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
146 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
5,575 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
3 Oct 2026
44 pages
+493 −330 lines
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
As of v2.1.199, a subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude instead of returning the error text
A subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude. What Claude receives depends on where the subagent
As of v2.1.199, `SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned ba
`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent t
+2 −2 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
settings-reference
±changed
+5−7
claude-codechanged
settings-reference
Protect environment variables from sandboxed commands. With `"mode": "deny"`, Claude Code removes the variable from the environment of sandboxed commands. With `"mode": "mask"`, sa
Protect environment variables from sandboxed commands. With `"mode": "deny"`, Claude Code removes the variable from the environment of sandboxed commands. With `"mode": "mask"`, sa
The `name` must start with a letter or underscore and contain only letters, digits, and underscores. Claude Code merges the arrays from every settings scope the session loads, and
The `name` must start with a letter or underscore and contain only letters, digits, and underscores. Claude Code merges the arrays from every settings scope the session loads, and
| `injectHosts` | array of strings, each a host that [`sandbox.network.allowedDomains`](#sandbox-network-alloweddomains) also admits | Narrow the hosts where the sandbox proxy subs
+5 −7 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
sandboxing
±changed
+2−4
claude-codechanged
sandboxing
When you mask a credential, Claude Code shows sandboxed commands a per-session placeholder called the sentinel, and the [sandbox proxy](#network-isolation) substitutes the real val
Masking environment variables requires Claude Code v2.1.199 or later. The [`sandbox.credentials`](/docs/en/settings-reference#sandbox-credentials) reference lists every field.
When you mask a credential, Claude Code shows sandboxed commands a per-session placeholder called the sentinel, and the [sandbox proxy](#network-isolation) substitutes the real val
The built-in proxy enforces the allowlist based on the requested hostname and, by default, does not terminate or inspect TLS traffic. The experimental [`network.tlsTerminate`](/d
+2 −4 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
Claude Code denies calls matching your explicit [`ask` rules](/docs/en/permissions#manage-permissions) rather than prompting. It also denies the built-in `AskUserQuestion` tool eve
Claude Code denies calls matching your explicit [`ask` rules](/docs/en/permissions#manage-permissions) rather than prompting. It also denies the built-in `AskUserQuestion` tool eve
+1 −1 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
mcp
±changed
+0−2
claude-codechanged
mcp
The `anthropic/requiresUserInteraction` annotation requires Claude Code v2.1.199 or later. Earlier versions ignore it and apply the standard permission flow.
+0 −2 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
As of v2.1.199, an MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't s
An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval
+1 −1 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
As of v2.1.199, an idle teammate's row stays in the panel while any teammate or subagent is still working, so you can select it to review its transcript or send it more work. Once
An idle teammate's row stays in the panel while any teammate or subagent is still working, so you can select it to review its transcript or send it more work. Once every agent in t
+1 −1 lines
Upstream edited 3 Oct 2026 01:12 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
routines
±changed
+1−1
claude-codechanged
routines
In the **Edit cloud environment** dialog, change **Network access** to **Custom** and enter your domains in **Allowed domains**. Check **Also include default list of common pac
In the **Edit environment** dialog, change **Network access** to **Custom** and enter your domains in **Allowed domains**. Check **Also include default list of common package m
+1 −1 lines
Upstream edited 3 Oct 2026 01:11 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* In the **Edit cloud environment** dialog, change **Network access** from **Trusted** to **Custom**, then add the blocked domain to **Allowed domains**. Enter one domain per line.
* In the **Edit environment** dialog, change **Network access** from **Trusted** to **Custom**, then add the blocked domain to **Allowed domains**. Enter one domain per line. Check
+1 −1 lines
Upstream edited 3 Oct 2026 01:11 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
cloud-environments
±changed
+2−2
claude-codechanged
cloud-environments
You add credentials one at a time from the editor of an environment that already exists. The dialog for a new environment doesn't offer them. There's no edit, either. To change a c
You add credentials one at a time, and you can't edit a credential after you add it. To change a credential's hosts or value, delete it and add it again.
[Open the environment for editing](#configure-your-environment) at [claude.ai/code](https://claude.ai/code). In the **Edit cloud environment** dialog, find **API credentials**
[Open the environment for editing](#configure-your-environment) at [claude.ai/code](https://claude.ai/code). In the **Edit environment** dialog, find the **API credentials** se
+2 −2 lines
Upstream edited 3 Oct 2026 01:11 UTC Recorded here 3 Oct 2026 01:37 UTC
claude-code
errors
±changed
+18−0
claude-codechanged
errors
| `API Error: Output blocked by content filtering policy` | [Request errors](#output-blocked-by-content-filtering-policy) |
* A response the API's output content filter blocked. Claude Code shows [Output blocked by content filtering policy](#output-blocked-by-content-filtering-policy) at once and doesn'
| [`CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES`](/docs/en/env-vars) | unset | Limit on re-sends of a [non-streaming request](#streaming-response-ended-before-any-complete-data-was-re
### Output blocked by content filtering policy
+18 −0 lines
Upstream edited 3 Oct 2026 00:40 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude
Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude
+1 −1 lines
Upstream edited 3 Oct 2026 00:39 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
* Projects are available at claude.ai/code, in the desktop app, and in the Claude mobile app, not in the terminal CLI, the VS Code extension, or the JetBrains plugin, and not throu
* Projects are available at claude.ai/code, in the desktop app, and in the Claude mobile app, not in the terminal CLI, the VS Code extension, or the JetBrains plugin, and not throu
+1 −1 lines
Upstream edited 3 Oct 2026 00:39 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
claude-directory
±changed
+7−5
claude-codechanged
claude-directory
Scratchpad files last as long as the session's transcript: the [retention sweep](#cleaned-up-automatically) deletes the directory when it deletes the transcript, and [`claude proje
Scratchpad files last as long as the session's transcript: the [retention sweep](#cleaned-up-automatically) deletes the directory when it deletes the transcript, and [`claude purge
Run `claude project purge` to delete the state Claude Code holds for one project. It deletes:
Run `claude purge` to delete the state Claude Code holds for one project. It deletes:
Before v2.1.288, the command was `claude project purge`.
