One read of Claude Code CLIclaude-code-20261020T183702Z
212 pages moved out of 228 read.
Pages moved
212
significant first
Pages read
228
in this capture
Captured
18:37 UTC
Corpus hash
f4a7dc09bf09
corpus-hash
What this read moved
201-212 of 212, page 9 of 9This capture is too large to show at once. Changes 201-212 of 212 are below, significant first; the rest are on the following screens.
whats-new/2026-w32 Changed · +36 / -70 lines
from line 2
22
33> Claude Code sessions message each other, self-hosted environments run cloud sessions on your infrastructure, and auto mode becomes the default permission mode.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-220">v2.1.220 → v2.1.224</a></span>
7 <span>3 features · August 3–7</span>
8</div>
5Releases [v2.1.220 → v2.1.224](/docs/en/changelog#2-1-220)
63 features · August 3–7
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">Cross-session messaging</span>
13 <span className="digest-feature-pill">v2.1.224</span>
14 </div>
8Cross-session messaging
9v2.1.224
1510
16 <p className="digest-feature-lede">Your Claude Code sessions can now message each other. Claude discovers your other sessions with the <code>ListAgents</code> tool and sends with <code>SendMessage</code>, either when you ask it to or on its own, such as after a change in one session affects what another is working on. A message is text Claude writes for the other session, never your conversation history or files. Available on macOS and Linux. Requires v2.1.224 or later.</p>
11Your Claude Code sessions can now message each other. Claude discovers your other sessions with the `ListAgents` tool and sends with `SendMessage`, either when you ask it to or on its own, such as after a change in one session affects what another is working on. A message is text Claude writes for the other session, never your conversation history or files. Available on macOS and Linux. Requires v2.1.224 or later.
1712
18 <Frame>
19 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/cross-session-messaging.mp4?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=8f33c3390f78660a4a26dc980f46159f" data-path="images/whats-new/cross-session-messaging.mp4" />
20 </Frame>
13<video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/cross-session-messaging.mp4?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=8f33c3390f78660a4a26dc980f46159f" />
2114
22 <p className="digest-feature-try">With two sessions open on the same machine, ask one of them to pass something along:</p>
15With two sessions open on the same machine, ask one of them to pass something along:
2316
24 ```text title="Claude Code" wrap theme={null}
25 Tell the session working on the payments API that users.name is now users.display_name
26 ```
17```text title="Claude Code" wrap theme={null}
18Tell the session working on the payments API that users.name is now users.display_name
19```
2720
28 <p className="digest-feature-try">The other session shows a <code>Message from</code> row once Claude has read the message; press <code>Ctrl+O</code> to expand it. To see which sessions Claude can reach, run <code>/list-agents</code>.</p>
21The other session shows a `Message from` row once Claude has read the message; press `Ctrl+O` to expand it. To see which sessions Claude can reach, run `/list-agents`.
2922
30 <a className="digest-feature-link" href="/docs/en/cross-session-messaging#message-another-session">Message another session</a>
31</div>
23[Message another session](/docs/en/cross-session-messaging#message-another-session)
3224
33<div className="digest-feature">
34 <div className="digest-feature-header">
35 <span className="digest-feature-title">Self-hosted environments</span>
36 <span className="digest-feature-pill">v2.1.224</span>
37 </div>
25Self-hosted environments
26v2.1.224
3827
39 <p className="digest-feature-lede">Self-hosted environments run Claude Code cloud sessions on your organization's own infrastructure, in public beta on Team and Enterprise plans. Run <code>claude self-hosted-runner</code> on your machines or containers to turn them into runners. When someone picks your environment while starting a session from claude.ai, the mobile or desktop apps, or `claude --cloud`, that session runs inside your network, with access to your internal services. An Owner turns on <strong>Allow self-hosted environments</strong> in <a href="https://claude.ai/admin-settings/cloud-environments">admin settings</a> first.</p>
28Self-hosted environments run Claude Code cloud sessions on your organization's own infrastructure, in public beta on Team and Enterprise plans. Run `claude self-hosted-runner` on your machines or containers to turn them into runners. When someone picks your environment while starting a session from claude.ai, the mobile or desktop apps, or `claude --cloud`, that session runs inside your network, with access to your internal services. An Owner turns on **Allow self-hosted environments** in [admin settings](https://claude.ai/admin-settings/cloud-environments) first.
4029
41 <Frame>
42 <img className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/self-hosted-environments.jpg?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=ae9152cb1670c8af517d1aee57689b14" alt="The self-hosted environments admin page listing environments such as linux-dev and macos-prod with their status and active session counts" width="2048" height="1152" data-path="images/whats-new/self-hosted-environments.jpg" />
43 </Frame>
30
4431
45 <p className="digest-feature-try">Signed in as an Owner, run the guided setup, which walks you through creating the environment and starts a runner:</p>
32Signed in as an Owner, run the guided setup, which walks you through creating the environment and starts a runner:
4633
47 ```bash terminal theme={null}
48 claude self-hosted-runner setup
49 ```
34```bash terminal theme={null}
35claude self-hosted-runner setup
36```
5037
51 <p className="digest-feature-try">The environment shows <strong>Healthy</strong> in admin settings once the runner registers.</p>
38The environment shows **Healthy** in admin settings once the runner registers.
5239
53 <a className="digest-feature-link" href="/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner">Self-hosted environments quickstart</a>
54</div>
40[Self-hosted environments quickstart](/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner)
5541
56<div className="digest-feature">
57 <div className="digest-feature-header">
58 <span className="digest-feature-title">Auto mode becomes the default</span>
59 <span className="digest-feature-pill">CLI</span>
60 </div>
42Auto mode becomes the default
43CLI
6144
62 <p className="digest-feature-lede">Starting August 14, auto mode is the default permission mode for new sessions on Pro, Max, and Team plans. If you set a default mode yourself, it stays in place unless you accept the one-time switch prompt, and a default your organization manages doesn't change. You can still switch modes at any time. Already in effect on those plans: the classifier calls auto mode makes no longer count toward your usage limits.</p>
45Starting August 14, auto mode is the default permission mode for new sessions on Pro, Max, and Team plans. If you set a default mode yourself, it stays in place unless you accept the one-time switch prompt, and a default your organization manages doesn't change. You can still switch modes at any time. Already in effect on those plans: the classifier calls auto mode makes no longer count toward your usage limits.
6346
64 <p className="digest-feature-try">To start every session in auto mode before the switch, set it as your default in your user settings:</p>
47To start every session in auto mode before the switch, set it as your default in your user settings:
6548
66 ```json ~/.claude/settings.json {3} theme={null}
67 {
68 "permissions": {
69 "defaultMode": "auto"
70 }
49```json ~/.claude/settings.json {3} theme={null}
50{
51 "permissions": {
52 "defaultMode": "auto"
7153 }
72 ```
54}
55```
7356
74 <p className="digest-feature-try">New sessions then show <code>auto mode on</code> in the status bar.</p>
57New sessions then show `auto mode on` in the status bar.
7558
76 <a className="digest-feature-link" href="/docs/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode requirements and controls</a>
77</div>
59[Auto mode requirements and controls](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
7860
79<div className="digest-wins">
80 <p className="digest-wins-title">Other wins</p>
61Other wins
8162
82 <div className="digest-wins-grid">
83 <div>The VS Code extension gets <a href="/docs/en/vs-code#extension-settings">Focus view</a>, which hides tool activity behind one expandable row per turn; toggle it from the command menu or with <code>Ctrl+Alt+F</code> (<code>Ctrl+Option+F</code> on Mac)</div>
84 <div>Sandbox credential files accept <a href="/docs/en/sandboxing#mask-credential-files"><code>mode: "mask"</code></a> on Linux and WSL2, so sandboxed commands read a sentinel copy while the sandbox proxy substitutes the real value on egress; credential masking also gains <code>extract</code>, JWT-aware <code>decode</code>, and AWS SigV4 re-signing options</div>
85 <div>Marketplaces can distribute a plugin as a <a href="/docs/en/plugins/marketplace-reference#archive-plugin-source">zip archive</a> with the new <code>archive</code> source, downloaded over HTTPS with an optional SHA-256 pin, so installs work without git or npm</div>
86 <div><code>/review</code> is now an alias of <a href="/docs/en/code-review-local"><code>/code-review</code></a>, and <code>/code-review</code> with no effort level reuses the level you typed last</div>
87 <div>A session you copy with <a href="/docs/en/agent-view#copy-the-session-with-%2Ffork"><code>/fork</code></a> now makes its code changes in a worktree of its own instead of the original session's checkout</div>
88 <div>Plugins you install from <a href="/docs/en/plugins/install#install-a-plugin"><code>/plugin</code></a> activate in the current session when it's safe to do so; the install summary reports <code>Plugin is now active.</code> or tells you to run <code>/reload-plugins</code></div>
89 <div><a href="/docs/en/agent-view#how-file-edits-are-isolated">Background sessions</a> that changed code in a worktree now commit and push before finishing, open a draft pull request only when the task calls for one, and follow the git instructions in your <code>CLAUDE.md</code></div>
90 <div>The 200-subagent-per-session cap is removed, so long-running sessions no longer refuse new subagents; the <a href="/docs/en/sub-agents#concurrent-subagent-limit">concurrency</a> and depth limits still apply</div>
91 <div>A repository's checked-in settings can no longer turn on <a href="/docs/en/remote-control#enable-remote-control-for-all-sessions">Remote Control auto-connect</a>; set <code>remoteControlAtStartup</code> in your user or managed settings instead, and project and local settings can only turn it off</div>
92 <div><a href="/docs/en/worktrees#how-claude-code-enforces-isolation">Worktree isolation</a> now blocks not only file edits but also Bash commands and git redirects that reach the main checkout, in every session type and in the session's subagents</div>
93 <div>A Bash command can no longer hide part of itself from permission checks, and tab or invisible-Unicode padding no longer hides part of a command from the approval dialog</div>
94 <div>PreToolUse auto-allow hooks no longer bypass tool restrictions in Claude Code's internal side tasks such as summaries and compaction</div>
95 <div>The <a href="/docs/en/ultraplan">Ultraplan</a> research preview is removed, including the <code>/ultraplan</code> command and the <code>ultraplan</code> keyword; use plan mode or Claude Code on the web instead</div>
96 </div>
97</div>
63The VS Code extension gets [Focus view](/docs/en/vs-code#extension-settings), which hides tool activity behind one expandable row per turn; toggle it from the command menu or with `Ctrl+Alt+F` (`Ctrl+Option+F` on Mac)Sandbox credential files accept [`mode: "mask"`](/docs/en/sandboxing#mask-credential-files) on Linux and WSL2, so sandboxed commands read a sentinel copy while the sandbox proxy substitutes the real value on egress; credential masking also gains `extract`, JWT-aware `decode`, and AWS SigV4 re-signing optionsMarketplaces can distribute a plugin as a [zip archive](/docs/en/plugins/marketplace-reference#archive-plugin-source) with the new `archive` source, downloaded over HTTPS with an optional SHA-256 pin, so installs work without git or npm`/review` is now an alias of [`/code-review`](/docs/en/code-review-local), and `/code-review` with no effort level reuses the level you typed lastA session you copy with [`/fork`](/docs/en/agent-view#copy-the-session-with-%2Ffork) now makes its code changes in a worktree of its own instead of the original session's checkoutPlugins you install from [`/plugin`](/docs/en/plugins/install#install-a-plugin) activate in the current session when it's safe to do so; the install summary reports `Plugin is now active.` or tells you to run `/reload-plugins`[Background sessions](/docs/en/agent-view#how-file-edits-are-isolated) that changed code in a worktree now commit and push before finishing, open a draft pull request only when the task calls for one, and follow the git instructions in your `CLAUDE.md`The 200-subagent-per-session cap is removed, so long-running sessions no longer refuse new subagents; the [concurrency](/docs/en/sub-agents#concurrent-subagent-limit) and depth limits still applyA repository's checked-in settings can no longer turn on [Remote Control auto-connect](/docs/en/remote-control#enable-remote-control-for-all-sessions); set `remoteControlAtStartup` in your user or managed settings instead, and project and local settings can only turn it off[Worktree isolation](/docs/en/worktrees#how-claude-code-enforces-isolation) now blocks not only file edits but also Bash commands and git redirects that reach the main checkout, in every session type and in the session's subagentsA Bash command can no longer hide part of itself from permission checks, and tab or invisible-Unicode padding no longer hides part of a command from the approval dialogPreToolUse auto-allow hooks no longer bypass tool restrictions in Claude Code's internal side tasks such as summaries and compactionThe [Ultraplan](/docs/en/ultraplan) research preview is removed, including the `/ultraplan` command and the `ultraplan` keyword; use plan mode or Claude Code on the web instead
9864
9965[Full changelog for v2.1.220–v2.1.224 →](/docs/en/changelog#2-1-220)
10066
whats-new/2026-w33 Changed · +28 / -58 lines
from line 2
22
33> Claude Code Desktop auto-continues after a usage limit resets, fork mode turns on by default, and GitLab merge requests and marketplaces join GitHub.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-225">v2.1.225 → v2.1.233</a></span>
7 <span>3 features · August 10–14</span>
8</div>
5Releases [v2.1.225 → v2.1.233](/docs/en/changelog#2-1-225)
63 features · August 10–14
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">Auto-continue after a usage limit on Desktop</span>
13 <span className="digest-feature-pill">Desktop</span>
14 </div>
8Auto-continue after a usage limit on Desktop
9Desktop
1510
16 <p className="digest-feature-lede">When you hit your session limit in the Code tab of Claude Code Desktop, the limit card now offers an <strong>Auto-continue when limits reset</strong> checkbox. Check it, and the Desktop app retries the interrupted turn after the reset. The card shows the retry time. The weekly-limit card doesn't offer it.</p>
11When you hit your session limit in the Code tab of Claude Code Desktop, the limit card now offers an **Auto-continue when limits reset** checkbox. Check it, and the Desktop app retries the interrupted turn after the reset. The card shows the retry time. The weekly-limit card doesn't offer it.
