One read of Claude Code CLI

agent-sdk/subagents Changed · +21 / -20 lines

agent-sdk/typescript Changed · +25 / -20 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

claude-apps-gateway-config Changed · +24 / -7 lines

#### Mark prices up

debug-your-config Changed · +19 / -19 lines

desktop Changed · +9 / -3 lines

errors Changed · +6 / -6 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

fast-mode Changed · +14 / -3 lines

### Use fast mode in cloud sessions

mcp Changed · +20 / -4 lines

#### Credential variables that read as empty

settings-reference Changed · +6 / -2 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

skills Changed · +4 / -4 lines

sub-agents Changed · +14 / -7 lines

tools-reference Changed · +5 / -1 lines

vs-code Changed · +9 / -2 lines

whats-new/2026-w35 New page · 94 lines, new page

# Week 35 · August 24–28, 2026

A whole new page. There's nothing to diff it against, so here is what it says.

# Week 35 · August 24–28, 2026

> Resume terminal sessions in the Claude Code Desktop app, review feedback reports that Claude drafts for you, and start a session in restricted mode.

<div className="digest-meta">
  <span>Releases <a href="/docs/en/changelog#2-1-240">v2.1.240 → v2.1.250</a></span>
  <span>3 features · August 24–28</span>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Resume terminal sessions in the Desktop app</span>
    <span className="digest-feature-pill">Desktop</span>
  </div>

  <p className="digest-feature-lede">Type <code>/resume</code> in the Claude Code Desktop prompt box to pick up any session you started from the CLI and continue it in the app with the full conversation and context intact. Search your sessions by title, folder, or branch, and preview where you left off before you resume.</p>

  <Frame>
    <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/desktop-resume-cli-session.mp4?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=41e4a5fda6b9d63280589f2cbdabf44f" data-path="images/whats-new/desktop-resume-cli-session.mp4" />
  </Frame>

  <p className="digest-feature-try">In a Desktop session, run the command to list your terminal sessions:</p>

  ```text Claude Code theme={null}
  > /resume
  ```

  <p className="digest-feature-try">Select a session and press <code>Enter</code>. The conversation opens in the app where you left off.</p>

  <a className="digest-feature-link" href="/docs/en/desktop#coming-from-the-cli">Move between the CLI and Desktop</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Claude-drafted feedback</span>
    <span className="digest-feature-pill">CLI</span>
  </div>

  <p className="digest-feature-lede">When a tool keeps failing, Claude can't help with a request, or you point out a mistake, Claude now drafts a feedback report for you with the <code>SendFeedback</code> tool. A card above your prompt shows the draft, and you can review, send, or dismiss it from there. Nothing reaches Anthropic until you send it. Requires v2.1.238 or later.</p>

  <Frame>
    <img className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/claude-drafted-feedback.jpg?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=5cacb3be0dffd1cbd417381f3721637e" alt="A Claude Code session where Claude has drafted a bug report titled Sandbox image pull fails behind proxy, shown as a card above the prompt with options to review, send, or dismiss" width="1440" height="756" data-path="images/whats-new/claude-drafted-feedback.jpg" />
  </Frame>

  <p className="digest-feature-try">Run <code>/feedback</code> with no argument to open your queue of drafts from every session:</p>

  ```text Claude Code theme={null}
  > /feedback
  ```

  <p className="digest-feature-try">Select a draft, then edit, send, or discard it. To turn drafting off, set <strong>Claude-drafted feedback</strong> to <code>off</code> in <code>/config</code>.</p>

  <a className="digest-feature-link" href="/docs/en/tools-reference#sendfeedback-tool-behavior">SendFeedback tool behavior</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Restricted mode</span>
    <span className="digest-feature-pill">v2.1.248</span>
  </div>

  <p className="digest-feature-lede">Restricted mode starts Claude Code without the built-in tools that run commands or code. Use it when an evaluation harness drives <code>claude</code> on a shared machine. Start it with `--restricted` or set <code>CLAUDE\_CODE\_RESTRICTED=1</code>. Claude Code also removes <code>WebFetch</code>, confines the file tools to the working directories, loads only managed settings and `--settings`, and refuses the <code>bypassPermissions</code> permission mode.</p>

  <p className="digest-feature-try">Run a non-interactive query without the command-running tools:</p>

  ```bash terminal theme={null}
  claude --restricted -p "review src/ for SQL injection risks"
  ```

