How do you prevent an Agent from getting stuck in an infinite loop (e.g., Tool A keeps calling Tool B, which calls Tool A)?

What does a production-grade observability stack for AI agents look like? What metrics, logs, and traces are essential? How would you debug a scenario where an agent produces correct outputs 95% of the time but fails unpredictably?

Why do we typically include a 10–20% overlap between text chunks? What happens to the retrieval quality if the overlap is zero?

Agents generate a lot of "internal thought" and tool logs. How do you keep the context window from filling up with irrelevant logs during a long multi-step task?