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
6 Oct 2026
118 pages
+2901 −2116 lines
claude-code
desktop
±changed
+30−24
claude-codechanged
desktop
* Start or stop servers from the server dropdown in the session toolbar
* Persist cookies and local storage across server restarts by selecting **Persist sessions** in the dropdown, so you don't have to re-login during development
* Edit the server configuration or stop all servers at once
* Start or stop servers, or stop them all at once, from the **Dev servers** menu in the Browser pane's header
* Choose whether the Browser keeps cookies after you quit the app with **Keep cookies** in the Browser pane's **⋮** menu, so you don't have to sign in again during development
+30 −24 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
code-review
±changed
+1−1
claude-codechanged
code-review
In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop), Claude reports the review's findings through the [`ReportFindings` tool](/docs/e
In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop#review-your-code), Claude reports the review's findings through the [`ReportFindin
+1 −1 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
desktop-ios-simulator
±changed
+1−1
claude-codechanged
desktop-ios-simulator
You can also open the simulator pane yourself. Once the session has a simulator attached or has edited Swift files, the **Views** menu in the session toolbar shows an **iOS Simulat
You can also open the simulator pane yourself. Once the session has a simulator attached or Claude Code detects iOS app work, an **iOS Simulator** button appears in the session's t
+1 −1 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
fullscreen
±changed
+5−4
claude-codechanged
fullscreen
* **Click an option in a select menu** to choose it. This covers permission prompts, `/model`, `/config`, and other dialogs that show a list of options. Hovering shows a pointer on
* **Click an option in a select menu** to choose it. This covers permission prompts, `/model`, `/config`, and other dialogs that show a list of options.
* **Hold `Cmd` on macOS, or `Ctrl` on Linux and Windows, and click a URL or file path** to open it. Plain `http://` and `https://` URLs open in your browser, and file paths in tool
* **Hold `Cmd` on macOS, or `Ctrl` on Linux and Windows, and click a URL or file path** to open it. Plain `http://` and `https://` URLs open in your browser. When Claude Code handl
* On Linux and WSL, clicking a file path needs a file manager that provides the `org.freedesktop.FileManager1` D-Bus interface. Without one, nothing opens.
+5 −4 lines
Upstream edited 6 Oct 2026 01:01 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
keybindings
±changed
+5−5
claude-codechanged
keybindings
| `confirm:nextField` | Tab | Next field |
| `confirm:previousField` | (unbound) | Previous field |
| `confirm:nextField` | Tab | In the `/fast` dialog, turn fast mode on or off |
| `confirm:previousField` | (unbound) | Claude Code doesn't respond to this action, and a `keybindings.json` that names it remains valid |
| `confirm:cycleMode` | Shift+Tab\* | Cycle permission modes. On a file permission prompt, closes an open [comment field](/docs/en/permissions#add-a-comment-when-you-answer-a-permi
+5 −5 lines
Upstream edited 6 Oct 2026 00:59 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+2−1
claude-docschanged
third-party/claude-desktop/data-storage
* **Project folders are read-only.** A Chat conversation inside a project can read files in folders added to the project in Claude Desktop, under the conditions in [Project folders
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
+2 −1 lines
Upstream edited 6 Oct 2026 00:25 UTC Recorded here 6 Oct 2026 00:37 UTC
claude-docs
third-party/claude-desktop/chat
±changed
+16−7
claude-docschanged
third-party/claude-desktop/chat
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
| Project folders | For a conversation inside a project, read-only access to folders added to the project in Claude Desktop. Claude can list and read files in them. See [Project fo
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in an offline local sandbox against attached
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in an offline local sandbox against attached
+16 −7 lines
Upstream edited 6 Oct 2026 00:25 UTC Recorded here 6 Oct 2026 00:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 6 Oct 2026 00:07 UTC
5 Oct 2026
200 pages
+8992 −5065 lines
claude-code
changelog
±changed
+193−0
claude-codechanged
changelog
<Update label="2.1.290" description="October 5, 2026">
* Added `serverToolUses` to the result of a mod's `turn.step` hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end
* Added `agentId` to the `tool.check` event of plugin hooks, so a hook can tell a subagent's permission check from the main session's
* Added `ceiling` to the question and verdict a mod's `tool.check` hook reads, naming the approval an organization requires for a tool
+193 −0 lines
Upstream edited 5 Oct 2026 23:53 UTC Recorded here 6 Oct 2026 00:07 UTC
api
models/fable-5/overview
±changed
+1−1
apichanged
models/fable-5/overview
[Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview) is offered separately, by invitation only, for defensive cybersecurity workflows as part of [Project
[Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview) is offered separately, by invitation only, for defensive cybersecurity workflows as part of [Project
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5/migration-guide
±changed
+4−5
apichanged
models/fable-5/migration-guide
* **Safety classifiers:** Claude Fable 5 runs safety classifiers that can decline requests with `stop_reason: "refusal"`. Claude Mythos 5 does not include these classifiers. See [R
Migration is mostly drop-in. Claude Mythos 5 and Claude Fable 5 use the same [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the sam
Migration is mostly drop-in. Claude Mythos 5 and Claude Fable 5 use the same [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the sam
* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. Claude Fable 5 runs safety classifiers that Claude Mythos Preview an
* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. See [Refusals and fallback](https://platform.claude.com/docs/en/buil
+4 −5 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+6−6
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. Claude Mythos 5 does not include these classifiers. If your integration
The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. If your integration calls Claude Fable 5, plan for three changes: new re
| Model | API model ID | Description
| --------------- | ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------
| Claude Fable 5 | `claude-fable-5` | Built for demanding reasoning and long-horizon agentic work
+6 −6 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5-1/overview
±changed
+1−1
apichanged
models/fable-5-1/overview
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5-1/migration-guide
±changed
+0−1
apichanged
models/fable-5-1/migration-guide
* **Safety classifiers:** Claude Fable 5.1 runs safety classifiers covering the same `stop_details` categories as Claude Fable 5. A declined request returns `stop_reason: "refusal"
+0 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+115−21
apichanged
manage-claude/inference-hooks-endpoint
There is one hook event today: the prompt frame, sent once per governed inference request, before inference begins. Anthropic holds the request until your AI security server respon
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
| Field | Type | Description
| ------------ | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------
| `type` | string | The hook event. Always `"prompt"` today; other event types will be introduced in the future, so handle an unrecognized value gracefully (see [Forw
+115 −21 lines
Recorded here 5 Oct 2026 23:37 UTC
api
manage-claude/inference-hooks-configuration
±changed
+3−1
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
Shadow mode runs your hook against live traffic without blocking anything. Your AI security server receives governed prompts and returns verdicts exactly as it would when enforcing
Shadow mode runs your hook against live traffic without blocking anything. Your AI security server receives governed prompts and returns verdicts exactly as it would when enforcing
+3 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
manage-claude/inference-hooks
±changed
+5−1
apichanged
manage-claude/inference-hooks
Today the only hook event is `prompt`, which fires once per governed inference request, before inference begins. Response-side enforcement is planned as a later event.
