HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
820pages tracked
773 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
81 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
15 Oct 2026
193 pages
+16642 −5213 lines
claude-code
web-quickstart
±changed
+1−1
claude-codechanged
web-quickstart
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup) applied, cannot use `/web-setup` or other
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup) applied, cannot use `/web-setup` or other
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
ultrareview
±changed
+1−1
claude-codechanged
ultrareview
Ultrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/logi
Ultrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/logi
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
Claude Code expands the first skill plus up to five more stacked after it. Expansion stops at the first token that isn't an inline user-invocable skill, so a skill that runs as a [
Claude Code expands the first skill plus up to five more stacked after it. Expansion stops at the first token that isn't an inline user-invocable skill, so a skill that runs as a [
A forked skill that runs in the background applies its edits outside your session's [checkpoints](/docs/en/checkpointing), so `/rewind` doesn't undo them; use git to revert them.
A forked skill that runs in the background applies its edits outside your session's [checkpoints](/docs/en/checkpointing#subagent-edits-not-restored). After one, `/rewind` restores
+2 −2 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
github-enterprise-server
±changed
+1−1
claude-codechanged
github-enterprise-server
Go to [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code) and enable [Code Review](/docs/en/code-review#set-up-code-review) for your GHES repos
Go to [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code) and enable [Code Review](/docs/en/code-review-setup) for your GHES repositories using
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
In any session, you can also ask Claude in the prompt box to fix what the review found. For what `/code-review` looks for and the arguments it takes, see [Review a diff locally](/d
In any session, you can also ask Claude in the prompt box to fix what the review found. For what `/code-review` looks for and the arguments it takes, see [Review locally with `/cod
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-troubleshooting
+new page
+87−0
claude-codenew page
code-review-troubleshooting
No line of the body moved in this read.
+87 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-setup
+new page
+161−0
claude-codenew page
code-review-setup
No line of the body moved in this read.
+161 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-pull-requests
+new page
+145−0
claude-codenew page
code-review-pull-requests
No line of the body moved in this read.
+145 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-local
+new page
+171−0
claude-codenew page
code-review-local
No line of the body moved in this read.
+171 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-customize
+new page
+129−0
claude-codenew page
code-review-customize
No line of the body moved in this read.
+129 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
code-review-costs
+new page
+72−0
claude-codenew page
code-review-costs
No line of the body moved in this read.
+72 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup) applied, can't use `/web-setup` or other c
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled, or with the [HIPAA configuration](/docs/en/hipaa-setup) applied, can't use `/web-setup` or other c
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
checkpointing
±changed
+1−1
claude-codechanged
checkpointing
* **Any other subagent**: rewinding doesn't restore the edits. Use git to revert them. This includes a forked skill that runs in the background, the default, and a background [`/co
* **Any other subagent**: rewinding restores only the files Claude had already edited in your conversation. The subagent's edits to other files stay, so use git to revert them. Thi
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
analytics
±changed
+2−0
claude-codechanged
analytics
Code Review has its own dashboard. For review activity and spend, see [View usage](/docs/en/code-review-costs#view-usage).
+2 −0 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-code
agent-sdk/file-checkpointing
±changed
+1−1
claude-codechanged
agent-sdk/file-checkpointing
| Subagent edits | Edits a [subagent](/docs/en/agent-sdk/subagents) applies aren't tracked or restored, except a skill with `context: fork` running in the foreground; use git to re
| Subagent edits | Edits a [subagent](/docs/en/agent-sdk/subagents) applies aren't tracked, except a skill with `context: fork` running in the foreground. A rewind reverts them onl
+1 −1 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 15 Oct 2026 19:37 UTC
claude-docs
claude-science/changelog
±changed
+8−0
claude-docschanged
claude-science/changelog
<Update label="0.1.63" description="October 14, 2026">
* Tabs in the right pane are now all one width, and the tab you're viewing always shows its close button
* Newly saved artifacts now list more of their input files in Provenance when the code that created them read many files
* Linux: Claude Science now detects an NVIDIA GPU only if `nvidia-smi` can run without your `LD_LIBRARY_PATH` and is in `/usr/bin` or one of a few other fixed folders (`/usr/loca
+8 −0 lines
Upstream edited 15 Oct 2026 19:06 UTC Recorded here 15 Oct 2026 19:07 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 15 Oct 2026 18:37 UTC
claude-code
cloud-environments
±changed
+19−4
claude-codechanged
cloud-environments
Next, create the script at `scripts/install_pkgs.sh`. It exits immediately outside the cloud, then installs your dependencies:
Next, create the script at `scripts/install_pkgs.sh`. It exits immediately outside the cloud, then installs your dependencies. It skips `npm install` while `package.json`, `package
npm install
cd "$CLAUDE_PROJECT_DIR" || exit 1
hashes=node_modules/.install_pkgs.sha256
+19 −4 lines
Upstream edited 15 Oct 2026 18:27 UTC Recorded here 15 Oct 2026 18:37 UTC
claude-docs
claude-science/overview
±changed
+9−9
claude-docschanged
claude-science/overview
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux. You install it separately f
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux. You install it separately f
Claude Science isn't limited to the life sciences. Besides biology, chemistry, and clinical and medical research, it supports computer science and machine learning, engineering, ma
Claude Science isn't limited to the life sciences. Besides biology, chemistry, and clinical and medical research, it supports computer science and machine learning, engineering, ma
* **Remote compute.** For long-running or heavy analyses, Claude can run jobs on [a workstation or Slurm cluster you reach over SSH](/docs/claude-science/remote-compute-clusters.md
+9 −9 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-science/enable-claude-science
±changed
+8−8
claude-docschanged
claude-science/enable-claude-science
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations, and on by default for organizations on the [Claude Team plan for
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations, and on by default for organizations on the [Claude Team plan for
On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin
On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin
Review the [organization settings](/docs/claude-science/admin-controls.md#organization-settings) below the toggle, which unlock once Claude Science is on.\
+8 −8 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-science/overview
±changed
+9−9
claude-docschanged
claude-science/overview
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux. You install it separately f
