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
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
5,287 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
20 Oct 2026
81 pages
+7391 −8428 lines
claude-code
admin-setup
±changed
+5−5
claude-codechanged
admin-setup
<Note>
SSO, SCIM provisioning, and seat assignment are configured at the Claude account level. See the [Claude Enterprise Administrator Guide](https://claude.com/resources/tutorials/cla
</Note>
> [!NOTE]
>
+5 −5 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
web-quickstart
±changed
+1−1
claude-codechanged
web-quickstart
* [Routines](/docs/en/routines): automate work on a schedule, via API call, or in response to GitHub events
* [Cloud scheduled tasks](/docs/en/routines): automate work on a schedule, via API call, or in response to GitHub events
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
tools-reference
±changed
+5−5
claude-codechanged
tools-reference
| `CronCreate` | Schedules a recurring or one-shot prompt within the current session. Tasks are session-scoped and restored on `--resume` or `--continue` if unexpired. See [schedul
| `CronDelete` | Cancels a scheduled task by ID | No |
| `CronList` | Lists all scheduled tasks in the session | No |
| `CronCreate` | Schedules a recurring or one-shot prompt within the current session. Tasks are session-scoped and restored on `--resume` or `--continue` if unexpired. See [session
| `CronDelete` | Cancels a session-scoped scheduled task by ID | No |
+5 −5 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
skills
±changed
+6−6
claude-codechanged
skills
[Cowork](https://claude.com/product/cowork) sessions and [cloud sessions](/docs/en/cloud-environments#what-carries-over-from-your-setup), including [routines](/docs/en/routines), d
If a skill exists only in `~/.claude/skills/` on your machine, Claude Code reports that the skill was not found when a [routine](/docs/en/routines) invokes it, because each routine
[Cowork](https://claude.com/product/cowork) sessions and [cloud sessions](/docs/en/cloud-environments#what-carries-over-from-your-setup), including [cloud scheduled tasks](/docs/en
+6 −6 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
* Scheduled tasks: [tasks that haven't expired](/docs/en/scheduled-tasks#limitations) are restored. Background Bash and monitor tasks aren't.
* Session-scoped scheduled tasks: [tasks that haven't expired](/docs/en/scheduled-tasks#limitations) are restored. Background Bash and monitor tasks aren't.
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+2−2
claude-codechanged
self-hosted-environments-configuration
Anthropic's control plane attaches its own MCP server, named Claude Code Remote, to cloud sessions. Claude uses the server's tools to schedule [routines](/docs/en/routines), start
Anthropic's control plane attaches its own MCP server, named Claude Code Remote, to cloud sessions. Claude uses the server's tools to create [cloud scheduled tasks](/docs/en/routin
When a person starts their own session, Claude Code also downloads the [skills enabled for their claude.ai account](/docs/en/skills#skills-in-cowork-and-cloud-sessions) into that s
When a person starts their own session, Claude Code also downloads the [skills enabled for their claude.ai account](/docs/en/skills#skills-in-cowork-and-cloud-sessions) into that s
+2 −2 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
self-hosted-environments
±changed
+5−3
claude-codechanged
self-hosted-environments
A self-hosted environment executes Claude Code cloud sessions on infrastructure your organization operates. A [cloud session](/docs/en/claude-code-on-the-web) is any session that r
A self-hosted environment executes Claude Code cloud sessions on infrastructure your organization operates. A [cloud session](/docs/en/claude-code-on-the-web) is any session that r
In a self-hosted environment, those same sessions execute inside your network. The developer experience is otherwise the same apart from the differences in [Availability and limita
* **Surfaces**: sessions started from [claude.ai/code](https://claude.ai/code), the mobile and desktop apps, [scheduled routines](/docs/en/routines), and the terminal, with [`claud
+5 −3 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
scheduled-tasks
±changed
+21−8
claude-codechanged
scheduled-tasks
Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do s
Tasks are session-scoped. When you resume with `--resume` or `--continue`, Claude Code restores tasks that haven't [expired](#seven-day-expiry), except those listed under [Limitati
Session-scoped scheduled tasks let Claude re-run a prompt automatically on an interval within a Claude Code session. Use them to poll a deployment, babysit a PR, check back on a lo
+21 −8 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
routines
±changed
+223−168
claude-codechanged
routines
# Automate work with routines
> Put Claude Code on autopilot. Define routines that run on a schedule, trigger on API calls, or react to GitHub events from cloud infrastructure.
# Automate work with scheduled tasks
+223 −168 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
platforms
±changed
+1−1
claude-codechanged
platforms
* [Scheduled tasks](/docs/en/scheduled-tasks): run prompts on a recurring schedule
* [Scheduling options](/docs/en/scheduled-tasks#compare-scheduling-options): run prompts on a recurring schedule
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
Run `/recap` to generate a summary on demand. It runs only when you ask for it yourself. When it arrives in a message relayed from a Slack, Teams, or project thread, or in a prompt
Run `/recap` to generate a summary on demand. It runs only when you ask for it yourself. When it arrives in a message relayed from a Slack, Teams, or project thread, you get a [not
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
* A [scheduled task](/docs/en/scheduled-tasks) firing, including a `/loop` iteration
* A [session-scoped scheduled task](/docs/en/scheduled-tasks) firing, including a `/loop` iteration
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
goal
±changed
+1−1
claude-codechanged
goal
The approaches above keep the current session running. You can also schedule work that runs independent of any open session, such as nightly tests or morning triage. See [schedul
The approaches above keep the current session running. You can also schedule work that runs independent of any open session, such as nightly tests or morning triage. See [schedul
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
glossary
±changed
+3−1
claude-codechanged
glossary
A Claude Code session that keeps running after you close your laptop, because it runs on cloud infrastructure instead of your machine: Anthropic-managed by default, or a [self-host
A Claude Code session that keeps running after you close your laptop, because it runs on cloud infrastructure instead of your machine. That infrastructure is Anthropic-managed by d
A session in your terminal, IDE, or the Desktop app with **Local** selected is a local session; to reach a local session from another device, use [Remote Control](#remote-control).
