---
type: "post"
stable_id: "post:simon-llm-032-eventful-tool-runtime"
slug: "simon-llm-032-eventful-tool-runtime"
title: "LLM 0.32 Turns Tool Calls Into A Stored, Resumable Event Stream"
description: "LLM 0.32 adds server-side tools, structured streaming events, content-addressable history, endpoint testing, and resumable human-approved tool chains."
retrieval_nugget: "The release is a runtime-state change: reasoning, text, tool calls, images, and approval pauses can be represented as structured events and persisted without duplicating conversation history."
published_at: "2026-08-04"
updated_at: "2026-08-05"
record_date: "2026-08-04"
date_kind: "published_at"
topics: ["developer-tools","tool-use","mcp","agent-runtime"]
entities: ["LLM","Simon Willison","OpenAI","Anthropic"]
source_urls: ["https://simonwillison.net/2026/Aug/4/new-release-of-llm","https://simonwillison.net/2026/Aug/4/llm-anthropic"]
source_format: "article"
editorial_timing: {"lane":"urgent_half_hour","scheduled_at":"2026-08-06T13:30:00+03:00","real_news_delta":"fresh release, incident, or legal escalation"}
visual_decision: {"status":"not_applicable","reason":"the release contains several independent runtime and plugin changes; a single diagram would imply a false unified pipeline","reviewed_by":"codex"}
schema_version: "newruntime-agent-readable-v0.2"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/posts/simon-llm-032-eventful-tool-runtime/","markdown":"https://newruntime.com/posts/simon-llm-032-eventful-tool-runtime.md","json":"https://newruntime.com/posts/simon-llm-032-eventful-tool-runtime.json"}
---

# LLM 0.32 Turns Tool Calls Into A Stored, Resumable Event Stream

## Retrieval answer

The release is a runtime-state change: reasoning, text, tool calls, images, and approval pauses can be represented as structured events and persisted without duplicating conversation history.

Simon Willison released LLM 0.32 with a cluster of changes that make the CLI and Python library look more like a small inspectable agent runtime.

OpenAI server-side Code Interpreter and Web Search are exposed as tools. The llm-anthropic 0.26 plugin adds Claude 5 plus Web Search, Web Fetch, Code Execution, and Anthropic MCP. `llm openai endpoint` can probe OpenAI-compatible endpoints without adding those checks to the normal conversation log.

The deeper change is structured state. `stream_events()` exposes reasoning, text, tool calls, and images as typed events. A content-addressable message store avoids repeating the same history records, and tool chains can pause for human approval and resume from stored history instead of reconstructing the entire run in a fresh prompt.

For operators, this is a useful direction: tool use becomes replayable evidence rather than transient terminal output. Update with `pip install -U llm`; Anthropic users can update the plugin with `llm install -U llm-anthropic`.