+7 −5 lines
Upstream edited 3 Oct 2026 00:39 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
accessibility
±changed
+10−10
claude-codechanged
accessibility
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersRed
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersRed
* For every session on the machine: add `"axScreenReader": true` to your user [settings file](/docs/en/settings). The setting applies in any terminal, including the VS Code integra
* For every session on the machine: add `"axScreenReader": true` to your user [settings file](/docs/en/settings.md). The setting applies in any terminal, including the VS Code inte
Claude Code leaves everything it prints in your terminal's scrollback, so you can re-read earlier turns with your screen reader's review commands or your terminal's search. Claude
+10 −10 lines
Upstream edited 3 Oct 2026 00:38 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
plugins/manifest-reference
±changed
+1−0
claude-codechanged
plugins/manifest-reference
| `requestTimeout` | No | Milliseconds to wait for the server to answer a request, a positive integer. Defaults to `60000`, so a request the server never answers fails after 60 sec
+1 −0 lines
Upstream edited 3 Oct 2026 00:38 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
* Expect `idle_prompt` about 60 seconds after Claude finishes responding, and only if you haven't typed since. Claude Code doesn't send `idle_prompt` while it waits for a claude.
* Expect `idle_prompt` about 60 seconds after Claude finishes responding, and only if you haven't typed since and no background agent, such as a background [subagent](/docs/en/su
+1 −1 lines
Upstream edited 3 Oct 2026 00:38 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
code-review
±changed
+1−0
claude-codechanged
code-review
* `--max-findings <n>`, `--max-findings all`, or `--max-findings default`: reports up to `n` findings, or every finding with `all`, in place of the review's usual limit. Later
+1 −0 lines
Upstream edited 3 Oct 2026 00:38 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
accessibility
±changed
+1−1
claude-codechanged
accessibility
* Claude Code doesn't announce a permission mode change made in any way other than cycling with `Shift+Tab`, such as entering [plan mode](/docs/en/permission-modes#analyze-before-y
* Claude Code doesn't announce a permission mode change you make with a command, such as entering [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) with
+1 −1 lines
Upstream edited 3 Oct 2026 00:38 UTC Recorded here 3 Oct 2026 01:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 3 Oct 2026 00:37 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
* **URL mode**: Claude Code asks whether to open a link in your browser and opens it when you accept. Servers use this mode for a flow that finishes outside the terminal, such as s
* **URL mode**: Claude Code asks whether to open a link in your browser. Servers use this mode for a flow that finishes outside the terminal, such as sign-in.
+1 −1 lines
Upstream edited 3 Oct 2026 00:36 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
errors
±changed
+2−2
claude-codechanged
errors
Claude messaged a stopped [agent team](/docs/en/agent-teams) teammate, and Claude Code brought it back without re-applying the [subagent definition](/docs/en/agent-teams#use-subage
Claude messaged a stopped [agent team](/docs/en/agent-teams) teammate, and Claude Code brought it back without re-applying the [subagent definition](/docs/en/agent-teams#use-subage
Claude sent a [cross-session message](/docs/en/cross-session-messaging) to another of your sessions on this machine, and that session's inbox discarded it before Claude in that ses
Claude sent a [cross-session message](/docs/en/cross-session-messaging) to another of your sessions on this machine, and that session's inbox discarded it before Claude in that ses
+2 −2 lines
Upstream edited 3 Oct 2026 00:36 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-deploy
±changed
+14−1
claude-codechanged
claude-apps-gateway-deploy
Register a confidential OAuth/OpenID Connect (OIDC) web application with a single redirect URI, `https://<gateway>/oauth/callback`, and assign it to the users or groups who should
Register a confidential OAuth/OpenID Connect (OIDC) web application with a single redirect URI, `https://<gateway>/oauth/callback`, and assign it to the users or groups who should
| A developer signs in, then every request from that session fails with a `431` error | The session token in every request's `Authorization` header lists the developer's IdP groups
### Request headers too large after sign-in
+14 −1 lines
Upstream edited 3 Oct 2026 00:22 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
claude-apps-gateway-config
±changed
+61−3
claude-codechanged
claude-apps-gateway-config
| `client_id` / `client_secret` | Yes | From your OAuth client registration |
| `client_id` | Yes | From your OAuth client registration |
| `client_secret` | Unless `token_endpoint_auth_method` is `private_key_jwt` | From your OAuth client registration. Leave it out when you use [certificate client authentication](#c
| `token_endpoint_auth_method` | No | Override the token-endpoint auth method. Accepts `client_secret_basic` or `client_secret_post`. Auto-negotiated by default. |
| `token_endpoint_auth_method` | No | How the gateway authenticates to the IdP's token endpoint: `client_secret_basic`, `client_secret_post`, or `private_key_jwt` for [certificate
+61 −3 lines
Upstream edited 3 Oct 2026 00:22 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) and [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | The `o
| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) and [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | The `o
+1 −1 lines
Upstream edited 3 Oct 2026 00:10 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
cross-session-messaging
±changed
+3−1
claude-codechanged
cross-session-messaging
When the default holds a message, Claude Code opens an approval dialog in the receiving session. The dialog shows the sender and a preview:
When the default holds a message in an interactive terminal session, Claude Code opens an approval dialog there. The dialog shows the sender and a preview:
A session in the VS Code extension or the Desktop app can't show the dialog. Claude Code keeps a held message there until the same deadline, as [Non-interactive sessions](#non-inte
+3 −1 lines
Upstream edited 3 Oct 2026 00:10 UTC Recorded here 3 Oct 2026 00:37 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
* **The [Enabled by default](#enable-chrome-by-default) setting connected it at start**: Claude Code asks you before browser actions in Manual, Edit automatically, Auto, and Bypass
* **The [Enabled by default](#enable-chrome-by-default) setting connected it at start**: Claude Code asks you before browser actions on a site you haven't allowed, in Manual, Edit
+1 −1 lines
Upstream edited 3 Oct 2026 00:09 UTC Recorded here 3 Oct 2026 00:37 UTC
2 Oct 2026
91 pages
+2800 −1383 lines
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 2 Oct 2026 23:37 UTC
claude-code
ultrareview
±changed
+1−5
claude-codechanged
ultrareview
| Team and Enterprise | none | billed as [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |
Because ultrareview always bills as usage credits outside the free runs, your account or organization must have usage credits turned on before you can launch a paid review. If usag
* If you can manage billing for your account, Claude Code links you to the billing settings where you can turn on usage credits.
