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
821pages tracked
774 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
148 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
82 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
14 Oct 2026
440 pages
+22874 −3518 lines
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 14 Oct 2026 01:07 UTC
claude-code
errors
±changed
+69−7
claude-codechanged
errors
| `Failed to fetch session from Sessions API: Failed to fetch session logs` | [Network](#failed-to-fetch-session-from-sessions-api) |
| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#cloud-sessions-are-disabled-by-your-organizations-policy) |
| `Cloud sessions use your claude.ai login`, at the end of a policy denial that names a credential | [Command-line errors](#cloud-sessions-use-your-claude-ai-login) |
| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |
| `Cloud sessions aren't available:` followed by why your organization's policy couldn't be loaded | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessi
+69 −7 lines
Upstream edited 14 Oct 2026 01:06 UTC Recorded here 14 Oct 2026 01:07 UTC
claude-code
claude-code-on-the-web
±changed
+3−2
claude-codechanged
claude-code-on-the-web
| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | The `allow_remote_sessions` organization policy is off. |
| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code couldn't fetch your organization's policy, so it refus
| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | Your organization's `allow_remote_sessions` policy is off; see [Clo
| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code hasn't finished loading your organization's policy, so
| `Cloud sessions aren't available:` followed by a cause | Loading your organization's policy failed, and the rest of the message says how. Act on the cause it names; see [Couldn't
+3 −2 lines
Upstream edited 14 Oct 2026 01:06 UTC Recorded here 14 Oct 2026 01:07 UTC
claude-code
routines
±changed
+5−2
claude-codechanged
routines
API triggers are added to an existing routine from the web. The CLI cannot currently create or revoke tokens.
API triggers are added to an existing routine from the web. The CLI can't currently create, regenerate, or delete tokens.
Each routine has its own token, scoped to triggering that routine only. To rotate or revoke it, return to the same modal and click **Regenerate** or **Revoke**.
Each routine has its own token, scoped to triggering that routine only. To turn off API access or rotate the token, return to the same modal:
+5 −2 lines
Upstream edited 14 Oct 2026 00:08 UTC Recorded here 14 Oct 2026 00:37 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 14 Oct 2026 00:07 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Subagents support automatic compaction using the same logic as the main conversation. Compaction triggers under the same conditions, and `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` applies t
Subagents support automatic compaction. Compaction triggers as the subagent's own context window fills, and `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` applies to subagents as well. See [env
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
settings-reference
±changed
+45−1
claude-codechanged
settings-reference
| [`idleCompaction`](#idlecompaction) | Stop Claude Code from compacting a long conversation while your terminal session is idle | Memory and context | Any file |
The manual `/compact` command keeps working while auto-compact is off.
The manual `/compact` command keeps working while auto-compact is off. If you turn auto-compact off, [idle compaction](#idlecompaction) turns off too.
### `idleCompaction`
+45 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `precompute_reuse`: Only set when `trigger` is `"manual"`. Auto-compaction can prepare a summary in the background before the context window fills, and this attribute records whe
* `precompute_reuse`: Only set when `trigger` is `"manual"` or for an [idle compaction](/docs/en/settings-reference#idlecompaction), which reports `trigger` as `"auto"`. Auto-compa
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
model-config
±changed
+2−0
claude-codechanged
model-config
See the [`idleCompaction`](/docs/en/settings-reference#idlecompaction) setting for when Claude Code also compacts a conversation you leave idle.
+2 −0 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
Claude Code compacts automatically as you approach the limit, so a full context window doesn't end your session. The automatic pass works the same way as the `/compact` step in the
Claude Code compacts automatically as you approach the limit, so a full context window doesn't end your session. The automatic pass works the same way as the `/compact` step in the
+1 −1 lines
Upstream edited 14 Oct 2026 00:07 UTC Recorded here 14 Oct 2026 00:07 UTC
claude-code
code-review
±changed
+0−2
claude-codechanged
code-review
If the repository belongs to an organization and your membership in that organization is private, which is GitHub's default, GitHub doesn't identify you to Claude as a member. Clau
+0 −2 lines
Upstream edited 14 Oct 2026 00:00 UTC Recorded here 14 Oct 2026 00:07 UTC
13 Oct 2026
94 pages
+5285 −1440 lines
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
* **Repository scope**: the proxy serves GitHub API requests for the repositories attached to the session. An API request for another repository gets a 403 whose message starts wit
* **Repository scope**: the proxy serves GitHub API requests for the repositories attached to the session. An API request for another repository gets a 403 whose message starts wit
+1 −1 lines
Upstream edited 13 Oct 2026 23:57 UTC Recorded here 14 Oct 2026 00:07 UTC
api
managed-agents/secure-deployment-risks
+new page
+45−0
apinew page
managed-agents/secure-deployment-risks
No line of the body moved in this read.
+45 −0 lines
Recorded here 13 Oct 2026 23:37 UTC
api
managed-agents/secure-deployment-monitoring
+new page
+79−0
apinew page
managed-agents/secure-deployment-monitoring
No line of the body moved in this read.
+79 −0 lines
Recorded here 13 Oct 2026 23:37 UTC
api
managed-agents/secure-deployment
+new page
+860−0
apinew page
managed-agents/secure-deployment
No line of the body moved in this read.
