Follow Discord
← All releases Home ←olderv2.1.287

Claude Code v2.1.288

latestnext 425 entries read Grouped into 350 v2.1.287 → v2.1.288 Mods API: +3 added · 0 removed · 1 changed · 7 docs only Markdown JSON Follow Unofficial

You can now hold project settings changes made from a cloud session until you approve them, by running claude apply-project-settings in that folder. This applies when your computer serves the cloud session. Admins can force unattended serving off through managed settings with unattended_serving_off. Resumed sessions no longer keep the prompt cache warm unless the new resumeTouches setting is on. Claude Code's own stand-in for gh, added last release, can now reach any GitHub Enterprise host when ghesHosts is set to "any". Host apps can block file writes in chosen folders, except inside one declared worktree.

A /restart command that keeps your session is in this build but not switched on yet. It also answers to /update and offers newer versions. A shortcut that answers some artifact edit requests with direct file edits is also off for now. Cloud sessions can hand finished file writes to the next turn's worker, but only once that is switched on remotely. A setup guide feature is wired into the prompt box but does nothing yet.

An oversized reply from an MCP server over HTTP now fails only that request and keeps the connection open. Language server requests now time out instead of waiting forever. Reads and rewrites of a session transcript now wait for each other, so compaction and resume cannot clash. Resumed teammates no longer bring back an agent type that a rule or plugin now blocks. The Read tool instructions no longer include the guidance on PDF page ranges.

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

Watch out

25 changes that can affect you without you doing anything
+20 more in Read →

Five to try today

Picked from 23 you can use now
  1. claude mcp serve lists agent types and blocks background agents in restricted mode

    claude mcp serve now offers custom subagent types, and new switches can block background-agent launch and remote isolation, used in its http mode

    Sessions & agents
  2. Cloud sessions served by your computer take settings more cautiously

    When your computer serves a cloud session, changed project settings are held back until claude apply-project-settings, and user settings can only tighten

    Sessions & agents
  3. Host apps can fence off folders so file tools write only to a worktree

    Two new environment variables let an embedding app block file writes inside chosen paths, except inside one declared worktree

    Elsewhere
  4. Plugin runtime adds ui.selection and ties network and audio access to a plugin id

    Plugins get a new ui.selection operation, and http.fetch and URL audio playback now use a plugin storage id, with $.audio.play refusing URLs without one

    Extensions
  5. CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS turns off structured outputs

    Setting CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS stops Claude Code from asking the model for replies in a fixed format

    Elsewhere

You'll notice 186

All 186 in Read →

Nothing to try yet 22

All 22 in Read →

Removed 2

Want the reasoning? Read walks the 31 entries that probably matter to you, each one opening to what changed and why.

Read this release → Every row →
28 of 350 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
5 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.

+New
Use it now
Useful5 Signal4
Worktrees Notable no docs found unclear

Host apps can fence off folders so file tools write only to a worktree#

Two new environment variables let an embedding app block file writes inside chosen paths, except inside one declared worktree

Unclear Which host application sets these variables is not shown.

Details 0 0 Feedback
CLAUDE_CODE_HOST_WORKTREECLAUDE_CODE_HOST_WORKTREE_FENCE
+New
Use it now
Useful4 Signal3
Managed Settings unclear

Admins can switch off unattended serving through managed settings#

Managed settings can now force unattended serving off with unattended_serving_off, and auto_mode_off reports it as turned off by settings

Unclear Where these settings keys are defined, and exactly what unattended serving covers, is not confirmed.

Details 0 0 Feedback
↑Improved
Use it now
Useful3 Signal2
Telemetry unclear

Raw request and response logging can now leave message bodies out#

OpenTelemetry logging of raw API bodies can now record that a body was withheld instead of logging it, and filters bodies through an account memory step

Unclear It is not clear what causes a body to be withheld, or what the account memory step does to the logged bodies.

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.

11 entries here

Improvementsopen

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

↑Improved
Under the hood
Useful2 Signal2
Group of 5 Sessions no docs found unclear

Environment info now covers the GitHub CLI and its stand-in#

Claude's environment details gain a githubCli entry, the model is told when built-in gh goes away, and the gh stand-in can reach any GitHub host

Unclear It is not clear what sets ghesHosts to "any".

Details 0 0 Feedback
ghesHosts
↑Improved
You'll notice
Useful2 Signal2
Group of 2 Structured Outputs unclear

Side queries retry without structured output when a model rejects it#

Side queries now retry without the structured-output format when the API rejects output_config.format, and new helpers recognise PDF and format errors

Unclear It is not clear what check now decides whether the format is requested at first.

