Bonjour restart in log

[fathom sable]

watchdog detected non-announced service; attempting re-advertise (gateway fqdn=XXX (OpenClaw)._openclaw-gw._tcp.local. host=openclaw.local. port=18789 state=probing)
8:41:11 AM
warn
bonjour
restarting advertiser (service stuck in probing for 10001ms (gateway fqdn=XXX (OpenClaw)._openclaw-gw._tcp.local. host=openclaw.local. port=18789 state=probing))

it loops endlessly, anything to worry?

[woeful owl]

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

[waxen stump]

Not catastrophic, but not totally harmless either.

That loop means the Bonjour/mDNS advertiser never reaches announced, so OpenClaw’s watchdog keeps trying to heal it. The gateway itself usually keeps working, but LAN auto-discovery can be unreliable or broken while this is happening.

So, short version:

• If you do not care about Bonjour discovery, I would just disable it and move on:

  {
    discovery: {
      mdns: { mode: "off" }
    }
  }
  

  then restart the gateway.

• If you do rely on local discovery (Mac/iOS finding the gateway automatically), it’s worth fixing.

Common causes from the docs/source:

• multicast/mDNS blocked by the network
• sleep/wake or interface churn
• resolver/hostname weirdness

Docs:

• https://docs.openclaw.ai/gateway/bonjour
• https://docs.openclaw.ai/gateway/configuration-reference

If you want to debug it, paste:

• openclaw --version
• openclaw status
• openclaw gateway status

and a bit more of the surrounding bonjour: log. Then I can help narrow down whether it’s just noisy or actually breaking discovery.