* On Team and Enterprise plans, members without billing access send a request from the CLI asking their admin to turn on usage credits.
+1 −5 lines
Upstream edited 2 Oct 2026 23:20 UTC Recorded here 2 Oct 2026 23:37 UTC
claude-code
settings-reference
±changed
+6−3
claude-codechanged
settings-reference
| [`modelSettings`](#modelsettings) | Keep a saved [effort level](/docs/en/model-config#adjust-effort-level) per model, or cap one model's effort | Model and responses | Any file |
| [`modelSettings`](#modelsettings) | Keep a saved [effort level](/docs/en/model-config#adjust-effort-level) or [auto-compact window](/docs/en/model-config#set-the-auto-compact-win
* **Type**: object mapping a model name to an object with an `effortLevel` field, one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`, a [`maxEffortLevel`](#maxeffortlevel) field, o
* **Type**: object mapping a model name to an object with any of these fields:
* `effortLevel`: one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`
+6 −3 lines
Upstream edited 2 Oct 2026 23:16 UTC Recorded here 2 Oct 2026 23:37 UTC
claude-code
model-config
±changed
+5−4
claude-codechanged
model-config
If you set `ANTHROPIC_BASE_URL` to an [LLM gateway](/docs/en/llm-gateway) or another proxy, Claude Code gives each model it recognizes the same context window the model has on the
If you set `ANTHROPIC_BASE_URL` to an [LLM gateway](/docs/en/llm-gateway) or another proxy, Claude Code gives each model it recognizes the same context window the model has on the
You can set the auto-compact window in three places:
* **For this session and later ones**: run `/autocompact` with a value, like `/autocompact 500k`. Claude Code saves it to your user settings as [`autoCompactWindow`](/docs/en/setti
+5 −4 lines
Upstream edited 2 Oct 2026 23:16 UTC Recorded here 2 Oct 2026 23:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 2 Oct 2026 23:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `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
| `permissionDecisionReason` | For `"ask"`, shown to the user in the permission prompt. When Claude Code [denies the call](/docs/en/headless#turn-off-permission-prompts-in-unattend
+1 −1 lines
Upstream edited 2 Oct 2026 23:03 UTC Recorded here 2 Oct 2026 23:07 UTC
claude-code
plugins/publish
±changed
+30−15
claude-codechanged
plugins/publish
Anthropic's directory is the catalog people browse on claude.ai and in Cowork to add plugins and connectors. One listing there reaches people on claude.ai, in Cowork, and in Claude
Submitting requires a paid claude.ai plan. On Pro and Max you submit from your own account. On Team and Enterprise, an Owner can submit, and on Enterprise an Owner can also grant t
The submission steps, the checks each version must pass, and what happens after you publish are documented on claude.com, because they're the same whichever surface your users are
+30 −15 lines
Upstream edited 2 Oct 2026 22:48 UTC Recorded here 2 Oct 2026 23:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 2 Oct 2026 22:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
Choose how [background sessions](/docs/en/agent-view#how-file-edits-are-isolated) isolate their file edits. With `"worktree"`, Claude Code blocks `Edit` and `Write` in the main che
Choose how [background sessions](/docs/en/agent-view#how-file-edits-are-isolated) isolate their file edits. If you moved a session to the background with `←` or `/background`, that
+1 −1 lines
Upstream edited 2 Oct 2026 22:26 UTC Recorded here 2 Oct 2026 22:37 UTC
claude-code
agent-view
±changed
+4−3
claude-codechanged
agent-view
Every background session, whether started from agent view, `/bg`, or `claude --bg`, starts in your working directory. Before editing files, Claude moves the session into an isolate
When you dispatch a background session from agent view or start one with `claude --bg`, the session starts in your working directory. Before editing files, Claude moves the session
* You [moved a session you already had open to the background](#from-inside-a-session) with `←` or `/background`. That session keeps editing files where it was already working
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
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, a sessi
+4 −3 lines
Upstream edited 2 Oct 2026 22:26 UTC Recorded here 2 Oct 2026 22:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 2 Oct 2026 22:07 UTC
claude-code
setup
±changed
+9−5
claude-codechanged
setup
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+9 −5 lines
Upstream edited 2 Oct 2026 22:05 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
errors
±changed
+2−0
claude-codechanged
errors
* If you run `claude update` on the [stable release channel](/docs/en/setup#configure-release-channel), it doesn't move you past the newest stable release, which can still be below
* On the [stable release channel](/docs/en/setup#configure-release-channel), updating doesn't move you past the newest stable release, which can still be older than these versions.