+860 −0 lines
Recorded here 13 Oct 2026 23:37 UTC
api
managed-agents/multiagent-orchestration
±changed
+1−1
apichanged
managed-agents/multiagent-orchestration
Whether your client can read the advice is the advisor model's policy. It mirrors the [result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#r
Whether your client can read the advice is the advisor model's policy. It mirrors the [result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#r
+1 −1 lines
Recorded here 13 Oct 2026 23:07 UTC
api
managed-agents/dreams
±changed
+10−10
apichanged
managed-agents/dreams
"model": "claude-opus-4-8",
"model": "claude-opus-5-5",
model: claude-opus-4-8
model: claude-opus-5-5
model="claude-opus-4-8",
+10 −10 lines
Recorded here 13 Oct 2026 23:07 UTC
api
managed-agents/budgets
±changed
+1−1
apichanged
managed-agents/budgets
The cap is enforced between model requests, not mid-request. Before each model request, the platform checks the session's consumed list cost, and once that total reaches the cap ev
The cap is enforced between model requests, not mid-request. Before each model request, the platform checks the session's consumed list cost, and once that total reaches the cap ev
+1 −1 lines
Recorded here 13 Oct 2026 23:07 UTC
api
managed-agents/agent-setup
±changed
+15−15
apichanged
managed-agents/agent-setup
| Field | Description
| ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------
| `name` (java, php; csharp, go: `Name`) | Required. A human-readable name for the agent.
| `model` (java, php; csharp, go: `Model`) | Required. The Claude [model](https://platform.claude.com/docs/en/models/overview) that powers th
| `system` (java, php; csharp, go: `System`; ruby: `system_`) | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claud
+15 −15 lines
Recorded here 13 Oct 2026 23:07 UTC
api
manage-claude/usage-cost-api
±changed
+2−2
apichanged
manage-claude/usage-cost-api
description: Programmatically access your organization's API usage and cost data with the Usage & Cost Admin API.
description: Programmatically access your organization's API usage and cost data with the Usage and Cost Admin API.
The Usage & Cost Admin API provides programmatic and granular access to historical API usage and cost data for your organization. This data is similar to the information available
The Usage and Cost Admin API provides programmatic and granular access to historical API usage and cost data for your organization. This data is similar to the information availabl
+2 −2 lines
Recorded here 13 Oct 2026 23:07 UTC
api
manage-claude/rate-limits-api
±changed
+11−9
apichanged
manage-claude/rate-limits-api
curl "https://api.anthropic.com/v1/organizations/rate_limits?model=claude-opus-5" \
curl "https://api.anthropic.com/v1/organizations/rate_limits?model=claude-opus-5-5" \
ant organization:rate-limits list --model claude-opus-5
ant organization:rate-limits list --model claude-opus-5-5
rate_limits = client.organization.rate_limits.list(model="claude-opus-5")
+11 −9 lines
Recorded here 13 Oct 2026 23:07 UTC
api
manage-claude/analytics-api
±changed
+5−1
apichanged
manage-claude/analytics-api
Looking for API usage and cost data rather than product analytics? See the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api), which explains
Looking for API usage and cost data rather than product analytics? See the
[Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api)
+5 −1 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/vision
±changed
+1−1
apichanged
build-with-claude/vision
To estimate cost, multiply the token count by the [per-token price of the model](https://claude.com/pricing) you're using. For example, at Claude Haiku 4.5's $1 USD per million inp
To estimate cost, multiply the token count by the [per-token price of the model](https://claude.com/pricing) you're using. For example, at Claude Haiku 4.5's $1 USD per million inp
+1 −1 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/thinking-troubleshooting
±changed
+1−3
apichanged
build-with-claude/thinking-troubleshooting
Claude Haiku 5.5 returns the same message for a per-message effort change while `thinking: {type: "disabled"}` is set.
Remove that per-message effort, or set it to the level in effect. To vary effort per turn, use adaptive thinking, which is what the message means by "enable thinking".
Remove that per-message effort, or set it to the level in effect. To vary effort per turn, use adaptive thinking: omit the `thinking` field or send `thinking: {"type": "adaptive"}`
+1 −3 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+27−31
apichanged
build-with-claude/thinking-tool-workflows
"model": "claude-opus-4-8",
"model": "claude-opus-5-5",
model: claude-opus-4-8
model: claude-opus-5-5
model="claude-opus-4-8",
+27 −31 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/thinking
±changed
+22−22
apichanged
build-with-claude/thinking
On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, and Claude Haiku
On Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, thinking is off until you set `thinking: {type: "adaptive"}`, which lets Claude determine when and how
On Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Mythos Preview, and Claude Haiku
+22 −22 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+9−9
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
"model": "claude-opus-4-8",
"model": "claude-opus-5-5",
model: claude-opus-4-8
model: claude-opus-5-5
model="claude-opus-4-8",
+9 −9 lines
Recorded here 13 Oct 2026 23:07 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+2−2
apichanged
build-with-claude/claude-in-microsoft-foundry
2. Search for and select a Claude model (for example, claude-opus-5). Each model appears once in the catalog regardless of how many hosting options it supports.
2. Search for and select a Claude model (for example, claude-opus-5-5). Each model appears once in the catalog regardless of how many hosting options it supports.
* **Solution:** Verify you're using the correct deployment name. If you haven't created a custom deployment, use the default model ID (for example, claude-opus-5).
* **Solution:** Verify you're using the correct deployment name. If you haven't created a custom deployment, use the default model ID (for example, claude-opus-5-5).
