Openclaw isn't sending the system context/prompt/skills to my LLM
Everything is set up, I can message Discord and Openclaw will take that message and run Ollama, sending me the response.
But, it's not being an agent, its being an LLM. The sessions tab shows new sessions start with no context.
When i run /context, there is the first message claiming to inject the usual 20-30k tokens, but then it states "session context", 3k. Which checks out, my agent is incapable of understanding the tools and skills that it is supposed to have, and doesnt know any basic .md information such as its own name.
Why might openclaw not be properly prompting my LLM all of the sudden? It wasnt doing this yesterday.
But, it's not being an agent, its being an LLM. The sessions tab shows new sessions start with no context.
When i run /context, there is the first message claiming to inject the usual 20-30k tokens, but then it states "session context", 3k. Which checks out, my agent is incapable of understanding the tools and skills that it is supposed to have, and doesnt know any basic .md information such as its own name.
Why might openclaw not be properly prompting my LLM all of the sudden? It wasnt doing this yesterday.
The AI that actually does things. Emails, calendar, home automation - all from your favorite chat app. New shell, ready to help. The lobster way.
83,815Members
Resources
Recent Announcements
Similar Threads
Was this page helpful?
