ReleaseBytes
anthropic Claude Code Releases · · 2.1.219

Claude-Code v2.1.219: Opus 5 default, stricter sandbox, nested subagents

sdkai
feature patch

Claude-Code version 2.1.219 updates the default Opus model to Claude Opus 5, offering a 1M context window and a faster mode. New sandboxing features enhance security by strictly allowing hosts, and subagent nesting is deepened to depth 3, benefiting complex workflow execution. These changes primarily impact developers and architects working with Anthropic's Claude models and require attention to updated security settings and workflow design.

  • →Added Claude Opus 5 (claude-opus-5), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok
  • →Added sandbox.network.strictAllowlist setting to deny non-allowlisted hosts for sandboxed commands without prompting
  • →Added the current default workflow size to the running-workflow status line, with a pointer to /config for changing it
  • →Fixed claude -p text output dropping the answer already produced when a turn dies on a mid-stream API error
  • →Fixed the Fable model row showing "Requires usage credits" for plans that include it, when a stale cache had baked the label in
Features (9) ›
  • Added Claude Opus 5 (claude-opus-5), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok
  • Added sandbox.network.strictAllowlist setting to deny non-allowlisted hosts for sandboxed commands without prompting

  • Added DirectoryAdded hook that fires after /add-dir or the SDK register_repo_root control request registers a new working directory mid-session

  • Added mcp_server_errors to the headless stream-json init event, listing --mcp-config entries skipped by config validation; terminal runs print a startup warning

  • Added the workflowSizeGuideline settings key so the advisory Dynamic workflow size guideline can be set from any settings file; the /config row is hidden while one does

  • Added nested subagent forwarding in stream-json: subagents spawned at depth-2+ now appear when --forward-subagent-text is set, keyed by their spawning Agent tool_use id

  • Added HTTP status and error text to claude mcp list and /mcp when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace

  • Added structured failure categories to self-hosted runner spawn and session failures, so hook errors, runner crashes and config errors can be told apart

  • Added the current default workflow size to the running-workflow status line, with a pointer to /config for changing it
Enhancements (6) ›
  • Improved the "Remote Control is only available via api.anthropic.com" error to name the specific setting that caused it
  • Improved claude --teleport to show which repo your current checkout points at when it doesn't match the session's repo

  • Changed dynamic workflows to default to a medium size guideline (aim for fewer than 15 agents); pick another size or unrestricted with Dynamic workflow size in /config

  • Changed managed MCP allowlist/denylist ${VAR} entries to resolve from the startup environment and managed-settings env instead of settings-file env

  • Changed the /model picker to highlight only the newest model's name, so the highlight marks the new release rather than an arbitrary subset of the list

  • Updated the claude-api skill to default to Claude Opus 5, with a migration path from Opus 4.8
Fixes (10) ›
  • Fixed claude -p text output dropping the answer already produced when a turn dies on a mid-stream API error

  • Fixed a permission you approved while a self-hosted runner was restarting being dropped when the session resumed, so the approved action now runs

  • Fixed the Fable model row showing "Requires usage credits" for plans that include it, when a stale cache had baked the label in

  • Fixed a SIGTERM arriving while a self-hosted runner was starting up leaving a stale active row until the lease expired; it now deregisters cleanly

  • Fixed the /model picker showing the merged Opus row as plain "Opus" instead of "Opus (1M context)"
  • Fixed copy-on-select inside GNU screen printing base64 into the terminal instead of copying the selection
  • Fixed Remote Control clients keeping a stale fast-mode status after a model switch, reconnect, or failed org check

  • Fixed CLAUDE_CODE_GIT_BASH_PATH on Windows exiting or being used as bash when the path isn't a bash/sh binary; it's now ignored with a warning

  • Fixed Vim mode: pressing ← on an empty prompt now returns to the agent view from NORMAL mode, not just INSERT
  • Fixed screen-reader mode rewriting the entire input line on every keystroke instead of echoing only the typed character
Read the original announcement →

https://github.com/anthropics/claude-code/releases/tag/v2.1.219

Related releases