HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
ReadSourcePageWhatLines
29 Aug 2026
73 pages
+1340 −727 lines
claude-code
sessions
±changed
+8−7
claude-codechanged
sessions
| To | Set | Where |
| ------------------------------------------------------------------------------- | --------------------------------------------------------------- | ------------------------- |
| Move storage off `~/.claude` | [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) | Environment variable
| [Name the `<project>` directory yourself](#name-the-project-directory-yourself) | [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/env-vars) | Environment variable
| Change the 30-day retention | [`cleanupPeriodDays`](/docs/en/settings-reference#cleanupperioddays) | `settings.json`
+8 −7 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
server-managed-settings
±changed
+2−2
claude-codechanged
server-managed-settings
* The cache at `~/.claude/remote-settings.json` stores the salvaged payload with invalid entries removed. The raw invalid payload is never persisted.
* When no field in the payload can be salvaged, Claude Code rejects the payload, keeps the last-accepted cached settings, and writes `Remote settings: Settings validation failed -
* The cache at `~/.claude/remote-settings.json` stores the salvaged payload with invalid entries removed, apart from invalid `cleanupPeriodDays` and `desktopSessionCleanupPeriodDay
* When no field in the payload can be salvaged and the payload isn't only those retention keys, Claude Code rejects the payload, keeps the last-accepted cached settings, and writes
+2 −2 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
prompt-caching
±changed
+3−3
claude-codechanged
prompt-caching
You can also require this confirmation or skip it with a [PreModelSwitch hook](/docs/en/hooks#premodelswitch-decision-control).
If you enable one mid-session, Claude Code changes the tool set at most once in that session. Once Claude Code has had a language server available, it keeps the LSP tool in the req
When you disable a plugin you enabled earlier in the session, Claude Code restores the previous request shape, apart from the [LSP tool](#code-intelligence-plugins), which Claude C
+3 −3 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
plugins-reference
±changed
+2−0
claude-codechanged
plugins-reference
| `PreModelSwitch` | Before Claude Code applies a model switch that you or a client requested. Can block the switch
| `PostModelSwitch` | After the session's model changes, including changes Claude Code makes on its own, such as restoring the model when you resume a session
+2 −0 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
overview
±changed
+5−5
claude-codechanged
overview
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={n
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} th
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={
+5 −5 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
monitoring-usage
±changed
+2−1
claude-codechanged
monitoring-usage
* `"settings_invalid_key_set"`: Settings have validation errors and `cleanupPeriodDays` is explicitly set, so falling back to the default could delete files the setting was meant
* `"settings_invalid_key_set"`: Settings have validation errors and `cleanupPeriodDays` or `desktopSessionCleanupPeriodDays` is explicitly set, so falling back to the default cou
* `transcripts_exempted_desktop`: Number of transcripts past the retention period that the sweep kept under the [Claude Desktop and Cowork rule](/docs/en/claude-directory#cleaned-u
+2 −1 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
managed-settings
±changed
+20−0
claude-codechanged
managed-settings
## Turn telemetry off for your organization
Claude Code sends Anthropic operational [telemetry](/docs/en/data-usage#telemetry-services) by default on sessions that use the Anthropic API, whether directly, through an LLM gate
```json theme={null}
+20 −0 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
hooks-guide
±changed
+31−22
claude-codechanged
hooks-guide
| `PreModelSwitch` | Before Claude Code applies a model switch that you or a client requested. Can block the switch
| `PostModelSwitch` | After the session's model changes, including changes Claude Code makes on its own, such as restoring the model when you resume a session
* **Exit 0**: the hook reports no objection through its exit code. For a `PreToolUse` hook this doesn't approve the tool call: the normal [permission flow](/docs/en/permissions) st
* **Exit 0**: your hook reports no objection through its exit code.
* For a `PreToolUse` hook this doesn't approve the tool call: the normal [permission flow](/docs/en/permissions) still applies.
+31 −22 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
hooks
±changed
+276−51
claude-codechanged
hooks
<img src="https://mintcdn.com/claude-code/jhXrDR5TrSZ5hgXM/images/hooks-lifecycle.svg?fit=max&auto=format&n=jhXrDR5TrSZ5hgXM&q=85&s=3ca47113d5956460e6e4611b8dbc63b7" className=
<img src="https://mintcdn.com/claude-code/jhXrDR5TrSZ5hgXM/images/hooks-lifecycle-dark.svg?fit=max&auto=format&n=jhXrDR5TrSZ5hgXM&q=85&s=0ffe95014d33411538778a66e4173973" class
<img src="https://mintcdn.com/claude-code/x7pO8l4XcvAXCoVc/images/hooks-lifecycle.svg?fit=max&auto=format&n=x7pO8l4XcvAXCoVc&q=85&s=81b9256c1bbe8832553485f5d9e9c746" className=
+276 −51 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `DISABLE_TELEMETRY` | Set to any non-empty value, such as `1`, to opt out of telemetry. **Setting it to `0` or `false` still opts out**, unlik
| `DISABLE_TELEMETRY` | Set to any non-empty value, such as `1`, to opt out of telemetry. **Setting it to `0` or `false` still opts out**, unlik
+1 −1 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
discover-plugins
±changed
+1−1
claude-codechanged
discover-plugins
Code intelligence plugins enable Claude Code's built-in LSP tool, giving Claude the ability to jump to definitions, find references, and see type errors immediately after edits. Th
Code intelligence plugins enable Claude Code's built-in LSP tool, giving Claude the ability to jump to definitions, find references, and see type errors immediately after edits. Th
+1 −1 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
data-usage
±changed
+2−0
claude-codechanged
data-usage
Transcripts of sessions started or most recently continued in Claude Desktop or Cowork are [exempt from that limit by default](/docs/en/claude-directory#cleaned-up-automatically)
+2 −0 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
claude-directory
±changed
+8−3
claude-codechanged
claude-directory
Claude Code makes four exceptions to this sweep:
Session files in `sessions/`, auto memory, and Claude Desktop and Cowork transcripts each follow their own retention rule:
* **Claude Desktop and Cowork transcripts**: Claude Code keeps the transcript of a session you started or most recently continued in Claude Desktop or Cowork at any age. To give th
Claude Code skips the sweep entirely in these cases:
+8 −3 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
agent-sdk/typescript
±changed
+58−0
claude-codechanged
agent-sdk/typescript
| "PreModelSwitch"
| "PostModelSwitch"
| PreModelSwitchHookInput
| PostModelSwitchHookInput
};
+58 −0 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
agent-sdk/hooks
±changed
+5−2
claude-codechanged
agent-sdk/hooks
| [`PreModelSwitch`](/docs/en/hooks#premodelswitch) | No | Yes | A requested model switch, before it happens (can block)
| [`PostModelSwitch`](/docs/en/hooks#postmodelswitch) | No | Yes | The session's model changes, including an automatic fallback
Claude Code runs each callback with a timeout, which you set in seconds with the `timeout` field on its `HookMatcher`. When you don't set one, Claude Code uses the event's default:
Claude Code runs each callback with a timeout, which you set in seconds with the `timeout` field on its `HookMatcher`. When you don't set one, Claude Code uses the event's default:
* Other events, such as `Notification` and `PreCompact`: Claude Code logs the failure and continues.
