#LLM request rejected: input length and max_tokens exceed context limit

1 messages · Page 1 of 1 (latest)

fresh basin
#

it could either be a limit set somewhere in your configuration files, or the model your using can't handle the ammout of context

try running openclaw doctor --deep, them openclaw doctor --fix and restart the gateway

if its a configuration issue (that you didn't add yourself), that should fix it

if not, run /status and see how many tokens your using, and see if that exceeds the context window os the AI model your using

#

oop sorry, before doing all this, run /compact

#

it might tempoarily fix your issue

sterile geyser
#

thanks! i've solved it

sick ermine