visualize the complete Agent Loop with an interactive UML

[EnggQasim]

🤔 Why we need this

The “Agent Loop” is the SDK’s most complex subsystem:

1. It spans ~2 000 lines across run.py, guardrails, hand-offs, and streaming helpers.
2. Contributors often ask “Where do guardrails fire?” or “How does the Runner decide between tool-calls and hand-offs?”

A single picture out-ranks a thousand words; the diagram turns that spaghetti into a map:

Runner ──▶ Agent ──▶ Model ──▷ Response
  ▲           │           │
  │           ▼           ▼
Guardrails ◀──┘     Tool-Calls / Handoffs