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
812pages tracked
765 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
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
ReadSourcePageWhatLines
24 Aug 2026
159 pages
+267553 −80359 lines
api
build-with-claude/claude-in-amazon-bedrock
±changed
+1−1
apichanged
build-with-claude/claude-in-amazon-bedrock
Model IDs in Claude in Amazon Bedrock carry an `anthropic.` provider prefix. Model capabilities and behaviors are documented on the [Models overview](https://platform.claude.com/do
Model IDs in Claude in Amazon Bedrock carry an `anthropic.` provider prefix. Model capabilities and behaviors are documented on the [Models overview](https://platform.claude.com/do
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
build-with-claude/citations
±changed
+1−1
apichanged
build-with-claude/citations
All [active models](https://platform.claude.com/docs/en/about-claude/models/overview) support citations.
All [active models](https://platform.claude.com/docs/en/models/overview) support citations.
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
build-with-claude/batch-processing
±changed
+1−1
apichanged
build-with-claude/batch-processing
All [active models](https://platform.claude.com/docs/en/about-claude/models/overview) support the Message Batches API.
All [active models](https://platform.claude.com/docs/en/models/overview) support the Message Batches API.
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/service-tiers
±changed
+1−1
apichanged
api/service-tiers
Check the [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview) for more details on available models.
Check the [Models overview](https://platform.claude.com/docs/en/models/overview) for more details on available models.
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/organizations/settings/retrieve
±changed
+3−1
apichanged
api/compliance/organizations/settings/retrieve
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 43 more`
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 44 more`
- `"group_skill_sharing_enabled"`
+3 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/organizations/settings
±changed
+6−2
apichanged
api/compliance/organizations/settings
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 43 more`
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 44 more`
- `"group_skill_sharing_enabled"`
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 43 more`
+6 −2 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/organizations
±changed
+6−2
apichanged
api/compliance/organizations
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 43 more`
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 44 more`
- `"group_skill_sharing_enabled"`
- `name: "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or "artifact_connectors_enabled" or 43 more`
+6 −2 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions/local/retrieve
±changed
+6−1
apichanged
api/compliance/apps/sessions/local/retrieve
- `updated_at: string`
Timestamp of the session's last retained inference call (RFC 3339, UTC). Always at or after `created_at`. When a session's activity spans the child organization's retention bound
"created_at": "2026-07-09T14:02:11Z"
+6 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions/local/messages/list
±changed
+15−5
apichanged
api/compliance/apps/sessions/local/messages/list
- `data: array of object { id, content, created_at, 3 more }`
Transcript turns for this page, ordered by `created_at` in the direction selected by the `order` parameter (ascending by default). Turns sharing a `created_at` (all messages of o
- `data: array of object { id, content, created_at, 4 more }`
+15 −5 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions/local/messages
±changed
+21−7
apichanged
api/compliance/apps/sessions/local/messages
- `data: array of object { id, content, created_at, 3 more }`
Transcript turns for this page, ordered by `created_at` in the direction selected by the `order` parameter (ascending by default). Turns sharing a `created_at` (all messages of o
- `data: array of object { id, content, created_at, 4 more }`
+21 −7 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions/local/list
±changed
+14−3
apichanged
api/compliance/apps/sessions/local/list
- `updated_at: optional object { gte }`
- `gte: optional string`
Only return sessions whose last inference call is at or after this time (RFC 3339; a UTC offset is required). Combines with `created_at.gte` / `created_at.lt`; the ordering and
+14 −3 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions/local
±changed
+52−14
apichanged
api/compliance/apps/sessions/local
- `updated_at: optional object { gte }`
- `gte: optional string`
Only return sessions whose last inference call is at or after this time (RFC 3339; a UTC offset is required). Combines with `created_at.gte` / `created_at.lt`; the ordering and
+52 −14 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/sessions
±changed
+52−14
apichanged
api/compliance/apps/sessions
- `updated_at: optional object { gte }`
- `gte: optional string`
Only return sessions whose last inference call is at or after this time (RFC 3339; a UTC offset is required). Combines with `created_at.gte` / `created_at.lt`; the ordering and
+52 −14 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/chats/messages/list
±changed
+3−3
apichanged
api/compliance/apps/chats/messages/list
Model selected for this chat (e.g. 'claude-opus-4-7'). May be null for legacy chats that never had a model recorded.
Model selected for this chat (e.g. 'claude-opus-5'). May be null for legacy chats that never had a model recorded.
"organization_uuid": "abcdef0123-4567-89ab-cdef-0123456789ab",
"organization_uuid": "abcdef01-2345-6789-abcd-ef0123456789",
"model": "claude-opus-4-7",
+3 −3 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/chats/messages
±changed
+3−3
apichanged
api/compliance/apps/chats/messages
Model selected for this chat (e.g. 'claude-opus-4-7'). May be null for legacy chats that never had a model recorded.
Model selected for this chat (e.g. 'claude-opus-5'). May be null for legacy chats that never had a model recorded.