+2 −0 lines
Upstream edited 2 Oct 2026 22:05 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+1−0
claude-codechanged
self-hosted-environments-deploy
| Your cloud provider's endpoints for model requests, model lookups, and renewing credentials, such as `bedrock-runtime.us-east-1.amazonaws.com` or `aiplatform.googleapis.com` | 44
+1 −0 lines
Upstream edited 2 Oct 2026 21:57 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
self-hosted-environments-configuration
±changed
+91−2
claude-codechanged
self-hosted-environments-configuration
| `ANTHROPIC_BASE_URL` | The API base URL the child will use, delivered by the control plane per session and normally `https://api.anthropic.com`. Don't override it: the session's
| `ANTHROPIC_BASE_URL` | The API base URL the child will use, delivered by the control plane per session and normally `https://api.anthropic.com`. Don't override it: the session's
## Send model requests to Bedrock or Agent Platform
If your organization needs model requests to go through its own AWS or Google Cloud account, configure the runner for [Amazon Bedrock](/docs/en/amazon-bedrock) or [Google Cloud's A
+91 −2 lines
Upstream edited 2 Oct 2026 21:57 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
self-hosted-environments
±changed
+5−5
claude-codechanged
self-hosted-environments
When a developer starts a cloud session, the session-start UI shows an environment picker listing Anthropic-hosted environments alongside any your organization has created. If they
When a developer starts a cloud session, the session-start UI shows an environment picker listing Anthropic-hosted environments alongside any your organization has created. If they
* **Model inference**: sessions use the Anthropic API, and inference can't be routed through [Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry](/docs/en/third-party
* **Model inference**: sessions use the Anthropic API unless you configure a runner to [send model requests to Amazon Bedrock or Google Cloud's Agent Platform](/docs/en/self-hosted
* **Compliance**: repository checkouts and build artifacts stay on infrastructure you control. Session content still goes to `api.anthropic.com` for model inference.
+5 −5 lines
Upstream edited 2 Oct 2026 21:57 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
[Claude Code in Slack](/docs/en/slack) and [cloud sessions](/docs/en/claude-code-on-the-web) always use Anthropic's API; they aren't part of a gateway deployment. Gateway variables
[Claude Code in Slack](/docs/en/slack) and [cloud sessions](/docs/en/claude-code-on-the-web) aren't part of a gateway deployment. Gateway variables set in a cloud session's environ
+1 −1 lines
Upstream edited 2 Oct 2026 21:57 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
model-config
±changed
+5−2
claude-codechanged
model-config
Claude Code hides excluded models from the `/model` picker. A full model ID in the list that has no built-in picker row, such as an older version that the list pins, appears in the
Claude Code hides excluded models from the `/model` picker. Whether a model ID you list also gets a row of its own differs by provider:
* **Anthropic API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), [Claude apps gateway](/docs/en/claude-apps-gateway), or an [LLM gateway](/docs/en/llm-gateway) set thr
* **Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry**: unless a model ID you list starts with `anthropic.`, Claude Code doesn't add a row for it, whether it's a
+5 −2 lines
Upstream edited 2 Oct 2026 21:50 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
Entries with the `anthropic.` prefix are added as custom picker options and routed to Mantle. Replace `anthropic.claude-haiku-4-5` with the model ID your account has been granted.
Entries with the `anthropic.` prefix are added as custom picker options, and the ones that match the Mantle format are routed to Mantle. Replace `anthropic.claude-haiku-4-5` with t
+1 −1 lines
Upstream edited 2 Oct 2026 21:50 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
workflows
±changed
+2−2
claude-codechanged
workflows
* **A `PreToolUse` hook**: a [hook](/docs/en/hooks#pretooluse) that returns `allow` for the call approves it.
* **Your host**: a [`--permission-prompt-tool`](/docs/en/cli-reference#cli-flags) approves it, or, with the Agent SDK, a [`canUseTool`](/docs/en/agent-sdk/permissions) callback or
* **A hook**: a [`PreToolUse`](/docs/en/hooks#pretooluse) hook that allows the call approves it.
* **Your host**: a [`--permission-prompt-tool`](/docs/en/cli-reference#cli-flags) or, with the Agent SDK, a [`canUseTool`](/docs/en/agent-sdk/permissions) callback approves it.
+2 −2 lines
Upstream edited 2 Oct 2026 21:37 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
hooks-guide
±changed
+1−3
claude-codechanged
hooks-guide
* `PermissionRequest` hooks fire when Claude Code is about to ask you for permission.
* In [non-interactive mode](/docs/en/headless) with the `-p` flag, that prompt only exists when the Agent SDK's [`canUseTool` callback](/docs/en/agent-sdk/permissions) supplies i
* Background subagents can't show a prompt in non-interactive mode. Claude Code still runs the hooks for their tool calls, and if no hook returns a decision, it denies the call.