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
With **Validate tool calls** on, Claude's tool calls are a third hooked point, which the diagram doesn't show: your AI security server returns one verdict for all the tool calls in
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
+5 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/organization/rbac_roles/retrieve
±changed
+9−2
apichanged
api/beta/organization/rbac_roles/retrieve
- `name: string`
- `display_name: string`
Name of the RBAC Role.
Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a
+9 −2 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/organization/rbac_roles/list
±changed
+9−2
apichanged
api/beta/organization/rbac_roles/list
- `name: string`
- `display_name: string`
Name of the RBAC Role.
Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a
+9 −2 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/organization/rbac_roles
±changed
+41−21
apichanged
api/beta/organization/rbac_roles
- `display_name: string`
Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a
- `updated_at: string`
+41 −21 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/organization
±changed
+28−14
apichanged
api/beta/organization
- `display_name: string`
Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a
- `updated_at: string`
+28 −14 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/agents/update
±changed
+1−1
apichanged
api/beta/agents/update
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 256 tools across all toolsets allowed.
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/agents/create
±changed
+1−1
apichanged
api/beta/agents/create
Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed.
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta/agents
±changed
+2−2
apichanged
api/beta/agents
Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed.
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 256 tools across all toolsets allowed.
+2 −2 lines
Recorded here 5 Oct 2026 23:37 UTC
api
api/beta
±changed
+30−16
apichanged
api/beta
Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed.
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 128 tools across all toolsets allowed.
Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 256 tools across all toolsets allowed.
- `display_name: string`
+30 −16 lines
Recorded here 5 Oct 2026 23:37 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 5 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/legal
±changed
+5−5
claude-docschanged
third-party/claude-desktop/legal
If your organization manages Claude Desktop on 3P from the [Enterprise Admin Console for Desktop 3P](/docs/third-party/claude-desktop/admin-console.md) (**Organization settings** o
If your organization manages Claude Desktop on 3P from the [Enterprise Admin Console for Desktop 3P](https://claude.com/docs/third-party/claude-desktop/admin-console.md) (**Organiz
See the [Overview](/docs/third-party/claude-desktop/overview.md) for the architecture and [Data handling by provider](/docs/third-party/claude-desktop/overview.md#data-handling-by-
See the [Overview](https://claude.com/docs/third-party/claude-desktop/overview.md) for the architecture and [Data handling by provider](https://claude.com/docs/third-party/claude-d
For HIPAA, see [HIPAA](/docs/third-party/claude-desktop/overview.md#hipaa) on the Overview page. For Google Cloud's Agent Platform and Amazon Bedrock, Anthropic does not interact w
+5 −5 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/legal
±changed
+5−5
claude-docschanged
third-party/claude-desktop/legal
If your organization manages Claude Desktop on 3P from the [Enterprise Admin Console for Desktop 3P](/docs/third-party/claude-desktop/admin-console) (**Organization settings** on c
If your organization manages Claude Desktop on 3P from the [Enterprise Admin Console for Desktop 3P](/docs/third-party/claude-desktop/admin-console.md) (**Organization settings** o
See the [Overview](/docs/third-party/claude-desktop/overview) for the architecture and [Data handling by provider](/docs/third-party/claude-desktop/overview#data-handling-by-provid
See the [Overview](/docs/third-party/claude-desktop/overview.md) for the architecture and [Data handling by provider](/docs/third-party/claude-desktop/overview.md#data-handling-by-
For HIPAA, see [HIPAA](/docs/third-party/claude-desktop/overview#hipaa) on the Overview page. For Google Cloud's Agent Platform and Amazon Bedrock, Anthropic does not interact with
+5 −5 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/overview
±changed
+2−2
claude-docschanged
third-party/claude-desktop/overview
For Google Cloud's Agent Platform and Amazon Bedrock, Claude Desktop on 3P does not send user data, prompts, or completions to Anthropic, so Anthropic does not interact with PHI a
For Google Cloud's Agent Platform and Amazon Bedrock, Claude Desktop on 3P does not send user data, prompts, or completions to Anthropic, so Anthropic does not interact with PHI a
For Microsoft Foundry, HIPAA readiness is not available. Anthropic operates the Claude models in Microsoft Foundry and processes conversation data, as described under [Data handlin
Anthropic's API accessed through Microsoft Foundry (Hosted on Anthropic or Hosted on Azure) is an Eligible Service, as long as you have the HIPAA configuration enabled. Either opti
+2 −2 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/legal
±changed
+1−1
claude-docschanged
third-party/claude-desktop/legal
For HIPAA, see [HIPAA](/docs/third-party/claude-desktop/overview#hipaa) on the Overview page. For Google Cloud's Agent Platform and Amazon Bedrock, Anthropic does not interact with
For HIPAA, see [HIPAA](/docs/third-party/claude-desktop/overview#hipaa) on the Overview page. For Google Cloud's Agent Platform and Amazon Bedrock, Anthropic does not interact with
+1 −1 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+2−0
claude-docschanged
third-party/claude-desktop/connectors-m365
The hosted M365 server has not been evaluated for HIPAA compliance. If your organization follows HIPAA compliance, please use the [local connector](#local-connector) instead.
