mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-27 11:22:03 +00:00
43b8ba4181
After a prolonged outage the in-process network-error ladder escalates to fatal and GatewayRunner._platform_reconnect_watcher rebuilds a fresh adapter that reconnects through the bootstrap path. That path called start_polling(drop_pending_updates=True), discarding every update Telegram queued during the outage — all messages sent while the bot was down were silently lost. The in-process ladder and 409-conflict handler already passed drop_pending_updates=False; only bootstrap did not distinguish a cold first boot from a reconnect. Thread an is_reconnect signal from the watcher through _connect_adapter_with_timeout into adapter.connect(). The base BasePlatformAdapter.connect() gains a keyword-only is_reconnect=False so every adapter inherits a tolerant signature (no per-platform breakage when the runner forwards the kwarg). Telegram translates is_reconnect into drop_pending_updates=not is_reconnect on both the polling and webhook bootstrap calls. Cold boot still drops the stale queue; a watcher reconnect preserves it. Fixes #46621. Co-authored-by: annguyenNous <annguyen@nousresearch.com> Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com> Co-authored-by: Kewe63 <Kewe63@users.noreply.github.com>
100 lines
3.3 KiB
Python
100 lines
3.3 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, *, is_reconnect: bool = False) -> 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, *, is_reconnect: bool = False) -> 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
|
|
AND keep the gateway alive — the background reconnect watcher recovers
|
|
the platform when the underlying issue clears. (Previously this
|
|
exited-with-failure to trigger a systemd restart; that converted
|
|
transient failures into infinite restart loops.)
|
|
"""
|
|
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)
|
|
|
|
# Gateway stays alive — watcher will retry in background
|
|
runner.stop.assert_not_awaited()
|
|
assert runner._exit_with_failure is False
|
|
assert Platform.WHATSAPP in runner._failed_platforms
|
|
assert runner._failed_platforms[Platform.WHATSAPP]["attempts"] == 0
|