+5 −2 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
admin-setup
±changed
+4−2
claude-codechanged
admin-setup
Server-managed settings reach devices at authentication time and refresh hourly during active sessions, with no endpoint infrastructure. Delivery through the claude.ai admin consol
Claude Code fetches server-managed settings at startup and refreshes them hourly during the session, with no endpoint infrastructure to deploy. Delivery through the claude.ai admin
* Verify by running `/status` inside a WSL session: the `Setting sources` line should show `Enterprise managed settings` with the Windows source you deployed, `(HKLM)` or `(file)`.
* Verify by running `/status` inside a WSL session and reading the `Setting sources` line. Claude Code names only the [managed source it selected](/docs/en/server-managed-settings#
* **In a session that [fetches server-managed settings](/docs/en/server-managed-settings#platform-availability) and receives any keys**: `Enterprise managed settings (remote)`, b
+4 −2 lines
Recorded here 29 Aug 2026 16:07 UTC
claude-code
web-quickstart
±changed
+6−2
claude-codechanged
web-quickstart
If you already use the GitHub CLI (`gh`), you can set up Claude Code on the web without opening a browser. This requires the [Claude Code CLI](/docs/en/quickstart). `/web-setup` re
If you already use the GitHub CLI (`gh`), you can set up Claude Code on the web without opening a browser. This requires the [Claude Code CLI](/docs/en/quickstart). When you run `/
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled cannot use `/web-setup` or other cloud session features. If the GitHub CLI isn't installed or authe
Organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled cannot use `/web-setup` or other cloud session features. If the GitHub CLI isn't installed or isn't
### `/web-setup` warns that your token doesn't have the `workflow` scope
+6 −2 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
* **`/clear`**: start fresh with an empty context. Claude Code saves the previous conversation; resume it with `/resume`, or, in the same Claude Code process, from [the rewind menu
* **`/clear`**: start fresh with an empty context. Claude Code saves the previous conversation; resume it with `/resume`, or, in the same Claude Code process, from [the rewind menu
+1 −1 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
routines
±changed
+2−2
claude-codechanged
routines
Routines are available on Pro, Max, Team, and Enterprise plans with [Claude Code on the web](/docs/en/claude-code-on-the-web) enabled. Create and manage them at [claude.ai/code/rou
Routines are available on Pro, Max, Team, and Enterprise plans. Create and manage them at [claude.ai/code/routines](https://claude.ai/code/routines), or from the CLI with `/schedul
Create a routine from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud accou
Create a routine from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud accou
+2 −2 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
To prevent developers from using auto mode, set `disableAutoMode` to `"disable"` in [managed settings](/docs/en/managed-settings). This removes `auto` from the `Shift+Tab` cycle, a
To prevent developers from using auto mode, set `disableAutoMode` to `"disable"` in [managed settings](/docs/en/managed-settings). This removes `auto` from the `Shift+Tab` cycle, a
+1 −1 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
hooks
±changed
+17−2
claude-codechanged
hooks
When `source` is `"resume"` or `"fork"` and the transcript contains at least one response from Claude, SessionStart hooks also receive the four fields below. Your hook can use them
| Field | Description
| :---------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------
| `seconds_since_last_response` | Wall-clock seconds since the last response in the resumed transcript
+17 −2 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
desktop-scheduled-tasks
±changed
+1−1
claude-codechanged
desktop-scheduled-tasks
On Claude Desktop before 1.1.5368, local scheduled tasks aren't available. In the [**Code** tab](/docs/en/desktop), click **Routines** in the sidebar, then click **New routine** an
On Claude Desktop before 1.1.5368, local scheduled tasks aren't available. In the [**Code** tab](/docs/en/desktop), click **Routines** in the sidebar or in the sidebar's **More** m
+1 −1 lines
Recorded here 29 Aug 2026 15:37 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
On Windows, removing a worktree doesn't delete files outside it. If a folder inside the worktree is really a link to somewhere else, such as an NTFS junction or a directory symlink
On Windows, removing a worktree doesn't delete files outside it. If a folder inside the worktree is a link to somewhere else, such as an NTFS junction or a directory symlink, Claud
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
workflows
±changed
+1−1
claude-codechanged
workflows
A dynamic workflow is a JavaScript script that orchestrates [subagents](/docs/en/sub-agents) at scale. Claude writes the script for the task you describe, and a runtime executes it
A dynamic workflow is a JavaScript script that orchestrates many [subagents](/docs/en/sub-agents) at once. Claude writes the script for the task you describe, and a runtime execute
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
A session can make at most 200 WebSearch calls, counted across the main conversation and every [subagent](/docs/en/sub-agents) it spawns, so searches made by parallel research fan-
A session can make at most 200 WebSearch calls, counted across the main conversation and every [subagent](/docs/en/sub-agents) it spawns, so searches made by parallel research fan-
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
third-party-integrations
±changed
+3−1
claude-codechanged
third-party-integrations
### Leverage MCP for integrations
<h3 id="leverage-mcp-for-integrations">
Use MCP for integrations
</h3>