"organization_uuid": "abcdef0123-4567-89ab-cdef-0123456789ab",
"organization_uuid": "abcdef01-2345-6789-abcd-ef0123456789",
"model": "claude-opus-4-7",
+3 −3 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/chats/list
±changed
+17−8
apichanged
api/compliance/apps/chats/list
**Deprecation notice:** Combining `user_ids[]` with any `updated_at.*`
filter is deprecated and will be rejected with HTTP 400 after
2026-09-22. For incremental polling by update time, omit `user_ids[]`
and set `order_by=updated_at` with `after_id` cursor pagination —
+17 −8 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps/chats
±changed
+21−12
apichanged
api/compliance/apps/chats
**Deprecation notice:** Combining `user_ids[]` with any `updated_at.*`
filter is deprecated and will be rejected with HTTP 400 after
2026-09-22. For incremental polling by update time, omit `user_ids[]`
and set `order_by=updated_at` with `after_id` cursor pagination —
this returns the same chats across the whole organization in a single
+21 −12 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/apps
±changed
+73−26
apichanged
api/compliance/apps
**Deprecation notice:** Combining `user_ids[]` with any `updated_at.*`
filter is deprecated and will be rejected with HTTP 400 after
2026-09-22. For incremental polling by update time, omit `user_ids[]`
and set `order_by=updated_at` with `after_id` cursor pagination —
this returns the same chats across the whole organization in a single
+73 −26 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/activities/list
±changed
+52228−15260
apichanged
api/compliance/activities/list
No line of the body moved in this read.
+52228 −15260 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance/activities
±changed
+104368−30512
apichanged
api/compliance/activities
No line of the body moved in this read.
+104368 −30512 lines
Recorded here 24 Aug 2026 21:07 UTC
api
api/compliance
±changed
+104447−30540
apichanged
api/compliance
No line of the body moved in this read.
+104447 −30540 lines
Recorded here 24 Aug 2026 21:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+1−1
apichanged
agents-and-tools/tool-use/overview
See the [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison) table for current per-model prices.
See the [Models overview](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) table for current per-model prices.
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/use-case-guides/content-moderation
±changed
+1−1
apichanged
about-claude/use-case-guides/content-moderation
In this example, the `batch_moderate_messages` function handles the moderation of an entire batch of messages with a single Claude API call. Inside the function, a prompt is create
In this example, the `batch_moderate_messages` function handles the moderation of an entire batch of messages with a single Claude API call. Inside the function, a prompt is create
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/whats-new-sonnet-5
−removed
+0−216
apiremoved
about-claude/models/whats-new-sonnet-5
No line of the body moved in this read.
+0 −216 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/whats-new-opus-5
−removed
+0−351
apiremoved
about-claude/models/whats-new-opus-5
No line of the body moved in this read.
+0 −351 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/overview
−removed
+0−183
apiremoved
about-claude/models/overview
No line of the body moved in this read.
+0 −183 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+14−2
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
| You are not on the latest model | Upgrade; the current model solves more, usually at lower cost per solved task
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, and the budgets and caps it works within. S
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, and the budgets and caps it works within. S
### Upgrade the model
+14 −2 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/model-ids-and-versions
±changed
+1−1
apichanged
about-claude/models/model-ids-and-versions
For the full list of current model IDs and their Amazon Bedrock and Google Cloud equivalents, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview
For the full list of current model IDs and their Amazon Bedrock and Google Cloud equivalents, see [Models overview](https://platform.claude.com/docs/en/models/overview).
+1 −1 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/migration-guide
±changed
+13−13
apichanged
about-claude/models/migration-guide
[Claude Fable 5](https://platform.claude.com/docs/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5) is Anthropic's most capable widely released model, availabl
[Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) is Anthropic's most capable widely released model, available on
[Claude Mythos 5](https://anthropic.com/glasswing) is the access-gated successor to [Claude Mythos Preview](https://anthropic.com/glasswing), the invitation-only research preview.
[Claude Mythos 5](https://anthropic.com/glasswing) is the access-gated successor to [Claude Mythos Preview](https://anthropic.com/glasswing), the invitation-only research preview.
Claude Fable 5 and Claude Mythos 5 use the same [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the same [tool use](https://platform
+13 −13 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/introducing-claude-fable-5-and-claude-mythos-5
−removed
+0−133
apiremoved
about-claude/models/introducing-claude-fable-5-and-claude-mythos-5
No line of the body moved in this read.
+0 −133 lines
Recorded here 24 Aug 2026 21:07 UTC
api
about-claude/models/choosing-a-model
±changed
+4−4
apichanged
about-claude/models/choosing-a-model
**Claude Fable 5** (`claude-fable-5`) is Anthropic's most capable widely released model, delivering next-generation intelligence for long-running agents. **Claude Mythos 5** (`clau
**Claude Fable 5** (`claude-fable-5`) is Anthropic's most capable widely released model, delivering next-generation intelligence for long-running agents. **Claude Mythos 5** (`clau
<Card title="Model comparison chart" icon="settings" href="https://platform.claude.com/docs/en/about-claude/models/overview">
<Card title="Model comparison chart" icon="settings" href="https://platform.claude.com/docs/en/models/overview">
<Card title="What's new in Claude Opus 5" icon="sparkle" href="https://platform.claude.com/docs/en/about-claude/models/whats-new-opus-5">
+4 −4 lines
Recorded here 24 Aug 2026 21:07 UTC
claude-docs
connectors/building/enterprise-managed-auth
±changed
+8−4
claude-docschanged
connectors/building/enterprise-managed-auth
Enterprise Managed Auth is in beta and is available on Claude Team and Enterprise plans. Organizations can [join the waitlist](https://claude.com/form/ema-waitlist) to request ac
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
<Note>
Enterprise Managed Auth is in beta. [Register interest](https://docs.google.com/forms/d/e/1FAIpQLSf1goHGNDVFK7rncYuh6wnRpWSy7eGOcgL1i8uw3oyKFO9UUA/viewform) to get onboarded for
</Note>
+8 −4 lines
Recorded here 24 Aug 2026 20:37 UTC
claude-docs
claude-tag/admins/skills-repo
±changed
+14−0
claude-docschanged
claude-tag/admins/skills-repo
## Upload a plugin as a zip file
To upload instead, on the **Plugins** page at [`claude.ai/admin-settings/plugins`](https://claude.ai/admin-settings/plugins), click **Add plugins**, choose **Upload a file**, and u
* A `.claude-plugin/plugin.json` manifest at the archive root, with each skill in its own folder at `skills/<name>/SKILL.md`
+14 −0 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+8−0
claude-docschanged
claude-tag/admins/restrict-access
### Restrict who can link a Claude account by email domain
On Enterprise plans, if your organization belongs to a parent enterprise organization, you see one more toggle in the same **Manage** dialog, **Restrict to your verified domains**.