Claude Science is a desktop application that pairs Claude with an analysis environment on your computer. Available in beta on macOS, Windows, and Linux. You install it separately f
Claude Science isn't limited to the life sciences. Besides biology, chemistry, and clinical and medical research, it supports computer science and machine learning, engineering, ma
Claude Science isn't limited to the life sciences. Besides biology, chemistry, and clinical and medical research, it supports computer science and machine learning, engineering, ma
* **Remote compute.** For long-running or heavy analyses, Claude can run jobs on [a workstation or Slurm cluster you reach over SSH](/docs/claude-science/remote-compute-clusters),
+9 −9 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/enable-claude-science
±changed
+8−8
claude-docschanged
claude-science/enable-claude-science
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations, and on by default for organizations on the [Claude Team plan for
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations, and on by default for organizations on the [Claude Team plan for
On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin
On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin
Review the [organization settings](/docs/claude-science/admin-controls#organization-settings) below the toggle, which unlock once Claude Science is on.\
+8 −8 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/overview
±changed
+3−3
claude-docschanged
claude-science/overview
<Note>
Claude can make mistakes. The reviewer reduces, but doesn't eliminate, errors. It checks claims against the execution record and doesn't re-run analyses. Verify results before re
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-science/overview
±changed
+1−1
claude-docschanged
claude-science/overview
* A Claude account on a Pro, Max, Team, or Enterprise plan. On Team and Enterprise plans, an Owner must [enable Claude Science for the organization](/docs/claude-science/enable-cla
* A Claude account on a Pro, Max, Team, or Enterprise plan. The [Claude Team plan for scientists](https://claude.com/programs/team-plan-for-scientists) has Claude Science on by def
+1 −1 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
claude-science/get-started
±changed
+1−1
claude-docschanged
claude-science/get-started
Install Claude Science on your computer, sign in with your Claude account, and run your first analysis. You need a Claude Pro, Max, Team, or Enterprise plan, and on Team and Enterp
Install Claude Science on your computer, sign in with your Claude account, and run your first analysis. You need a Claude Pro, Max, Team, or Enterprise plan. The [Claude Team plan
+1 −1 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
claude-science/enable-claude-science
±changed
+7−2
claude-docschanged
claude-science/enable-claude-science
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations. Turning it on in **Organization settings** > **Claude Science**
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations, and on by default for organizations on the [Claude Team plan for
| Claude Team plan for scientists | On; turn off in **Organization settings** |
If your organization has HIPAA compliance enabled, Claude Science app access is also off by default. You can turn it on, but usage isn't covered under your Business Associate Agree
On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin
+7 −2 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
claude-science/admin-controls
±changed
+3−3
claude-docschanged
claude-science/admin-controls
The [**Organization settings** > **Claude Science**](https://claude.ai/admin-settings/claude-science) page in claude.ai holds the controls that apply to every member of your Team o
The [**Organization settings** > **Claude Science**](https://claude.ai/admin-settings/claude-science) page in claude.ai holds the controls that apply to every member of your Team o
In the **Featured connectors** list, the rows marked **Web** (PubMed, Clinical Trials, ChEMBL, and bioRxiv) are connectors Anthropic hosts in the Claude connector directory rather
In the **Featured connectors** list, the rows marked **Web** (PubMed, Clinical Trials, ChEMBL, and bioRxiv) are connectors Anthropic hosts in the Claude connector directory rather
| Claude Science > Enable for your organization | Supported in Claude Science | Off by default for Team and Enterprise. An Owner or Primary Owner turns it on under **Organization s
+3 −3 lines
Upstream edited 15 Oct 2026 18:05 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
connectors/building/enterprise-managed-auth
±changed
+10−10
claude-docschanged
connectors/building/enterprise-managed-auth
> Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
> Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
Enterprise Managed Auth also works with [lazy authentication](/docs/connectors/building/lazy-authentication.md). When your server returns `401 Unauthorized` for a protected tool ca
Enterprise Managed Auth also works with [lazy authentication](https://claude.com/docs/connectors/building/lazy-authentication.md). When your server returns `401 Unauthorized` for a
Your MCP server returns the same `401` with a `WWW-Authenticate` header as described in the [lazy authentication guide](/docs/connectors/building/lazy-authentication.md#answer-a-pr
+10 −10 lines
Upstream edited 15 Oct 2026 17:59 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
connectors/building/enterprise-managed-auth
±changed
+10−10
claude-docschanged
connectors/building/enterprise-managed-auth
> Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
> Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
Enterprise Managed Auth also works with [lazy authentication](/docs/connectors/building/lazy-authentication). When your server returns `401 Unauthorized` for a protected tool call,
Enterprise Managed Auth also works with [lazy authentication](/docs/connectors/building/lazy-authentication.md). When your server returns `401 Unauthorized` for a protected tool ca
Your MCP server returns the same `401` with a `WWW-Authenticate` header as described in the [lazy authentication guide](/docs/connectors/building/lazy-authentication#answer-a-prote
+10 −10 lines
Upstream edited 15 Oct 2026 17:59 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
connectors/building/enterprise-managed-auth
±changed
+47−51
claude-docschanged
connectors/building/enterprise-managed-auth
<Note>
Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
</Note>
> [!NOTE]
>
+47 −51 lines
Upstream edited 15 Oct 2026 17:59 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
connectors/building/enterprise-managed-auth
±changed
+1−1
claude-docschanged
connectors/building/enterprise-managed-auth
Enterprise Managed Auth is available on Claude Team and Enterprise plans. MCP server developers and identity provider vendors can [register interest](https://docs.google.com/form
Enterprise Managed Auth is available on Claude Team and Enterprise plans. After your authorization server supports it, email `[email protected]` to have [your directory li
+1 −1 lines
Upstream edited 15 Oct 2026 17:59 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/import
±changed
+1−1
claude-docschanged
third-party/claude-desktop/import
* **Your organization's optional plugins**: the ones you had turned on are turned on again, if they come from your organization's plugins directory or from a marketplace hosted at
* **Your organization's optional plugins**: the ones you had turned on are turned on again, if they come from your organization's plugins directory or from a marketplace hosted at
+1 −1 lines
Upstream edited 15 Oct 2026 17:58 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/admin-console
±changed
+5−4
claude-docschanged
third-party/claude-desktop/admin-console
Update devices to Claude Desktop 2.37337.1 or later. Earlier releases migrate fewer items.