  <p className="digest-feature-try">To give Claude one of the removed tools back, list it in `--tools` together with the other built-in tools you want, for example `--tools "Bash,Read,Edit"`. `--tools` is an allowlist, and its <code>default</code> preset doesn't restore the removed tools.</p>

  <a className="digest-feature-link" href="/docs/en/cli-reference#cli-flags">CLI flags</a>
</div>

<div className="digest-wins">
  <p className="digest-wins-title">Other wins</p>

  <div className="digest-wins-grid">
    <div>Set the new <a href="/docs/en/settings-reference#modelpicker"><code>modelPicker</code></a> setting to extend or replace the <code>/model</code> picker's built-in list with your own ordered, labeled entries, including Amazon Bedrock or Google Cloud's Agent Platform model IDs</div>
    <div>Set <a href="/docs/en/prompt-caching#choose-the-ttl-yourself"><code>promptCacheTtl</code></a> to <code>1h</code> to keep a one-hour prompt cache on the main conversation when you use an API key or a cloud provider; <code>subagentPromptCacheTtl</code> sets the TTL for subagents and all other requests outside the main conversation</div>
    <div>On Pro, Max, Team, and Enterprise plans, <a href="/docs/en/costs#plan-usage-breakdown"><code>/usage</code></a> adds a Loops breakdown: run count, total tokens, tokens per run, and last run for the <code>/loop</code> and scheduled tasks that used the most tokens</div>
    <div>Organizations on contracted rates can set the <a href="/docs/en/costs#report-spend-at-your-contracted-rates"><code>modelPricing</code></a> managed setting so <code>/usage</code>, the status line, and OpenTelemetry report cost at those rates instead of list price</div>
    <div><code>/login</code> offers <strong>Sign in with your Console account</strong> under the <strong>Anthropic Console account</strong> option, so members of Console organizations that don't allow API keys can sign in without creating one</div>
    <div>Run <code>/permissions</code> and open the new <a href="/docs/en/auto-mode-config#edit-rules-from-permissions"><strong>Auto mode</strong> tab</a> to view and edit auto mode classifier rules without opening a settings file</div>
    <div>When auto mode is available, Bash permission prompts in the Manual and <code>acceptEdits</code> permission modes offer a <a href="/docs/en/permission-modes#switch-permission-modes"><strong>Yes, and switch to auto mode</strong></a> option; select it to approve the command and switch the session to auto mode</div>
    <div>After you <a href="/docs/en/permissions#move-the-session-to-another-directory">move a session with <code>/cd</code></a>, the new directory's project settings, hooks, <code>.mcp.json</code> servers, skills, and subagents take effect immediately instead of on the next `--resume`</div>
    <div>In non-interactive sessions, including <code>-p</code> runs, Agent SDK runs, and cloud sessions, Claude Code <a href="/docs/en/errors#the-response-above-may-be-incomplete">continues a response</a> that a server error, dropped connection, or stall cut off mid-stream, when the partial response contains text and no tool calls</div>
    <div>A subagent that stops at its <code>maxTurns</code> limit returns its output marked as partial, with a hint that Claude can <a href="/docs/en/sub-agents#resume-subagents">continue it with <code>SendMessage</code></a>, instead of appearing finished</div>
    <div>On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, sessions on the same machine can now <a href="/docs/en/cross-session-messaging#availability">message each other</a>, <code>/loop</code> can <a href="/docs/en/scheduled-tasks#let-claude-choose-the-interval">choose its own interval</a>, and <code>/model</code> and <code>/effort</code> apply immediately instead of after the turn ends</div>
    <div>The native installer and auto-updater download a zstd-compressed build, about 75 MB instead of 340 MB on Linux x64, and native builds load code on demand, using roughly 40 to 70 MB less memory per session</div>
  </div>
</div>

[Full changelog for v2.1.240–v2.1.250 →](/docs/en/changelog#2-1-240)

whats-new/2026-w36 New page · 105 lines, new page

# Week 36 · August 31 – September 4, 2026

A whole new page. There's nothing to diff it against, so here is what it says.

# Week 36 · August 31 – September 4, 2026

> Switch to Claude Fable 5.1, let computer use run in the background on Desktop, and watch Claude's edits in a live /diff panel.

