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
30 Sep 2026
63 pages
+3919 −261 lines
claude-code
plugins/troubleshooting
±changed
+45−1
claude-codechanged
plugins/troubleshooting
<h3 id="installed-plugins-json-holds-a-record-this-version-cannot-read">
`installed_plugins.json holds a record under "<id>" that this version of Claude Code cannot read`
</h3>
+45 −1 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
plugins/marketplace-reference
±changed
+6−4
claude-codechanged
plugins/marketplace-reference
* <span id="reserved-name-spellings" />**Another spelling of a reserved name**: a name that differs from a reserved name only by a trailing dot, or by a symbol other than an unders
* <span id="reserved-name-spellings" />**Another spelling of a reserved name**: a name that differs from a reserved name only by a trailing dot, or by a symbol other than an unders
| `name` | string | Marketplace identifier. No spaces, control characters, or bidirectional-formatting characters, no `/` or `\`, no `..`, and not `.`. See [Reserved names](#reserv
| `name` | string | Marketplace identifier: letters, digits, `.`, `_`, and `-`, starting with a letter or digit, and no `..`. It forms the half after `@` of every [plugin id](/docs
| `name` | string | Plugin identifier, with no spaces, control characters, or bidirectional-formatting characters. Users type it before `@` when they install, even when the plugin'
+6 −4 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
plugins/loading
±changed
+1−0
claude-codechanged
plugins/loading
| `installed_plugins.set-aside.<date>.<hash>.json` and `installed_plugins.unreadable.<date>.<hash>.kept` | Dated copies Claude Code keeps before it drops install records that no ve
+1 −0 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
plugins/create-marketplace
±changed
+2−2
claude-codechanged
plugins/create-marketplace
* `name`: the identifier people type before `@` when they install. It can't contain spaces.
* `name`: the identifier people type before `@` when they install. [Plugin entries](/docs/en/plugins/marketplace-reference#plugin-entries) gives the characters a name can use.
* A marketplace name with spaces, non-ASCII characters, or a form that imitates an official Anthropic marketplace, such as `claude-official`
* A marketplace or plugin name that breaks the naming rules in the [marketplace reference](/docs/en/plugins/marketplace-reference#top-level-fields)
+2 −2 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
plugins/cli-reference
±changed
+7−3
claude-codechanged
plugins/cli-reference
If the failure line continues with `"formatter" was not uninstalled:`, Claude Code couldn't confirm that the scope's settings no longer switch the plugin on, so the plugin stays in
If the failure line continues with `"formatter" was not uninstalled:` and names a settings file, Claude Code couldn't confirm that the scope's settings no longer switch the plugin
When you remove a marketplace from the last scope that declares it, Claude Code also deletes its cache and uninstalls every plugin you installed from it. Without `--scope`, the c
When you remove a marketplace from the last scope that declares it, Claude Code also deletes its cache and uninstalls every plugin you installed from it. It also deletes their sa
+7 −3 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
errors
±changed
+2−1
claude-codechanged
errors
| `Plugin "<plugin>" was not uninstalled: installed_plugins.json` | [Plugin troubleshooting](/docs/en/plugins/troubleshooting#installed-plugins-json-holds-a-record-this-version-can
You ran [`claude plugin uninstall`](/docs/en/plugins/cli-reference#plugin-uninstall), or chose **Uninstall** in the `/plugin` **Installed** tab, and the uninstall stopped with a me
You ran [`claude plugin uninstall`](/docs/en/plugins/cli-reference#plugin-uninstall), or chose **Uninstall** in the `/plugin` **Installed** tab, and the uninstall stopped with a me
+2 −1 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
claude-directory
±changed
+2−0
claude-codechanged
claude-directory
| `plugins/installed_plugins.set-aside.<date>.<hash>.json`, `plugins/installed_plugins.unreadable.<date>.<hash>.kept` | Dated copies Claude Code makes before rewriting [`installed_
| `~/.claude/plugins/installed_plugins.set-aside.<date>.<hash>.json`, `~/.claude/plugins/installed_plugins.unreadable.<date>.<hash>.kept` | The copies of plugin install records tha
+2 −0 lines
Upstream edited 30 Sep 2026 03:24 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
agent-view
±changed
+26−2
claude-codechanged
agent-view
You can use `claude agents` as your primary entry point instead of `claude`: dispatch every task from agent view, attach when you want the full conversation, and press `←` to retur
### Open agent view by default
+26 −2 lines
Upstream edited 30 Sep 2026 03:22 UTC Recorded here 30 Sep 2026 03:37 UTC
claude-code
routines
±changed
+18−8
claude-codechanged
routines
Routines belong to your individual claude.ai account. They are not shared with teammates, and they count against your account's daily run allowance. Anything a routine does through
Routines belong to your individual claude.ai account. They are not shared with teammates, and their runs count against your account's [usage and limits](#usage-and-limits). Anythin
One-off runs do not count against the daily routine run cap. See [Usage and limits](#usage-and-limits) for details.
