Local Jev-style trading bot stress test: the model can adjust quotes but not override hard risk controls
A local trading bot using Jev-style three-tier decisions (NORMAL/WIDE/PAUSE) narrowed quotes and paused orders as order flow turned one-sided, while unsafe books were blocked in code without waiting for the model.
we built a local Jev-style AI trader. its most important result was an order that never got sent. Cloudflare's Jev-compatible Clef had three choices: NORMAL, WIDE, PAUSE. No BUY button. No permission to change position limits. Code owned the order book, quotes, cancels and fills. We ran a stress replay. As order flow turned one-sided, the bot moved from NORMAL to WIDE and pulled its quotes back. When the pressure persisted, it moved to PAUSE and stopped sending new orders. Then came the result that mattered more than the mode switch: an unsafe book stopped new orders in code, without waiting for Clef's next answer. The model could change how the bot quoted. It could not talk the bot past a hard stop. The log showed the chain from market snapshot to model choice to quote action to risk veto. It also kept compute and trading costs beside those decisions. No green P&L screenshot. The result was a bot that could refuse its own model before an order reached the exchange. save this, then open the piece below
This post quotes another post: x.com/paonx_eth/status/2103881060878533066