llm-echo 0.5 发布：模拟 token 用量计入工具调用与推理 token

llm-echo 0.5

AI 导读

Simon Willison 发布 llm-echo 0.5，这个调试插件提供的“模型”不调用任何 LLM，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、system prompt 和推理 token 一并计入。示例中 `llm -m echo 'hi there' -o thinking 1 --usage` 显示 2 input、24 output token。

正文

I'm working towards a new LLM release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it. The new release now updates the simulated token usage counts to take tool calls, system prompts, and reasoning tokens into account.

Example usage:

uvx --with llm-echo llm -m echo 'hi there' -o thinking 1 --usage

Outputs:

First I consider the prompt, then I decide what to say.
{
  "prompt": "hi there",
  "system": "",
  "attachments": [],
  "stream": true,
  "previous": []
}
Token usage: 2 input, 24 output

来源：Simon Willison · simonwillison.net