+2 −2 lines
Recorded here 13 Oct 2026 23:07 UTC
api
api/errors
±changed
+2−2
apichanged
api/errors
model="claude-opus-4-8",
model="claude-opus-5-5",
model: "claude-opus-4-8",
model: "claude-opus-5-5",
+2 −2 lines
Recorded here 13 Oct 2026 23:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+16−16
apichanged
agents-and-tools/tool-use/server-tools
"model": "claude-opus-4-8",
"model": "claude-opus-5-5",
model: claude-opus-4-8
model: claude-opus-5-5
model="claude-opus-4-8", max_tokens=1024, tools=tools, messages=messages
+16 −16 lines
Recorded here 13 Oct 2026 23:07 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+57−51
apichanged
agents-and-tools/tool-use/advisor-tool
"model": "claude-opus-5"
"model": "claude-opus-5-5"
model: claude-opus-5
model: claude-opus-5-5
"model": "claude-opus-5",
+57 −51 lines
Recorded here 13 Oct 2026 23:07 UTC
api
about-claude/use-case-guides/legal-summarization
±changed
+10−16
apichanged
about-claude/use-case-guides/legal-summarization
Model accuracy is extremely important when summarizing legal documents. Claude Opus 5 is an excellent choice for use cases such as this where high accuracy is required. If the size
Model accuracy is extremely important when summarizing legal documents. Claude Opus 5.5 is an excellent choice for use cases such as this where high accuracy is required. If the si
* Input tokens: 108M, about 108,000 per agreement (about 1 token per 2.8 characters, the rate all three models showed on this guide's sample agreement)
* Output tokens per summary, including any thinking tokens, which are billed as output: about 4,800 on Claude Opus 5, 2,000 on Claude Opus 4.8, and 3,100 on Claude Haiku 5.5
* Total output tokens: 4.8M on Claude Opus 5, 2.0M on Claude Opus 4.8, and 3.1M on Claude Haiku 5.5
+10 −16 lines
Recorded here 13 Oct 2026 23:07 UTC
api
about-claude/use-case-guides/customer-support-chat
±changed
+1−1
apichanged
about-claude/use-case-guides/customer-support-chat
For customer support chat, Claude Opus 5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning across
For customer support chat, Claude Opus 5.5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning acros
+1 −1 lines
Recorded here 13 Oct 2026 23:07 UTC
api
about-claude/pricing
±changed
+15−15
apichanged
about-claude/pricing
A one-hour coding session using Claude Opus 5 that consumes 50,000 input tokens and 15,000 output tokens:
| Line item | Calculation | Cost |
| --------------- | ------------------------ | ---------- |
| Input tokens | 50,000 × $5 / 1,000,000 | $0.25 |
+15 −15 lines
Recorded here 13 Oct 2026 23:07 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+6−6
claude-docschanged
third-party/claude-desktop/local-access
Like [Cowork](/docs/cowork/overview.md) in standard Claude Desktop, Claude Desktop on third-party (3P) works directly with files on the user's computer. Users attach one or more **
Like [Cowork](https://claude.com/docs/cowork/overview.md) in standard Claude Desktop, Claude Desktop on third-party (3P) works directly with files on the user's computer. Users att
Set [`allowedWorkspaceFolders`](/docs/third-party/claude-desktop/configuration#allowedworkspacefolders) in the managed configuration to restrict which paths users may attach as wor
Set [`allowedWorkspaceFolders`](https://claude.com/docs/third-party/claude-desktop/configuration#allowedworkspacefolders) in the managed configuration to restrict which paths users
A leading `~` expands to the user's home directory, so a single profile can express per-user roots like `~/Documents/Claude` across the fleet. A path may also reference one of a fi
+6 −6 lines
Upstream edited 13 Oct 2026 22:40 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+6−6
claude-docschanged
third-party/claude-desktop/local-access
Like [Cowork](/docs/cowork/overview) in standard Claude Desktop, Claude Desktop on third-party (3P) works directly with files on the user's computer. Users attach one or more **wor
Like [Cowork](/docs/cowork/overview.md) in standard Claude Desktop, Claude Desktop on third-party (3P) works directly with files on the user's computer. Users attach one or more **
Set [`allowedWorkspaceFolders`](/docs/third-party/claude-desktop/configuration#allowedworkspacefolders) in the managed configuration to restrict which paths users may attach as wor
Set [`allowedWorkspaceFolders`](/docs/third-party/claude-desktop/configuration#allowedworkspacefolders) in the managed configuration to restrict which paths users may attach as wor
A leading `~` expands to the user's home directory, so a single profile can express per-user roots like `~/Documents/Claude` across the fleet. A path may also reference one of a fi
+6 −6 lines
Upstream edited 13 Oct 2026 22:40 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+3−3
claude-docschanged
third-party/claude-desktop/local-access
<Note>
The allowlist controls what users can **attach**. Within an attached read/write folder, the agent can read and write every file the user's OS account can reach. Data outside the
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 13 Oct 2026 22:40 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/ssh-remote-sessions
±changed
+98−18
claude-docschanged
third-party/claude-desktop/ssh-remote-sessions
### Where MCP servers run in a remote session
An MCP server in a remote session runs on the device or on the host, depending on how it was added.
+98 −18 lines
Upstream edited 13 Oct 2026 22:40 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+1−1
claude-docschanged
third-party/claude-desktop/local-access
| `mode` | `rw` (the default) or `ro`. The agent can view and search a read-only folder but cannot modify it in Cowork. In Code sessions, read-only applies to Claude's file tools o
| `mode` | `rw` (the default) or `ro`. The agent can view and search a read-only folder but cannot modify it in Cowork. In Code sessions other than SSH remote sessions, read-only a
+1 −1 lines
Upstream edited 13 Oct 2026 22:40 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
claude-science/compute-providers
±changed
+3−3
claude-docschanged
claude-science/compute-providers
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
If your organization manages the network allowlist, set **Network restrictions** on the Modal page under **Settings** > **Compute** to **Allowlist** or **No network** before you ru
If your organization manages the network allowlist, set **Network restrictions** on the Modal page under **Settings** > **Compute** to **Allowlist** or **No network** before you ru
On Team and Enterprise plans, your organization's admin can turn off scientific model endpoints for the organization. When your admin turns them off, you can't connect these provid
+3 −3 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-science/compute-providers
±changed
+3−3
claude-docschanged
claude-science/compute-providers
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
If your organization manages the network allowlist, set **Network restrictions** on the Modal page under **Settings** > **Compute** to **Allowlist** or **No network** before you ru
If your organization manages the network allowlist, set **Network restrictions** on the Modal page under **Settings** > **Compute** to **Allowlist** or **No network** before you ru
On Team and Enterprise plans, your organization's admin can turn off scientific model endpoints for the organization. When your admin turns them off, you can't connect these provid
+3 −3 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/compute-providers
±changed
+3−3
claude-docschanged
claude-science/compute-providers
<Note>
Closing the app doesn't cancel a running Modal job; it continues billing until it finishes or times out.
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-science/run-on-remote-linux-server
±changed
+5−5
claude-docschanged
claude-science/run-on-remote-linux-server
* **Ask the server's administrator** to set up what the sandbox needs: bubblewrap 0.8.0 or later, socat, and a kernel that allows unprivileged user namespaces.
