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
5,591 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
29 Sep 2026
60 pages
+1333 −1202 lines
claude-code
whats-new/2026-w19
±changed
+15−40
claude-codechanged
whats-new/2026-w19
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-128">v2.1.128 → v2.1.136</a></span>
<span>2 features · May 4–8</span>
</div>
Releases [v2.1.128 → v2.1.136](/docs/en/changelog#2-1-128)
+15 −40 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w18
±changed
+44−77
claude-codechanged
whats-new/2026-w18
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-120">v2.1.120 → v2.1.126</a></span>
<span>4 features · April 27 – May 1</span>
</div>
Releases [v2.1.120 → v2.1.126](/docs/en/changelog#2-1-120)
+44 −77 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w17
±changed
+39−78
claude-codechanged
whats-new/2026-w17
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-114">v2.1.114 → v2.1.119</a></span>
<span>4 features · April 20–24</span>
</div>
Releases [v2.1.114 → v2.1.119](/docs/en/changelog#2-1-114)
+39 −78 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w16
±changed
+49−93
claude-codechanged
whats-new/2026-w16
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-105">v2.1.105 → v2.1.113</a></span>
<span>5 features · April 13–17</span>
</div>
Releases [v2.1.105 → v2.1.113](/docs/en/changelog#2-1-105)
+49 −93 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w14
±changed
+57−97
claude-codechanged
whats-new/2026-w14
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-86">v2.1.86 → v2.1.91</a></span>
<span>5 features · March 30 – April 3</span>
</div>
Releases [v2.1.86 → v2.1.91](/docs/en/changelog#2-1-86)
+57 −97 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w13
±changed
+70−116
claude-codechanged
whats-new/2026-w13
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-83">v2.1.83 → v2.1.85</a></span>
<span>6 features · March 23–27</span>
</div>
Releases [v2.1.83 → v2.1.85](/docs/en/changelog#2-1-83)
+70 −116 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w33
±changed
+1−1
claude-codechanged
whats-new/2026-w33
<p className="digest-feature-lede">Plugin marketplaces clone bare <code>gitlab.com</code> URLs, including nested subgroups. On v2.1.233 or later, pass a GitLab merge request URL
<p className="digest-feature-lede">Plugin marketplaces clone bare <code>gitlab.com</code> URLs, including nested subgroups. On v2.1.233 or later, pass a GitLab merge request URL
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w22
±changed
+2−2
claude-codechanged
whats-new/2026-w22
<div>In <code>claude agents</code>, prefix a shell command with <code>!</code> to run it as a background job you can attach to and detach from; also available as <code>claude -
<div>In <code>claude agents</code>, prefix a shell command with <code>!</code> to run it as a background job you can attach to and detach from; also available as `claude --bg -
<div>Claude Code now switches to your configured <code>--fallback-model</code> for the rest of the session when the primary model is not found, instead of failing every request
<div>Claude Code now switches to your configured `--fallback-model` for the rest of the session when the primary model is not found, instead of failing every request</div>
+2 −2 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w21
±changed
+2−2
claude-codechanged
whats-new/2026-w21
<div>New <a href="/docs/en/code-review"><code>/code-review</code></a> command reports correctness bugs at a chosen effort level such as <code>/code-review high</code>, and <cod
<div>New <a href="/docs/en/code-review"><code>/code-review</code></a> command reports correctness bugs at a chosen effort level such as <code>/code-review high</code>, and `--c
<div><code>claude agents --json</code> lists live sessions as JSON for scripting, such as status bars and session pickers</div>
<div>`claude agents --json` lists live sessions as JSON for scripting, such as status bars and session pickers</div>
+2 −2 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w20
±changed
+1−1
claude-codechanged
whats-new/2026-w20
<div><code>claude agents</code> gained dispatch flags (<code>--add-dir</code>, <code>--settings</code>, <code>--mcp-config</code>, <code>--plugin-dir</code>, <code>--permission
<div><code>claude agents</code> gained dispatch flags (`--add-dir`, `--settings`, `--mcp-config`, `--plugin-dir`, `--permission-mode`, `--model`, `--effort`, `--dangerously-ski
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w19
±changed
+2−2
claude-codechanged
whats-new/2026-w19
<div>New <code>worktree.baseRef</code> setting (<code>fresh</code> | <code>head</code>) controls whether <code>--worktree</code>, the <code>EnterWorktree</code> tool, and agent
<div>New <code>worktree.baseRef</code> setting (<code>fresh</code> | <code>head</code>) controls whether `--worktree`, the <code>EnterWorktree</code> tool, and agent-isolation
<div><code>--channels</code> now works with console (API key) authentication</div>
<div>`--channels` now works with console (API key) authentication</div>
+2 −2 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w18
±changed
+3−3
claude-codechanged
whats-new/2026-w18
<div>New <code>claude plugin prune</code> removes orphaned auto-installed plugin dependencies, and <code>plugin uninstall --prune</code> cascades</div>
<div>New <code>claude plugin prune</code> removes orphaned auto-installed plugin dependencies, and `plugin uninstall --prune` cascades</div>
<div>New <a href="/docs/en/ultrareview"><code>claude ultrareview</code></a> subcommand runs <code>/ultrareview</code> non-interactively from CI or scripts: prints findings to s
<div><code>--dangerously-skip-permissions</code> now bypasses prompts for writes to <code>.claude/</code>, <code>.git/</code>, <code>.vscode/</code>, shell config files, and ot
<div>New <a href="/docs/en/ultrareview"><code>claude ultrareview</code></a> subcommand runs <code>/ultrareview</code> non-interactively from CI or scripts: prints findings to s
+3 −3 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w17
±changed
+1−1
claude-codechanged
whats-new/2026-w17
<div><code>--from-pr</code> now accepts GitLab merge request, Bitbucket pull request, and GitHub Enterprise PR URLs in addition to github.com</div>
<div>`--from-pr` now accepts GitLab merge request, Bitbucket pull request, and GitHub Enterprise PR URLs in addition to github.com</div>
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w16
±changed
+1−1
claude-codechanged
whats-new/2026-w16
