[BUG] Webfetch is still requiring permission for each individual website

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

Every web page fetch during a research task triggers its own approval prompt, and “Always allow for this website” only covers that one domain. A normal research task touches a dozen or more sites (wire services, SEC filings, trade press, company pages), so I end up clicking through prompts constantly and can’t leave the task running while I do something else. I can’t find any setting to approve fetches for all sites or for the length of a conversation, making agentic research tasks outside of deep research virtually impossible and exhausting. Please add an option to approve web fetches for a whole conversation or across all sites, or stop requiring per-domain approval for read-only fetches of public pages.

What Should Happen?

Should autoapprove safe website scraping just as it did before.

Error Messages/Logs

Steps to Reproduce

In claude.ai do a research / web search intensive task without deep research

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.107

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_