Hey
I'm getting this error on Groq even in a brand-new chat with a one-line prompt:
Request too large. Limit: 8000, Requested: 38458
It seems the system prompt + attached tools (GitHub, Playwright, etc.) exceed the model's context limit before my prompt is added.
Is this a known issue? Is there a way to reduce the tools sent per request or disable unused ones?
Also, I've already tried Gemini, OpenRouter, Cerebras, and ChatGPT. Are there any other free providers/models you recommend that work well with Archestra and tool-heavy workflows?