1712
18 <Frame>
19 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/desktop-auto-continue.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=1937f489695feaea715e48ecfd7e62cd" data-path="images/whats-new/desktop-auto-continue.mp4" />
20 </Frame>
13<video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/desktop-auto-continue.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=1937f489695feaea715e48ecfd7e62cd" />
2114
22 <p className="digest-feature-try">The next time a session-limit card appears, check <strong>Auto-continue when limits reset</strong> and leave the session open. The card shows <code>Auto-resuming at</code> followed by the reset time, and the turn picks up on its own once the limit resets.</p>
15The next time a session-limit card appears, check **Auto-continue when limits reset** and leave the session open. The card shows `Auto-resuming at` followed by the reset time, and the turn picks up on its own once the limit resets.
2316
24 <a className="digest-feature-link" href="/docs/en/errors#youve-hit-your-session-limit">What to do when you hit a usage limit</a>
25</div>
17[What to do when you hit a usage limit](/docs/en/errors#youve-hit-your-session-limit)
2618
27<div className="digest-feature">
28 <div className="digest-feature-header">
29 <span className="digest-feature-title">Fork mode on by default</span>
30 <span className="digest-feature-pill">v2.1.232</span>
31 </div>
19Fork mode on by default
20v2.1.232
3221
33 <p className="digest-feature-lede">Fork mode is now on by default in interactive sessions. Claude can request the <code>fork</code> subagent type, which inherits the full conversation and prompt cache instead of starting fresh, so you don't have to re-explain the context for a side task. Subagents Claude spawns in interactive sessions, apart from the ones an agent-team teammate spawns, also run in the background by default.</p>
22Fork mode is now on by default in interactive sessions. Claude can request the `fork` subagent type, which inherits the full conversation and prompt cache instead of starting fresh, so you don't have to re-explain the context for a side task. Subagents Claude spawns in interactive sessions, apart from the ones an agent-team teammate spawns, also run in the background by default.
3423
35 <p className="digest-feature-try">Start a fork yourself with a task that needs everything you've discussed so far:</p>
24Start a fork yourself with a task that needs everything you've discussed so far:
3625
37 ```text Claude Code theme={null}
38 > /subtask draft unit tests for the parser changes so far
39 ```
26```text Claude Code theme={null}
27> /subtask draft unit tests for the parser changes so far
28```
4029
41 <p className="digest-feature-try">The fork appears in the panel below your prompt and its result arrives in your conversation when it finishes. To turn fork mode off, set <code>CLAUDE\_CODE\_FORK\_SUBAGENT=0</code>.</p>
30The fork appears in the panel below your prompt and its result arrives in your conversation when it finishes. To turn fork mode off, set `CLAUDE_CODE_FORK_SUBAGENT=0`.
4231
43 <a className="digest-feature-link" href="/docs/en/sub-agents#turn-fork-mode-on-or-off">Turn fork mode on or off</a>
44</div>
32[Turn fork mode on or off](/docs/en/sub-agents#turn-fork-mode-on-or-off)
4533
46<div className="digest-feature">
47 <div className="digest-feature-header">
48 <span className="digest-feature-title">GitLab merge requests and marketplaces</span>
49 <span className="digest-feature-pill">v2.1.232</span>
50 </div>
34GitLab merge requests and marketplaces
35v2.1.232
5136
52 <p className="digest-feature-lede">Plugin marketplaces clone bare <code>gitlab.com</code> URLs, including nested subgroups. On v2.1.233 or later, pass a GitLab merge request URL to `--worktree` to branch from it, and the <code>claude agents</code> view labels sessions linked to a merge request as <code>!N</code>. Claude Code also redacts GitLab token families such as <code>glpat-</code> and <code>glrt-</code>, and protects the <code>glab</code> CLI's config store the same way it protects <code>gh</code>.</p>
37Plugin marketplaces clone bare `gitlab.com` URLs, including nested subgroups. On v2.1.233 or later, pass a GitLab merge request URL to `--worktree` to branch from it, and the `claude agents` view labels sessions linked to a merge request as `!N`. Claude Code also redacts GitLab token families such as `glpat-` and `glrt-`, and protects the `glab` CLI's config store the same way it protects `gh`.
5338
54 <p className="digest-feature-try">Start a session in a worktree branched from a merge request:</p>
39Start a session in a worktree branched from a merge request:
5540
56 ```bash terminal theme={null}
57 claude --worktree https://gitlab.com/group/project/-/merge_requests/42
58 ```
41```bash terminal theme={null}
42claude --worktree https://gitlab.com/group/project/-/merge_requests/42
43```
5944
60 <p className="digest-feature-try">When <code>origin</code> is on gitlab.com, Claude Code fetches <code>merge-requests/42/head</code> and opens the session on that branch in its own worktree.</p>
45When `origin` is on gitlab.com, Claude Code fetches `merge-requests/42/head` and opens the session on that branch in its own worktree.
6146
62 <a className="digest-feature-link" href="/docs/en/worktrees#branch-from-a-pull-request">Branch a worktree from a pull or merge request</a>
63</div>
47[Branch a worktree from a pull or merge request](/docs/en/worktrees#branch-from-a-pull-request)
6448
65<div className="digest-wins">
66 <p className="digest-wins-title">Other wins</p>
49Other wins
6750
68 <div className="digest-wins-grid">
69 <div>Type <code>@</code> in the prompt to <a href="/docs/en/cross-session-messaging#message-another-session">mention another Claude session</a> by name, and Claude messages it directly with <code>SendMessage</code>; a bare name that matches exactly one live session now delivers without a confirmation step</div>
70 <div>Interactive sessions on one machine keep <a href="/docs/en/cross-session-messaging#see-which-sessions-claude-can-reach">unique names</a>: if you start or rename a session with a name another live session already uses, Claude Code gives yours a <code>name-word-word</code> variant and tells you</div>
71 <div>Plugin marketplaces accept <a href="/docs/en/plugins/marketplace-reference#command-plugin-source"><code>command</code> sources</a>: a local command prints the plugin directory, which Claude Code re-resolves each session and applies without a restart</div>
72 <div>On Linux and WSL, set <a href="/docs/en/tools-reference#memory-limit-on-linux-and-wsl"><code>CLAUDE\_CODE\_TOOL\_MEMORY\_LIMIT</code></a> to a size such as <code>4G</code> to cap the memory Bash and PowerShell tool commands can use</div>
73 <div>The task-tracking tools, such as <code>TaskCreate</code>, <code>TaskUpdate</code>, and <code>TodoWrite</code>, are <a href="/docs/en/tools-reference#task-tool-availability">no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and later models in those families</a>; set <code>CLAUDE\_CODE\_ENABLE\_TODO\_TOOLS=1</code> to re-enable them</div>
74 <div><a href="/docs/en/code-review-local"><code>/code-review</code></a> at high, xhigh, and max effort now runs in a background agent like the other levels</div>
75 <div><a href="/docs/en/plugins/install#install-a-plugin"><code>/plugin install plugin\@marketplace</code></a> refreshes the marketplace first, so newly published plugins install without a manual marketplace update</div>
76 <div>Settings accept <a href="/docs/en/settings-reference#marketplace-key-aliases"><code>additionalMarketplaces</code> and <code>allowedMarketplaces</code></a> as aliases for <code>extraKnownMarketplaces</code> and <code>strictKnownMarketplaces</code></div>
77 <div>On newer models, Claude can <a href="/docs/en/tools-reference#write-tool-behavior">overwrite an existing file with the Write tool</a> without reading it first this session, matching the Edit tool's rules; older models require the read</div>
78 <div>The VS Code extension can <a href="/docs/en/vs-code#organize-sessions-into-groups">organize the sessions list into groups</a>: right-click to create, rename, or delete a group, and Cmd/Ctrl- or Shift-click to move several sessions at once</div>
79 <div>If your organization routes Claude Code through a <a href="/docs/en/claude-apps-gateway-spend-limits">Claude apps gateway with spend limits</a>, Claude Code shows the limit period, its reset time, and the operator's message when you reach the limit</div>
80 </div>
81</div>
51Type `@` in the prompt to [mention another Claude session](/docs/en/cross-session-messaging#message-another-session) by name, and Claude messages it directly with `SendMessage`; a bare name that matches exactly one live session now delivers without a confirmation stepInteractive sessions on one machine keep [unique names](/docs/en/cross-session-messaging#see-which-sessions-claude-can-reach): if you start or rename a session with a name another live session already uses, Claude Code gives yours a `name-word-word` variant and tells youPlugin marketplaces accept [`command` sources](/docs/en/plugins/marketplace-reference#command-plugin-source): a local command prints the plugin directory, which Claude Code re-resolves each session and applies without a restartOn Linux and WSL, set [`CLAUDE_CODE_TOOL_MEMORY_LIMIT`](/docs/en/tools-reference#memory-limit-on-linux-and-wsl) to a size such as `4G` to cap the memory Bash and PowerShell tool commands can useThe task-tracking tools, such as `TaskCreate`, `TaskUpdate`, and `TodoWrite`, are [no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and later models in those families](/docs/en/tools-reference#task-tool-availability); set `CLAUDE_CODE_ENABLE_TODO_TOOLS=1` to re-enable them[`/code-review`](/docs/en/code-review-local) at high, xhigh, and max effort now runs in a background agent like the other levels[`/plugin install plugin@marketplace`](/docs/en/plugins/install#install-a-plugin) refreshes the marketplace first, so newly published plugins install without a manual marketplace updateSettings accept [`additionalMarketplaces` and `allowedMarketplaces`](/docs/en/settings-reference#marketplace-key-aliases) as aliases for `extraKnownMarketplaces` and `strictKnownMarketplaces`On newer models, Claude can [overwrite an existing file with the Write tool](/docs/en/tools-reference#write-tool-behavior) without reading it first this session, matching the Edit tool's rules; older models require the readThe VS Code extension can [organize the sessions list into groups](/docs/en/vs-code#organize-sessions-into-groups): right-click to create, rename, or delete a group, and Cmd/Ctrl- or Shift-click to move several sessions at onceIf your organization routes Claude Code through a [Claude apps gateway with spend limits](/docs/en/claude-apps-gateway-spend-limits), Claude Code shows the limit period, its reset time, and the operator's message when you reach the limit
8252
8353[Full changelog for v2.1.225–v2.1.233 →](/docs/en/changelog#2-1-225)
8454
whats-new/2026-w34 Changed · +36 / -72 lines
from line 2
22
33> Draft editable UI artboards with the /design skill, set the Concise output style, and start a Claude Code session on your machine from your phone.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-234">v2.1.234 → v2.1.239</a></span>
7 <span>3 features · August 17–21</span>
8</div>
5Releases [v2.1.234 → v2.1.239](/docs/en/changelog#2-1-234)
63 features · August 17–21
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">/design</span>
13 <span className="digest-feature-pill">research preview</span>
14 </div>
8/design
9research preview
1510
16 <p className="digest-feature-lede">The <code>/design</code> skill brings Claude Design's artboard workflow into the CLI and Claude Code Desktop, built on artifacts. Run it with a brief and Claude publishes a canvas of editable artboards for your UI. Pick one, tweak it, then have Claude implement it. Available on Pro, Max, Team, and Enterprise. Requires v2.1.234 or later.</p>
11The `/design` skill brings Claude Design's artboard workflow into the CLI and Claude Code Desktop, built on artifacts. Run it with a brief and Claude publishes a canvas of editable artboards for your UI. Pick one, tweak it, then have Claude implement it. Available on Pro, Max, Team, and Enterprise. Requires v2.1.234 or later.