+3 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
Skills can bundle and run scripts in any language, giving Claude capabilities beyond what's possible in a single prompt. One powerful pattern is generating visual output: interacti
Skills can bundle and run scripts in any language, giving Claude capabilities beyond what's possible in a single prompt. One pattern is generating visual output: interactive HTML f
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
self-hosted-environments-identity
±changed
+1−1
claude-codechanged
self-hosted-environments-identity
A [self-hosted environment](/docs/en/self-hosted-environments) lets [Claude Code on the web](/docs/en/claude-code-on-the-web) sessions run on infrastructure you operate instead of
A [self-hosted environment](/docs/en/self-hosted-environments) lets [Claude Code on the web](/docs/en/claude-code-on-the-web) sessions run on infrastructure you operate instead of
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
sandboxing
±changed
+2−2
claude-codechanged
sandboxing
The sandboxed Bash tool leverages operating system security primitives:
The sandboxed Bash tool uses operating system security primitives:
* **Privilege escalation via Unix sockets**: the `allowUnixSockets` configuration can inadvertently grant access to powerful system services that could lead to sandbox bypasses. Fo
* **Privilege escalation via Unix sockets**: the `allowUnixSockets` configuration can inadvertently grant access to system services that could lead to sandbox bypasses. For example
+2 −2 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
overview
±changed
+6−6
claude-codechanged
overview
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={n
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} th
```batch theme={null}
+6 −6 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
The event data provides detailed insights into Claude Code interactions:
The event data describes each Claude Code interaction in detail:
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
managed-mcp
±changed
+1−1
claude-codechanged
managed-mcp
`managed-mcp.json` is a standalone file, so it cannot be delivered through [server-managed settings](/docs/en/server-managed-settings). Any process that can write to a system path
`managed-mcp.json` is a standalone file, so it cannot be delivered through [server-managed settings](/docs/en/server-managed-settings). Any process that can write to a system path
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
jetbrains
±changed
+1−1
claude-codechanged
jetbrains
Enabling **Accept connections from all network interfaces** makes the IDE MCP port reachable from your local network. Connections still require the auth token from the lock file,
Enabling **Accept connections from all network interfaces** makes the IDE MCP port reachable from your local network. Connections still require the auth token from the lock file,
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
gitlab-ci-cd
±changed
+1−1
claude-codechanged
gitlab-ci-cd
Claude Code enables powerful CI/CD workflows that transform how you work with code:
In a GitLab pipeline, Claude Code can:
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* If the file genuinely lives on a network share, it's outside the session's local workspace; edit it from a regular interactive session instead
* If the file is on a network share rather than a local file spelled with a network path, it's outside the session's local workspace; edit it from a regular interactive session ins
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
This last step happens on a developer machine, not the server. Set `forceLoginMethod` to `"gateway"` and `forceLoginGatewayUrl` to your gateway's `public_url` in that machine's
This last step happens on a developer machine, not the server. Set `forceLoginMethod` to `"gateway"` and `forceLoginGatewayUrl` to your gateway's `public_url` in that machine's
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
champion-kit
±changed
+16−16
claude-codechanged
champion-kit
| Activity | Time per week | Guidance
| --------------------------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------
| Posting wins and prompts | About 15 minutes | Capture these in the moment with a screenshot and one or two sentences; avoid turning them into formal write-ups.
| Answering questions in a shared channel | About 20 minutes | Answer publicly once, then link back to that answer when the question recurs.
| Hosting a weekly show-and-tell thread | About 5 minutes | You post the opening prompt; the team supplies the content.
+16 −16 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
best-practices
±changed
+2−2
claude-codechanged
best-practices
Since context is your fundamental constraint, subagents are one of the most powerful tools available. When Claude researches a codebase it reads lots of files, all of which consume
Since context is your fundamental constraint, use subagents to keep research out of it. When Claude researches a codebase it reads lots of files, all of which consume your context.
<Step title="Test on a few files, then run at scale">
<Step title="Test on a few files, then run on all of them">
+2 −2 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
An artifact is a capture of work, not an application. It is one self-contained page with no backend, so it can't store form input or serve multiple routes, and its only path to out
An artifact is a capture of work: one self-contained page with no backend, so it can't store form input or serve multiple routes, and its only path to outside data when someone vie
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
Scale up only when the work genuinely benefits from having teammates work simultaneously. Three focused teammates often outperform five scattered ones.
Scale up only when the work benefits from having teammates work simultaneously. Three focused teammates often outperform five scattered ones.
