event · Story package

LLM 0.32 adds typed events, provider tools, and content-addressable logging

The release expands command-line and Python workflows with separate reasoning traces, provider-side tools, compatible endpoints, and resumable approved tool chains.

Overview

Simon Willison describes LLM 0.32 as adding typed model events, provider-side tools, and content-addressable message logging for command-line and Python workflows.

The release author says the CLI can surface reasoning traces separately, invoke supported provider tools, target OpenAI-compatible endpoints, and resume approved tool chains from stored history. No local installation or compatibility test was performed in the supplied evidence.

Why it matters

Typed events and separate reasoning traces can make model activity easier for applications and operators to inspect.

Provider-tool and compatible-endpoint support may broaden workflows, but actual interoperability depends on provider-specific behavior that remains untested here.

Key facts

  • LLM 0.32 adds typed model events, provider-side tools, and content-addressable message logging.

    Simon Willison

  • The release author says the CLI can separate reasoning traces and invoke supported provider tools.

    Simon Willison

  • The release author says workflows can target OpenAI-compatible endpoints and resume approved tool chains from stored history.

    Simon Willison

Latest update

No public update is available.

Full timeline

No public timeline entries are available.

Sources

Blogs

Open questions

  • Which providers and tools support the new event and tool interfaces completely?
  • How portable are stored histories and resumable tool chains across compatible endpoints?
  • What security boundaries govern replaying approved tool chains?

Related stories

No related stories are listed.

Roundup appearances

No roundup appearances are available.

View story activity