Cheaper LLM labelling

A developer used GPT 5.6 Luna via Simon Willison's `llm` CLI tool to label git commits as "maintenance" or "new development", reporting that the model matched their own manual labels across the entire test set before rolling the classifier out more widely. The implementation calls `llm -m openrouter/openai/gpt-5.6-luna` from a Perl script using `open2`, with an earlier version of the loop retrying failed requests a few times.

I have a small project where I needed to label commits as either “maintenance” or “new development”. The obvious way to do it is with a cheap but relatively capable LLM, like GPT 5.6 Luna. I tested it on a small set of commits and manually verified its labelling, and it emitted the same label as I would have for the entire test set. That was good enough for me to roll out on a wider scale. If we have Simon Willison’s llm CLI tool installed and you should – it’s great , we can call it in a pipe from Perl, and read its response. My script had a loop that retried the request a few times, but without that bookkeeping, the code for this is simple enough. php sub classify { my $msg = @ ; my $pid = open2 my $output, my $prompt, 'llm -m openrouter/openai/gpt-5.6-luna' ; print $prompt prompt template $msg ; close $prompt; Slurp the entire response and chomp off the trailing newline. chomp my $result = do { local $/; <$output } ; waitpid $pid, 0 ; return $result; }