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
**Unix socket security:** The `allowUnixSockets` option can grant access to powerful system services. For example, allowing `/var/run/docker.sock` effectively grants full host sy
**Unix socket security:** The `allowUnixSockets` option can grant access to system services that reach outside the sandbox. For example, allowing `/var/run/docker.sock` effective
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-sdk/subagents
±changed
+1−1
claude-codechanged
agent-sdk/subagents
You can create agent definitions dynamically based on runtime conditions. This example creates a security reviewer with different strictness levels, using a more powerful model for
You can create agent definitions dynamically based on runtime conditions. This example creates a security reviewer with different strictness levels, using a more capable model for
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-sdk/secure-deployment
±changed
+1−1
claude-codechanged
agent-sdk/secure-deployment
Claude Code and the Agent SDK are powerful tools that can execute code, access files, and interact with external services on your behalf.
Claude Code and the Agent SDK can execute code, access files, and interact with external services on your behalf.
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
**Unix socket security**: The `allowUnixSockets` option can grant access to powerful system services. For example, allowing `/var/run/docker.sock` effectively grants full host sy
**Unix socket security**: The `allowUnixSockets` option can grant access to system services that reach outside the sandbox. For example, allowing `/var/run/docker.sock` effective
+1 −1 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
agent-sdk/overview
±changed
+2−2
claude-codechanged
agent-sdk/overview
Everything that makes Claude Code powerful is available in the SDK.
These Claude Code capabilities are available in the SDK:
* [Agent harness design](https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code): how the Claude Code team uses dynamic workflows to orchestrate subagent
* [Agent harness design](https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code): how the Claude Code team uses dynamic workflows to orchestrate many sub
+2 −2 lines
Recorded here 29 Aug 2026 04:37 UTC
claude-code
gitlab-ci-cd
±changed
+2−2
claude-codechanged
gitlab-ci-cd
> This integration is built on top of the [Claude Code CLI and Agent SDK](/docs/en/agent-sdk/overview), enabling programmatic use of Claude in your CI/CD jobs and custom automation
> This integration is built on top of the [Claude Code CLI and Agent SDK](/docs/en/agent-sdk/overview.md), enabling programmatic use of Claude in your CI/CD jobs and custom automat
GitLab mints the job's OIDC token from the `id_tokens:` block and exposes it as `GITLAB_OIDC_TOKEN`. Set `aud` to the audience value you configured on the Workload Identity Pool pr
GitLab mints the job's OIDC token from the `id_tokens:` block and exposes it as `GITLAB_OIDC_TOKEN`. Set `aud` to the audience value you configured on the Workload Identity Pool pr
+2 −2 lines
Upstream edited 29 Aug 2026 04:34 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
gitlab-ci-cd
±changed
+74−76
claude-codechanged
gitlab-ci-cd
<Info>
Claude Code for GitLab CI/CD is currently in beta. Features and functionality may evolve as we refine the experience.
This integration is maintained by GitLab. For support, see the following [GitLab issue](https://gitlab.com/gitlab-org/gitlab/-/issues/573776).
</Info>
+74 −76 lines
Upstream edited 29 Aug 2026 04:34 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
champion-kit
±changed
+50−50
claude-codechanged
champion-kit
| Behavior | What it looks like in practice
| ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------
| Share what you discover | Post the prompts, screenshots, and small wins from your own work in the places your team already reads, such as an engineering channel, a standup threa
| Be the person people ask | When a colleague asks how you accomplished something, respond with the actual prompt you used so they can apply it directly to their own task.
| Grow the circle | Establish a small number of lightweight, recurring habits, such as a dedicated channel or a weekly thread, so that momentum continues even when your at
+50 −50 lines
Upstream edited 29 Aug 2026 04:34 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/secure-deployment
±changed
+45−45
claude-codechanged
agent-sdk/secure-deployment
| Resource | Restriction options |
| ------------------- | ----------------------------------------------- |
| Filesystem | Mount only needed directories, prefer read-only |
| Network | Restrict to specific endpoints via proxy |
| Credentials | Inject via proxy rather than exposing directly |
+45 −45 lines
Upstream edited 29 Aug 2026 04:34 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
ultrareview
±changed
+3−1
claude-codechanged
ultrareview
Without arguments, ultrareview reviews the diff between your current branch and the default branch, including uncommitted and staged changes. For a branch review, Claude Code bundl
Without arguments, ultrareview reviews the diff between your current branch and the default branch, including uncommitted and staged changes. For uncommitted changes to files named
For a branch review, Claude Code bundles the repository state and uploads it to a remote sandbox; when you [review a pull request](#review-a-pull-request), Claude Code uploads noth
+3 −1 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
remote-control
±changed
+1−3
claude-codechanged
remote-control
A banner appears above the prompt box showing connection status. Once connected, click **claude.ai/code** in the banner to go directly to the session, or find it in the session
To disconnect, click the close icon on the banner or run `/remote-control` again.
While Remote Control is on, Claude Code shows a **Remote Control** indicator in the prompt box footer. Once the session connects, click the indicator to go directly to the sess
+1 −3 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
network-config
±changed
+2−0
claude-codechanged
network-config
Claude Code never sends its WebSocket connections to `localhost`, `::1`, or `127.0.0.0/8` through the proxy, so you don't need a loopback entry in `NO_PROXY` for them.
