llm-echo 0.5 发布：模拟 token 统计纳入工具调用与推理 token

AI 摘要

Simon Willison 为其 LLM 工具链中的调试插件 llm-echo 发布 0.5 版本。该插件提供一个不调用真实 LLM、仅回显输入提示的模拟模型，新版本更新了模拟 token 用量统计，将工具调用、系统提示和推理 token 纳入计算。此举服务于作者正在筹备的新 LLM 版本发布，便于测试 PR 时更准确地模拟用量。

正文节选

18th October 2026 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, t

发布时间：2026-10-19 07:16

抓取时间：2026-10-19 08:02

来源机构：Simon Willison