fix(gateway): cancel active runs during shutdown
Track adapter background message-processing tasks, cancel them during gateway shutdown, and interrupt running agents before disconnecting adapters. This prevents old gateway instances from continuing in-flight work after stop/replace, which was contributing to the restart-time task continuation/flicker behavior reported in #1414. Adds regression coverage for adapter task cancellation and shutdown interrupts.
This commit is contained in:
parent
621fd80b1e
commit
21c20aeaa5
3 changed files with 149 additions and 2 deletions
106
tests/gateway/test_gateway_shutdown.py
Normal file
106
tests/gateway/test_gateway_shutdown.py
Normal file
|
|
@ -0,0 +1,106 @@
|
|||
import asyncio
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from gateway.config import GatewayConfig, Platform, PlatformConfig
|
||||
from gateway.platforms.base import BasePlatformAdapter, MessageEvent, SendResult
|
||||
from gateway.run import GatewayRunner
|
||||
from gateway.session import SessionSource, build_session_key
|
||||
|
||||
|
||||
class StubAdapter(BasePlatformAdapter):
|
||||
def __init__(self):
|
||||
super().__init__(PlatformConfig(enabled=True, token="***"), Platform.TELEGRAM)
|
||||
|
||||
async def connect(self):
|
||||
return True
|
||||
|
||||
async def disconnect(self):
|
||||
return None
|
||||
|
||||
async def send(self, chat_id, content, reply_to=None, metadata=None):
|
||||
return SendResult(success=True, message_id="1")
|
||||
|
||||
async def send_typing(self, chat_id, metadata=None):
|
||||
return None
|
||||
|
||||
async def get_chat_info(self, chat_id):
|
||||
return {"id": chat_id}
|
||||
|
||||
|
||||
def _source(chat_id="123456", chat_type="dm"):
|
||||
return SessionSource(
|
||||
platform=Platform.TELEGRAM,
|
||||
chat_id=chat_id,
|
||||
chat_type=chat_type,
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_cancel_background_tasks_cancels_inflight_message_processing():
|
||||
adapter = StubAdapter()
|
||||
release = asyncio.Event()
|
||||
|
||||
async def block_forever(_event):
|
||||
await release.wait()
|
||||
return None
|
||||
|
||||
adapter.set_message_handler(block_forever)
|
||||
event = MessageEvent(text="work", source=_source(), message_id="1")
|
||||
|
||||
await adapter.handle_message(event)
|
||||
await asyncio.sleep(0)
|
||||
|
||||
session_key = build_session_key(event.source)
|
||||
assert session_key in adapter._active_sessions
|
||||
assert adapter._background_tasks
|
||||
|
||||
await adapter.cancel_background_tasks()
|
||||
|
||||
assert adapter._background_tasks == set()
|
||||
assert adapter._active_sessions == {}
|
||||
assert adapter._pending_messages == {}
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_gateway_stop_interrupts_running_agents_and_cancels_adapter_tasks():
|
||||
runner = object.__new__(GatewayRunner)
|
||||
runner.config = GatewayConfig(platforms={Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")})
|
||||
runner._running = True
|
||||
runner._shutdown_event = asyncio.Event()
|
||||
runner._exit_reason = None
|
||||
runner._pending_messages = {"session": "pending text"}
|
||||
runner._pending_approvals = {"session": {"command": "rm -rf /tmp/x"}}
|
||||
runner._shutdown_all_gateway_honcho = lambda: None
|
||||
|
||||
adapter = StubAdapter()
|
||||
release = asyncio.Event()
|
||||
|
||||
async def block_forever(_event):
|
||||
await release.wait()
|
||||
return None
|
||||
|
||||
adapter.set_message_handler(block_forever)
|
||||
event = MessageEvent(text="work", source=_source(), message_id="1")
|
||||
await adapter.handle_message(event)
|
||||
await asyncio.sleep(0)
|
||||
|
||||
disconnect_mock = AsyncMock()
|
||||
adapter.disconnect = disconnect_mock
|
||||
|
||||
session_key = build_session_key(event.source)
|
||||
running_agent = MagicMock()
|
||||
runner._running_agents = {session_key: running_agent}
|
||||
runner.adapters = {Platform.TELEGRAM: adapter}
|
||||
|
||||
with patch("gateway.status.remove_pid_file"), patch("gateway.status.write_runtime_status"):
|
||||
await runner.stop()
|
||||
|
||||
running_agent.interrupt.assert_called_once_with("Gateway shutting down")
|
||||
disconnect_mock.assert_awaited_once()
|
||||
assert runner.adapters == {}
|
||||
assert runner._running_agents == {}
|
||||
assert runner._pending_messages == {}
|
||||
assert runner._pending_approvals == {}
|
||||
assert runner._shutdown_event.is_set() is True
|
||||
Loading…
Add table
Add a link
Reference in a new issue