+2 −0 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
monitoring-usage
±changed
+4−2
claude-codechanged
monitoring-usage
To verify a setup that exports metrics, check your backend for the `claude_code.session.count` metric, which Claude Code emits when a session starts. To verify a logs-only setup, s
To verify a setup that exports metrics, check your backend for the `claude_code.session.count` metric, which Claude Code emits when a session starts. To verify a logs-only setup, s
If nothing arrives, run `claude --debug` and check the debug log. Claude Code reports failures from the exporters you configure as `[3P telemetry]` errors, where 3P means third-par
To confirm events arrive, submit a prompt in a session running under this configuration and check your SIEM for the `claude_code.user_prompt` event. If nothing arrives, run `claude
+4 −2 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
code-review
±changed
+3−1
claude-codechanged
code-review
`/code-review ultra --fix` runs the deeper [ultrareview](/docs/en/ultrareview) in the cloud, then applies its findings to your working tree when they arrive back in your session. U
`/code-review ultra --fix` runs the deeper [ultrareview](/docs/en/ultrareview) in the cloud, then applies its findings to your working tree when they arrive back in your session.
Ultrareview uses its own scope: your current branch against the repository's default branch, plus uncommitted and staged changes in the working tree. For uncommitted changes to fil
+3 −1 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
claude-code-on-the-web
±changed
+5−2
claude-codechanged
claude-code-on-the-web
When you run `claude --cloud` from a repository that isn't connected to GitHub, Claude Code bundles your local repository and uploads it directly to the cloud session. The bundle i
When you run `claude --cloud` from a repository that isn't connected to GitHub, Claude Code bundles your local repository and uploads it directly to the cloud session. The bundle i
On macOS, Linux, and WSL, Claude Code leaves uncommitted changes to files named like credentials or keys out of the upload and names the files it left out. This covers `.env` files
| `Couldn't verify your organization's policy for cloud sessions. Check your network connection and try again.` | Claude Code couldn't fetch your organization's polic
+5 −2 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
agent-teams
±changed
+4−7
claude-codechanged
agent-teams
* **Idle notifications**: when a teammate finishes and stops, it automatically notifies the lead. The notification doesn't carry the teammate's output; a teammate shares results by
* **Idle notifications**: when a teammate finishes and stops, it automatically notifies the lead and includes its final answer in the notification. A teammate whose turn ends on an
While agent teams are enabled, a subagent that Claude names in the lead's session launches as a teammate. Claude [can name subagents on its own](#how-claude-starts-agent-teams), so
* **Subagents**: Claude receives the subagent's result when it completes.
+4 −7 lines
Recorded here 29 Aug 2026 03:37 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
Some commands can't run inside the sandbox at all, such as tools that are incompatible with it or that need a host you haven't allowed. When a command fails after the sandbox denie
Some commands can't run inside the sandbox at all, such as tools that are incompatible with it or that need a host you haven't allowed. Claude Code reports sandbox violations in th
+1 −1 lines
Recorded here 29 Aug 2026 03:07 UTC
claude-code
workflows
±changed
+1−7
claude-codechanged
workflows
Claude can start a workflow from a script file only when it can already read that file without a permission prompt, such as:
* The run's own persisted script under `~/.claude/projects/`
* A file in your working directory or an [additional directory](/docs/en/permissions#working-directories)
* A path your [Read allow rules](/docs/en/permissions#read-and-edit) cover
+1 −7 lines
Recorded here 29 Aug 2026 02:37 UTC
claude-code
settings-reference
±changed
+3−1
claude-codechanged
settings-reference
* **Default**: unset, so Claude Code adds `Co-Authored-By: <model name> <[email protected]>`, where the model name reflects the active model for the session, such as `Claude So
* **Default**: unset, so Claude Code adds `Co-Authored-By: <name> <[email protected]>`. The name is the session's active model, such as `Claude Sonnet 5`.
* When Claude Code recognizes the model as a Claude model but can't confirm its exact version, it writes `Claude` alone.
* When it can't match the model ID to any Claude model, such as a third-party model served through a custom [`ANTHROPIC_BASE_URL`](/docs/en/env-vars), it writes `Claude Code`.
+3 −1 lines
Recorded here 29 Aug 2026 02:37 UTC
claude-code
agent-view
±changed
+7−1
claude-codechanged
agent-view
* The file that Claude is editing is inside a linked git worktree, such as one that the session or its subagent created with `git worktree add`
When the hook fails in a directory that isn't a git repository, the session skips isolation for that directory and edits the working directory in place. Inside a git repository, wr
When the hook fails in a directory that isn't a git repository, Claude skips isolation for that directory and edits the working directory in place. Inside a git repository, Claude
Claude Code forwards a gateway in front of a cloud provider. If the shell you dispatch from selects the provider and exports its gateway endpoint with its auth-bypass flag, Claude
+7 −1 lines
Recorded here 29 Aug 2026 02:37 UTC
claude-code
workflows
±changed
+8−0
claude-codechanged
workflows
Claude can start a workflow from a script file only when it can already read that file without a permission prompt, such as:
* The run's own persisted script under `~/.claude/projects/`
* A file in your working directory or an [additional directory](/docs/en/permissions#working-directories)
* A path your [Read allow rules](/docs/en/permissions#read-and-edit) cover
+8 −0 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
terminal-config
±changed
+17−16
claude-codechanged
terminal-config
| Token | Controls |
| :------------- | :------------------------------------------------- |
| `promptBorder` | Input box border in Manual mode |
| `planMode` | Plan mode accent and border |
| `autoAccept` | Accept-edits mode accent and border |
+17 −16 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
sub-agents
±changed
+2−0
claude-codechanged
sub-agents
A background subagent can leave a background [Bash or PowerShell command](/docs/en/tools-reference#background-commands) [running past the end of its turn](/docs/en/interactive-mode
+2 −0 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
statusline
±changed
+11−4
claude-codechanged
statusline
| `rate_limits.spend_limit.used_percentage`, `rate_limits.spend_limit.resets_at` | Behind a [Claude apps gateway](/docs/en/claude-apps-gateway-spend-limits#usage-warnings-in-clau
},
"spend_limit": {
"used_percentage": 62.8,
"resets_at": 1740787200
+11 −4 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
permissions
±changed
+4−0
claude-codechanged
permissions
When a tool opens an approved file, Claude Code [confirms the path still resolves to the location the permission check approved](/docs/en/errors#refusing-after-a-symlink-changed).