1712
18 <Frame>
19 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/design-skill.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=0b376a94227c14a4204af89c4c9fd7ac" data-path="images/whats-new/design-skill.mp4" />
20 </Frame>
13<video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/design-skill.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=0b376a94227c14a4204af89c4c9fd7ac" />
2114
22 <p className="digest-feature-try">Describe what you want designed and let Claude draft the options:</p>
15Describe what you want designed and let Claude draft the options:
2316
24 ```text Claude Code theme={null}
25 > /design redesign the composer based on what people actually use it for
26 ```
17```text Claude Code theme={null}
18> /design redesign the composer based on what people actually use it for
19```
2720
28 <p className="digest-feature-try">Claude prints a link to the published canvas. Open it, pick an artboard, and tell Claude which option to implement.</p>
21Claude prints a link to the published canvas. Open it, pick an artboard, and tell Claude which option to implement.
2922
30 <a className="digest-feature-link" href="/docs/en/artifacts#availability">Where artifacts are available</a>
31</div>
23[Where artifacts are available](/docs/en/artifacts#availability)
3224
33<div className="digest-feature">
34 <div className="digest-feature-header">
35 <span className="digest-feature-title">Concise output style</span>
36 <span className="digest-feature-pill">v2.1.237</span>
37 </div>
25Concise output style
26v2.1.237
3827
39 <p className="digest-feature-lede">Concise is a new built-in output style. Claude leads with the result and skips preamble and narration, while doing the work as thoroughly as in the Default style. When you ask for an explanation or more detail, Claude answers in full. Error reports, security warnings, and confirmations for destructive actions keep their complete content.</p>
28Concise is a new built-in output style. Claude leads with the result and skips preamble and narration, while doing the work as thoroughly as in the Default style. When you ask for an explanation or more detail, Claude answers in full. Error reports, security warnings, and confirmations for destructive actions keep their complete content.
4029
41 <Frame>
42 <video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/concise-output-style.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=dfb40ec8921ed1bc82eb629042a8ec17" data-path="images/whats-new/concise-output-style.mp4" />
43 </Frame>
30<video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/concise-output-style.mp4?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=dfb40ec8921ed1bc82eb629042a8ec17" />
4431
45 <p className="digest-feature-try">Turn it on under <strong>Output style</strong> in <code>/config</code>, or set it in your settings file:</p>
32Turn it on under **Output style** in `/config`, or set it in your settings file:
4633
47 ```json ~/.claude/settings.json {2} theme={null}
48 {
49 "outputStyle": "Concise"
50 }
51 ```
34```json ~/.claude/settings.json {2} theme={null}
35{
36 "outputStyle": "Concise"
37}
38```
5239
53 <p className="digest-feature-try">Run <code>/clear</code> or start a new session, and Claude's replies lead with the result.</p>
40Run `/clear` or start a new session, and Claude's replies lead with the result.
5441
55 <a className="digest-feature-link" href="/docs/en/output-styles#built-in-output-styles">Built-in output styles</a>
56</div>
42[Built-in output styles](/docs/en/output-styles#built-in-output-styles)
5743
58<div className="digest-feature">
59 <div className="digest-feature-header">
60 <span className="digest-feature-title">Start a session on your machine from your phone</span>
61 <span className="digest-feature-pill">mobile</span>
62 </div>
44Start a session on your machine from your phone
45mobile
6346
64 <p className="digest-feature-lede">Any machine running <code>claude remote-control</code> now shows up as a device card at the top of the Code tab in the Claude app. Remote Control is also out of research preview.</p>
47Any machine running `claude remote-control` now shows up as a device card at the top of the Code tab in the Claude app. Remote Control is also out of research preview.
6548
66 <Frame>
67 <img className="w-full" src="https://mintcdn.com/claude-code/2SnAdpL4dJ18nKb3/images/whats-new/remote-control-phone-start.jpg?fit=max&auto=format&n=2SnAdpL4dJ18nKb3&q=85&s=9f0ebedab23aa0e1732cc37782573907" alt="The Code tab in the Claude mobile app with a Devices section showing a connected MacBook as a device card above the sessions list" width="1206" height="895" data-path="images/whats-new/remote-control-phone-start.jpg" />
68 </Frame>
49
6950
70 <p className="digest-feature-try">Start Remote Control on the machine you want to reach, then open the Code tab on your phone:</p>
51Start Remote Control on the machine you want to reach, then open the Code tab on your phone:
7152
72 ```bash terminal theme={null}
73 claude remote-control
74 ```
53```bash terminal theme={null}
54claude remote-control
55```
7556
76 <p className="digest-feature-try">Your machine appears as a device card at the top of the Code tab. Tap it to pick a directory and start a session there.</p>
57Your machine appears as a device card at the top of the Code tab. Tap it to pick a directory and start a session there.
7758
78 <a className="digest-feature-link" href="/docs/en/remote-control#start-a-remote-control-session">Start a Remote Control session</a>
79</div>
59[Start a Remote Control session](/docs/en/remote-control#start-a-remote-control-session)
8060
81<div className="digest-wins">
82 <p className="digest-wins-title">Other wins</p>
61Other wins
8362
84 <div className="digest-wins-grid">
85 <div>Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off from the <strong>Continue automatically at usage limit</strong> row in <code>/config</code></div>
86 <div>The optional <a href="/docs/en/interactive-mode#check-spelling-as-you-type"><code>spellcheck</code> setting</a> underlines misspelled words in the prompt input as you type, using your installed <code>aspell</code>, <code>hunspell</code>, or <code>ispell</code></div>
87 <div>On a branch with an open GitLab merge request, with the <code>glab</code> CLI authenticated through <code>glab auth login</code>, the footer shows an <a href="/docs/en/interactive-mode#gitlab-merge-requests"><code>MR !N</code> badge</a> colored by whether the merge request is a draft, open, or mergeable</div>
88 <div>Change the effort level from your phone or claude.ai/code and it <a href="/docs/en/remote-control#what-connected-devices-see">applies to the session on your machine</a>; Remote Control sessions hosted by Desktop or VS Code also show connected devices the session's current permission mode</div>
89 <div>You can open <a href="/docs/en/permissions#manage-permissions"><code>/permissions</code></a> or run <code>/add-dir \<path></code> while Claude is working; permission rule changes apply to the rest of the current turn</div>
90 <div>When background tasks keep a <a href="/docs/en/goal#background-work-defers-evaluation"><code>/goal</code></a> waiting, Claude checks in on them after 30 minutes instead of waiting indefinitely and keeps checking in, at longer intervals while the session sits idle; set <code>CLAUDE\_CODE\_GOAL\_CHECKIN\_MINUTES=0</code> to opt out</div>
91 <div>Your own prompts now render markdown in the transcript, with highlighted code blocks, inline code, and lists, the same way replies do</div>
92 <div>The new <a href="/docs/en/model-config#set-a-default-model-for-new-sessions"><code>ANTHROPIC\_DEFAULT\_MODEL</code></a> environment variable sets the model new sessions start on; a <code>/model</code> pick still overrides it and persists across restarts</div>
93 <div>With the <code>notify\_when\_idle</code> input on <code>SendMessage</code>, Claude can ask another Claude Code session on the same machine to <a href="/docs/en/cross-session-messaging#get-a-notice-when-another-session-goes-idle">send one notice when it next goes idle</a></div>
94 <div>Set <a href="/docs/en/interactive-mode#make-ctrl-w-delete-back-to-whitespace"><code>keybindingFlavor</code></a> to <code>"readline"</code> to make <code>Ctrl+W</code> in the prompt delete back to the previous whitespace, as Bash does, instead of stopping at punctuation such as <code>/</code></div>
95 <div>On native Windows, your Claude Code sessions can now <a href="/docs/en/cross-session-messaging#availability">message each other</a> with <code>SendMessage</code> and find each other with <code>ListAgents</code>, as on macOS and Linux</div>
96 <div>Self-hosted runners accept `--defer-shutdown-max-min`, which <a href="/docs/en/self-hosted-environments-deploy#defer-the-drain-past-the-first-signal">keeps serving attached sessions</a> for a set number of minutes after SIGTERM</div>
97 <div>Self-hosted runners accept `--proxy-authorization-command` or `--proxy-authorization-file` to supply a fresh `Proxy-Authorization` header for <a href="/docs/en/self-hosted-environments-deploy#authenticate-to-an-egress-proxy">egress proxies that require one</a></div>
98 </div>
99</div>
63Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off from the **Continue automatically at usage limit** row in `/config`The optional [`spellcheck` setting](/docs/en/interactive-mode#check-spelling-as-you-type) underlines misspelled words in the prompt input as you type, using your installed `aspell`, `hunspell`, or `ispell`On a branch with an open GitLab merge request, with the `glab` CLI authenticated through `glab auth login`, the footer shows an [`MR !N` badge](/docs/en/interactive-mode#gitlab-merge-requests) colored by whether the merge request is a draft, open, or mergeableChange the effort level from your phone or claude.ai/code and it [applies to the session on your machine](/docs/en/remote-control#what-connected-devices-see); Remote Control sessions hosted by Desktop or VS Code also show connected devices the session's current permission modeYou can open [`/permissions`](/docs/en/permissions#manage-permissions) or run `/add-dir <path>` while Claude is working; permission rule changes apply to the rest of the current turnWhen background tasks keep a [`/goal`](/docs/en/goal#background-work-defers-evaluation) waiting, Claude checks in on them after 30 minutes instead of waiting indefinitely and keeps checking in, at longer intervals while the session sits idle; set `CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0` to opt outYour own prompts now render markdown in the transcript, with highlighted code blocks, inline code, and lists, the same way replies doThe new [`ANTHROPIC_DEFAULT_MODEL`](/docs/en/model-config#set-a-default-model-for-new-sessions) environment variable sets the model new sessions start on; a `/model` pick still overrides it and persists across restartsWith the `notify_when_idle` input on `SendMessage`, Claude can ask another Claude Code session on the same machine to [send one notice when it next goes idle](/docs/en/cross-session-messaging#get-a-notice-when-another-session-goes-idle)Set [`keybindingFlavor`](/docs/en/interactive-mode#make-ctrl-w-delete-back-to-whitespace) to `"readline"` to make `Ctrl+W` in the prompt delete back to the previous whitespace, as Bash does, instead of stopping at punctuation such as `/`On native Windows, your Claude Code sessions can now [message each other](/docs/en/cross-session-messaging#availability) with `SendMessage` and find each other with `ListAgents`, as on macOS and LinuxSelf-hosted runners accept `--defer-shutdown-max-min`, which [keeps serving attached sessions](/docs/en/self-hosted-environments-deploy#defer-the-drain-past-the-first-signal) for a set number of minutes after SIGTERMSelf-hosted runners accept `--proxy-authorization-command` or `--proxy-authorization-file` to supply a fresh `Proxy-Authorization` header for [egress proxies that require one](/docs/en/self-hosted-environments-deploy#authenticate-to-an-egress-proxy)
10064
10165[Full changelog for v2.1.234–v2.1.239 →](/docs/en/changelog#2-1-234)
10266
whats-new/2026-w35 Changed · +33 / -66 lines
from line 2
22
33> Resume terminal sessions in the Claude Code Desktop app, review feedback reports that Claude drafts for you, and start a session in restricted mode.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-240">v2.1.240 → v2.1.250</a></span>
7 <span>3 features · August 24–28</span>
8</div>
5Releases [v2.1.240 → v2.1.250](/docs/en/changelog#2-1-240)
63 features · August 24–28
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">Resume terminal sessions in the Desktop app</span>
13 <span className="digest-feature-pill">Desktop</span>
14 </div>
8Resume terminal sessions in the Desktop app
9Desktop
1510
16 <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>
11Type `/resume` 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.
