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
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
7 Oct 2026
209 pages
+3198 −2398 lines
api
manage-claude/inference-hooks
±changed
+2−2
apichanged
manage-claude/inference-hooks
Governed requests are the inference requests behind the user's conversation. Ancillary requests aren't sent to your endpoint. These include conversation title generation and a meas
Governed requests are the inference requests behind the user's conversation. Ancillary requests aren't sent to your endpoint. These include conversation title generation and a meas
With **Validate tool calls** on, `tool_call` events may leave out calls to some of claude.ai's own tools, such as tools that suggest connectors or skills, give Claude the user's lo
With **Validate tool calls** on, `tool_call` events may leave out calls to some of claude.ai's own tools, such as tools that list, search for, or suggest connectors, plugins, or sk
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/cmek-google-cloud-kms
±changed
+34−34
apichanged
manage-claude/cmek-google-cloud-kms
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
ant beta:organization:external-keys create <<'YAML'
ant organization:external-keys create <<'YAML'
external_key = client.beta.organization.external_keys.create(
+34 −34 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/cmek-azure-key-vault
±changed
+36−36
apichanged
manage-claude/cmek-azure-key-vault
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
ant beta:organization:external-keys create <<'YAML'
ant organization:external-keys create <<'YAML'
external_key = client.beta.organization.external_keys.create(
+36 −36 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/cmek-aws-kms
±changed
+38−38
apichanged
manage-claude/cmek-aws-kms
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
**Finding your organization ID:** Copy the **Organization ID** field under **Settings > Organization** in the Claude Console, or under **Organization settings > Organization*
**Finding your compartment ID:** Each workspace has a compartment ID that scopes its CMEK data. To find it in the Claude Console, go to [Manage > Security](https://platform.c
**Finding your compartment ID:** Each workspace has a compartment ID that scopes its CMEK data. To find it in the Claude Console, go to [Manage > Security](https://platform.c
ant beta:organization:external-keys create <<'YAML'
+38 −38 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/admin-api
±changed
+170−179
apichanged
manage-claude/admin-api
The [Admin API](https://platform.claude.com/docs/en/api/beta/organization) lets you manage your organization's members, workspaces, invites, and API keys programmatically instead o
The [Admin API](https://platform.claude.com/docs/en/api/organization) lets you manage your organization's members, workspaces, invites, and API keys programmatically instead of by
The Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs expose the Admin API under `client.beta.organization`, and the `ant` CLI under `ant beta:organization`. The examples on thi
The Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs expose the endpoints on this page under `client.organization` (csharp, go: `client.Organization`; java: `client.organizatio
ant beta:organization retrieve
+170 −179 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/working-with-messages
±changed
+1−1
apichanged
build-with-claude/working-with-messages
On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, Cla
On Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/mode
+1 −1 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/prompt-caching
±changed
+4−4
apichanged
build-with-claude/prompt-caching
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok | $20
| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok | $20
* 512 tokens for Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Fable 5, and [Claude Mythos 5](https://anthropic.com/glasswing)
+4 −4 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+1−1
apichanged
build-with-claude/mid-conversation-system-messages
This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Op
This feature is available on Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://plat
+1 −1 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+2−2
apichanged
build-with-claude/claude-on-vertex-ai
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` |
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | `claude-mythos-5-1` |
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5` |
| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | `claude-mythos-5` |
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+2−2
apichanged
build-with-claude/claude-in-microsoft-foundry
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` | | ✓ |
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | `claude-mythos-5-1` | | ✓ |
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5` | | ✓ |
| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | `claude-mythos-5` | | ✓ |
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+14−14
apichanged
build-with-claude/claude-in-amazon-bedrock
| Model | Model ID | Access
| :------------------------------------------------------------------------------ | :-------------------------------- | :-----------------------------------------------------------
| Claude Fable 5.1 | `anthropic.claude-fable-5-1` | Open
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `anthropic.claude-mythos-5-1` | Invitation only
| Claude Fable 5 | `anthropic.claude-fable-5` | Open
+14 −14 lines
Recorded here 7 Oct 2026 04:37 UTC
api
build-with-claude/batch-processing
±changed
+3−3
apichanged
build-with-claude/batch-processing
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | $5 / MTok | $25 / MTok |
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $5 / MTok | $25 / MTok |
| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $5 / MTok | $25 / MTok |
* **Limited access:** Offered separately, by invitation only, as part of [Project Glasswing](https://anthropic.com/glasswing). For access, contact your Anthropic, AWS, or Google Cl
+3 −3 lines
Recorded here 7 Oct 2026 04:37 UTC
api
api/errors
±changed
+2−2
apichanged
api/errors
On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, and [Claude Mythos P
On Claude Fable 5.1, [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), Claude Fable 5, [Claude Mythos 5](https://platform.claude.com/docs/en/mode
Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://anthropic.com/glasswing) don't support forced tool use. Sending `tool_choice: {"type": "any"}`
Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) don't support forced tool use. Sending
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+4−4
apichanged
agents-and-tools/tool-use/define-tools
| Model or setting | Restriction
| ----------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------
| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and resul
| Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://anthropic.com/glasswing) | `any` and `tool` return a [400 error](https:
| Model or setting | Restriction
+4 −4 lines
Recorded here 7 Oct 2026 04:37 UTC
api
about-claude/pricing
±changed
+6−6
apichanged
about-claude/pricing
| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok |
| Claude Mythos 5.1 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok |
| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | $10 / MTok | $12.50 / MTok |
| Claude Mythos 5 ([limited availability](https://support.claude.com/en/articles/14604842)) | $10 / MTok | $12.50 / MTok |
* **Limited access:** Offered separately, by invitation only, as part of [Project Glasswing](https://anthropic.com/glasswing). For access, contact your Anthropic, AWS, or Google Cl
+6 −6 lines
Recorded here 7 Oct 2026 04:37 UTC
api
about-claude/models/choosing-a-model
±changed
+1−1
apichanged
about-claude/models/choosing-a-model
**Claude Fable 5.1** (`claude-fable-5-1`) is Anthropic's most capable model open to all customers. It extends Claude Fable 5 with stronger long-running agentic coding, knowledge wo
**Claude Fable 5.1** (`claude-fable-5-1`) is Anthropic's most capable model open to all customers. It extends Claude Fable 5 with stronger long-running agentic coding, knowledge wo
+1 −1 lines
Recorded here 7 Oct 2026 04:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
claude-code
plugins/mods/reference
±changed
+1−1
claude-codechanged
plugins/mods/reference
* **Height of a `Pane` beside the transcript**: where `e.props.placement` is `'dock'`, `e.props.scroll.bodyRows` is the number of rows the pane has
* **Height of a `Pane` beside the transcript**: where `e.props.placement` is `'dock'`, `e.props.scroll.bodyRows` is the number of rows the pane has for your tree
+1 −1 lines
Upstream edited 7 Oct 2026 04:28 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
plugins/mods/interface
±changed
+4−2
claude-codechanged
plugins/mods/interface
╭──────────────────────────────────────────────────────────╮
│ Note: Type a note and press Enter ⏎ add ✕ │
╭────────────────────────────────────────────────────────✕─╮
│ Note: Type a note and press Enter ⏎ add │
+4 −2 lines
Upstream edited 7 Oct 2026 04:28 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
errors
±changed
+1−0
claude-codechanged
errors
| `Cloud sessions need a claude.ai sign-in` | [Unable to get organization UUID](/docs/en/claude-code-on-the-web#unable-to-get-organization-uuid) |
+1 −0 lines
Upstream edited 7 Oct 2026 04:26 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
claude-code-on-the-web
±changed
+4−2
claude-codechanged
claude-code-on-the-web
* A message that API key authentication is not sufficient
* ``Cloud sessions need a claude.ai sign-in. Run `claude auth login` (or /login in a local session), then try again.``
Run `/login` to sign in with your claude.ai account, then retry the command. If the error names your provider instead, see the [error table](#errors-when-sending-to-a-cloud-session
Run [`claude auth login`](/docs/en/cli-reference#cli-commands) in your shell to sign in with your claude.ai account, then retry the command. Inside a running session, `/login` does
+4 −2 lines
Upstream edited 7 Oct 2026 04:26 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
| `name` | Yes | Unique identifier, such as `code-reviewer` or `reviewer-v2`. [Hooks](/docs/en/hooks#subagentstart) receive this value as `agent_type`. The filename doesn't have to
| `name` | Yes | Unique identifier of at most 256 characters, such as `code-reviewer` or `reviewer-v2`. [Hooks](/docs/en/hooks#subagentstart) receive this value as `agent_type`. Th
* **A `name` that starts with `-` or contains `:`**: Claude Code skips the file and writes an error to the debug log. See the `name` row in the table above.
* **A `name` that starts with `-`, contains `:`, or is longer than 256 characters**: Claude Code skips the file and writes an error to the debug log.
+2 −2 lines
Upstream edited 7 Oct 2026 04:25 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
plugins/components
±changed
+1−1
claude-codechanged
plugins/components
This agent is named `my-plugin:security-reviewer`, and the user can [invoke it explicitly](/docs/en/sub-agents#invoke-subagents-explicitly) with `@agent-my-plugin:security-reviewer
This agent is named `my-plugin:security-reviewer`, and the user can [invoke it explicitly](/docs/en/sub-agents#invoke-subagents-explicitly) with `@agent-my-plugin:security-reviewer
+1 −1 lines
Upstream edited 7 Oct 2026 04:25 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
agent-view
±changed
+1−0
claude-codechanged
agent-view
| `claude daemon logs` | Follow the supervisor's log file, [`~/.claude/daemon.log`](#where-state-is-stored), printing new lines as they arrive until you press `Ctrl+C` |
+1 −0 lines
Upstream edited 7 Oct 2026 04:09 UTC Recorded here 7 Oct 2026 04:37 UTC
claude-code
plugins/troubleshooting
±changed
+1−0
claude-codechanged
plugins/troubleshooting
* **A `hooks module not loaded` or `hooks module did not load` message**: the plugin is a [mod](/docs/en/plugins/mods/overview), so read [The mod doesn't load](/docs/en/plugins/m
+1 −0 lines
Upstream edited 7 Oct 2026 04:09 UTC Recorded here 7 Oct 2026 04:37 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 7 Oct 2026 04:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `suppressAlwaysAllowRule` | `boolean` | When `true`, don't offer a persistent always-allow choice for this request, because the rule it would write grants more than the request's
| `suppressAlwaysAllowRule` | `boolean` | When `true`, don't offer a persistent always-allow choice for this request. Requires Agent SDK v0.3.268 or later |
+1 −1 lines
Upstream edited 7 Oct 2026 04:04 UTC Recorded here 7 Oct 2026 04:07 UTC
claude-code
desktop-ios-simulator
±changed
+1−1
claude-codechanged
desktop-ios-simulator
To tune the video stream from the simulator, open the pane's **Display** menu. Lower **Frame rate** or **Resolution** if the pane strains your Mac. Both settings change how the pan
If the pane shows a **Display** menu, use it to tune the video stream from the simulator. Lower **Frame rate** or **Resolution** if the pane strains your Mac. Both settings change
+1 −1 lines
Upstream edited 7 Oct 2026 04:03 UTC Recorded here 7 Oct 2026 04:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 01:07 UTC
claude-code
sessions
±changed
+3−3
claude-codechanged
sessions
* Session picker at launch: a session you select from the [session picker](#use-the-session-picker), whether you opened it with `claude --resume` alone, `claude --from-pr`, or a na
* `/resume` inside a session, with or without an argument: Claude Code doesn't restore the stored permission mode. The conversation you switch to continues in the permission mode y
* Session picker at launch: a session you select from the [session picker](#use-the-session-picker), whether you opened it with `claude --resume` alone, `claude --from-pr`, or a na
* `/resume` inside a session, with or without an argument: the conversation you switch to continues in the permission mode your current session is in, except that a conversation th
| `plan` | Terminal | The permission mode a new session would start in |
+3 −3 lines
Upstream edited 7 Oct 2026 01:02 UTC Recorded here 7 Oct 2026 01:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+1−1
claude-codechanged
claude-apps-gateway-on-aws
The instance runs in the private subnets with no public address and storage encryption on. The engine version is pinned to Postgres 16, which satisfies the gateway's supported
The instance runs Postgres 16 in the private subnets, with no public address and storage encryption on.