+8 −0 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/customize
±changed
+1−1
claude-docschanged
claude-tag/admins/customize
An Owner configures Claude's connections, plugins, and skills, and they apply per scope. They are separate from the connectors, skills, or MCP servers an individual user has set up
An Owner configures Claude's connections, plugins, and skills, and they apply per scope. They are separate from the connectors, skills, or MCP servers an individual user has set up
+1 −1 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/connections/custom
±changed
+4−0
claude-docschanged
claude-tag/admins/connections/custom
After saving, where the credential has an allow rule, you can narrow it by HTTP method and path from its **Edit connection** dialog; see [Restrict by path or method](/docs/claude-t
If Claude reports that it can't use the credential, check its status on the [Access bundles page](https://claude.ai/admin-settings/claude-tag/access-bundles). **Not active** means
+4 −0 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/attach-to-scope
±changed
+6−0
claude-docschanged
claude-tag/admins/attach-to-scope
At the channel's top level, outside any thread, Claude works from a single long-lived channel session. After a configuration change, Claude replaces that session on the next channe
What Claude reads in a channel is the concatenated custom instructions of its scope chain, plus the `CLAUDE.md` of any repository it clones. Projects in claude.ai don't apply here;
A new instruction applies to sessions started after you save it. Claude reads it in every new thread right away, keeps the old text in a thread that's already running, and picks it
+6 −0 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/add-connections
±changed
+16−2
claude-docschanged
claude-tag/admins/add-connections
You don't have to predict the full list up front. When a request is blocked, Claude says so in the thread and names the host; add that host here and retry; if it's still blocked, s
You don't have to predict the full list up front. When a request is blocked, Claude says so in the thread and names the host, with wording like "blocked by the network egress proxy
* **The bundle is attached to the channel's scope.** Claude can use a Domains entry only in channels whose scope, or an ancestor scope, has this bundle attached; see [Attach bundle
* **The entry matches the exact host.** A wildcard like `*.example.com` doesn't cover `example.com` itself, and `www.example.com` and `example.com` are different hosts.
+16 −2 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-code
vs-code
±changed
+7−7
claude-codechanged
vs-code
* **Status Bar**: click **✱ Claude Code** in the bottom-right corner of the window. This works even when no file is open.
* **Status Bar**: if you've set [`preferredLocation`](#extension-settings) to `sidebar`, or opened Claude with **Claude Code: Open in Side Bar**, click **✱ Claude Code** in the
* The Settings section also includes **Focus view**, which hides tool calls, tool results, and thinking behind expandable rows, leaving your prompts and Claude's responses. Claud
* The Settings section also includes **Focus view**, which hides tool calls, tool results, and thinking behind expandable rows, leaving your prompts and Claude's responses. Claud
| Open in Side Bar | - | Open Claude in the left sidebar
+7 −7 lines
Recorded here 24 Aug 2026 20:07 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+1−1
claude-docschanged
claude-tag/admins/setup-overview
<Step title="Set up an email for Claude">
<Step title="Create an email address for Claude">
+1 −1 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
plugin-marketplaces
±changed
+7−2
claude-codechanged
plugin-marketplaces
To support "stable" and "latest" release channels for your plugins, you can set up two marketplaces that point to different refs or SHAs of the same repo. You can then assign the t
To support "stable" and "latest" release channels for your plugins, you can set up two marketplaces that point to different refs or SHAs of the same repo. You can then give each us
* Deploy separate [endpoint-managed settings](/docs/en/managed-settings#delivery-mechanisms), such as a managed settings file or an MDM profile, to each group's devices. On each de
* Define one [Claude apps gateway policy](/docs/en/claude-apps-gateway-config#managed) per group. The gateway applies the first policy whose match rule fits a user, so order the po
+7 −2 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
permission-modes
±changed
+2−18
claude-codechanged
permission-modes
This example sets Plan mode as the default for new local sessions:
```json theme={null}
{
"permissions": {
+2 −18 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
Cloud sessions on [Claude Code on the web](/docs/en/claude-code-on-the-web) don't read your local `~/.claude/settings.json`; hooks there come from the repo and from your organizati
Cloud sessions on [Claude Code on the web](/docs/en/claude-code-on-the-web) don't read your local `~/.claude/settings.json`; hooks there come from the repo and from your organizati
+1 −1 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
* Get the [PowerShell tool](/docs/en/tools-reference#powershell-tool) by default for claude.ai and Console accounts on Windows with Git Bash installed; Claude Code routes shell com
+1 −0 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
