An agent loop is designed to run until the model returns no tool calls. During a stress test, the loop executes 200 iterations on a complex task without terminating. The model continues generating tool calls indefinitely. What termination conditions should the architect add to prevent infinite loops?

B is correct because robust agent loop termination requires multiple independent guards rather than relying on a single condition. An iteration counter catches infinite loops directly; a time limit catches loops where each iteration is slow; detecting repeated identical tool calls catches the specific pathology of a model oscillating between the same two actions without progress. Combining these three makes the termination logic resilient to different failure modes. C is wrong because tracking cumulative input tokens is useful for context management but not as a primary termination mechanism; a loop making short tool calls could execute thousands of iterations without approaching the context limit. A is wrong because instructing the model to 'stop after completing the task' is already implied by normal agent design and evidently insufficient when the model cannot determine task completion; a 1,000-iteration fallback is dangerously high and would cause severe cost overruns before triggering. B is wrong because routing every tool result through a secondary evaluator model doubles the API call overhead and adds latency per iteration; it is over-engineered for what is fundamentally a loop control problem.