<div className="digest-meta">
  <span>Releases <a href="/docs/en/changelog#2-1-251">v2.1.251 → v2.1.261</a></span>
  <span>4 features · August 31 – September 4</span>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Claude Fable 5.1</span>
    <span className="digest-feature-pill">new model</span>
  </div>

  <p className="digest-feature-lede">Claude Fable 5.1 is available in Claude Code with a 1M-token context window, and the <code>fable</code> alias now selects it. In Claude apps gateway sessions, <code>fable</code> still selects Fable 5. If your gateway serves Fable 5.1, run <code>/model claude-fable-5-1</code>. Requires v2.1.257 or later.</p>

  <p className="digest-feature-try">Switch the current session to Fable 5.1 and save it as your default:</p>

  ```text Claude Code theme={null}
  > /model fable
  ```

  <p className="digest-feature-try">On the Anthropic API, the picker lists Fable only once the server reports it available for your organization, but typing <code>/model fable</code> checks with the server directly.</p>

  <a className="digest-feature-link" href="/docs/en/model-config#work-with-fable">Work with Fable</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Computer use runs in the background on Desktop</span>
    <span className="digest-feature-pill">Desktop</span>
  </div>

  <p className="digest-feature-lede">On macOS, computer use in the Claude Code Desktop app now works in the background: Claude sees and acts in the apps you've approved while you keep working. Background computer use is in beta on Pro and Max plans.</p>

  <Frame>
    <img className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/background-computer-use.jpg?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=a599a6c6fa544cb8d1b426b93706caf4" alt="A Claude Code Desktop session where Claude asks to use Xcode, with a Computer use permission card that reads Let Claude see and act in the apps you approve, in the background or with full control of your screen, next to an Enable button" width="1440" height="810" data-path="images/whats-new/background-computer-use.jpg" />
  </Frame>

  <a className="digest-feature-link" href="/docs/en/desktop#let-claude-use-your-computer">Let Claude use your computer</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Live diff panel in fullscreen rendering</span>
    <span className="digest-feature-pill">v2.1.260</span>
  </div>

  <p className="digest-feature-lede">In fullscreen rendering, <code>/diff</code> now opens a panel beside the conversation instead of a viewer you have to close. The panel lists the changed files with their added and removed line counts and refreshes each time Claude edits a file or runs a shell command. Select lines in the panel with the mouse to attach them to your next prompt.</p>

  <Frame>
    <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/diff-panel.mp4?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=9d7553c19e7f227891cd95f1f59d796d" data-path="images/whats-new/diff-panel.mp4" />
  </Frame>

  <p className="digest-feature-try">With fullscreen rendering on, inside a git repository, and in a terminal at least 110 columns wide, toggle the panel:</p>

  ```text Claude Code theme={null}
  > /diff
  ```

  <p className="digest-feature-try">Run <code>/diff</code> again or click the <code>✕</code> in its header to close it.</p>

  <a className="digest-feature-link" href="/docs/en/interactive-mode#diff-panel">Diff panel</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Find unused skills with /skill-doctor</span>
    <span className="digest-feature-pill">CLI</span>
  </div>

  <p className="digest-feature-lede"><code>/skill-doctor</code> shows what each of your skills costs in context and how often it gets used, so you can decide which ones to turn off. Every skill in the <a href="/docs/en/skills#skill-descriptions-are-cut-short">skill listing</a> adds to your context on every turn, whether or not Claude ever uses it. Requires v2.1.252 or later and isn't available in sessions that skip <a href="/docs/en/env-vars#features-that-need-feature-flag-fetching">feature-flag fetching</a>.</p>

  <p className="digest-feature-try">Run it in an interactive session to open the report in the <code>/plugin</code> manager's <strong>Stats</strong> tab:</p>

  ```text Claude Code theme={null}
  > /skill-doctor
  ```

  <p className="digest-feature-try">In non-interactive mode with <code>-p</code>, Claude Code prints the report as text instead.</p>

  <a className="digest-feature-link" href="/docs/en/skills#find-unused-skills">Find unused skills</a>
</div>