One-off runs count against the same hourly limit as other scheduled runs. See [Usage and limits](#usage-and-limits) for details.
During the research preview, GitHub webhook events are subject to per-routine and per-account hourly caps. Events beyond the limit are dropped until the window resets. See your c
+18 −8 lines
Upstream edited 30 Sep 2026 03:21 UTC Recorded here 30 Sep 2026 03:37 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 30 Sep 2026 03:07 UTC
claude-code
model-config
±changed
+3−1
claude-codechanged
model-config
If your account supports 1M context, the option appears in the `/model` picker in the latest versions of Claude Code. If you don't see it, try restarting your session.
If your account supports 1M context, the option appears in the `/model` picker in the latest versions of Claude Code. If you don't see it, restart your session, and on a third-part
When you set an `ANTHROPIC_DEFAULT_*_MODEL` variable, the `/model` picker shows one row for that model in place of the family's built-in rows, including any 1M context rows. To rea
+3 −1 lines
Upstream edited 30 Sep 2026 03:05 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
google-vertex-ai
±changed
+1−1
claude-codechanged
google-vertex-ai
The [setup wizard](#sign-in-with-agent-platform) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. Se
The [setup wizard](#sign-in-with-agent-platform) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. Se
+1 −1 lines
Upstream edited 30 Sep 2026 03:05 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
The [setup wizard](#sign-in-with-bedrock) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin
The [setup wizard](#sign-in-with-bedrock) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin
+1 −1 lines
Upstream edited 30 Sep 2026 03:05 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
self-hosted-environments-reference
±changed
+6−4
claude-codechanged
self-hosted-environments-reference
The orchestrator can hold a standing WebSocket connection to Anthropic's control plane so that hosted pre-session flows, such as the repository picker and the branch or ref resolve
The SCM connector isn't available, so leave the flags in this section unset. If you set `--scm-connector-host`, the connection doesn't open, and the orchestrator keeps retrying it.
The connector is a standing WebSocket connection from the orchestrator to Anthropic's control plane. It's designed to let hosted pre-session flows, such as the repository picker an
| `--scm-connector-host <host[:port]>` | unset | GitHub Enterprise Server hostname to forward requests to. Port defaults to `443`. Setting this flag enables the connector. |
+6 −4 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
self-hosted-environments
±changed
+1−1
claude-codechanged
self-hosted-environments
* **Repositories**: sessions check out repositories from GitHub; see [GitHub authentication options](/docs/en/claude-code-on-the-web#github-authentication-options).