Update devices to Claude Desktop 2.42304.0 or later. Earlier releases migrate fewer items.
* Scheduled tasks from Cowork and Code, except one-time tasks
* Scheduled tasks from Cowork and Code, except one-time tasks whose time has passed
* Optional organization plugins that users turned on from other marketplaces, such as a git repository, if you offer the marketplace from the same repository or URL as your earlier
+5 −4 lines
Upstream edited 15 Oct 2026 17:58 UTC Recorded here 15 Oct 2026 18:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 15 Oct 2026 17:37 UTC
claude-code
artifacts
±changed
+1−2
claude-codechanged
artifacts
| You turned [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) off | Asks before the first publish of each artifact |
* **Plan mode, or feature-flag fetching turned off**: in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), or if you turned [feature-flag fetching](/do
* **Plan mode**: in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), Claude Code asks before the Artifact tool reads an artifact someone else in your
+1 −2 lines
Upstream edited 15 Oct 2026 17:34 UTC Recorded here 15 Oct 2026 17:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 15 Oct 2026 17:07 UTC
claude-code
skills
±changed
+4−0
claude-codechanged
skills
#### Control characters in injected commands
`No shell command in <name> was run` means one of the file's `!` commands contains a raw control character other than tab or newline, so none of them runs. See [how to find and rem
+4 −0 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
remote-control
±changed
+1−0
claude-codechanged
remote-control
| `--sandbox`, `--no-sandbox` | Removed in v2.1.300. If you pass either flag, the server [exits with an error](/docs/en/errors#sandbox-is-not-supported-by-claude-remote-control
+1 −0 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
memory
±changed
+1−0
claude-codechanged
memory
* If an `Instruction file not loaded` notice appears, see [what it means and what to do about it](/docs/en/errors#instruction-file-not-loaded).
+1 −0 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
mcp-quickstart
±changed
+2−0
claude-codechanged
mcp-quickstart
Before v2.1.299, some connections to HTTP servers that were up timed out at startup regardless of `MCP_TIMEOUT`. If you use one of those versions and an HTTP server that is up
+2 −0 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
To change the limits for every MCP server in your session, set [`CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH`](/docs/en/env-vars#variables) to a number of characters. The number you set
Descriptions and instructions from some of the MCP servers that Anthropic hosts at `api.anthropic.com` reach Claude in full. To change the limits for the other MCP servers in your
+1 −1 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
errors
±changed
+121−1
claude-codechanged
errors
| `Remote Control could not renew this computer's connection` | [Authentication](#remote-control-could-not-renew-this-computers-connection) |
| `--sandbox is not supported by claude remote-control` / `--no-sandbox is not supported by claude remote-control` | [Command-line errors](#sandbox-is-not-supported-by-claude-remot
| `No shell command in <name> was run, because the <tool> tool does not accept one of them` | [Command-line errors](#no-shell-command-was-run) |
| `Instruction file not loaded` | [Configuration warnings](#instruction-file-not-loaded) |
| `"<name>" is a reserved MCP server name and was not loaded` | [Configuration warnings](#mcp-server-name-is-reserved) |
+121 −1 lines
Upstream edited 15 Oct 2026 17:01 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
plugins/mods/admin
±changed
+4−1
claude-codechanged
plugins/mods/admin
* **You turn off the WebFetch tool with [`CLAUDE_CODE_DISABLE_WEB_FETCH`](/docs/en/env-vars#variables) or a `WebFetch` [deny rule](/docs/en/permissions#tool-specific-permission-r
To stop them for every mod your users install, [keep user-installed mods from loading](#stop-user-installed-mods-from-loading), or hook `http.fetch` in a [policy mod](#enforce-
Neither covers a program the mod starts with `$.process.run`, which reaches the network with the user's own access.
None of these covers a program the mod starts with `$.process.run`, which reaches the network with the user's own access.
+4 −1 lines
Upstream edited 15 Oct 2026 16:54 UTC Recorded here 15 Oct 2026 17:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 15 Oct 2026 16:37 UTC
claude-code
vs-code
±changed
+16−0
claude-codechanged
vs-code
### Plugins that draw in the panel
A plugin that contains a [mod](/docs/en/plugins/mods/overview) can draw in the chat panel. Drawing requires extension version 2.1.299 or later and a session that [fetches feature f
+16 −0 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/troubleshoot
±changed
+12−9
claude-codechanged
plugins/mods/troubleshoot
Your pane doesn't have keyboard focus.
Press Ctrl+X then Tab, or click the pane. Open it with `focus: true` from a command.
