Five Components of Context

With each LLM call, the context consists of five parts: System Prompt, Tool Definitions, User Message, Model Responses (reasoning + content + tool_calls), and Tool Execution Results. The first two are a static prefix, unchanged throughout the dialogue; the last three are a dynamic trajectory. Ablation demonstrates the indispensability of each: without Tool Definitions the agent cannot act; without Tool Results it loops; without Reasoning decisions contradict each other.

Related: [Agent Cycle in Code], Chat Template, [Context Engineering]