+2 −0 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-code
legal-and-compliance
±changed
+4−4
claude-codechanged
legal-and-compliance
* **HIPAA configuration**: the Claude Code CLI or the Code tab in Claude Desktop, used with a Claude for Enterprise account. The organization must have HIPAA enabled and the HIPAA
* **Zero Data Retention**: Claude Code with [Zero Data Retention (ZDR)](/docs/en/zero-data-retention.md) enabled for the relevant organization. ZDR isn't available for all organiza
* **HIPAA configuration**: the Claude Code CLI or the Code tab in Claude Desktop, used with a Claude for Enterprise account. The organization must have HIPAA enabled and the HIPAA
* **Zero Data Retention**: Claude Code with [Zero Data Retention (ZDR)](https://code.claude.com/docs/en/zero-data-retention.md) enabled for the relevant organization. ZDR isn't ava
* **OAuth authentication** is intended exclusively for purchasers of Claude Free, Pro, Max, Team, and Enterprise subscription plans and is designed to support ordinary use of Claud
+4 −4 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
legal-and-compliance
±changed
+4−4
claude-codechanged
legal-and-compliance
* **HIPAA configuration**: the Claude Code CLI or the Code tab in Claude Desktop, used with a Claude for Enterprise account. The organization must have HIPAA enabled and the HIPAA
* **Zero Data Retention**: Claude Code with [Zero Data Retention (ZDR)](/docs/en/zero-data-retention) enabled for the relevant organization. ZDR isn't available for all organizatio
* **HIPAA configuration**: the Claude Code CLI or the Code tab in Claude Desktop, used with a Claude for Enterprise account. The organization must have HIPAA enabled and the HIPAA
* **Zero Data Retention**: Claude Code with [Zero Data Retention (ZDR)](/docs/en/zero-data-retention.md) enabled for the relevant organization. ZDR isn't available for all organiza
* **OAuth authentication** is intended exclusively for purchasers of Claude Free, Pro, Max, Team, and Enterprise subscription plans and is designed to support ordinary use of Claud
+4 −4 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
zero-data-retention
±changed
+1−1
claude-codechanged
zero-data-retention
Claude for Enterprise organizations that have enabled HIPAA can bring the Claude Code CLI and the Code tab in Claude Desktop under their Business Associate Agreement (BAA) without
Claude for Enterprise organizations that have enabled HIPAA can bring the Claude Code CLI and the Code tab in Claude Desktop under their Business Associate Agreement (BAA) without
+1 −1 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-code
legal-and-compliance
±changed
+1−1
claude-codechanged
legal-and-compliance
Under the HIPAA configuration, cloud sessions, Remote Control, Claude Code in the Claude mobile app, and Claude Code routed through a third-party cloud provider or a gateway aren't
Under the HIPAA configuration, cloud sessions, Remote Control, Claude Code in the Claude mobile app, and Claude Code routed through a third-party cloud provider or a gateway aren't
+1 −1 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-code
hipaa-setup
±changed
+2−2
claude-codechanged
hipaa-setup
The Claude Code extensions for VS Code and JetBrains aren't part of (local mode). They keep working with the HIPAA configuration applied, but your BAA doesn't cover them. See the
The Claude Code extensions for VS Code and JetBrains aren't part of (local mode). They keep working with the HIPAA configuration applied, but your BAA doesn't cover them. See the
The HIPAA configuration doesn't remove cloud provider or GitHub credentials, so a command that pushes to GitHub or calls another service still works with that developer's access. Y
The HIPAA configuration doesn't remove cloud provider or GitHub credentials, so a command that pushes to GitHub or calls another service still works with that developer's access. Y
+2 −2 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
In Enterprise organizations that have HIPAA enabled, Claude in Chrome is off by default, and an [Owner](/docs/en/server-managed-settings#access-control) can turn it on in [**Organi
In Enterprise organizations that have HIPAA enabled, Claude in Chrome is off by default, and an [Owner](/docs/en/server-managed-settings#access-control) can turn it on in [**Organi
+1 −1 lines
Upstream edited 5 Oct 2026 23:36 UTC Recorded here 5 Oct 2026 23:37 UTC
claude-docs
cowork/hipaa-setup
±changed
+1−1
claude-docschanged
cowork/hipaa-setup
The Claude Code extensions for VS Code and JetBrains aren't part of (local mode). They keep working with the HIPAA configuration applied, but your BAA doesn't cover them. See the
The Claude Code extensions for VS Code and JetBrains aren't part of (local mode). They keep working with the HIPAA configuration applied, but your BAA doesn't cover them. See the
+1 −1 lines
Upstream edited 5 Oct 2026 23:29 UTC Recorded here 5 Oct 2026 23:37 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 5 Oct 2026 22:37 UTC
claude-code
voice-dictation
±changed
+42−44
claude-codechanged
voice-dictation
<Tip>
To skip the warmup, switch to [tap mode](#tap-to-record-and-send) with `/voice tap`, or [rebind to a modifier combination](#rebind-the-dictation-key) like `meta+k`. Modifier comb
</Tip>
> [!TIP]
>
+42 −44 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
voice-dictation
±changed
+1−1
claude-codechanged
voice-dictation
Dictation also works in [agent view](/docs/en/agent-view#peek-and-reply). Hold or tap your push-to-talk key while the dispatch input or a peek-panel reply is focused to dictate to
In [hold mode](#hold-to-record), dictation also works in [agent view](/docs/en/agent-view#peek-and-reply). Hold your push-to-talk key while the dispatch input or a peek-panel reply
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
skills
±changed
+2−2
claude-codechanged
skills
`/verify` can also record its own recipe. When it has to build and drive your app without a recorded recipe, it writes what worked to `.claude/skills/verify/SKILL.md` at the repo r
`/verify` can also record its own recipe. When it has to build and drive your app without a recorded recipe, it writes what worked to `.claude/skills/verify/SKILL.md` at the repo r
If the install summary reports `Run /reload-plugins to activate.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conversat
If the install summary reports `Run /reload-plugins to apply.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conversation
+2 −2 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
security-guidance
±changed
+1−1
claude-codechanged
security-guidance
Check the install summary. If it reports `Run /reload-plugins to activate.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activat
Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate t
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **The message doesn't say to contact your organization admin**: your organization has a HIPAA configuration that is incompatible with Remote Control, and `/status` lists `HIPAA`