<div><a href="/docs/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode</a> is now available for Max subscribers on Opus 4.7, and the <code>--enable-auto-mode</code
<div><a href="/docs/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode</a> is now available for Max subscribers on Opus 4.7, and the `--enable-auto-mode` flag is n
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w14
±changed
+1−1
claude-codechanged
whats-new/2026-w14
<div>New <code>defer</code> value for <code>permissionDecision</code> in <code>PreToolUse</code> hooks: <code>-p</code> sessions pause at a tool call and exit with a <code>defe
<div>New <code>defer</code> value for <code>permissionDecision</code> in <code>PreToolUse</code> hooks: <code>-p</code> sessions pause at a tool call and exit with a <code>defe
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
whats-new/2026-w13
±changed
+1−1
claude-codechanged
whats-new/2026-w13
<p className="digest-feature-lede">Auto mode hands your permission prompts to a classifier. Safe edits and commands run without interrupting you; anything destructive or suspicio
<p className="digest-feature-lede">Auto mode hands your permission prompts to a classifier. Safe edits and commands run without interrupting you; anything destructive or suspicio
+1 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
plugin-evals
±changed
+3−1
claude-codechanged
plugin-evals
### "--json output path must end in .json"
<h3 id="json-output-path-must-end-in-json">
`--json output path must end in .json`
</h3>
+3 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
errors
±changed
+11−7
claude-codechanged
errors
| `--bg and --print conflict` | [Command-line errors](#command-line-errors) |
| `--bg and --print conflict` | [Command-line errors](#conflict-between-bg-and-print) |
| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#command-line-errors) |
| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#the-json-schema-value-is-not-a-valid-json-schema) |
### Conflict between --bg and --print
+11 −7 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
desktop-linux
±changed
+3−1
claude-codechanged
desktop-linux
### Running as root without --no-sandbox is not supported
<h3 id="running-as-root-without-no-sandbox-is-not-supported">
Running as root without `--no-sandbox` is not supported
</h3>
+3 −1 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
desktop-ios-simulator
±changed
+19−17
claude-codechanged
desktop-ios-simulator
* Use Xcode 26.x. The pane doesn't yet work with Xcode 27, which replaces the Simulator app with Device Hub. If `xcode-select` points at Xcode 27 on your Mac, see [The simulator
* Xcode 26.x or Xcode 27 is recommended, and the pane works with either. If you have more than one Xcode installed, see [Choose which Xcode the simulator pane uses](#choose-which
### Choose which Xcode the simulator pane uses
+19 −17 lines
Upstream edited 29 Sep 2026 16:28 UTC Recorded here 29 Sep 2026 16:37 UTC
claude-code
worktrees
±changed
+1−1
claude-codechanged
worktrees
When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, uncommitted work inside checked-out submod
When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, uncommitted work inside checked-out submod
+1 −1 lines
Upstream edited 29 Sep 2026 15:28 UTC Recorded here 29 Sep 2026 15:37 UTC
claude-code
hooks
±changed
+7−1
claude-codechanged
hooks
For git-based worktrees, Claude Code handles cleanup automatically with `git worktree remove`. If you configured a WorktreeCreate hook for a non-git version control system, pair it
For git-based worktrees, Claude Code handles cleanup automatically with `git worktree remove`. If you configured a WorktreeCreate hook, pair it with a WorktreeRemove hook to contro
* **No WorktreeRemove hook**: when you exit a `--worktree` session and choose removal, Claude Code falls back to `git worktree remove --force` on the path your WorktreeCreate hook
* **Hook exits 0**: the worktree counts as removed. Claude Code reads nothing else from the hook, so make sure your hook deleted the directory.
+7 −1 lines
Upstream edited 29 Sep 2026 15:28 UTC Recorded here 29 Sep 2026 15:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+29−3
claude-codechanged
self-hosted-environments-configuration
| `CLAUDE_RUNNER_ORDER_ID` | Opaque idempotency key, unique per spawn request and safe for Kubernetes resource names. Use it as your provisioner's dedup key. |
| `CLAUDE_RUNNER_SESSION_ID` | The session this request is for. Empty for pre-warming requests, which boot a standby runner ahead of any specific session when [`--min-idle`](/docs/
| `CLAUDE_RUNNER_ORDER_ID` | Opaque idempotency key, unique per spawn request and safe for Kubernetes resource names. Use only the order ID as your provisioner's dedup key. |
| `CLAUDE_RUNNER_SESSION_ID` | The session this request is for. It repeats on every re-request for the session, so use it for logging and routing, not as a dedup key. Empty for pre
1. **Be idempotent on `CLAUDE_RUNNER_ORDER_ID`.** Redelivery of the same request must spawn at most one runner. Derive a deterministic resource name from the ID and let your platfo
+29 −3 lines
Upstream edited 29 Sep 2026 15:03 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
monitoring-usage
±changed
+32−3
claude-codechanged
monitoring-usage
| `OTEL_METRICS_INCLUDE_SESSION_ID` | Include session.id attribute in metrics | `true` | `false` |
| `OTEL_METRICS_INCLUDE_SESSION_ID` | Include session.id and, on cloud sessions, ccr.session.id attributes in metrics | `true` | `false` |
## Telemetry from cloud sessions and Claude Tag
[Cloud sessions](/docs/en/claude-code-on-the-web), including [Claude Tag](https://claude.com/docs/claude-tag/overview) channel sessions, run in [cloud environments](/docs/en/cloud-
+32 −3 lines
Upstream edited 29 Sep 2026 15:03 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
model-config
±changed
+3−2
claude-codechanged
model-config
| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced | Enforced | Not delivered |
| [Server-managed settings](/docs/en/server-managed-settings) from the admin console | Enforced | Enforced | Enforced, except in [Claude Tag](https://claude.com/docs/claude-tag/ove
* [Cloud sessions](/docs/en/claude-code-on-the-web), including those you start from the Desktop app, run on Anthropic-managed VMs by default: settings deployed to your device do no
* [Cloud sessions](/docs/en/claude-code-on-the-web), including those you start from the Desktop app, run on Anthropic-managed VMs by default: settings deployed to your device do no
