mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
fix(gateway): harden Telegram polling conflict handling
- 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⚠ Installed gateway service definition is outdated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
parent
21ad98b74c
commit
5a2fcaab39
9 changed files with 692 additions and 9 deletions
|
|
@ -245,6 +245,8 @@ class GatewayRunner:
|
|||
self.delivery_router = DeliveryRouter(self.config)
|
||||
self._running = False
|
||||
self._shutdown_event = asyncio.Event()
|
||||
self._exit_cleanly = False
|
||||
self._exit_reason: Optional[str] = None
|
||||
|
||||
# Track running agents per session for interrupt support
|
||||
# Key: session_key, Value: AIAgent instance
|
||||
|
|
@ -463,6 +465,41 @@ class GatewayRunner:
|
|||
"""Run the sync memory flush in a thread pool so it won't block the event loop."""
|
||||
loop = asyncio.get_event_loop()
|
||||
await loop.run_in_executor(None, self._flush_memories_for_session, old_session_id)
|
||||
|
||||
@property
|
||||
def should_exit_cleanly(self) -> bool:
|
||||
return self._exit_cleanly
|
||||
|
||||
@property
|
||||
def exit_reason(self) -> Optional[str]:
|
||||
return self._exit_reason
|
||||
|
||||
async def _handle_adapter_fatal_error(self, adapter: BasePlatformAdapter) -> None:
|
||||
"""React to a non-retryable adapter failure after startup."""
|
||||
logger.error(
|
||||
"Fatal %s adapter error (%s): %s",
|
||||
adapter.platform.value,
|
||||
adapter.fatal_error_code or "unknown",
|
||||
adapter.fatal_error_message or "unknown error",
|
||||
)
|
||||
|
||||
existing = self.adapters.get(adapter.platform)
|
||||
if existing is adapter:
|
||||
try:
|
||||
await adapter.disconnect()
|
||||
finally:
|
||||
self.adapters.pop(adapter.platform, None)
|
||||
self.delivery_router.adapters = self.adapters
|
||||
|
||||
if not self.adapters:
|
||||
self._exit_reason = adapter.fatal_error_message or "All messaging adapters disconnected"
|
||||
logger.error("No connected messaging platforms remain. Shutting down gateway cleanly.")
|
||||
await self.stop()
|
||||
|
||||
def _request_clean_exit(self, reason: str) -> None:
|
||||
self._exit_cleanly = True
|
||||
self._exit_reason = reason
|
||||
self._shutdown_event.set()
|
||||
|
||||
@staticmethod
|
||||
def _load_prefill_messages() -> List[Dict[str, Any]]:
|
||||
|
|
@ -647,6 +684,11 @@ class GatewayRunner:
|
|||
"""
|
||||
logger.info("Starting Hermes Gateway...")
|
||||
logger.info("Session storage: %s", self.config.sessions_dir)
|
||||
try:
|
||||
from gateway.status import write_runtime_status
|
||||
write_runtime_status(gateway_state="starting", exit_reason=None)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Warn if no user allowlists are configured and open access is not opted in
|
||||
_any_allowlist = any(
|
||||
|
|
@ -676,6 +718,7 @@ class GatewayRunner:
|
|||
logger.warning("Process checkpoint recovery: %s", e)
|
||||
|
||||
connected_count = 0
|
||||
startup_nonretryable_errors: list[str] = []
|
||||
|
||||
# Initialize and connect each configured platform
|
||||
for platform, platform_config in self.config.platforms.items():
|
||||
|
|
@ -687,8 +730,9 @@ class GatewayRunner:
|
|||
logger.warning("No adapter available for %s", platform.value)
|
||||
continue
|
||||
|
||||
# Set up message handler
|
||||
# Set up message + fatal error handlers
|
||||
adapter.set_message_handler(self._handle_message)
|
||||
adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
|
||||
|
||||
# Try to connect
|
||||
logger.info("Connecting to %s...", platform.value)
|
||||
|
|
@ -701,10 +745,24 @@ class GatewayRunner:
|
|||
logger.info("✓ %s connected", platform.value)
|
||||
else:
|
||||
logger.warning("✗ %s failed to connect", platform.value)
|
||||
if adapter.has_fatal_error and not adapter.fatal_error_retryable:
|
||||
startup_nonretryable_errors.append(
|
||||
f"{platform.value}: {adapter.fatal_error_message}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error("✗ %s error: %s", platform.value, e)
|
||||
|
||||
if connected_count == 0:
|
||||
if startup_nonretryable_errors:
|
||||
reason = "; ".join(startup_nonretryable_errors)
|
||||
logger.error("Gateway hit a non-retryable startup conflict: %s", reason)
|
||||
try:
|
||||
from gateway.status import write_runtime_status
|
||||
write_runtime_status(gateway_state="startup_failed", exit_reason=reason)
|
||||
except Exception:
|
||||
pass
|
||||
self._request_clean_exit(reason)
|
||||
return True
|
||||
logger.warning("No messaging platforms connected.")
|
||||
logger.info("Gateway will continue running for cron job execution.")
|
||||
|
||||
|
|
@ -712,6 +770,11 @@ class GatewayRunner:
|
|||
self.delivery_router.adapters = self.adapters
|
||||
|
||||
self._running = True
|
||||
try:
|
||||
from gateway.status import write_runtime_status
|
||||
write_runtime_status(gateway_state="running", exit_reason=None)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Emit gateway:startup hook
|
||||
hook_count = len(self.hooks.loaded_hooks)
|
||||
|
|
@ -806,8 +869,12 @@ class GatewayRunner:
|
|||
self._shutdown_all_gateway_honcho()
|
||||
self._shutdown_event.set()
|
||||
|
||||
from gateway.status import remove_pid_file
|
||||
from gateway.status import remove_pid_file, write_runtime_status
|
||||
remove_pid_file()
|
||||
try:
|
||||
write_runtime_status(gateway_state="stopped", exit_reason=self._exit_reason)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
logger.info("Gateway stopped")
|
||||
|
||||
|
|
@ -4340,6 +4407,10 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
|
|||
success = await runner.start()
|
||||
if not success:
|
||||
return False
|
||||
if runner.should_exit_cleanly:
|
||||
if runner.exit_reason:
|
||||
logger.error("Gateway exiting cleanly: %s", runner.exit_reason)
|
||||
return True
|
||||
|
||||
# Write PID file so CLI can detect gateway is running
|
||||
import atexit
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue