Version 2

On April 29, 2026, Simon Willison released two alpha versions of his popular llm CLI tool and Python library in rapid succession, marking a significant architectural overhaul. The headline change in 0.32a0 is the replacement of the previous prompt/response model with a message-sequence API that allows full prior conversations to be injected without requiring SQLite as an intermediary.[1] This is a backwards-compatible refactor, but a major one that reshapes how the library models both inputs and outputs.

The new streaming API is perhaps the most technically ambitious aspect of the release: responses are now exposed as typed event parts — text, tool_call_name, tool_call_args, and reasoning — enabling downstream consumers to handle the mixed-type outputs increasingly common from modern models like Claude.[1] Willison frames this as a direct response to the reality of contemporary LLMs: "Many of today's models return mixed types of content. A prompt run against Claude might return reasoning output, then text, then a JSON request for a tool call, then more text content." The CLI immediately leverages this by rendering reasoning/thinking tokens in a distinct color and routing them to stderr, keeping piped output clean.[1] A new to_dict/from_dict serialization mechanism rounds out the release, letting Python API users store and restore responses in any storage layer rather than being coupled to SQLite.[1]

The 0.32a1 patch followed the same day, fixing a bug in which tool-calling conversations were not correctly reinflated from SQLite storage — a regression introduced by the architectural changes in 0.32a0.[2] The release sequence (alpha → same-day bugfix alpha) is consistent with Willison's iterative, public development style.

Since the initial synthesis, the story has begun attracting third-party amplification: tech aggregators Let's Data Science and daily.dev have indexed and republished the 0.32a0 announcement.[3][4] The official llm.datasette.io changelog and documentation pages have also been indexed by the pipeline's searches.[5][6] However, none of these new items contain extracted claims or original analysis — they are either re-aggregations of Willison's own post or reference documentation. The substantive discourse on the 0.32 release remains entirely driven by Willison himself; community and plugin-author reactions are still absent from coverage.