hermes-agent/tests/gateway/test_stop_thread_sibling.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

139 lines
4.5 KiB
Python

"""Regression tests: /stop can interrupt a sibling participant's run in a
per-user thread.
When ``thread_sessions_per_user=True``, each participant in a thread gets an
isolated session key (``...:{thread_id}:{user_id}``). A run another user
started lives under a different key, so the caller's own ``/stop`` used to find
nothing and reply "no active task to stop". Authorized users should be able to
stop any run in the same thread.
"""
import pytest
from gateway.run import GatewayRunner, _AGENT_PENDING_SENTINEL, _INTERRUPT_REASON_STOP
from gateway.session import SessionSource, build_session_key
from gateway.platforms.base import Platform, MessageEvent, MessageType
class _FakeAgent:
pass
def _thread_source(uid, thread_id="thr1", chat_id="chan1"):
return SessionSource(
platform=Platform.DISCORD,
chat_type="forum",
chat_id=chat_id,
thread_id=thread_id,
user_id=uid,
)
def _per_user_key(uid, thread_id="thr1", chat_id="chan1"):
return build_session_key(
_thread_source(uid, thread_id, chat_id),
thread_sessions_per_user=True,
)
# ---------------------------------------------------------------------------
# _sibling_thread_run_keys
# ---------------------------------------------------------------------------
def test_sibling_returns_empty_for_non_thread_source():
# Non-thread group/channel must NOT trigger the cross-user fallback.
runner = object.__new__(GatewayRunner)
nonthread = SessionSource(
platform=Platform.DISCORD, chat_type="group", chat_id="chan1", user_id="userA"
)
grp_b = build_session_key(
SessionSource(
platform=Platform.DISCORD, chat_type="group", chat_id="chan1", user_id="userB"
)
)
runner._running_agents = {grp_b: _FakeAgent()}
assert runner._sibling_thread_run_keys(nonthread, "agent:main:discord:group:chan1:userA") == []
# ---------------------------------------------------------------------------
# _handle_stop_command fallback path
# ---------------------------------------------------------------------------
class _StoreEntry:
def __init__(self, session_key):
self.session_key = session_key
class _FakeStore:
def __init__(self, session_key):
self._key = session_key
def get_or_create_session(self, source):
return _StoreEntry(self._key)
@pytest.mark.asyncio
async def test_stop_does_not_interrupt_sibling_when_unauthorized(monkeypatch):
runner = object.__new__(GatewayRunner)
key_a = _per_user_key("userA")
key_b = _per_user_key("userB")
runner._running_agents = {key_b: _FakeAgent()}
runner.session_store = _FakeStore(key_a)
interrupted = []
async def _fake_interrupt(session_key, source, *, interrupt_reason, invalidation_reason):
interrupted.append(session_key)
runner._interrupt_and_clear_session = _fake_interrupt
runner._is_user_authorized = lambda source: False
event = MessageEvent(
text="/stop", message_type=MessageType.TEXT, source=_thread_source("userA")
)
result = await runner._handle_stop_command(event)
assert interrupted == []
assert "no active" in str(getattr(result, "text", result)).lower()
# ---------------------------------------------------------------------------
# /stop with no active agent still clears a stuck platform status (#32295)
# ---------------------------------------------------------------------------
class _FakeStatusAdapter:
def __init__(self):
self.cleared = []
async def _stop_typing_with_metadata(self, chat_id, metadata=None):
self.cleared.append((chat_id, metadata))
@pytest.mark.asyncio
async def test_stop_no_active_agent_survives_status_clear_failure():
"""A failing adapter clear must not break the /stop reply."""
runner = object.__new__(GatewayRunner)
runner._running_agents = {}
key = _per_user_key("userA")
runner.session_store = _FakeStore(key)
runner._is_user_authorized = lambda source: True
class _BoomAdapter:
async def _stop_typing_with_metadata(self, chat_id, metadata=None):
raise RuntimeError("boom")
runner.adapters = {Platform.DISCORD: _BoomAdapter()}
runner._thread_metadata_for_source = (
lambda source, reply_to_message_id=None: None
)
runner._reply_anchor_for_event = lambda event: None
event = MessageEvent(
text="/stop", message_type=MessageType.TEXT, source=_thread_source("userA")
)
result = await runner._handle_stop_command(event)
assert "no active" in str(getattr(result, "text", result)).lower()