Desktop application changeddesktop
Nearest release: v2.1.314, published 17 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 30 Oct 2026 17:44 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 30 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+77added
Lines−76removed
From line
4
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits97to this page, all time
The whole hunk
from line 4, old and new numbered
/
from line 4
44
55In the Claude Desktop app, Claude Code is the **Code** tab. The app also has chat and [Cowork](https://claude.com/product/cowork), which handles Dispatch and longer agentic work. This page is the reference for the Code tab.
66
7> **[Download for macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs)**
7> [card] [Download for macOS](https://claude.ai/api/desktop/darwin/universal/dmg/latest/redirect?utm_source=claude_code\&utm_medium=docs)
88>
99> Universal build for Intel and Apple Silicon
1010
11> **[Download for Windows](https://claude.ai/api/desktop/win32/x64/setup/latest/redirect?utm_source=claude_code\&utm_medium=docs)**
11> [card] [Download for Windows](https://claude.ai/api/desktop/win32/x64/setup/latest/redirect?utm_source=claude_code\&utm_medium=docs)
1212>
1313> For x64 processors
1414
15> **[Get Claude for Linux (beta)](https://code.claude.com/docs/en/desktop-linux.md)**
15> [card] [Get Claude for Linux (beta)](https://code.claude.com/docs/en/desktop-linux.md)
1616>
1717> apt or .deb for Ubuntu and Debian
1818
from line 88
8888| **Accept edits** | `acceptEdits` | Claude auto-accepts file edits and common filesystem commands like `mkdir`, `touch`, and `mv`, but still asks before running other terminal commands. Use this when you trust file changes and want faster iteration. |
8989| **Plan** | `plan` | Claude reads files and runs commands to explore, then proposes a plan without editing your source code. Good for complex tasks where you want to review the approach first. |
9090| **Auto** | `auto` | Claude runs without routine prompts; before actions such as shell commands and network requests run, a background classifier checks that they align with your request. Appears when [auto mode is available](#auto-mode-availability); there is no separate Settings toggle for it. |
91| **Bypass permissions** | `bypassPermissions` | Claude runs without permission prompts, except for the [actions no mode auto-approves](https://code.claude.com/docs/en/permission-modes.md#actions-no-mode-auto-approves), safety classifiers when Claude [acts on external sites](#browse-external-sites), or desktop actions such as deleting a session, though not [archiving one](#work-across-sessions). Equivalent to `--dangerously-skip-permissions` in the CLI. On Pro and Max plans, enable "Allow bypass permissions mode" in **Settings > Code** or **Settings > Claude Code**. On Team and Enterprise plans there is no Settings toggle, and organization policy controls it instead. Only use this in sandboxed containers or VMs. |
91| **Bypass permissions** | `bypassPermissions` | Claude runs without permission prompts, except for the [actions no mode auto-approves](https://code.claude.com/docs/en/permission-modes.md#actions-no-mode-auto-approves), safety classifiers when Claude [acts on external sites](#browse-external-sites), or desktop actions such as deleting a session, though not [archiving one](#work-across-sessions). Equivalent to `--dangerously-skip-permissions` in the CLI. On Pro, Max, and Ultra plans, enable "Allow bypass permissions mode" in **Settings > Code** or **Settings > Claude Code**. On Team and Enterprise plans there is no Settings toggle, and organization policy controls it instead. Only use this in sandboxed containers or VMs. |
9292
9393Earlier versions of the Code tab labeled these modes Ask permissions, Auto accept edits, and Plan mode.
9494
from line 316
316316
317317> [!NOTE]
318318>
319> Computer use is a research preview on macOS and Windows that requires a Pro or Max plan. It is not available on Team or Enterprise plans. The Claude Desktop app must be running. On macOS, computer use requires macOS 14 or later.
319> Computer use is a research preview on macOS and Windows that requires a Pro, Max, or Ultra plan. It is not available on Team or Enterprise plans. The Claude Desktop app must be running. On macOS, computer use requires macOS 14 or later.
320320
321321Computer use is off by default. [Enable it in Settings](#enable-computer-use) before Claude can control your screen. On macOS, you also need to grant Accessibility and Screen Recording permissions.
322322
from line 358
358358* **Windows**: the toggle takes effect immediately and setup is complete
359359* **macOS**: continue to the next step
360360
361If you don't see the toggle, confirm you're on macOS or Windows with a Pro or Max plan, then update and restart the app.
361If you don't see the toggle, confirm you're on macOS or Windows with a Pro, Max, or Ultra plan, then update and restart the app.