If you have SessionStart hooks in your user-level `~/.claude/settings.json`, don't expect them in the cloud: user-level settings stay on your machine. In a cloud session, Claude Co
If you have SessionStart hooks in your user-level `~/.claude/settings.json`, don't expect them in the cloud: user-level settings stay on your machine. In a cloud session, Claude Co
+1 −1 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
Each `cli` value is a complete Claude Code `managed-settings.json` document, the same schema you would deploy via MDM or `/etc/claude-code/managed-settings.json`, expressed here as
Each `cli` value is a complete Claude Code `managed-settings.json` document, the same schema you would deploy via MDM or `/etc/claude-code/managed-settings.json`, expressed here as
+1 −1 lines
Recorded here 24 Aug 2026 19:37 UTC
claude-code
settings-reference
±changed
+3−3
claude-codechanged
settings-reference
Permission rules layer on top of every mode: `deny` rules block in every mode, including `bypassPermissions`. See [Permission modes](/docs/en/permission-modes). `manual` names the
Permission rules layer on top of every mode: `deny` rules block in every mode, including `bypassPermissions`. See [Permission modes](/docs/en/permission-modes). `manual` names the
[`allowedMcpServers`](#allowedmcpservers) and [`deniedMcpServers`](#deniedmcpservers) still apply to the connectors this key loads. Connectors delivered to [cloud sessions](/docs/e
[`allowedMcpServers`](#allowedmcpservers) and [`deniedMcpServers`](#deniedmcpservers) still apply to the connectors this key loads. Connectors delivered to [cloud sessions](/docs/e
Choose how [background sessions](/docs/en/agent-view#how-file-edits-are-isolated) isolate their file edits. With `"worktree"`, Claude Code blocks `Edit` and `Write` in the main che
+3 −3 lines
Recorded here 24 Aug 2026 19:07 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null}
+5 −5 lines
Recorded here 24 Aug 2026 19:07 UTC
claude-code
managed-mcp
±changed
+10−10
claude-codechanged
managed-mcp
To make the allowlist authoritative, set `allowedMcpServers` and `allowManagedMcpServersOnly: true` together in a [managed settings source](/docs/en/admin-setup#decide-how-settings
To make the allowlist authoritative, set `allowedMcpServers` and `allowManagedMcpServersOnly: true` together in a [managed settings source](/docs/en/admin-setup#decide-how-settings
1. **Merge the lists.** Allowlist and denylist entries from every settings source combine into one allowlist and one denylist. When `allowManagedMcpServersOnly` is `true`, only the
1. **Merge the lists.** Allowlist and denylist entries from every settings scope combine into one allowlist and one denylist, with the managed scope's lists read from the one [mana
When `allowManagedMcpServersOnly` is `true`, allowlists from user, project, and local settings are ignored. The denylist still merges from all sources, so users can always block se
+10 −10 lines
Recorded here 24 Aug 2026 19:07 UTC
claude-code
context-window
±changed
+34−20
claude-codechanged
context-window
restoredAfterCompact: true,
restoredAfterCompact: true,
restoredAfterCompact: true,
restoredAfterCompact: true,
restoredAfterCompact: true,
+34 −20 lines
Recorded here 24 Aug 2026 19:07 UTC
claude-code
quickstart
±changed
+6−6
claude-codechanged
quickstart
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+6 −6 lines
Recorded here 24 Aug 2026 18:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
If you set `defaultMode: "auto"` in [settings](/docs/en/settings-reference#all-settings) and a terminal session starts in Manual mode with no error, the setting is likely in `.clau
If you set `defaultMode: "auto"` in [settings](/docs/en/settings-reference#all-settings) and a terminal session starts in Manual mode with no error, the setting is likely in `.clau
+1 −1 lines
Recorded here 24 Aug 2026 18:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
Unable to connect to API: Self-signed certificate detected
Unable to connect to API: Self-signed certificate detected. Check your proxy or corporate SSL certificates
+1 −1 lines
Recorded here 24 Aug 2026 18:37 UTC
claude-code
agent-sdk/skills
±changed
+6−2
claude-codechanged
agent-sdk/skills
For project and personal skills, the `allowed-tools` frontmatter field applies only when you use the Claude Code CLI directly. In SDK sessions, manage tool approval for these ski
For project and personal skills, Claude Code applies the [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter field in SDK sessions. You can also pre-appr
Before TypeScript Agent SDK 0.3.221, the SDK didn't run this check.
+6 −2 lines
Recorded here 24 Aug 2026 18:37 UTC
claude-docs
third-party/claude-desktop/web-tools
±changed
+18−16
claude-docschanged
third-party/claude-desktop/web-tools
| Provider | Web Search
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------
| Google Cloud's Agent Platform | Available
| Microsoft Foundry | Available
| Amazon Bedrock | Not available natively; use the [built-in web search](#built-in-web-search) below
+18 −16 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+8−4
claude-docschanged
third-party/claude-desktop/telemetry
When Claude Desktop on third-party (3P) is configured with Google Cloud's Agent Platform, Amazon Bedrock, or Microsoft Foundry, the app sends conversation content only to your conf
This page covers what each category contains, how to turn it off, and the complete set of outbound hostnames the app uses so you can configure your perimeter firewall.