+1 −1 lines
Upstream edited 7 Oct 2026 00:29 UTC Recorded here 7 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-deploy
±changed
+7−1
claude-codechanged
claude-apps-gateway-deploy
The gateway stores its state in a PostgreSQL database:
* **Database**: PostgreSQL itself, self-hosted or managed, at the [minimum version](/docs/en/claude-apps-gateway#prerequisites) or later. Databases that only implement the Postgres
* **Address**: `store.postgres_url` takes one host. If the database has several nodes, use the address in front of them, such as your managed service's endpoint, a load balancer, o
+7 −1 lines
Upstream edited 7 Oct 2026 00:29 UTC Recorded here 7 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-config
±changed
+3−3
claude-codechanged
claude-apps-gateway-config
2. Replace the key and certificate files that `gateway.yaml` loads, then restart the gateway.
3. Remove the old certificate from the IdP.
2. Replace the key and certificate files that `gateway.yaml` loads, then restart the gateway. If you run several replicas, a [rolling restart](/docs/en/claude-apps-gateway-deploy#u
3. After every replica has restarted, remove the old certificate from the IdP.
| `postgres_url` | Yes | `postgres://` or `postgresql://` URL. Required: the device-grant rendezvous, where the browser callback writes and the polling CLI reads, needs cross-repli
+3 −3 lines
Upstream edited 7 Oct 2026 00:29 UTC Recorded here 7 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway
±changed
+2−2
claude-codechanged
claude-apps-gateway
| PostgreSQL 14 or later | Backs the device sign-in flow, where the browser callback writes and the polling CLI reads, plus rate-limit counters. Any managed Postgres works, includi
| PostgreSQL 11 or later | Backs the device sign-in flow and rate-limit counters. A managed PostgreSQL service works, including the smallest tier; see [which databases are supporte
Any Postgres 14 or later works, including the smallest managed tier. The gateway runs its own schema migrations at boot, so the database role needs rights to create and alter t
Use PostgreSQL 11 or later. The smallest managed tier is enough. The gateway runs its own schema migrations at boot, so the database role needs rights to create and alter table
+2 −2 lines
Upstream edited 7 Oct 2026 00:29 UTC Recorded here 7 Oct 2026 00:37 UTC
6 Oct 2026
118 pages
+2901 −2116 lines
claude-docs
third-party/claude-desktop/gateway
±changed
+31−0
claude-docschanged
third-party/claude-desktop/gateway
Users with no saved selection start on the standard entry. To start them on the **1M context window** entry of the default (first) model instead, add `prefer1m: true` next to `supp
### Context window and compaction
Cowork and Code sessions keep a long conversation within the model's context window by compacting it. To compact, the session sends one request that asks the model to summarize the
+31 −0 lines
Upstream edited 6 Oct 2026 23:06 UTC Recorded here 6 Oct 2026 23:07 UTC
api
release-notes/overview
±changed
+5−1
apichanged
release-notes/overview
### October 5, 2026
* We've added `capabilities.thinking.types.disabled` to the [Models API](https://platform.claude.com/docs/en/api/models/list). `GET /v1/models` and `GET /v1/models/{model_id}` now
* You can now restrict which sites a Claude Managed Agents agent's `web_search` and `web_fetch` tools can reach. Set `allowed_domains` or `blocked_domains` on the tool's entry in t
+5 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
models/overview
±changed
+2−0
apichanged
models/overview
Each model's `capabilities` object includes `thinking.types.disabled`, which reports whether the model accepts `thinking: {type: "disabled"}`, the setting that [turns thinking off]
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
models/fable-5-1/migration-guide
±changed
+1−1
apichanged
models/fable-5-1/migration-guide
3. **Use `fallbacks: "default"` for refusals:** Keep handling `stop_reason: "refusal"` and reading `stop_details.category` before response content. To re-run refused requests on an
3. **Use `fallbacks: "default"` for refusals:** Keep handling `stop_reason: "refusal"` and reading `stop_details.category` before response content. To re-run refused requests on an
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/tools-web-restrictions
+new page
+523−0
apinew page
managed-agents/tools-web-restrictions
No line of the body moved in this read.
