Summary & Key Takeaways ​

• llm-echo is a debug plugin that repeats back prompts without involving an actual LLM.
• The new release updates simulated token usage counts.
• It now accounts for tool calls, system prompts, and reasoning tokens.
• This helps developers understand token consumption in complex LLM interactions.

Our Commentary ​

Simon Willison's llm-echo plugin is a neat little utility for debugging LLM interactions. We appreciate the attention to detail in simulating token usage, especially with the increasing complexity of tool calls and system prompts. It's a small but useful improvement for anyone deep in LLM development.