* **The message doesn't say to contact your organization admin**: your organization has the [HIPAA configuration](/docs/en/hipaa-setup) applied, which turns Remote Control off. To
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
[Nested CLAUDE.md files in subdirectories](/docs/en/memory) and [rules with `paths:` frontmatter](/docs/en/memory#path-specific-rules) load later, when Claude first reads a matchin
[Nested CLAUDE.md files in subdirectories](/docs/en/memory) and [rules with `paths:` frontmatter](/docs/en/memory#path-specific-rules) load later, when Claude first reads a matchin
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/troubleshooting
±changed
+4−4
claude-codechanged
plugins/troubleshooting
`Run /reload-plugins to activate.`
</h3>
The install summary in `/plugin` ended with `Run /reload-plugins to activate.` instead of `Plugin is now active.`
`Run /reload-plugins to apply.`
+4 −4 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/mods/troubleshoot
±changed
+3−5
claude-codechanged
plugins/mods/troubleshoot
### Your version is older than 2.1.287
`claude --version` prints a version older than 2.1.287. Your version predates mods being on by default.
[Update Claude Code](/docs/en/setup#update-claude-code).
+3 −5 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/mods/overview
±changed
+4−1
claude-codechanged
plugins/mods/overview
Mods require Claude Code v2.1.287 or later, and they're on by default. In your shell, run `claude --version` to check, and update Claude Code if yours is older.
Mods are on by default. In the terminal, use Claude Code v2.1.287 or later. The Desktop app includes its own copy of Claude Code, and mods work there from v2.1.286. Check the versi
* **Terminal**: in your shell, run `claude --version`. If yours is older, [update Claude Code](/docs/en/setup#update-claude-code).
* **Desktop app**: in a local session in the Code tab, enter `/status` and read the **Claude Code** row, which shows a version such as `2.1.286`. If yours is older, update the Desk
+4 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/mods/create
±changed
+1−1
claude-codechanged
plugins/mods/create
Mods require Claude Code v2.1.287 or later. In your shell, run `claude --version` to check. To see whether mods can load for you, see [Check whether mods can load](/docs/en/plugi
Use Claude Code v2.1.287 or later. In your shell, run `claude --version` to check. To see whether mods can load for you, see [Check whether mods can load](/docs/en/plugins/mods/t
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/mods/admin
±changed
+1−1
claude-codechanged
plugins/mods/admin
This page is for the person who deploys managed settings for Claude Code, whether as a file, through MDM, or from the claude.ai admin console. Mods are on by default in Claude Code
This page is for the person who deploys managed settings for Claude Code, whether as a file, through MDM, or from the claude.ai admin console. Mods are on by default in Claude Code
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
plugins/install
±changed
+1−1
claude-codechanged
plugins/install
* **Reload needed**: `Run /reload-plugins to activate.` The panel closes and Claude Code runs that reload for you. If the reload would [invalidate the prompt cache](/docs/e
* **Reload needed**: `Run /reload-plugins to apply.` The panel closes and Claude Code runs that reload for you. If the reload would [invalidate the prompt cache](/docs/en/p
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
memory
±changed
+4−3
claude-codechanged
memory
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, they are included when Clau
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, they are included when Clau
The `/memory` command lists your CLAUDE.md, CLAUDE.local.md, and other memory file locations across user and project scopes, including user and project CLAUDE.md entries for files
The `/memory` command lists your CLAUDE.md, CLAUDE.local.md, and other memory file locations across user and project scopes, including user and project CLAUDE.md entries for files
* Run `/context` and check the list under **Memory files** to verify your CLAUDE.md and CLAUDE.local.md files loaded. If a `CLAUDE.md` file is missing there, Claude can't see it. U
+4 −3 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
If the install summary reports `Run /reload-plugins to activate.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conve
If the install summary reports `Run /reload-plugins to apply.`, Claude Code then runs that reload for you. If the reload warns that your next message would re-read the conversa
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
hipaa-setup
±changed
+11−4
claude-codechanged
hipaa-setup
* **Versions older than v2.1.285**: these versions ignore `allowedProviders`, so they can still start on a cloud provider or a gateway. To make v2.1.163 through v2.1.284 refuse to
If your organization needs a developer's session data removed before the retention sweep deletes it, you can remove most of it with one command. Sign in to the computer as that dev
If your organization needs a developer's session data removed before the retention sweep deletes it, you can remove most of it with one command. Sign in to the computer as that dev
On Claude Code v2.1.288 or later, run `claude purge`:
+11 −4 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
debug-your-config
±changed
+2−2
claude-codechanged
debug-your-config
If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md`
If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md`
| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | They load after Claude uses the Read, Write, or Edit tool on a file
| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | See [when subdirectory files load](/docs/en/memory#how-claude-md-fi
+2 −2 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
claude-security
±changed
+1−1
claude-codechanged
claude-security
Check the install summary. If it reports `Run /reload-plugins to activate.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activat
Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate t
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
claude-directory
±changed
+2−2
claude-codechanged
claude-directory
* Your organization has the HIPAA configuration applied and Claude Code connects directly to the Claude API
* The [HIPAA configuration applies to your sessions](/docs/en/hipaa-setup#check-how-developers-sign-in-and-connect)
| `history.jsonl` | Every prompt you've typed, with timestamp and project path. Used for up-arrow recall, `Ctrl+R` history search, and `!` shell-command completion. In an organizat
| `history.jsonl` | Every prompt you've typed, with timestamp and project path. Used for up-arrow recall, `Ctrl+R` history search, and `!` shell-command completion. Each sweep remo
+2 −2 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
channels
±changed
+4−4
claude-codechanged
channels
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
If the install summary reports `Run /reload-plugins to activate.`, you don't need to act on it here, because restarting in the next step picks up the plugin.