+3 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
github-enterprise-server
±changed
+1−1
claude-codechanged
github-enterprise-server
The session clones your repository from GHES and pushes changes back to a branch. Monitor progress at [claude.ai/code](https://claude.ai/code). See [Use Claude Code in the cloud](/
The session clones your repository from GHES and pushes changes back to a branch. Monitor progress at [claude.ai/code](https://claude.ai/code). See [Use Claude Code in the cloud](/
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
feature-availability
±changed
+2−2
claude-codechanged
feature-availability
* [Routines](/docs/en/routines) (`/schedule`)
* [Cloud scheduled tasks](/docs/en/routines) (`/schedule`)
| [Routines](/docs/en/routines) | ✓ | ✓ | ✓ | ✓ |
| [Cloud scheduled tasks](/docs/en/routines) | ✓ | ✓ | ✓ | ✓ |
+2 −2 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
errors
±changed
+15−13
claude-codechanged
errors
| `403` with `x-deny-reason: host_not_allowed` in a cloud or routine session | [Network](#host-not-allowed-in-a-cloud-session) |
| `403` with `x-deny-reason: host_not_allowed` in a cloud session or cloud scheduled task | [Network](#host-not-allowed-in-a-cloud-session) |
An Owner in your Team or Enterprise organization has turned off routines at the organization level. The error appears when you try to create or run a routine, for example from the
An Owner in your Team or Enterprise organization has turned off [cloud scheduled tasks](/docs/en/routines), formerly routines, at the organization level. The error appears when you
* Ask an Owner in your organization to enable the **Routines** toggle at [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code)
+15 −13 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
desktop-scheduled-tasks
±changed
+74−18
claude-codechanged
desktop-scheduled-tasks
The Desktop app's **Routines** page lets you create both local scheduled tasks and remote [routines](/docs/en/routines). A local task runs on your machine with direct access to you
The Desktop app's **Scheduled tasks** page lists both local scheduled tasks and [cloud scheduled tasks](/docs/en/routines), formerly routines:
* **Local task**: runs on your machine with direct access to your files and tools, but only fires while the app is open and your computer is awake
* **Cloud task**: runs even when your computer is off, and can also start on API calls or GitHub events
+74 −18 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
costs
±changed
+4−2
claude-codechanged
costs
* **Loops**: a row for each of the heaviest [`/loop` or other scheduled tasks](/docs/en/scheduled-tasks) that ran recently, ordered by total tokens, with a count of the rest. Claud
* **Loops**: a row for each of the heaviest [`/loop` or other session-scoped scheduled tasks](/docs/en/scheduled-tasks) that ran recently, ordered by total tokens, with a count of
* **What each row reports**: how often the task fires, how many times it ran, its total and per-run tokens, and when it last ran
* **Stopped and re-created loops**: Claude Code keys a row by the task's prompt, so a loop you stop and re-create stays one row
* **Scheduled tasks**: a [scheduled task](/docs/en/scheduled-tasks) fires on its interval even while the session is idle, sending your full context each time
+4 −2 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
| [Routines](/docs/en/routines) | Cloud, Anthropic-managed by default | Tasks that should run even when your computer is off. Can also trigger on API calls or GitHub events in addi
| [Cloud scheduled tasks](/docs/en/routines) | Cloud, Anthropic-managed by default | Tasks that should run even when your computer is off. Can also trigger on API calls or GitHub e
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
code-review-local
±changed
+2−2
claude-codechanged
code-review-local
* **From a scheduled task**: a [scheduled task](/docs/en/scheduled-tasks) with `/code-review` as its prompt runs the review
* **From a scheduled task**: a [session-scoped scheduled task](/docs/en/scheduled-tasks) with `/code-review` as its prompt runs the review
A scheduled task never launches the [cloud review](#escalate-to-ultrareview), so schedule `/code-review` without the `ultra` argument.
A session-scoped scheduled task never launches the [cloud review](#escalate-to-ultrareview), so schedule `/code-review` without the `ultra` argument.
+2 −2 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
cloud-environments
±changed
+17−6
claude-codechanged
cloud-environments
The same environments apply wherever you start a cloud session: the [Desktop app](/docs/en/desktop), the [Claude mobile app](/docs/en/mobile), your browser at [claude.ai/code](http
The same environments apply wherever you start a cloud session:
* The [Desktop app](/docs/en/desktop)
* The [Claude mobile app](/docs/en/mobile)
+17 −6 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
claude-projects
±changed
+17−13
claude-codechanged
claude-projects
In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, walk away, and find the threads that need you under [**Waiting on you**](#see-what
In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, and walk away. When you're back, you can find the threads that need you under [**W
* **One task that repeats on a schedule with no conversation around it**: "Post a dependency report every Monday." Create a [routine](/docs/en/routines) on its own.