* **Ask the server's administrator** to set up what the sandbox needs: bubblewrap 0.8.0 or later and socat, installed for the whole system (from the distribution's packages, or by
Administrators usually install bubblewrap and socat, and only an administrator can change the kernel setting. On Ubuntu 23.10 and later, bubblewrap can also need an AppArmor profil
An administrator installs bubblewrap and socat, and only an administrator can change the kernel setting. On Ubuntu 23.10 and later, bubblewrap can also need an AppArmor profile tha
| An error mentioning `bwrap not found on PATH` | bubblewrap isn't installed, or isn't on your PATH. Install it as shown in [Install dependencies](#install-dependencies), or ask th
+5 −5 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
claude-science/manage-on-devices
±changed
+11−0
claude-docschanged
claude-science/manage-on-devices
## Windows signing certificate
Claude Science for Windows is signed by Anthropic, PBC. If your security software allows apps by their signature, allow the publisher, Anthropic, PBC, rather than one exact certifi
If you allow by SHA-1 thumbprint, keep both of these on your list until every PC runs version 0.1.61 or later:
+11 −0 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
claude-science/get-started
±changed
+4−4
claude-docschanged
claude-science/get-started
Install the sandbox dependencies, then run the installer. The sandbox needs bubblewrap 0.8.0 or later and socat, and installing them takes administrator (root or `sudo`) access
Install the sandbox dependencies, then run the installer. The sandbox needs bubblewrap 0.8.0 or later and socat, and installing them takes administrator (root or `sudo`) access
* On Linux, `claude-science serve` stops with `Sandbox unavailable: bwrap not found on PATH`: bubblewrap isn't installed, or isn't on your PATH. Install bubblewrap and socat with t
* On Linux, `claude-science serve` stops with `Sandbox unavailable: bwrap too old`: the installed bubblewrap is older than 0.8.0. Check the version with `bwrap --version`, then upg
* On Linux, `claude-science serve` stops with a `Sandbox unavailable:` message that says `bwrap not found in` a list of folders, or `bwrap was found on PATH at` a path: bubblewrap
+4 −4 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
claude-science/compute-providers
±changed
+2−0
claude-docschanged
claude-science/compute-providers
To run a local container, install Docker for the whole computer. If Docker is installed only in your home folder, ask Claude to call it by its full path in the endpoint's start and
+2 −0 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
claude-science/changelog
±changed
+11−0
claude-docschanged
claude-science/changelog
<Update label="0.1.61" description="October 13, 2026">
* Sessions you start in the Example project now show on the home screen
* A GitHub token you paste in **Settings > Credentials** now stays after a restart, instead of switching back to the token found on your computer; if yours switched back, paste i
* Fixed some figures in Claude's answers showing a "Load" button where the picture should be
+11 −0 lines
Upstream edited 13 Oct 2026 22:37 UTC Recorded here 13 Oct 2026 23:07 UTC
claude-docs
government/desktop/models
±changed
+3−3
claude-docschanged
government/desktop/models
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls comp
When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls comp
The models a member sees come from the **Allowed models** of their [seat tier](/docs/government/org-admin/seat-tiers.md). Whether a model offers the [1M context window](#larger-con
+3 −3 lines
Upstream edited 13 Oct 2026 21:38 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
government/desktop/models
±changed
+3−3
claude-docschanged
government/desktop/models
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls comp
When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls comp
The models a member sees come from the **Allowed models** of their [seat tier](/docs/government/org-admin/seat-tiers). Whether a model offers the [1M context window](#larger-contex
+3 −3 lines
Upstream edited 13 Oct 2026 21:38 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
government/desktop/models
±changed
+3−3
claude-docschanged
government/desktop/models
<Note>
Before Claude Desktop 2.31226.0, such a model appears twice. To be sure of the larger window, check that the entry marked **1M context window**, or **1M** in Code, is selected wh
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 13 Oct 2026 21:38 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
government/org-admin/seat-tiers
±changed
+1−1
claude-docschanged
government/org-admin/seat-tiers
* Users choose among a tier's allowed models in the Claude Desktop model picker, described in [Models in Claude Desktop](/docs/government/desktop/models). For some models the picke
* Users choose among a tier's allowed models in the Claude Desktop model picker, described in [Models in Claude Desktop](/docs/government/desktop/models). Some models also offer a
+1 −1 lines
Upstream edited 13 Oct 2026 21:38 UTC Recorded here 13 Oct 2026 22:07 UTC
claude-docs
government/desktop/models
±changed
+10−12
claude-docschanged
government/desktop/models
> How the model picker in Claude Desktop works in Claude for Government, what the 1M context window entry does for long conversations that would otherwise be compacted at the stand
> Switch models in Claude Desktop on Claude for Government, see what the 1M context window does, and find what controls which models you see.
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depe
+10 −12 lines
Upstream edited 13 Oct 2026 21:38 UTC Recorded here 13 Oct 2026 22:07 UTC
claude-docs
government/deploy-claude-code/configure
±changed
+2−0
claude-docschanged
government/deploy-claude-code/configure
* Claude Code connects to Claude for Government through a user's [sign-in](#sign-in) rather than an API key or service account. A CI pipeline or other unattended run therefore work
* With Claude for Government, the command-line tool has no access to Claude Code features that [require a claude.ai account](https://code.claude.com/docs/en/feature-availability#fe
+2 −0 lines
Upstream edited 13 Oct 2026 21:27 UTC Recorded here 13 Oct 2026 21:37 UTC
claude-code
claude-tag
±changed
+65−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+65 −1 lines
Recorded here 13 Oct 2026 20:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code, or otherwise stop the `claude` process, t
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code that runs the session on your machine, or
+1 −1 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
claude-code
desktop-quickstart
±changed
+1−1
claude-codechanged
desktop-quickstart
* **SSH**: Connect to a remote machine over SSH, such as your own servers, cloud VMs, or dev containers. Desktop installs Claude Code on the remote machine automatically the fi
* **SSH**: Connect to a remote machine over SSH, such as your own servers, cloud VMs, or dev containers. Desktop installs Claude Code on the remote machine automatically the fi
+1 −1 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
claude-code
desktop
±changed
+163−5
claude-codechanged
desktop
* **Environment**: choose where Claude runs. Select **Local** for your machine, **Cloud** for a [cloud session](#cloud-sessions) that continues after you close the app, an [**SSH c
* **Environment**: choose where Claude runs. Select **Local** for your machine, **Cloud** for a [cloud session](#cloud-sessions) that continues after you close the app, an [**SSH c
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
The integrated terminal lets you run commands alongside your session without switching to another app. Click **Terminal** in the session's title bar or press **Ctrl+\`** on macOS o
+163 −5 lines
Upstream edited 13 Oct 2026 20:19 UTC Recorded here 13 Oct 2026 20:37 UTC
api
api/compliance/activities/list
±changed
+527−3
apichanged
api/compliance/activities/list
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 522 more`
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 524 more`
- `"claude_artifact_type_default_updated"`
An organization's default artifact for an artifact type (for example, its default design system) was set or cleared. Neither artifact named is itself modified.