* [`PermissionRequest`](/docs/en/hooks#permissionrequest) hooks fire when Claude Code is about to ask you for permission, or when it would otherwise auto-deny a call that can't pro
+1 −3 lines
Upstream edited 2 Oct 2026 21:37 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
Runs when Claude Code is about to ask you for permission to use a tool. In sessions that can't show a prompt, such as background subagents in [non-interactive mode](/docs/en/headle
Runs when Claude Code is about to ask you for permission to use a tool. In sessions that can't show a prompt, such as background subagents in [non-interactive mode](/docs/en/headle
+1 −1 lines
Upstream edited 2 Oct 2026 21:37 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
* **With neither**: a bare `-p` run, or `query()` that sets neither `canUseTool` nor `permissionPromptToolName`, denies any tool call that would have prompted, and this event repor
* **With neither**: a bare `-p` run, or `query()` that sets neither `canUseTool` nor `permissionPromptToolName`, denies any tool call that would have prompted unless a [`Permission
+1 −1 lines
Upstream edited 2 Oct 2026 21:37 UTC Recorded here 2 Oct 2026 22:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 2 Oct 2026 21:37 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
Let an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when
Let an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when
| Owner case | Case-sensitive, like exact-entry matching | Case-insensitive |
| Owner case | Case-sensitive | Case-insensitive |
+2 −2 lines
Upstream edited 2 Oct 2026 21:36 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Subagent definitions from any of these scopes are also available to [agent teams](/docs/en/agent-teams#use-subagent-definitions-for-teammates): when spawning a teammate, you can re
You can also reuse a subagent definition as an [agent team](/docs/en/agent-teams) teammate: name the subagent type when you ask Claude to spawn the teammate, and Claude Code applie
+1 −1 lines
Upstream edited 2 Oct 2026 21:36 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
tools-reference
±changed
+10−6
claude-codechanged
tools-reference
After a question sits that long with no input, the dialog closes on its own: it submits any options you'd already selected and tells Claude you may be away from your keyboard, so C
The timeout applies only to `AskUserQuestion`'s multiple-choice questions; permission prompts, including plan approval, never auto-resolve on idle.
After a question sits that long with no input, the dialog closes on its own: it submits any options you'd already selected and tells Claude you may be away from your keyboard, so C
+10 −6 lines
Upstream edited 2 Oct 2026 21:34 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
memory
±changed
+1−1
claude-codechanged
memory
Rules without a `paths` field are loaded unconditionally and apply to all files. Path-scoped rules trigger when Claude reads files matching the pattern, not on every tool use. Matc
Rules without a `paths` field are loaded unconditionally and apply to all files. Path-scoped rules trigger when Claude uses the Read, Write, or Edit tool on a file matching the pat
+1 −1 lines
Upstream edited 2 Oct 2026 21:31 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
Modular instruction files in `.claude/rules/` that load alongside CLAUDE.md. A rule can be path-scoped with YAML `paths:` frontmatter so it only loads when Claude reads a matching
Modular instruction files in `.claude/rules/` that load alongside CLAUDE.md. A rule can be path-scoped with YAML `paths:` frontmatter so it only loads when Claude reads, writes, or
+1 −1 lines
Upstream edited 2 Oct 2026 21:31 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
debug-your-config
±changed
+2−2
claude-codechanged
debug-your-config
If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md`
If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md`
| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | They load when Claude reads a file in that directory with the Read
| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | They load after Claude uses the Read, Write, or Edit tool on a file
+2 −2 lines
Upstream edited 2 Oct 2026 21:31 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
claude-directory
±changed
+1−1
claude-codechanged
claude-directory
description: [<>Project instructions split into topic files that can load conditionally based on file paths. A rule without <C>paths:</C> frontmatter loads at session sta
description: [<>Project instructions split into topic files that can load conditionally based on file paths. A rule without <C>paths:</C> frontmatter loads at session sta
+1 −1 lines
Upstream edited 2 Oct 2026 21:31 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
To check on the task or stop it in the meantime, type `/tasks` in the prompt box to open the [agent map](#use-the-prompt-box). A subagent keeps its place in the tree of agents ther
To check on the task or stop it in the meantime, type `/tasks` in the prompt box to open the [agent map](#use-the-prompt-box). A subagent keeps its place in the tree of agents ther
+1 −1 lines
Upstream edited 2 Oct 2026 21:20 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
* Background Bash and PowerShell commands have a time limit, counted from the moment the command enters the background: 30 minutes, or the `timeout` Claude asks for when it starts
* Background commands in a local session you work in from a terminal, the desktop app, or the VS Code extension have no time limit. In a session that runs unattended, such as a `-p
+1 −1 lines
Upstream edited 2 Oct 2026 21:20 UTC Recorded here 2 Oct 2026 21:37 UTC
claude-code
claude-tag
±changed
+12−13
claude-codechanged
claude-tag
No line of the body moved in this read.
+12 −13 lines
Recorded here 2 Oct 2026 20:37 UTC
claude-code
changelog
±changed
+92−0
claude-codechanged
changelog
<Update label="2.1.288" description="October 2, 2026">
* Added `$.ui.selection()` for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row
* Added a built-in `gh api` to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the
* Added recovery for a prompt cleared with Ctrl+C: pressing Up on the empty prompt brings the draft back, including pasted text and images
+92 −0 lines
Upstream edited 2 Oct 2026 20:36 UTC Recorded here 2 Oct 2026 20:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 2 Oct 2026 14:37 UTC
claude-code
claude-apps-gateway-spend-limits
±changed
+3−3
claude-codechanged
claude-apps-gateway-spend-limits
<Warning>
`q=` and `user_ids[]=` ride GET query strings, so any fronting proxy or load balancer captures them in its access logs. If your PII log policy is strict, scrub these parameters t
</Warning>
> [!WARNING]
>
+3 −3 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
statusline
±changed
+39−7
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-claude
| `rate_limits.spend_limit.used_percentage`, `rate_limits.spend_limit.resets_at` | Behind a Claude apps gateway, how much of your spend limit you have used and when its period rese
| `rate_limits.spend_limit.used_usd`, `rate_limits.spend_limit.limit_usd`, `rate_limits.spend_limit.period` | Your estimated spend and your limit in US dollars, and the limit's per
"resets_at": 1740787200
"resets_at": 1740787200,
+39 −7 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
claude-apps-gateway-spend-limits
±changed
+9−6
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 most-consumed cap. When the gateway blocks a request, Claude Code
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
The warning works off response headers:
Each display needs a minimum Claude Code version on the developer's machine and on the gateway server:
* With v2.1.225 or later on the gateway server, each successful `/v1/messages` response for a developer who has a cap carries their own cap utilization and reset time in the `anthr
+9 −6 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
vs-code
±changed
+2−0
claude-codechanged
vs-code
To have each session connect to your browser as it starts, without typing `@browser`, see [Enable Chrome by default](/docs/en/chrome#enable-chrome-by-default). For when Claude Code
+2 −0 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
settings-reference
±changed
+6−4
claude-codechanged
settings-reference
| [`claudeInChromeDefaultEnabled`](#claudeinchromedefaultenabled) | Turn on [Chrome integration](/docs/en/chrome) in every interactive CLI session without passing `--chrome` | Glob
| [`claudeInChromeDefaultEnabled`](#claudeinchromedefaultenabled) | Turn on [Chrome integration](/docs/en/chrome) when a session starts, in the interactive CLI and the VS Code exte
Start every interactive CLI session with [Chrome integration](/docs/en/chrome) on, without passing `--chrome` each time. If you run [`claude remote-control`](/docs/en/remote-contro
Start every interactive CLI session with [Chrome integration](/docs/en/chrome) on, without passing `--chrome` each time. If you run [`claude remote-control`](/docs/en/remote-contro
+6 −4 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
permission-modes
±changed
+2−0
claude-codechanged
permission-modes
In the VS Code extension, how [Claude in Chrome](/docs/en/chrome) browser actions get approved depends on how the session connected to the browser: see [Permission prompts in V
+2 −0 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
chrome
±changed
+12−5
claude-codechanged
chrome
To avoid passing `--chrome` each session, run `/chrome` and select "Enabled by default".