+523 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/tools
±changed
+41−452
apichanged
managed-agents/tools
The agent toolset includes the following tools. All are enabled by default when you include the toolset in your agent configuration. Each entry in the `configs` array is identified
The agent toolset includes the following tools. All are enabled by default when you include the toolset in the agent configuration.
Enable the full toolset with `agent_toolset_20260401` when creating an agent. Use the `configs` array to disable specific tools or override their settings. Each config entry can al
Config entries for `web_search` and `web_fetch` also accept domain filters and other web settings; see [Restrict web search and web fetch domains](https://platform.claude.com/docs/
+41 −452 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/session-operations
±changed
+1−1
apichanged
managed-agents/session-operations
You can update a session's `agent.tools` and `agent.mcp_servers`, including permission policies and per-tool web settings such as [domain filters](https://platform.claude.com/docs/
You can update a session's `agent.tools` and `agent.mcp_servers`, including permission policies and per-tool web settings such as [domain filters](https://platform.claude.com/docs/
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/migration
±changed
+1−1
apichanged
managed-agents/migration
* **Web search and web fetch settings:** Same `allowed_domains`, `blocked_domains`, `max_content_tokens`, and `user_location` fields, now set once on the `web_search` and `web_fetc
* **Web search and web fetch settings:** Same `allowed_domains`, `blocked_domains`, `max_content_tokens`, and `user_location` fields, now set once on the `web_search` and `web_fetc
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/mcp-connector
±changed
+1−1
apichanged
managed-agents/mcp-connector
The `mcp_toolset` entry supports a `default_config` object and a `configs` array, applied to the tools the MCP server exposes. Each `configs` entry accepts only `name`, `enabled`,
The `mcp_toolset` entry supports a `default_config` object and a `configs` array, applied to the tools the MCP server exposes. Each `configs` entry accepts only `name`, `enabled`,
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
managed-agents/environments
±changed
+3−3
apichanged
managed-agents/environments
The `networking` field controls the sandbox's outbound network access. It does not affect the `web_search` or `web_fetch` tools, which run on Anthropic's servers; to restrict the s
The `networking` field controls the sandbox's outbound network access. It does not affect the `web_search` or `web_fetch` tools, which run on Anthropic's servers; to restrict the s
* `allowed_hosts` specifies domains the sandbox can reach. Specify bare hostnames or wildcard patterns (such as `*.example.com`). Do not include a URL scheme, port, or path.
* `allowed_hosts` specifies domains the sandbox can reach. Specify bare hostnames or wildcard patterns (such as `*.example.com`). Do not include a URL scheme, port, or path. A bare
An agent that only uses the `web_search` and `web_fetch` tools does not need `unrestricted` networking if you can list the sites it needs. [Networking](https://platform.claude.com/
+3 −3 lines
Recorded here 6 Oct 2026 22:07 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+1−1
apichanged
manage-claude/inference-hooks-endpoint
There are two hook events, told apart by the top-level `type` field. The prompt frame is sent once per governed inference request, before inference begins. The tool call frame is s
There are two hook events, told apart by the top-level `type` field. The prompt frame is sent once per governed inference request, before inference begins. The tool call frame is s
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
manage-claude/inference-hooks-configuration
±changed
+1−1
apichanged
manage-claude/inference-hooks-configuration
Turn on **Validate tool calls**, below **Enforce verdicts**, and confirm in the dialog, to also send the tool calls in each of Claude's responses to your AI security server and
**Validate tool calls**, below **Enforce verdicts**, also sends the tool calls in each of Claude's responses to your AI security server and waits for its verdict before they ru
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
manage-claude/inference-hooks
±changed
+3−5
apichanged
manage-claude/inference-hooks
There are two hook events. `prompt` fires once per governed inference request, before inference begins. `tool_call` fires when Claude's response contains tool calls, before any of
There are two hook events. `prompt` fires once per governed inference request, before inference begins. `tool_call` fires when Claude's response contains tool calls, before any of
The following diagram traces one example (a Cowork request where Claude also calls an O365 tool) to illustrate which parts of the flow are hooked. The hooked points are the diagram
The following diagram traces one example (a Cowork request where Claude also calls an O365 tool) to illustrate which parts of the flow are hooked. The hooked points are the diagram
+3 −5 lines
Recorded here 6 Oct 2026 22:07 UTC
api
manage-claude/compliance-sessions
±changed
+4−0
apichanged
manage-claude/compliance-sessions
On a very large session, the messages endpoint can return a 400 for a page, with a message saying that the page is too large to read; see [Transcript page too large](https://platfo
On a very large session, the messages endpoint might also return a 429 whose `error.details.error_code` is `transcript_read_server_busy`. It does not mean that your organization ex
+4 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
manage-claude/compliance-errors
±changed
+40−4
apichanged
manage-claude/compliance-errors
Match on the HTTP status code and `error.type`, not on the message string. Messages are stable enough to copy into runbooks but might be reworded over time; the status codes and ty
Match on the HTTP status code and `error.type`, not on the message string. Messages are stable enough to copy into runbooks but might be reworded over time; the status codes and ty
| [400 Bad Request](https://platform.claude.com/docs/en/manage-claude/compliance-errors#400-bad-request) | No | Fix the request, or ena
| [400 Bad Request](https://platform.claude.com/docs/en/manage-claude/compliance-errors#400-bad-request) | No | Fix the request, or ena
The request was syntactically valid, but the server rejected a parameter or the Compliance API is not enabled for the organization. Fix the cause named in the message and resend.