+527 −3 lines
Recorded here 13 Oct 2026 20:07 UTC
api
api/compliance/activities
±changed
+1036−4
apichanged
api/compliance/activities
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 522 more`
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 524 more`
- `"claude_artifact_type_default_updated"`
An organization's default artifact for an artifact type (for example, its default design system) was set or cleared. Neither artifact named is itself modified.
+1036 −4 lines
Recorded here 13 Oct 2026 20:07 UTC
api
api/compliance
±changed
+527−3
apichanged
api/compliance
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 522 more`
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 524 more`
- `"claude_artifact_type_default_updated"`
An organization's default artifact for an artifact type (for example, its default design system) was set or cleared. Neither artifact named is itself modified.
+527 −3 lines
Recorded here 13 Oct 2026 20:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+42−29
claude-docschanged
claude-tag/admins/restrict-access
A Slack Connect channel is a channel your Slack workspace shares with another company. The [**How should Claude work in channels with guests**](#restrict-guest-channels) setting de
A Slack Connect channel is a channel your Slack workspace shares with another company. The [**How should Claude work in channels with guests**](#restrict-guest-channels) setting, t
* **Channel only** or **Full access**: Claude answers with the [limited access it has in a Slack Connect channel](#what-access-claude-has-in-a-slack-connect-channel). **Full access
To turn Claude on in Slack Connect channels, go to [**Claude's access > Channels**](https://claude.ai/admin-settings/claude-tag?access=channels), open the **Slack** page, a workspa
+42 −29 lines
Upstream edited 13 Oct 2026 19:59 UTC Recorded here 13 Oct 2026 20:07 UTC
claude-docs
third-party/claude-desktop/feature-matrix
±changed
+88−71
claude-docschanged
third-party/claude-desktop/feature-matrix
The tables below compare the feature set of Claude Desktop on third-party (3P) to Claude Enterprise.
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
## Key differences
## Key differences from Claude Enterprise
**Configuration.** Both are administered from the web-based [admin console](/docs/third-party/claude-desktop/admin-console) in **Organization settings** on claude.ai. Claude Deskto
+88 −71 lines
Upstream edited 13 Oct 2026 19:39 UTC Recorded here 13 Oct 2026 20:07 UTC
mcp
community/interest-groups/primitive-grouping
−removed
+0−129
mcpremoved
community/interest-groups/primitive-grouping
No line of the body moved in this read.
+0 −129 lines
Recorded here 13 Oct 2026 19:37 UTC
mcp
community/working-groups/progressive-disclosure
±changed
+5−5
mcpchanged
community/working-groups/progressive-disclosure
The Progressive Disclosure Working Group explores how MCP Primitives (Tools, Resources, Prompts, Tasks) might be organized, beyond the flat lists maintained by the protocol, and ho
The Progressive Disclosure Working Group explores how MCP Primitives (Tools, Resources, Prompts, Tasks) might be organized, beyond the flat lists maintained by the protocol, and ho
* **[Tool Annotations IG](/community/interest-groups/tool-annotations)** - annotation-based filtering and selection of primitives intersects with how primitives are organized and s
* **[Skills Over MCP WG](/community/working-groups/skills-over-mcp)** - maintains the published [Skills extension](/extensions/skills/overview); skill discovery and progressive dis
* **[Tool Annotations IG](/community/interest-groups/tool-annotations.md)** - annotation-based filtering and selection of primitives intersects with how primitives are organized an
+5 −5 lines
Upstream edited 13 Oct 2026 19:11 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
community/working-groups/skills-over-mcp
±changed
+2−2
mcpchanged
community/working-groups/skills-over-mcp
Primitive Grouping IG (progressive disclosure patterns), and external projects including
[Progressive Disclosure WG](/community/working-groups/progressive-disclosure) (progressive disclosure patterns), and external projects including
* **Primitive Grouping IG** — Progressive disclosure patterns
* **[Progressive Disclosure WG](/community/working-groups/progressive-disclosure)** — Progressive disclosure patterns
+2 −2 lines
Upstream edited 13 Oct 2026 19:11 UTC Recorded here 13 Oct 2026 19:37 UTC
mcp
community/working-groups/progressive-disclosure
+new page
+129−0
mcpnew page
community/working-groups/progressive-disclosure
No line of the body moved in this read.
+129 −0 lines
Upstream edited 13 Oct 2026 19:11 UTC Recorded here 13 Oct 2026 19:37 UTC
claude-code
claude-tag
±changed
+11−10
claude-codechanged
claude-tag
No line of the body moved in this read.
+11 −10 lines
Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/web-tools
±changed
+11−9
claude-docschanged
third-party/claude-desktop/web-tools
You can add it from the [in-app configuration window](/docs/third-party/claude-desktop/in-app-configuration): under **Connectors**, add a **Web search** server, choose the search p
You can add it from the [in-app configuration window](/docs/third-party/claude-desktop/in-app-configuration.md): under **Connectors**, add a **Web search** server, choose the searc
The Web search server in the Connectors section of the in-app configuration window, with the search provider menu open.
