Claude Code v2.1.222

v2.1.222
Changed 4
  • Auto mode safety improved: messages sent to other agent sessions via SendMessage are now evaluated by the permission classifier before dispatch
  • Improved the refusal when Claude tries to invoke a skill with disable-model-invocation; Claude is now told to ask you to run the skill instead of replicating its workflow
  • The /diff view, the Remote Control workspace diff, and file-edit diffs in Claude Code on the web sessions now use raw git blob content, ignoring workspace-configured diff drivers and textconv
  • Remote Control auto-start changed so repo-local settings (.claude/settings.json or .claude/settings.local.json) can no longer turn it on; enable it at user scope via /config
Fixed 16
  • Worktree-isolated sessions and their subagents can no longer run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type
  • PreToolUse auto-allow hooks no longer bypass tool restrictions in background agent tasks such as summaries, compaction, and renames
  • /usage-credits on Team and Enterprise no longer shows "you've already sent a usage credit request" for members whose earlier request was dismissed, allowing them to send a new one
  • Startup connectivity check no longer hangs and fails behind an HTTPS proxy; it now uses the same proxy-aware transport as API requests and times out with a clear message
  • "Connection closed mid-response" errors are no longer reported on responses that had actually completed
  • /usage no longer overattributes usage to MCP servers; a server's share now reflects only the requests that actually consumed its tool results
Removed 1
  • Removed ultraplan feature
What's changed
  • Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type
  • Fixed PreToolUse auto-allow hooks bypassing tool restrictions in background agent tasks (summaries, compaction, renames)
  • Fixed /usage-credits on Team and Enterprise showing "you've already sent a usage credit request" for members whose earlier request was dismissed, blocking them from sending a new one
  • Fixed the startup connectivity check hanging and then failing behind an HTTPS proxy; it now uses the same proxy-aware transport as API requests and times out with a clear message
  • Fixed "Connection closed mid-response" errors being reported on responses that had actually completed
  • Fixed /usage overattributing usage to MCP servers: a server's share now reflects only the requests that actually consumed its tool results, instead of every turn after any call to it
  • Fixed sessions not linking to pull requests created after the branch was pushed, including through the GitHub REST API
  • Fixed org-restricted model: opus-style subagent and teammate family aliases dropping to the parent model instead of stepping down to the newest org-allowed model in the family
  • Fixed stream idle timeout firing on custom ANTHROPIC_BASE_URL gateways despite server keep-alive pings arriving on the wire
  • Fixed claude.ai connectors being falsely marked as needing authorization when the session token is invalid — they now show a /login hint instead
  • Fixed tool errors not being displayed for tools no longer available locally, for example after an MCP server is removed
  • Fixed SendMessage rejecting a long summary — it now truncates instead, so sends no longer fail on a character limit
  • Fixed the spinner's effort label in a subagent's transcript view showing the session's effort level instead of the subagent's own effort: setting
  • Fixed rare crashes when a file watcher hit a filesystem error or during file-watcher teardown
  • Fixed screen readers re-reading the whole input line on every backspace in --ax-screen-reader mode — end-of-line deletions now echo just the deleted characters
  • Fixed host model-selection keys not taking precedence over a stale on-disk managed-settings.json when CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST is set
  • Improved auto mode safety: messages sent to other agent sessions via SendMessage are now evaluated by the permission classifier before dispatch
  • Improved the refusal when Claude tries to invoke a skill with disable-model-invocation: Claude is now told to ask you to run the skill instead of replicating its workflow
  • Improved the /diff view, the Remote Control workspace diff, and file-edit diffs in Claude Code on the web sessions to use raw git blob content, ignoring workspace-configured diff drivers and textconv
  • Changed Remote Control auto-start so repo-local settings (.claude/settings.json or .claude/settings.local.json) can no longer turn it on (they can still turn it off); enable it at user scope via /config
  • Removed ultraplan feature
View original

Upgraded? How did it go?

Discussion