You can't load-test an LLM agent with a dumb mock

The first thing I tried was the obvious thing: stand up a fake OpenAI endpoint that returns a hardcoded response, point the agent at it, and ramp up concurrent users. Mock the expensive dependency, isolate the variable, measure the infrastructure. The agent entered an infinite loop on every request. The reason comes down to how LangGraph agents work. Each turn, the agent calls OpenAI and gets back either a tool invocation or text. If it's a tool invocation, the agent runs the tool, appends the...