* **One task that repeats on a schedule with no conversation around it**: "Post a dependency report every Monday." Create a [cloud scheduled task](/docs/en/routines) on its own.
* **The Overview pane**: where you [see all the threads at once](#see-what-needs-you-in-overview) and which of them need you. Its other tabs are **Library** for the files you added
+17 −13 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
claude-code-on-the-web
±changed
+5−3
claude-codechanged
claude-code-on-the-web
* **Routines**: [scheduled and triggered runs](/docs/en/routines) each run as a cloud session
* **Cloud scheduled tasks**: [scheduled and triggered runs](/docs/en/routines) each run as a cloud session
* **Organization IP allowlist**: cloud sessions call the Anthropic API from Anthropic-managed infrastructure, not your network, while sessions in a [self-hosted environment](/docs/
* **Organization IP allowlist**: cloud sessions call the Anthropic API from Anthropic-managed infrastructure, not your network, while sessions in a [self-hosted environment](/docs/
* **Code Review and scheduled tasks**: the same applies to [Code Review](/docs/en/code-review) and to [cloud scheduled tasks](/docs/en/routines) that run on Anthropic-hosted envi
+5 −3 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
channels
±changed
+1−1
claude-codechanged
channels
* [Scheduled tasks](/docs/en/scheduled-tasks) to poll on a timer instead of reacting to pushed events
* [Session-scoped scheduled tasks](/docs/en/scheduled-tasks) to poll on a timer instead of reacting to pushed events
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
| Claude publishes in a turn that a [scheduled task](/docs/en/scheduled-tasks) firing in your session started, rather than a prompt you typed | Asks before the first publish of eac
| Claude publishes in a turn that a [session-scoped scheduled task](/docs/en/scheduled-tasks) firing in your session started, rather than a prompt you typed | Asks before the first
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* A [routine](/docs/en/routines) runs a session on a schedule in the cloud, not in parallel on your machine.
* A [cloud scheduled task](/docs/en/routines) runs a session on a schedule in the cloud, not in parallel on your machine.
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
Some Claude Code features require a claude.ai account. [Cloud sessions](/docs/en/claude-code-on-the-web), [Routines](/docs/en/routines), [Code Review](/docs/en/code-review), [Remot
Some Claude Code features require a claude.ai account. [Cloud sessions](/docs/en/claude-code-on-the-web), [cloud scheduled tasks](/docs/en/routines), [Code Review](/docs/en/code-re
+1 −1 lines
Upstream edited 20 Oct 2026 02:25 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
permission-modes
±changed
+56−4
claude-codechanged
permission-modes
| [`dontAsk`](#allow-only-pre-approved-tools-with-dontask-mode) | File reads inside your working directories and pre-approved tools; anything that would prompt is denied | Locked-d
| [`dontAsk`](#allow-only-pre-approved-tools-with-dontask-mode) | File reads inside your working directories and pre-approved tools; anything that would prompt is denied, though a
* Pushing to any branch of the repository you're working in, including the default branch. A non-default branch whose name marks it as a deploy or publication target, such as `prod
* Pushing to any branch of the repository you're working in, including the default branch. A non-default branch whose name marks it as a deploy or publication target, such as `prod
+56 −4 lines
Upstream edited 20 Oct 2026 02:22 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
plugins/mods/reference
±changed
+9−21
claude-codechanged
plugins/mods/reference
<Note>
The complete reference is Claude Code's [TypeScript declarations for mods](https://github.com/anthropics/claude-code/blob/main/mods/types/claude-code.d.ts), which describe every
</Note>
> [!NOTE]
>
+9 −21 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/overview
±changed
+10−14
claude-codechanged
plugins/mods/overview
<Note>
Claude Code's existing [hooks](/docs/en/hooks) also run on events, as a shell command, HTTP request, or prompt you configure in a settings file. A mod's handlers are functions th
</Note>
> [!NOTE]
>
+10 −14 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/events
±changed
+4−6
claude-codechanged
plugins/mods/events
<Note>
A `tool.check` hook can also return `allow` or `ask`. In [plan mode](/docs/en/permissions#hook-approvals-in-plan-mode), for a call that isn't read-only, such as a file edit, your
</Note>
> [!NOTE]
>
+4 −6 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/admin
±changed
+7−9
claude-codechanged
plugins/mods/admin
<Note>
These cases are covered on other pages:
* **You haven't deployed managed settings before**: start with [Deploy managed settings](/docs/en/managed-settings)
* **You want to control which plugins users can install**: see [Manage plugins for your organization](/docs/en/plugins/org)
+7 −9 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
permissions
±changed
+44−56
claude-codechanged
permissions
<Frame>
<img src="https://mintcdn.com/claude-code/oa7CKjMeIChox26S/images/permission-prompt-bash-light.png?fit=max&auto=format&n=oa7CKjMeIChox26S&q=85&s=87585d008a29304873466399f7b476f6"
<img src="https://mintcdn.com/claude-code/oa7CKjMeIChox26S/images/permission-prompt-bash-dark.png?fit=max&auto=format&n=oa7CKjMeIChox26S&q=85&s=dd25688056898df1d1e4f1b5542bc978"
</Frame>
+44 −56 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
hooks-guide
±changed
+290−298
claude-codechanged
hooks-guide
<Tip>
This guide covers common use cases and how to get started. For full event schemas, JSON input/output formats, and advanced features like async hooks and MCP tool hooks, see the [
</Tip>
> [!TIP]
>
+290 −298 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
best-practices
±changed
+132−140
claude-codechanged
best-practices
<Tip>
Give Claude a check it can run: tests, a build, a screenshot to compare. It's the difference between a session you watch and one you walk away from.
