APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

fix(gateway): harden Telegram polling conflict handling

Browse source 
- detect Telegram getUpdates conflicts and stop polling cleanly instead of retry-spamming forever
- add a machine-local token-scoped lock so different HERMES_HOME profiles on the same host can't poll the same bot token at once
- persist gateway runtime health/fatal adapter state and surface it in ● hermes-gateway.service - Hermes Agent Gateway - Messaging Platform Integration
     Loaded: loaded (/home/teknium/.config/systemd/user/hermes-gateway.service; enabled; preset: enabled)
     Active: active (running) since Sat 2026-03-14 09:25:35 PDT; 2h 45min ago
 Invocation: 8879379b25994201b98381f4bd80c2af
   Main PID: 1147926 (python)
      Tasks: 16 (limit: 76757)
     Memory: 151.4M (peak: 168.1M)
        CPU: 47.883s
     CGroup: /user.slice/user-1000.slice/user@1000.service/app.slice/hermes-gateway.service
             ├─1147926 /home/teknium/.hermes/hermes-agent/venv/bin/python -m hermes_cli.main gateway run --replace
             └─1147966 node /home/teknium/.hermes/hermes-agent/scripts/whatsapp-bridge/bridge.js --port 3000 --session /home/teknium/.hermes/whatsapp/session --mode self-chat

Mar 14 09:27:03 teknium-dev python[1147926]: 🔄 Retrying API call (2/3)...
Mar 14 09:27:04 teknium-dev python[1147926]: [409B blob data]
Mar 14 09:27:04 teknium-dev python[1147926]:    Content: ''
Mar 14 09:27:04 teknium-dev python[1147926]: ❌ Max retries (3) for empty content exceeded.
Mar 14 09:27:07 teknium-dev python[1147926]: [1K blob data]
Mar 14 09:27:07 teknium-dev python[1147926]:    Content: ''
Mar 14 09:27:07 teknium-dev python[1147926]: 🔄 Retrying API call (1/3)...
Mar 14 09:27:12 teknium-dev python[1147926]: [1.7K blob data]
Mar 14 09:27:12 teknium-dev python[1147926]:    Content: ''
Mar 14 09:27:12 teknium-dev python[1147926]: 🔄 Retrying API call (2/3)...
⚠ Installed gateway service definition is outdated
  Run: hermes gateway restart  # auto-refreshes the unit

✓ Gateway service is running
✓ Systemd linger is enabled (service survives logout)
- cleanly exit non-retryable startup conflicts without triggering service restart loops

Tests:
- gateway status runtime-state helpers
- Telegram token-lock and polling-conflict behavior
- GatewayRunner clean exit on non-retryable startup conflict
- CLI runtime health summary
This commit is contained in:
teknium1 2026-03-14 12:11:23 -07:00
parent 21ad98b74c
commit 5a2fcaab39
9 changed files with 692 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

77
gateway/platforms/telegram.py
View file

@ -110,7 +110,35 @@ class TelegramAdapter(BasePlatformAdapter):
super().__init__(config, Platform.TELEGRAM)
self._app: Optional[Application] = None
self._bot: Optional[Bot] = None
self._token_lock_identity: Optional[str] = None
self._polling_error_task: Optional[asyncio.Task] = None
@staticmethod
def _looks_like_polling_conflict(error: Exception) -> bool:
text = str(error).lower()
return (
error.__class__.__name__.lower() == "conflict"
or "terminated by other getupdates request" in text
or "another bot instance is running" in text
)
async def _handle_polling_conflict(self, error: Exception) -> None:
if self.has_fatal_error and self.fatal_error_code == "telegram_polling_conflict":
return
message = (
"Another Telegram bot poller is already using this token. "
"Hermes stopped Telegram polling to avoid endless retry spam. "
"Make sure only one gateway instance is running for this bot token."
)
logger.error("[%s] %s Original error: %s", self.name, message, error)
self._set_fatal_error("telegram_polling_conflict", message, retryable=False)
try:
if self._app and self._app.updater:
await self._app.updater.stop()
except Exception as stop_error:
logger.warning("[%s] Failed stopping Telegram polling after conflict: %s", self.name, stop_error, exc_info=True)
await self._notify_fatal_error()
async def connect(self) -> bool:
"""Connect to Telegram and start polling for updates."""
if not TELEGRAM_AVAILABLE:
@ -125,6 +153,25 @@ class TelegramAdapter(BasePlatformAdapter):
return False
try:
from gateway.status import acquire_scoped_lock
self._token_lock_identity = self.config.token
acquired, existing = acquire_scoped_lock(
"telegram-bot-token",
self._token_lock_identity,
metadata={"platform": self.platform.value},
)
if not acquired:
owner_pid = existing.get("pid") if isinstance(existing, dict) else None
message = (
"Another local Hermes gateway is already using this Telegram bot token"
+ (f" (PID {owner_pid})." if owner_pid else ".")
+ " Stop the other gateway before starting a second Telegram poller."
)
logger.error("[%s] %s", self.name, message)
self._set_fatal_error("telegram_token_lock", message, retryable=False)
return False
# Build the application
self._app = Application.builder().token(self.config.token).build()
self._bot = self._app.bot
@ -150,9 +197,20 @@ class TelegramAdapter(BasePlatformAdapter):
# Start polling in background
await self._app.initialize()
await self._app.start()
loop = asyncio.get_running_loop()
def _polling_error_callback(error: Exception) -> None:
if not self._looks_like_polling_conflict(error):
logger.error("[%s] Telegram polling error: %s", self.name, error, exc_info=True)
return
if self._polling_error_task and not self._polling_error_task.done():
return
self._polling_error_task = loop.create_task(self._handle_polling_conflict(error))
await self._app.updater.start_polling(
allowed_updates=Update.ALL_TYPES,
drop_pending_updates=True,
error_callback=_polling_error_callback,
)
# Register bot commands so Telegram shows a hint menu when users type /
@ -188,11 +246,17 @@ class TelegramAdapter(BasePlatformAdapter):
exc_info=True,
)
self._running = True
self._mark_connected()
logger.info("[%s] Connected and polling for Telegram updates", self.name)
return True
except Exception as e:
if self._token_lock_identity:
try:
from gateway.status import release_scoped_lock
release_scoped_lock("telegram-bot-token", self._token_lock_identity)
except Exception:
pass
logger.error("[%s] Failed to connect to Telegram: %s", self.name, e, exc_info=True)
return False
@ -205,10 +269,17 @@ class TelegramAdapter(BasePlatformAdapter):
await self._app.shutdown()
except Exception as e:
logger.warning("[%s] Error during Telegram disconnect: %s", self.name, e, exc_info=True)
if self._token_lock_identity:
try:
from gateway.status import release_scoped_lock
release_scoped_lock("telegram-bot-token", self._token_lock_identity)
except Exception as e:
logger.warning("[%s] Error releasing Telegram token lock: %s", self.name, e, exc_info=True)
self._running = False
self._mark_disconnected()
self._app = None
self._bot = None
self._token_lock_identity = None
logger.info("[%s] Disconnected from Telegram", self.name)
async def send(