mm.is_running() is True
|
|
|
|
messages = [r.getMessage() for r in caplog.records]
|
|
assert any("[MEMORY] baseline " in m for m in messages), messages
|
|
assert any("Periodic memory monitoring started" in m for m in messages), messages
|
|
|
|
|
|
def test_double_start_is_noop():
|
|
assert mm.start_memory_monitoring(interval_seconds=3600.0) is True
|
|
assert mm.start_memory_monitoring(interval_seconds=3600.0) is False
|
|
assert mm.is_running() is True
|
|
|
|
|
|
def test_stop_logs_shutdown_snapshot(caplog):
|
|
mm.start_memory_monitoring(interval_seconds=3600.0)
|
|
caplog.clear()
|
|
caplog.set_level(logging.INFO, logger="gateway.memory_monitor")
|
|
mm.stop_memory_monitoring(timeout=1.0)
|
|
assert mm.is_running() is False
|
|
|
|
messages = [r.getMessage() for r in caplog.records]
|
|
assert any("[MEMORY] shutdown " in m for m in messages), messages
|
|
assert any("Periodic memory monitoring stopped" in m for m in messages), messages
|
|
|
|
|