1712
18 <Frame>
19 <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" />
20 </Frame>
13<video autoPlay muted loop playsInline 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" />
2114
22 <p className="digest-feature-try">In a Desktop session, run the command to list your terminal sessions:</p>
15In a Desktop session, run the command to list your terminal sessions:
2316
24 ```text Claude Code theme={null}
25 > /resume
26 ```
17```text Claude Code theme={null}
18> /resume
19```
2720
28 <p className="digest-feature-try">Select a session and press <code>Enter</code>. The conversation opens in the app where you left off.</p>
21Select a session and press `Enter`. The conversation opens in the app where you left off.
2922
30 <a className="digest-feature-link" href="/docs/en/desktop#coming-from-the-cli">Move between the CLI and Desktop</a>
31</div>
23[Move between the CLI and Desktop](/docs/en/desktop#coming-from-the-cli)
3224
33<div className="digest-feature">
34 <div className="digest-feature-header">
35 <span className="digest-feature-title">Claude-drafted feedback</span>
36 <span className="digest-feature-pill">CLI</span>
37 </div>
25Claude-drafted feedback
26CLI
3827
39 <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>
28When 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 `SendFeedback` 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.
4029
41 <Frame>
42 <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" />
43 </Frame>
30
4431
45 <p className="digest-feature-try">Run <code>/feedback</code> with no argument to open your queue of drafts from every session:</p>
32Run `/feedback` with no argument to open your queue of drafts from every session:
4633
47 ```text Claude Code theme={null}
48 > /feedback
49 ```
34```text Claude Code theme={null}
35> /feedback
36```
5037
51 <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>
38Select a draft, then edit, send, or discard it. To turn drafting off, set **Claude-drafted feedback** to `off` in `/config`.
5239
53 <a className="digest-feature-link" href="/docs/en/tools-reference#sendfeedback-tool-behavior">SendFeedback tool behavior</a>
54</div>
40[SendFeedback tool behavior](/docs/en/tools-reference#sendfeedback-tool-behavior)
5541
56<div className="digest-feature">
57 <div className="digest-feature-header">
58 <span className="digest-feature-title">Restricted mode</span>
59 <span className="digest-feature-pill">v2.1.248</span>
60 </div>
42Restricted mode
43v2.1.248
6144
62 <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>
45Restricted mode starts Claude Code without the built-in tools that run commands or code. Use it when an evaluation harness drives `claude` on a shared machine. Start it with `--restricted` or set `CLAUDE_CODE_RESTRICTED=1`. Claude Code also removes `WebFetch`, confines the file tools to the working directories, loads only managed settings and `--settings`, and refuses the `bypassPermissions` permission mode.
6346
64 <p className="digest-feature-try">Run a non-interactive query without the command-running tools:</p>
47Run a non-interactive query without the command-running tools:
6548
66 ```bash terminal theme={null}
67 claude --restricted -p "review src/ for SQL injection risks"
68 ```
49```bash terminal theme={null}
50claude --restricted -p "review src/ for SQL injection risks"
51```
6952
70 <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>
53To 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 `default` preset doesn't restore the removed tools.
7154
72 <a className="digest-feature-link" href="/docs/en/cli-reference#cli-flags">CLI flags</a>
73</div>
55[CLI flags](/docs/en/cli-reference#cli-flags)
7456
75<div className="digest-wins">
76 <p className="digest-wins-title">Other wins</p>
57Other wins
7758
78 <div className="digest-wins-grid">
79 <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>
80 <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>
81 <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>
82 <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>
83 <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>
84 <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>
85 <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>
86 <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>
87 <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>
88 <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>
89 <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>
90 <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>
91 </div>
92</div>
59Set the new [`modelPicker`](/docs/en/settings-reference#modelpicker) setting to extend or replace the `/model` picker's built-in list with your own ordered, labeled entries, including Amazon Bedrock or Google Cloud's Agent Platform model IDsSet [`promptCacheTtl`](/docs/en/prompt-caching#choose-the-ttl-yourself) to `1h` to keep a one-hour prompt cache on the main conversation when you use an API key or a cloud provider; `subagentPromptCacheTtl` sets the TTL for subagents and all other requests outside the main conversationOn Pro, Max, Team, and Enterprise plans, [`/usage`](/docs/en/costs#plan-usage-breakdown) adds a Loops breakdown: run count, total tokens, tokens per run, and last run for the `/loop` and scheduled tasks that used the most tokensOrganizations on contracted rates can set the [`modelPricing`](/docs/en/costs#report-spend-at-your-contracted-rates) managed setting so `/usage`, the status line, and OpenTelemetry report cost at those rates instead of list price`/login` offers **Sign in with your Console account** under the **Anthropic Console account** option, so members of Console organizations that don't allow API keys can sign in without creating oneRun `/permissions` and open the new [**Auto mode** tab](/docs/en/auto-mode-config#edit-rules-from-permissions) to view and edit auto mode classifier rules without opening a settings fileWhen auto mode is available, Bash permission prompts in the Manual and `acceptEdits` permission modes offer a [**Yes, and switch to auto mode**](/docs/en/permission-modes#switch-permission-modes) option; select it to approve the command and switch the session to auto modeAfter you [move a session with `/cd`](/docs/en/permissions#move-the-session-to-another-directory), the new directory's project settings, hooks, `.mcp.json` servers, skills, and subagents take effect immediately instead of on the next `--resume`In non-interactive sessions, including `-p` runs, Agent SDK runs, and cloud sessions, Claude Code [continues a response](/docs/en/errors#the-response-above-may-be-incomplete) that a server error, dropped connection, or stall cut off mid-stream, when the partial response contains text and no tool callsA subagent that stops at its `maxTurns` limit returns its output marked as partial, with a hint that Claude can [continue it with `SendMessage`](/docs/en/sub-agents#resume-subagents), instead of appearing finishedOn Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, sessions on the same machine can now [message each other](/docs/en/cross-session-messaging#availability), `/loop` can [choose its own interval](/docs/en/scheduled-tasks#let-claude-choose-the-interval), and `/model` and `/effort` apply immediately instead of after the turn endsThe 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
9360
9461[Full changelog for v2.1.240–v2.1.250 →](/docs/en/changelog#2-1-240)
9562
whats-new/2026-w36 Changed · +37 / -74 lines
from line 2
22
33> 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.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-251">v2.1.251 → v2.1.261</a></span>
7 <span>4 features · August 31 – September 4</span>
8</div>
5Releases [v2.1.251 → v2.1.261](/docs/en/changelog#2-1-251)
64 features · August 31 – September 4
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">Claude Fable 5.1</span>
13 <span className="digest-feature-pill">new model</span>
14 </div>
8Claude Fable 5.1
9new model
1510
16 <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>
11Claude Fable 5.1 is available in Claude Code with a 1M-token context window, and the `fable` alias now selects it. In Claude apps gateway sessions, `fable` still selects Fable 5. If your gateway serves Fable 5.1, run `/model claude-fable-5-1`. Requires v2.1.257 or later.
1712
18 <p className="digest-feature-try">Switch the current session to Fable 5.1 and save it as your default:</p>
13Switch the current session to Fable 5.1 and save it as your default:
1914
20 ```text Claude Code theme={null}
21 > /model fable
22 ```
15```text Claude Code theme={null}
16> /model fable
17```
2318
24 <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>
19On the Anthropic API, the picker lists Fable only once the server reports it available for your organization, but typing `/model fable` checks with the server directly.
2520
26 <a className="digest-feature-link" href="/docs/en/model-config#work-with-fable">Work with Fable</a>
27</div>
21[Work with Fable](/docs/en/model-config#work-with-fable)
2822
29<div className="digest-feature">
30 <div className="digest-feature-header">
31 <span className="digest-feature-title">Computer use runs in the background on Desktop</span>
32 <span className="digest-feature-pill">Desktop</span>
33 </div>
23Computer use runs in the background on Desktop
24Desktop
3425
35 <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>
26On 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.
3627
37 <Frame>
38 <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" />
39 </Frame>
28
4029
41 <a className="digest-feature-link" href="/docs/en/desktop#let-claude-use-your-computer">Let Claude use your computer</a>
42</div>
30[Let Claude use your computer](/docs/en/desktop#let-claude-use-your-computer)
4331
44<div className="digest-feature">
45 <div className="digest-feature-header">
46 <span className="digest-feature-title">Live diff panel in fullscreen rendering</span>
47 <span className="digest-feature-pill">v2.1.260</span>
48 </div>
32Live diff panel in fullscreen rendering
33v2.1.260
4934
50 <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>
35In fullscreen rendering, `/diff` 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.
5136
52 <Frame>
53 <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" />
54 </Frame>
37<video autoPlay muted loop playsInline src="https://mintcdn.com/claude-code/f9HTZGyMtxIFOUgt/images/whats-new/diff-panel.mp4?fit=max&auto=format&n=f9HTZGyMtxIFOUgt&q=85&s=9d7553c19e7f227891cd95f1f59d796d" />
5538
56 <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>
39With fullscreen rendering on, inside a git repository, and in a terminal at least 110 columns wide, toggle the panel:
5740
58 ```text Claude Code theme={null}
59 > /diff
60 ```
41```text Claude Code theme={null}
42> /diff
43```
6144
62 <p className="digest-feature-try">Run <code>/diff</code> again or click the <code>✕</code> in its header to close it.</p>
45Run `/diff` again or click the `✕` in its header to close it.
6346
64 <a className="digest-feature-link" href="/docs/en/interactive-mode#diff-panel">Diff panel</a>
65</div>
47[Diff panel](/docs/en/interactive-mode#diff-panel)
6648
67<div className="digest-feature">
68 <div className="digest-feature-header">
69 <span className="digest-feature-title">Find unused skills with /skill-doctor</span>
70 <span className="digest-feature-pill">CLI</span>
71 </div>
49Find unused skills with /skill-doctor
50CLI
7251
73 <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>
52`/skill-doctor` 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 [skill listing](/docs/en/skills#skill-descriptions-are-cut-short) 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 [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching).
7453
75 <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>
54Run it in an interactive session to open the report in the `/plugin` manager's **Stats** tab:
7655
77 ```text Claude Code theme={null}
78 > /skill-doctor
79 ```
56```text Claude Code theme={null}
57> /skill-doctor
58```
8059
81 <p className="digest-feature-try">In non-interactive mode with <code>-p</code>, Claude Code prints the report as text instead.</p>
60In non-interactive mode with `-p`, Claude Code prints the report as text instead.
