llm-echo 0.5 counts tool calls, system prompts and reasoning tokens in simulated usage
What happened
On October 19, 2026, Simon Willison released llm-echo 0.5, a debugging plugin that offers a "model" with no LLM behind it, echoing the prompt back unchanged. The update reworks the simulated token usage counts to include tool calls, system prompts and reasoning tokens. The example command in the post is `llm -m echo 'hi there' -o thinking 1 --usage`, which shows 2 input tokens and 24 output tokens. Those numbers come from the plugin's simulation, not a real LLM call.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- Simon Willisonllm-echo 0.5
Simon Willison 发布 llm-echo 0.5，这个调试插件提供一个不涉及 LLM 的“模型”，只把收到的提示词原样回显。新版本更新了模拟 token 用量统计，将工具调用、系统提示词和推理 token 纳入计算。示例中 `llm -m echo 'hi there' -o thinking 1 --usage` 显示 2 input、24 output。
Heat over time
Not enough continuous observations to draw a trend yet.