+40 −4 lines
Recorded here 6 Oct 2026 22:07 UTC
api
cli-sdks-libraries/middleware
±changed
+2−0
apichanged
cli-sdks-libraries/middleware
accTitle: How a request and its response pass through middleware
accDescr: Your code sends the request to Middleware A. Middleware A calls next(request) to pass it to Middleware B, and Middleware B calls next(request) to pass it to the SDK c
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
build-with-claude/thinking
±changed
+2−0
apichanged
build-with-claude/thinking
To check whether a model accepts `"disabled"` before you send a request, read its `capabilities.thinking.types.disabled.supported` value from the Models API. [Using the Models API]
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
build-with-claude/fallback-credit
±changed
+1−1
apichanged
build-with-claude/fallback-credit
Send the request that may be refused with the `anthropic-beta: fallback-credit-2026-07-01` header. The `server-side-fallback-2026-07-01` header also grants the same fields, and
Send the request that may be refused with the `anthropic-beta: fallback-credit-2026-07-01` header. The `server-side-fallback-2026-07-01` header also grants the same fields, exc
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+3−3
apichanged
agents-and-tools/tool-use/web-search-tool
These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) se
These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) se
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_search` entry of the agent toolset; see [Restrict web search a
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_search` entry of the agent toolset; see [Restrict web search a
On Claude Managed Agents, the `web_search` entry of the agent toolset accepts a `user_location` object with the same fields. The API rejects an unsupported `country` code with a 40
+3 −3 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/web-fetch-tool
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_fetch` entry of the agent toolset, where each listed domain mu
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_fetch` entry of the agent toolset, where each listed domain mu
On Claude Managed Agents, the `web_fetch` entry of the agent toolset also accepts `max_content_tokens`; see [Restrict web search and web fetch domains](https://platform.claude.com/
On Claude Managed Agents, the `web_fetch` entry of the agent toolset also accepts `max_content_tokens`; see the [web tool settings](https://platform.claude.com/docs/en/managed-agen
+2 −2 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/tool-runner
±changed
+2−0
apichanged
agents-and-tools/tool-use/tool-runner
accTitle: The tool runner loop
accDescr: In each iteration, the tool runner sends a request with the current state to the Messages API. It receives the response message and yields it to your code. Your loop bo
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+1−1
apichanged
agents-and-tools/tool-use/server-tools
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) uses the same `allowed_domains` and `blocked_domains` fields on the `web_search` and `web_fetch
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) uses the same `allowed_domains` and `blocked_domains` fields on the `web_search` and `web_fetch
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+1−1
apichanged
agents-and-tools/tool-use/define-tools
+1 −1 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+2−0
apichanged
agents-and-tools/tool-use/advisor-tool
accTitle: How the executor model consults the advisor model
accDescr: Your application sends a request with the advisor tool to the executor model, which begins the task. The executor emits a server_tool_use block, and Anthropic runs the
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
api
agents-and-tools/mcp-tunnels/concepts
±changed
+2−0
apichanged
agents-and-tools/mcp-tunnels/concepts
accTitle: How a request reaches an MCP server through a tunnel
accDescr: cloudflared, the proxy, and the upstream MCP server run inside your network. cloudflared opens an outbound connection on port 7844 to the tunnel edge on the Cloudflare
+2 −0 lines
Recorded here 6 Oct 2026 22:07 UTC
claude-docs
third-party/claude-desktop/code
±changed
+23−0
claude-docschanged
third-party/claude-desktop/code
## Claude Code mods
Code sessions support Claude Code [mods](https://code.claude.com/docs/en/plugins/mods/overview), code that a plugin runs inside Claude Code, and users can load their own. To stop u
```json managed-settings.json theme={null}
+23 −0 lines
Upstream edited 6 Oct 2026 21:58 UTC Recorded here 6 Oct 2026 22:07 UTC
claude-docs
claude-science/the-reviewer
±changed
+1−1
claude-docschanged
claude-science/the-reviewer
If the reviewer finds something, each finding appears as a card directly under the message it refers to, showing what the reviewer found and the finding's status. A message with mo
If the reviewer finds something, each finding appears as a card directly under the message it refers to, showing what the reviewer found and the finding's status. A message with mo
+1 −1 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/corporate-networks
±changed
+56−8
claude-docschanged
claude-science/corporate-networks
| Authenticated package mirror | Supported, with the credential saved in Settings | Supported, with the credential saved in Settings | Supported, with the credential saved in Setti
| Authenticated package mirror | Supported, with the credential saved in Settings or in a file you deploy | Supported, with the credential saved in Settings or, with version 0.1.56
The organization setting takes a conda channel URL and a Python package index (PyPI) URL, which apply to every member whether or not the organization manages the network allowlist.
The organization setting takes a conda channel URL and a Python package index (PyPI) URL, which apply to every member whether or not the organization manages the network allowlist.
