Agents & InferenceSimon Willison

llm 0.32.1

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

Match the models (Optional)

Which model wrote which summary? Select a matchup mapping below before voting.

Summary A

Fresh installs of the LLM command-line utility broke because the OpenAI Python library dropped its dependency on httpx, exposing a broken transitive dependency. To avoid CI/CD and deployment failures, you must immediately upgrade to LLM version 0.32.1 to pin the OpenAI dependency below version 3, and prepare your environments for the upcoming migration to httpx2 in version 0.33.