</Tip>
> [!TIP]
>
+132 −140 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/permissions
±changed
+159−169
claude-codechanged
agent-sdk/permissions
<Steps>
<Step title="Hooks">
Run [hooks](/docs/en/agent-sdk/hooks) first. A hook can deny the call outright or pass it on. A hook that returns `allow` does not skip the deny and ask rules below; those are
</Step>
+159 −169 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/agent-loop
±changed
+178−184
claude-codechanged
agent-sdk/agent-loop
<img src="https://mintcdn.com/claude-code/ikqp3_70mqIahteV/images/agent-loop-diagram.svg?fit=max&auto=format&n=ikqp3_70mqIahteV&q=85&s=1c6e8f28d80dba14a7287419656f1237" className="
<img src="https://mintcdn.com/claude-code/_xqph1dUOslCOwsj/images/agent-loop-diagram-dark.svg?fit=max&auto=format&n=_xqph1dUOslCOwsj&q=85&s=afe723c52a324d3c61fa72fb02432ab6" classN
 or a Team or Enterprise [`/login`](/docs/en/authentication#authentication-precedence) as the sessio
+1 −1 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
plugins/mods/events
±changed
+6−4
claude-codechanged
plugins/mods/events
Hooks in your organization's [managed settings](/docs/en/server-managed-settings) run before any mod's `tool.call` hook, and a block from one of them is final.
Hooks in your organization's [managed settings](/docs/en/server-managed-settings) run before any mod's `tool.call` hook. When a managed hook blocks the call, no mod's `tool.call` h
A hook can return `allow`, `ask`, or `deny`, so it can also approve a call that a `PreToolUse` hook outside managed settings blocked. In [plan mode](/docs/en/permissions#hook-appro
<Note>
A `tool.check` hook can also return `allow` or `ask`. In [plan mode](/docs/en/permissions#hook-approvals-in-plan-mode), for a call that isn't read-only, such as a file edit, your
+6 −4 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
plugins/mods/admin
±changed
+12−8
claude-codechanged
plugins/mods/admin
* The user is signed in to Claude Code with a Team or Enterprise plan
A user who authenticates with an API key, or through Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, gets the guard only on a machine that has managed settin
* The session runs on [`/login` credentials](/docs/en/authentication#authentication-precedence) for a Team or Enterprise plan
+12 −8 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
permissions
±changed
+16−7
claude-codechanged
permissions
| `dontAsk` | Auto-denies every call that would otherwise prompt; file reads in your working directories and other actions that need no approval still run, as do tools pre-approved
| `dontAsk` | Auto-denies every call that would otherwise prompt, though a [mod](/docs/en/plugins/mods/overview) you installed can still approve some of those calls. File reads in
That precedence covers hooks in settings files and in a plugin's `hooks/hooks.json`. A [mod](/docs/en/plugins/mods/overview) you install that handles `tool.check` answers after the
* **Ask rules**: the mod can approve a call that an ask rule would prompt for
+16 −7 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
hooks-guide
±changed
+5−1
claude-codechanged
hooks-guide
A [mod](/docs/en/plugins/mods/overview) you install that handles `tool.check` can approve a call that your `PreToolUse` hook blocked, unless the hook is in managed settings. In pla
<Note>
If your machine has no [managed settings](/docs/en/settings#check-what-your-organization-enforces) and your session doesn't use [`/login` credentials](/docs/en/authentication#aut
In plan mode, a mod can approve such a blocked call only when it's read-only, so not a file edit. For the cases where a mod's approval doesn't get past your rules and hooks, see
+5 −1 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
headless
±changed
+3−1
claude-codechanged
headless
* **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs. Actions that need no approval in Manual mode still run, such as
* **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs, though a [mod](/docs/en/plugins/mods/overview) you installed ca
Actions that need no approval in Manual mode still run, such as file reads in your working directories and the [read-only command set](/docs/en/permissions#read-only-commands). A
+3 −1 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
Refine your prompt based on what goes wrong with the first 2-3 files, then run on the full set. The `--allowedTools` flag pre-approves the tools the migration needs, and [`--pe
Refine your prompt based on what goes wrong with the first 2-3 files, then run on the full set. The `--allowedTools` flag pre-approves the tools the migration needs. [`--permis
+1 −1 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
agent-sdk/permissions
±changed
+8−4
claude-codechanged
