openAIAutoModeMiddleware

Blocks listed tool calls that the OpenAI Decisions API judges risky (beta).

A call runs only when the probability that it is risky is below 0.5. Risky calls and refusals return an error ToolMessage without running the tool, and classification errors propagate. This blocks; it does not ask for approval, so combine it with humanInTheLoopMiddleware where approval is needed.