Search queries go to whichever backend you configure. In every option, the query is also visible to your inference provider as part of the conversation, because the model emits the
+11 −9 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/vertex
±changed
+8−8
claude-docschanged
third-party/claude-desktop/vertex
| Your organization already has tooling that obtains a bearer token accepted by Google Cloud's Agent Platform | [Credential helper](/docs/third-party/claude-desktop/configuration#i
| You already operate an LLM proxy | [Gateway provider](/docs/third-party/claude-desktop/gateway) instead of Google Cloud's Agent Platform | None | At your gateway | The proxy hold
| Your organization already has tooling that obtains a bearer token accepted by Google Cloud's Agent Platform | [Credential helper](/docs/third-party/claude-desktop/configuration.m
| You already operate an LLM proxy | [Gateway provider](/docs/third-party/claude-desktop/gateway.md) instead of Google Cloud's Agent Platform | None | At your gateway | The proxy h
When your IdP is Microsoft Entra ID, you can run this sign-in through the [OS identity broker](/docs/third-party/claude-desktop/entra-broker) on Windows and macOS instead of the sy
+8 −8 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/web-tools
±changed
+13−15
claude-docschanged
third-party/claude-desktop/web-tools
<Note>
`coworkEgressAllowedHosts` governs client-side egress (Web Fetch and in-sandbox shell network activity). The SDK Web Search tool in the table above executes server-side at your i
</Note>
> [!NOTE]
>
+13 −15 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/vertex
±changed
+82−88
claude-docschanged
third-party/claude-desktop/vertex
<Warning>
If your Google Workspace or Cloud Identity organization enforces a **Google Cloud session length** of a few hours or less (Admin console → Security → Google Cloud session control
</Warning>
> [!WARNING]
>
+82 −88 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/web-tools
±changed
+20−8
claude-docschanged
third-party/claude-desktop/web-tools
In Claude Desktop on third-party (3P), both are subject to your configuration: search depends on your inference provider, and fetch is gated by the sandbox network allowlist.
In Claude Desktop on third-party (3P), both are subject to your configuration: search depends on your inference provider, and fetch depends on the egress allowlist you set.
Web Fetch runs in the Claude Desktop main process on the user's device. The model supplies only the target URL; it cannot set headers, a request body, or credentials. Every fetch,
In Cowork and Chat, Web Fetch runs in the Claude Desktop main process on the user's device. The model supplies only the target URL; it cannot set headers, a request body, or creden
By default, the sandbox can reach only your inference provider's endpoint, so Web Fetch will fail for any other host unless you've allowed it. To permit fetches:
+20 −8 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/vertex
±changed
+1−1
claude-docschanged
third-party/claude-desktop/vertex
At the start of each Cowork session, the app writes an `authorized_user` Application Default Credentials file (the same format produced by `gcloud auth application-default login`)
At the start of each Cowork session, the app writes an `authorized_user` Application Default Credentials file (the same format produced by `gcloud auth application-default login`)
+1 −1 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+3−3
claude-docschanged
third-party/claude-desktop/telemetry
Leaving this enabled also adds `api.anthropic.com` to the [agent egress allowlist](#required-egress-paths) automatically, so Claude Code can deliver its usage telemetry from inside
Claude Code's usage telemetry is part of this category and goes to `api.anthropic.com`. While this category is on, allow that host at the perimeter, as listed under [Non-essential
The export carries logs and metrics. Cowork sessions, Code sessions, and the desktop application's own events arrive under the `service.name` values `cowork`, `claude-code-desktop`
The export carries logs and metrics. Cowork sessions, Code sessions, and the desktop application's own events arrive under the `service.name` values `cowork`, `claude-code-desktop`
2. **Agent egress allowlist:** the [`coworkEgressAllowedHosts`](/docs/third-party/claude-desktop/configuration#coworkegressallowedhosts) key controls what the agent's web-fetch and
+3 −3 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/overview
±changed
+1−1
claude-docschanged
third-party/claude-desktop/overview
* **Sandboxed tool execution.** Shell commands run in the hardened Cowork VM; file access is scoped to your allowed folders and web fetches to your egress allowlist.
* **Sandboxed tool execution.** In Cowork, shell commands run in the hardened Cowork VM; file access is scoped to your allowed folders and web fetches to your egress allowlist. For
+1 −1 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/network-proxy
±changed
+1−1
claude-docschanged
third-party/claude-desktop/network-proxy
* **Commands in Cowork's sandboxed shell on Linux.** No proxy settings reach the Cowork sandbox on Linux, so `curl`, `pip`, `npm`, `git`, and anything else the agent runs there con
* **Commands in Cowork's sandboxed shell on Linux.** No proxy settings reach the Cowork sandbox on Linux, so `curl`, `pip`, `npm`, `git`, and anything else the agent runs there con
+1 −1 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+1−1
claude-docschanged
third-party/claude-desktop/data-storage
| Per-session working directory | For Cowork sessions, the same file-based credentials (Google Cloud's Agent Platform and Amazon Bedrock) are written into the session's working dir
| Per-session working directory | For Cowork sessions, the same file-based credentials (Google Cloud's Agent Platform and Amazon Bedrock) are written into the session's working dir
+1 −1 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+6−6
claude-docschanged
third-party/claude-desktop/configuration
```json theme={null}
```json theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null}
```json theme={null}
+6 −6 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/code
±changed
+5−1
claude-docschanged
third-party/claude-desktop/code
| `coworkEgressAllowedHosts` | A network sandbox restricted to your hosts plus the inference and telemetry endpoints, `WebFetch` permission rules for the same hosts, and `allowMana
| `coworkEgressAllowedHosts` | A network sandbox restricted to your hosts, `allowManagedDomainsOnly`, and `WebFetch` allow rules for the same hosts, which [don't block other hosts]
<Warning>
Shell commands that run unsandboxed can reach hosts outside `coworkEgressAllowedHosts` and change files outside `allowedWorkspaceFolders`. Where the sandbox runs, a command that
+5 −1 lines
Upstream edited 13 Oct 2026 19:06 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-code
desktop
±changed
+56−0
claude-codechanged
desktop
<Note>
If you use Desktop with a [third-party provider](/docs/en/third-party-integrations), SSH sessions need their own setup. See [SSH remote sessions in Claude Desktop on 3P](https://
</Note>
+56 −0 lines
Upstream edited 13 Oct 2026 19:05 UTC Recorded here 13 Oct 2026 19:07 UTC
claude-docs
cowork/changelog
±changed
+62−0
claude-docschanged
cowork/changelog
<Update label="v2.37337.1" description="2026-10-13">
Bundled Claude Code version: 2.1.295.