When Claude Desktop on third-party (3P) is configured with Google Cloud's Agent Platform, Amazon Bedrock, or Microsoft Foundry, the app sends conversation content only to your conf
+8 −4 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/overview
±changed
+20−6
claude-docschanged
third-party/claude-desktop/overview
Claude Desktop on 3P is designed for organizations whose security, regulatory, or contractual requirements prevent them from sending data to Anthropic's first-party infrastructure.
Claude Desktop on 3P is designed for organizations whose security, regulatory, or contractual requirements prevent them from sending data through Anthropic's first-party products (
How far a deployment is separated from Anthropic depends on the provider you choose. On Google Cloud's Agent Platform and Amazon Bedrock, the cloud provider processes conversation
* **Conversation content goes only to your configured endpoint.** Prompts, responses, files, and tool outputs are sent only to your configured inference endpoint and stored only on
+20 −6 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/legal
±changed
+10−2
claude-docschanged
third-party/claude-desktop/legal
When using Google Cloud's Agent Platform or Amazon Bedrock, conversation content is sent only to your configured inference endpoint and stored on the local device; data handling is
When using Google Cloud's Agent Platform or Amazon Bedrock, the app sends conversation content only to your configured inference endpoint and stores it on the local device. Data ha
When using Microsoft Foundry, the app also sends conversation content only to your configured inference endpoint and stores it on the local device.
+10 −2 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+1−1
claude-docschanged
third-party/claude-desktop/gateway
```yaml theme={null} theme={null} theme={null} theme={null} theme={null}
```yaml theme={null}
+1 −1 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/foundry
±changed
+3−1
claude-docschanged
third-party/claude-desktop/foundry
Claude models in Microsoft Foundry are available in two hosting options, Hosted on Azure and Hosted on Anthropic. Anthropic acts as an independent processor for Microsoft, and cu
Microsoft Foundry offers Claude models in two hosting options, Hosted on Azure and Hosted on Anthropic, and you choose one when you configure the model deployment in Microsoft Fo
Deployments hosted on Azure run inference in an Anthropic-operated service on Azure infrastructure, not in your Azure tenant, and prompts and completions remain within Azure. The
+3 −1 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/feature-matrix
±changed
+2−2
claude-docschanged
third-party/claude-desktop/feature-matrix
**Inference.** Claude Desktop on 3P routes all inference through the provider you configure. For Google Cloud's Agent Platform and Amazon Bedrock, data handling is governed by Goog
**Inference.** Claude Desktop on 3P routes all inference through the provider you configure, and data handling at the inference endpoint depends on that provider. For Google Cloud'
§ Amazon Bedrock deployments (and gateways that do not forward Anthropic server tools) need a web search provider configured first; see [Web search options](/docs/third-party/claud
§ Amazon Bedrock deployments, Microsoft Foundry deployments [hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options), an
+2 −2 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+7−7
claude-docschanged
third-party/claude-desktop/configuration
```yaml theme={null} theme={null}
```yaml theme={null}
```json theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null}
+7 −7 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/claude-api
±changed
+1−1
claude-docschanged
third-party/claude-desktop/claude-api
To use Anthropic's Claude API directly as the inference provider, set [`inferenceProvider`](/docs/third-party/claude-desktop/configuration#inferenceprovider) to `anthropic` and sup
To use Anthropic's Claude API directly as the inference provider, set [`inferenceProvider`](/docs/third-party/claude-desktop/configuration#inferenceprovider) to `anthropic` and sup
+1 −1 lines
Recorded here 24 Aug 2026 17:37 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+16−14
claude-docschanged
third-party/claude-desktop/connectors-m365
If the broker rejects the app's sign-in request, or a brokered attempt fails with an error the broker cannot recover from, the connector falls back to the system browser automa
If a brokered attempt fails with an error the broker cannot recover from, the connector falls back to the system browser automatically and stays on the browser flow until Claud
A missing broker redirect URI does not trigger the fallback on Windows. The broker shows Entra error `AADSTS50011` in its own sign-in dialog, and closing that dialog counts as
| Symptom | Cause
+16 −14 lines
Recorded here 24 Aug 2026 16:37 UTC
claude-docs
government/tenant-admin/organizations
±changed
+4−3
claude-docschanged
government/tenant-admin/organizations
Each organization appears with its name and ID. Clicking an organization's name opens its organization admin view. When you do this you are acting as an administrator of that organ
Each organization appears with its name and ID. Clicking an organization's name opens its organization admin view. When you do this you are acting as an Owner of that organization
* **Primary owner email** is the email address of the person who will be the new organization's first administrator. This person becomes the Primary Owner and can immediately manag
* **Primary Owner email** is the email address of the person who will be the new organization's first administrator. This person becomes the Primary Owner and can immediately manag
> **For organization owners:** Being named the primary owner of a new organization does **not** make you a tenant administrator. Tenant admin access is granted separately on the [A
+4 −3 lines
Recorded here 24 Aug 2026 11:37 UTC
claude-docs
government/org-admin/users
±changed
+3−1
claude-docschanged
government/org-admin/users
An organization must always have at least one active Primary Owner and may have up to three. Keeping more than one is recommended so that you are never locked out if a single Prima
An organization must always have at least one active Primary Owner and may have up to three. Keep at least two so that when one leaves your agency or loses account access, a remain
If your organization no longer has a Primary Owner who can sign in, contact Anthropic to have a new one appointed. A tenant administrator cannot grant the role for you, because ope
+3 −1 lines
Recorded here 24 Aug 2026 11:37 UTC
claude-docs
government/config/settings
±changed
+13−1
claude-docschanged
government/config/settings
> Reference for the product settings on the Config page in Claude for Government, including session timeout, maximum session length, telemetry, automatic updates, Claude Desktop ba
> Reference for the product settings on the Config page in Claude for Government, including session timeout, maximum session length, organization instructions, telemetry, automatic
</Note>
### Organization instructions
+13 −1 lines
Recorded here 24 Aug 2026 11:37 UTC
claude-docs
government/config/plugins-and-connectors
±changed
+1−1
claude-docschanged
government/config/plugins-and-connectors
Paths inside the zip must use forward slashes: File Explorer's **Compress to ZIP file**, 7-Zip, `tar.exe`, PowerShell 7, and Python's `zipfile` all write them, while Windows PowerS
Paths inside the zip must use forward slashes: File Explorer's **Compress to ZIP file**, 7-Zip, `tar.exe`, PowerShell 7, and Python's `zipfile` all write them, while Windows PowerS
+1 −1 lines
Recorded here 24 Aug 2026 11:37 UTC
claude-docs
government/org-admin/users
±changed
+6−6
claude-docschanged
government/org-admin/users
| Field | Description
| -------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------------------
| **Role** | The user's role in this organization. You can change it directly from the dropdown.