+4 −4 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
agent-view
±changed
+1−1
claude-codechanged
agent-view
With [voice dictation](/docs/en/voice-dictation) enabled, hold or tap your push-to-talk key while the reply input is focused to dictate a reply instead of typing it. The same works
With [voice dictation](/docs/en/voice-dictation) enabled in [hold mode](/docs/en/voice-dictation#hold-to-record), hold your push-to-talk key while the reply input is focused to dic
+1 −1 lines
Upstream edited 5 Oct 2026 22:35 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
prompt-library
±changed
+25−25
claude-codechanged
prompt-library
prompt: 'read {input} and write up the action items, then create a {tracker} ticket for each with acceptance criteria',
prompt: 'read {input} and write up the action items, then create a ticket in {tracker} for each one, with acceptance criteria',
tracker: 'Linear'
tracker: 'our issue tracker'
example: 'the GitHub webhook handler',
+25 −25 lines
Upstream edited 5 Oct 2026 22:34 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/troubleshooting
±changed
+6−2
claude-docschanged
claude-tag/admins/troubleshooting
**How to resolve**
An Owner may find that the switch can't be turned on, and that hovering over it shows "Your organization's policy doesn't allow changing this setting." In that case, a compliance c
**How to resolve**
+6 −2 lines
Upstream edited 5 Oct 2026 22:32 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/healthcare
±changed
+1−1
claude-docschanged
claude-tag/admins/healthcare
If your Claude organization has the HIPAA configuration applied to Claude Code (local mode) and Cowork (local mode), Claude Tag isn't available in that organization. [Plan and orga
If your Claude organization has the [HIPAA configuration](https://support.claude.com/en/articles/17318731) applied to Claude Code (local mode) and Cowork (local mode), Claude Tag i
+1 −1 lines
Upstream edited 5 Oct 2026 22:32 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/configure-github
±changed
+11−11
claude-docschanged
claude-tag/admins/configure-github
> Using GitLab instead of GitHub? See [Configure GitLab access](/docs/claude-tag/admins/configure-gitlab.md). GitLab uses a service-account token rather than an installed app.
> Using GitLab instead of GitHub? See [Configure GitLab access](https://claude.com/docs/claude-tag/admins/configure-gitlab.md). GitLab uses a service-account token rather than an i
The remaining steps are in Claude Tag admin settings, not GitHub's settings. Granting repositories requires the **Owner** role or the [**Claude Tag Admin** permission](/docs/claude
The remaining steps are in Claude Tag admin settings, not GitHub's settings. Granting repositories requires the **Owner** role or the [**Claude Tag Admin** permission](https://clau
A [bundle](/docs/claude-tag/admins/add-connections.md#create-a-bundle)'s places decide which channels can use the repositories in it.
+11 −11 lines
Upstream edited 5 Oct 2026 22:28 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-tag/admins/configure-github
±changed
+11−11
claude-docschanged
claude-tag/admins/configure-github
> Using GitLab instead of GitHub? See [Configure GitLab access](/docs/claude-tag/admins/configure-gitlab). GitLab uses a service-account token rather than an installed app.
> Using GitLab instead of GitHub? See [Configure GitLab access](/docs/claude-tag/admins/configure-gitlab.md). GitLab uses a service-account token rather than an installed app.
The remaining steps are in Claude Tag admin settings, not GitHub's settings. Granting repositories requires the **Owner** role or the [**Claude Tag Admin** permission](/docs/claude
The remaining steps are in Claude Tag admin settings, not GitHub's settings. Granting repositories requires the **Owner** role or the [**Claude Tag Admin** permission](/docs/claude
A [bundle](/docs/claude-tag/admins/add-connections#create-a-bundle)'s places decide which channels can use the repositories in it.
+11 −11 lines
Upstream edited 5 Oct 2026 22:28 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-tag/admins/configure-github
±changed
+43−47
claude-docschanged
claude-tag/admins/configure-github
export const BetaNote = () => <Info>Claude Tag is in public beta. Features and behavior described here may change before general availability.</Info>;
> [!NOTE]
>
> Claude Tag is in public beta. Features and behavior described here may change before general availability.