362362
363363**3. Grant macOS permissions**
364364
from line 558
558558
559559#### Set up Dispatch
560560
561For setup, pairing, and Dispatch settings, see the [Dispatch help article](https://support.claude.com/en/articles/13947068). Dispatch requires a Pro or Max plan and is not available on Team or Enterprise plans.
561* **Plans**: Dispatch requires a Pro, Max, or Ultra plan and is not available on Team or Enterprise plans
562* **Setup, pairing, and Dispatch settings**: see the [Dispatch help article](https://support.claude.com/en/articles/13947068)
562563
563564Dispatch is one of several ways to work with Claude when you're away from your terminal. For a comparison with the other options, see [Platforms and integrations](https://code.claude.com/docs/en/platforms.md#work-when-you-are-away-from-your-terminal).
564565
from line 735
734735
735736These configurations show common setups for different project types:
736737
737**Next.js**
738> [tab] Next.js
739>
740> This configuration runs a Next.js app using Yarn on port 3000:
741>
742> ```json theme={null}
743> {
744> "version": "0.0.1",
745> "configurations": [
746> {
747> "name": "web",
748> "runtimeExecutable": "yarn",
749> "runtimeArgs": ["dev"],
750> "port": 3000
751> }
752> ]
753> }
754> ```
738755
739This configuration runs a Next.js app using Yarn on port 3000:
756> [tab] Multiple servers
757>
758> For a monorepo with a frontend and an API server, define multiple configurations. The frontend uses `autoPort: true` so it picks a free port if 3000 is taken, while the API server requires port 8080 exactly:
759>
760> ```json theme={null}
761> {
762> "version": "0.0.1",
763> "configurations": [
764> {
765> "name": "frontend",
766> "runtimeExecutable": "npm",
767> "runtimeArgs": ["run", "dev"],
768> "cwd": "apps/web",
769> "port": 3000,
770> "autoPort": true
771> },
772> {
773> "name": "api",
774> "runtimeExecutable": "npm",
775> "runtimeArgs": ["run", "start"],
776> "cwd": "server",
777> "port": 8080,
778> "env": { "NODE_ENV": "development" },
779> "autoPort": false
780> }
781> ]
782> }
783> ```
740784
741```json theme={null}
742{
743 "version": "0.0.1",
744 "configurations": [
745 {
746 "name": "web",
747 "runtimeExecutable": "yarn",
748 "runtimeArgs": ["dev"],
749 "port": 3000
750 }
751 ]
752}
753```
785> [tab] Node.js script
786>
787> To run a Node.js script directly instead of using a package manager command, use the `program` field:
788>
789> ```json theme={null}
790> {
791> "version": "0.0.1",
792> "configurations": [
793> {
794> "name": "server",
795> "program": "server.js",
796> "args": ["--verbose"],
797> "port": 4000
798> }
799> ]
800> }
801> ```
754802
755**Multiple servers**
756
757For a monorepo with a frontend and an API server, define multiple configurations. The frontend uses `autoPort: true` so it picks a free port if 3000 is taken, while the API server requires port 8080 exactly:
758
759```json theme={null}
760{
761 "version": "0.0.1",
762 "configurations": [
763 {
764 "name": "frontend",
765 "runtimeExecutable": "npm",
766 "runtimeArgs": ["run", "dev"],
767 "cwd": "apps/web",
768 "port": 3000,
769 "autoPort": true
770 },
771 {
772 "name": "api",
773 "runtimeExecutable": "npm",
774 "runtimeArgs": ["run", "start"],
775 "cwd": "server",
776 "port": 8080,
777 "env": { "NODE_ENV": "development" },
778 "autoPort": false
779 }
780 ]
781}
782```
783
784**Node.js script**
785
786To run a Node.js script directly instead of using a package manager command, use the `program` field:
787
788```json theme={null}
789{
790 "version": "0.0.1",
791 "configurations": [
792 {
793 "name": "server",
794 "program": "server.js",
795 "args": ["--verbose"],
796 "port": 4000
797 }
798 ]
799}
800```
801
802803## Environment configuration
803804
804805The environment you pick when [starting a session](#start-a-session) determines where Claude executes and how you connect:
from line 1324
13231324* **Workflows**: Desktop checks each new [workflow](https://code.claude.com/docs/en/workflows.md) before it starts, so while Desktop is disconnected a new one waits up to 10 minutes and then fails
13241325* **MCP servers**: MCP servers that Claude Code starts on the remote machine don't run through Desktop, so Claude can still call their tools. Servers from `claude_desktop_config.json` are among them only if Desktop doesn't use its [built-in SSH client](#worktree-edits-while-disconnected). Otherwise, and on [some Windows remote machines](#windows-remote-machines), Claude can't call their tools while Desktop is disconnected.
