---
title: 'In the News: August 5, 2026, Morning'
description: "Rust adopts an LLM policy that permits review but not creation, plus a Claude Code isolation fix and a look at MCP's simpler stateless spec."
canonical_url: 'https://darkfactory.dev/news/2026-08-05-morning'
markdown_url: 'https://darkfactory.dev/news/2026-08-05-morning.md'
collection: news
date_published: '2026-08-05T10:30:00-04:00'
date_modified: '2026-08-05T10:30:00-04:00'
---

# In the News: August 5, 2026, Morning


Rust has published what it will and will not accept from a language model. Claude Code closed a containment gap, while a protocol change made a controlled agent tool surface easier to build.

## 1. Rust adopts a policy: LLMs may review, not create

**[rust-lang/rust is adopting an LLM policy](https://blog.rust-lang.org/inside-rust/2026/08/05/rust-langrust-is-adopting-an-llm-policy/)** · Jynn Nelson, Rust project · Inside Rust Blog, August 5, 2026

Five teams inside the Rust project have adopted an LLM usage policy for the `rust-lang/rust` monorepo, written by Nelson. The policy summarizes itself in one line: "It's fine to use LLMs to answer questions, analyze, distill, refine, check, suggest, review. But not to create." Disclosure is mandatory for public LLM-assisted content, LLM-generated code changes are held to a higher bar than human-authored ones (tests required, soundness-critical changes strongly discouraged even for domain experts), and reviewers may close non-compliant PRs without further discussion. Nelson names the pressure that forced the issue: at the time of writing there are 1,281 open PRs against the repository, and "with LLMs, none of these signals are reliable" that a polished, well-tested PR represents someone who understands their own code and intends to stick around.

**Why it matters:** Rust is the fourth institutional AI-contribution policy Dark Factory has tracked, after Codeberg, Debian and GCC, and the first to publish its reasoning at length instead of just the rule. If your factory contributes upstream to projects that have not yet drawn this line, expect them to draw it soon, and expect the Rust framing, LLMs may critique but not originate, to be the template they borrow.

## 2. Claude Code closes a worktree isolation gap

**[Claude Code changelog, version 2.1.222](https://code.claude.com/docs/en/changelog)** · Anthropic, first-party release notes · August 4, 2026

Version 2.1.222 fixed two containment gaps in the same release. Worktree-isolated sessions and their subagents could run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type. Separately, PreToolUse auto-allow hooks were bypassing tool restrictions inside background agent tasks such as summaries, compaction and renames. The same release removed the "ultraplan" feature and changed Remote Control so a repository's own settings file can no longer silently turn it on, only off.

**Why it matters:** If your operating assumption is that a git worktree keeps a background agent's mistakes off your main checkout, that assumption did not hold for subagents until yesterday. Anyone running parallel or unattended Claude Code sessions on the strength of worktree isolation should treat this as the point their containment story actually became true, not before.

## 3. Stateless MCP has recaptured my interest

**[Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)](https://simonwillison.net/2026/Jul/31/stateless-mcp/)** · Simon Willison, independent developer (Datasette, LLM) · July 31, 2026

The July 28 Model Context Protocol specification collapses MCP's stateful two-request handshake, initialize a session, then call the tool, into a single stateless HTTP call, removing the need for a server to track session IDs or route repeat calls to the same backend. Willison built three tools against the new spec inside a week to test the claim rather than take it on faith: `mcp-explorer`, a CLI that lists and calls tools on any MCP server through `uvx` with no install step; `datasette-mcp`, a Datasette plugin exposing three SQL tools over MCP; and an alpha `llm-mcp-client` plugin for his own LLM tool, demonstrated querying his blog's database and returning a correct count of 151 notes. His stated reason for leaning back into MCP over giving an agent a shell and `curl`: "MCP tools are easier to audit and control, and simple enough that smaller models that run on a laptop can still drive them reasonably well."

**Why it matters:** Shell access is powerful and hard to secure, while a fixed tool surface is auditable and controllable. Stateless MCP makes the controlled option measurably cheaper to implement correctly on both the client and server side.