agent-sdk/permissions
If not resolved by any of the above, call your [`canUseTool` callback](/docs/en/agent-sdk/user-input) for a decision. In `dontAsk` mode, this step is skipped and the tool is de
If not resolved by any of the above, call your [`canUseTool` callback](/docs/en/agent-sdk/user-input) for a decision. In `dontAsk` mode, this step is skipped and the tool is de
Listed tools are approved, apart from the [actions no mode auto-approves](/docs/en/permission-modes#actions-no-mode-auto-approves) and [reads from network paths](/docs/en/permissio
Listed tools are approved, apart from the [actions no mode auto-approves](/docs/en/permission-modes#actions-no-mode-auto-approves) and [reads from network paths](/docs/en/permissio
+8 −4 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
claude-code
agent-sdk/agent-loop
±changed
+1−1
claude-codechanged
agent-sdk/agent-loop
| `"dontAsk"` | Never prompts. Tools pre-approved by [permission rules](/docs/en/settings-reference#permission-settings) run, and so do calls that need no approval in `default` mod
| `"dontAsk"` | Never prompts. Tools pre-approved by [permission rules](/docs/en/settings-reference#permission-settings) run, and so do calls that need no approval in `default` mod
+1 −1 lines
Upstream edited 20 Oct 2026 02:14 UTC Recorded here 20 Oct 2026 02:37 UTC
19 Oct 2026
61 pages
+15561 −15306 lines
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 19 Oct 2026 23:37 UTC
claude-code
gateways
±changed
+1−3
claude-codechanged
gateways
<Frame>
<img src="https://mintcdn.com/claude-code/-uq-4JE0W_JO5Er5/images/llm-gateway-flow.svg?fit=max&auto=format&n=-uq-4JE0W_JO5Er5&q=85&s=1c1a8dcc0cfcc3a58652cc8e28cd3e20" alt="Diagra
</Frame>
 that Claude Code sends, such as `x-claude-code-session-id`. The gateway do
+2 −0 lines
Upstream edited 19 Oct 2026 23:07 UTC Recorded here 19 Oct 2026 23:37 UTC
claude-code
claude-apps-gateway
±changed
+7−1
claude-codechanged
claude-apps-gateway
Claude Code uses one sign-in at a time: a gateway sign-in takes the place of a Claude for Teams or Enterprise login. Gateway sessions don't fetch the [server-managed settings](/d
The [gateway overview](/docs/en/gateways) covers what a gateway does and why you'd run one. Claude apps gateway is Anthropic's own gateway, built into the `claude` binary and teste
The [gateway overview](/docs/en/gateways) covers what a gateway does and why you'd run one. Claude apps gateway is Anthropic's own gateway, built into the `claude` binary and teste
+7 −1 lines
Upstream edited 19 Oct 2026 23:07 UTC Recorded here 19 Oct 2026 23:37 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 19 Oct 2026 22:37 UTC
claude-code
network-config
±changed
+19−19
claude-codechanged
network-config
<Note>
All environment variables shown on this page can also be configured in [`settings.json`](/docs/en/settings).
</Note>
> [!NOTE]
>
+19 −19 lines
Upstream edited 19 Oct 2026 22:14 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
* `API_TIMEOUT_MS` limits the wait for response headers. Where the first-byte deadline doesn't run, such as a Claude apps gateway session, set it below `300000`, which is 5 minutes
* `API_TIMEOUT_MS` limits the wait for response headers, not how long a response streams after them. Where the first-byte deadline doesn't run, such as a Claude apps gateway sessio
+1 −1 lines
Upstream edited 19 Oct 2026 22:14 UTC Recorded here 19 Oct 2026 22:37 UTC
claude-code
errors
±changed
+2−2
claude-codechanged
errors
| [`API_TIMEOUT_MS`](/docs/en/env-vars) | 600000 | Per-request timeout in milliseconds. Raise it for slow networks or proxies. It also caps how long Claude Code waits for response
| [`API_TIMEOUT_MS`](/docs/en/env-vars) | 600000 | Time in milliseconds that each request attempt has to receive its response headers. It doesn't limit how long a streaming respons
This can happen during periods of high load or when the model is generating a very large response. The default request timeout is 10 minutes.
The default request timeout is 10 minutes.
+2 −2 lines
Upstream edited 19 Oct 2026 22:14 UTC Recorded here 19 Oct 2026 22:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
* `API_TIMEOUT_MS`: per-request timeout on the Anthropic client, in milliseconds. Default `600000`. Applies to the main loop and all subagents.
* [`API_TIMEOUT_MS`](/docs/en/env-vars): how long each request attempt can wait for response headers, in milliseconds. It doesn't limit how long a streaming response runs after the
+1 −1 lines
Upstream edited 19 Oct 2026 22:14 UTC Recorded here 19 Oct 2026 22:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
* `API_TIMEOUT_MS`: per-request timeout on the Anthropic client, in milliseconds. Default `600000`. Applies to the main loop and all subagents.