### A drawing works in the terminal and not in the Desktop app
+12 −9 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/reference
±changed
+33−24
claude-codechanged
plugins/mods/reference
Look up any event a [mod](/docs/en/plugins/mods/overview) can handle, mods API method it can call, or render site it can draw in, for the Claude Code CLI and the Desktop app as of
Look up any event a [mod](/docs/en/plugins/mods/overview) can handle, mods API method it can call, or render site it can draw in. Entries cover the Claude Code CLI and the Desktop
A render site is an extension point in Claude Code's interface. Each row is a value of `e.component` in a `ui.render` hook, with the fields of `e.props` and the apps that render it
A render site is an extension point in Claude Code's interface. Each row is a value of `e.component` in a `ui.render` hook, with the fields of `e.props` and the apps that render it
+33 −24 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/overview
±changed
+3−3
claude-codechanged
plugins/mods/overview
Mods work in the Claude Code CLI and in the Code tab of the Claude Desktop app. See [Where mods run](#where-mods-run) to understand how they behave elsewhere, such as in the VS Cod
Mods work in the Claude Code CLI, the Code tab of the Claude Desktop app, and the VS Code extension. See [Where mods run](#where-mods-run) for how they behave elsewhere, such as in
A mod's hooks run in every kind of session that loads the plugin, whichever provider serves the model, including Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundr
A mod's hooks run in every kind of session that loads the plugin, whichever provider serves the model, including Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundr
| The VS Code extension's chat panel | Yes | No |
+3 −3 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/interface
±changed
+32−15
claude-codechanged
plugins/mods/interface
`Pane`, `AskUserQuestion`, `Spinner`, `UserMessage`, `AssistantMessage`, and the tool call sites work in the terminal, the Desktop app, and the VS Code extension. The [render sites
The terminal and the Desktop app don't raise all the same sites. `Pane`, `AbovePrompt`, `Spinner`, and the transcript sites work in both. A few other status lines are raised in the
The [VS Code extension](#draw-in-the-vs-code-extension) ignores `rows` and `columns` and sizes the pane itself.
+32 −15 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/gallery
±changed
+3−3
claude-codechanged
plugins/mods/gallery
`Code` draws source text with Claude Code's own syntax colors, or a diff.
`Code` draws source text with Claude Code's own syntax colors, or a diff. In the VS Code extension, `Code` shows its `source` as plain text, with none of the colors, line numbers,
Opening a pane with `focus: true` gives the pane keyboard focus. Typed letters reach an `Input` once it has the focus, so add `autoFocus: true` to a field that should take typing a
Open a pane with `focus: true` to request keyboard focus for it. Typed letters reach an `Input` once it has the focus. To choose which field has the focus when the pane opens, see
An `Svg` draws an SVG document in the Desktop app:
+3 −3 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-code
plugins/mods/api
±changed
+2−0
claude-codechanged
plugins/mods/api
In the [VS Code extension](/docs/en/plugins/mods/interface#draw-in-the-vs-code-extension), status lines and toasts show above the prompt box instead, and log lines in the conversat
+2 −0 lines
Upstream edited 15 Oct 2026 16:35 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-docs
government/connectors/overview
±changed
+3−3
claude-docschanged
government/connectors/overview
The **Connectors** card appears on your [tenant](/docs/government/tenant-admin/configuration.md) or [organization](/docs/government/org-admin/configuration.md) Config page alongsid
The **Connectors** card appears on your [tenant](https://claude.com/docs/government/tenant-admin/configuration.md) or [organization](https://claude.com/docs/government/org-admin/co
* On the Config page for a [directory group](/docs/government/config/overview.md#group-specific-settings), it reaches that group's members: in every organization when you open the
* On the Config page for a [directory group](https://claude.com/docs/government/config/overview.md#group-specific-settings), it reaches that group's members: in every organization
A connector added for a group does not always reach every member of the group. Someone who belongs to more than one directory group receives group settings, connectors included, fr
+3 −3 lines
Upstream edited 15 Oct 2026 16:19 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
government/connectors/overview
±changed
+5−3
claude-docschanged
government/connectors/overview
Video: Connectors and plugins (2 min 8 s). Narrated with an AI-generated voice, with on-screen captions.
The **Connectors** card appears on your [tenant](/docs/government/tenant-admin/configuration) or [organization](/docs/government/org-admin/configuration) Config page alongside the
The **Connectors** card appears on your [tenant](/docs/government/tenant-admin/configuration.md) or [organization](/docs/government/org-admin/configuration.md) Config page alongsid
* On the Config page for a [directory group](/docs/government/config/overview#group-specific-settings), it reaches that group's members: in every organization when you open the gro
+5 −3 lines
Upstream edited 15 Oct 2026 16:19 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
government/connectors/overview
±changed
+20−22
claude-docschanged
government/connectors/overview
<Frame caption="Video: Connectors and plugins (2 min 8 s). Narrated with an AI-generated voice, with on-screen captions.">
<video controls preload="metadata" playsInline className="w-full aspect-video" src="https://mintcdn.com/claude-ai/gGFKuNSbKYs4JMmK/images/government/videos/admin-07-connectors-an
</Frame>
<video controls preload="metadata" playsInline src="https://mintcdn.com/claude-ai/gGFKuNSbKYs4JMmK/images/government/videos/admin-07-connectors-and-plugins.mp4?fit=max&auto=format&
<Accordion title="Transcript">
+20 −22 lines
Upstream edited 15 Oct 2026 16:19 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
government/connectors/overview
±changed
+5−0
claude-docschanged
government/connectors/overview
**OAuth (pre-registered app)** also has two optional fields:
* **Callback port**: if your sign-in provider requires the exact port in the app's registered redirect URI, enter that port
* **Callback host**: if the app's registered redirect URI uses `localhost` rather than `127.0.0.1`, select **localhost**
+5 −0 lines
Upstream edited 15 Oct 2026 16:19 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-docs
cowork/monitoring
±changed
+12−12
claude-docschanged
cowork/monitoring
<Note>
Monitoring is available for Team and Enterprise plans. OTel monitoring requires Claude desktop app version 1.1.4173 or later.
</Note>
> [!NOTE]
>
+12 −12 lines
Upstream edited 15 Oct 2026 16:10 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
cowork/monitoring
±changed
+9−8
claude-docschanged
cowork/monitoring
Cowork exports the following events to your OTel collector. The collector settings in [Setup](#setup) apply to every Cowork session that runs on a user's computer in Claude Desktop
Cowork exports the following events to your OTel collector. The collector settings in [Setup](#setup) apply to every Cowork session that runs on a user's computer in Claude Desktop
The table shows what events carry on Claude Desktop version 1.17377 or later, for a Cowork session that runs on the user's computer.