* [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions run in cloud environments but don't receive server-managed settings; in a [self-hosted environment](/docs/en/se
+3 −2 lines
Upstream edited 29 Sep 2026 15:03 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
managed-settings
±changed
+1−0
claude-codechanged
managed-settings
* **Claude Tag sessions**: [Claude Tag](https://claude.com/docs/claude-tag/overview) sessions run in cloud environments but don't receive server-managed settings. In a [self-hosted
+1 −0 lines
Upstream edited 29 Sep 2026 15:03 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
cloud-environments
±changed
+6−5
claude-codechanged
cloud-environments
Each session copies the environment's values once, at startup, into ordinary environment variables that any command Claude runs can read. Because running sessions don't re-read the
Each session copies the environment's values once, at startup, into ordinary environment variables that any command Claude runs can read, except `OTEL_*` variables. Claude Code use
* **Claude Code's telemetry export**: Claude Code sends its [telemetry export](/docs/en/monitoring-usage#telemetry-from-cloud-sessions-and-claude-tag) itself rather than through a
Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. [Server-managed settings](/docs/en/s
Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. No [server-managed setting](/docs/en
+6 −5 lines
Upstream edited 29 Sep 2026 15:03 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
The session isn't talking to the Anthropic API directly, so there is no claude.ai backend to pair with. This happens on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft
The session isn't talking to the Anthropic API directly, which Remote Control requires. This happens on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. It als
+1 −1 lines
Upstream edited 29 Sep 2026 14:37 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
If `/mcp` shows a connector as `connected · session token rejected`, or its detail view shows [`claude.ai rejected the session token`](/docs/en/errors#claude-ai-rejected-the-sessio
If `/mcp` shows a connector as `session token rejected`, or its detail view shows [`claude.ai rejected the session token`](/docs/en/errors#claude-ai-rejected-the-session-token), cl
+1 −1 lines
Upstream edited 29 Sep 2026 14:37 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
errors
±changed
+44−84
claude-codechanged
errors
| `Error during compaction: Conversation too long` | [Request errors](#error-during-compaction-conversation-too-long) |
| `Refusing to send: connected endpoint is not the expected process` / `Refusing to send: connected endpoint identity could not be read` | [Tool errors](#refusing-to-send-a-cross-s
| `Refusing to send: connected endpoint is not owned by this user` / `Refusing to send: connected endpoint owner could not be read` | [Tool errors](#refusing-to-send-a-cross-sessio
| `Refusing to send: connected endpoint is a different process with the expected pid` | [Tool errors](#refusing-to-send-a-cross-session-message) |
Claude Code retries transient failures up to 10 times with exponential backoff before showing you an error. It doesn't always retry a failure that arrives partway through Claude's
+44 −84 lines
Upstream edited 29 Sep 2026 14:37 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
cross-session-messaging
±changed
+1−1
claude-codechanged
cross-session-messaging
* The reply target on this machine fails a safety check, such as a symlinked target or an endpoint that isn't the expected process. [Refusing to send a cross-session message](/docs
* The reply target on this machine fails a safety check, such as a symlinked target. [Refusing to send a cross-session message](/docs/en/errors#refusing-to-send-a-cross-session-mes
+1 −1 lines
Upstream edited 29 Sep 2026 14:37 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
authentication
±changed
+3−3
claude-codechanged
authentication
You can check for this state before a request fails: [`/status`](/docs/en/commands) shows a `Login` row reading `Expired — log in again`, plus the organization and email it has sav
The warning appears only when a claude.ai or Claude Console login is the active credential, and not when a cloud provider, `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHe
You can check for this state before a request fails: [`/status`](/docs/en/commands) shows a `Login` row reading `Expired — log in again`, plus the organization and email it has sav
+3 −3 lines
Upstream edited 29 Sep 2026 14:37 UTC Recorded here 29 Sep 2026 15:07 UTC
claude-code
authentication
±changed
+15−15
claude-codechanged
authentication
Unset `ANTHROPIC_API_KEY` before you sign in without a key. A profile written by Claude Code's own Console sign-in, or by the Claude Platform CLI's `ant auth login`, is the same ki
Unset `ANTHROPIC_API_KEY` before you sign in without a key.
Developers can log in from several paths: the terminal `/login` flow, the [VS Code extension](/docs/en/vs-code), the Agent SDK, `claude setup-token`, `/install-github-app`, and [ga
* **Terminal, VS Code extension, and Agent SDK logins**: verify `forceLoginOrgUUID` for claude.ai account logins
+15 −15 lines
Upstream edited 29 Sep 2026 06:28 UTC Recorded here 29 Sep 2026 06:37 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Upstream edited 29 Sep 2026 02:30 UTC Recorded here 29 Sep 2026 02:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
For decisions that require judgment rather than deterministic rules, use `type: "prompt"` hooks. Instead of running a shell command, Claude Code sends your prompt and the hook's in
For decisions that require judgment rather than deterministic rules, use `type: "prompt"` hooks. Instead of running a shell command, Claude Code sends your prompt and the hook's in
+1 −1 lines
Upstream edited 29 Sep 2026 00:19 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
hooks
±changed
+6−6
claude-codechanged
hooks
| `model` | no | Model to use for evaluation. Defaults to a fast model |
| `model` | no | Model to use for evaluation. Defaults to the model Claude Code uses for [background functionality](/docs/en/costs#background-token-usage) |
| `permissionDecisionReason` | For `"allow"` and `"ask"`, shown to the user but not Claude. For `"deny"`, shown to Claude. For `"defer"`, ignored |
| `permissionDecisionReason` | For `"ask"`, shown to the user but not Claude. For `"deny"`, shown to Claude. For `"allow"` and `"defer"`, written to the [debug log](#debug-hooks) o
"tool_response": " 1\tfrom __future__ import annotations\n 2\t..."