* [`API_TIMEOUT_MS`](/docs/en/env-vars): how long each request attempt can wait for response headers, in milliseconds. It doesn't limit how long a streaming response runs after the
+1 −1 lines
Upstream edited 19 Oct 2026 22:14 UTC Recorded here 19 Oct 2026 22:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+8−1
claude-codechanged
self-hosted-environments-deploy
### Post a status message before a restart
Before a restart that will interrupt sessions, have an [Owner](/docs/en/cloud-environments#organization-shared-environments) post a status message on the environment from the [**Cl
Each session's child Claude Code process runs the runner's own binary, and the runner turns off auto-update inside the sessions it spawns, so every session runs the version you ins
+8 −1 lines
Upstream edited 19 Oct 2026 22:11 UTC Recorded here 19 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 19 Oct 2026 22:07 UTC
claude-code
vs-code
±changed
+139−147
claude-codechanged
vs-code
<img src="https://mintcdn.com/claude-code/-YhHHmtSxwr7W8gy/images/vs-code-extension-interface.jpg?fit=max&auto=format&n=-YhHHmtSxwr7W8gy&q=85&s=300652d5678c63905e6b0ea9e50835f8" al
 for the chat panel. To run `claude` in VS Code's integrated terminal, you also need the [standalone CLI ins
</Tip>
+139 −147 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/mods/interface
±changed
+280−304
claude-codechanged
plugins/mods/interface
<img src="https://mintcdn.com/claude-code/dgiVO_Od1X1faduV/images/mods-screen-map.svg?fit=max&auto=format&n=dgiVO_Od1X1faduV&q=85&s=5fda26b6609c62b68c6f9e528c1590ea" className="dar
<img src="https://mintcdn.com/claude-code/dgiVO_Od1X1faduV/images/mods-screen-map-dark.svg?fit=max&auto=format&n=dgiVO_Od1X1faduV&q=85&s=5b4161581a1bd2c0450b0c8b57bc1225" className
 can draw in the chat panel. Drawing requires extension version 2.1.299 or later and a session that [fetches feature f
A plugin that contains a [mod](/docs/en/plugins/mods/overview) can draw in the chat panel. Drawing requires extension version 2.1.299 or later. A session that [doesn't fetch featur
+1 −1 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
plugins/mods/troubleshoot
±changed
+1−1
claude-codechanged
plugins/mods/troubleshoot
* **The VS Code session doesn't fetch feature flags**: drawing in the chat panel requires it. Sessions on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or th
* **The extension is older than 2.1.304 and the session doesn't fetch feature flags**: update the extension, or run `claude` in VS Code's integrated terminal instead. Sessions on A
+1 −1 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
plugins/mods/reference
±changed
+1−1
claude-codechanged
plugins/mods/reference
Rendering in the VS Code extension requires extension version 2.1.299 or later and a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching
Rendering in the VS Code extension requires extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetch
+1 −1 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
plugins/mods/overview
±changed
+1−1
claude-codechanged
plugins/mods/overview
| The VS Code extension's chat panel | Yes | Yes, with extension version 2.1.299 or later, in a session that [fetches feature flags](/docs/en/env-vars#features-that-need-feature-fl
| The VS Code extension's chat panel | Yes | Yes, with extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#features-that-need-feature
+1 −1 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
plugins/mods/interface
±changed
+1−1
claude-codechanged
plugins/mods/interface
In the VS Code extension, what a mod draws appears in the chat panel with extension version 2.1.299 or later, in a session that [fetches feature flags](/docs/en/env-vars#features-t
In the VS Code extension, what a mod draws appears in the chat panel with extension version 2.1.299 or later. A session that [doesn't fetch feature flags](/docs/en/env-vars#feature
+1 −1 lines
Upstream edited 19 Oct 2026 21:54 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
changelog
±changed
+11027−11027
claude-codechanged
changelog
No line of the body moved in this read.
+11027 −11027 lines
Upstream edited 19 Oct 2026 21:50 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
changelog
±changed
+90−0
claude-codechanged
changelog
<Update label="2.1.304" description="October 19, 2026">
**Added**
* Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin
+90 −0 lines
Upstream edited 19 Oct 2026 21:50 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
Claude Code fires hook events at specific points in its lifecycle. When an event fires, Claude Code runs all matching hooks in parallel; see [Hook handler fields](/docs/en/hooks#ho
Claude Code fires hook events at specific points in its lifecycle. When an event fires, Claude Code runs the matching hooks in parallel; see [Hook handler fields](/docs/en/hooks#ho
+1 −1 lines
Upstream edited 19 Oct 2026 21:49 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
hooks
±changed
+3−1
claude-codechanged
hooks
All matching hooks run in parallel. If you define the same handler in more than one settings file, it runs once. A plugin's or skill's copy of the same handler stays separate.
When an event fires, its matching hooks run in parallel. If more than 12 of them are prompt or agent hooks, 12 of those run at once and the rest start as running ones finish. Each
If you define the same handler in more than one settings file, it runs once. A plugin's or skill's copy of the same handler stays separate.
+3 −1 lines
Upstream edited 19 Oct 2026 21:49 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
claude-apps-gateway-config
±changed
+4−0
claude-codechanged
claude-apps-gateway-config
<Note>
If you set `forward_user_identity` on an Amazon Bedrock upstream, the gateway exits at startup with `Unrecognized key(s) in object: 'forward_user_identity'`. If your proxy sits i
</Note>
+4 −0 lines
Upstream edited 19 Oct 2026 21:49 UTC Recorded here 19 Oct 2026 22:07 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
There is no service-token flow for unattended pipelines. Gateway sign-in always runs the browser device flow, so a CI job with no developer to approve the sign-in can't authenticat
There is no service-token flow for unattended pipelines. Gateway sign-in always runs the browser device flow, so a CI job with no developer to approve the sign-in can't authenticat
+1 −1 lines
Upstream edited 19 Oct 2026 21:49 UTC Recorded here 19 Oct 2026 22:07 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 19 Oct 2026 21:37 UTC
claude-code
claude-directory
±changed
+6−3
claude-codechanged
claude-directory
Pass `--all` instead of a path to purge state for every project at once, which deletes `history.jsonl` outright rather than filtering it. Pass `-i` to step through the deletion pla
Other options:
* Pass `--all` instead of a path to purge state for every project at once, which deletes `history.jsonl` outright rather than filtering it.
