docs: Claude Code v2.1.274 - Projects: Claude-coordinated parallel cloud sessions (public beta)

content/claude/claude-science/changelog.md

@@ -7,6 +7,7 @@
 > Release notes for Claude Science, including new features, improvements, and bug fixes by version.
 
 <Update label="0.1.49" description="September 16, 2026">
+  * If your organization is in Anthropic's Life Sciences Verification Program (beta), you can now [choose a use case](/docs/claude-science/safeguards#choose-a-use-case) for your sessions
   * Saved credentials now reach Claude's code only when it asks for them and you approve. They're no longer present in every cell
   * Access Claude Science work saved on your computer from other sign-ins, from Home or Settings. Admins control it on Team and Enterprise plans
   * Claude can send you a short message, such as a link to a file, while it keeps working on a task

content/claude/claude-science/glossary.md

@@ -50,6 +50,8 @@ One-sentence definitions for the terms you meet in Claude Science, from artifact
 
 **SSH host**: a remote machine (server, cluster node, or a job submission host) added by its SSH name, that Claude can run jobs on, or dispatch jobs from.
 
+**[Use case](/docs/claude-science/safeguards#choose-a-use-case)**: a research purpose that Anthropic has approved for your organization under the Life Sciences Verification Program (beta); if you have more than one, you choose which one a session uses.
+
 **Version**: one immutable save of an artifact; saving again adds a new version on top instead of overwriting.
 
 **Workspace**: the per-session folder on disk where Claude's code reads and writes files before they are saved as artifacts.

content/claude/claude-science/safeguards.md

@@ -0,0 +1,35 @@
+> ## Documentation Index
+> Fetch the complete documentation index at: https://claude.com/docs/llms.txt
+> Use this file to discover all available pages before exploring further.
+
+# Safeguards
+
+> What happens when a model's safeguards flag a message, how to switch models automatically, and how to choose a use case under the Life Sciences Verification Program (beta).
+
+Claude models include safeguards that can flag a message and stop the response. Some are intentionally broad and can flag legitimate coding, cybersecurity, and biology work. See [Our Approach to User Safety](https://support.claude.com/en/articles/8106465-our-approach-to-user-safety) for more about these safeguards.
+
+## When safeguards flag a message
+
+When a model's safeguards flag a message, Claude Science pauses the session and shows a **Chat paused** card above the composer. If another model can continue, select **Retry with `<model>`** to retry on the model the card names. That model has its own safeguards. The session stays on it until you choose a different model in the composer.
+
+## Switch models automatically
+
+To have Claude Science retry without stopping at the **Chat paused** card, turn on the **Automatically switch models when a message is flagged** switch under **Settings** > **General** > **Model**. You can also select it on the card before you retry. Claude Science then retries a flagged message on another model right away and shows a notice that names the model it switched to. If no other model can continue, or after several automatic switches in one session, you see the **Chat paused** card instead. Automatic switching is off by default and applies to every session on this computer.
+
+## Life Sciences Verification Program (beta)
+
+Under Anthropic's Life Sciences Verification Program (beta), verified organizations on Team and Enterprise plans can use Claude models with fewer life sciences restrictions. Protections against the most serious misuse stay in place, and safeguards can still flag a message. [What is the Life Sciences Verification Program?](https://support.claude.com/en/articles/16975617) has the details, including which models it applies to and how an organization applies.
+
+## Choose a use case
+
+If you have access through the Life Sciences Verification Program (beta), your organization specified one or more approved research use cases. Claude Science sends a session's use case with the requests it makes for that session, so Claude's safeguards can apply the access approved for that work. Anthropic also monitors program usage against the scope your organization shared when it applied. See [What is the Life Sciences Verification Program?](https://support.claude.com/en/articles/16975617) for data retention and safety review.
+
+With one use case, Claude Science applies it to every session.
+
+With more than one use case, you choose one for each session:
+
+* Claude Science asks you to choose the one that matches your work when you first send a message in a session, unless you've set a default. Everyday tasks like writing or coding are allowed with any use case.
+* To switch during a session, open the model picker in the composer and select **Use case**.
+* To set a default on this computer, select **Set as default** when Claude Science offers it, or choose one from the **Default use case** menu under **Settings** > **General** > **Model**.
+
+The use case controls need version 0.1.49 or later of the Claude Science app. If you're up to date and don't see a use case, ask your organization's admin.