+6 −6 lines
Upstream edited 29 Sep 2026 00:19 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
vs-code
±changed
+10−1
claude-codechanged
vs-code
You can reposition the Claude panel, run multiple conversations, organize the sessions list into groups, or switch to terminal mode.
You can reposition the Claude panel, run multiple conversations, group or filter the sessions list, or switch to terminal mode.
### Filter the sessions list
+10 −1 lines
Upstream edited 29 Sep 2026 00:13 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
settings-reference
±changed
+97−1
claude-codechanged
settings-reference
| [`claudeInChromeDefaultEnabled`](#claudeinchromedefaultenabled) | Turn on [Chrome integration](/docs/en/chrome) in every interactive CLI session without passing `--chrome` | Glob
| [`copyFullResponse`](#copyfullresponse) | Make [`/copy`](/docs/en/commands) copy the full response without showing the code block picker | Global config settings | Global config
| [`defaultToAgentsView`](#defaulttoagentsview) | Open [agent view](/docs/en/agent-view) instead of a new conversation when you run `claude` with no arguments | Global config setti
| [`leftArrowOpensAgents`](#leftarrowopensagents) | Turn off the `←` shortcut that [backgrounds the session and opens agent view](/docs/en/agent-view#switch-sessions-without-leavin
| [`prStatusFooterEnabled`](#prstatusfooterenabled) | Turn off the prompt footer's [PR review status](/docs/en/interactive-mode#pr-review-status) badge and the pull request check b
+97 −1 lines
Upstream edited 29 Sep 2026 00:12 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
agent-view
±changed
+1−1
claude-codechanged
agent-view
You can turn this shortcut off with the `leftArrowOpensAgents` setting in `/config`.
You can turn this shortcut off for foreground sessions with the [`leftArrowOpensAgents`](/docs/en/settings-reference#leftarrowopensagents) setting in `/config`.
+1 −1 lines
Upstream edited 29 Sep 2026 00:11 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
authentication
±changed
+8−0
claude-codechanged
authentication
To stay signed in to multiple accounts at once, such as work and personal accounts, give each account its own configuration directory. When you start `claude`, set the [`CLAUDE_CON
```bash theme={null}
alias claude-work='CLAUDE_CONFIG_DIR=~/.claude-work claude'
+8 −0 lines
Upstream edited 29 Sep 2026 00:09 UTC Recorded here 29 Sep 2026 00:37 UTC
claude-code
mcp
±changed
+5−10
claude-codechanged
mcp
Two actions in a server's menu in `/mcp` also affect that server's cache entry:
* **Reconnect**: on a `cached` server, Claude Code connects it now rather than on its first tool call and keeps the entry. On a connected or failed server, Claude Code reconnects i
* **Clear authentication**: Claude Code revokes the server's authentication and also discards the entry.
+5 −10 lines
Upstream edited 29 Sep 2026 00:08 UTC Recorded here 29 Sep 2026 00:37 UTC
28 Sep 2026
62 pages
+5356 −4868 lines
claude-code
settings-reference
±changed
+13−12
claude-codechanged
settings-reference
The `/model` picker has a **Default** option that resolves to your [organization default model](/docs/en/model-config#organization-default-model) when one applies, and otherwise to
The `/model` picker has a **Default** option, and [`default` model setting](/docs/en/model-config#default-model-setting) describes the model it resolves to. An [`availableModels`](
* **Effect on ultracode**: a cap below `xhigh` makes [ultracode](#ultracode) unavailable on the models the cap applies to
Start sessions with [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode) on. With it on, Claude plans a workflow for each substantive task instead of waiting for you to
+13 −12 lines
Upstream edited 28 Sep 2026 23:55 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
model-config
±changed
+20−12
claude-codechanged
model-config
On an Enterprise plan, when you're logged in with your claude.ai account and save a default with `/model`, Claude Code also records the choice on that account. This requires Claude
* When your admin hasn't set an [organization default model](#organization-default-model), the [Default option](#default-model-setting) can resolve to the recorded model, and when
* If [model restrictions](#restrict-model-selection) exclude the recorded model or it isn't available to your account, and your admin hasn't set an organization default model, the
* If you choose Default or `opusplan` in `/model`, the recorded choice doesn't change.
+20 −12 lines
Upstream edited 28 Sep 2026 23:55 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
monitoring-usage
±changed
+14−7
claude-codechanged
monitoring-usage
| `OTEL_LOG_TOOL_DETAILS` | Enable logging of tool parameters and input arguments in tool events and trace span attributes: Bash commands, MCP server and tool names, skill names, u
| `OTEL_LOG_TOOL_DETAILS` | Enable logging of tool parameters and input arguments in tool events and trace span attributes: Bash commands, MCP server and tool names, skill names, u
Claude Code derives these attributes once per session from the repository's `origin` remote. The HTTPS and SSH remotes of one repository produce identical values:
Claude Code derives these attributes once per session from the repository's `origin` remote. When the HTTPS and SSH remotes of a repository name the same host and the same path, as
To get these attributes from a [cloud session](/docs/en/claude-code-on-the-web), set the telemetry variables, including `OTEL_METRICS_INCLUDE_REPOSITORY`, on its [cloud environment
+14 −7 lines
Upstream edited 28 Sep 2026 23:54 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
managed-mcp
±changed
+1−1
claude-codechanged
managed-mcp
When [OpenTelemetry export](/docs/en/monitoring-usage) is configured, Claude Code can record which MCP servers and tools users invoke. Set `OTEL_LOG_TOOL_DETAILS=1` to include MCP
When you configure [OpenTelemetry export](/docs/en/monitoring-usage), Claude Code can record which MCP servers and tools users invoke. Set `OTEL_LOG_TOOL_DETAILS=1` to include MCP
+1 −1 lines
Upstream edited 28 Sep 2026 23:54 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
agent-sdk/observability
±changed
+1−1
claude-codechanged
agent-sdk/observability
| `OTEL_LOG_TOOL_DETAILS=1` | Tool input arguments (file paths, shell commands, search patterns) on `claude_code.tool_result` events |
| `OTEL_LOG_TOOL_DETAILS=1` | Tool input arguments such as file paths, shell commands, and search patterns on `claude_code.tool_result` events, and real agent, skill, plugin, and M
+1 −1 lines
Upstream edited 28 Sep 2026 23:54 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
managed-settings
±changed
+29−12
claude-codechanged
managed-settings
| HKCU registry, Windows and WSL | As a Windows `HKCU` registry value; see [where each mechanism stores the policy](#where-each-mechanism-stores-the-policy) | Read at startup and c
| HKCU registry, Windows and WSL | As a Windows `HKCU` registry value; see [where each mechanism stores the policy](#where-each-mechanism-stores-the-policy) | Read at startup and c
4. The HKCU registry, on Windows, and on WSL once the HKLM registry or the Windows managed settings file turns [`wslInheritsWindowsSettings`](/docs/en/settings-reference#wslinherit
4. The HKCU registry, on Windows, and on WSL once the HKLM registry or the Windows managed settings file turns [`wslInheritsWindowsSettings`](/docs/en/settings-reference#wslinherit
+29 −12 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
workflows
±changed
+10−10
claude-codechanged
workflows
Ultracode is a Claude Code setting that combines `xhigh` [reasoning effort](/docs/en/model-config#adjust-effort-level) with automatic workflow orchestration. With it on, Claude pla
Ultracode is a Claude Code setting that turns on automatic workflow orchestration for the session, at whichever [effort level](/docs/en/model-config#adjust-effort-level) the sessio
To start a session with ultracode already on, launch with `claude --effort ultracode`. Requires Claude Code v2.1.203 or later.