Select **Save**, then **Check**: a green result confirms the mirror answered, and a `401` or `403` on an authenticated mirror is expected until a credential is saved (see [Mirr
+56 −8 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/connectors-and-skills
±changed
+1−1
claude-docschanged
claude-science/connectors-and-skills
Name a source in your request, or describe what you need and Claude chooses from available connector tools. Connector queries appear in the conversation as expandable code steps. F
Name a source in your request, or describe what you need and Claude chooses from available connector tools. Connector queries appear in the conversation as expandable code steps. F
+1 −1 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/configuration-file-reference
±changed
+16−1
claude-docschanged
claude-science/configuration-file-reference
> Claude Science's config.toml file: where it lives, how its values interact with the Settings page, and the network-related keys for the outbound proxy, certificate bundles, packa
> Claude Science's config.toml file: where it lives, how it interacts with Settings, and its network, web search, and upload keys.
## Web search and upload keys
Put `enable_web_search`, `chunked_upload_threshold_bytes`, or both at the top of `config.toml`, above the first line in square brackets such as `[network]`, as in this example:
+16 −1 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/command-line-settings
±changed
+6−1
claude-docschanged
claude-science/command-line-settings
An app started from the macOS Dock or Finder, or from the Windows Start menu, does not see variables exported in a terminal. The macOS app reads the `env` file in the data director
An app started from the macOS Dock or Finder, or from the Windows Start menu, does not see variables exported in a terminal.
* **macOS**: the app reads the `env` file in the data directory (by default `~/.claude-science/env`) when it starts. It applies only a fixed list of variables from the file, which
* **Windows**: set the variable as a user environment variable, then quit and reopen the app.
+6 −1 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/changelog
±changed
+15−0
claude-docschanged
claude-science/changelog
<Update label="0.1.56" description="October 2, 2026">
* Excel (.xlsx) previews now show cell colors, bold text, and color-scale heat maps
* Reviewer findings now open in place, with a button to the reviewer's full transcript
* A stalled file upload now stops by itself, and a failed upload says why under the file
+15 −0 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-docs
claude-science/admin-controls
±changed
+2−2
claude-docschanged
claude-science/admin-controls
Mirror credentials stay with each member. A member signs in to your mirror once per mirror host under **Settings** > **Network** > **Package mirror** > **Mirror credentials**, and
Mirror credentials stay with each member. A member signs in to your mirror once per mirror host under **Settings > Network > Package mirror > Mirror credentials**, unless you [depl
| Plugins > plugins you add for the organization | Partially supported in Claude Science | Plugins you set to **Installed by default** or **Required** are synced to members' Claude
| Plugins > plugins you add for the organization | Partially supported in Claude Science | Plugins you set to **Installed by default** or **Required** are synced to members' Claude
+2 −2 lines
Upstream edited 6 Oct 2026 20:28 UTC Recorded here 6 Oct 2026 20:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 6 Oct 2026 20:07 UTC
claude-code
sessions
±changed
+3−2
claude-codechanged
sessions
| `↑` / `↓` | Navigate between sessions |
| `↑` / `↓` or `k` / `j` | Navigate between sessions |
| `1` to `9` | Resume the session at that position in the list |
| `/` or any printable character other than `Space` | Enter search mode and filter sessions. Paste a GitHub, GitHub Enterprise, GitLab, or Bitbucket pull or merge request URL to fi
| `/` or any printable character other than `Space`, `j`, `k`, or a digit | Enter search mode and filter sessions. Paste a GitHub, GitHub Enterprise, GitLab, or Bitbucket pull or m
+3 −2 lines
Upstream edited 6 Oct 2026 20:02 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
| `effort` | No | Effort level when this subagent is active. Overrides the session effort level. Default: inherits from session. Options: `low`, `medium`, `high`, `xhigh`, `max`; a
| `effort` | No | Effort level when this subagent is active. Overrides the session effort level, but not the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment v
+1 −1 lines
Upstream edited 6 Oct 2026 19:59 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
The per-task `effort` field is the reasoning effort set for that subagent, in its [definition frontmatter](/docs/en/sub-agents#supported-frontmatter-fields) or on the individual in
The per-task `effort` field is the reasoning effort set for that subagent, in its [definition frontmatter](/docs/en/sub-agents#supported-frontmatter-fields) or on the individual in
+1 −1 lines
Upstream edited 6 Oct 2026 19:59 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
plugins/mods/reference
±changed
+7−6
claude-codechanged
plugins/mods/reference
Look up any event a [mod](/docs/en/plugins/mods/overview) can handle, mods API method it can call, or render site it can draw in, for the Claude Code CLI and the Desktop app as of
Look up any event a [mod](/docs/en/plugins/mods/overview) can handle, mods API method it can call, or render site it can draw in, for the Claude Code CLI and the Desktop app as of
| `prompt.mention` | Claude Code is about to read a file that a prompt @-mentions. Requires Claude Code v2.1.290 or later. | `next({ ...e, path })` to read a different file, or `{
| `engine.create` | The mods API is being built for this mod | A changed mods API, to add a namespace or withhold one |
| `engine.create` | The mods API is being built for this mod | A changed mods API, to add a namespace. A mod outside the `user` [tier](#the-hook-function) can also withhold one. |
+7 −6 lines
Upstream edited 6 Oct 2026 19:59 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
remote-control
±changed
+4−0
claude-codechanged
remote-control
<Note>
Remote Control is a Claude Code feature. For conversations in other Claude products, see the [Claude Help Center](https://support.claude.com).
</Note>
+4 −0 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
plugins/troubleshooting
±changed
+1−1
claude-codechanged
plugins/troubleshooting
Several command spellings are in use that Claude Code doesn't have. The table below maps each one to the real command. The [plugin commands reference](/docs/en/plugins/cli-referenc
Several command spellings are in use that Claude Code doesn't have. The table below maps each one to the real command. The [plugin commands reference](/docs/en/plugins/cli-referenc
+1 −1 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
plugins/install
±changed
+1−1
claude-codechanged
plugins/install
For every `claude plugin install` flag, see [plugin install](/docs/en/plugins/cli-reference#plugin-install).
