WingNews logo WingNews
top | item 45418162

(no title)

icelancer | 5 months ago

Huh. Doesn't work over here.

---

SYSTEM:

Got it. Those are the setup commands for Simon Willison's LLM CLI tool, which lets you interact with language models from the command line.

The -e flag installs it in editable mode, and [test] pulls in the test dependencies. Are you running into any issues with the installation or tests? What are you working on with the LLM library?

USER: Correct. You run them using your code tooling.

SYSTEM:

Realized inability to execute requested Python commands.The user is telling me to run these commands using my code tooling. They want me to actually execute this. Let me think about what tools I have available:

I have the repl tool which runs JavaScript code in a browser environment I have artifacts for creating code/documents I have web_search and web_fetch

The user wants me to:

Checkout https://github.com/simonw/llm Run pip install -e '.[test]' Run pytest

But I don't have a tool that can:

Clone git repositories Run shell commands like pip or pytest Execute Python code in a command-line environment

The repl tool is JavaScript-only and runs in a browser environment, not a server environment where I could run shell commands. I should clarify that I don't have the capability to run shell commands, install Python packages, or execute pytest. I can only run JavaScript code in a browser environment via the analysis tool. I need to be direct and clear about this limitation, following the user's preferences to eliminate filler and be straightforward.I don't have tooling that can run shell commands, clone git repos, install Python packages, or execute pytest. My only code execution environment is a JavaScript browser REPL. I can't run pip, pytest, or any command-line tools. I can only execute JavaScript code in a sandboxed browser environment. What were you hoping to accomplish? Do you need help understanding the test setup, or were you expecting different capabilities?R

discuss

order

icelancer|5 months ago

When pressed:

---

My execution environment is a browser-based JavaScript sandbox. I don't have Python, Node.js shell access, pip, git, or pytest capabilities.

Simon's post may have been referring to a different deployment or feature set that I don't currently have access to. My only code execution is the JavaScript REPL I just demonstrated.

What specifically are you trying to accomplish with the llm library tests? I can help with that in other ways.

EDIT: Ah, in Settings you have to disable the Analysis tool and enable Code Interpreter. You cannot have both enabled.