content/claude/cowork/changelog.md

@@ -6,6 +6,55 @@
 
 > Release notes for Claude Desktop
 
+<Update label="v2.2553.0" description="2026-09-17">
+  Bundled Claude Code version: 2.1.274.
+
+  **General**
+
+  * Changed the sidebar's Pinned list to show its first 20 items, with a Show more link for the rest.
+  * Fixed connector and extension tools in Cowork and Code sessions failing with "expected nonoptional" when Claude left out an optional parameter that has a default.
+  * Fixed plugins past the first 100 in a marketplace not opening from Customize.
+  * Fixed Read Aloud continuing to play the old response after you regenerate, edit, or retry a reply, and cutting off early when a server error ended the read.
+  * Fixed some extensions that use the built-in Node.js runtime stopping with a "Server disconnected" error right after they start.
+  * Fixed the app closing and then failing to reopen on some Windows-on-ARM (Snapdragon) PCs installed from the Microsoft Store package.
+  * Fixed update restarts ending Code tab sessions and MCP servers abruptly instead of shutting them down the way quitting does.
+  * Fixed re-enabled plugins sometimes turning themselves back off, and new sessions sometimes starting without a plugin that was shown as enabled.
+
+  **Code**
+
+  * Added file viewing to cloud sessions, so file links in the transcript open in the app, the Files pane can search the session's files, and the Background tasks panel shows background command output.
+  * Fixed `!` commands and a code block's Run being dropped when the terminal was not ready; they now run within seconds, use the selected terminal tab when it is idle, show as terminal rows when sent while Claude is still working, and no longer leave the session marked as running after their output is sent.
+  * Fixed a case where a session could stop accepting messages after the app relaunched or the computer slept, until the app was restarted.
+  * Fixed a routine created with every connector removed still using all of your connectors.
+  * Fixed new sessions sometimes taking minutes to start while another session's worktree was being cleaned up or recycled.
+  * Fixed Plan mode skipping permission prompts when the Bypass permissions option is on and the session fell back to an older bundled Claude Code CLI while an update downloaded.
+  * Fixed turns failing with "OAuth token has expired" hours into a session; the token is now renewed in the background, and when a fresh sign-in is genuinely required the app asks before sending and keeps your message.
+  * Fixed sessions in large repositories starting slowly, including repositories that use a `.worktreeinclude` file, and worktrees occasionally starting without their local settings files.
+
+  **Cowork**
+
+  * Fixed plugin skills that reference `${CLAUDE_PLUGIN_ROOT}` or `${CLAUDE_SKILL_DIR}` sometimes running their commands with those paths blank.
+  * Fixed preinstalled Node.js packages such as `pptxgenjs`, `docx`, `pdf-lib` and `sharp` not being found by `require()`.
+  * Fixed search and session loading crashing on very long conversations.
+  * Fixed stacked permission prompts sliding up under the mouse pointer right after one is answered, which could send the next click to the wrong prompt.
+  * Fixed workspace updates failing with "Not enough disk space" on computers that had enough room once the update replaced the previous version.
+
+  **3P**
+
+  * Added `allowedPluginMcpServers`: when set, Cowork, Chat and Code sessions connect only the plugin MCP servers whose URL matches an entry (an empty list allows none), in addition to `managedMcpServers` and organization plugins, even when `managedMcpServers` is empty; the app also stops starting plugin MCP servers on the device, except for organization plugins. The Setup window can now author an empty list for this key and for `allowedWorkspaceFolders`.
+  * Added `builtinBrowserEnabled` to offer a built-in browser in Cowork and Code sessions, with `builtinBrowserDefaultDomainPolicy`, `builtinBrowserAllowedDomains`, and `builtinBrowserBlockedDomains` to control which sites Claude may open in it.
+  * Added `inferenceCredentialHelperWindows`: the absolute path of the credential helper executable on Windows devices, used there instead of `inferenceCredentialHelper`, so one configuration can serve Windows and macOS or Linux devices.
+  * Added a Salesforce preset to the plugin marketplace picker in the Setup window.
+  * Changed `inferenceFoundryResource`: a value delivered by a bootstrap URL the user configured themselves (in Settings or a local configuration file) now asks that user to approve it before it takes effect, as the Foundry base URL and the other providers' endpoints already do, and declining quits the app. Because the resource name is required, each such Foundry install prompts once after updating. Values delivered through device management, or by a bootstrap URL that device management set or that `trustBootstrapDelivery: true` covers, are unchanged and never prompt.
+  * Updated Customize to a full page with redesigned Skills, Plugins and Connectors lists (search, an Add menu, a page per item) in place of the old tables in Settings; Memory moved under Settings.
+  * Fixed a `Bash` entry in `disabledBuiltinTools` or `builtinToolPolicy` not applying to PowerShell commands on Windows PCs without Git for Windows; a `Bash(**)` entry is now treated as `Bash`.
+  * Fixed Settings > Desktop app > General on macOS offering a Voice shortcut that could not work; a Caps Lock or custom shortcut chosen earlier no longer opens the dictation bar.
+  * Fixed the app continuously re-fetching its configuration from the configuration server and re-testing the inference connection while the inference provider rejects the configured API key.
+  * Fixed the Code tab's `/status` card showing a placeholder account; it now shows your signed-in identity and the deployment name.
+  * Fixed the model list, organization configuration, or an MCP server occasionally failing to load right after launch when `egressProxyUrl` is set and the network is reachable only through that proxy.
+  * Fixed the model picker listing a model twice when a gateway's `/v1/models` endpoint returns both `<id>` and `<id>[1m]`; the pair now shows as the model and its 1M-context row.
+</Update>
+
 <Update label="v2.110.0" description="2026-09-15">
   **General**
 