8261
83 <a className="digest-feature-link" href="/docs/en/skills#find-unused-skills">Find unused skills</a>
84</div>
62[Find unused skills](/docs/en/skills#find-unused-skills)
8563
86<div className="digest-wins">
87 <p className="digest-wins-title">Other wins</p>
64Other wins
8865
89 <div className="digest-wins-grid">
90 <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>
91 <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>
92 <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>
93 <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>
94 <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>
95 <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>
96 <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>
97 <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>
98 <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>
99 <div>Seat-based Enterprise plans now <a href="/docs/en/model-config#default-model-setting">default to Opus 5</a></div>
100 <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>
101 <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>
102 </div>
103</div>
66A [`PreModelSwitch`](/docs/en/hooks#premodelswitch) hook can block a model switch you request, and a [`PostModelSwitch`](/docs/en/hooks#postmodelswitch) hook can add context for Claude after the session's model changes[`/cost`](/docs/en/costs#prompt-cache-statistics) adds a `Prompt cache (main)` 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 `prompt_cache` objectOrganizations can list HTTP and SSE MCP servers under the [`managedMcpServers`](/docs/en/managed-mcp#provide-servers-through-managed-settings) managed setting to give them to every user, in addition to the servers that users add on their own`/effort` and the `/model` picker now [save a separate effort level for each model](/docs/en/model-config#adjust-effort-level); press `s` instead of `Enter` to apply a level to the current session onlyBy default, the auto mode classifier [now also blocks](/docs/en/permission-modes#what-the-classifier-blocks-by-default) actions such as requesting credentials from the cloud instance-metadata endpoint or connecting to sibling containers that Claude didn't startIn auto mode, Claude Code asks you before Claude [first reads a file outside your working directories](/docs/en/permission-modes#first-read-outside-the-working-directories), with an option to block such reads from then onRaise [`bashOutputMaxChars`](/docs/en/settings-reference#bashoutputmaxchars) and [`taskOutputMaxChars`](/docs/en/settings-reference#taskoutputmaxchars), up to 128,000 characters, so Claude receives more of the output from a successful command or background task inlineThe prompt's [word-editing shortcuts follow readline](/docs/en/interactive-mode#make-ctrl-w-delete-back-to-whitespace) for everyone, and the `keybindingFlavor` setting no longer has any effect. `Ctrl+W` deletes back to the previous whitespace, and `Alt+B`, `Alt+F`, and `Alt+D` treat punctuation such as `/` and `.` as word breaksIf you set `defaultMode` to `"bypassPermissions"` in a project's `.claude/settings.json` or `.claude/settings.local.json`, it [no longer takes effect](/docs/en/permission-modes#which-mode-a-session-starts-in) and the session starts in Manual mode; set `"bypassPermissions"` in user or managed settings instead, or pass `--permission-mode`Seat-based Enterprise plans now [default to Opus 5](/docs/en/model-config#default-model-setting)In the VS Code extension, click the model name at the bottom of the prompt box to [open the model picker](/docs/en/vs-code#use-the-prompt-box)In the VS Code extension, select **Output styles** in the command menu's Customize section to [pick an output style](/docs/en/vs-code#use-the-prompt-box), including your custom ones
10467
10568[Full changelog for v2.1.251–v2.1.261 →](/docs/en/changelog#2-1-251)
10669
whats-new/2026-w37 Changed · +19 / -46 lines
from line 2
22
33> Test your plugins with claude plugin eval and pop Claude Code Desktop panes out into their own windows.
44
5<div className="digest-meta">
6 <span>Releases <a href="/docs/en/changelog#2-1-263">v2.1.263 → v2.1.269</a></span>
7 <span>2 features · September 7–11</span>
8</div>
5Releases [v2.1.263 → v2.1.269](/docs/en/changelog#2-1-263)
62 features · September 7–11
97
10<div className="digest-feature">
11 <div className="digest-feature-header">
12 <span className="digest-feature-title">Test plugins with claude plugin eval</span>
13 <span className="digest-feature-pill">v2.1.269</span>
14 </div>
8Test plugins with claude plugin eval
9v2.1.269
1510
16 <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>
11`claude plugin eval` 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. `claude plugin eval init` 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.
1712
18 <Frame>
19 <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" />
20 </Frame>
13
2114
22 <p className="digest-feature-try">From your plugin's root directory, have Claude draft the suite:</p>
15From your plugin's root directory, have Claude draft the suite:
2316
24 ```bash terminal theme={null}
25 claude plugin eval init
26 ```
17```bash terminal theme={null}
18claude plugin eval init
19```
2720
28 <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>
21When Claude tells you the suite is ready, exit the session that `claude plugin eval init` opened and run `claude plugin eval .` to score every case. The summary table prints in your terminal, and `report.html` under `evals/results/` has the per-run detail.
2922
30 <a className="digest-feature-link" href="/docs/en/plugin-evals">Test plugins with evals</a>
31</div>
23[Test plugins with evals](/docs/en/plugin-evals)
3224
33<div className="digest-feature">
34 <div className="digest-feature-header">
35 <span className="digest-feature-title">Pop Desktop panes out into their own windows</span>
36 <span className="digest-feature-pill">Desktop</span>
37 </div>
25Pop Desktop panes out into their own windows
26Desktop
3827
39 <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>
28In 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.
4029
41 <Frame>
42 <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" />
43 </Frame>
30<video autoPlay muted loop playsInline 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" />
4431
45 <a className="digest-feature-link" href="/docs/en/desktop#arrange-your-workspace">Arrange your workspace</a>
46</div>
32[Arrange your workspace](/docs/en/desktop#arrange-your-workspace)
4733
48<div className="digest-wins">
49 <p className="digest-wins-title">Other wins</p>
34Other wins
5035
51 <div className="digest-wins-grid">
52 <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>
53 <div>Point `--plugin-dir` at a folder of plugins to <a href="/docs/en/plugins/create#load-a-directory-or-archive-for-one-session">load each immediate subfolder that has a manifest</a></div>
54 <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>
55 <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/cli-reference#plugin-json-result">one JSON object on the last line of stdout</a></div>
56 <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>
57 <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>
58 <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>
59 <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>
60 <div>Claude can pick a <a href="/docs/en/artifacts#create-an-artifact">browser-tab icon</a> to match each artifact it publishes</div>
61 <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>
62 </div>
63</div>
36Set [`maxEffortLevel`](/docs/en/settings-reference#maxeffortlevel) at the top level or per model under `modelSettings` 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 capPoint `--plugin-dir` at a folder of plugins to [load each immediate subfolder that has a manifest](/docs/en/plugins/create#load-a-directory-or-archive-for-one-session)If WebFetch hasn't finished downloading a page within five minutes, [the fetch fails with a deadline error](/docs/en/tools-reference#webfetch-tool-behavior) instead of hanging; set `CLAUDE_CODE_WEBFETCH_DEADLINE_MS` to change the deadline, or to `0` to remove the limitPass `--json` to `claude plugin install`, `uninstall`, `update`, `enable`, or `disable` to print the result as [one JSON object on the last line of stdout](/docs/en/plugins/cli-reference#plugin-json-result)When the auto mode classifier blocks an action, the reason Claude receives [usually names the rule that matched](/docs/en/auto-mode-config#fix-a-denial-with-an-allow-rule-an-environment-entry-or-a-retry), such as `[Data Exfiltration]`When you type `/` partway through a prompt, you can now pick from [a list of matching commands](/docs/en/interactive-mode#complete-a-command-mid-prompt) 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 prefixIn the VS Code extension, click the agent count at the bottom of the prompt box to open the [agent map](/docs/en/vs-code#use-the-prompt-box), where you can open a subagent's read-only transcript or stop itIn the VS Code extension, select **Hooks** or **Permissions** in the command menu's Customize section to [add or remove hooks and permission rules](/docs/en/vs-code#use-the-prompt-box) in your user, project, and local settingsClaude can pick a [browser-tab icon](/docs/en/artifacts#create-an-artifact) to match each artifact it publishesIn 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 `Esc` or `Up`, and the text returns to the message box
6437
6538[Full changelog for v2.1.263–v2.1.269 →](/docs/en/changelog#2-1-263)
6639
whats-new/index Changed · +120 / -120 lines
from line 4
44
55The weekly dev digest highlights the features most likely to change how you work. Each entry includes runnable code, a short demo, and a link to the full docs. For every bug fix and minor improvement, see the [changelog](/docs/en/changelog).
66
7<Update label="Week 37" description="September 7–11, 2026" tags={["v2.1.263–v2.1.269"]}>
8 **`claude plugin eval`**: run your plugin against a suite of test cases, score the results, and compare against a no-plugin baseline. `claude plugin eval init` drafts the cases and graders for you.
7**Week 37**
98
10 Also this week: pop any **Claude Code Desktop pane** out into its own window and dock it back later; the **`maxEffortLevel`** setting caps the effort level on every provider; and a page that **WebFetch** hasn't finished downloading within five minutes fails instead of hanging.
9**`claude plugin eval`**: run your plugin against a suite of test cases, score the results, and compare against a no-plugin baseline. `claude plugin eval init` drafts the cases and graders for you.
1110
12 [Read the Week 37 digest →](/docs/en/whats-new/2026-w37)
13</Update>
11Also this week: pop any **Claude Code Desktop pane** out into its own window and dock it back later; the **`maxEffortLevel`** setting caps the effort level on every provider; and a page that **WebFetch** hasn't finished downloading within five minutes fails instead of hanging.
1412
15<Update label="Week 36" description="August 31 – September 4, 2026" tags={["v2.1.251–v2.1.261"]}>
16 **Claude Fable 5.1**: available in Claude Code with a 1M-token context window.
13[Read the Week 37 digest →](/docs/en/whats-new/2026-w37)
1714
18 Also this week: on Pro and Max plans, **computer use in the Desktop app** works in the background on macOS while you keep working; in fullscreen rendering, **`/diff`** opens a live panel beside the conversation that refreshes as Claude edits; and **`/skill-doctor`** shows what each of your skills costs in context and how often it gets used.
15**Week 36**
1916
20 [Read the Week 36 digest →](/docs/en/whats-new/2026-w36)
21</Update>
17**Claude Fable 5.1**: available in Claude Code with a 1M-token context window.
2218
23<Update label="Week 35" description="August 24–28, 2026" tags={["v2.1.240–v2.1.250"]}>
24 **Resume terminal sessions in the Desktop app**: type `/resume` in the Claude Code Desktop prompt box to pick up any session you started from the CLI, with the full conversation and context intact.
19Also this week: on Pro and Max plans, **computer use in the Desktop app** works in the background on macOS while you keep working; in fullscreen rendering, **`/diff`** opens a live panel beside the conversation that refreshes as Claude edits; and **`/skill-doctor`** shows what each of your skills costs in context and how often it gets used.
2520
26 Also this week: **Claude-drafted feedback** has Claude write up a feedback report when something goes wrong in a session, which you review and send from `/feedback`; **`--restricted`** starts a session without the command-running tools or your user and project settings, for evaluation harnesses on shared machines; and the **`modelPicker`** setting controls which models the `/model` picker lists.
21[Read the Week 36 digest →](/docs/en/whats-new/2026-w36)
2722
28 [Read the Week 35 digest →](/docs/en/whats-new/2026-w35)
29</Update>
23**Week 35**
3024
31<Update label="Week 34" description="August 17–21, 2026" tags={["v2.1.234–v2.1.239"]}>
32 **`/design`**: a research preview that brings Claude Design's artboard workflow into the CLI and Claude Code Desktop, built on artifacts, so Claude drafts editable artboards for your UI and implements the one you pick.
25**Resume terminal sessions in the Desktop app**: type `/resume` in the Claude Code Desktop prompt box to pick up any session you started from the CLI, with the full conversation and context intact.
3326
34 Also this week: the built-in **Concise output style** makes Claude lead with the result and skip preamble; any machine running `claude remote-control` shows up as a **device card** on your phone so you can start a session on it from the Code tab; and **`ANTHROPIC_DEFAULT_MODEL`** sets the model new sessions start on.
27Also this week: **Claude-drafted feedback** has Claude write up a feedback report when something goes wrong in a session, which you review and send from `/feedback`; **`--restricted`** starts a session without the command-running tools or your user and project settings, for evaluation harnesses on shared machines; and the **`modelPicker`** setting controls which models the `/model` picker lists.
3528
36 [Read the Week 34 digest →](/docs/en/whats-new/2026-w34)
37</Update>
29[Read the Week 35 digest →](/docs/en/whats-new/2026-w35)
3830
39<Update label="Week 33" description="August 10–14, 2026" tags={["v2.1.225–v2.1.233"]}>
40 **Auto-continue after a usage limit on Desktop**: when you hit your session limit in Claude Code Desktop, check **Auto-continue when limits reset** on the limit card and the app retries the interrupted turn once the limit resets.
31**Week 34**
4132
42 Also this week: **fork mode** is on by default in interactive sessions, so Claude can delegate a side task to a subagent that inherits the full conversation; **GitLab** merge request URLs work with `--worktree` and the `claude agents` view, and marketplaces clone bare `gitlab.com` URLs; and typing **`@`** in the prompt mentions another Claude session by name.
33**`/design`**: a research preview that brings Claude Design's artboard workflow into the CLI and Claude Code Desktop, built on artifacts, so Claude drafts editable artboards for your UI and implements the one you pick.
4334
44 [Read the Week 33 digest →](/docs/en/whats-new/2026-w33)
45</Update>
35Also this week: the built-in **Concise output style** makes Claude lead with the result and skip preamble; any machine running `claude remote-control` shows up as a **device card** on your phone so you can start a session on it from the Code tab; and **`ANTHROPIC_DEFAULT_MODEL`** sets the model new sessions start on.
