Short model names such as opus and sonnet now work beyond Anthropic's own API. Fable is now recognised as a short model name too. A new Claude Test panel in the terminal shows each test's pass, fail or blocked mark, with a progress bar and time left. It builds on the groundwork for that panel in v2.1.309. On Vertex and Bedrock, default models can now come from a published model document. Setting CLAUDE_CODE_RETRY_WATCHDOG_SCOPE=capacity limits the automatic retry waiting to capacity errors only.
Several features are in this build but not switched on yet. A /claude-api check that scans your project for retiring Claude model names is built and stays off. Sending a project's documents to Claude as plain text is also off unless switched on remotely. The tool that writes project documents gains a safety check that is off by default. When switched on, it refuses to replace a document whose text differs from what Claude last saw. Groundwork for picking up background agents left behind after a resume is present but hidden.
Starting a cloud session now recovers when this computer is not yet a trusted device. Claude Code re-enrolls the computer and retries, or tells you to run /login. Saving incoming attachments no longer overwrites files that have the same name. Inline images inside tmux now stay in place when the pane moves, resizes or regains focus. A NODE_EXTRA_CA_CERTS file with one blocked certificate no longer causes the whole file to be ignored. The bundled claude-code.d.ts type definitions file is removed.
Written by our agent from the shipped bundle, not by Anthropic.
Short model names such as opus and sonnet are no longer limited to Anthropic's own API, and fable is now recognised as one
Sessions & agentsMCP server settings accept a new connectorId field, stdio servers keep their original configuredCommand, and mcp_call refuses some servers' tools
ExtensionsIn proxied sessions, the built-in gh now refuses to run outside the session's proxy, and a new standalone-proxy mode sets up git and gh
Tools & outputOn Windows, strict sandbox mode now explains why a command was refused, and the CLAUDE_CODE_NANKEEN_KESTREL switch remembers it was on
Interface
CLAUDE_CODE_RETRY_WATCHDOG_SCOPE limits the retry watchdog to capacity waitsSet CLAUDE_CODE_RETRY_WATCHDOG_SCOPE=capacity to keep the retry watchdog waiting through capacity errors without its other retry changes
Want the reasoning? Read walks the 22 entries that probably matter to you, each one opening to what changed and why.
Read this release → Every row →6 more of these are in What probably matters to you, on page 1.
An MCP server named like a desktop connector is now reported as refused, and artifact tool swaps report when an entry is not served
Unclear It is not clear whether such a server is actually blocked or only recorded.
Claude Code now has two new MCP-related categories, one for desktop connector names and one called question brake
Unclear It is not clear what triggers the question brake or whether you would ever notice it.
The permission check for MCP tools now reacts when an older-style access grant was refused, for plugin servers or failed owner checks
Unclear It is not clear whether a refused legacy grant now blocks the tool, asks for approval, or something else.
Claude Code now classifies requests that list an MCP server's tools separately from the server's opening setup requests
Unclear What the separate handling of tool-list requests changes for users is not known.
Requests sent with CLAUDE_CODE_SESSION_ACCESS_TOKEN now carry a marker saying they hold Claude Code's own token when they go through a proxy
Unclear It is not clear what the new marker changes about how the token is sent through a proxy.
WebSocket connections now get their own TLS settings, and the Google sign-in client takes its network options from a shared helper
Unclear What connection options the shared helper supplies, and so what changes for Google sign-in users, is not stated.
The error shown when a value cannot be copied now says it holds a Proxy or a vm context, and the check runs in one more place
Claude Code now hands out small ids by picking a random unused one rather than counting up in sequence
Claude Code stopped reading a titles field when it parses a report, so reports now carry only names, look, more, stopped and from
Unclear Which feature used these titles, and so what a reader stops seeing, is not stated.
When a plugin asks Claude to complete or classify text, the call is now tagged as coming from a plugin
The instructions Claude gets for showing a plugin install card can now include an extra section when a certain check passes
Unclear The added text and the check that adds it are not known.
For plugin MCP servers run as local programs, Claude Code now also keeps their settings as they were before the environment is filled in
Unclear It is not clear what the extra copy of the settings is used for or whether it changes anything a user sees.
Claude is now told to name suggested skills in plain text when the tool for showing them is not among its tools
When a plugin starts its own model call, it can now pass along names identifying that call
Claude Code can now add a host status nudge and a host prompt reminder to the start of a turn when a host condition holds
Unclear Which setups meet the host condition that adds these reminders is not stated.