To turn it on while you choose a model, move the `/model` picker's effort slider to `ultracode` with the arrow keys. [Adjust effort level](/docs/en/model-config#adjust-effort-level
+10 −10 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
vs-code
±changed
+2−0
claude-codechanged
vs-code
When [dynamic workflows](/docs/en/workflows) are enabled and the current model supports it, an **Ultracode** switch appears under the **Effort** row. Turn it on to have Claude pl
+2 −0 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
| `effort.level` | Current reasoning effort (`low`, `medium`, `high`, `xhigh`, or `max`). Reflects the live session value, including mid-session `/effort` changes. Ultracode is not
| `effort.level` | Current reasoning effort (`low`, `medium`, `high`, `xhigh`, or `max`). Reflects the live session value, including mid-session `/effort` changes. Absent when the
+1 −1 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Ultracode is not a distinct level and reports as `xhigh`. Use this to adapt skill instr
| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Use this to adapt skill instructions to the active effort setting. |
+1 −1 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `effort` | Object with a `level` field holding the [effort level](/docs/en/model-config#adjust-effort-level) in effect when the hook runs: `"low"`, `"medium"`, `"high"`, `"xhigh"
| `effort` | Object with a `level` field holding the [effort level](/docs/en/model-config#adjust-effort-level) in effect when the hook runs: `"low"`, `"medium"`, `"high"`, `"xhigh"
+1 −1 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/work
`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which requests `xhigh` effort with [ultracode](/docs/en/work
+1 −1 lines
Upstream edited 28 Sep 2026 23:53 UTC Recorded here 29 Sep 2026 00:07 UTC
claude-code
prompt-caching
±changed
+33−36
claude-codechanged
prompt-caching
| Layer | Content | Changes when |
| --------------- | ----------------------------------------------- | ----------------------------------------------- |
| System prompt | Core instructions, tool definitions | The set of loaded tool definitions changes |
| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |
| Conversation | Your messages, Claude's responses, tool results | Every turn |
+33 −36 lines
Upstream edited 28 Sep 2026 23:26 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/python
±changed
+435−435
claude-codechanged
agent-sdk/python
| Feature | `query()` | `ClaudeSDKClient` |
| :------------------ | :--------------------------------------------- | :--------------------------------- |
| **Session** | Creates a new session by default | Reuses same session |
| **Conversation** | Single exchange | Multiple exchanges in same context |
| **Connection** | Managed automatically | Manual control |
+435 −435 lines
Upstream edited 28 Sep 2026 23:26 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+32−31
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 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
* **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 and security and safety instructions. Set `systemPrompt: { type: "preset",
| You're building | Use | What you get
+32 −31 lines
Upstream edited 28 Sep 2026 23:26 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+63−61
claude-codechanged
vs-code
* To report a bug, click **Report a problem** at the bottom of the menu, or type `/bug` or `/feedback` with an optional description that prefills the report. When you submit the
If your organization's policy turns product feedback off, **Report a problem** doesn't appear in the menu, and `/bug` and `/feedback` show a `Feedback is turned off by your org
* To report a bug, click **Report a problem** at the bottom of the menu, or type `/bug` or `/feedback` with an optional description that prefills the report. When you submit the
+63 −61 lines
Upstream edited 28 Sep 2026 23:18 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
keybindings
±changed
+213−210
claude-codechanged
keybindings
| Field | Description |
| :--------- | :------------------------------------------------- |
| `$schema` | Optional JSON Schema URL for editor autocompletion |
| `$docs` | Optional documentation URL |
| `bindings` | Array of binding blocks by context |
+213 −210 lines
Upstream edited 28 Sep 2026 23:18 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
errors
±changed
+337−331
claude-codechanged
errors
| Message
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| `API Error: 500 Internal server error`
| `API Error: Repeated 529 Overloaded errors`
| `Opus is experiencing high load` / `Fable is experiencing high load`
+337 −331 lines
Upstream edited 28 Sep 2026 23:17 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
permission-modes
±changed
+51−50
claude-codechanged
permission-modes
| Mode | What runs without asking |
| :------------------------------------------------------------------ | :-------------------------------------------------------------------------------------------------------- |
| `default` | Reads only |
| [`acceptEdits`](#auto-approve-file-edits-with-acceptedits-mode) | Reads, file edits, and common filesystem commands (`mkdir`, `touch`, `mv`, `cp`, etc.) |
| [`plan`](#analyze-before-you-edit-with-plan-mode) | Reads, plus classifier-approved commands when [auto mode](#eliminate-prompts-with-auto-mode) is available |
+51 −50 lines
Upstream edited 28 Sep 2026 23:15 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
remote-control
±changed
+23−23
claude-codechanged
remote-control
* **Workspace trust**: run `claude` in your project directory at least once to accept the workspace trust dialog. The startup trust dialog never saves trust for your home directory
* **Workspace trust**: in a directory you haven't trusted yet, `claude remote-control` prints what trusting it turns on and asks `Trust <directory>? [y/N]` before it starts. Answer
| Flag | Description
| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------
| `--name "My Project"` | Set a custom session title visible in the session list at claude.ai/code.
