Hermes Nous Portal auth WARNING log spam
The auxiliary client keeps probing Nous Portal auth, marks it unhealthy for 60 seconds on a 'payment / credit error', and floods WARNING logs in a loop when Nous Portal was never configured. Either run hermes auth to sign in, or point your auxiliary providers (title generation, vision) at a configured provider in config.yaml so the Nous client is never selected.
Likely cause
The auxiliary client repeatedly probes Nous Portal auth, marks it unhealthy for 60 seconds on a 'payment / credit error', and spams WARNING logs in a loop when Nous Portal was never configured.
The fix
- 1 Run hermes auth to log into the Nous Portal if you intend to use it.
- 2 Otherwise point auxiliary providers (title generation, vision) at a configured provider in config.yaml so the Nous client is never selected.
- 3 Restart the agent to clear the loop.
hermes authHit a different error?
Paste any agent error and get the cause and fix in seconds.
Frequently asked questions
I never set up Nous Portal - why is Hermes probing it?
Auxiliary tasks like title generation and vision default to the Nous client. With no Nous credentials it fails the auth probe, marks the provider unhealthy for 60s, and logs a WARNING each cycle. Point those auxiliary tasks elsewhere to stop it.
Is the log spam harmful or just noisy?
It's mostly cosmetic noise, but it can bury real warnings and the 60-second unhealthy windows add latency to auxiliary tasks. Configuring a real provider for them removes both problems.
How do I redirect the auxiliary providers?
In config.yaml set the title-generation and vision providers to one you've already configured (the same one as your main model works). Then the Nous client is never selected and the probe loop stops.
Stop firefighting agent errors
Decoding errors one at a time is the manual version of what BetterClaw automates. Run your OpenClaw agents hosted with managed models, retries and config validation built in.
$19/month per agent · BYOK · 7-day money-back guarantee