← AUTOMATER NEWSROOM

Claude Code 2.1.330 Makes Destructive rm Ask First, and Unattended Runs Refuse Instead of Waiting

Claude Code v2.1.330 changes four defaults that unattended lanes depend on: destructive rm now asks and is refused when nobody can answer, scheduled tasks and /loop reach 30 days, a deniedMcpServers name blocks only one connector, and claude -p exits 1 on a full disk.

Two panels comparing the same rm -rf ./build command in an interactive Claude Code session, where a person approves it, and in a headless lane, where no prompt can be answered and the command is refused. Three cards below summarize the 30-day scheduled task ceiling, the narrowed deniedMcpServers name rule and the new exit 1 on a full disk.Two panels comparing the same rm -rf ./build command in an interactive Claude Code session, where a person approves it, and in a headless lane, where no prompt can be answered and the command is refused. Three cards below summarize the 30-day scheduled task ceiling, the narrowed deniedMcpServers name rule and the new exit 1 on a full disk.
Original diagram summarizing the v2.1.330 default changes described in Anthropic's GitHub release notes: an approval prompt that a headless lane cannot answer becomes a refusal, alongside the scheduled-task, deniedMcpServers and full-disk exit changes.

Anthropic published Claude Code v2.1.330 on Nov. 20 at 22:32 UTC. Past the long list of fixes, four entries change default behavior in ways that decide whether an unattended lane finishes its work, refuses a step, or quietly stops enforcing a block you wrote months ago. If you run claude -p in CI, keep scheduled tasks alive, or govern MCP servers through managed policy, this release changes what asking means when nobody is at the keyboard.

GitHub release page for anthropics/claude-code v2.1.330, marked Latest and released 20 Nov 22:32 by claude-code-publisher, showing the release header and the opening entries of the What's changed list.
GitHub's release page for anthropics/claude-code v2.1.330, captured viewport: the header shows v2.1.330 marked Latest, released 20 Nov 22:32 by claude-code-publisher, commit e791a1c, and the What's changed list opens with the Enterprise Admin Console sign-in, the easel chart mod, CLAUDE_CODE_FULL_SIGN_IN_LINK, the self-hosted runner --start-dir flag and two runner metrics additions, followed by the first Fixed entries; the rm approval, 30-day scheduled task, deniedMcpServers and full-disk exit entries this article covers lie further down the page and are not in this viewport. · Original source

A destructive rm now asks, and an unattended lane refuses

The v2.1.330 release notes say that “more rm commands aimed at the root, home, a top-level folder or the working folder” now ask for approval, and that “where nobody can answer, they’re refused.” That is a fail-closed default: the same command that pops a prompt in your terminal becomes a hard stop in a headless run.

The mechanism is already documented. The CLI reference describes --permission-prompts, where passing none means nobody answers and Claude Code denies the prompt instead of hanging. Version 2.1.330 widens the set of commands that reach that gate, so lanes that previously ran a wide rm untouched will now stop mid-job.

Flow diagram: an rm command aimed at root, home, a top-level folder or the working folder now triggers an approval request. If someone can answer, such as in an interactive terminal, Remote Control, a prompt tool or an SDK callback, the command runs after approval. If nobody can answer, as in claude -p with --permission-prompts none, a scheduled task or a runner, the command is refused and the lane stops.Flow diagram: an rm command aimed at root, home, a top-level folder or the working folder now triggers an approval request. If someone can answer, such as in an interactive terminal, Remote Control, a prompt tool or an SDK callback, the command runs after approval. If nobody can answer, as in claude -p with --permission-prompts none, a scheduled task or a runner, the command is refused and the lane stops.
Original diagram of the v2.1.330 approval path for destructive rm commands, based on the change entry in Anthropic's GitHub release notes and the --permission-prompts flag documented in the Claude Code CLI reference.

If your lane legitimately deletes a build directory, write the allowance down rather than raising the permission mode:

{
  "permissions": {
    "allow": [
      "Bash(rm -rf ./build)",
      "Bash(rm -rf ./tmp/cache)"
    ]
  }
}

Put that in ~/.claude/settings.json, in the shared .claude/settings.json, or in managed settings. The settings documentation notes that permissions.allow lists merge across files instead of overriding each other, and that a standing approval saved to .claude/settings.local.json applies without the workspace-trust step while the file stays untracked. Managed settings still sit above everything you write locally, so an organization deny rule wins. Test the exact command string your lane issues: a pattern that does not match still ends in a refusal.

Scheduled lanes stretch from 7 days to 30, but only new ones

Recurring scheduled tasks and /loop now run “up to 30 days instead of 7 while their session keeps running,” and they say when they end. Tasks created before this release still stop at day 7. The overview documentation splits the surface into cloud scheduled tasks, desktop scheduled tasks and /loop inside a CLI session, so the lane you care about may live in any of the three.