+23 −23 lines
Upstream edited 28 Sep 2026 23:14 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
auto-mode-config
±changed
+9−9
claude-codechanged
auto-mode-config
| Boundary | Mechanism | Behavior in auto mode
| :-------------------------------- | :--------------------------------------------------------- | :--------------------------------------------------------------------------------
| Prompt before the action | `permissions.ask` | Always prompts for a command that matches a content-scoped rule like the recipe a
| Never run the action | `permissions.deny` | Blocks before the classifier is consulted. Neither the classifier nor user intent
| Boundary | Mechanism | Behavior in auto mode |
+9 −9 lines
Upstream edited 28 Sep 2026 19:33 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
auto-mode-config
±changed
+2−0
claude-codechanged
auto-mode-config
The text in square brackets, such as `[Data Exfiltration]`, is the name of the rule the classifier matched. To read that rule's full wording, see [Inspect the defaults and your eff
+2 −0 lines
Upstream edited 28 Sep 2026 19:33 UTC Recorded here 28 Sep 2026 19:37 UTC
claude-code
mcp
±changed
+26−26
claude-codechanged
mcp
| Scope | Loads in | Shared with team | Stored in |
| ------------------------- | -------------------- | ------------------------ | --------------------------- |
| [Local](#local-scope) | Current project only | No | `~/.claude.json` |
| Scope | Loads in | Shared with team | Stored in |
| - | - | - | - |
+26 −26 lines
Upstream edited 28 Sep 2026 18:43 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
artifacts
±changed
+25−25
claude-codechanged
artifacts
| Constraint | Effect
| :---------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------
| Constraint | Effect |
| :- | :- |
| No backend | An artifact is a static page. It can't authenticate viewers itself.
+25 −25 lines
Upstream edited 28 Sep 2026 18:43 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
mcp
±changed
+2−0
claude-codechanged
mcp
Anthropic also provides some connectors itself, without you or an admin adding them. On accounts where [Claude Docs](/docs/en/artifacts#write-a-document-with-claude-docs) is availa
+2 −0 lines
Upstream edited 28 Sep 2026 18:43 UTC Recorded here 28 Sep 2026 19:07 UTC
claude-code
commands
±changed
+2−1
claude-codechanged
commands
| `/design [brief]` | **[Skill](/docs/en/skills#bundled-skills).** Draft UI mockups, scre
| `/design [brief]` | **[Skill](/docs/en/skills#bundled-skills).** Draft UI mockups, scre
| `/slides [brief]` | **[Skill](/docs/en/skills#bundled-skills).** Make a new presentatio
+2 −1 lines
Upstream edited 28 Sep 2026 18:43 UTC Recorded here 28 Sep 2026 19:07 UTC
claude-code
artifacts
±changed
+30−4
claude-codechanged
artifacts
## Draft a design canvas
To mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes
## Start from a Slides, Design, or Docs template
+30 −4 lines
Upstream edited 28 Sep 2026 18:43 UTC Recorded here 28 Sep 2026 19:07 UTC
claude-code
changelog
±changed
+103−0
claude-codechanged
changelog
<Update label="2.1.284" description="September 28, 2026">
* Added Claude Sonnet 5.5 (`claude-sonnet-5-5`), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with \$0.20/Mtok cache reads
* Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later
* Added dollar amounts to the Claude apps gateway spend limit in `/usage` and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this versio
+103 −0 lines
Upstream edited 28 Sep 2026 18:16 UTC Recorded here 28 Sep 2026 18:37 UTC
claude-code
settings-reference
±changed
+316−316
claude-codechanged
settings-reference
| Key | Description
| :---------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------
| [`advisorModel`](#advisormodel) | Pick which model answers when Claude asks the [advisor tool](/docs/en/advi
| [`agent`](#agent) | Start every session as a named [subagent](/docs/en/sub-agents) with its pr
| [`agentPushNotifEnabled`](#agentpushnotifenabled) | Let Claude send a [push notification to your phone](/docs/en/remote-contro
+316 −316 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
model-config
±changed
+82−82
claude-codechanged
model-config
| Model alias | Behavior
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------
| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias
| **`best`** | Uses the model the [`fable` alias resolves to](#fable-alias-resolution) where Fable is available to you, otherwise the same model as `opus`
| **`fable`** | Uses the [Fable model for your provider](#fable-alias-resolution) for your hardest and longest-running tasks
+82 −82 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
llm-gateway-protocol
±changed
+43−43
claude-codechanged
llm-gateway-protocol
| Format | Selected by | Endpoints
| :--------------------------------------- | :------------------------------------------------------------ | :----------------------------------------------------------------------
| Anthropic Messages | `ANTHROPIC_BASE_URL` | `/v1/messages`, `/v1/messages/count_tokens` (optional)
| Amazon Bedrock InvokeModel | `ANTHROPIC_BEDROCK_BASE_URL` with `CLAUDE_CODE_USE_BEDROCK=1` | `/model/{model}/invoke`, `/model/{model}/invoke-with-response-stream`,
| Google Cloud's Agent Platform rawPredict | `ANTHROPIC_VERTEX_BASE_URL` with `CLAUDE_CODE_USE_VERTEX=1` | `:rawPredict`, `:streamRawPredict`, `count-tokens:rawPredict` (optional
+43 −43 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
interactive-mode
±changed
+150−150
claude-codechanged
interactive-mode
| Shortcut | Description
| :------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------
| `Ctrl+C` | Interrupt, or clear input
| `Ctrl+X Ctrl+K` | Stop all running [background subagents](/docs/en/sub-agents#run-subagents-in-foregr
| `Ctrl+D` | Exit Claude Code session
+150 −150 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
feature-availability
±changed
+17−17
claude-codechanged
feature-availability
| Feature | Pro | Max | Team | Enterprise |
| :-------------------------------------------------------------------------- | :-- | :-- | :------------ | :-------------------------------- |
| [Cloud sessions](/docs/en/claude-code-on-the-web) | ✓ | ✓ | ✓ | ✓ <sup><a href="#fn6">6</a></sup> |
| [Routines](/docs/en/routines) | ✓ | ✓ | ✓ | ✓ |
| [Remote Control](/docs/en/remote-control) | ✓ | ✓ | Admin-enabled | Admin-enabled |
+17 −17 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
desktop
±changed
+86−86
claude-codechanged
desktop
| Mode | Settings key | Behavior
| ---------------------- | ------------------- | -----------------------------------------------------------------------------------------------------------------------------------
| **Manual** | `default` | Claude asks before editing files or running commands. You see a diff and can accept or reject each change.