For the other `claude plugin install` flags, see [plugin install](/docs/en/plugins/cli-reference#plugin-install).
+1 −1 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
plugins/cli-reference
±changed
+2−2
claude-codechanged
plugins/cli-reference
> Complete reference for the claude plugin shell commands, /plugin and /reload-plugins in a session, and the flags that load a plugin for one session.
> Reference for the claude plugin shell commands, /plugin and /reload-plugins in a session, and the flags that load a plugin for one session.
Run `claude plugin --help` on your build to confirm which subcommands your version has.
The tables below list each subcommand's commonly used options, not every option. Run `claude plugin --help` in your shell to see which subcommands your version has, and `claude plu
+2 −2 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
Claude Code couldn't obtain usable credentials from the AWS credential provider chain or from your Google application default credentials on the machine it runs on, so no request r
Claude Code couldn't obtain usable credentials from the AWS credential provider chain or from your Google application default credentials on the machine it runs on, so no request r
+1 −1 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
This page covers how to [track your costs](#track-your-costs), [manage costs for your organization](#manage-costs-for-your-organization), and [reduce token usage](#reduce-token-usa
This page covers Claude Code usage only: how to [track your costs](#track-your-costs), [manage costs for your organization](#manage-costs-for-your-organization), and [reduce token
+1 −1 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
amazon-bedrock
±changed
+3−1
claude-codechanged
amazon-bedrock
If browser tabs spawn repeatedly when using AWS SSO, remove the `awsAuthRefresh` setting from your [settings file](/docs/en/settings). This can occur when corporate VPNs or TLS ins
If browser sign-in tabs keep opening when you use AWS SSO, remove the `awsAuthRefresh` setting from your [settings file](/docs/en/settings).
The loop can occur when corporate VPNs or TLS inspection proxies interrupt the SSO browser flow. Claude Code treats the interrupted connection as an authentication failure. When a
+3 −1 lines
Upstream edited 6 Oct 2026 19:57 UTC Recorded here 6 Oct 2026 20:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 6 Oct 2026 19:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+30−16
claude-codechanged
self-hosted-environments-deploy
* <span id="processes-a-stopped-session-leaves" />When the runner stops a session, it sends no signal to a process still running after its shell command exited, such as a service
On `SIGTERM`, the runner stops taking new work and, unless you set [`--defer-shutdown-max-min`](#defer-the-drain-past-the-first-signal), waits up to `--drain-wait-sec`, zero by def
The full drain path needs up to `--session-stop-grace-sec` + `--drain-wait-sec` + `--post-session-hook-timeout-sec`, plus 15 seconds of fixed overhead for process cleanup, plus 30
+30 −16 lines
Upstream edited 6 Oct 2026 19:35 UTC Recorded here 6 Oct 2026 19:37 UTC
claude-code
changelog
±changed
+95−0
claude-codechanged
changelog
<Update label="2.1.292" description="October 6, 2026">
* Added `--marketplace <source>` to `claude plugin install`: adds the marketplace if needed, under the same policy checks as `claude plugin marketplace add`, then installs the pl
* Added an `effort` parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for
* Added `CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS` environment variable to set a longer base delay for the backoff when retrying an overloaded (529) request
+95 −0 lines
Upstream edited 6 Oct 2026 19:14 UTC Recorded here 6 Oct 2026 19:37 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 6 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+1−1
claude-docschanged
third-party/claude-desktop/telemetry
| `downloads.claude.ai` | VM workspace bundle and Claude CLI binary, fetched at session start |
| `downloads.claude.ai` | VM workspace bundle and Claude CLI binary, fetched in the background or at session start |
+1 −1 lines
Upstream edited 6 Oct 2026 19:04 UTC Recorded here 6 Oct 2026 19:07 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 6 Oct 2026 19:04 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+30−1
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.26454.0" description="2026-10-06">
<div className="cfg-keys">
| MDM key | Type | Description |
| - | - | - |
| [`microsoftAuthDefaultAccount`](/docs/third-party/claude-desktop/configuration#microsoftauthdefaultaccount) | `enum` | Microsoft 365 sign-in with the Windows account |
+30 −1 lines
Upstream edited 6 Oct 2026 19:04 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+14−2
claude-docschanged
third-party/claude-desktop/configuration
| <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
Each folder is interpreted on the machine the session runs on. For a Code session on an SSH host, `~` means the remote user's home, an entry that references a `%VAR%` is ignore
Each folder is interpreted on the machine the session runs on. For a Code session on an SSH host, `~` means the remote user's home, an entry that references a `%VAR%` is ignore
+14 −2 lines
Upstream edited 6 Oct 2026 19:04 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-docs
cowork/changelog
±changed
+44−0
claude-docschanged
cowork/changelog
<Update label="v2.26454.0" description="2026-10-06">
Bundled Claude Code version: 2.1.289.