**General**
+62 −0 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+3−1
claude-docschanged
third-party/claude-desktop/telemetry
To find out whether a managed profile's keys apply on a device that uses the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console), see [Which settings apply o
| `api.anthropic.com` | Claude Code usage telemetry, sent from inside the agent sandbox |
| `api.anthropic.com` | Claude Code usage telemetry |
+3 −1 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+1−1
claude-docschanged
third-party/claude-desktop/gateway
| <span id="inferencegatewayauthscheme" />Gateway auth scheme<br />`inferenceGatewayAuthScheme` | `enum` | MDM + Bootstrap<br />Added in 1.3036.0 | `bearer` | How the gateway crede
| <span id="inferencegatewayauthscheme" />Gateway auth scheme<br />`inferenceGatewayAuthScheme` | `enum` | MDM + Bootstrap<br />Added in 1.3036.0 | `bearer` | How the gateway crede
+1 −1 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+39−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.37337.1" description="2026-10-13">
<div className="cfg-keys">
| MDM key | Type | Description |
| - | - | - |
+39 −0 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+61−40
claude-docschanged
third-party/claude-desktop/configuration
When a managed source is present, it wins and locally written values are ignored. The exception is a managed source that sets only [app-behavior keys](/docs/third-party/claude-desk
When a managed source is present, locally written values are ignored. The exception is a managed source that sets only [app-behavior keys](/docs/third-party/claude-desktop/mdm#upda
Claude Desktop on 3P reads the same managed-configuration sources as standard Claude Desktop but ignores keys scoped to standard deployments. Keys such as `forceLoginOrgUUID` hav
Claude Desktop on 3P reads the same managed-configuration sources as standard Claude Desktop but ignores keys scoped to standard deployments, except [`forceLoginOrgUUID`](/docs/c
| <span id="inferencecustomheaders" />Custom inference headers<br />`inferenceCustomHeaders` | `object` | MDM + Bootstrap<br />Added in 1.8089.0 | — | Extra headers on every infere
+61 −40 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/bootstrap
±changed
+4−2
claude-docschanged
third-party/claude-desktop/bootstrap
On a device whose MDM profile carries the bootstrap keys, a user who signs in to any organization that uses the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-co
| <span id="bootstrapheaders" />Bootstrap request headers<br />`bootstrapHeaders` | `object` | MDM only<br />Added in 1.32885.1 | — | HTTP headers sent on every bootstrap config fe
| <span id="bootstrapheaders" />Bootstrap request headers<br />`bootstrapHeaders` | `object` | MDM only<br />Added in 1.32885.1 | — | HTTP headers sent on every bootstrap config fe
| <span id="trustbootstrapdelivery" />Trust bootstrap-delivered settings<br />`trustBootstrapDelivery` | `boolean` | MDM only<br />Added in 1.26832.0 | `false` | Skip the per-user
+4 −2 lines
Upstream edited 13 Oct 2026 18:24 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/extensions
±changed
+2−2
claude-docschanged
third-party/claude-desktop/extensions
Put plugin content directly in the marketplace repository with a relative `source` path. Plugins whose `source` points at a different repository are listed in the Organization tab
Put plugin content directly in the marketplace repository with a relative `source` path. When Claude Desktop syncs the marketplace, it doesn't fetch or auto-install a plugin whose
Archive URLs must share the manifest's origin. That origin is the only host you need to allow through your perimeter firewall, and the only host the [marketplace credential](#marke
Archive URLs must share the manifest's origin. That origin is the only host you need to allow through your perimeter firewall, and the only host the [marketplace credential](#marke
+2 −2 lines
Upstream edited 13 Oct 2026 18:11 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/overview
±changed
+1−1
claude-docschanged
third-party/claude-desktop/overview
* **Centrally managed.** Configuration is delivered through your existing MDM (Jamf, Intune, Workspace ONE, Group Policy), a [bootstrap server](/docs/third-party/claude-desktop/boo
* **Centrally managed.** Configuration is delivered through your existing MDM (Jamf, Intune, Workspace ONE, Group Policy), a [bootstrap server](/docs/third-party/claude-desktop/boo
+1 −1 lines
Upstream edited 13 Oct 2026 18:07 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/mdm
±changed
+4−2
claude-docschanged
third-party/claude-desktop/mdm
Distribute the profile through your MDM, then push the installer. Deploying the configuration first means users open Claude for the first time and land directly in the third-pa
Distribute the profile through your MDM, then push the installer. Deploying the configuration first means users open Claude for the first time and land directly in the third-pa
When a managed source sets any key other than the [app-behavior keys](#update-keys-and-managed-precedence) listed below, the managed configuration owns the device: it takes effect,
When a managed source sets any key other than the [app-behavior keys](#update-keys-and-managed-precedence) listed below, the managed configuration takes effect, the in-app configur
+4 −2 lines
Upstream edited 13 Oct 2026 18:07 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/installation
±changed
+1−1
claude-docschanged
third-party/claude-desktop/installation
The models don't combine. A device whose MDM profile or registry policy sets any key other than the [app-behavior keys](/docs/third-party/claude-desktop/mdm#update-keys-and-managed
A device whose MDM profile or registry policy sets any key other than the [app-behavior keys](/docs/third-party/claude-desktop/mdm#update-keys-and-managed-precedence) uses that con
+1 −1 lines
Upstream edited 13 Oct 2026 18:07 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/admin-console
±changed
+64−9
claude-docschanged
third-party/claude-desktop/admin-console
* **MDM or bootstrap fleets:** remove the Claude Desktop configuration profile or registry policy, including a profile or policy that carries only bootstrap keys. A device that kee
* **MDM or bootstrap fleets:** remove the Claude Desktop configuration profile or registry policy, including a profile or policy that carries only bootstrap keys. A profile that se
* Devices carry no MDM-delivered Claude Desktop configuration. If a managed profile or registry policy sets any key other than the [app-behavior keys](/docs/third-party/claude-desk
* Devices carry no MDM-delivered Claude Desktop configuration other than the [app-behavior keys](/docs/third-party/claude-desktop/mdm#update-keys-and-managed-precedence) (the updat
The account menu at the bottom of the sidebar shows your organization's name and an **Inference configuration** item marked **Managed by your organization**, and **Settings → P
+64 −9 lines
Upstream edited 13 Oct 2026 18:07 UTC Recorded here 13 Oct 2026 18:37 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+25−25
claude-docschanged
claude-tag/concepts/security-and-data
In channels, Claude acts under its own service accounts. By default it can read and post in Slack channels it's been added to and search public channels by keyword; it has no acces
In channels, Claude acts under its own service accounts. By default it can read and post in Slack channels it's been added to and search public channels by keyword; it has no acces
One-to-one DMs from members who have connected a Claude account run on the member's own claude.ai account instead and are covered separately on [How agent identity works](/docs/cla
One-to-one DMs from members who have connected a Claude account run on the member's own claude.ai account instead and are covered separately on [How agent identity works](https://c
| Agent Proxy | Injects credentials from the credential store at request time, and blocks a request that no [credential's allowed websites](/docs/claude-tag/admins/add-connections.