<div className="digest-wins">
  <p className="digest-wins-title">Other wins</p>

  <div className="digest-wins-grid">
    <div>A <a href="/docs/en/hooks#premodelswitch"><code>PreModelSwitch</code></a> hook can block a model switch you request, and a <a href="/docs/en/hooks#postmodelswitch"><code>PostModelSwitch</code></a> hook can add context for Claude after the session's model changes</div>
    <div><a href="/docs/en/costs#prompt-cache-statistics"><code>/cost</code></a> adds a <code>Prompt cache (main)</code> line: the share of input tokens served from cache, the cache misses, whether the cache is warm, and a likely cause for the last miss when Claude Code can name one. Status line scripts get a matching <code>prompt\_cache</code> object</div>
    <div>Organizations can list HTTP and SSE MCP servers under the <a href="/docs/en/managed-mcp#provide-servers-through-managed-settings"><code>managedMcpServers</code></a> managed setting to give them to every user, in addition to the servers that users add on their own</div>
    <div><code>/effort</code> and the <code>/model</code> picker now <a href="/docs/en/model-config#adjust-effort-level">save a separate effort level for each model</a>; press <code>s</code> instead of <code>Enter</code> to apply a level to the current session only</div>
    <div>By default, the auto mode classifier <a href="/docs/en/permission-modes#what-the-classifier-blocks-by-default">now also blocks</a> actions such as requesting credentials from the cloud instance-metadata endpoint or connecting to sibling containers that Claude didn't start</div>
    <div>In auto mode, Claude Code asks you before Claude <a href="/docs/en/permission-modes#first-read-outside-the-working-directories">first reads a file outside your working directories</a>, with an option to block such reads from then on</div>
    <div>Raise <a href="/docs/en/settings-reference#bashoutputmaxchars"><code>bashOutputMaxChars</code></a> and <a href="/docs/en/settings-reference#taskoutputmaxchars"><code>taskOutputMaxChars</code></a>, up to 128,000 characters, so Claude receives more of the output from a successful command or background task inline</div>
    <div>The prompt's <a href="/docs/en/interactive-mode#make-ctrl-w-delete-back-to-whitespace">word-editing shortcuts follow readline</a> for everyone, and the <code>keybindingFlavor</code> setting no longer has any effect. <code>Ctrl+W</code> deletes back to the previous whitespace, and <code>Alt+B</code>, <code>Alt+F</code>, and <code>Alt+D</code> treat punctuation such as <code>/</code> and <code>.</code> as word breaks</div>
    <div>If you set <code>defaultMode</code> to <code>"bypassPermissions"</code> in a project's <code>.claude/settings.json</code> or <code>.claude/settings.local.json</code>, it <a href="/docs/en/permission-modes#which-mode-a-session-starts-in">no longer takes effect</a> and the session starts in Manual mode; set <code>"bypassPermissions"</code> in user or managed settings instead, or pass `--permission-mode`</div>
    <div>Seat-based Enterprise plans now <a href="/docs/en/model-config#default-model-setting">default to Opus 5</a></div>
    <div>In the VS Code extension, click the model name at the bottom of the prompt box to <a href="/docs/en/vs-code#use-the-prompt-box">open the model picker</a></div>
    <div>In the VS Code extension, select <strong>Output styles</strong> in the command menu's Customize section to <a href="/docs/en/vs-code#use-the-prompt-box">pick an output style</a>, including your custom ones</div>
  </div>
</div>

[Full changelog for v2.1.251–v2.1.261 →](/docs/en/changelog#2-1-251)

whats-new/2026-w37 New page · 65 lines, new page

# Week 37 · September 7–11, 2026

A whole new page. There's nothing to diff it against, so here is what it says.

# Week 37 · September 7–11, 2026

> Test your plugins with claude plugin eval and pop Claude Code Desktop panes out into their own windows.

<div className="digest-meta">
  <span>Releases <a href="/docs/en/changelog#2-1-263">v2.1.263 → v2.1.269</a></span>
  <span>2 features · September 7–11</span>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Test plugins with claude plugin eval</span>
    <span className="digest-feature-pill">v2.1.269</span>
  </div>

  <p className="digest-feature-lede"><code>claude plugin eval</code> runs your plugin against a suite of test cases, scores the results, and by default runs each case again without the plugin so you can see what it contributes. <code>claude plugin eval init</code> asks you what a good result looks like, then proposes test cases and the checks that score them, tries the suite once, and writes the files. Every run, and every check that has a second model judge the reply, is a real model call on your account.</p>