Grep and Glob search the directory the `path` argument resolves to. Claude Code applies `Read` deny rules to that directory.
+4 −0 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
feature-availability
±changed
+8−5
claude-codechanged
feature-availability
* **[Commands](/docs/en/commands#all-commands)**: `/design-sync`, `/import` with its `claude import` subcommand form, and `/radio` are unavailable on Amazon Bedrock, Google Cloud's
* **[Commands](/docs/en/commands#all-commands)**:
* `/design-sync` and `/import` with its `claude import` subcommand form are unavailable on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform o
* `/voice` requires a claude.ai account
* `/list-agents` and its alias `/peers` are available only in sessions where [cross-session messaging is enabled](/docs/en/cross-session-messaging#availability)
+8 −5 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
errors
±changed
+233−201
claude-codechanged
errors
| Message
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| `API Error: 500 Internal server error`
| `API Error: Repeated 529 Overloaded errors`
| `Request timed out`
+233 −201 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
When Claude messages another session through this surface, Claude Code shows it there as a card labeled with the sending session's title and a link back, so you can always tell whe
When Claude messages another session through this surface, Claude Code shows it there as a card labeled with the sending session's title and a link back, so you can always tell whe
+1 −1 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
cross-session-messaging
±changed
+2−4
claude-codechanged
cross-session-messaging
When a message that starts a new turn mentions a file as an `@` immediately followed by its path, Claude Code [attaches that file](/docs/en/common-workflows#reference-files-and-dir
A message that Claude reads during an active turn arrives as plain text with nothing attached, even if it mentions files or MCP resources with `@`.
A message from another session arrives as plain text. If it mentions a file or an [MCP resource](/docs/en/mcp#use-mcp-resources) with `@`, Claude sees the mention as written and Cl
Claude receives the message with the sender's name and a reply address, except for a [one-way cross-machine message](#message-sessions-on-other-machines), which carries no reply ad
+2 −4 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/radio` | Open Claude FM lo-fi radio in your browser. Prints the stream URL when no browser
| `/radio` | Open Claude FM lo-fi radio in your browser. Prints the stream URL when no browser
+1 −1 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
claude-apps-gateway-spend-limits
±changed
+3−1
claude-codechanged
claude-apps-gateway-spend-limits
Claude Code warns a developer as they approach their cap: once utilization passes 75%, and again past 95% of their fullest cap. When the gateway blocks a request, Claude Code shows
Claude Code warns a developer as they approach their cap: once utilization passes 75%, and again past 95% of their most-consumed cap. When the gateway blocks a request, Claude Code
With v2.1.251 or later on the developer's machine, Claude Code also reads the same headers to show a **Spend limit** bar in `/usage`, with the percentage of their cap used and when
+3 −1 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
agent-sdk/typescript
±changed
+3−2
claude-codechanged
agent-sdk/typescript
| `scriptPath` | `string` | Path to a workflow script file on disk. Takes precedence over `script` and `name`. Every invocation persists its script and returns the path in th
| `scriptPath` | `string` | Path to a workflow script file on disk. Takes precedence over `script` and `name`. Claude Code persists every invocation's script and returns the
noop?: boolean;
Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 sec
Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 sec
+3 −2 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+4−4
claude-codechanged
agent-sdk/modifying-system-prompts
* **Minimal default**: when you don't set `systemPrompt` in TypeScript or `system_prompt` in Python, the SDK uses a minimal prompt that covers tool calling but omits Claude Code's
* **`claude_code` preset**: the full system prompt that the Claude Code CLI uses, with tool usage instructions, code style and formatting guidelines, response tone and verbosity ru
* **Minimal default**: when you don't set `systemPrompt` in TypeScript or `system_prompt` in Python, the SDK uses a minimal prompt that covers tool calling but omits the rest of th
* **`claude_code` preset**: the system prompt that the Claude Code CLI uses, with tool usage instructions, security and safety instructions, and context about the working directory
| A CLI or IDE-like coding tool where a human watches and steers, and Claude Code's defaults are what you want | `claude_code` preset | The full Claude Code prompt: t
+4 −4 lines
Recorded here 29 Aug 2026 01:37 UTC
claude-code
sub-agents
±changed
+3−1
claude-codechanged
sub-agents
The `--agents` flag accepts JSON with a `prompt` field plus these [frontmatter](#supported-frontmatter-fields) fields: `description`, `tools`, `disallowedTools`, `model`, `permissi
The `--agents` flag accepts JSON with a `prompt` field plus these [frontmatter](#supported-frontmatter-fields) fields: `description`, `tools`, `disallowedTools`, `model`, `permissi
For what Claude Code does with a value it can't load, and the flags and environment variable that skip that check, see [`Invalid --agents configuration`](/docs/en/errors#invalid-ag
+3 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
On models that always think, such as Fable 5, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instea
On models that always think, such as Fable 5, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thinking` parameter instea
* **Default**: unset, so Claude Code uses the Anthropic-hosted environment when one is in your list, and otherwise the first environment it finds
* **Default**: unset, so Claude Code uses the Anthropic-hosted environment when your list has one, and otherwise the first environment in your list that isn't a [Remote Control bri
+2 −2 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
self-hosted-environments-reference
±changed
+1−1
claude-codechanged
self-hosted-environments-reference
| `--kill-session-after-min <n>` | `SELF_HOSTED_RUNNER_MAX_LIFETIME_MS` | `0` | Terminate a session child once it has lived N minu
| `--kill-session-after-min <n>` | `SELF_HOSTED_RUNNER_MAX_LIFETIME_MS` | `0` | Terminate a session child once it has lived N minu
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+3−1
claude-codechanged
self-hosted-environments-deploy
On `SIGTERM`, the runner stops taking new work and, unless you set [`--defer-shutdown-max-min`](#defer-the-drain-past-the-first-signal), waits up to `--drain-wait-sec`, zero by def
On `SIGTERM`, the runner stops taking new work and, unless you set [`--defer-shutdown-max-min`](#defer-the-drain-past-the-first-signal), waits up to `--drain-wait-sec`, zero by def
The full drain path needs up to `--session-stop-grace-sec` + `--drain-wait-sec` + `--post-session-hook-timeout-sec`, plus 15 seconds of fixed overhead for process cleanup, plus 30
+3 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
remote-control
±changed
+11−2
claude-codechanged
remote-control
* **Survive interruptions**: if your laptop sleeps or your network drops, Claude Code reconnects automatically when your machine comes back online. Claude Code queues status update
* **Survive interruptions**: if your laptop sleeps or your network drops, Claude Code reconnects automatically when your machine comes back online. While the connection is rebuildi
| `--permission-mode <mode>` | Set the starting [permission mode](/docs/en/permission-modes) for the server's sessions, such as `acceptEdits`. Accepts `man
| `--debug-file <path>` | Write debug logs to the given file.
