The native tool-calling loop repeats by having the LLM emit `tool_calls`, executing those tools, observing results, and iterating so that the agent can progress through tool-mediated reasoning cycles.

4. Native tool calling loop: LLM emits tool_calls → execute tools → observe → repeat

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

implements native tool calling via LiteLLM

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md

**Execution Flow:**

— PYRANA_PLATFORM_ARCHITECTURE_REFERENCE.md