The table shows what events carry on current versions of Claude Desktop, for a Cowork session that runs on the user's computer.
| Not set, on a first-party deployment | User prompt text, model response text, and the [`toolDetails` content](#security-and-privacy) |
+9 −8 lines
Upstream edited 15 Oct 2026 16:10 UTC Recorded here 15 Oct 2026 16:37 UTC
claude-docs
government/deploy-desktop/configure
±changed
+1−1
claude-docschanged
government/deploy-desktop/configure
The `.reg` file from the Export menu targets `HKEY_CURRENT_USER`, which is correct for single-machine testing. For fleet deployment, deliver the values under `HKEY_LOCAL_MACHINE` a
For fleet deployment, deliver the values under `HKEY_LOCAL_MACHINE` as shown here. If the `.reg` file from the **Export** menu has `HKEY_CURRENT_USER` in the line in square bracket
+1 −1 lines
Upstream edited 15 Oct 2026 15:35 UTC Recorded here 15 Oct 2026 15:37 UTC
claude-docs
government/config/settings
±changed
+10−4
claude-docschanged
government/config/settings
A group of separate switches that control which Claude products and features are available to members. Each switch appears as its own row: **Claude Desktop**, **Chat in Claude Desk
Turning off **Claude Code** or **Claude for Microsoft 365** stops the members the setting applies to from using that application. Turning off **Claude Desktop** stops the app from
A group of separate switches that control which Claude products and features are available to members. Each switch appears as its own row: **Claude Desktop**, **Chat in Claude Desk
+10 −4 lines
Upstream edited 15 Oct 2026 15:35 UTC Recorded here 15 Oct 2026 15:37 UTC
claude-docs
cowork/changelog
±changed
+44−0
claude-docschanged
cowork/changelog
<Update label="v2.42304.0" description="2026-10-15">
Bundled Claude Code version: 2.1.299.
**General**
+44 −0 lines
Upstream edited 15 Oct 2026 15:33 UTC Recorded here 15 Oct 2026 15:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+8−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.42304.0" description="2026-10-15">
**Changed:**
* `chatAdvancedFileAnalysisEnabled` and `coworkEgressAllowedHosts`: commands in Chat's file-analysis sandbox can now reach the listed hosts. With no list, or an empty one, they h
+8 −0 lines
Upstream edited 15 Oct 2026 15:33 UTC Recorded here 15 Oct 2026 15:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+27−13
claude-docschanged
third-party/claude-desktop/configuration
Also enables inline data analysis. Of the user's own files, the sandbox can read only those attached to the conversation, plus folders added to the chat's project through the a
Also enables inline data analysis. Of the user's own files, the sandbox can read only those attached to the conversation, plus folders added to the chat's project through the a
Commands in the sandbox can reach the hosts in `coworkEgressAllowedHosts`, and no others. If that list is unset or empty, they have no network access. With `*` in the list they
+27 −13 lines
Upstream edited 15 Oct 2026 15:33 UTC Recorded here 15 Oct 2026 15:37 UTC
claude-docs
office-agents/outlook
±changed
+9−9
claude-docschanged
office-agents/outlook
[Why sign-in redirects through pivot.claude.ai](/docs/office-agents/third-party-platforms.md#why-sign-in-redirects-through-pivot-claude-ai)
[Why sign-in redirects through pivot.claude.ai](https://claude.com/docs/office-agents/third-party-platforms.md#why-sign-in-redirects-through-pivot-claude-ai)
with the [setup wizard](/docs/office-agents/third-party-platforms.md#run-the-setup-wizard),
with the [setup wizard](https://claude.com/docs/office-agents/third-party-platforms.md#run-the-setup-wizard),
[Deploy to Outlook](/docs/office-agents/third-party-platforms.md#deploy-to-outlook).
+9 −9 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
office-agents/opentelemetry
±changed
+2−2
claude-docschanged
office-agents/opentelemetry
[Use Claude for M365 with third-party platforms](/docs/office-agents/third-party-platforms.md).
[Use Claude for M365 with third-party platforms](https://claude.com/docs/office-agents/third-party-platforms.md).
custom manifest, with `otlp_headers` after `#` so the credential stays out of [server request logs](/docs/office-agents/third-party-platforms.md#keep-credentials-out-of-the-manifes
custom manifest, with `otlp_headers` after `#` so the credential stays out of [server request logs](https://claude.com/docs/office-agents/third-party-platforms.md#keep-credentials-
+2 −2 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
office-agents/outlook
±changed
+11−9
claude-docschanged
office-agents/outlook
[Why sign-in redirects through pivot.claude.ai](/docs/office-agents/third-party-platforms#why-sign-in-redirects-through-pivot-claude-ai)
[Why sign-in redirects through pivot.claude.ai](/docs/office-agents/third-party-platforms.md#why-sign-in-redirects-through-pivot-claude-ai)
with the [setup wizard](/docs/office-agents/third-party-platforms#run-the-setup-wizard),
with the [setup wizard](/docs/office-agents/third-party-platforms.md#run-the-setup-wizard),
[Deploy to Outlook](/docs/office-agents/third-party-platforms#deploy-to-outlook).
+11 −9 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
office-agents/opentelemetry
±changed
+2−2
claude-docschanged
office-agents/opentelemetry
[Use Claude for M365 with third-party platforms](/docs/office-agents/third-party-platforms).