+11 −2 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
Enabling [fast mode](/docs/en/fast-mode) adds a request header that is part of the cache key, so the next request reads the entire conversation history with no cache hits. Those un
Enabling [fast mode](/docs/en/fast-mode) adds a request header that is part of the cache key, so the first request Claude Code sends with fast mode on reads the entire conversation
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
network-config
±changed
+13−9
claude-codechanged
network-config
Claude Code runs three independent timers that abort a streaming model response when it goes quiet, so a dead connection fails and retries instead of hanging. Each timer watches a
| Timer | Aborts when
| :------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------
| Event-level watchdog | No response events parse. On connections where the byte-level watchdog runs, arriving bytes, including keep-alive pings, also reset this watchdog, for up t
+13 −9 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
model-config
±changed
+8−8
claude-codechanged
model-config
* **`/effort`**: run `/effort` with no arguments to open an interactive slider, `/effort` followed by a level name to set it directly, or `/effort auto` to reset to the model defau
* **`/effort`**: run `/effort` with no arguments to open an interactive slider, `/effort` followed by a level name to set it directly, or `/effort auto` to reset to the model defau
Extended thinking is the reasoning Claude emits before responding. On models that support [adaptive reasoning](#adjust-effort-level), the effort level is the primary control for ho
| Control | How to set it
+8 −8 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
interactive-mode
±changed
+7−7
claude-codechanged
interactive-mode
Claude Code runs some commands as soon as you send them instead of queueing them, among them `/model`, `/effort`, and `/fast`. Each of the three changes a setting: the model, the e
* [`/model`](/docs/en/model-config#setting-your-model): once you confirm the [cache warning](/docs/en/prompt-caching#switching-models), if Claude Code shows one, Claude Code applie
* [`/effort`](/docs/en/model-config#adjust-effort-level): once you confirm the [cache warning](/docs/en/prompt-caching#changing-effort-level), if Claude Code shows one, Claude Code
* [`/fast`](/docs/en/fast-mode#toggle-fast-mode): Claude Code keeps the fast mode setting that was active when the turn started, so your speed change applies from your next turn. I
+7 −7 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
hooks
±changed
+9−9
claude-codechanged
hooks
| Field | Description
| :---------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------
| `session_id` | Current session identifier
| `prompt_id` | UUID identifying the user prompt currently being processed. Matches the [`prompt.id` attribute on OpenTelemetry events](/docs/en/monitoring-usage#event-correl
| `transcript_path` | Path to conversation JSON. The transcript file is written asynchronously and may lag the in-memory conversation, so it may not yet include the current turn's
+9 −9 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
gateways
±changed
+1−1
claude-codechanged
gateways
* **Client telemetry**: on a Claude apps gateway session, Claude Code sends no client analytics to Anthropic. It disables the Anthropic-bound analytics when the session signs in, a
* **Client telemetry**: on a Claude apps gateway session, Claude Code sends no client analytics to Anthropic. It disables the Anthropic-bound analytics when the session signs in. F
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
fast-mode
±changed
+3−1
claude-codechanged
fast-mode
You can run `/fast` while Claude is working, and Claude Code toggles fast mode without waiting for the turn to end. Claude Code finishes the running turn at its original speed, so
* If you're on a different model, Claude Code automatically switches to Opus
* If your current model doesn't support fast mode, Claude Code switches to Opus
+3 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
errors
±changed
+98−6
claude-codechanged
errors
| `API Error: No response from API`
| `Effort '<level>' isn't available with thinking turned off on this model`
| `effort '<level>' is not supported when thinking is disabled`
| `Error: Invalid --agents configuration:`
| `` `<flag>` before `remote-control` is not carried over to the sessions Remote Control starts ``
+98 −6 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
env-vars
±changed
+14−9
claude-codechanged
env-vars
| `CLAUDE_BYTE_STREAM_IDLE_TIMEOUT_MS` | Timeout in milliseconds for the byte-level streaming idle watchdog only; when set, it takes precedence over `CLAUDE_STRE
| `CLAUDE_BYTE_STREAM_IDLE_TIMEOUT_MS` | Timeout in milliseconds for the byte-level streaming idle watchdog; when set, it takes precedence over `CLAUDE_STREAM_ID
| `CLAUDE_CODE_CONNECT_TIMEOUT_MS` | Removed in v2.1.186 and now a no-op. Previously set a separate timeout for the connect, TLS, and response-header phase o
| `CLAUDE_CODE_CONNECT_TIMEOUT_MS` | Removed in v2.1.186 and now a no-op. Previously set a separate timeout for the connect, TLS, and response-header phase o
| `CLAUDE_EFFORT` | Set automatically in Bash tool subprocesses and hook commands to the active [effort level](/docs/en/model-config#adjust-
+14 −9 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
desktop
±changed
+3−1
claude-codechanged
desktop
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), `MAX_THINKING_TOKENS` values other than `0` are ignored because adaptive reasoning controls thinking
+3 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
debug-your-config
±changed
+2−4
claude-codechanged
debug-your-config
The `/context` command shows everything occupying the context window for the current session, broken down by category: system prompt, system tools, MCP tools, custom subagents with
The `/context` command shows everything occupying the context window for the current session, broken down by category: system prompt, system tools, MCP tools, custom subagents with
Run [`/doctor`](/docs/en/commands#all-commands) to find invalid settings files.