| **Accept edits** | `acceptEdits` | Claude auto-accepts file edits and common filesystem commands like `mkdir`, `touch`, and `mv`, but still asks before running other
| **Plan** | `plan` | Claude reads files and runs commands to explore, then proposes a plan without editing your source code. Good for complex tasks wher
+86 −86 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
costs
±changed
+18−18
claude-codechanged
costs
| Your role | What `/usage-credits` does
| :----------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------
| Pro or Max subscriber | Opens [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai in the browser. In its **Usage credits** section yo
| Team or Enterprise member with billing access | Opens your organization's usage settings, [**Admin settings > Usage**](https://claude.ai/admin-settings/usage), in the browser
| Team or Enterprise member without billing access | Asks you to confirm, then sends a request to your organization's admins. Before v2.1.211, Claude Code sent the request without
+18 −18 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
context-window
±changed
+13−13
claude-codechanged
context-window
| Mechanism | After compaction
| :-------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------
| System prompt and output style | Both still apply
| Project-root CLAUDE.md and unscoped rules | Re-injected from disk
| Auto memory | Re-injected from disk
+13 −13 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
communications-kit
±changed
+32−32
claude-codechanged
communications-kit
| Item | Why it matters
| ------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------
| `#claude-code` channel created and linked in the message | Gives questions one place to land
| Install command tested on at least one machine in your environment | Catches proxy or firewall issues before everyone hits them at once
| Security and data-handling link ready ([Data usage](/docs/en/data-usage) or your internal equivalent) | "Where does my code go?" will be the first reply
+32 −32 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
advisor
±changed
+24−24
claude-codechanged
advisor
| Main model | Accepted advisors | Notes |
| ---------------------- | ------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| Haiku 4.5 | Fable, Opus, Sonnet | Haiku can call the advisor but cannot act as one |
| Sonnet 4.6 | Fable, Opus, Sonnet | |
| Sonnet 5.5 or Sonnet 5 | Fable, Opus 4.7 or later, Sonnet 5 or later | A Sonnet 4.6 advisor is rejected, and the API refuses an Opus 4.6 advisor |
+24 −24 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
On models that always think, such as Opus 5.5 and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code omits the `thin
On models that always think, such as Opus 5.5, Sonnet 5.5, and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code om
+1 −1 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
prompt-caching
±changed
+3−3
claude-codechanged
prompt-caching
* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Opus 5.5 and Fable 5.1 with an API key or
* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Opus 5.5, Sonnet 5.5, and Fable 5.1 with a
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, and Opus 5 is also a model switch. When a safety classifier flags a request in
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models, Opus 5.5, Sonnet 5.5, and Opus 5 is also a model switch. When a safety classifier flags
On Opus 5.5 and Fable 5.1 with an API key or a Claude subscription, changing effort keeps the cache, and Claude Code applies the new level without asking. This doesn't apply on Ama
+3 −3 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-co
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-co
Only Claude Sonnet 5, Opus 4.7 or later, and the Fable models are supported on these providers. On any other model, the session starts in Manual instead.
Only Claude Sonnet 5 or later, Opus 4.7 or later, and the Fable models are supported on these providers. On any other model, the session starts in Manual instead.
+2 −2 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
model-config
±changed
+78−57
claude-codechanged
model-config
| Model alias | Behavior
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------
| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias
| **`best`** | Uses the model the [`fable` alias resolves to](#fable-alias-resolution) where Fable is available to you, otherwise the same model as `opus`
| **`fable`** | Uses the [Fable model for your provider](#fable-alias-resolution) for your hardest and longest-running tasks
+78 −57 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
* Same model as a built-in alias: when a discovered explicit ID names the model that a built-in alias currently resolves to, the picker shows only the alias row. For example, while
* Same model as a built-in alias: when a discovered explicit ID names the model that a built-in alias currently resolves to, the picker shows only the alias row. For example, while
+1 −1 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking
+1 −1 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
feature-availability
±changed
+4−4
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and th
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5 or later, Opus 4.7 or late
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5 or later, Opus 4.7 or later, and Fable models only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5, Opus 4.7 or later, and Fable models only
+4 −4 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
errors
±changed
+5−5
claude-codechanged
errors
| `Opus 5.5's safeguards flagged this session`
| `<model>'s safeguards flagged this session`
* Run `claude update` and restart Claude Code. Opus 4.7 needs v2.1.111 or later. Opus 4.8 needs v2.1.154 or later. Sonnet 5 needs v2.1.197 or later. Opus 5 needs v2.1.219 or later.
* Run `claude update` and restart Claude Code. Opus 4.7 needs v2.1.111 or later. Opus 4.8 needs v2.1.154 or later. Sonnet 5 needs v2.1.197 or later. Opus 5 needs v2.1.219 or later.