[Use Claude for M365 with third-party platforms](/docs/office-agents/third-party-platforms.md).
custom manifest, with `otlp_headers` after `#` so the credential stays out of [server request logs](/docs/office-agents/third-party-platforms#keep-credentials-out-of-the-manifest-u
custom manifest, with `otlp_headers` after `#` so the credential stays out of [server request logs](/docs/office-agents/third-party-platforms.md#keep-credentials-out-of-the-manifes
+2 −2 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
office-agents/outlook
±changed
+118−128
claude-docschanged
office-agents/outlook
<Note>
Claude for Outlook is currently in beta and available to Pro, Max, Team,
and Enterprise plans.
</Note>
> [!NOTE]
+118 −128 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
office-agents/outlook
±changed
+28−8
claude-docschanged
office-agents/outlook
Go to the [Claude for Outlook listing on Microsoft AppSource](https://appsource.microsoft.com/).
Go to the [Claude for Outlook listing on Microsoft AppSource](https://marketplace.microsoft.com/en-us/product/office/WA200010724?tab=Overview).
[Why sign-in redirects through pivot.claude.ai](/docs/office-agents/third-party-platforms#why-sign-in-redirects-through-pivotclaudeai)
[Why sign-in redirects through pivot.claude.ai](/docs/office-agents/third-party-platforms#why-sign-in-redirects-through-pivot-claude-ai)
<Step title="Append the client ID to the manifest URL">
+28 −8 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 15 Oct 2026 15:07 UTC
claude-docs
office-agents/opentelemetry
±changed
+63−18
claude-docschanged
office-agents/opentelemetry
All span attributes are included. They carry user-generated content:
For the setups described under [Set up the collector](#set-up-the-collector),
all span attributes are included. They carry user-generated content:
connector-specific name. Assistant response text is not included in
span data. Your organization owns the collected data; treat the
+63 −18 lines
Upstream edited 15 Oct 2026 14:57 UTC Recorded here 15 Oct 2026 15:07 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+2−2
claude-docschanged
third-party/claude-desktop/data-storage
[Chat](/docs/third-party/claude-desktop/chat) conversations follow the same storage model as Cowork sessions: each conversation is a session state file plus a working directory und
[Chat](/docs/third-party/claude-desktop/chat) conversations follow the same storage model as Cowork sessions: each conversation is a session state file plus a working directory und
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
+2 −2 lines
Upstream edited 15 Oct 2026 14:43 UTC Recorded here 15 Oct 2026 14:54 UTC
claude-docs
third-party/claude-desktop/chat
±changed
+26−8
claude-docschanged
third-party/claude-desktop/chat
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in an offline local sandbox against attached
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in a local sandbox against attached files and
* **Read or write the filesystem** beyond the conversation's own uploads and scratch directories and, inside a project, the project's memory (read-only). The tool for requesting fo
* **Run code on the host.** There is no shell access. With advanced file analysis off (the default), the sandbox VM is never started for Chat; with it on, code runs only inside the
* **Act without asking.** Chat conversations always run in the default permission mode. Auto mode and other reduced-supervision modes are rejected for Chat regardless of `autoModeE
+26 −8 lines
Upstream edited 15 Oct 2026 14:43 UTC Recorded here 15 Oct 2026 14:54 UTC
claude-code
claude-tag
±changed
+5−5
claude-codechanged
claude-tag
No line of the body moved in this read.
+5 −5 lines
Recorded here 15 Oct 2026 05:07 UTC
claude-code
desktop
±changed
+68−0
claude-codechanged
desktop
You won't find Desktop's SSH connections in Claude Code's [metrics and events](/docs/en/monitoring-usage#available-metrics-and-events). To find out from them which remote machine a
#### Connections that close before login
If the SSH server's log shows connections that close before any login, they can be Desktop's tests of the SSH port. Desktop tests whether a machine answers, for example after a con
+68 −0 lines
Upstream edited 15 Oct 2026 04:54 UTC Recorded here 15 Oct 2026 05:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+1−1
apichanged
build-with-claude/claude-platform-on-aws
- **Admin API:** Workspace endpoints (create, get, list, update, and archive on `/v1/organizations/workspaces`) and external key endpoints (register, get, list, update, and delete
- **Admin API:** Workspace endpoints (create, get, list, update, and archive on `/v1/organizations/workspaces`), external key endpoints (register, get, list, update, and delete on
+1 −1 lines
Recorded here 15 Oct 2026 02:37 UTC
api
api/claude-platform-on-aws-iam-actions
±changed
+111−116
apichanged
api/claude-platform-on-aws-iam-actions
The following tables list every route on Claude Platform on AWS and the IAM action required to call it. Each IAM action also authorizes requests that use the `anthropic-beta` heade
| Method | Route | IAM action | CloudTrail event type |
| -------- | ---------------------------------------------------- | -------------------------------- | --------------------- |
| `POST` | `/v1/messages` | `CreateInference` | Data |
+111 −116 lines
Recorded here 15 Oct 2026 02:37 UTC
claude-docs
third-party/claude-desktop/move-to-claude-enterprise
+new page
+113−0
claude-docsnew page
third-party/claude-desktop/move-to-claude-enterprise
No line of the body moved in this read.