4636
47<Update label="Week 32" description="August 3–7, 2026" tags={["v2.1.220–v2.1.224"]}>
48 **Cross-session messaging**: on macOS and Linux, your Claude Code sessions can now message each other, so Claude passes a finding or a decision from one session to another instead of you re-explaining it.
37[Read the Week 34 digest →](/docs/en/whats-new/2026-w34)
4938
50 Also this week: **self-hosted environments** run Claude Code cloud sessions on infrastructure your organization operates, in public beta on Team and Enterprise plans; **auto mode** becomes the default permission mode for new sessions on Pro, Max, and Team plans starting August 14; and the **VS Code extension** gets Focus view.
39**Week 33**
5140
52 [Read the Week 32 digest →](/docs/en/whats-new/2026-w32)
53</Update>
41**Auto-continue after a usage limit on Desktop**: when you hit your session limit in Claude Code Desktop, check **Auto-continue when limits reset** on the limit card and the app retries the interrupted turn once the limit resets.
5442
55<Update label="Week 30" description="July 20–24, 2026" tags={["v2.1.214–v2.1.219"]}>
56 **Claude Opus 5**: the new default Opus model in Claude Code, with a 1M-token context window and fast mode at \$10/\$50 per MTok.
43Also this week: **fork mode** is on by default in interactive sessions, so Claude can delegate a side task to a subagent that inherits the full conversation; **GitLab** merge request URLs work with `--worktree` and the `claude agents` view, and marketplaces clone bare `gitlab.com` URLs; and typing **`@`** in the prompt mentions another Claude session by name.
5744
58 Also this week: **Claude Code Desktop** opens an iOS Simulator pane in public beta so Claude can run your app and tap through it while you watch; the **Claude Security plugin** runs a multi-agent vulnerability scan of your codebase and turns the findings you pick into patches you apply yourself; and **`/code-review`** runs as a background subagent.
45[Read the Week 33 digest →](/docs/en/whats-new/2026-w33)
5946
60 [Read the Week 30 digest →](/docs/en/whats-new/2026-w30)
61</Update>
47**Week 32**
6248
63<Update label="Week 29" description="July 13–17, 2026" tags={["v2.1.207–v2.1.212"]}>
64 **Artifacts call your MCP connectors**: a published artifact can pull live data and take actions through each viewer's own MCP connectors when they open the page, and this week also adds public sharing links, editor roles on Team and Enterprise, and artifacts created from Claude Tag sessions.
49**Cross-session messaging**: on macOS and Linux, your Claude Code sessions can now message each other, so Claude passes a finding or a decision from one session to another instead of you re-explaining it.
6550
66 Also this week: **screen reader mode** replaces the visual terminal interface with plain, linear text for screen readers such as VoiceOver and NVDA; **`/fork`** copies your conversation into a new background session while you keep working; and **auto mode** no longer needs an opt-in variable on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry.
51Also this week: **self-hosted environments** run Claude Code cloud sessions on infrastructure your organization operates, in public beta on Team and Enterprise plans; **auto mode** becomes the default permission mode for new sessions on Pro, Max, and Team plans starting August 14; and the **VS Code extension** gets Focus view.
6752
68 [Read the Week 29 digest →](/docs/en/whats-new/2026-w29)
69</Update>
53[Read the Week 32 digest →](/docs/en/whats-new/2026-w32)
7054
71<Update label="Week 28" description="July 6–10, 2026" tags={["v2.1.202–v2.1.206"]}>
72 **In-app browser on Desktop**: Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any other site and interact with pages the same way it does with your local dev server previews.
55**Week 30**
7356
74 Also this week: **`/doctor`** is a full setup checkup that diagnoses issues and can fix them, with `/checkup` as its alias; **auto mode** blocks transcript tampering and asks before `rm -rf` on unresolved variables; and **agent view rows** show a colored state word and a classifier-written headline.
57**Claude Opus 5**: the new default Opus model in Claude Code, with a 1M-token context window and fast mode at \$10/\$50 per MTok.
7558
76 [Read the Week 28 digest →](/docs/en/whats-new/2026-w28)
77</Update>
59Also this week: **Claude Code Desktop** opens an iOS Simulator pane in public beta so Claude can run your app and tap through it while you watch; the **Claude Security plugin** runs a multi-agent vulnerability scan of your codebase and turns the findings you pick into patches you apply yourself; and **`/code-review`** runs as a background subagent.
7860
79<Update label="Week 27" description="June 29 – July 3, 2026" tags={["v2.1.195–v2.1.201"]}>
80 **Claude Sonnet 5**: the new default model for Pro, Team Standard, and Enterprise subscription seats, with top-tier coding and tool use at Sonnet pricing, a native 1M-token context window, and adaptive thinking on by default.
61[Read the Week 30 digest →](/docs/en/whats-new/2026-w30)
8162
82 Also this week: **Claude in Chrome** is generally available on all direct Anthropic plans; **subagents run in the background by default** so Claude keeps working while they run; **Claude Desktop on Linux** lands in beta on Ubuntu and Debian; and **`/radio`** tunes into Claude FM lo-fi radio.
63**Week 29**
8364
84 [Read the Week 27 digest →](/docs/en/whats-new/2026-w27)
85</Update>
65**Artifacts call your MCP connectors**: a published artifact can pull live data and take actions through each viewer's own MCP connectors when they open the page, and this week also adds public sharing links, editor roles on Team and Enterprise, and artifacts created from Claude Tag sessions.
8666
87<Update label="Week 26" description="June 22–26, 2026" tags={["v2.1.185–v2.1.193"]}>
88 **`claude mcp login`**: authenticate a configured MCP server from your shell instead of the interactive `/mcp` menu, and clear its stored credentials later with `claude mcp logout`.
67Also this week: **screen reader mode** replaces the visual terminal interface with plain, linear text for screen readers such as VoiceOver and NVDA; **`/fork`** copies your conversation into a new background session while you keep working; and **auto mode** no longer needs an opt-in variable on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry.
8968
90 Also this week: **shell mode responds to command output** (`! npm test` gets an explanation without a second prompt); **`/rewind`** can resume a conversation from before `/clear` was run; and **background subagents** now surface permission prompts in the main session instead of auto-denying.
69[Read the Week 29 digest →](/docs/en/whats-new/2026-w29)
9170
92 [Read the Week 26 digest →](/docs/en/whats-new/2026-w26)
93</Update>
71**Week 28**
9472
95<Update label="Week 25" description="June 15–19, 2026" tags={["v2.1.178–v2.1.183"]}>
96 **Artifacts**: turn a session's output into a live, shareable page on claude.ai that updates in place as the session works, now in beta on Team and Enterprise plans.
73**In-app browser on Desktop**: Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any other site and interact with pages the same way it does with your local dev server previews.
9774
98 Also this week: **deny and ask rules match tool parameters** with `Tool(param:value)`, for example `Agent(model:opus)`; **`/config key=value`** sets any setting from the prompt, in `-p` mode, and from Remote Control; and **auto mode blocks destructive git commands** when you didn't ask to discard local work.
75Also this week: **`/doctor`** is a full setup checkup that diagnoses issues and can fix them, with `/checkup` as its alias; **auto mode** blocks transcript tampering and asks before `rm -rf` on unresolved variables; and **agent view rows** show a colored state word and a classifier-written headline.
9976
100 [Read the Week 25 digest →](/docs/en/whats-new/2026-w25)
101</Update>
77[Read the Week 28 digest →](/docs/en/whats-new/2026-w28)
10278
103<Update label="Week 24" description="June 8–12, 2026" tags={["v2.1.166–v2.1.176"]}>
104 **`/cd`**: move the current session to a new working directory mid-conversation without rebuilding the prompt cache.
79**Week 27**
10580
106 Also this week: **sub-agents can spawn their own sub-agents** (background chains are capped at five levels deep); **`--safe-mode`** starts Claude Code with all customizations disabled for troubleshooting; and **`fallbackModel`** configures up to three fallback models tried in order.
81**Claude Sonnet 5**: the new default model for Pro, Team Standard, and Enterprise subscription seats, with top-tier coding and tool use at Sonnet pricing, a native 1M-token context window, and adaptive thinking on by default.
10782
108 [Read the Week 24 digest →](/docs/en/whats-new/2026-w24)
109</Update>
83Also this week: **Claude in Chrome** is generally available on all direct Anthropic plans; **subagents run in the background by default** so Claude keeps working while they run; **Claude Desktop on Linux** lands in beta on Ubuntu and Debian; and **`/radio`** tunes into Claude FM lo-fi radio.
11084
111<Update label="Week 23" description="June 1–5, 2026" tags={["v2.1.158–v2.1.165"]}>
112 **Auto mode on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry**: auto mode is now available on third-party providers for Opus 4.7 and Opus 4.8, replacing permission prompts with background safety checks.
85[Read the Week 27 digest →](/docs/en/whats-new/2026-w27)
11386
114 Also this week: **safer automatic edits** prompt before writing files that can run code in `acceptEdits` mode; **`/plugin list`** prints your installed plugins inline; and **version requirements** let managed deployments require an approved Claude Code version range.
87**Week 26**
11588
116 [Read the Week 23 digest →](/docs/en/whats-new/2026-w23)
117</Update>
89**`claude mcp login`**: authenticate a configured MCP server from your shell instead of the interactive `/mcp` menu, and clear its stored credentials later with `claude mcp logout`.
11890
119<Update label="Week 22" description="May 25–29, 2026" tags={["v2.1.150–v2.1.157"]}>
120 **Claude Opus 4.8**: the new default model for Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API accounts, with high effort by default and `/effort xhigh` for the hardest tasks.
91Also this week: **shell mode responds to command output** (`! npm test` gets an explanation without a second prompt); **`/rewind`** can resume a conversation from before `/clear` was run; and **background subagents** now surface permission prompts in the main session instead of auto-denying.
12192
122 Also this week: **dynamic workflows** orchestrate dozens to hundreds of subagents from a script Claude writes; the **security-guidance plugin** reviews Claude's changes for vulnerabilities as it works; and **fast mode** runs on Opus 4.8 at \$10/\$50 per MTok.
93[Read the Week 26 digest →](/docs/en/whats-new/2026-w26)
12394
124 [Read the Week 22 digest →](/docs/en/whats-new/2026-w22)
125</Update>
95**Week 25**
12696
127<Update label="Week 21" description="May 18–22, 2026" tags={["v2.1.143–v2.1.149"]}>
128 **Auto mode on the Pro plan**: auto mode now runs on Pro accounts and supports Sonnet 4.6 alongside Opus, replacing permission prompts with background safety checks.
97**Artifacts**: turn a session's output into a live, shareable page on claude.ai that updates in place as the session works, now in beta on Team and Enterprise plans.
12998
130 Also this week: **`/usage`** breaks down what drives your plan limits by skill, subagent, plugin, and MCP server; the new **`/code-review`** command reports correctness bugs; and **background sessions** appear in `/resume` and stay alive when pinned.
99Also this week: **deny and ask rules match tool parameters** with `Tool(param:value)`, for example `Agent(model:opus)`; **`/config key=value`** sets any setting from the prompt, in `-p` mode, and from Remote Control; and **auto mode blocks destructive git commands** when you didn't ask to discard local work.
131100
132 [Read the Week 21 digest →](/docs/en/whats-new/2026-w21)
133</Update>
101[Read the Week 25 digest →](/docs/en/whats-new/2026-w25)
134102
135<Update label="Week 20" description="May 11–15, 2026" tags={["v2.1.139–v2.1.142"]}>
136 **Agent view**: `claude agents` opens one screen for every Claude Code session, showing what's running, what's blocked on you, and what's done.
103**Week 24**
137104
138 Also this week: **`/goal`** keeps Claude working across turns until a completion condition holds; **fast mode** now runs on Opus 4.7 by default; and the **Rewind menu** can compress earlier context with "Summarize up to here".
105**`/cd`**: move the current session to a new working directory mid-conversation without rebuilding the prompt cache.
139106
140 [Read the Week 20 digest →](/docs/en/whats-new/2026-w20)
141</Update>
107Also this week: **sub-agents can spawn their own sub-agents** (background chains are capped at five levels deep); **`--safe-mode`** starts Claude Code with all customizations disabled for troubleshooting; and **`fallbackModel`** configures up to three fallback models tried in order.