* If you hit this in the [Agent SDK](/docs/en/agent-sdk/overview), upgrade the SDK package instead. Opus 4.8 needs TypeScript SDK v0.3.154 or later and Python SDK v0.2.88 or later.
+5 −5 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
env-vars
±changed
+5−4
claude-codechanged
env-vars
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants a
| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/docs/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fal
| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/docs/en/model-config#extended-context) support. When set, 1M model variants a
| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/docs/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fal
| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and g
+5 −4 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
desktop
±changed
+3−3
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
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
[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
+3 −3 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
+1 −1 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
context-window
±changed
+3−3
claude-codechanged
context-window
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended c
Sonnet 5 runs with the 1M context window and has no `[1m]` variant to select. See [Sonnet 5 context window](/docs/en/model-config#sonnet-5-context-window) for its auto-compaction t
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [
+3 −3 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
communications-kit
±changed
+5−4
claude-codechanged
communications-kit
biology content falls back to Opus automatically. Opus 5.5 and Opus 5 run
their own checks too: flagged content switches to an earlier Opus, except
that flagged biology content on Opus 5 is refused.
biology content falls back to Opus automatically. Opus 5.5, Sonnet 5.5, and
Opus 5 run their own checks too: flagged content switches to an earlier model
+5 −4 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
advisor
±changed
+10−10
claude-codechanged
advisor
| Main model | Accepted advisors | Notes |
| -------------------- | ---------------------------------- | ---------------------------------------------------------------------------------------------- |
| Haiku 4.5 | Fable, Opus, Sonnet | Haiku can call the advisor but cannot act as one |
| Sonnet 4.6 | Fable, Opus, Sonnet | |
| Sonnet 5 | Fable, Opus 4.7 or later, Sonnet 5 | A Sonnet 4.6 advisor is rejected, and the API refuses an Opus 4.6 advisor |
+10 −10 lines
Upstream edited 28 Sep 2026 17:53 UTC Recorded here 28 Sep 2026 18:07 UTC
claude-code
model-config
±changed
+10−8
claude-codechanged
model-config
| Level | When to use it |
| :---------- | :------------------------------------------------------------------------------------------------------------------------------------- |
| `low` | Reserve for short, scoped, latency-sensitive tasks that are not intelligence-sensitive |
| `medium` | Reduces token usage for cost-sensitive work that can trade off some intelligence. The default on Opus 5.5 |
| `high` | Balances token usage and intelligence. The default on every model except Opus 5.5 and Opus 4.7 |
+10 −8 lines
Upstream edited 28 Sep 2026 17:21 UTC Recorded here 28 Sep 2026 17:37 UTC
claude-code
agent-sdk/user-input
±changed
+33−33
claude-codechanged
agent-sdk/user-input
| Argument | Description
| ----------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------
| `toolName` | The name of the tool Claude wants to use (for example, `"Bash"`, `"Write"`, `"Edit"`)
| `input` | The parameters Claude is passing to the tool. Contents vary by tool.
| Argument | Description |
+33 −33 lines
Upstream edited 28 Sep 2026 00:43 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/typescript
±changed
+390−390
claude-codechanged
agent-sdk/typescript
| Parameter | Type | Description |
| :-------- | :--------------------------------------------------------------- | :---------------------------------------------------------------- |
| `prompt` | `string \| AsyncIterable<`[`SDKUserMessage`](#sdkusermessage)`>` | The input prompt as a string or async iterable for streaming mode |
| `options` | [`Options`](#options) | Optional configuration object (see Options type below) |
| Parameter | Type | Description |
+390 −390 lines
Upstream edited 28 Sep 2026 00:43 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/user-input
±changed
+2−0
claude-codechanged
agent-sdk/user-input
In TypeScript, skip the always-allow choice for a request whose options carry [`suppressAlwaysAllowRule: true`](/docs/en/agent-sdk/typescript#canusetool). The hint requires Age
+2 −0 lines
Upstream edited 28 Sep 2026 00:43 UTC Recorded here 28 Sep 2026 01:07 UTC
claude-code
agent-sdk/typescript
±changed
+122−36
claude-codechanged
agent-sdk/typescript
Re-exported from `@modelcontextprotocol/sdk/types.js`. All fields are optional hints; clients should not rely on them for security decisions.
Defined in `@modelcontextprotocol/sdk/types.js`. All fields are optional hints; clients should not rely on them for security decisions.
| Property | Type | Description |
| :------------- | :-------------------- | :-------------------------------------------------------------------------- |
| `sessionId` | `string` | Unique session identifier (UUID) |
+122 −36 lines
Upstream edited 28 Sep 2026 00:43 UTC Recorded here 28 Sep 2026 01:07 UTC
claude-code
sessions
±changed
+52−52
claude-codechanged
sessions
| Command | What it does |
| :---------------------------------- | :--------------------------------------------------------------------------------------------------------------------- |
| `claude --continue` | Reopens the most recent conversation in the current directory |
| `claude --resume` | Opens the [session picker](#use-the-session-picker) |
| `claude --resume <name>` | Resumes the named session directly |
+52 −52 lines
Upstream edited 28 Sep 2026 00:42 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
claude-code-on-the-web
±changed
+21−21
claude-codechanged
claude-code-on-the-web
| Method | How you connect | Repositories sessions can reach
| :--------------- | :----------------------------------------------------------------------------------------- | :-----------------------------------------------------------------
| **GitHub App** | Authorize the Claude GitHub App during [web onboarding](/docs/en/web-quickstart) | Any public repository, and private repositories that the Clau
| **`/web-setup`** | Run `/web-setup` in your terminal to send your local `gh` CLI token to your Claude account | Any repository your `gh` token can access, whether or not the Clau
| Method | How you connect | Repositories sessions can reach | Best for |
+21 −21 lines
Upstream edited 28 Sep 2026 00:42 UTC Recorded here 28 Sep 2026 23:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.