+25 −25 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+25−25
claude-docschanged
claude-tag/concepts/security-and-data
In channels, Claude acts under its own service accounts. By default it can read and post in Slack channels it's been added to and search public channels by keyword; it has no acces
In channels, Claude acts under its own service accounts. By default it can read and post in Slack channels it's been added to and search public channels by keyword; it has no acces
One-to-one DMs from members who have connected a Claude account run on the member's own claude.ai account instead and are covered separately on [How agent identity works](/docs/cla
One-to-one DMs from members who have connected a Claude account run on the member's own claude.ai account instead and are covered separately on [How agent identity works](/docs/cla
| Agent Proxy | Injects credentials from the credential store at request time, and blocks a request that no [credential's allowed websites](/docs/claude-tag/admins/add-connections#
+25 −25 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+5−9
claude-docschanged
claude-tag/concepts/security-and-data
export const BetaNote = () => <Info>Claude Tag is in public beta. Features and behavior described here may change before general availability.</Info>;
<BetaNote />
> [!NOTE]
>
+5 −9 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-tag/concepts/security-and-data
±changed
+1−1
claude-docschanged
claude-tag/concepts/security-and-data
Connector credentials reach a channel shared with another company through [Slack Connect](/docs/claude-tag/admins/restrict-access#slack-connect-channels) only through a bundle an O
In a channel shared with another company through [Slack Connect](/docs/claude-tag/admins/restrict-access#slack-connect-channels), once Claude is turned on there, it has the connect
+1 −1 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 13 Oct 2026 17:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+4−2
claude-docschanged
claude-tag/admins/restrict-access
* No [bundles](/docs/claude-tag/admins/attach-to-scope) or connections, except a bundle an Owner [attaches directly to the channel](/docs/claude-tag/admins/attach-to-scope#attach-t
* No [bundles](/docs/claude-tag/admins/attach-to-scope) or connections inherited from the workspace or the **Slack** page, and none attached by a [channel rule](/docs/claude-tag/ad
Treat the channel's instructions as visible to the other company. In a Slack Connect channel, Claude also doesn't search your workspace, look up people or channels, read other chan
Treat the channel's instructions, and the connectors in its bundles, as available to the other company. Before you turn Claude on in a Slack Connect channel, or share a channel whe
+4 −2 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 13 Oct 2026 17:07 UTC
claude-docs
claude-tag/admins/attach-to-scope
±changed
+4−1
claude-docschanged
claude-tag/admins/attach-to-scope
In a channel shared across more than one workspace in your Enterprise Grid, bundles on the channel or its workspace don't apply. See [Channels shared across workspaces in your Ente
Sharing a channel changes which bundles apply there:
* **Shared across workspaces in your Enterprise Grid**: bundles on the channel or its workspace don't apply. See [Channels shared across workspaces in your Enterprise Grid](/docs/c
* **Shared with another company through Slack Connect**: once Claude is [turned on in the channel](/docs/claude-tag/admins/restrict-access#slack-connect-channels), bundles attached
+4 −1 lines
Upstream edited 13 Oct 2026 17:06 UTC Recorded here 13 Oct 2026 17:07 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+17−4
claude-docschanged
third-party/claude-desktop/telemetry
| `assistantResponses` | Model response text |
| `assistantResponses` | Model response text, up to the [content length limit](#content-length-limit) |
| `toolContent` | Tool output content |
| `rawApiBodies` | Full inference request and response bodies |
| `toolContent` | Tool output content, up to the [content length limit](#content-length-limit) |
+17 −4 lines
Upstream edited 13 Oct 2026 16:31 UTC Recorded here 13 Oct 2026 16:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+1−1
claude-docschanged
third-party/claude-desktop/gateway
**`Your context window is full` in a Code session, or `This conversation is too long to continue. Start a new session, or remove some tools to free up space.` in a Cowork session.*
**`Your context window is full` in a Code session, or `Couldn’t compact this conversation to free up space. Try again, or start a new session.` in a Cowork session.** The app shows
+1 −1 lines
Upstream edited 13 Oct 2026 15:56 UTC Recorded here 13 Oct 2026 16:07 UTC
claude-docs
claude-science/enable-claude-science
±changed
+1−1
claude-docschanged
claude-science/enable-claude-science
By continuing, you authorize your team to let Claude use the optional enabled resources on their behalf. These resources and content they reach may be subject to third-party terms
By continuing, you represent that your team has the necessary rights to access these resources and you authorize Claude to do so on their behalf. You can review terms in Settings.
+1 −1 lines
Upstream edited 13 Oct 2026 15:46 UTC Recorded here 13 Oct 2026 16:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.