142108
143<Update label="Week 19" description="May 4–8, 2026" tags={["v2.1.128–v2.1.136"]}>
144 **Plugins load from `.zip` archives and URLs**: `--plugin-dir` now accepts `.zip` files, and `--plugin-url` fetches a plugin archive for the current session.
109[Read the Week 24 digest →](/docs/en/whats-new/2026-w24)
145110
146 Also this week: **`worktree.baseRef`** chooses whether new worktrees branch from the remote default or local `HEAD`; **auto mode hard deny rules** block actions unconditionally regardless of allow exceptions; and **hooks see the active effort level** via `effort.level` and `$CLAUDE_EFFORT`.
111**Week 23**
147112
148 [Read the Week 19 digest →](/docs/en/whats-new/2026-w19)
149</Update>
113**Auto mode on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry**: auto mode is now available on third-party providers for Opus 4.7 and Opus 4.8, replacing permission prompts with background safety checks.
150114
151<Update label="Week 18" description="April 27 – May 1, 2026" tags={["v2.1.120–v2.1.126"]}>
152 **Windows without Git Bash**: Git for Windows is no longer required, and Claude Code uses PowerShell as the shell tool when Bash is absent.
115Also this week: **safer automatic edits** prompt before writing files that can run code in `acceptEdits` mode; **`/plugin list`** prints your installed plugins inline; and **version requirements** let managed deployments require an approved Claude Code version range.
153116
154 Also this week: **`claude ultrareview`** brings cloud code review to CI and scripts; **`claude project purge`** cleans up local state for a project; and pasting a **PR URL into `/resume`** finds the session that created it.
117[Read the Week 23 digest →](/docs/en/whats-new/2026-w23)
155118
156 [Read the Week 18 digest →](/docs/en/whats-new/2026-w18)
157</Update>
119**Week 22**
158120
159<Update label="Week 17" description="April 20–24, 2026" tags={["v2.1.114–v2.1.119"]}>
160 **`/ultrareview`** opens as a public research preview: a fleet of bug-hunting agents runs in the cloud and findings land back in your CLI or Desktop automatically.
121**Claude Opus 4.8**: the new default model for Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API accounts, with high effort by default and `/effort xhigh` for the hardest tasks.
161122
162 Also this week: **session recap** shows you what happened while a terminal was unfocused; **custom themes** let you build and ship color palettes from `/theme` or a plugin; and **Claude Code on the web** gets a redesign with a new sessions sidebar and drag-and-drop layout.
123Also this week: **dynamic workflows** orchestrate dozens to hundreds of subagents from a script Claude writes; the **security-guidance plugin** reviews Claude's changes for vulnerabilities as it works; and **fast mode** runs on Opus 4.8 at \$10/\$50 per MTok.
163124
164 [Read the Week 17 digest →](/docs/en/whats-new/2026-w17)
165</Update>
125[Read the Week 22 digest →](/docs/en/whats-new/2026-w22)
166126
167<Update label="Week 16" description="April 13–17, 2026" tags={["v2.1.105–v2.1.113"]}>
168 **Claude Opus 4.7** lands as the new default on Max and Team Premium, with a new `xhigh` effort level that's the recommended setting for most coding work and an interactive `/effort` slider to dial it in.
127**Week 21**
169128
170 Also this week: **Routines** on Claude Code on the web fire templated cloud agents from a schedule, GitHub event, or API call; **mobile push notifications** ping your phone when a long task finishes or Claude needs you; `/usage` shows what's driving your limits; and the CLI moves to native binaries.
129**Auto mode on the Pro plan**: auto mode now runs on Pro accounts and supports Sonnet 4.6 alongside Opus, replacing permission prompts with background safety checks.
171130
172 [Read the Week 16 digest →](/docs/en/whats-new/2026-w16)
173</Update>
131Also this week: **`/usage`** breaks down what drives your plan limits by skill, subagent, plugin, and MCP server; the new **`/code-review`** command reports correctness bugs; and **background sessions** appear in `/resume` and stay alive when pinned.
174132
175<Update label="Week 15" description="April 6–10, 2026" tags={["v2.1.92–v2.1.101"]}>
176 **Ultraplan** enters early preview: draft a plan in the cloud from your CLI, review and comment on it in a web editor, then run it remotely or pull it back local. The first run now auto-creates a cloud environment for you.
133[Read the Week 21 digest →](/docs/en/whats-new/2026-w21)
177134
178 Also this week: the **Monitor** tool streams background events into the conversation so Claude can tail logs and react live, `/loop` self-paces when you omit the interval, `/team-onboarding` packages your setup into a replayable guide, and `/autofix-pr` turns on PR auto-fix from your terminal.
135**Week 20**
179136
180 [Read the Week 15 digest →](/docs/en/whats-new/2026-w15)
181</Update>
137**Agent view**: `claude agents` opens one screen for every Claude Code session, showing what's running, what's blocked on you, and what's done.
182138
183<Update label="Week 14" description="March 30 – April 3, 2026" tags={["v2.1.86–v2.1.91"]}>
184 **Computer use** comes to the CLI in research preview: Claude can open native apps, click through UI, and verify changes from your terminal. Best for closing the loop on things only a GUI can verify.
139Also this week: **`/goal`** keeps Claude working across turns until a completion condition holds; **fast mode** now runs on Opus 4.7 by default; and the **Rewind menu** can compress earlier context with "Summarize up to here".
185140
186 Also this week: `/powerup` interactive lessons, flicker-free alt-screen rendering, a per-tool MCP result-size override up to 500K, and plugin executables on the Bash tool's `PATH`.
141[Read the Week 20 digest →](/docs/en/whats-new/2026-w20)
187142
188 [Read the Week 14 digest →](/docs/en/whats-new/2026-w14)
189</Update>
143**Week 19**
190144
191<Update label="Week 13" description="March 23–27, 2026" tags={["v2.1.83–v2.1.85"]}>
192 **Auto mode** lands in research preview: a classifier handles your permission prompts so safe actions run without interruption and risky ones get blocked. The middle ground between approving everything and `--dangerously-skip-permissions`.
145**Plugins load from `.zip` archives and URLs**: `--plugin-dir` now accepts `.zip` files, and `--plugin-url` fetches a plugin archive for the current session.
193146
194 Also this week: computer use in the Desktop app, PR auto-fix on Web, transcript search with `/`, a native PowerShell tool for Windows, and conditional `if` hooks.
147Also this week: **`worktree.baseRef`** chooses whether new worktrees branch from the remote default or local `HEAD`; **auto mode hard deny rules** block actions unconditionally regardless of allow exceptions; and **hooks see the active effort level** via `effort.level` and `$CLAUDE_EFFORT`.
195148
196 [Read the Week 13 digest →](/docs/en/whats-new/2026-w13)
197</Update>
149[Read the Week 19 digest →](/docs/en/whats-new/2026-w19)
150
151**Week 18**
152
153**Windows without Git Bash**: Git for Windows is no longer required, and Claude Code uses PowerShell as the shell tool when Bash is absent.
154
155Also this week: **`claude ultrareview`** brings cloud code review to CI and scripts; **`claude project purge`** cleans up local state for a project; and pasting a **PR URL into `/resume`** finds the session that created it.
156
157[Read the Week 18 digest →](/docs/en/whats-new/2026-w18)
158
159**Week 17**
160
161**`/ultrareview`** opens as a public research preview: a fleet of bug-hunting agents runs in the cloud and findings land back in your CLI or Desktop automatically.
162
163Also this week: **session recap** shows you what happened while a terminal was unfocused; **custom themes** let you build and ship color palettes from `/theme` or a plugin; and **Claude Code on the web** gets a redesign with a new sessions sidebar and drag-and-drop layout.
164
165[Read the Week 17 digest →](/docs/en/whats-new/2026-w17)
166
167**Week 16**
168
169**Claude Opus 4.7** lands as the new default on Max and Team Premium, with a new `xhigh` effort level that's the recommended setting for most coding work and an interactive `/effort` slider to dial it in.
170
171Also this week: **Routines** on Claude Code on the web fire templated cloud agents from a schedule, GitHub event, or API call; **mobile push notifications** ping your phone when a long task finishes or Claude needs you; `/usage` shows what's driving your limits; and the CLI moves to native binaries.
172
173[Read the Week 16 digest →](/docs/en/whats-new/2026-w16)
174
175**Week 15**
176
177**Ultraplan** enters early preview: draft a plan in the cloud from your CLI, review and comment on it in a web editor, then run it remotely or pull it back local. The first run now auto-creates a cloud environment for you.
178
179Also this week: the **Monitor** tool streams background events into the conversation so Claude can tail logs and react live, `/loop` self-paces when you omit the interval, `/team-onboarding` packages your setup into a replayable guide, and `/autofix-pr` turns on PR auto-fix from your terminal.
180
181[Read the Week 15 digest →](/docs/en/whats-new/2026-w15)
182
183**Week 14**
184
185**Computer use** comes to the CLI in research preview: Claude can open native apps, click through UI, and verify changes from your terminal. Best for closing the loop on things only a GUI can verify.
186
187Also this week: `/powerup` interactive lessons, flicker-free alt-screen rendering, a per-tool MCP result-size override up to 500K, and plugin executables on the Bash tool's `PATH`.
188
189[Read the Week 14 digest →](/docs/en/whats-new/2026-w14)
190
191**Week 13**
192
193**Auto mode** lands in research preview: a classifier handles your permission prompts so safe actions run without interruption and risky ones get blocked. The middle ground between approving everything and `--dangerously-skip-permissions`.
194
195Also this week: computer use in the Desktop app, PR auto-fix on Web, transcript search with `/`, a native PowerShell tool for Windows, and conditional `if` hooks.
196
197[Read the Week 13 digest →](/docs/en/whats-new/2026-w13)
198198
workflows Changed · +32 / -34 lines
from line 2
22
33> Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.
44
5<Note>
6 Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.
7</Note>
5> [!NOTE]
6>
7> Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.
88
99A dynamic workflow is a JavaScript script that orchestrates many [subagents](/docs/en/sub-agents) at once. Claude writes the script for the task you describe, and a runtime executes it in the background while your session stays responsive.
1010
from line 31
3131
3232The quickest way to see a workflow in action is to run `/deep-research`, the [built-in workflow](#bundled-workflows) Claude Code includes for investigating a question across many sources. You'll see agents work through a set of phases in the background while your session stays free, and get one report at the end instead of a turn-by-turn transcript.
3333
34<Steps>
35 <Step title="Run the workflow">
36 Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.
34**1. Run the workflow**
3735
38 ```text wrap theme={null}
39 /deep-research What changed in the Node.js permission model between v20 and v22?
40 ```
41 </Step>
36Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.
4237
43 <Step title="Allow workflows">
44 Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.
45 </Step>
38```text wrap theme={null}
39/deep-research What changed in the Node.js permission model between v20 and v22?
40```
4641
47 <Step title="Watch progress">
48 The run starts in the background. Run `/workflows` to open its progress view:
42**2. Allow workflows**
4943
50 ```text wrap theme={null}
51 /workflows
52 ```
44Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.
5345
54 If `/workflows` shows a list of runs instead, select the run you just started and press Enter. The view shows each phase with its agent count. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.
46**3. Watch progress**
5547
56 You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.
57 </Step>
48The run starts in the background. Run `/workflows` to open its progress view:
5849
59 <Step title="Read the report">
60 When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
50```text wrap theme={null}
51/workflows
52```
6153
62 When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
63 </Step>
64</Steps>
54If `/workflows` shows a list of runs instead, select the run you just started and press Enter. The view shows each phase with its agent count. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.
55
56You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.
57
58**4. Read the report**
59
60When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
61
62When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
6563
6664To run a workflow for your own task, [have Claude write one](#have-claude-write-a-workflow), and once a run does what you wanted you can [save it](#save-the-workflow-for-reuse) as a command of your own.
6765
worktrees Changed · +21 / -21 lines
### Git LFS files are pointer files in a worktree Claude Code created
from line 4
44
55A [git worktree](https://git-scm.com/docs/git-worktree) is a separate working directory with its own files and branch, sharing the same repository history and remote as your main checkout. Running each Claude Code session in its own worktree gives it a separate copy of the files to edit, so one session can build a feature while a second fixes a bug.
