Want the reasoning? Read walks every section of this release, each entry opening to what changed and why.
Read this release → Every row →Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.
On macOS, the helper app's Info.plist now comes from the Claude Code program; without one, background sessions run from the installed path instead
Unclear It is not clear whether released Claude Code programs carry the embedded description, so the stable helper path may or may not still be used.
The version string moves from 2.1.315 to 2.1.316 with a new build time and identifier, and nothing else changes in these parts
Published verbatim by Anthropic for v2.1.316. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.
Of these 55 bullets, 0 name something an entry on this page also names, 27 name something no entry here does, and 28 name nothing specific enough to line up either way. The pairings are made on names both sides wrote down, a flag or a setting or a slash command, so read one as probably the same thing rather than as a fact, and read the middle number as candidates rather than as a miss count.
CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword off
No entry names this pooled_budget on the spend limits admin API
No entry names this CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP to keep system cross-certificates that certify each other in a loop, for servers whose private CA needs one
No entry names this CLAUDE_CODE_SUBAGENT_EFFORT to set the effort level subagents run at when nothing else names one, instead of inheriting the session's
No entry names this managed.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 first
No entry names this guardrail.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 prompt
No entry names this SHELLOPTS is exported
No entry names this param, using or an attribute
Nothing to match on sonnet, 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 region
Nothing to match on availableModels, deniedModels and models; a request that names a blocked model now gets a 400 naming the field
No entry names this claude auth login refusing to run where managed settings require a Claude apps gateway; in a terminal it now shows the gateway sign-in
No entry names this --restricted sessions uploading files from outside the working directories when a Read allow rule covered them
No entry names this autoMode.allow list without "$defaults" getting the built-in exceptions back from a host app's --settings, a first rule added in /permissions, or /auto-mode-setup
No entry names this claude -p text output sometimes not saying why auto mode stopped a turn when a background agent was still running
No entry names this CLAUDE_CODE_AUTO_MODE_SERVER=1 being ignored in sessions started by a host application (such as Claude Desktop) behind a proxy or LLM gateway with experimental betas turned off
No entry names this headersHelper scripts receiving a corrupted CLAUDE_PLUGIN_ROOT and server URL when a credential-named environment variable was set to a switch value such as 1
No entry names this register_repo_root control request not loading the CLAUDE.md of a directory outside the working directory (with CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1)
No entry names this ? for artifact database access rules at the self level, and not quoting those rules back when it refuses a republish that would drop them
Nothing to match on /model <id> not warning when the model isn't recognized by this version and auto-compact will assume a 200K context window
No entry names this /clear or /resume had been run while part of that conversation was still being saved
No entry names this /code-review started from the Code tab in Claude Desktop or on the web: cloud and claude remote-control sessions now show the findings card, not a plain-text list
No entry names this /diff on large repositories: each refresh usually runs one fewer full-repository git command, and refreshes are spaced out when git is slow
No entry names this /ultrareview, a cloud session or a cloud agent finds no GitHub remote: they now say to create a repository at https://github.com/new, and /ultrareview no longer suggests a gh command that gh rejects
No entry names this autoMode.allow list without "$defaults" no longer removes the built-in rule on scheduled-task prompts
No entry names this ultrathink to run its turn at xhigh effort and show in a rainbow in the chat box, as in the terminal
Nothing to match on [1m] tag, such as opus[1m]
No entry names this /btw side-question history being deleted too early while a settings file has errors
No entry names this No change to the system prompt since v2.1.315.
Claude Code, interactive mode
One prompt change in this release could not be quoted from the build, so no entry on this page describes it.
670 documentation changes were recorded within 24 hours either side of this release, nearest first. The closest 12 are below. They're here because they happened near this release in time. That's not a claim that this release caused the edit, or that the page documents anything in it.
What's wrong with this entry?