Follow Discord

Claude Code v2.1.321

476 entries read Grouped into 418 v2.1.319 → v2.1.321 Mods API: +7 added · 0 removed · 10 changed · 13 docs only Markdown JSON Follow Unofficial

You can now use the Fable 5.2 and Mythos 5.2 models in Claude Code with the short names fable-5-2 and mythos-5-2. Fable 5.2 is now listed as the latest model, and fable52 works as an alias too. Plugins can use a new tool.check hook to make tool permissions stricter, but never looser for built-in tools. Plugins can also answer or rewrite outgoing web requests, and they are never lent your sign-in. Setting CLAUDE_CODE_ULTRAREVIEW_PR_AS_MERGED asks /ultrareview to review a pull request as it was merged. This release has 418 entries, and 270 of them are usable today.

Some features are in the build but are not switched on yet. A remote switch can make /privacy-settings open your privacy settings on claude.ai in your browser. Video attachments can carry a preview image, but only in hosted remote environments with a switch on. A skill's compatibility note can tell Claude when the skill needs your own computer or network, behind a switch that is off by default. Code editors may show a recommended extension, also behind a remote switch.

Stalled secure connections now stop with a clear error instead of hanging. The usual limit is 120 seconds, and the error says to check your network or proxy. The bridge command now loads the settings file you pass with --settings. Plugin sync now keeps plugins you already installed when your account's plugin list fails to load. A skills folder created after startup is now picked up and watched. The email address privacy prompt for shell and web actions no longer appears in the list of features.

Written by our agent from the shipped bundle, not by Anthropic.

Five to try today

Picked from 28 you can use now
  1. Fable 5.2 and Mythos 5.2 arrive, and fast mode changes around them

    Claude Code recognises the Fable 5.2 and Mythos 5.2 models, needs an explicit opt-in for fast mode on them, and keeps your model when fast mode supports it

    Sessions & agents
  2. Remote Control gets a --settings option and pins what its sessions start with

    claude remote-control --settings <file> passes a settings file to spawned sessions, which refuse to start if that file or their start folder changed

    Sessions & agents
  3. Fable 5.2 added as a model alias and highlighted in a reworked model picker

    A fable52 model alias is added, and the model picker gains a collapsible 'More models' row with Fable 5.2 highlighted

    Sessions & agents
  4. Claude Code can read a list of MCP tools to deny

    Claude Code can now check and merge a list of blocked MCP tools, called mcpDeniedTools, into its settings

    Extensions
  5. Plugins can intercept and rewrite Claude Code's web requests

    Plugins can now hook outgoing web requests to answer or rewrite them, but are never lent your sign-in

    Extensions

Want the reasoning? Read walks the 54 entries that probably matter to you, each one opening to what changed and why.

Read this release → Every row →
41 of 418 shownClear
Reading as
Show only
Who it's for
Tier
Flag state
Names
Pick an entry · j / k steps through · rest on a row to peek
9 entries here

What probably matters to you

Anything you can use today, anything that visibly changes, and anything worth poking at. One line each, open for detail.

↑Improved
You'll notice
Useful2 Signal4
Delegated Sessions unclear

User-delegated sessions are blocked from some API routes#

In a user-delegated session, Claude Code now refuses API calls to routes that are not allowed and shows an error

Unclear It is not clear what makes a session user-delegated, so it is unclear who is affected.

Details 0 0 Feedback
Were these the right ones to put at the top? 0 answered
Below the fold

Everything else

Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.

25 entries here

Improvementsopen

18 more of these are in What probably matters to you, above.

↑Improved
You'll notice
Useful2 Signal3
Group of 3 MCP unclear

Organization connector blocks can apply to plugin MCP servers#

Plugin MCP servers matching a connector your organization blocked on claude.ai can now be blocked or just counted

Unclear It is not settled which mode applies when nothing sets require_connector_block_on_plugin_servers, so whether blocking is enforced by default is unclear.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal3
Group of 2 Cloud Providers unclear

Cloud provider sign-in checks a credential source before environment variables#

Bedrock, Mantle, Foundry and Vertex now look up a credential first and use it as a bearer token or API key before the usual sign-in

Unclear Where the credential lookup gets its values from, and so how you would supply one, is not clear.

Details 0 0 Feedback
AWS_BEARER_TOKEN_BEDROCKANTHROPIC_FOUNDRY_API_KEY
↑Improved
You'll notice
Useful3 Signal2
MCP unclear

Organizations can block MCP server connections that send certain headers#

Claude Code skips connecting to an MCP server when the headers it would send fall under an organization's connector block

Unclear Where the organization's connector block is set, and which users it applies to, is not stated.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal2
MCP unclear

MCP connections are checked against your organization's Claude in Chrome policy#

Claude Code now checks MCP servers against the organization's Claude in Chrome policy before and after connecting, and skips refused ones

Unclear Whether this check applies to every MCP server or only to the Claude in Chrome one is not clear.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal1
Elsewhere unclear

Managed settings that fail to load are read again, with a clearer message#

If managed settings cannot be read, Claude Code tries again during the session and says plainly that the settings were not checked

Unclear It is not settled whether Claude Code holds back restricted actions or carries on when the managed settings still cannot be read.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal1
MCP unclear

MCP servers added through the SDK must now pass a check before connecting#

MCP servers added on the fly through the SDK are checked before and after connecting; a refused one is closed and adds no tools

Unclear What the check compares a server against, such as an organization policy or an allowlist, is not known.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal1
MCP unclear

Stricter policy checks before MCP servers are reused or refreshed#

Claude Code now rechecks SDK MCP servers against policy before reuse, refreshes tools only for allowed servers, and sorts private addresses by type

Unclear Which servers the new checks would turn away, and what you would see when that happens, is not stated.

Details 0 0 Feedback
↑Improved
You'll notice
Useful2 Signal1
Plugins unclear

Admin-set plugin marketplaces replace copies installed from elsewhere#

A marketplace named in managed settings now removes a same-named install from another source, and admins can word the policy error

Unclear Where administrators set the custom lines for the unreadable-policy error is not stated.

Details 0 0 Feedback
7 entries here

Internal Changesopen

3 more of these are in What probably matters to you, above.

·Internal
Under the hood
Useful1 Signal1
Cloud Providers unclear

AWS and Google credential variables added to cloud provider settings lists#

Five AWS and Google credential environment variables were added to three lists of cloud provider settings

Unclear What the three lists control, for example limits in managed settings or removal before running other programs, is not clear.

Details 0 0 Feedback
1 entry hereElsewhere · none marked notable
1 entry hereMCP · none marked notable
·Internal
Under the hood
Useful1 Signal0
MCP unclear

MCP server policy rules are now combined in one shared step#

Claude Code now builds its MCP server policy rules through a single shared merge step

Unclear It is not clear whether the shared merge step makes allow, deny or ask decisions behave differently.

Details 0 0 Feedback
2 entries hereNetwork · none marked notable
1 entry herePlugins · none marked notable
Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.321. 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 118 bullets, 23 name something an entry on this page also names, 30 name something no entry here does, and 65 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.

A model matched these bullets to the GitHub issues they fix, so a link can be wrong.

System prompt

2 added and 2 removed, of 218 lines, about 38 words, in the prompt 14 of 27 arms receive. 4 other prompts also changed. The appended system-reminder blocks moved: 2 lines added, 2 lines removed.

Claude Code, interactive mode

5 prompt changes in this release could not be quoted from the build, so no entry on this page describes them.

Documentation

What the docs did around this release

834 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.

Switches

Every name in this release

The 57 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.

Slash commands

CLI flags

Environment variables

Settings and names in the code

Feedback