My OpenClaw is constantly at 50k+ context & always stops half way through a chat. I asked it to use perplexity to search & analyze what is going on. it said that ~15-20k tokens of system prompt + workspace files + tool definitions load before we talk. is that normal!?
From Twitter
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments
Share





