hermes-agent/tests/gateway/test_max_concurrent_sessions.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

134 lines
4.6 KiB
Python

"""Tests for the gateway max_concurrent_sessions active-session cap."""
import asyncio
import time
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from gateway.config import GatewayConfig, Platform, PlatformConfig
from gateway.platforms.base import MessageEvent, MessageType
from gateway.run import GatewayRunner, _AGENT_PENDING_SENTINEL
from gateway.session import SessionSource, build_session_key
@pytest.fixture(autouse=True)
def _isolated_active_session_registry(tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path / ".hermes"))
class _FakeAdapter:
def __init__(self):
self._pending_messages = {}
self._active_sessions = {}
async def send(self, chat_id, text, **kwargs):
return None
async def interrupt_session_activity(self, session_key, chat_id):
event = self._active_sessions.get(session_key)
if event is not None:
event.set()
def _make_source(chat_id: str = "chat-1") -> SessionSource:
return SessionSource(
platform=Platform.TELEGRAM,
chat_id=chat_id,
chat_type="dm",
user_id=f"user-{chat_id}",
)
def _make_event(text: str = "hello", chat_id: str = "chat-1") -> MessageEvent:
return MessageEvent(
text=text,
message_type=MessageType.TEXT,
source=_make_source(chat_id),
)
def _make_runner(max_concurrent_sessions: int | None = None) -> GatewayRunner:
runner = object.__new__(GatewayRunner)
runner.config = GatewayConfig(
platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")},
max_concurrent_sessions=max_concurrent_sessions,
)
runner.adapters = {Platform.TELEGRAM: _FakeAdapter()}
runner._running_agents = {}
runner._running_agents_ts = {}
runner._active_session_leases = {}
runner._session_run_generation = {}
runner._pending_messages = {}
runner._pending_approvals = {}
runner._voice_mode = {}
runner._background_tasks = set()
runner._draining = False
runner._restart_requested = False
runner._restart_task_started = False
runner._restart_detached = False
runner._restart_via_service = False
runner._restart_drain_timeout = 0.0
runner._stop_task = None
runner._exit_code = None
runner._busy_ack_ts = {}
runner._busy_input_mode = "interrupt"
runner._busy_text_mode = "interrupt"
runner._queued_events = {}
runner._update_runtime_status = MagicMock()
runner._is_user_authorized = lambda _source: True
runner.hooks = MagicMock()
runner.hooks.emit = AsyncMock()
runner.session_store = MagicMock()
runner.delivery_router = MagicMock()
return runner
def _occupy_session(runner: GatewayRunner, chat_id: str = "busy"):
source = _make_source(chat_id)
session_key = build_session_key(source)
runner._running_agents[session_key] = MagicMock()
runner._running_agents_ts[session_key] = time.time()
return session_key
def _silence_global_gateway_hooks(monkeypatch):
monkeypatch.setattr("hermes_cli.plugins.invoke_hook", lambda *args, **kwargs: [])
monkeypatch.setattr("tools.slash_confirm.get_pending", lambda *args, **kwargs: None)
monkeypatch.setattr("tools.slash_confirm.clear_if_stale", lambda *args, **kwargs: None)
monkeypatch.setattr("tools.approval.has_blocking_approval", lambda *args, **kwargs: False)
def test_new_session_gets_clean_error_at_active_session_limit(monkeypatch):
_silence_global_gateway_hooks(monkeypatch)
runner = _make_runner(max_concurrent_sessions=1)
_occupy_session(runner, "busy")
event = _make_event(chat_id="new")
new_key = build_session_key(event.source)
async def fail_if_agent_runs(self_inner, ev, src, qk, generation):
raise AssertionError("_handle_message_with_agent should not run at capacity")
with patch.object(GatewayRunner, "_handle_message_with_agent", fail_if_agent_runs):
result = asyncio.run(runner._handle_message(event))
assert result == (
"Hermes is at the active session limit (1/1). "
"Try again when another session finishes."
)
assert new_key not in runner._running_agents
runner.session_store.get_or_create_session.assert_not_called()
def test_status_command_bypasses_active_session_limit(monkeypatch):
_silence_global_gateway_hooks(monkeypatch)
runner = _make_runner(max_concurrent_sessions=1)
_occupy_session(runner, "busy")
runner._handle_status_command = AsyncMock(return_value="status ok")
result = asyncio.run(runner._handle_message(_make_event("/status", chat_id="new")))
assert result == "status ok"
runner._handle_status_command.assert_awaited_once()