From the terminal, `claude doctor` prints read-only installation and settings diagnostics without starting a session.
+2 −4 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
commands
±changed
+3−3
claude-codechanged
commands
| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level): `low` to `xhigh
| `/effort [level\|auto\|status]` | Set the [effort level](/docs/en/model-config#adjust-effort-level): `low` to `xhigh
| `/fast [on\|off]` | Toggle [fast mode](/docs/en/fast-mode) on or off. Availability in non-interactive
| `/fast [on\|off]` | Toggle [fast mode](/docs/en/fast-mode) on or off. Run it while Claude is respondin
| `/model [model]` | Switch the AI model and save it as your default for new sessions. For models that
+3 −3 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
cloud-environments
±changed
+2−2
claude-codechanged
cloud-environments
* From the CLI, sessions use your [`/remote-env` pick](#select-an-environment-from-the-cli), or fall back to your first available cloud environment. For a [self-hosted environment]
* From the CLI, Claude Code uses your [`/remote-env` pick](#select-an-environment-from-the-cli), or falls back to the Anthropic-hosted environment when your list has one, and other
* No new session can start in an archived environment, on any surface. If the environment was your saved [CLI default](#select-an-environment-from-the-cli), CLI cloud sessions fall
* No new session can start in an archived environment, on any surface. If the environment was your saved [CLI default](#select-an-environment-from-the-cli), Claude Code starts CLI
+2 −2 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-t
| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-t
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
`claude --cloud` and `claude --teleport` require sign-in with a claude.ai account. If you authenticate with an API key, or your stored account details are stale, these commands fai
`claude --cloud` and `claude --teleport` require sign-in with a claude.ai account. If you authenticate with an API key, or your stored account details are stale, these commands fai
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+2−2
claude-codechanged
claude-apps-gateway-deploy
* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. On machines where a [managed settings file, an MDM profile, or a
* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. Before the sign-in, including on a first run where a [managed set
* **Survey ratings**: gateway sign-in, or managed settings that force gateway sign-in, disables the Anthropic-bound rating sink from the same point as the analytics streams, so rat
* **Survey ratings**: gateway sign-in disables the Anthropic-bound rating sink from the same point as the analytics streams, so ratings aren't sent to Anthropic.
+2 −2 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
agent-sdk/user-input
±changed
+2−2
claude-codechanged
agent-sdk/user-input
The callback can stay pending indefinitely. Execution remains paused until your callback returns, and the SDK only cancels the wait when the query itself is cancelled. If a user mi
The callback can stay pending indefinitely. Execution remains paused until your callback returns, and the SDK only cancels the wait when the query itself is cancelled. If a user mi
```json theme={null}
```jsonc theme={null}
+2 −2 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
agent-sdk/typescript
±changed
+10−7
claude-codechanged
agent-sdk/typescript
timeout?: number;
| Parameter | Type | Description
| :--------------------- | :---------------------------- | :------------------------------------------------------------------------------------------------------------------------
| `options.name` | `string` | The name of the MCP server
| `options.version` | `string` | Optional version string
+10 −7 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
agent-sdk/structured-outputs
±changed
+1−1
claude-codechanged
agent-sdk/structured-outputs
```json theme={null}
```jsonc theme={null}
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
agent-sdk/mcp
±changed
+2−0
claude-codechanged
agent-sdk/mcp
In TypeScript, you can set the tool-call limit for a single [SDK MCP server](#sdk-mcp-servers) by passing [`timeout` to `createSdkMcpServer()`](/docs/en/agent-sdk/typescript#create
+2 −0 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
advisor
±changed
+1−1
claude-codechanged
advisor
| [`/model`](/docs/en/model-config#setting-your-model) | For all subsequent turns
| [`/model`](/docs/en/model-config#setting-your-model) | From the next request onward
+1 −1 lines
Recorded here 29 Aug 2026 00:07 UTC
claude-code
agent-sdk/structured-outputs
±changed
+3−3
claude-codechanged
agent-sdk/structured-outputs
| Subtype | Meaning |
| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `success` | Output was generated and validated successfully |
| Subtype | Meaning |
| - | - |
+3 −3 lines
Upstream edited 29 Aug 2026 00:00 UTC Recorded here 28 Sep 2026 23:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.