Claude Code 2.1.326 asks for approval more often and refuses writes to sign-in files

Claude Code 2.1.326 tightens its safety checks: more Bash and file-write actions need approval, and writes to credential files are refused. A useful read for anyone running AI coding agents on a product.

Anthropic released Claude Code 2.1.326 on 16 November 2026. The headline is not a new feature. It is that the AI coding agent now stops and asks more often.

What the release notes say

Why a non-developer should care

This follows 2.1.325 on 13 November, which also changed sandbox and git permission behaviour. The direction is consistent: vendors are making AI coding agents more cautious by default. For anyone commissioning software, that is reassuring, but it also means unattended automated runs may now pause waiting for a human.

So what

If a supplier says AI agents work on your codebase, ask how permissions are configured, who approves risky actions, and how secrets are kept away from the agent. Good answers are specific. Our AI-assisted development work is built around that kind of controlled workflow. To discuss it, start a project.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work