  <Frame>
    <img className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/plugin-eval.jpg?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=913066f6d4a2a15426e98a627802f47f" alt="Terminal output of claude plugin eval: a table of seven cases with each case's score with and without the plugin, the delta between them, the run count, and the cost, followed by a summary line with the mean delta, total duration, and total cost" width="1600" height="900" data-path="images/whats-new/plugin-eval.jpg" />
  </Frame>

  <p className="digest-feature-try">From your plugin's root directory, have Claude draft the suite:</p>

  ```bash terminal theme={null}
  claude plugin eval init
  ```

  <p className="digest-feature-try">When Claude tells you the suite is ready, exit the session that <code>claude plugin eval init</code> opened and run <code>claude plugin eval .</code> to score every case. The summary table prints in your terminal, and <code>report.html</code> under <code>evals/results/</code> has the per-run detail.</p>

  <a className="digest-feature-link" href="/docs/en/plugin-evals">Test plugins with evals</a>
</div>

<div className="digest-feature">
  <div className="digest-feature-header">
    <span className="digest-feature-title">Pop Desktop panes out into their own windows</span>
    <span className="digest-feature-pill">Desktop</span>
  </div>

  <p className="digest-feature-lede">In the Claude Code Desktop app, you can pop any pane out into its own window. Drag the diff or terminal to a second screen while Claude keeps working in the main window, then dock the pane back when you're done.</p>

  <Frame>
    <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/desktop-pop-out-panes.mp4?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=ff3770dd09bb15ed9cf17a460f3d1e23" data-path="images/whats-new/desktop-pop-out-panes.mp4" />
  </Frame>

  <a className="digest-feature-link" href="/docs/en/desktop#arrange-your-workspace">Arrange your workspace</a>
</div>

<div className="digest-wins">
  <p className="digest-wins-title">Other wins</p>

  <div className="digest-wins-grid">
    <div>Set <a href="/docs/en/settings-reference#maxeffortlevel"><code>maxEffortLevel</code></a> at the top level or per model under <code>modelSettings</code> to cap the effort level on every provider, including Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry; any higher level runs at the cap</div>
    <div>Point `--plugin-dir` at a folder of plugins to <a href="/docs/en/plugins#test-your-plugins-locally">load each immediate subfolder that has a manifest</a></div>
    <div>If WebFetch hasn't finished downloading a page within five minutes, <a href="/docs/en/tools-reference#webfetch-tool-behavior">the fetch fails with a deadline error</a> instead of hanging; set <code>CLAUDE\_CODE\_WEBFETCH\_DEADLINE\_MS</code> to change the deadline, or to <code>0</code> to remove the limit</div>
    <div>Pass `--json` to <code>claude plugin install</code>, <code>uninstall</code>, <code>update</code>, <code>enable</code>, or <code>disable</code> to print the result as <a href="/docs/en/plugins-reference#plugin-json-result">one JSON object on the last line of stdout</a></div>
    <div>When the auto mode classifier blocks an action, the reason Claude receives <a href="/docs/en/auto-mode-config#fix-a-denial-with-an-allow-rule-an-environment-entry-or-a-retry">usually names the rule that matched</a>, such as <code>\[Data Exfiltration]</code></div>
    <div>When you type <code>/</code> partway through a prompt, you can now pick from <a href="/docs/en/interactive-mode#complete-a-command-mid-prompt">a list of matching commands</a> instead of a single suggestion. The list opens as you type in fullscreen rendering. A plugin skill also matches on its name without the plugin prefix</div>
    <div>In the VS Code extension, click the agent count at the bottom of the prompt box to open the <a href="/docs/en/vs-code#use-the-prompt-box">agent map</a>, where you can open a subagent's read-only transcript or stop it</div>
    <div>In the VS Code extension, select <strong>Hooks</strong> or <strong>Permissions</strong> in the command menu's Customize section to <a href="/docs/en/vs-code#use-the-prompt-box">add or remove hooks and permission rules</a> in your user, project, and local settings</div>
    <div>Claude can pick a <a href="/docs/en/artifacts#create-an-artifact">browser-tab icon</a> to match each artifact it publishes</div>
    <div>In Claude Code on the web, take back a queued message in a cloud session before Claude reads it: remove it from the queue, or press <code>Esc</code> or <code>Up</code>, and the text returns to the message box</div>
  </div>
</div>

[Full changelog for v2.1.263–v2.1.269 →](/docs/en/changelog#2-1-263)

whats-new/index Changed · +24 / -0 lines