Agent Updates: Official AI Agent Release Notes

1.Auto mode is now available without CLAUDECODEENABLEAUTOMODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings

1.Added directory path suggestions to /cd, matching /add-dir behavior

1.Added an auto mode rule that blocks tampering with session transcript files

1.no notable user-facing improvements in this release

1.Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted

1.Added a "Dynamic workflow size" setting in /config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap

1.Changed AskUserQuestion dialogs to no longer auto-continue by default; opt into an idle timeout via /config

1.no notable user-facing improvements in this release

1.Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first

1.Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finish (previously a gradual rollout)

1.Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5

1.Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in /model when you haven't picked one yourself

1.Added CLAUDECODEDISABLEMOUSECLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll

1.Added autoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns

1.no notable user-facing improvements in this release

1.Added /rewind support for resuming a conversation from before /clear was run

1.Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables

1.Added claude mcp login and claude mcp logout to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH

1.The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s

1.Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific stack

1.Added /config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Control

1.no notable user-facing improvements in this release

1.Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents

1.no notable user-facing improvements in this release

1.Added wheelScrollAccelerationEnabled setting to disable mouse-wheel scroll acceleration in fullscreen mode

1.Session titles are now generated in the language of your conversation (set the language setting to pin a specific language)

1.Added enforceAvailableModels managed setting — when enabled, the availableModels allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a managed availableModels list