<BetaNote />
+43 −47 lines
Upstream edited 5 Oct 2026 22:28 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
claude-tag/admins/configure-github
±changed
+8−8
claude-docschanged
claude-tag/admins/configure-github
The person who completes the link must be both an **owner of the GitHub organization** and an **Owner in your Claude organization**. If you aren't a GitHub organization owner, us
The person who completes the link must be both an **owner of the GitHub organization** and an **Owner in your Claude organization**. If you aren't a GitHub organization owner, cl
<Step title="Open the GitHub settings page">
Open [`claude.ai/admin-settings/github`](https://claude.ai/admin-settings/github). This page is shared with Claude Code; one connection serves both products. Until the Claude G
<Step title="Open the Git providers page">
+8 −8 lines
Upstream edited 5 Oct 2026 22:28 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, `plan`, or `manual` as an alias for `default`. The
| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, `plan`, or `manual` as an alias for `default`. Ign
* **Foreground**: if a rate limit, overload, or server error cuts off a subagent that already produced text output, the Agent tool returns that partial output with a note that the
* **Foreground**: if a rate limit, overload, or server error cuts off a subagent that already produced text output, the Agent tool returns that partial output with a note that the
+2 −2 lines
Upstream edited 5 Oct 2026 22:24 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
settings-reference
±changed
+4−4
claude-codechanged
settings-reference
* `"manual"`: an alias for `"default"`, in Claude Code v2.1.200 or later
* `"manual"`: an alias for `"default"`
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). In cloud sessions,
Let an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when
+4 −4 lines
Upstream edited 5 Oct 2026 22:24 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
permissions
±changed
+2−2
claude-codechanged
permissions
| `default` | Prompts for permission on first use of each tool. Labeled Manual in the CLI, the VS Code and JetBrains extensions, and the desktop app, and Claude Code accepts `manua
| `default` | Prompts for permission on first use of each tool. Labeled Manual in the CLI, the VS Code and JetBrains extensions, and the desktop app, and Claude Code accepts `manua
On versions 2.1.196 through 2.1.199, Claude Code held the file's rules in your configuration home and outside git repositories too, and printed the [`this workspace has not been tr
Before v2.1.207, Claude Code applied an untracked file's rules before you accepted the dialog.
+2 −2 lines
Upstream edited 5 Oct 2026 22:24 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
permission-modes
±changed
+5−8
claude-codechanged
permission-modes
The mode that reviews every action is named **Manual** in the CLI, in `claude --help`, in the VS Code and JetBrains extensions, and in the desktop app. Its config value is `default
The mode that reviews every action is named **Manual** in the CLI, in `claude --help`, in the VS Code and JetBrains extensions, and in the desktop app. Its config value is `default
The classifier trusts your working directory and the remotes that were configured for it when the session started. A remote added or repointed during the session with `git remote a
The classifier trusts your working directory and the remotes that were configured for it when the session started. A remote added or repointed during the session with `git remote a
* Including sensitive details in content sent, uploaded, published, or written to other people or shared systems, when your own message didn't authorize those details for that reci
+5 −8 lines
Upstream edited 5 Oct 2026 22:24 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alia
| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alia
+1 −1 lines
Upstream edited 5 Oct 2026 22:24 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `G` | End of input |
| `G` | Beginning of last line |
+1 −1 lines
Upstream edited 5 Oct 2026 22:18 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
desktop
±changed
+0−1
claude-codechanged
desktop
* **Disable Bypass permissions mode**: prevent users in your organization from enabling bypass permissions mode
+0 −1 lines
Upstream edited 5 Oct 2026 22:16 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
agent-sdk/cost-tracking
±changed
+31−31
claude-codechanged
agent-sdk/cost-tracking
For complete API documentation, see the [TypeScript SDK reference](/docs/en/agent-sdk/typescript.md) and [Python SDK reference](/docs/en/agent-sdk/python.md).
For complete API documentation, see the [TypeScript SDK reference](https://code.claude.com/docs/en/agent-sdk/typescript.md) and [Python SDK reference](https://code.claude.com/docs/
> The `total_cost_usd` and `costUSD` fields are client-side estimates, not authoritative billing data. The SDK computes them locally from a price table bundled at build time, unles
> The `total_cost_usd` and `costUSD` fields are client-side estimates, not authoritative billing data. The SDK computes them locally from a price table bundled at build time, unles
* **`query()` call:** one invocation of the SDK's `query()` function. A single call can involve multiple steps: Claude responds, uses tools, gets results, and responds again. Each
+31 −31 lines
Upstream edited 5 Oct 2026 22:11 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
agent-sdk/cost-tracking
±changed
+16−16
claude-codechanged
agent-sdk/cost-tracking
For complete API documentation, see the [TypeScript SDK reference](/docs/en/agent-sdk/typescript) and [Python SDK reference](/docs/en/agent-sdk/python).
For complete API documentation, see the [TypeScript SDK reference](/docs/en/agent-sdk/typescript.md) and [Python SDK reference](/docs/en/agent-sdk/python.md).
* **`query()` call:** one invocation of the SDK's `query()` function. A single call can involve multiple steps: Claude responds, uses tools, gets results, and responds again. Each
* **`query()` call:** one invocation of the SDK's `query()` function. A single call can involve multiple steps: Claude responds, uses tools, gets results, and responds again. Each
In [streaming input mode](/docs/en/agent-sdk/streaming-vs-single-mode), one `query()` call carries multiple user turns and each turn emits its own result message. The result fields
+16 −16 lines
Upstream edited 5 Oct 2026 22:11 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/cost-tracking
±changed
+160−172
claude-codechanged
agent-sdk/cost-tracking
<span id="estimates-not-billing" />
<Warning>
The `total_cost_usd` and `costUSD` fields are client-side estimates, not authoritative billing data. The SDK computes them locally from a price table bundled at build time, unles
+160 −172 lines
Upstream edited 5 Oct 2026 22:11 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies
For a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies
+1 −1 lines
Upstream edited 5 Oct 2026 22:11 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-code
agent-sdk/cost-tracking
±changed
+4−0
claude-codechanged
agent-sdk/cost-tracking
<span id="estimates-not-billing" />
Either way, the combined figure is still a [client-side estimate](#estimates-not-billing).
