Files
nousresearch--hermes-agent/tests/gateway/test_stale_platform_lock_retryable.py
wehub-resource-sync b4fbd6fe9f
Deploy Site / deploy-vercel (push) Has been skipped
Deploy Site / deploy-docs (push) Has been skipped
Build Skills Index / build-index (push) Has been skipped
CI / Deny unrelated histories (push) Has been skipped
CI / Detect affected areas (push) Successful in 27m35s
CI / OSV scan (push) Failing after 4s
CI / Build&Test Docker image (push) Successful in 9s
CI / Supply-chain scan (push) Has been skipped
CI / Lint Docker scripts (push) Failing after 5m13s
CI / Check contributors (push) Failing after 12m8s
CI / Docs Site (push) Failing after 12m8s
CI / TypeScript (push) Failing after 12m8s
CI / Python lints (push) Failing after 12m9s
CI / Python tests (push) Failing after 12m9s
CI / Check uv.lock (push) Failing after 23m22s
CI / CI timing report (push) Has been cancelled
Build Skills Index / trigger-deploy (push) Has been cancelled
CI / All required checks pass (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 11:56:03 +08:00

74 lines
2.3 KiB
Python

"""Regression test for #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.
Contract asserted here
----------------------
``_set_fatal_error`` is called with ``retryable=True`` when lock
acquisition fails, regardless of the reason.
"""
from typing import Any, Dict
from unittest.mock import MagicMock, patch
import pytest
from gateway.platforms.base import BasePlatformAdapter
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._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"