13251326
1326> **When edits in a worktree keep working**
1327> [accordion] When edits in a worktree keep working
13271328>
13281329> On a Linux or macOS remote machine, the check doesn't go through Desktop, so edits inside the worktree keep working while Desktop is disconnected. Before Claude Desktop v2.37337.0, this holds on a Linux remote machine only.
13291330>
from line 1365
13641365* **Remembered password**: a password that you let Desktop remember also works without a prompt, but for a long absence prefer a key that your SSH agent holds. If sign-ins with that password break off or hang, Desktop can stop reconnecting and wait for you.
13651366* **Any other prompt**: if the remote machine prompts for anything else, such as a one-time code, you can get a notification on your computer. Click the notification, or send a message in the session, and Desktop shows the prompt.
13661367
1367> **If a jump host asks for a sign-in, the outage is long, output is missing, or the process is gone**
1368> [accordion] If a jump host asks for a sign-in, the outage is long, output is missing, or the process is gone
13681369>
13691370> * **Jump host, pushes stop while you're away**: this can happen with Desktop on macOS or Linux when nobody answers a jump host's sign-in, for example a push to a phone. Desktop then stops reconnecting while nobody is at your computer. When you unlock or use the computer, you can get another push, because Desktop can try again. After three unanswered attempts it waits until you retry or send a message.
13701371> * **Jump host, pushes keep coming**: where Desktop can't tell that nobody answers, as with Desktop on Windows, it keeps trying while it has a process to rejoin, whether or not that process still runs. You can get another push with each attempt. To end the attempts, quit Desktop, which [can cost you the running task](#reopen-a-session-after-you-quit-desktop).
from line 2052
20512052| `--model sonnet` | Model picker in the row under the prompt box |
20522053| `--resume`, `--continue` | Click a session in the sidebar, or type `/resume` in the prompt box to pick up a session you started from the CLI |
20532054| `--permission-mode` | Mode selector in the row under the prompt box |
2054| `--dangerously-skip-permissions` | Bypass permissions mode. On Pro and Max plans, enable "Allow bypass permissions mode" in **Settings > Code** or **Settings > Claude Code**; on Team and Enterprise plans, organization policy controls it |
2055| `--dangerously-skip-permissions` | Bypass permissions mode. On Pro, Max, and Ultra plans, enable "Allow bypass permissions mode" in **Settings > Code** or **Settings > Claude Code**; on Team and Enterprise plans, organization policy controls it |
20552056| `--add-dir` | [Add folders to a session](#add-folders-to-a-session) in local and SSH sessions, or select [several repositories](#run-long-running-tasks-in-the-cloud) in a cloud session |
20562057| `--allowedTools`, `--disallowedTools` | No per-session equivalent. Permission rules in [settings files](https://code.claude.com/docs/en/settings.md) still apply. |
20572058| `--verbose` | [Verbose view mode](#switch-view-modes) |
from line 2088
20872088
20882089| Feature | CLI | Desktop |
20892090| - | - | - |
2090| Permission modes | All modes including `dontAsk` | Manual, Accept edits, Plan, and Auto. Bypass permissions appears in the mode selector once enabled: through the Settings toggle on Pro and Max plans, or through organization policy on Team and Enterprise plans |
2091| Permission modes | All modes including `dontAsk` | Manual, Accept edits, Plan, and Auto. Bypass permissions appears in the mode selector once enabled: through the Settings toggle on Pro, Max, and Ultra plans, or through organization policy on Team and Enterprise plans |
20912092| [Third-party providers](https://code.claude.com/docs/en/third-party-integrations.md) | Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry | Anthropic's API by default. For gateway routing, see [connect the desktop app to a gateway](https://code.claude.com/docs/en/llm-gateway-connect.md#desktop-app). To run the Code tab on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or a self-hosted LLM gateway, see [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview). |
20922093| [MCP servers](https://code.claude.com/docs/en/mcp.md) | Configure in settings files | Connectors UI for local and SSH sessions, or settings files |
20932094| [Plugins](https://code.claude.com/docs/en/plugins/overview.md) | `/plugin` command | Plugin manager UI |
from line 2150
21492150If you see `Error 403: Forbidden` or other authentication failures when using the Code tab:
21502151
215121521. Sign out and back in from the app menu. This is the most common fix.
21522. Verify you have an active paid subscription: Pro, Max, Team, or Enterprise.
21532. Verify you have an active paid subscription: Pro, Max, Ultra, Team, or Enterprise.
215321543. If the CLI works but Desktop does not, quit the desktop app completely, not just close the window, then reopen and sign in again.
215421554. Check your internet connection and proxy settings.
21552156
No line in this hunk matches that.