+4 −0 lines
Upstream edited 5 Oct 2026 22:11 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/setup-oncall
±changed
+9−9
claude-docschanged
claude-tag/admins/setup-oncall
* **Enterprise plan:** an Owner or a [Claude Tag admin](/docs/claude-tag/admins/restrict-access.md#delegate-claude-tag-administration), meaning a member whose custom role sets **Cl
* **Enterprise plan:** an Owner or a [Claude Tag admin](https://claude.com/docs/claude-tag/admins/restrict-access.md#delegate-claude-tag-administration), meaning a member whose cus
Your organization's on-call is an [Access bundle](/docs/claude-tag/concepts/glossary.md#access-bundle) carrying the connections, repositories, and skills Claude uses for incident w
Your organization's on-call is an [Access bundle](https://claude.com/docs/claude-tag/concepts/glossary.md#access-bundle) carrying the connections, repositories, and skills Claude u
On-call work is billed to your organization as usage. You can cap it with a monthly spend limit. [Set a spend limit](/docs/claude-tag/admins/set-spend-limit.md) covers what counts
+9 −9 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-tag/admins/setup-oncall
±changed
+8−8
claude-docschanged
claude-tag/admins/setup-oncall
* **Enterprise plan:** an Owner or a [Claude Tag admin](/docs/claude-tag/admins/restrict-access#delegate-claude-tag-administration), meaning a member whose custom role sets **Claud
* **Enterprise plan:** an Owner or a [Claude Tag admin](/docs/claude-tag/admins/restrict-access.md#delegate-claude-tag-administration), meaning a member whose custom role sets **Cl
Your organization's on-call is an [Access bundle](/docs/claude-tag/concepts/glossary#access-bundle) carrying the connections, repositories, and skills Claude uses for incident work
Your organization's on-call is an [Access bundle](/docs/claude-tag/concepts/glossary.md#access-bundle) carrying the connections, repositories, and skills Claude uses for incident w
On-call work is billed to your organization as usage. You can cap it with a monthly spend limit. [Set a spend limit](/docs/claude-tag/admins/set-spend-limit) covers what counts tow
+8 −8 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-tag/admins/setup-oncall
±changed
+3−3
claude-docschanged
claude-tag/admins/setup-oncall
export const BetaNote = () => <Info>Claude Tag is in public beta. Features and behavior described here may change before general availability.</Info>;
<BetaNote />
> [!NOTE]
>
+3 −3 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+5−5
claude-docschanged
third-party/claude-desktop/configuration
```json theme={null} theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null} theme={null}
```json theme={null}
```json theme={null} theme={null} theme={null}
+5 −5 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/setup-oncall
+new page
+61−0
claude-docsnew page
claude-tag/admins/setup-oncall
No line of the body moved in this read.
+61 −0 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 5 Oct 2026 22:37 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+1−0
claude-docschanged
claude-tag/admins/restrict-access
* Open [on-call setup](/docs/claude-tag/admins/setup-oncall) at [`claude.ai/oncall`](https://claude.ai/oncall)
+1 −0 lines
Upstream edited 5 Oct 2026 22:07 UTC Recorded here 5 Oct 2026 22:37 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 5 Oct 2026 21:37 UTC
claude-code
agent-sdk/typescript
±changed
+22−0
claude-codechanged
agent-sdk/typescript
### `SDKSessionStateChangedMessage`
Emitted when Claude Code reports the session's state. To receive these messages, set [`CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1`](/docs/en/env-vars#variables). Claude Code can repor
The `state` field carries one of these values:
+22 −0 lines
Upstream edited 5 Oct 2026 21:14 UTC Recorded here 5 Oct 2026 21:37 UTC
claude-code
agent-sdk/python
±changed
+2−0
claude-codechanged
agent-sdk/python
Subtypes that have no dataclass of their own arrive as `SystemMessage`. To follow the session between turns, set [`CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1`](/docs/en/env-vars#varia
+2 −0 lines
Upstream edited 5 Oct 2026 21:14 UTC Recorded here 5 Oct 2026 21:37 UTC
claude-code
claude-tag
±changed
+6−6
claude-codechanged
claude-tag
No line of the body moved in this read.
+6 −6 lines
Recorded here 5 Oct 2026 21:07 UTC
claude-code
agent-sdk/python
±changed
+23−0
claude-codechanged
agent-sdk/python
3. **TypedDict class**: a typed schema whose `NotRequired` keys are left out of `required`.
* **Python 3.11 and later**: import `TypedDict` and `NotRequired` from `typing`.
* **Python 3.10**: `typing` has no `NotRequired`. Import `TypedDict` and `NotRequired` from `typing_extensions`, which the SDK installs on Python 3.10.
+23 −0 lines
Upstream edited 5 Oct 2026 20:58 UTC Recorded here 5 Oct 2026 21:07 UTC
claude-code
agent-sdk/custom-tools
±changed
+76−12
claude-codechanged
agent-sdk/custom-tools
| Make a parameter optional | Declare it optional in the schema and apply the default in the handler. See [Make a parameter optional](#make-a-parameter-optional). |
* **Input schema:** the arguments Claude must provide. In TypeScript this is always a [Zod schema](https://zod.dev/), and the handler's `args` are typed from it automatically. In P
* **Input schema:** the arguments the tool accepts, declared per language:
* **TypeScript**: a [Zod schema](https://zod.dev/). The handler's `args` take their types from it. Call `.describe()` on a field to give it a description Claude sees.