**General**
+44 −0 lines
Upstream edited 6 Oct 2026 19:04 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
llm-gateway-rollout
±changed
+51−51
claude-codechanged
llm-gateway-rollout
> * To connect Claude Code on your own machine to an existing gateway, see [Connect Claude Code to an LLM gateway](/docs/en/llm-gateway-connect.md)
> * For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol.md)
> * To connect Claude Code on your own machine to an existing gateway, see [Connect Claude Code to an LLM gateway](https://code.claude.com/docs/en/llm-gateway-connect.md)
> * For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](https://code.claude.com/docs/en/llm-gateway-protocol.md)
* For a cloud provider: cloud credentials with model access. See the prerequisites on the [Amazon Bedrock](/docs/en/amazon-bedrock.md#prerequisites), [Google Cloud's Agent Platfo
+51 −51 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
llm-gateway-rollout
±changed
+44−44
claude-codechanged
llm-gateway-rollout
> * To connect Claude Code on your own machine to an existing gateway, see [Connect Claude Code to an LLM gateway](/docs/en/llm-gateway-connect)
> * For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol)
> * To connect Claude Code on your own machine to an existing gateway, see [Connect Claude Code to an LLM gateway](/docs/en/llm-gateway-connect.md)
> * For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol.md)
* For a cloud provider: cloud credentials with model access. See the prerequisites on the [Amazon Bedrock](/docs/en/amazon-bedrock#prerequisites), [Google Cloud's Agent Platform]
+44 −44 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
llm-gateway-rollout
±changed
+76−84
claude-codechanged
llm-gateway-rollout
<Note>
* To connect Claude Code on your own machine to an existing gateway, see [Connect Claude Code to an LLM gateway](/docs/en/llm-gateway-connect)
* For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol)
</Note>
> [!NOTE]
+76 −84 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
security
±changed
+1−1
claude-codechanged
security
* Consider using [dev containers](/docs/en/devcontainer) for additional isolation
* For additional isolation, run the whole Claude Code (local mode) process inside the [sandbox runtime](/docs/en/sandbox-environments#sandbox-runtime) or a [dev container](/docs/en
+1 −1 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
sandboxing
±changed
+2−0
claude-codechanged
sandboxing
* **Background sessions**: a [background session](/docs/en/agent-view) runs in its own process, and its Bash commands are sandboxed when [its settings](/docs/en/agent-view#settings
* **A boundary around the whole process**: to put the processes in [What runs outside the sandbox](#what-runs-outside-the-sandbox) behind a boundary too, run Claude Code (local mod
+2 −0 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
permission-modes
±changed
+16−0
claude-codechanged
permission-modes
| Your organization has the [HIPAA configuration](#hipaa-configuration) applied and the session is [eligible for it](/docs/en/hipaa-setup#check-how-developers-sign-in-and-connect)
<h3 id="hipaa-configuration">
Permission modes with the HIPAA configuration
</h3>
+16 −0 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
monitoring-usage
±changed
+44−1
claude-codechanged
monitoring-usage
* `files_past_cutoff`: Files older than the retention period that the sweep failed to delete, for example because of a permission error or a file held open. A value above zero mean
* `files_past_cutoff`: Files older than the retention period that the sweep failed to delete, for example because of a permission error or a file held open. The count also includes
### Map egress paths to managed controls and events
The table pairs paths that can carry session content off a machine, plus local retention, with the [managed settings](/docs/en/managed-settings) keys that restrict them and the eve
+44 −1 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
llm-gateway-rollout
±changed
+11−0
claude-codechanged
llm-gateway-rollout
#### The HIPAA configuration behind a gateway
Sessions that go through a gateway aren't eligible for the HIPAA configuration. [Check how developers sign in and connect](/docs/en/hipaa-setup#check-how-developers-sign-in-and-con
To restrict features for those sessions in the managed settings file, use the keys in [Map egress paths to managed controls and events](/docs/en/monitoring-usage#map-egress-paths-t
+11 −0 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
llm-gateway-protocol
±changed
+2−0
claude-codechanged
llm-gateway-protocol
Sessions that go through a gateway aren't eligible for the HIPAA configuration. [Check how developers sign in and connect](/docs/en/hipaa-setup#check-how-developers-sign-in-and-con
+2 −0 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-code
claude-directory
±changed
+5−1
claude-codechanged
claude-directory
To check that the machines in your organization run the sweep with the retention period you set, see [Check the retention sweep](/docs/en/monitoring-usage#check-the-retention-sweep
The command leaves `shell-snapshots/` and `backups/` alone because those are not project-scoped, and warns about them in the plan output.
In a script, check the output rather than the exit status alone. A run that deletes everything in its plan ends with `Purged N item(s)`. Treat that line as the sign of success.
+5 −1 lines
Upstream edited 6 Oct 2026 18:41 UTC Recorded here 6 Oct 2026 19:07 UTC
claude-docs
claude-tag/concepts/personal-connectors
±changed
+11−11
claude-docschanged
claude-tag/concepts/personal-connectors
Personal connectors in channels are on for every organization on the Team plan, with nothing for an admin to set up. On the Enterprise plan, an admin manages them in the **Personal
Personal connectors in channels are on for every organization on the Team plan, with nothing for an admin to set up. On the Enterprise plan, an admin manages them in the **Personal
* **Claude starts work on its own.** [Routines](/docs/claude-tag/users/proactivity.md) and other work Claude starts on its own in a channel use the channel's own access, never your
* **You ask in a [group DM](/docs/claude-tag/users/group-dms.md).** Claude uses your connectors after you allow it, and only your own requests use them.
* **You ask in a one-to-one direct message (DM).** Your connectors apply on their own, because a DM runs on [your own claude.ai account](/docs/claude-tag/concepts/agent-identity.md
+11 −11 lines
Upstream edited 6 Oct 2026 18:31 UTC Recorded here 23 Oct 2026 18:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.