+113 −0 lines
Upstream edited 15 Oct 2026 02:25 UTC Recorded here 15 Oct 2026 02:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+5−5
claude-docschanged
third-party/claude-desktop/configuration
```json theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null}
+5 −5 lines
Upstream edited 15 Oct 2026 02:25 UTC Recorded here 15 Oct 2026 02:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 15 Oct 2026 01:37 UTC
claude-code
artifacts
±changed
+5−2
claude-codechanged
artifacts
Claude reads files in your session's [working directories](/docs/en/permissions#working-directories), and in the temporary directory it writes pages to, without asking. To let Clau
| In [Manual](/docs/en/permission-modes) or `acceptEdits` mode, Claude makes a small change to an artifact's file it can't edit without your approval, such as a project file in Man
To let Claude read a file outside your [working directories](/docs/en/permissions#working-directories) without your approval, add its folder as a working directory with [`--add-dir
+5 −2 lines
Upstream edited 15 Oct 2026 01:32 UTC Recorded here 15 Oct 2026 01:37 UTC
claude-code
vs-code
±changed
+8−2
claude-codechanged
vs-code
Click any conversation to resume it with the full message history. If the conversation is already open in another tab of the current window, clicking it switches to that tab. For m
Click any conversation to resume it with the full message history. If the conversation is already open in another tab of the current window, clicking it switches to that tab. If th
If another Claude Code process still has the conversation open, you're asked before it opens here, with the same **Open here anyway** notice as when you [resume it from session his
If another Claude Code process still has the conversation open, you're asked before it opens here, with the same **Open here anyway** notice as when you [resume it from session his
### A resumed conversation is blank at first
+8 −2 lines
Upstream edited 15 Oct 2026 01:30 UTC Recorded here 15 Oct 2026 01:37 UTC
claude-code
workflows
±changed
+4−4
claude-codechanged
workflows
* **Permission rule**: `Workflow` in your allow rules approves every workflow, and `Workflow(<name>)` approves one saved workflow by name.
* **Auto permission mode**: the [classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) reviews the call and can approve it.
* **Bypass permissions mode**: Claude Code approves the call.
* **A hook**: a [`PreToolUse`](/docs/en/hooks#pretooluse) hook that allows the call approves it.
* **Permission rule**: add `Workflow` to your allow rules to approve every workflow, or `Workflow(<name>)` to approve one saved workflow by name.
+4 −4 lines
Upstream edited 15 Oct 2026 01:29 UTC Recorded here 15 Oct 2026 01:37 UTC
claude-code
agent-sdk/observability
±changed
+17−17
claude-codechanged
agent-sdk/observability
This guide explains how the SDK emits telemetry, how to configure the export, and how to tag and filter the data once it reaches your backend. To read token usage and cost directly
This guide explains how the SDK emits telemetry, how to configure the export, and how to tag and filter the data once it reaches your backend. To read token usage and cost directly
For the complete list of metric names, event names, and attributes, see the Claude Code [Monitoring](/docs/en/monitoring-usage) reference. The Agent SDK emits the same data because
For the complete list of metric names, event names, and attributes, see the Claude Code [Monitoring](/docs/en/monitoring-usage.md) reference. The Agent SDK emits the same data beca
* **`claude_code.hook`:** wraps each [hook](/docs/en/agent-sdk/hooks) execution. Requires detailed beta tracing (`ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`), a pa
+17 −17 lines
Upstream edited 15 Oct 2026 01:28 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/observability
±changed
+128−136
claude-codechanged
agent-sdk/observability
<Note>
For the Claude API or Managed Agents, see [OpenTelemetry for the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry).
</Note>
> [!NOTE]
>
+128 −136 lines
Upstream edited 15 Oct 2026 01:28 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
monitoring-usage
±changed
+5−1
claude-codechanged
monitoring-usage
Track Claude Code usage, costs, and tool activity across your organization by exporting telemetry data through OpenTelemetry (OTel). Claude Code exports metrics as time series data
Track Claude Code usage, costs, and tool activity across your organization by exporting telemetry data through OpenTelemetry (OTel). Claude Code exports metrics as time series data
<Note>
For the Claude API or Managed Agents, see [OpenTelemetry for the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry).
+5 −1 lines
Upstream edited 15 Oct 2026 01:28 UTC Recorded here 15 Oct 2026 01:37 UTC
claude-code
agent-sdk/observability
±changed
+4−0
claude-codechanged
agent-sdk/observability
<Note>
For the Claude API or Managed Agents, see [OpenTelemetry for the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry).
</Note>
+4 −0 lines
Upstream edited 15 Oct 2026 01:28 UTC Recorded here 15 Oct 2026 01:37 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+9−3
claude-docschanged
third-party/claude-desktop/data-storage
The copy holds full conversations and can hold unencrypted secrets, such as [cloud credentials in Cowork session working directories](#transient-credential-files). Encrypt any in
The copy holds full conversations. Encrypt any intermediate copy, restrict access to it, and delete it when you're done.
* `host-creds-*.json` and `ccd-session-secrets/`, which hold unencrypted credentials and can remain after a crash
* `spaces-present/*/*/link-key`, `ccd-environment-config.json`, and `cowork-enabled-cli-ops.json`, which the new device can't decrypt. If you copied them, quit Claude Desktop
+9 −3 lines
Upstream edited 15 Oct 2026 00:39 UTC Recorded here 15 Oct 2026 01:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 15 Oct 2026 00:07 UTC
claude-code
desktop
±changed
+164−2
claude-codechanged
desktop
* **Network**: Claude Code runs on the remote machine and makes its network requests from there, so the machine needs the [network access that Claude Code requires](/docs/en/networ
* **Network**: Claude Code runs on the remote machine and makes its network requests from there, so the machine needs the [network access that Claude Code requires](/docs/en/networ
#### Set a proxy or a CA certificate for SSH sessions
+164 −2 lines
Upstream edited 15 Oct 2026 00:00 UTC Recorded here 15 Oct 2026 00:07 UTC
14 Oct 2026
440 pages
+22725 −3369 lines
api
release-notes/overview
±changed
+2−0
apichanged
release-notes/overview
- Claude Managed Agents [scheduled deployments](https://platform.claude.com/docs/en/managed-agents/scheduled-deployments) are now available on [Claude Platform on AWS](https://plat
+2 −0 lines
Recorded here 14 Oct 2026 23:37 UTC
api
managed-agents/scheduled-deployments
±changed
+8−0
apichanged
managed-agents/scheduled-deployments
<Note>
On [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), each run creates its session as an IAM role in your AWS account. Before
* **Trust policy:** Allow the `aws-external-anthropic.amazonaws.com` service principal to call `sts:AssumeRole` and `sts:SetSourceIdentity`.
