Files
hermes-agent/tests/gateway/test_runner_fatal_adapter.py
Teknium 708f187549 fix(gateway): exit with failure when all platforms fail with retryable errors (#3592)
When all messaging platforms exhaust retries and get queued for background
reconnection, exit with code 1 so systemd Restart=on-failure can restart
the process. Previously the gateway stayed alive as a zombie with no
connected platforms and exit code 0.

Salvaged from PR #3567 by kelsia14. Test updates added.

Co-authored-by: kelsia14 <kelsia14@users.noreply.github.com>
2026-03-28 14:25:12 -07:00

97 lines
3.0 KiB
Python

from unittest.mock import AsyncMock
import pytest
from gateway.config import GatewayConfig, Platform, PlatformConfig
from gateway.platforms.base import BasePlatformAdapter
from gateway.run import GatewayRunner
class _FatalAdapter(BasePlatformAdapter):
def __init__(self):
super().__init__(PlatformConfig(enabled=True, token="token"), Platform.TELEGRAM)
async def connect(self) -> bool:
self._set_fatal_error(
"telegram_token_lock",
"Another local Hermes gateway is already using this Telegram bot token.",
retryable=False,
)
return False
async def disconnect(self) -> None:
self._mark_disconnected()
async def send(self, chat_id, content, reply_to=None, metadata=None):
raise NotImplementedError
async def get_chat_info(self, chat_id):
return {"id": chat_id}
class _RuntimeRetryableAdapter(BasePlatformAdapter):
def __init__(self):
super().__init__(PlatformConfig(enabled=True, token="token"), Platform.WHATSAPP)
async def connect(self) -> bool:
return True
async def disconnect(self) -> None:
self._mark_disconnected()
async def send(self, chat_id, content, reply_to=None, metadata=None):
raise NotImplementedError
async def get_chat_info(self, chat_id):
return {"id": chat_id}
@pytest.mark.asyncio
async def test_runner_requests_clean_exit_for_nonretryable_startup_conflict(monkeypatch, tmp_path):
config = GatewayConfig(
platforms={
Platform.TELEGRAM: PlatformConfig(enabled=True, token="token")
},
sessions_dir=tmp_path / "sessions",
)
runner = GatewayRunner(config)
monkeypatch.setattr(runner, "_create_adapter", lambda platform, platform_config: _FatalAdapter())
ok = await runner.start()
assert ok is True
assert runner.should_exit_cleanly is True
assert "already using this Telegram bot token" in runner.exit_reason
@pytest.mark.asyncio
async def test_runner_queues_retryable_runtime_fatal_for_reconnection(monkeypatch, tmp_path):
"""Retryable runtime fatal errors queue the platform for reconnection
instead of shutting down the gateway."""
config = GatewayConfig(
platforms={
Platform.WHATSAPP: PlatformConfig(enabled=True, token="token")
},
sessions_dir=tmp_path / "sessions",
)
runner = GatewayRunner(config)
adapter = _RuntimeRetryableAdapter()
adapter._set_fatal_error(
"whatsapp_bridge_exited",
"WhatsApp bridge process exited unexpectedly (code 1).",
retryable=True,
)
runner.adapters = {Platform.WHATSAPP: adapter}
runner.delivery_router.adapters = runner.adapters
runner.stop = AsyncMock()
await runner._handle_adapter_fatal_error(adapter)
# Should shut down with failure — systemd Restart=on-failure will restart
runner.stop.assert_awaited_once()
assert runner._exit_with_failure is True
assert Platform.WHATSAPP in runner._failed_platforms
assert runner._failed_platforms[Platform.WHATSAPP]["attempts"] == 0