Claude Code: Added sandbox.allowNestedUserNamespaces for sandboxed Linux commands

What changed

5 points

1. 1

   Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman), but this lets them get around the sandbox's file protections.

   Official wording · c1

   Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections

2. 2

   Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode notices a usage limit that was lifted before its reset.

   Official wording · c2

   Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode ( CLAUDE_CODE_RETRY_WATCHDOG ) notices a usage limit that was lifted before its reset

3. 3

   Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search.

   Official wording · c3

   Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search

4. 4

   Fixed Bash commands on a full disk failing with a raw ENOSPC file path; the error now says the disk is full and that nothing ran.

   Official wording · c4

   Fixed Bash commands on a full disk failing with a raw ENOSPC file path: the error now says the disk is full and that nothing ran

5. 5

   The /artifacts delete confirmation now takes 1 or Enter to keep, 2 to delete, and Esc to cancel; y and n no longer answer it.

   Official wording · c5

   Changed the /artifacts delete confirmation to take 1 or Enter to keep, 2 to delete, and Esc to cancel; y and n no longer answer it

Change details

Fields in this table are taken verbatim from the official text.

Version timeline

Published updates for this tool on this site, newest official date first.

1. 2026-10-20CurrentAdded sandbox.allowNestedUserNamespaces for sandboxed Linux commands
2. 2026-10-14Cache write token fields added to OpenTelemetry api_request event

About this tool

Claude Code

Claude Code is Anthropic's coding agent for reading codebase context, editing files, running commands and assisting development work.

CategoriesAI Coding

View Claude Code details

Related guides

• AI coding tools: choose by workflow, sign-in and costsChoose an AI coding tool by IDE or terminal workflow, sign-in method and billing limits. Compare six listed tools using official sources; no performance tests.
• AGENTS.md vs CLAUDE.md: which one Claude Code reads and how to share one fileBy default Claude Code reads AGENTS.md only when no CLAUDE.md exists; an @AGENTS.md import in CLAUDE.md shares one file. Not tested; check the official docs.
• Claude Code code-review plugin (a plugin command, not a Skill)Official Anthropic code-review plugin: /code-review runs multi-agent PR review, needs the gh CLI, not tested
• frontend-design: avoiding templated defaults in UI designAnthropic's frontend-design skill: plan the visual direction, check it against the brief, avoid templated defaults. Not tested; follow the official text.
• Splitting agent instructions by directory in a monorepoPer-directory AGENTS.md and CLAUDE.md in a monorepo: an example tree, then load scope, nesting and conflict rules per tool. Per official docs, not tested.
• skill-creator: Anthropic's skill for writing, editing and evaluating skillsAnthropic's skill-creator skill: draft a skill, run evals, revise it and tune its trigger description. Not tested here; follow the official text and docs.
• webapp-testing Skill: drive local web apps with PlaywrightOfficial Anthropic webapp-testing Skill: Python Playwright scripts for local web apps, not tested