content/claude/government/config/settings.md

@@ -142,6 +142,12 @@ Turning a switch off also changes this layout. For example, with **Chat in Claud
   This layout applies to Claude Desktop 1.26832.0 and later. Earlier versions show **Chat**, **Cowork**, and **Code** as three separate tabs, controlled by the same switches.
 </Note>
 
+The **Claude Desktop home** setting chooses what members see in Claude Desktop. **Standard** gives them Chat with file analysis, plus Cowork. **Simple** gives them Chat with file analysis, without Cowork. **Off** gives them neither, which leaves only Code. If you choose **Off**, keep Code turned on, or Claude Desktop has nothing to open. While the setting has a value, it overrides the separate Chat, file analysis, and Cowork switches at every level, including a directory group's. By default it is not set, and those switches apply.
+
+<Note>
+  **Claude Desktop home** needs Claude Desktop 1.52386.0 or later. Earlier versions ignore it and follow the switches.
+</Note>
+
 ### Member-added plugins and marketplaces
 
 Two switches that control whether members can add plugins of their own in Claude Desktop. **Let members add plugin marketplaces** lets members add plugin marketplaces and install plugins from them. **Let members add their own plugins** lets members upload plugin files or have Claude create a plugin for them. Both switches are off by default.

content/claude/third-party/claude-desktop/admin-console.md

@@ -105,6 +105,8 @@ The console refuses API keys, tokens, and secrets anywhere in the configuration,
 
 Most of these settings can also differ per group of users, on the **Permission policies** page under **People**, as described under [Per-group permission policies](#per-group-permission-policies).
 
+To turn on the built-in browser, open the **Capabilities** page in **Organization settings**, outside the **Desktop 3P** section, and turn on the **Built-in browser** switch under **Data sources**, as described under [Manage the built-in browser from the Enterprise Admin Console](/docs/third-party/claude-desktop/browser#manage-the-built-in-browser-from-the-enterprise-admin-console).
+
 ### Choose how users authenticate to your provider
 
 <Tip>