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.
86 lines
2.6 KiB
Python
86 lines
2.6 KiB
Python
"""Gateway /agents surfaces background delegations with live activity (#51690).
|
|
|
|
Drives the REAL GatewayRunner._handle_agents_command against a REAL
|
|
async-delegation registry dispatch (no mocked list function), so the test
|
|
covers the whole projection: registry record → list_async_delegations()
|
|
live sampling → /agents rendering.
|
|
"""
|
|
|
|
import threading
|
|
import time
|
|
|
|
import pytest
|
|
|
|
from tools import async_delegation as ad
|
|
from tools.process_registry import process_registry
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_state():
|
|
ad._reset_for_tests()
|
|
while not process_registry.completion_queue.empty():
|
|
process_registry.completion_queue.get_nowait()
|
|
yield
|
|
deadline = time.monotonic() + 2.0
|
|
while ad.active_count() and time.monotonic() < deadline:
|
|
time.sleep(0.02)
|
|
ad._reset_for_tests()
|
|
while not process_registry.completion_queue.empty():
|
|
process_registry.completion_queue.get_nowait()
|
|
|
|
|
|
def _make_runner():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner._running_agents = {}
|
|
runner._running_agents_ts = {}
|
|
runner._background_tasks = set()
|
|
runner._session_key_for_source = lambda source: "agent:main:test:dm:1"
|
|
return runner
|
|
|
|
|
|
class _Event:
|
|
source = None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agents_command_marks_stalling_delegation(monkeypatch):
|
|
monkeypatch.setattr(ad, "_STALE_CHECK_INTERVAL", 0.03)
|
|
monkeypatch.setattr(ad, "_STALE_IDLE_SECONDS", 0.1)
|
|
# Long grace so the record stays in 'stalling' while we render.
|
|
monkeypatch.setattr(ad, "_STALL_GRACE_SECONDS", 30.0)
|
|
gate = threading.Event()
|
|
|
|
res = ad.dispatch_async_delegation(
|
|
goal="wedged child", context=None, toolsets=None, role="leaf",
|
|
model="m", session_key="agent:main:test:dm:1", max_async_children=1,
|
|
runner=lambda: {} if gate.wait(timeout=10) else {},
|
|
progress_fn=lambda: ((0, None), False),
|
|
)
|
|
assert res["status"] == "dispatched"
|
|
|
|
try:
|
|
deadline = time.monotonic() + 5.0
|
|
while time.monotonic() < deadline:
|
|
items = ad.list_async_delegations()
|
|
if any(
|
|
d["delegation_id"] == res["delegation_id"]
|
|
and d.get("status") == "stalling"
|
|
for d in items
|
|
):
|
|
break
|
|
time.sleep(0.02)
|
|
else:
|
|
pytest.fail("delegation never reached stalling state")
|
|
|
|
runner = _make_runner()
|
|
out = await runner._handle_agents_command(_Event())
|
|
finally:
|
|
gate.set()
|
|
|
|
assert res["delegation_id"] in out
|
|
assert "stalling" in out
|
|
assert "no progress" in out
|
|
|
|
|