Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-05 · high
Reasoning output now streams to stderr instead of stdout, letting reasoning models run cleanly inside Unix pipes for the first time.
Why now: Willison published the 0.32 release notes on August 4.
LLM 0.32 lets tools pause mid-chain and wait for a human to approve before continuing, per Simon Willison's August 4 release notes. He's calling it the most significant version since the project launched, and Willison doesn't reach for that word lightly. For anyone wiring LLM into a script that touches real systems, that's the difference between a demo and something safe to leave unattended.
A tool can raise llm.PauseChain to stop a chain, and it resumes later from the pending call instead of replaying steps that already ran. Every call now carries a tool_call_id for tracking.
Prompts and responses are now typed Part objects, covering text, reasoning, tool calls, tool results, and attachments, with messages= replacing prompt= and system= arguments. Provider-hosted tools invoke straight from the command line, like -T WebSearch or -T 'CodeInterpreter(memory_limit="4g")', and llm tools -m MODEL lists what a given model supports.
The SQLite log behind every session now stores messages once, content-addressed by hash, instead of duplicating JSON on each append, per the release notes. A new message_tree view renders whole threads as indented outlines.
The quieter change is reasoning output moving to stderr, suppressible with -R. That's the fix Willison undersells. A reasoning model can now sit inside a chain of piped shell commands without dumping its thinking into stdout. That's what makes 0.32 worth adopting, not the approval prompts.
Each link below shares sources, entities, or timing with this story.
Simon Willison released datasette-agent / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released datasette-agent); both cover LLM, PauseChain, Simon Willison; reported by the same outlet (simonwillison.net).
Simon Willison released LLM / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM, Model, Simon Willison; reported by the same outlet (simonwillison.net).
Simon Willison released LLM / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover August, JSON, LLM; overlapping topics (agent, prompt).
Simon Willison released LLM / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover Model, Simon Willison; reported by the same outlet (simonwillison.net).
Simon Willison uses Claude Code / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison uses Claude Code); both cover LLM, Model; overlapping topics (agent, model, tool).
Simon Willison released LLM / Shared entities / Same source domain / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover JSON, LLM, Simon Willison; reported by the same outlet (simonwillison.net).
Linked by a graph relationship (Simon Willison released LLM); both cover CLI, JSON, Simon Willison; reported by the same outlet (simonwillison.net).
Simon Willison uses Fable / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison uses Fable); both cover August, Simon Willison; reported by the same outlet (simonwillison.net).