Timeline diagram comparing two bars on a 30-day axis: tasks created before Claude Code 2.1.330 still end at day 7, while tasks created from 2.1.330 run up to day 30 while the session keeps running and report when they end.Timeline diagram comparing two bars on a 30-day axis: tasks created before Claude Code 2.1.330 still end at day 7, while tasks created from 2.1.330 run up to day 30 while the session keeps running and report when they end.
Original timeline of the recurring scheduled task and /loop change in Anthropic's v2.1.330 release notes, showing that the 7-day cap still applies to tasks created before the release while new tasks reach 30 days.

Two consequences follow. A lane you want alive past day 7 has to be recreated after the upgrade, not merely left running. And a month-long unattended lane is a month of spend and a month of accumulated state, so cost caps and notification paths sized for a weekly job need resizing. A related fix matters here: the notice for a skipped scheduled task that names no organization now tells you to start Claude Code with --resume, because /resume inside a running session does not run the task.

deniedMcpServers names got narrower

This is the quietest and most consequential governance change in the release. A deniedMcpServers entry that names a connector now “hides only the named claude.ai connector, not others at its URL; to block them all, deny its exact URL.” The MCP documentation shows the name form, where a serverName entry of "claude.ai Slack" blocks the Slack connector, and it also warns that a server blocked by an allowlist or denylist in managed MCP configuration “is hidden from both commands rather than shown with this status.”

Read those two sentences together. After this upgrade a name-based block may cover less than it did, and claude mcp list will not tell you, because blocked servers are hidden rather than labelled. If your policy leans on connector names, inventory the denylist and convert anything meant to cover a shared endpoint into an exact-URL denial. The same release stops a spurious “MCP server blocked by enterprise policy: easel” warning from printing at every start when your allowlist or denylist excludes the new built-in chart tool, which stays blocked.

Full disks now fail loudly

claude -p used to exit 0 with no message when its output went to a file on a full disk. It now prints an error and exits 1, with the caveat in the release notes that “a full NFS export may go unnoticed.” Expect jobs that were falsely green to turn red, and treat that red as the fix working rather than a new regression. Self-hosted runners get the parallel change: a runner that starts on a full disk now waits for room and exits 1 after a minute with no session, instead of claiming sessions and failing them.

Two more lines belong in the same audit. claude --teleport now prints the git commands for switching branch instead of running them in some setups, and with -p it exits 1 until you switch. And incomplete backups of ~/.claude.json no longer displace good ones when the disk fills.

Enterprise sign-in and runner transcripts

Signing in to an organization managed in Anthropic’s Enterprise Admin Console now applies that organization’s settings and uses its cloud provider or gateway after claude auth login. Under the precedence rules in the settings documentation, managed keys beat anything in your own files, so confirm with /status that the Setting sources line names the source you expect before you debug a policy that seems ignored.

On self-hosted runners, Bash commands now skip the file diff when nothing needs it, “so transcripts can lack it”; set bashEditDiffEnabled to true in managed settings if your audit trail requires every diff. A 403 from an IP allowlist is no longer logged as a bad secret or token, which will break log alerts that match the old wording. Warn mode for repository settings no longer stops at the first finding either, reporting up to 50 per session.

Before you roll it out

Change in 2.1.330 Who feels it What to do
Destructive rm asks, and is refused when nobody can answer CI, cron, self-hosted runners Add an allow rule for each rm the lane needs
Scheduled tasks and /loop reach 30 days Long-lived lanes Recreate lanes that must outlive day 7; resize spend caps
deniedMcpServers names hide one connector Orgs with connector denylists Deny the exact URL to keep blocking everything behind it
claude -p exits 1 on a full disk Pipelines writing output to a file Expect newly red jobs; watch disk, distrust NFS
Runner transcripts can omit Bash diffs Audit and compliance lanes Set bashEditDiffEnabled in managed settings

Anthropic also reverted 2.1.329’s removal of the automatic retry when max_tokens exceeds a model’s or gateway’s limit, so if you held back from 2.1.329 for that reason, 2.1.330 is the version to move to. This is the second release in a row that tightens an unattended default: Claude Code 2.1.325 made sandboxed Bash ask for permission by default. For scheduling mechanics see Claude Code cron job setup, for headless scripting see Claude Code headless mode, and for connector scopes see Claude Code MCP setup.

Sources

  1. Release v2.1.330 · anthropics/claude-code · GitHub
  2. Overview - Claude Code Docs
  3. Settings files and precedence - Claude Code Docs
  4. Connect Claude Code to tools via MCP - Claude Code Docs
  5. CLI reference - Claude Code Docs