在脚本的shebang行中使用LLM

AI 导读

本文介绍了一种创新方法，将LLM工具直接嵌入脚本的shebang行中执行指令。通过LLM的fragments模式，shebang行可执行简单任务，如生成SVG图像；使用-T选项能调用外部工具（如llm_time）创作包含当前时间的俳句；更复杂的是运行YAML模板，其中定义了Python函数作为工具进行数学计算，示例中演示了计算2344乘以5252加134的过程，并通过调试输出展示了分步结果，最终得到12,310,822。这展现了LLM作为脚本解释器的强大扩展性，能够支持从内容生成到数据查询的多样化任务。

推荐理由

Simon 这个 shebang 技巧让 LLM 直接变成脚本解释器，虽然是极客玩法，但对常写自动化脚本的开发者来说可以直接抄走，创意很妙。

正文

TIL Using LLM in the shebang line of a script — [This comment](https://news.ycombinator.com/item?id=48073246#48090590) on Hacker News inspired me to investigate patterns for using my [LLM](https://llm.datasette.io/) CLI tool in a shebang line:

Kim_Bruning on Hacker News:

But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) [...]

This inspired me to look at patterns for doing exactly that with LLM. Here's the simplest, which takes advantage of LLM fragments:

#!/usr/bin/env -S llm -f
Generate an SVG of a pelican riding a bicycle

But you can also incorporate tool calls using the -T name_of_tool option:

#!/usr/bin/env -S llm -T llm_time -f
Write a haiku that mentions the exact current time

Or even execute YAML templates directly that define extra tools as Python functions:

#!/usr/bin/env -S llm -t
model: gpt-5.4-mini
system: |
  Use tools to run calculations
functions: |
  def add(a: int, b: int) -> int:
      return a + b
  def multiply(a: int, b: int) -> int:
      return a * b

Then:

./calc.sh 'what is 2344 * 5252 + 134' --td

Which outputs (thanks to that --td tools debug option):

Tool call: multiply({'a': 2344, 'b': 5252})
  12310688

Tool call: add({'a': 12310688, 'b': 134})
  12310822

2344 × 5252 + 134 = **12,310,822**

Read the full TIL for a more complex example that uses the Datasette SQL API to answer questions about content on my blog.