mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
228 lines
8.2 KiB
Python
228 lines
8.2 KiB
Python
"""Tests that on_session_finalize and on_session_reset plugin hooks fire in the gateway."""
|
|
from datetime import datetime
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from gateway.config import GatewayConfig, Platform, PlatformConfig
|
|
from gateway.platforms.base import MessageEvent
|
|
from gateway.session import SessionEntry, SessionSource, build_session_key
|
|
|
|
|
|
def _make_source() -> SessionSource:
|
|
return SessionSource(
|
|
platform=Platform.TELEGRAM,
|
|
user_id="u1",
|
|
chat_id="c1",
|
|
user_name="tester",
|
|
chat_type="dm",
|
|
)
|
|
|
|
|
|
def _make_event(text: str) -> MessageEvent:
|
|
return MessageEvent(text=text, source=_make_source(), message_id="m1")
|
|
|
|
|
|
def _make_runner():
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner.config = GatewayConfig(
|
|
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")}
|
|
)
|
|
adapter = MagicMock()
|
|
adapter.send = AsyncMock()
|
|
runner.adapters = {Platform.TELEGRAM: adapter}
|
|
runner._voice_mode = {}
|
|
runner.hooks = SimpleNamespace(emit=AsyncMock(), loaded_hooks=False)
|
|
runner._session_model_overrides = {}
|
|
runner._pending_model_notes = {}
|
|
runner._background_tasks = set()
|
|
|
|
session_key = build_session_key(_make_source())
|
|
session_entry = SessionEntry(
|
|
session_key=session_key,
|
|
session_id="sess-old",
|
|
created_at=datetime.now(),
|
|
updated_at=datetime.now(),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
new_session_entry = SessionEntry(
|
|
session_key=session_key,
|
|
session_id="sess-new",
|
|
created_at=datetime.now(),
|
|
updated_at=datetime.now(),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
runner.session_store = MagicMock()
|
|
runner.session_store.get_or_create_session.return_value = new_session_entry
|
|
runner.session_store.reset_session.return_value = new_session_entry
|
|
runner.session_store._entries = {session_key: session_entry}
|
|
runner.session_store._generate_session_key.return_value = session_key
|
|
runner._running_agents = {}
|
|
runner._pending_messages = {}
|
|
runner._pending_approvals = {}
|
|
runner._session_db = None
|
|
runner._agent_cache_lock = None
|
|
runner._is_user_authorized = lambda _source: True
|
|
runner._format_session_info = lambda: ""
|
|
|
|
return runner
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@patch("hermes_cli.plugins.invoke_hook")
|
|
async def test_idle_expiry_fires_finalize_hook(mock_invoke_hook):
|
|
"""Regression test for #14981.
|
|
|
|
When ``_session_expiry_watcher`` sweeps a session that has aged past
|
|
its reset policy (idle timeout, scheduled reset), it must fire
|
|
``on_session_finalize`` so plugin providers get the same final-pass
|
|
extraction opportunity they'd get from /new or CLI shutdown. Before
|
|
the fix, the expiry path evicted the agent but silently skipped the
|
|
hook.
|
|
"""
|
|
from datetime import datetime, timedelta
|
|
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner._running = True
|
|
runner._running_agents = {}
|
|
runner._agent_cache = {}
|
|
runner._agent_cache_lock = None
|
|
runner._last_session_store_prune_ts = 0.0
|
|
|
|
session_key = "agent:main:telegram:dm:42"
|
|
expired_entry = SessionEntry(
|
|
session_key=session_key,
|
|
session_id="sess-expired",
|
|
created_at=datetime.now() - timedelta(hours=2),
|
|
updated_at=datetime.now() - timedelta(hours=2),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
expired_entry.expiry_finalized = False
|
|
|
|
runner.session_store = MagicMock()
|
|
runner.session_store._ensure_loaded = MagicMock()
|
|
runner.session_store._entries = {session_key: expired_entry}
|
|
runner.session_store._is_session_expired = MagicMock(return_value=True)
|
|
runner.session_store._lock = MagicMock()
|
|
runner.session_store._lock.__enter__ = MagicMock(return_value=None)
|
|
runner.session_store._lock.__exit__ = MagicMock(return_value=None)
|
|
runner.session_store._save = MagicMock()
|
|
|
|
runner._evict_cached_agent = MagicMock()
|
|
runner._cleanup_agent_resources = MagicMock()
|
|
runner._sweep_idle_cached_agents = MagicMock(return_value=0)
