CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword offReleased · Anthropic
CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword offWhat's changed
CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword offpooled_budget on the spend limits admin APICLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP to keep system cross-certificates that certify each other in a loop, for servers whose private CA needs oneCLAUDE_CODE_SUBAGENT_EFFORT to set the effort level subagents run at when nothing else names one, instead of inheriting the session'smanaged.policy_mode: layered to the Claude apps gateway: every policy that matches a developer applies, each merged over the ones listed below it, not only the firstguardrail.input_tagging on Claude apps gateway Bedrock upstreams, which wraps prompts in the input tags that an Amazon Bedrock guardrail's prompt attacks filter needs; all_messages_and_system also tags the system promptSHELLOPTS is exportedparam, using or an attributesonnet, opus and haiku on Vertex AI and Amazon Bedrock showing an error mid-session instead of switching to an older model when the newest is not yet available to the account or regionavailableModels, deniedModels and models; a request that names a blocked model now gets a 400 naming the fieldclaude auth login refusing to run where managed settings require a Claude apps gateway; in a terminal it now shows the gateway sign-in--restricted sessions uploading files from outside the working directories when a Read allow rule covered themautoMode.allow list without "$defaults" getting the built-in exceptions back from a host app's --settings, a first rule added in /permissions, or /auto-mode-setupclaude -p text output sometimes not saying why auto mode stopped a turn when a background agent was still runningCLAUDE_CODE_AUTO_MODE_SERVER=1 being ignored in sessions started by a host application (such as Claude Desktop) behind a proxy or LLM gateway with experimental betas turned offheadersHelper scripts receiving a corrupted CLAUDE_PLUGIN_ROOT and server URL when a credential-named environment variable was set to a switch value such as 1register_repo_root control request not loading the CLAUDE.md of a directory outside the working directory (with CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1)? for artifact database access rules at the self level, and not quoting those rules back when it refuses a republish that would drop them/model <id> not warning when the model isn't recognized by this version and auto-compact will assume a 200K context window/clear or /resume had been run while part of that conversation was still being saved/code-review started from the Code tab in Claude Desktop or on the web: cloud and claude remote-control sessions now show the findings card, not a plain-text list/diff on large repositories: each refresh usually runs one fewer full-repository git command, and refreshes are spaced out when git is slow/ultrareview, a cloud session or a cloud agent finds no GitHub remote: they now say to create a repository at https://github.com/new, and /ultrareview no longer suggests a gh command that gh rejects