+8 −0 lines
Recorded here 14 Oct 2026 23:37 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+18−0
apichanged
manage-claude/inference-hooks-endpoint
A `tool_use` block for a web search tool that claude.ai provides itself:
```json
{
"type": "tool_use",
+18 −0 lines
Recorded here 14 Oct 2026 23:37 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+1−1
apichanged
build-with-claude/claude-platform-on-aws
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) is available on Claude Platform on AWS, including [agents](https://platform.claude.com/docs/en/
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) is available on Claude Platform on AWS, including [agents](https://platform.claude.com/docs/en/
+1 −1 lines
Recorded here 14 Oct 2026 23:37 UTC
api
about-claude/api-credits-for-subscribers
+new page
+151−0
apinew page
about-claude/api-credits-for-subscribers
No line of the body moved in this read.
+151 −0 lines
Recorded here 14 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/installation
±changed
+10−1
claude-docschanged
third-party/claude-desktop/installation
The helper is Authenticode-signed with publisher `Anthropic, PBC`. For Defender ASR or AppLocker, allowlist by publisher rather than path. Standard installs use `%APPDATA%\Claude\`
The helper is Authenticode-signed with publisher `Anthropic, PBC`. Standard installs use `%APPDATA%\Claude\` with the same subpath.
For Defender ASR, a Microsoft Defender for Endpoint [certificate indicator](https://learn.microsoft.com/en-us/defender-endpoint/indicator-certificates) matches one certificate, not
+10 −1 lines
Upstream edited 14 Oct 2026 23:37 UTC Recorded here 15 Oct 2026 00:07 UTC
claude-docs
third-party/claude-desktop/models
±changed
+7−7
claude-docschanged
third-party/claude-desktop/models
Claude Desktop on third-party (3P) builds the model picker in Chat, Cowork, and Code from your configuration. Your configuration decides which models the picker offers, which model
Claude Desktop on third-party (3P) builds the model picker in Chat, Cowork, and Code from your configuration. Your configuration decides which models the picker offers, which model
If you leave `inferenceModels` unset and your provider supports [model discovery](/docs/third-party/claude-desktop/configuration#modeldiscoveryenabled), Claude Desktop fills the pi
If you leave `inferenceModels` unset and your provider supports [model discovery](/docs/third-party/claude-desktop/configuration.md#modeldiscoveryenabled), Claude Desktop fills the
* `prefer1m: true`, with `supports1m: true`, shows the model as one entry. New conversations with it use the 1M context window. To do this for every entry that sets `supports1m`, s
+7 −7 lines
Upstream edited 14 Oct 2026 23:16 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+140−144
claude-docschanged
third-party/claude-desktop/gateway
<Steps>
<Step title="Register an application in Entra ID">
In the [Microsoft Entra admin center](https://entra.microsoft.com), go to **Identity → Applications → App registrations** and select **New registration**. Give it a name such a
On the overview page, copy the **Application (client) ID** and **Directory (tenant) ID**. You will use both in the next two steps.
+140 −144 lines
Upstream edited 14 Oct 2026 23:16 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/models
±changed
+8−3
claude-docschanged
third-party/claude-desktop/models
* `prefer1m: true`, with `supports1m: true`, shows the model as one entry. New conversations with it use the 1M context window.
* `prefer1m: true`, with `supports1m: true`, shows the model as one entry. New conversations with it use the 1M context window. To do this for every entry that sets `supports1m`, s
On any provider, a Chat conversation, Cowork session, or Code session on an entry without `supports1m` assumes a context window from the model ID:
+8 −3 lines
Upstream edited 14 Oct 2026 23:16 UTC Recorded here 14 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+3−3
claude-docschanged
third-party/claude-desktop/gateway
If your deployment supports the 1M-token context window for a model, set `supports1m: true` on that model's entry:
A session assumes 200K tokens for a model ID it doesn't recognize as having a native 1M context window (see [Context window and compaction](#context-window-and-compaction)). If you
[{"name": "bedrock/us.anthropic.claude-opus-5", "supports1m": true}]
[{"name": "bedrock/us.anthropic.claude-opus-4-6-v1", "supports1m": true}]
To show a model as one entry, add `prefer1m: true` next to `supports1m` on its entry. New conversations with that model use the 1M context window. To do this for every model that s
+3 −3 lines
Upstream edited 14 Oct 2026 23:16 UTC Recorded here 14 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/feature-matrix
±changed
+46−46
claude-docschanged
third-party/claude-desktop/feature-matrix
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through [a provider you configure](/docs/third-party/claude-desktop/overvi
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through [a provider you configure](https://claude.com/docs/third-party/cla
The Claude Enterprise features in this table are enduring differences between Claude Enterprise and Claude Desktop on 3P. Anthropic doesn't have the technical ability to bring thes
The Claude Enterprise features in this table are enduring differences between Claude Enterprise and Claude Desktop on 3P. Anthropic doesn't have the technical ability to bring thes
| [Connect to your cloud provider for inference](/docs/third-party/claude-desktop/configuration.md#connection) | No | **Yes** |
+46 −46 lines
Upstream edited 14 Oct 2026 22:48 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/feature-matrix
±changed
+45−45
claude-docschanged
third-party/claude-desktop/feature-matrix
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through [a provider you configure](/docs/third-party/claude-desktop/overvi
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through [a provider you configure](/docs/third-party/claude-desktop/overvi
The Claude Enterprise features in this table are enduring differences between Claude Enterprise and Claude Desktop on 3P. Anthropic doesn't have the technical ability to bring thes
The Claude Enterprise features in this table are enduring differences between Claude Enterprise and Claude Desktop on 3P. Anthropic doesn't have the technical ability to bring thes
| [Connect to your cloud provider for inference](/docs/third-party/claude-desktop/configuration#connection) | No | **Yes** |
+45 −45 lines
Upstream edited 14 Oct 2026 22:48 UTC Recorded here 22 Oct 2026 18:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.