|
|
|
|
# The watcher starts with `await asyncio.sleep(0.2)` and loops while
|
|
# `self._running`. Patch sleep so the 60s initial delay is instant, and
|
|
# make the expiry hook invocation flip `_running` false so the loop
|
|
# exits cleanly after one pass.
|
|
_orig_sleep = __import__("asyncio").sleep
|
|
|
|
async def _fast_sleep(_):
|
|
await _orig_sleep(0)
|
|
|
|
def _hook_and_stop(*a, **kw):
|
|
runner._running = False
|
|
return None
|
|
|
|
mock_invoke_hook.side_effect = _hook_and_stop
|
|
|
|
with patch("gateway.run.asyncio.sleep", side_effect=_fast_sleep):
|
|
await runner._session_expiry_watcher(interval=0)
|
|
|
|
# Look for the finalize call targeting the expired session.
|
|
finalize_calls = [
|
|
c for c in mock_invoke_hook.call_args_list
|
|
if c[0] and c[0][0] == "on_session_finalize"
|
|
]
|
|
session_ids = {c[1].get("session_id") for c in finalize_calls}
|
|
assert "sess-expired" in session_ids, (
|
|
f"on_session_finalize was not fired during idle expiry; "
|
|
f"got session_ids={session_ids} (regression of #14981)"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@patch("hermes_cli.plugins.invoke_hook")
|
|
async def test_idle_expiry_clears_last_resolved_model(mock_invoke_hook):
|
|
"""Regression test for #58403.
|
|
|
|
``_session_expiry_watcher`` permanently finalizes an expired session and
|
|
already drops ``_session_model_overrides`` / the reasoning override /
|
|
``_pending_model_notes`` — a resumed conversation must not inherit stale
|
|
per-session state. It missed ``_last_resolved_model``: without clearing
|
|
it, a resumed session could serve a cached model from before it went
|
|
idle on a transient config-cache miss, exactly the #58403 class the
|
|
/new and compression-exhausted-reset paths already guard against.
|
|
"""
|
|
from datetime import datetime, timedelta
|
|
|
|
from gateway.run import GatewayRunner
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner._running = True
|
|
runner._running_agents = {}
|
|
runner._agent_cache = {}
|
|
runner._agent_cache_lock = None
|
|
runner._last_session_store_prune_ts = 0.0
|
|
|
|
session_key = "agent:main:telegram:dm:42"
|
|
expired_entry = SessionEntry(
|
|
session_key=session_key,
|
|
session_id="sess-expired",
|
|
created_at=datetime.now() - timedelta(hours=2),
|
|
updated_at=datetime.now() - timedelta(hours=2),
|
|
platform=Platform.TELEGRAM,
|
|
chat_type="dm",
|
|
)
|
|
expired_entry.expiry_finalized = False
|
|
|
|
runner.session_store = MagicMock()
|
|
runner.session_store._ensure_loaded = MagicMock()
|
|
runner.session_store._entries = {session_key: expired_entry}
|
|
runner.session_store._is_session_expired = MagicMock(return_value=True)
|
|
runner.session_store._lock = MagicMock()
|
|
runner.session_store._lock.__enter__ = MagicMock(return_value=None)
|
|
runner.session_store._lock.__exit__ = MagicMock(return_value=None)
|
|
runner.session_store._save = MagicMock()
|
|
|
|
runner._evict_cached_agent = MagicMock()
|
|
runner._cleanup_agent_resources = MagicMock()
|
|
runner._sweep_idle_cached_agents = MagicMock(return_value=0)
|
|
runner._session_model_overrides = {}
|
|
runner._pending_model_notes = {}
|
|
runner._last_resolved_model = {
|
|
session_key: "gpt-5",
|
|
"agent:main:telegram:dm:other": "keep-me",
|
|
}
|
|
|
|
_orig_sleep = __import__("asyncio").sleep
|
|
|
|
async def _fast_sleep(_):
|
|
await _orig_sleep(0)
|
|
|
|
def _hook_and_stop(*a, **kw):
|
|
runner._running = False
|
|
return None
|
|
|
|
mock_invoke_hook.side_effect = _hook_and_stop
|
|
|
|
with patch("gateway.run.asyncio.sleep", side_effect=_fast_sleep):
|
|
await runner._session_expiry_watcher(interval=0)
|
|
|
|
assert session_key not in runner._last_resolved_model, (
|
|
"session-expiry finalization did not clear the expired session's "
|
|
"_last_resolved_model entry (#58403)"
|
|
)
|
|
assert runner._last_resolved_model["agent:main:telegram:dm:other"] == "keep-me", (
|
|
"session-expiry finalization must only clear the expired session's "
|
|
"own key, not unrelated sessions' cached entries"
|
|
)
|