| **Seat tier** | Which seat tier the user currently occupies. You can change it directly from the dropdown.
| **Usage** | Two bars showing how much of the user's 5-hour and 7-day spend limits are currently used, with the exact percentage alongside each. Hover over the bars to see wh
+6 −6 lines
Upstream edited 24 Aug 2026 11:26 UTC Recorded here 28 Sep 2026 22:07 UTC
23 Aug 2026
2 pages
+6 −2 lines
mcp
docs/2026-07-28/getting-started/intro
±changed
+2−2
mcpchanged
docs/2026-07-28/getting-started/intro
* **AI applications or agents**: MCP provides access to an ecosystem of data sources, tools and apps which will enhance capabilities and improve the end-user experience.
* **End-users**: MCP results in more capable AI applications or agents which can access your data and take actions on your behalf when necessary.
* **AI applications or agents**: MCP gives them access to an ecosystem of data sources, tools and apps, which enhances their capabilities and improves the end-user experience.
* **End-users**: MCP results in more capable AI applications or agents that can access user data and take actions on the user's behalf when necessary.
+2 −2 lines
Recorded here 23 Aug 2026 08:37 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.241" description="August 23, 2026">
* Bug fixes and reliability improvements
</Update>
+4 −0 lines
Recorded here 23 Aug 2026 01:07 UTC
22 Aug 2026
85 pages
+982 −576 lines
claude-code
plugins-reference
±changed
+1−1
claude-codechanged
plugins-reference
When more than one source sets the same key, managed settings take precedence, then `--settings`, then user settings. The [`--setting-sources`](/docs/en/cli-reference#cli-flags) fl
When more than one source sets the same key, managed settings take precedence, then `--settings`, then user settings. The only source you can remove from this list is user settings
+1 −1 lines
Recorded here 22 Aug 2026 19:07 UTC
claude-docs
claude-tag/users/when-claude-responds
±changed
+1−1
claude-docschanged
claude-tag/users/when-claude-responds
When you @-mention Claude in a channel, it reacts to your message with an emoji within a few seconds to show that it picked the message up. It then answers in a thread under your m
When you @-mention Claude in a channel, it reacts to your message with an emoji within a few seconds to show that it picked the message up. The message goes to the channel's own [s
+1 −1 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+5−3
claude-docschanged
claude-tag/concepts/how-it-works
When someone tags Claude in with a task, a working session starts for that thread. Claude works through the task and posts the result back into the conversation. It runs in an ephe
When someone tags Claude in at a channel's top level, the channel's own [session](/docs/claude-tag/concepts/glossary#session) picks the message up. A task that needs investigation,
1. **The session starts.** Someone tags `@Claude` with a task, or a [scheduled routine](/docs/claude-tag/users/proactivity) runs.
1. **The session starts.** Someone tags `@Claude` with a task that needs a working session, or a [scheduled routine](/docs/claude-tag/users/proactivity) runs. At a channel's top le
+5 −3 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+1−1
claude-docschanged
claude-tag/concepts/agent-identity
A user asks Claude to chart last week's signups or fix a deploy test. The request starts a new session.
A user asks Claude to chart last week's signups or fix a deploy test. The task gets a session in a thread under the message.
+1 −1 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+1−0
claude-docschanged
claude-tag/admins/setup-overview
* [Claude Tag in production at Anthropic](https://claude.com/blog/ai-ci-cd-on-call): how Anthropic runs Claude Tag as its first responder for CI/CD failures
+1 −0 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
whats-new/index
±changed
+16−0
claude-codechanged
whats-new/index
<Update label="Week 34" description="August 17–21, 2026" tags={["v2.1.234–v2.1.239"]}>
**`/design`**: a research preview that brings Claude Design's artboard workflow into the CLI and Claude Code Desktop, built on artifacts, so Claude drafts editable artboards for
Also this week: the built-in **Concise output style** makes Claude lead with the result and skip preamble; any machine running `claude remote-control` shows up as a **device card
+16 −0 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
whats-new/2026-w34
+new page
+101−0
claude-codenew page
whats-new/2026-w34
No line of the body moved in this read.
