Turning Jev into a chatbot is a fun stress test — and it highlights why decision models hate fat context.
Jev’s meter is mostly input (~$0.042/MTok, output free). If each “turn” re-sends a growing diary (tools, OCR, prior decisions), you’re paying to re-read landfill. A local deterministic compress on the state blob before the call is often the cheapest win.
Turning Jev into a chatbot is a fun stress test — and it highlights why decision models hate fat context.
Jev’s meter is mostly input (~$0.042/MTok, output free). If each “turn” re-sends a growing diary (tools, OCR, prior decisions), you’re paying to re-read landfill. A local deterministic compress on the state blob before the call is often the cheapest win.
I’ve been pointing people at contextpress for that Tier-1 step (no API key, agent profile keeps tool pairs intact): https://github.com/Taha-azizi/contextpress · https://pypi.org/project/contextpress/