* Pass `-i` to step through the deletion plan one item at a time.
+6 −3 lines
Upstream edited 19 Oct 2026 21:28 UTC Recorded here 19 Oct 2026 21:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `trigger`: What caused the change. One of `"shift_tab"`, `"exit_plan_mode"`, `"auto_gate_denied"`, or `"auto_opt_in"`. Absent for some changes, such as when the SDK sets the perm
* `trigger`: What caused the change, for example `"shift_tab"`, `"exit_plan_mode"`, or `"auto_gate_denied"`. Absent for some changes, such as when the SDK sets the permission mode
+1 −1 lines
Upstream edited 19 Oct 2026 21:27 UTC Recorded here 19 Oct 2026 21:37 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 19 Oct 2026 20:37 UTC
claude-code
claude-apps-gateway-config
±changed
+11−0
claude-codechanged
claude-apps-gateway-config
#### Send cumulative metrics
If your collector accepts only cumulative metrics, set [`OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE`](/docs/en/monitoring-usage#common-configuration-variables) to `cumulativ
* **Terminal sessions**: in the `env` block under a policy's [`cli` or `code` key](#choose-cli-or-code)
+11 −0 lines
Upstream edited 19 Oct 2026 20:30 UTC Recorded here 19 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 19 Oct 2026 20:07 UTC
claude-code
keybindings
±changed
+3−1
claude-codechanged
keybindings
<Note>Changes to the keybindings file are automatically detected and applied without restarting Claude Code.</Note>
> [!NOTE]
>
> Changes to the keybindings file are automatically detected and applied without restarting Claude Code.
+3 −1 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
fullscreen
±changed
+7−9
claude-codechanged
fullscreen
<Note>
Fullscreen rendering is a [research preview](#research-preview). Whether you [start in fullscreen or in the classic renderer](#fullscreen-by-default) depends on your setup. Run `
</Note>
> [!NOTE]
>
+7 −9 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
vs-code
±changed
+22−8
claude-codechanged
vs-code
Click any conversation to resume it with the full message history. If the conversation is already open in another tab of the current window, clicking it switches to that tab. If th
Click any conversation to resume it. If the conversation is already open in another tab of the current window, clicking it switches to that tab. If the conversation opens with no m
* **To open it anyway**: click **Open it anyway** or pick the conversation from Session history. If it opens and the panel keeps working, it comes back after later reloads as usual
* **To open it anyway**: click **Open it anyway** or pick the conversation from Session history. Once the conversation finishes opening, it [comes back after later reloads as usual
* **If the panel stops responding while the conversation loads**: reload the window. A new chat opens.
+22 −8 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
tools-reference
±changed
+11−6
claude-codechanged
tools-reference
| `ShareOnboardingGuide` | Uploads `ONBOARDING.md` and returns a share link teammates can open in Claude Code. Called from `/team-onboarding` after the guide is written. Available
| `ShareOnboardingGuide` | Uploads `ONBOARDING.md` and returns a share link teammates can open in Claude Code. Called from `/team-onboarding` after the guide is written. Available
The Agent tool spawns a subagent in a separate context window. The subagent works through its task autonomously, then returns its result to the parent conversation. The parent does
The Agent tool spawns a subagent in a separate context window. The subagent works through its task autonomously, then returns its result to the parent conversation. The parent does
+11 −6 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
sessions
±changed
+3−2
claude-codechanged
sessions
* Conversation history: the full history, including tool calls and results. A tool that was still running when the previous process ended, for example in a crash, doesn't finish or
* Conversation history: the messages, tool calls, and results. If the session was [compacted](/docs/en/context-window#what-survives-compaction), the conversation opens at a `Conver
* Interrupted tool calls: a tool that was still running when the previous process ended, for example in a crash, doesn't finish or get rerun when you resume. Claude sees the call m
| From the desktop app | Rename a session in the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions) |
| From the desktop app | Rename a session in the [desktop app](/docs/en/desktop#organize-and-find-sessions) |
+3 −2 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
monitoring-usage
±changed
+41−4
claude-codechanged
monitoring-usage
| `decision` | `accept` or `reject` | |
| `source` | Decision source, matching the [Tool decision event](#tool-decision-event) | |
| `decision` | `accept`, `reject`, or `cancelled`, where `cancelled` means Claude Code stopped waiting for a permission decision on the tool call and didn't run it | |
| `source` | For an `accept` or `reject`, where the decision came from, such as `config`, `hook`, or `user_temporary`, with the meanings given under the [Tool decision event](#tool
+41 −4 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
keybindings
±changed
+3−4
claude-codechanged
keybindings
Two contexts bind more keys to these actions by default:
* **`AbovePrompt`**: Right and Left also run `abovePrompt:next` and `abovePrompt:previous`, and Space also runs `abovePrompt:press`
* **`AbovePromptInput`**: Down and Up also run `abovePrompt:next` and `abovePrompt:previous`
In the [`AbovePrompt` context](#contexts), Right and Left also run `abovePrompt:next` and `abovePrompt:previous` by default, and Space also runs `abovePrompt:press`.
