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.
108 lines
3.7 KiB
Python
108 lines
3.7 KiB
Python
"""Regression tests for platform-lock acquire behavior.
|
|
|
|
#54167 — stale platform lock must be retryable.
|
|
When a gateway process is killed (SIGKILL, crash) during Telegram
|
|
initialization, the scoped lock file survives. On next startup,
|
|
``acquire_scoped_lock()`` detects the stale lock and deletes it, but may
|
|
still return ``(False, existing_dict)`` to the caller (e.g. if the
|
|
unlink fails due to permissions, or a race condition lets another
|
|
process grab the lock first).
|
|
|
|
``_acquire_platform_lock()`` must mark such failures as **retryable**
|
|
so the reconnect watcher can retry after a delay — not permanently kill
|
|
the platform.
|
|
|
|
#65176 — a live gateway token conflict may attempt one-shot takeover only
|
|
during the initial connect of an explicit ``gateway run --replace`` startup.
|
|
``gateway run --replace`` only kills same-HERMES_HOME PID-file holders.
|
|
A normal start or reconnect must retain the retryable conflict behavior and
|
|
must never evict the active holder.
|
|
"""
|
|
|
|
from typing import Any, Dict
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from gateway.platforms.base import BasePlatformAdapter
|
|
from gateway.run import GatewayRunner
|
|
|
|
|
|
class _StubAdapter(BasePlatformAdapter):
|
|
"""Minimal concrete subclass for testing _acquire_platform_lock."""
|
|
|
|
platform = MagicMock(value="telegram")
|
|
|
|
async def connect(self, *, is_reconnect: bool = False) -> bool:
|
|
return True
|
|
|
|
async def disconnect(self) -> None:
|
|
pass
|
|
|
|
async def send(self, *args: Any, **kwargs: Any) -> None:
|
|
pass
|
|
|
|
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
|
|
return {}
|
|
|
|
|
|
@pytest.fixture()
|
|
def adapter():
|
|
"""Create a stub adapter with __init__ bypassed."""
|
|
obj = _StubAdapter.__new__(_StubAdapter)
|
|
obj._running = True
|
|
obj._fatal_error_code = None
|
|
obj._fatal_error_message = None
|
|
obj._fatal_error_retryable = True
|
|
obj._fatal_error_handler = None
|
|
obj._platform_lock_scope = None
|
|
obj._platform_lock_identity = None
|
|
obj._platform_lock_takeover_allowed = False
|
|
obj._platform_lock_takeover_attempted = False
|
|
obj._status_write_logged = None
|
|
return obj
|
|
|
|
|
|
def test_stale_lock_failure_is_retryable(adapter):
|
|
"""Lock failure must be retryable, not permanently fatal (#54167)."""
|
|
with patch(
|
|
"gateway.status.acquire_scoped_lock",
|
|
return_value=(False, {"pid": 99999, "start_time": "2026-01-01T00:00:00Z"}),
|
|
), patch.object(adapter, "_write_runtime_status_safe"):
|
|
result = adapter._acquire_platform_lock(
|
|
"telegram-bot-token", "test-token", "Telegram bot token"
|
|
)
|
|
|
|
assert result is False
|
|
assert adapter._fatal_error_retryable is True
|
|
assert adapter._fatal_error_code == "telegram-bot-token_lock"
|
|
|
|
|
|
def test_explicit_replace_takeover_reacquires_lock_once(adapter):
|
|
"""Initial explicit --replace may hand off and re-acquire once (#65176)."""
|
|
existing = {
|
|
"pid": 4242,
|
|
"kind": "hermes-gateway",
|
|
"argv": ["hermes", "gateway", "run"],
|
|
"start_time": 123,
|
|
}
|
|
acquire = MagicMock(side_effect=[(False, existing), (True, None)])
|
|
adapter._platform_lock_takeover_allowed = True
|
|
|
|
with patch("gateway.status.acquire_scoped_lock", acquire), patch(
|
|
"gateway.status.take_over_scoped_lock_holder",
|
|
return_value=4242,
|
|
) as takeover, patch.object(
|
|
adapter, "_write_runtime_status_safe"
|
|
):
|
|
result = adapter._acquire_platform_lock(
|
|
"telegram-bot-token", "test-token", "Telegram bot token"
|
|
)
|
|
|
|
assert result is True
|
|
assert adapter._platform_lock_takeover_allowed is False
|
|
assert adapter._platform_lock_takeover_attempted is True
|
|
takeover.assert_called_once_with(existing)
|
|
assert acquire.call_count == 2
|
|
|
|
|