feat(gateway): notify /restart requester when gateway comes back online

When a user sends /restart, the gateway now persists their routing info
(platform, chat_id, thread_id) to .restart_notify.json. After the new
gateway process starts and adapters connect, it reads the file, sends a
'Gateway restarted successfully' message to that specific chat, and
cleans up the file.

This follows the same pattern as _send_update_notification (used by
/update). Thread IDs are preserved so the notification lands in the
correct Telegram topic or Discord thread.

Previously, after /restart the user had no feedback that the gateway was
back — they had to send a message to find out. Now they get a proactive
notification and know their session continues.
This commit is contained in:
Teknium 2026-04-12 21:19:44 -07:00 committed by Teknium
parent b22663ea69
commit 8a64f3e368
2 changed files with 234 additions and 0 deletions

View file

@ -1717,6 +1717,9 @@ class GatewayRunner:
):
self._schedule_update_notification_watch()
# Notify the chat that initiated /restart that the gateway is back.
await self._send_restart_notification()
# Drain any recovered process watchers (from crash recovery checkpoint)
try:
from tools.process_registry import process_registry
@ -4147,6 +4150,22 @@ class GatewayRunner:
return f"⏳ Draining {count} active agent(s) before restart..."
return "⏳ Gateway restart already in progress..."
# Save the requester's routing info so the new gateway process can
# notify them once it comes back online.
try:
import json as _json
notify_data = {
"platform": event.source.platform.value if event.source.platform else None,
"chat_id": event.source.chat_id,
}
if event.source.thread_id:
notify_data["thread_id"] = event.source.thread_id
(_hermes_home / ".restart_notify.json").write_text(
_json.dumps(notify_data)
)
except Exception as e:
logger.debug("Failed to write restart notify file: %s", e)
active_agents = self._running_agent_count()
self.request_restart(detached=True, via_service=False)
if active_agents:
@ -6880,6 +6899,48 @@ class GatewayRunner:
return True
async def _send_restart_notification(self) -> None:
"""Notify the chat that initiated /restart that the gateway is back."""
import json as _json
notify_path = _hermes_home / ".restart_notify.json"
if not notify_path.exists():
return
try:
data = _json.loads(notify_path.read_text())
platform_str = data.get("platform")
chat_id = data.get("chat_id")
thread_id = data.get("thread_id")
if not platform_str or not chat_id:
return
platform = Platform(platform_str)
adapter = self.adapters.get(platform)
if not adapter:
logger.debug(
"Restart notification skipped: %s adapter not connected",
platform_str,
)
return
metadata = {"thread_id": thread_id} if thread_id else None
await adapter.send(
chat_id,
"♻ Gateway restarted successfully. Your session continues.",
metadata=metadata,
)
logger.info(
"Sent restart notification to %s:%s",
platform_str,
chat_id,
)
except Exception as e:
logger.warning("Restart notification failed: %s", e)
finally:
notify_path.unlink(missing_ok=True)
def _set_session_env(self, context: SessionContext) -> list:
"""Set session context variables for the current async task.