66
7<Note>
8 If you use another version control system or the desktop app, follow the instructions for your setup:
7> [!NOTE]
8>
9> If you use another version control system or the desktop app, follow the instructions for your setup:
10>
11> * **Other version control systems**: worktrees require a git repository; [configure hooks to replace the git logic](#non-git-version-control)
12> * **Desktop app**: see [Run a session in its own worktree](/docs/en/desktop#run-a-session-in-its-own-worktree)
913
10 * **Other version control systems**: worktrees require a git repository; [configure hooks to replace the git logic](#non-git-version-control)
11 * **Desktop app**: see [Run a session in its own worktree](/docs/en/desktop#run-a-session-in-its-own-worktree)
12</Note>
13
1414Worktrees are one of several ways to run Claude in parallel. They isolate file edits. [Subagents](/docs/en/sub-agents) split work up inside one session, and [cross-session messaging](/docs/en/cross-session-messaging) lets Claude pass findings between the sessions in your worktrees. See [Run agents in parallel](/docs/en/agents) to compare the approaches, or skip ahead to [Isolate subagents with worktrees](#isolate-subagents-with-worktrees) to use worktrees and subagents together.
1515
1616Most sessions need only the first two sections: [start Claude in a worktree](#start-claude-in-a-worktree), then [clean up when you exit](#clean-up-worktrees). Return to the rest of the page when you need to [resume a session](#resume-a-worktree-session), [change how worktrees are created](#customize-worktree-creation), or [debug a failure](#troubleshooting).
from line 27
2727
2828Interactive runs require [workspace trust](/docs/en/security): if you haven't run Claude in the directory before, run `claude` once there to accept the trust dialog, or `--worktree` exits with an error prompting you to. Non-interactive runs with `-p` skip the trust check, so `claude -p --worktree` proceeds without it.
2929
30<Tip>
31 Add `.claude/worktrees/` to your `.gitignore` so worktree contents don't appear as untracked files in your main checkout.
32</Tip>
30> [!TIP]
31>
32> Add `.claude/worktrees/` to your `.gitignore` so worktree contents don't appear as untracked files in your main checkout.
3333
3434### Set up the worktree environment
3535
from line 41
4141
4242When Claude enters a path outside the repository's `.claude/worktrees/` directory, Claude Code asks for your approval first, because the move takes the session's working directory, write access, and project configuration such as `CLAUDE.md` and settings to that location. An `EnterWorktree` [permission rule](/docs/en/permissions) or choosing "don't ask again" doesn't suppress this prompt; only `bypassPermissions` mode skips it. Before v2.1.206, Claude could enter any existing worktree path without asking.
4343
44<Note>
45 **Hook paths don't follow the worktree.** After Claude enters a worktree, Claude Code keeps `${CLAUDE_PROJECT_DIR}` in your [hooks](/docs/en/hooks#reference-scripts-by-path) where it was and passes the worktree path to them a different way:
44> [!NOTE]
45>
46> **Hook paths don't follow the worktree.** After Claude enters a worktree, Claude Code keeps `${CLAUDE_PROJECT_DIR}` in your [hooks](/docs/en/hooks#reference-scripts-by-path) where it was and passes the worktree path to them a different way:
47>
48> * **`${CLAUDE_PROJECT_DIR}` stays put**: it still points at the project root where the session started, so a hook command such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/check-style.sh` still runs the script in the main checkout.
49> * **`cwd` follows Claude**: the `cwd` field in the hook's [input JSON](/docs/en/hooks#common-input-fields) is the worktree root, and it moves again when Claude runs `cd`. Read it when a hook needs the worktree path.
4650
47 * **`${CLAUDE_PROJECT_DIR}` stays put**: it still points at the project root where the session started, so a hook command such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/check-style.sh` still runs the script in the main checkout.
48 * **`cwd` follows Claude**: the `cwd` field in the hook's [input JSON](/docs/en/hooks#common-input-fields) is the worktree root, and it moves again when Claude runs `cd`. Read it when a hook needs the worktree path.
49</Note>
50
5151## Clean up worktrees
5252
5353When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, uncommitted work inside checked-out submodules, and new commits. These rules apply to worktrees Claude created with git. For a worktree your [WorktreeCreate hook](/docs/en/hooks#worktreecreate) created, see [WorktreeRemove](/docs/en/hooks#worktreeremove) instead.
from line 72
7272* **`--fork-session`**: the forked session starts in the directory you launched Claude from, and Claude Code leaves the original session's worktree untouched.
7373* **Deleted worktree**: if the worktree directory no longer exists, Claude Code resumes the session in the directory you launched Claude from. It tells you the worktree is gone and clears the session's worktree binding.
7474
75<Note>
76 Before v2.1.212, a non-interactive resume stayed in the starting directory and `ExitWorktree` reported that there was no active worktree session to exit.
77</Note>
75> [!NOTE]
76>
77> Before v2.1.212, a non-interactive resume stayed in the starting directory and `ExitWorktree` reported that there was no active worktree session to exit.
7878
7979When Claude enters or exits a worktree that Claude Code created with git, the transcript follows: Claude Code records the session under the session's new working directory, the same way [`/cd`](/docs/en/commands) does, so `/desktop` and `--resume` find it there. Exiting moves it back the same way. A worktree created by a [`WorktreeCreate` hook](#non-git-version-control) keeps its transcript at the launch directory. Requires Claude Code v2.1.198 or later.
8080
from line 317
317317
318318Claude Code refuses to create a worktree when `.claude`, `.claude/worktrees`, or the worktree directory itself is a symlink, and the error names the symlinked path. Remove the symlink and retry. Before v2.1.212, if the repository already contained a committed symlink at one of those paths, worktree creation followed it and could create files outside the repository.
319319
320<h3 id="git-lfs-content-is-missing-from-a-worktree-claude-code-created">
321 Git LFS files are pointer files in a worktree Claude Code created
322</h3>
320### Git LFS files are pointer files in a worktree Claude Code created
323321
324322If you set up [Git LFS](https://git-lfs.com) with `git lfs install --local`, a worktree that Claude Code creates contains LFS pointer files instead of the real files. The `--local` flag writes the LFS filter into the repository's own `.git/config` rather than your global git config. A plain `git lfs install` writes to your global config and isn't affected. The same applies to any other [filter driver](https://git-scm.com/docs/gitattributes) defined in the repository's own config.
325323
from line 346
348346* **Says `it cannot be resumed or re-entered`**: nothing in this session vouches for the worktree from where you launched. Recreate it; the directory and its work remain on disk for manual recovery, and when the worktree has a parent checkout, resuming from there also works.
349347* **Says `it contains the protected checkout`**: the refused directory is a parent of your main checkout, such as your home directory. Don't delete it. Change the worktree path, such as the path your `WorktreeCreate` hook returns or the `EnterWorktree` target, so the worktree doesn't contain the checkout.
350348* **Says `the protected checkout <path> has a .git entry that could not be examined` or `has git metadata that could not be resolved`**: the problem is the main checkout's git metadata, not the worktree's. Don't delete the worktree, and ignore the message's trailing advice to recreate it, which doesn't apply to these two endings. Repair the main checkout, for example a permissions problem or a git `dubious ownership` refusal on its `.git`, and retry.
349
350 Before v2.1.302, with git 2.56 or later, the `could not be resolved` ending also appeared when the `<path>` after `the protected checkout` held a stray `.git` file. Stray here means the path on that file's `gitdir:` line doesn't lead to a valid git repository. To recover, [update Claude Code](/docs/en/setup#update-claude-code) and retry. When that `gitdir:` path no longer exists, you can also delete the `.git` file and retry.
351351* **Says `its recorded path has a network spelling`**: Claude Code never resumes into a worktree at a network path. Recreate the worktree at a local path.
352352* **Any other ending**: the message names the problem and its fix, such as removing a `core.worktree` redirect or recreating the worktree; follow it. Before deleting a directory whose message says its git identity could not be verified, address the named cause first, for example a symbolic link in the worktree's path or git itself failing to run, since the directory may be healthy. When you do recreate, salvage any changes you need from the old directory first; it stays on disk.
353353
zero-data-retention Changed · +6 / -6 lines
from line 4
44
55Zero Data Retention (ZDR) for Claude Code is available to qualified accounts on Claude for Enterprise. When ZDR is enabled, prompts and model responses generated during Claude Code sessions are processed in real time and not stored by Anthropic after the response is returned, except where needed to comply with law or combat misuse.
66
7<Note>
8 ZDR is not included in the standard Claude for Enterprise plan and cannot be enabled from your admin settings. It is available to qualified accounts and requires separate enablement by Anthropic. If your organization requires ZDR, [contact sales](https://www.anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=zero_data_retention_request) or your Anthropic account team to confirm eligibility.
9</Note>
7> [!NOTE]
8>
9> ZDR is not included in the standard Claude for Enterprise plan and cannot be enabled from your admin settings. It is available to qualified accounts and requires separate enablement by Anthropic. If your organization requires ZDR, [contact sales](https://www.anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=zero_data_retention_request) or your Anthropic account team to confirm eligibility.
1010
1111Claude for Enterprise organizations that have enabled HIPAA can bring the Claude Code CLI and the Code tab in Claude Desktop under their Business Associate Agreement (BAA) without ZDR once the HIPAA configuration is applied to Claude Code (local mode) and Cowork (local mode). See [Set up Claude Code (local mode) for a HIPAA-ready organization](/docs/en/hipaa-setup). Organizations without the HIPAA configuration still need ZDR for BAA coverage of Claude Code. See the [Implementation Guide](https://trust.anthropic.com/resources?s=l1wrssd9hsbi4gak0tp5a6\&name=%5Banthropic%5D-hipaa-ready-offering-implementation-guide) for a list of Eligible Services.
1212
from line 23
2323
2424ZDR covers Claude Code inference on Claude for Enterprise.
2525
26<Warning>
27 ZDR is enabled on a per-organization basis. Each new organization requires ZDR to be enabled separately by your Anthropic account team. ZDR does not automatically apply to new organizations created under the same account. Contact your account team to enable ZDR for any new organizations.
28</Warning>
26> [!WARNING]
27>
28> ZDR is enabled on a per-organization basis. Each new organization requires ZDR to be enabled separately by your Anthropic account team. ZDR does not automatically apply to new organizations created under the same account. Contact your account team to enable ZDR for any new organizations.
2929
3030### Route Claude Code traffic to your ZDR organization
3131
gateways Changed · +1 / -3 lines
from line 19
1919
2020The gateway authenticates the developer, applies whatever access and budget rules you configure, and forwards the request to your provider with the organization's credential. The provider can be Anthropic's API or a [cloud provider](/docs/en/third-party-integrations) such as Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry; the gateway's configuration decides. With Claude apps gateway, or another gateway that exposes a single Anthropic-format endpoint, changing provider doesn't require touching developer machines.
2121
22<Frame>
23 <img src="https://mintcdn.com/claude-code/-uq-4JE0W_JO5Er5/images/llm-gateway-flow.svg?fit=max&auto=format&n=-uq-4JE0W_JO5Er5&q=85&s=1c1a8dcc0cfcc3a58652cc8e28cd3e20" alt="Diagram showing Claude Code routing through a gateway. In a developer machines zone, the Claude Code CLI and VS Code extension send requests to the gateway address with a per-developer credential. In a zone labeled your infrastructure, the gateway handles authentication, usage tracking, budgets, and routing, and forwards requests with your organization's credential. In a model providers zone, a solid arrow leads to the provider you configure, shown as the Anthropic API, and dashed arrows lead to other provider options, illustrated with Amazon Bedrock, Google Cloud, and Microsoft Foundry as examples." width="780" height="322" data-path="images/llm-gateway-flow.svg" />
24</Frame>
22
2523
2624Two kinds of credential are involved:
2725
keybindings Changed · +3 / -1 lines
from line 8
88
99The keybindings configuration file is an object with a `bindings` array. Each block specifies a context and a map of keystrokes to actions.
1010
11<Note>Changes to the keybindings file are automatically detected and applied without restarting Claude Code.</Note>
11> [!NOTE]
12>
13> Changes to the keybindings file are automatically detected and applied without restarting Claude Code.
1214
1315| Field | Description |
1416| :- | :- |