+101 −0 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
whats-new/2026-w33
+new page
+83−0
claude-codenew page
whats-new/2026-w33
No line of the body moved in this read.
+83 −0 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
claude-apps-gateway
±changed
+26−22
claude-codechanged
claude-apps-gateway
<img src="https://mintcdn.com/claude-code/st9_ZQOFsZa3cKFl/images/claude-gateway-architecture.svg?fit=max&auto=format&n=st9_ZQOFsZa3cKFl&q=85&s=560770d8f49bbd6f1ca7090ed1f13c03"
<img src="https://mintcdn.com/claude-code/VbyXug8hBU9UK6oT/images/claude-gateway-architecture.svg?fit=max&auto=format&n=VbyXug8hBU9UK6oT&q=85&s=9e4f1190fc56718144190a3db61c63af"
Claude Desktop runs embedded Claude Code sessions and passes policy to each one it launches. It builds that policy from the configuration the gateway serves it at `/user/bootstrap`
Claude Desktop runs its Cowork and Code tabs, plus the Chat tab when you enable it, on embedded Claude Code sessions and sends their model requests through the gateway. It passes p
+26 −22 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.240" description="August 22, 2026">
* Bug fixes and reliability improvements
</Update>
+4 −0 lines
Recorded here 22 Aug 2026 18:37 UTC
claude-docs
claude-tag/users/proactivity
±changed
+4−2
claude-docschanged
claude-tag/users/proactivity
Claude can subscribe to a single pull request and react when it updates.
Claude can subscribe to a single pull request and react when it updates. A subscription is the one way Claude reacts to GitHub events; it wakes on activity on that pull request, su
Standing work is visible to the channel: jobs post into the channel they belong to. Routines keep running if their creator leaves the organization, but stop firing if the creator i
Standing work is visible to the channel: jobs post into the channel they belong to, or into another public channel you name that Claude has been added to. Routines keep running if
* Claude can post a job's output into another public channel in the same workspace only if the job's own channel is public and Claude has been added to the target channel. It label
+4 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-docs
claude-tag/concepts/for-claude-code-users
±changed
+11−0
claude-docschanged
claude-tag/concepts/for-claude-code-users
## Claude Tag versus a bot you build on the API
A Slack bot you build on the Claude API is software your team writes and hosts. It calls the API with your key, holds its own Slack tokens, and has the tools and memory you code in
Claude Tag is Anthropic's hosted Slack app. It takes care of the parts you would otherwise build.
+11 −0 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+19−5
claude-docschanged
claude-tag/admins/troubleshooting
**Allow Claude to respond to guests** is set to **Restrict** or **Channel only** for this channel's [scope](/docs/claude-tag/concepts/glossary#scope), so Claude checks the channel
**Allow Claude to work in channels with guests** is set to **Restrict** or **Channel only** for this channel's [scope](/docs/claude-tag/concepts/glossary#scope), so Claude checks t
The channel includes at least one Slack guest account, and **Allow Claude to respond to guests** is set to **Restrict** for this channel's scope. **Restrict** is the default.
The channel includes at least one Slack guest account, and **Allow Claude to work in channels with guests** is set to **Restrict** for this channel's scope. **Restrict** is the def
* Or change **Allow Claude to respond to guests** for the scope covering this channel; changing it needs an organization owner. **Channel only** restores replies while keeping Clau
+19 −5 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-docs
claude-tag/admins/setup-overview
±changed
+2−0
claude-docschanged
claude-tag/admins/setup-overview
You can use any address. The setup flow shows `claude@` followed by your own domain only as an example; Claude Tag never asks for the address and keeps only the credential you ente
+2 −0 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+2−2
claude-docschanged
claude-tag/admins/restrict-access
* **Guest channels.** By default Claude is off in any channel that includes a Slack guest. If a chosen channel has guests, also set [Allow Claude to respond to guests](#restrict-gu
* **Guest channels.** By default Claude is off in any channel that includes a Slack guest. If a chosen channel has guests, also set [Allow Claude to work in channels with guests](#
By default, Claude is disabled in any channel that includes a Slack guest. The **Allow Claude to respond to guests** setting changes that per scope. It's at [`claude.ai/admin-setti
By default, Claude is disabled in any channel that includes a Slack guest. The **Allow Claude to work in channels with guests** setting changes that per scope. It's at [`claude.ai/
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
whats-new/2026-w32
±changed
+2−2
claude-codechanged
whats-new/2026-w32
<p className="digest-feature-lede">Self-hosted environments run Claude Code cloud sessions on your organization's own infrastructure, in public beta on Team and Enterprise plans.
<p className="digest-feature-lede">Self-hosted environments run Claude Code cloud sessions on your organization's own infrastructure, in public beta on Team and Enterprise plans.
<p className="digest-feature-try">Signed in as an Owner or admin, run the guided setup, which walks you through creating the environment and starts a runner:</p>
<p className="digest-feature-try">Signed in as an Owner, run the guided setup, which walks you through creating the environment and starts a runner:</p>
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
slack
±changed
+2−2
claude-codechanged
slack
If you're an Owner or admin, recreate the environment as an [organization-shared environment](/docs/en/cloud-environments#organization-shared-environments) from the **Cloud environ
If you're an Owner, recreate the environment as an [organization-shared environment](/docs/en/cloud-environments#organization-shared-environments) from the **Cloud environments** p
If you're not an Owner or admin, send this entry to one.