Details 0 0 Feedback
output_config.format
↑Improved
You'll notice
Useful2 Signal2
Sessions unclear

Changed security certificates are reinstalled and retried automatically#

Claude Code now watches for a changed security certificate, updates the system and tool trust stores, and retries installs that do not take

Unclear It is not clear whether some of this certificate handling already existed in an earlier form.

Details 0 0 Feedback
↑Improved
You'll notice
Useful1 Signal2
Device Attestation unclear

Device attestation rejects more kinds of faulty certificate chains#

Device attestation now rejects certificate chains that run too long, end in an authority certificate, or name the wrong issuer

Unclear Where in Claude Code this check is used is not stated.

Details 0 0 Feedback
↑Improved
You'll notice
Useful1 Signal1
Plugins unclear

Plugin install error no longer mentions needing a direct Anthropic connection#

The cannot-install message for blocked plugins no longer says you need a direct Anthropic API connection, and always says the plugin is unavailable

Unclear It is not clear whether the requirement itself was removed or only the wording about it.

Details 0 0 Feedback
3 entries here

Bug Fixesopen

2 entries here

In Developmentopen

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

◌In dev
Nothing to try yet
Useful2 Signal3
Settings unclear

Groundwork for limiting which settings a launch folder can supply#

Claude Code's settings code gained handling for which settings keys come from the folder it was launched in, with no visible effect yet

Unclear Which settings keys are involved, and whether the empty panel field is ever shown, were not traced.

Details 0 0 Feedback
7 entries here

Internal Changesopen

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

3 entries hereSessions · none marked notable
·Internal
Under the hood
Useful1 Signal1
Sessions unclear

Agent proxy certificate setup reworked and no longer checks a server setting there#

Setting up trust for the agent proxy's certificate no longer checks a server switch there and now catches certificates listed in swapped order

Unclear It is not clear what the remaining use of the setting controls, or whether the trust step still depends on it in some other way.

Details 0 0 Feedback
2 entries hereElsewhere · none marked notable
·Internal
Under the hood
Useful2 Signal2
Elsewhere unclear

Self-hosted runner changes who may read its metrics page#

The self-hosted runner's health server now decides who may read /v1/metrics with a shared check instead of a fixed list of local addresses

Unclear It is not clear which callers the new check allows.

Details 0 0 Feedback
·Internal
Under the hood
Useful1 Signal2
Elsewhere unclear

Remote Control runner health check now tracks retirement and shutdown#

The health check of a self-hosted Remote Control runner now polls its token status, including a retire time and whether it is stopping

Unclear What the health check does with the retire time and stopping state is not established.

Details 0 0 Feedback
1 entry hereHooks · none marked notable
·Internal
Under the hood
Useful2 Signal3
Hooks unclear

Hooks modules are refused in shared claude-code-server processes#

A new error says no hooks module loads in a claude-code-server tenant, because that process serves many people

Unclear It is not clear when the new error is shown, or whether moving the deny-rule check changed how blocked tools are handled.

Details 0 0 Feedback
Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.288. 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 89 bullets, 18 name something an entry on this page also names, 29 name something no entry here does, and 42 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.

Read it on GitHub →
System prompt

2 of 27 tool descriptions changed. 1 of 25 tool schemas changed. The appended system-reminder blocks moved: 1 line added, 1 line removed.

Claude Code, interactive mode

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

Read the prompts for this release →
Documentation

What the docs did around this release

712 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.

plugins/pre-submission-checklist Changed +1 -1 upstream edited claude-docs plugins/platform-support Changed +1 -1 upstream edited claude-docs plugins/overview Changed +9 -1 upstream edited claude-docs claude-tag/overview Changed +1 -5 upstream edited claude-docs claude-tag/admins/setup-overview Changed +1 -2 upstream edited claude-docs claude-tag/admins/set-spend-limit Changed +1 -1 upstream edited claude-docs claude-tag/users/troubleshooting Changed +19 -0 upstream edited claude-docs claude-tag/users/when-claude-responds Changed +3 -2 upstream edited claude-docs claude-tag/users/use-cases/your-own-channel Changed +1 -1 upstream edited claude-docs claude-tag/users/troubleshooting Changed +17 -13 upstream edited claude-docs claude-tag/users/proactivity Changed +3 -2 upstream edited claude-docs claude-tag/users/models Changed +2 -2 upstream edited claude-docs
The documentation ledger →
Switches

Every name in this release

The 63 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