+3 −4 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
hooks
±changed
+2−2
claude-codechanged
hooks
| `status` | string | `"completed"` | `"completed"` for foreground subagents, `"async_launched"` for background subagents. Subagents run in the background by default, so an Agent c
| `status` | string | `"completed"` | `"completed"` for foreground subagents, `"async_launched"` for background subagents. For which subagents run each way, see [Run subagents in f
| `cache_ttl` | string | [Prompt cache lifetime](/docs/en/prompt-caching#cache-lifetime) Claude Code requests for this session: `"5m"` or `"1h"` |
| `cache_ttl` | string | [Prompt cache lifetime](/docs/en/prompt-caching#cache-lifetime) of the main conversation at the time of this switch: `"5m"` or `"1h"` |
+2 −2 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
You can scroll back to the start of the session even after [compaction](/docs/en/context-window#what-survives-compaction). Claude continues working from the compaction summary, but
If you close a [compacted](/docs/en/context-window#what-survives-compaction) session and [resume](/docs/en/sessions#what-a-resumed-session-restores) it, scrolling up stops at the `
+1 −1 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
agent-view
±changed
+8−0
claude-codechanged
agent-view
<h3 id="carried-into-this-session-and-not-resumed">
The conversation says a background agent `was carried into this session and not resumed`
</h3>
+8 −0 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
agent-sdk/agent-loop
±changed
+2−2
claude-codechanged
agent-sdk/agent-loop
| **Tool definitions** | Every request; MCP schemas deferred by default | Built-in tool schemas load every request. [Tool search](/docs/en/agent-sdk/mcp#mcp-tool-search) defers MCP
| **Tool definitions** | Every request for core built-in tools such as Bash, Read, and Edit; on demand for MCP tools and other built-in tools, which [tool search](/docs/en/agent-sd
* **Use subagents for subtasks.** Each subagent starts with a fresh conversation (no prior message history, though it does load its own system prompt and project-level context like
* **Use subagents for subtasks.** A subagent returns only its final response, so your main agent's context grows by a summary, not by the subtask's transcript.
+2 −2 lines
Upstream edited 19 Oct 2026 19:52 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
errors
±changed
+2−1
claude-codechanged
errors
* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `CronCreate`, remove the entry. To keep the tool, [turn fork mode off](/docs/en/sub-agen
* For a tool that [background subagents drop](/docs/en/sub-agents#available-tools), such as `CronCreate`, remove the entry
* To keep a tool such as `CronCreate` instead, [let Claude wait for the subagent](/docs/en/sub-agents#let-claude-wait-for-a-subagent), since a subagent Claude waits for runs in the
+2 −1 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
agent-teams
±changed
+13−17
claude-codechanged
agent-teams
<Warning>
Agent teams are experimental and disabled by default. Enable them by setting `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in your [settings.json](/docs/en/settings) or environment. W
</Warning>
> [!WARNING]
>
+13 −17 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/subagents
±changed
+516−530
claude-codechanged
agent-sdk/subagents
<CodeGroup>
```python Python theme={null}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, AgentDefinition
+516 −530 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
sub-agents
±changed
+45−29
claude-codechanged
sub-agents
| `background` | No | Set to `true` to keep this subagent in the background even when Claude asks to run it in the foreground. Where [fork mode](#turn-fork-mode-on-or-off) is on, C
| `background` | No | Set to `true` to keep this subagent in the background even when Claude asks to wait for it. By default, subagents Claude spawns from the main conversation alr
For each subagent Claude spawns with the Agent tool, Claude Code picks foreground or background from the first of these cases that applies:
* If an in-process [agent team](/docs/en/agent-teams#limitations) teammate spawned the subagent, Claude Code runs it in the foreground. Claude Code refuses with an error to spawn a
+45 −29 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
* **No background subagents from in-process teammates**: an in-process teammate's own subagents run in the foreground, because a teammate's background work can't outlive the lead's
* **No background subagents from in-process teammates**: an in-process teammate's own subagents run in the foreground, because a teammate's background work can't outlive the lead's
+1 −1 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
agent-sdk/subagents
±changed
+30−3
claude-codechanged
agent-sdk/subagents
Subagents run in the background by default. An Agent tool call that omits the [`run_in_background`](/docs/en/sub-agents#run-subagents-in-foreground-or-background) input launches a
Subagents can also spawn subagents of their own. To limit how deep that nesting goes, how many subagents run at once, and how much a query spends, see [Cap subagent depth, concurre
#### Choose whether Claude waits for subagents
+30 −3 lines
Upstream edited 19 Oct 2026 19:49 UTC Recorded here 19 Oct 2026 20:07 UTC
claude-code
code-review-setup
±changed
+29−31
claude-codechanged
code-review-setup
<Steps>
<Step title="Click the Allow code review switch">
Go to the **Code review** section of [**Admin settings > Claude Code**](https://claude.ai/admin-settings/claude-code#code-review) and click the **Allow code review** switch.
**1. Click the Allow code review switch**
If Code Review turns on right away with no dialog, your organization already has the Claude GitHub App linked or repositories added. Go to [Add more repositories](#add-more-rep
+29 −31 lines
Upstream edited 19 Oct 2026 19:47 UTC Recorded here 20 Oct 2026 18:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.