To connect Chrome without passing `--chrome` each time, run `/chrome` in a CLI session and select **Enabled by default**. In the [VS Code extension](/docs/en/vs-code#automate-brows
With the setting on and Claude Code v2.1.287 or later, each VS Code session connects to your browser as it starts, so Claude can use it before you type `@browser`. On earlier versi
In the [VS Code extension](/docs/en/vs-code#automate-browser-tasks-with-chrome), Chrome is available whenever the Chrome extension is installed. No additional flag is needed.
+12 −5 lines
Upstream edited 2 Oct 2026 14:25 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
setup
±changed
+5−5
claude-codechanged
setup
```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 2 Oct 2026 14:24 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
claude-apps-gateway-config
±changed
+19−0
claude-codechanged
claude-apps-gateway-config
#### Context window in terminal sessions
Terminal sessions signed in through `/login` use the 1M context window for Opus 4.7 and later, Sonnet 5 and later, and the Fable models. The model ID needs no `[1m]` suffix, and se
To have terminal sessions compact at the 200K boundary instead, set the [auto-compact window](/docs/en/model-config#set-the-auto-compact-window) in the policy's `env`:
+19 −0 lines
Upstream edited 2 Oct 2026 14:12 UTC Recorded here 2 Oct 2026 14:37 UTC
claude-code
mcp
±changed
+4−1
claude-codechanged
mcp
Claude Code supports MCP `list_changed` notifications, allowing MCP servers to dynamically update their available tools, prompts, and resources without requiring you to disconnect
An MCP server can change the tools, prompts, or resources it offers while connected and send a `list_changed` notification. When one arrives:
* **In an interactive terminal session**, Claude Code fetches the updated list from that server, so you don't need to reconnect it.
* **In [non-interactive mode](/docs/en/headless) with the `-p` flag and in the [Agent SDK](/docs/en/agent-sdk/overview)**, Claude Code refreshes only the tool list on these notific
+4 −1 lines
Upstream edited 2 Oct 2026 14:03 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+14−1
claude-codechanged
claude-apps-gateway-deploy
* **Client machines**: developers' CLIs still send WebFetch hostname checks and version checks to Anthropic unless `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` and `skipWebFetchPre
* **Client machines**: developers' CLIs still send WebFetch hostname checks and version checks to Anthropic unless `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` and `skipWebFetchPre
### Plugin marketplace requests
+14 −1 lines
Upstream edited 2 Oct 2026 14:03 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
sub-agents
±changed
+2−3
claude-codechanged
sub-agents
As of v2.1.198, the `/agents` command no longer opens the interactive creation wizard; running it prints a reminder to ask Claude or edit `.claude/agents/` directly. Subagent files
Running `/agents` prints a reminder to ask Claude or edit `.claude/agents/` and `~/.claude/agents/` directly.
As of v2.1.198, a subagent treats messages from the agent that launched it as normal task direction, including mid-task course corrections, and acts on them within its own permissi
A subagent treats messages from the agent that launched it as normal task direction, including mid-task course corrections, and acts on them within its own permission settings. Two
+2 −3 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
setup
±changed
+7−7
claude-codechanged
setup
```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={null}
```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} theme=
```batch theme={null}
+7 −7 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
permission-modes
±changed
+5−8
claude-codechanged
permission-modes
* Accessing a location listed as a sensitive data location in your [environment](/docs/en/auto-mode-config#define-trusted-infrastructure), or copying data out of one. As of v2.1.19
* Routing a package install around your internal package registry to a public registry. As of v2.1.198, this also applies when you've told Claude an internal registry or mirror exi
* Accessing a location listed as a sensitive data location in your [environment](/docs/en/auto-mode-config#define-trusted-infrastructure), copying data out of one, or sending data
* Routing a package install around your internal package registry to a public registry. This applies when an internal registry or mirror is listed in your environment or when you'v
* Launching an autonomous agent loop that runs without human approval or a sandbox, such as one started with `--dangerously-skip-permissions` or `--no-sandbox`. As of v2.1.198 this
+5 −8 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
hooks-guide
±changed
+0−2
claude-codechanged
hooks-guide
The `agent_needs_input` and `agent_completed` matchers require Claude Code v2.1.198 or later.