* **Python**: a dict mapping names to types, like `{"latitude": float}`, which the SDK converts to JSON Schema for you. Wrap a type in `Annotated`, like `{"latitude": Annotated[f
+76 −12 lines
Upstream edited 5 Oct 2026 20:58 UTC Recorded here 5 Oct 2026 21:07 UTC
mcp
docs/draft/tutorials/security/local-server-security
±changed
+9−9
mcpchanged
docs/draft/tutorials/security/local-server-security
[Authorization](/docs/draft/tutorials/security/authorization) and
[Security Best Practices](/docs/draft/tutorials/security/security_best_practices).
[Authorization](/docs/draft/tutorials/security/authorization.md) and
[Security Best Practices](/docs/draft/tutorials/security/security_best_practices.md).
([SEP-1024](/seps/1024-mcp-client-security-requirements-for-local-server-)),
+9 −9 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
docs/2026-07-28/tutorials/security/local-server-security
±changed
+9−9
mcpchanged
docs/2026-07-28/tutorials/security/local-server-security
[Authorization](/docs/2026-07-28/tutorials/security/authorization) and
[Security Best Practices](/docs/2026-07-28/tutorials/security/security_best_practices).
[Authorization](/docs/2026-07-28/tutorials/security/authorization.md) and
[Security Best Practices](/docs/2026-07-28/tutorials/security/security_best_practices.md).
([SEP-1024](/seps/1024-mcp-client-security-requirements-for-local-server-)),
+9 −9 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
docs/draft/tutorials/security/local-server-security
±changed
+45−47
mcpchanged
docs/draft/tutorials/security/local-server-security
<Note>
**Scope**: this guide is about servers running on a machine you (or your
organization's users) control — a laptop or workstation, typically launched
over stdio. Deploying and hardening remote or hosted servers is a different
topic with different controls.
+45 −47 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 20 Oct 2026 20:07 UTC
mcp
docs/2026-07-28/tutorials/security/local-server-security
±changed
+45−47
mcpchanged
docs/2026-07-28/tutorials/security/local-server-security
<Note>
**Scope**: this guide is about servers running on a machine you (or your
organization's users) control — a laptop or workstation, typically launched
over stdio. Deploying and hardening remote or hosted servers is a different
topic with different controls.
+45 −47 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 20 Oct 2026 20:07 UTC
mcp
docs/draft/tutorials/security/local-server-security
+new page
+439−0
mcpnew page
docs/draft/tutorials/security/local-server-security
No line of the body moved in this read.
+439 −0 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 5 Oct 2026 20:37 UTC
mcp
docs/2026-07-28/tutorials/security/local-server-security
+new page
+439−0
mcpnew page
docs/2026-07-28/tutorials/security/local-server-security
No line of the body moved in this read.
+439 −0 lines
Upstream edited 5 Oct 2026 20:31 UTC Recorded here 5 Oct 2026 20:37 UTC
claude-docs
claude-tag/users/group-dms
±changed
+1−1
claude-docschanged
claude-tag/users/group-dms
* **Settings.** A group DM has no [Configure page](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel), so you can't give it its own instructions, connections, or de
* **Settings.** A group DM has no [Configure page](/docs/claude-tag/users/good-habits#configure-claude-for-a-channel), so you can't give it its own instructions or connections.
+1 −1 lines
Upstream edited 5 Oct 2026 19:42 UTC Recorded here 5 Oct 2026 20:07 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+19−19
claude-docschanged
claude-tag/concepts/agent-identity
In Slack channels, and in [group DMs](#group-dms) that include Claude, Claude acts with its own service accounts, rather than as a specific user. An organization Owner [provisions
In Slack channels, and in [group DMs](#group-dms) that include Claude, Claude acts with its own service accounts, rather than as a specific user. An organization Owner [provisions
In one-to-one direct messages (DMs) between `@Claude` and a user who has connected a Claude account, the session runs on [the individual's own claude.ai account](#direct-message-ch
In one-to-one direct messages (DMs) between `@Claude` and a user who has connected a Claude account, the session runs on [the individual's own claude.ai account](#direct-message-ch
> How Claude behaves in channels (its standing instructions, plugins, and channel memory) is configured separately from its identity; see [custom instructions](/docs/claude-tag/adm
+19 −19 lines
Upstream edited 5 Oct 2026 19:41 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-tag/concepts/agent-identity
±changed
+17−17
claude-docschanged
claude-tag/concepts/agent-identity
In one-to-one direct messages (DMs) between `@Claude` and a user who has connected a Claude account, the session runs on [the individual's own claude.ai account](#direct-message-ch
In one-to-one direct messages (DMs) between `@Claude` and a user who has connected a Claude account, the session runs on [the individual's own claude.ai account](#direct-message-ch
> How Claude behaves in channels (its standing instructions, plugins, and channel memory) is configured separately from its identity; see [custom instructions](/docs/claude-tag/adm
> How Claude behaves in channels (its standing instructions, plugins, and channel memory) is configured separately from its identity; see [custom instructions](/docs/claude-tag/adm
A matching credential comes from the credential store, which keeps the credentials of the [connectors](/docs/claude-tag/admins/add-connections) an admin added. Once saved, a creden
+17 −17 lines
Upstream edited 5 Oct 2026 19:41 UTC Recorded here 22 Oct 2026 18:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.