█

AI/TLDR

Anthropic · 2026-11-19 · notable

Claude Code 2.1.328 — auto mode on cloud providers, a stricter /code-review

In short

Claude Code 2.1.328 brings auto mode to Opus 4.6 and Sonnet 4.6 on Bedrock, Google Cloud's Agent Platform, Foundry and the Claude apps gateway, and narrows /code-review to bugs and CLAUDE.md violations.

Anthropic · 2026-11-19 · 1 source checked

Claude Code repository card on GitHub

Claude Code 2.1.328 extends auto mode to third-party clouds and turns /code-review into a bugs-only pass.

What is it?

Auto mode now works for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and the Claude apps gateway in Claude Code 2.1.328, and interactive sessions with no permission mode start in it. /code-review on most models now reports only bugs and CLAUDE.md violations, labels each finding Important, Pre-existing or Nit, and ends with a suggested fix.

How does it work?

Hooks gain `"onFailure": "block"` for `mcp_tool` hooks, so a failed hook call blocks the action as it already did for command and HTTP hooks. Self-hosted runners get new flags such as `--repository-folder` and `--hook-label` plus orchestrator metrics. Most of the release is fixes, many for Code Mode scripts, which also lose a 0.75-second pause after most scripts in auto and bypass modes.

Why does it matter?

Teams that reach Claude through a cloud provider get the same fewer-prompts workflow as direct API users; `disableAutoMode` turns it off. Reuse and simplification suggestions move out of /code-review into /simplify, so review output gets shorter and more focused on real defects.

Who is it for?

Claude Code users and admins on cloud providers

Try it

npm i -g @anthropic-ai/claude-code@2.1.328

Sources

Tags

  • claude-code
  • anthropic
  • coding-agent
  • cli
  • auto-mode
  • code-review
  • code-mode
  • hooks
  • mcp
  • self-hosted-runner
  • bedrock
  • developer-tools
  • release

← All releases · Learn AI