+0 −2 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
hooks
±changed
+3−7
claude-codechanged
hooks
| `status` | string | `"completed"` | `"completed"` for foreground subagents, `"async_launched"` for background subagents. As of v2.1.198, subagents run in the background by defaul
| `status` | string | `"completed"` | `"completed"` for foreground subagents, `"async_launched"` for background subagents. Subagents run in the background by default, so an Agent c
The `agent_needs_input` and `agent_completed` types require Claude Code v2.1.198 or later.
To reference the project root from a PowerShell shell-form command, write `${CLAUDE_PROJECT_DIR}` or `$env:CLAUDE_PROJECT_DIR`. As of v2.1.198, Claude Code rewrites the `${CLAUDE_P
+3 −7 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
claude-platform-on-aws
±changed
+1−1
claude-codechanged
claude-platform-on-aws
If your SSO credentials expire mid-session, configure [`awsAuthRefresh`](/docs/en/amazon-bedrock#advanced-credential-configuration) so Claude Code re-runs your login command and re
If your SSO credentials expire mid-session, configure [`awsAuthRefresh`](/docs/en/amazon-bedrock#advanced-credential-configuration) so Claude Code re-runs your login command and re
+1 −1 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* For subagents in the current session, named background subagents appear in the @-mention typeahead with their status. As of v2.1.198, `/agents` no longer opens a panel; it prints
* For subagents in the current session, named background subagents appear in the @-mention typeahead with their status. The `/agents` command prints a notice pointing to the subage
+1 −1 lines
Upstream edited 2 Oct 2026 14:02 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
tools-reference
±changed
+2−2
claude-codechanged
tools-reference
The tool is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. It is also not available when `DISABLE_TELEMETRY` or `CLAUDE_CODE_DISABLE_NONESSEN
The tool is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. It is also not available when `DISABLE_TELEMETRY` or `CLAUDE_CODE_DISABLE_NONESSEN
WebFetch takes a URL and a prompt describing what to extract. It fetches the page, converts the response to Markdown when the server returns HTML, and runs the prompt against the c
WebFetch takes a URL and a prompt describing what to extract. It fetches the page and converts the response to Markdown when the server returns HTML. For most fetches, it then runs
+2 −2 lines
Upstream edited 2 Oct 2026 14:01 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
plugins/components
±changed
+2−2
claude-codechanged
plugins/components
A monitor is a shell command that Claude Code starts in the background when the session starts and keeps running until it ends, using the [Monitor tool](/docs/en/tools-referenc
A monitor is a shell command that Claude Code starts in the background when the session starts and keeps running until it ends. What it prints reaches Claude as notifications.
* **Interactive sessions only**: plugin monitors start in an interactive session and never in non-interactive mode with the `-p` flag. They also start only where the [Monitor tool]
* **Interactive sessions only**: plugin monitors start in an interactive session and never in non-interactive mode with the `-p` flag. They also don't start in sessions where the A
+2 −2 lines
Upstream edited 2 Oct 2026 14:01 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
plugins/cli-reference
±changed
+17−9
claude-codechanged
plugins/cli-reference
Update a plugin:
```bash theme={null}
claude plugin update formatter@my-marketplace
```
+17 −9 lines
Upstream edited 2 Oct 2026 13:59 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
plugin-evals
±changed
+4−4
claude-codechanged
plugin-evals
The judge for `llm` and `baseline` graders is a small fast model by default. Pass `--judge-model sonnet` or a full model ID to use a stronger one for nuanced rubrics.
By default, the judge for `llm` and `baseline` graders is the model Claude Code uses for background tasks. Pass `--judge-model sonnet` or a full model ID to choose the judge yourse
* **`type: agent`**: set `type: agent` to have a small model answer as the server from instructions in the body.
* **`type: agent`**: set `type: agent` to have the judge model answer as the server from instructions in the body.
| `--judge-model <model>` | A small fast model | Model for `llm` and `baseline` graders |
+4 −4 lines
Upstream edited 2 Oct 2026 13:59 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
goal
±changed
+2−2
claude-codechanged
goal
The `/goal` command sets a completion condition and Claude keeps working toward it without you prompting each step. After each turn, a small fast model checks whether the condition
The `/goal` command sets a completion condition and Claude keeps working toward it without you prompting each step. After each turn, a model checks whether the condition holds. If
`/goal` is a wrapper around a session-scoped [prompt-based Stop hook](/docs/en/hooks#prompt-based-hooks). Each time Claude finishes a turn, Claude Code sends the condition and the
`/goal` is a wrapper around a session-scoped [prompt-based Stop hook](/docs/en/hooks#prompt-based-hooks). Each time Claude finishes a turn, Claude Code sends the condition and the
+2 −2 lines
Upstream edited 2 Oct 2026 13:59 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
plugins/troubleshooting
±changed
+16−0
claude-codechanged
plugins/troubleshooting
<h3 id="the-packages-it-lists-are-not-installed">
`The packages it lists are not installed` or `were not installed, because ...`
</h3>
+16 −0 lines
Upstream edited 2 Oct 2026 13:58 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
plugins/loading
±changed
+6−7
claude-codechanged
plugins/loading
A failed or skipped install never blocks the plugin, which then loads without the dependencies. Each case leaves a different sign:
* A failed install, or one skipped because of its lockfile or one of the [limits on the install](#limits-on-the-dependency-install), appears in the `claude --debug` output as a `Pl
* A plugin with a `package.json` and no lockfile is skipped without a log entry
If the install fails or is skipped, the plugin still loads, but the parts of it that need the missing packages may not work.