The step that builds extra context for each turn now reads two new values, a status nudge and a prompt reminder
When a request is over the token limit, Claude Code now works out both how far over it is and the actual token count
When Claude Code rewrites tool results in the conversation, it now skips one more kind of result
Claude Code can now refuse a published model list when the publisher holds a provider on built-in behaviour or a model would move
Unclear Whether the published model list is used at all for a given setup is not stated.
Claude Code's model list now tracks which providers offer each model and can point a model alias at a different target per provider
Claude Code now records whether your default model was chosen by your organization or account, or is just the global default
Unclear Nothing shows what Claude Code does differently with this information, so its effect on which model you see or use is unclear.
The run skill that ships with Claude Code now carries a script file named install-tools.mjs
A new name tied to the Claude API skill points to a check for models that are being retired
Unclear Where this check is used and whether any notice actually reaches users is not shown.
Records of a skill's verification now note which git checkout it ran in, not only the method used
Onboarding has a new switch around the API key step and the terminal setup step, and it is currently always off, so nothing changes yet
The urgent tip banner can now show as one compact line with a small symbol in front, and the rule for when it appears has changed
The on-screen view of a turn in progress can now display an additional element when a certain internal condition is set
Unclear What the extra element shows and what switches it on is not stated.
Verifying a made-here marker now also confirms the folder is real, in the expected place, and unchanged during the check
When checking a file against its saved content, Claude Code now reports "other" for non-regular files and "unknown" on errors
When Claude Code itself sends a hook event, the event now carries where it came from and a mark saying Claude Code raised it
Hooks set by your organization now start without the environment variables from a repository's settings, and a debug line says so
Which limit applies to policy-driven permission asks now depends on one signal from the caller, not on whether the action came from a person
Unclear It is not shown what now decides which of the two limits applies.
The part of Claude Code that reads shell commands for permission checks can now be told how to treat backslashes inside quotes
The tool for reading and writing project documents can now tell whether a document's content is already in the conversation
Claude Code now treats reads of project documents as a separate kind of context and counts when they appear more than once
Before launching a session, a self-hosted runner's config check now also learns whether git config is on and whether the launched program's version is known
Unclear What the check does differently with these new details.
Sessions started by a self-hosted runner are no longer handled like other remote sessions when Claude Code sets up the artifacts MCP laptop entry
Unclear Whether self-hosted runner sessions now get the artifacts laptop entry or still go without it is not shown.
Which version of the 'Communicating with the user' prompt section Claude gets now also depends on a new input, not only the model and settings
Unclear What the new input represents and when it is set.
The two system prompt sections switched on and off remotely are still read through the same switches, with no clear difference beyond internal renaming
The script runtime now allows two more calls, clock.after and env.get, for timed delays and reading environment variables
A sleep call is now available next to the existing time call in a sandboxed module environment
Unclear It is not clear which modules run in this environment, so it is unclear whether you can use it.
The claude-code.d.ts type definitions file is no longer bundled inside Claude Code, and another bundled file was replaced
Published verbatim by Anthropic for v2.1.310. 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 26 bullets, 1 name something an entry on this page also names, 6 name something no entry here does, and 19 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.
effort-2025-11-24 beta value or mid-conversation system messages; Claude Code now retries without them
No entry names this cleanupPeriodDays is set to a very large value
No entry names this -p, Agent SDK) during compaction when the transcript file is very large
Nothing to match on Image to draw inside tmux with allow-passthrough and focus-events on, in kitty, Ghostty, and iTerm2 3.5+ with fullscreen rendering, where it showed only its alt text
Probably tmux-image-support-diagnostics-module-no-caller-seen /sandbox and the sandbox startup warning to name Ubuntu's AppArmor restriction on user namespaces, and how to lift it, when it keeps bubblewrap from starting the sandbox
No entry names this ! commands such as !restart and !help as ordinary messages when sent in bold, italic or strikethrough
Nothing to match on 3 of 30 tool descriptions changed. 1 of 28 tool schemas changed. The appended system-reminder blocks moved: 1 line added.
Claude Code, interactive mode
15 prompt changes in this release could not be quoted from the build, so no entry on this page describes them.
691 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.
The 29 literal strings found in the bundle, with the number of entries that name each one. Picking one searches for it. A name is here because this build's code mentions it, which is not the same as it working or being finished.
What's wrong with this entry?