If you're not an Owner, send this entry to one.
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-testing
±changed
+4−4
claude-codechanged
self-hosted-environments-testing
`$ADMIN_TOKEN` is a claude.ai OAuth access token for an account that holds an Owner or admin role, minted the same way as [Authenticate from CI](#authenticate-from-ci):
* **Mint it**: run `claude auth login` with an account that holds an Owner or admin role, then read the current access token from the OS keychain on macOS or `~/.claude/.credential
`$ADMIN_TOKEN` is a claude.ai OAuth access token for an account that holds an Owner role, minted the same way as [Authenticate from CI](#authenticate-from-ci):
+4 −4 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-reference
±changed
+2−2
claude-codechanged
self-hosted-environments-reference
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner or admin](/docs/en/cloud-environments#organization-shared-environments) enables them by turnin
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner](/docs/en/cloud-environments#organization-shared-environments) enables them by turning on **Al
| `claude_code_self_hosted_orchestrator_queue_circuit_broken_sessions` | Spawn requests blocked until an Owner or admin retries them from the environment's **Act
| `claude_code_self_hosted_orchestrator_queue_circuit_broken_sessions` | Spawn requests blocked until an Owner retries them from the environment's **Activity** t
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-quickstart
±changed
+2−2
claude-codechanged
self-hosted-environments-quickstart
* **Allow self-hosted environments** turned on by an [Owner or admin](/docs/en/cloud-environments#organization-shared-environments) on the [**Cloud environments** admin page](https
* **Allow self-hosted environments** turned on by an [Owner](/docs/en/cloud-environments#organization-shared-environments) on the [**Cloud environments** admin page](https://claude
Claude Code includes a guided setup: an interactive Claude Code session that walks you through creating the environment in the admin UI, starts a local runner with the secret file
Claude Code includes a guided setup: an interactive Claude Code session that walks you through creating the environment in the admin UI, starts a local runner with the secret file
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-identity
±changed
+1−1
claude-codechanged
self-hosted-environments-identity
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner or admin](/docs/en/cloud-environments#organization-shared-environments) enables them by turnin
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner](/docs/en/cloud-environments#organization-shared-environments) enables them by turning on **Al
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+1−1
claude-codechanged
self-hosted-environments-deploy
* **Dispatch is organization-wide**: any member of your Anthropic organization can dispatch a session to any of its environments, and there's no per-environment access control on d
* **Dispatch is organization-wide**: any member of your Anthropic organization can dispatch a session to any of its environments, and there's no per-environment access control on d
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+3−3
claude-codechanged
self-hosted-environments-configuration
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner or admin](/docs/en/cloud-environments#organization-shared-environments) enables them by turnin
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner](/docs/en/cloud-environments#organization-shared-environments) enables them by turning on **Al
3. **Use the exit-code contract.** Exit 0 means submitted. Exit 1 means retryable failure; the session backs off and is re-offered. Exit 2 or higher means non-retryable; the sessio
3. **Use the exit-code contract.** Exit 0 means submitted. Exit 1 means retryable failure; the session backs off and is re-offered. Exit 2 or higher means non-retryable; the sessio
Repository-committed `.claude/settings.json` layers on top as project settings. Sessions also read [`managed-settings.json`](/docs/en/settings#where-settings-live) from the standar
+3 −3 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
self-hosted-environments
±changed
+1−1
claude-codechanged
self-hosted-environments
* **Plans**: public beta for Team and Enterprise organizations. Self-hosted environments are off by default; an [Owner or admin](/docs/en/cloud-environments#organization-shared-env
* **Plans**: public beta for Team and Enterprise organizations. Self-hosted environments are off by default; an [Owner](/docs/en/cloud-environments#organization-shared-environments
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
remote-control
±changed
+2−2
claude-codechanged
remote-control
Trusted Devices is available on Team and Enterprise plans. It is off by default until an admin enables it.
Trusted Devices is available on Team and Enterprise plans. It is off by default until an Owner enables it.
Admins enable the setting from the Claude Code admin console.
An Owner enables the setting from the Claude Code admin console.
+2 −2 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* Cloud sessions, on [Claude Code on the web](/docs/en/claude-code-on-the-web) or in the Desktop app, run on Anthropic-managed VMs by default: settings deployed to your device do n
* Cloud sessions, on [Claude Code on the web](/docs/en/claude-code-on-the-web) or in the Desktop app, run on Anthropic-managed VMs by default: settings deployed to your device do n
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
* **Cloud sessions**: a session in an Anthropic-hosted environment doesn't read a device's MDM profile or file, so policy for it has to come from server-managed settings. A session
* **Cloud sessions**: a session in an Anthropic-hosted environment doesn't read a device's MDM profile or file, so policy for it has to come from server-managed settings. A session
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
* **[Cloud sessions](#cloud-sessions)**: receive [server-managed settings](/docs/en/server-managed-settings); device-deployed files don't reach them, because they run on Anthropic-
* **[Cloud sessions](#cloud-sessions)**: receive [server-managed settings](/docs/en/server-managed-settings); device-deployed files don't reach them, because they run on Anthropic-
+1 −1 lines
Recorded here 22 Aug 2026 17:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.