+6 −7 lines
Upstream edited 2 Oct 2026 13:58 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
errors
±changed
+75−0
claude-codechanged
errors
| `is less capable than the current main model` / `Advisor will not activate on the main model` / `cannot advise` | [Request errors](#advisor-is-less-capable-than-the-current-main-
| `Claude Code can't read the keyboard here: stdin is not a terminal` | [Command-line errors](#claude-code-cant-read-the-keyboard-here) |
| `The packages it lists are not installed` / `The packages it lists were not installed, because` | [Plugin troubleshooting](/docs/en/plugins/troubleshooting#the-packages-it-lists-
| `Not published: that file is on a network share` | [Tool errors](#not-published-that-file-is-on-a-network-share) |
### Advisor is less capable than the current main model
+75 −0 lines
Upstream edited 2 Oct 2026 13:58 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
artifacts
±changed
+1−0
claude-codechanged
artifacts
| Source location | A file at a path that names a network host is refused without being read. See [Not published: that file is on a network share](/docs/en/errors#not-published-tha
+1 −0 lines
Upstream edited 2 Oct 2026 13:58 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
advisor
±changed
+21−19
claude-codechanged
advisor
If the requested model can act as an advisor but [ranks below](#choose-an-advisor-model) the session's main model, Claude Code starts the session anyway. Outside background session
Both Claude Code and the API require an advisor at least as capable as the main model, and the two rank some models differently. The accepted advisors for each main model are:
| Main model | Accepted advisors | Notes |
+21 −19 lines
Upstream edited 2 Oct 2026 13:58 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
interactive-mode
±changed
+28−27
claude-codechanged
interactive-mode
If you queue a message with a selection attached from a [connected IDE](/docs/en/vs-code#the-built-in-ide-mcp-server) or the [diff panel](#diff-panel), it keeps the selection you h
If you queue a message with a selection attached from a [connected IDE](/docs/en/vs-code#the-built-in-ide-mcp-server), it keeps the selection you had when you pressed `Enter`, what
When you pass a prompt on the command line, as in `claude "fix the login bug"`, or pipe one into an interactive session, Claude Code doesn't wait for a second Enter. It removes the
When you pass a prompt on the command line, as in `claude "fix the login bug"`, Claude Code doesn't wait for a second Enter. It removes the characters, shows a notice, and sends th
Run `/diff` to look over the changes in your working tree without leaving Claude Code. You see the edits Claude has made so far alongside anything else you haven't committed.
+28 −27 lines
Upstream edited 2 Oct 2026 13:55 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
* **Pipe in data** by running `cat error.log | claude` to send file contents directly.
* **Pipe in data** by running `cat error.log | claude -p "explain this error"` to send file contents directly.
+1 −1 lines
Upstream edited 2 Oct 2026 13:55 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
keybindings
±changed
+10−6
claude-codechanged
keybindings
| `DiffDialog` | Diff viewer navigation |
| `DiffDialog` | [Diff viewer](#diff-actions) navigation |
These actions reach only Claude Code's earlier diff viewer, which `/diff` opens outside [fullscreen rendering](/docs/en/fullscreen) after you disable the [`cc-plugin-diff` mod](/do
Actions for the [diff panel](/docs/en/interactive-mode#diff-panel) that `/diff` opens in fullscreen rendering. `app:cycleDiffBase` is in the `DiffPanel` context, which is active wh
+10 −6 lines
Upstream edited 2 Oct 2026 13:37 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
In fullscreen rendering, [`/diff`](/docs/en/interactive-mode#review-changes-with-%2Fdiff) opens a panel beside the conversation rather than a viewer you have to close, so you can w
In fullscreen rendering, [`/diff`](/docs/en/interactive-mode#review-changes-with-%2Fdiff) opens a panel beside the conversation, so you can watch the changes accumulate while Claud
+1 −1 lines
Upstream edited 2 Oct 2026 13:37 UTC Recorded here 2 Oct 2026 14:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 2 Oct 2026 13:37 UTC
claude-code
errors
±changed
+93−2
claude-codechanged
errors
| `Your GitHub organization has an IP allowlist that is blocking Claude` | [Command-line errors](#a-github-organization-policy-is-blocking-claude) |
| `Your GitHub organization requires single sign-on` | [Command-line errors](#a-github-organization-policy-is-blocking-claude) |
| `Your GitHub organization's identity provider (Microsoft Entra ID) has a Conditional Access policy that is blocking Claude` | [Command-line errors](#a-github-organization-policy-
| `/recap only runs when you ask for it yourself in this session` | [Command-line errors](#recap-only-runs-when-you-ask-for-it-yourself) |
| `Error: No such tool available: <tool name>` | [Tool errors](#no-such-tool-available) |
+93 −2 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
claude-apps-gateway-config
±changed
+39−1
claude-codechanged
claude-apps-gateway-config
* The model list, from `availableModels`
* The model list, from `availableModels`. [Extended context in Claude Desktop](#extended-context-in-claude-desktop) covers each model's 1M context option
#### Extended context in Claude Desktop
+39 −1 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* A WebFetch or WebSearch call that Claude Code moved to the background because you interrupted the turn to [send your queued messages right away](/docs/en/interactive-mode#when-cl
* A WebFetch or WebSearch call that Claude Code moved to the background while it ran so that a waiting message could reach Claude. The result that arrives later isn't recorded eith
+1 −1 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
claude-code
agent-sdk/typescript
±changed
+44−11
claude-codechanged
agent-sdk/typescript
| `toggleMcpServer(serverName, enabled)` | Enable or disable an MCP server by name, with the same name resolution as `reconnectMcpServer()`. Disabling a stdio, SSE, or HTTP server
| `toggleMcpServer(serverName, enabled)` | Enable or disable an MCP server by name, with the same name resolution as `reconnectMcpServer()`. Disabling a server disconnects it and r
#### `toggleMcpServer()`
+44 −11 lines
Upstream edited 2 Oct 2026 13:32 UTC Recorded here 2 Oct 2026 13:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.