* **Repositories**: sessions check out repositories from GitHub; see [GitHub authentication options](/docs/en/claude-code-on-the-web#github-authentication-options). For a GitHub En
+1 −1 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
network-config
±changed
+5−3
claude-codechanged
network-config
| Event-level watchdog | No response events parse. On connections where the byte-level watchdog runs, arriving bytes, including keep-alive pings, also reset this watchdog, for up t
| Event-level watchdog | No response events parse. Where the byte-level watchdog runs on a connection other than Amazon Bedrock, arriving bytes, including keep-alive pings, also re
| Body idle timeout | No bytes arrive for 5 minutes | Providers other than the direct Anthropic API and Claude Platform on AWS, unless [`API_FORCE_IDLE_TIMEOUT`](/docs/en/env-vars)
| Body idle timeout | No bytes arrive for 5 minutes | Providers other than the direct Anthropic API, Claude Platform on AWS, and Amazon Bedrock with `CLAUDE_ENABLE_BYTE_WATCHDOG_BE
+5 −3 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
monitoring-usage
±changed
+5−3
claude-codechanged
monitoring-usage
When Claude Code is signed in to a [Claude apps gateway](/docs/en/claude-apps-gateway), the CLI stamps exports with the authenticated identity from the gateway session: `user.id` i
In sessions signed in to a [Claude apps gateway](/docs/en/claude-apps-gateway) through `/login`, the CLI stamps exports with the authenticated identity: `user.id` is the IdP subjec
For the identity attributes on Claude Desktop and Cowork sessions that connect through a gateway, see the [gateway `telemetry` reference](/docs/en/claude-apps-gateway-config#teleme
The [standard attributes](#standard-attributes) on each event include the authenticated user's identity: `user.email`, `user.account_uuid`, `user.account_id`, and `organization.id`
+5 −3 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
llm-gateway-protocol
±changed
+1−1
claude-codechanged
llm-gateway-protocol
Forward keep-alive pings as well. On connections through `ANTHROPIC_BASE_URL` or `ANTHROPIC_AWS_BASE_URL`, Claude Code counts every byte your gateway relays, including SSE `ping` e
Forward keep-alive pings as well, because Claude Code aborts a streaming response once no bytes reach it for [five minutes by default](/docs/en/network-config#streaming-idle-watchd
+1 −1 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
github-enterprise-server
±changed
+4−2
claude-codechanged
github-enterprise-server
For Anthropic-hosted sessions, your GHES instance must be reachable from Anthropic infrastructure so Claude can clone repositories and post review comments. If your GHES instance i
For Anthropic-hosted sessions, your GHES instance must be reachable from Anthropic infrastructure so Claude can clone repositories and post review comments. If your GHES instance i
Hosted pre-session flows, such as the repository picker, run on Anthropic's side before a session starts. They need your GHES instance to be reachable from Anthropic infrastructure
If reviews or Anthropic-hosted cloud sessions time out, your GHES instance may not be reachable from Anthropic infrastructure. Confirm your firewall allows inbound connections from
+4 −2 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+1−1
claude-codechanged
claude-apps-gateway-on-aws
The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring u
The gateway gives you per-developer usage metrics without any per-machine OTEL configuration. Claude Code emits OpenTelemetry (OTLP) metrics, logs, and opt-in traces; [Monitoring u
+1 −1 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+1−1
claude-codechanged
claude-apps-gateway-deploy
| Identity (email, groups, sub) | IdP → gateway → JWT → CLI; the CLI stamps it on OTLP exports. If you turn on [`forward_user_identity`](/docs/en/claude-apps-gateway-config#per-use
| Identity (email, groups, sub) | IdP → gateway → CLI; the CLI stamps it on OTLP exports. If you turn on [`forward_user_identity`](/docs/en/claude-apps-gateway-config#per-user-iden
+1 −1 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
The CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.groups` attributes. Per-developer cost a
In sessions signed in through `/login`, the CLI stamps each export with the authenticated user's identity, read from the gateway-issued JWT: the `user.id`, `user.email`, and `user.
+1 −1 lines
Upstream edited 30 Sep 2026 03:00 UTC Recorded here 30 Sep 2026 03:07 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 30 Sep 2026 02:07 UTC
claude-code
claude-apps-gateway-config
±changed
+29−0
claude-codechanged
claude-apps-gateway-config
##### Apply an Amazon Bedrock guardrail
To apply an Amazon Bedrock guardrail to every inference request the gateway sends through a Bedrock upstream, add a `guardrail` block to that upstream. Requires Claude Code v2.1.28
+29 −0 lines
Upstream edited 30 Sep 2026 01:55 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
settings-reference
±changed
+19−0
claude-codechanged
settings-reference
| [`allowClaudeInChromeWithManagedMcp`](#allowclaudeinchromewithmanagedmcp) | Let the built-in [Claude in Chrome](/docs/en/chrome) server run alongside a deployed [`managed-mcp.jso
### `allowClaudeInChromeWithManagedMcp`
Let the built-in [Claude in Chrome](/docs/en/chrome) server run alongside a deployed `managed-mcp.json`. Without this key, a deployed `managed-mcp.json` blocks Claude in Chrome in
+19 −0 lines
Upstream edited 30 Sep 2026 01:53 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
managed-mcp
±changed
+14−3
claude-codechanged
managed-mcp
| **Disable MCP** | No servers load, apart from [in-process servers the app that started the session registers](#exclusive-control-with-managed-mcp-json) and any you [provide throu
| **Disable MCP** | No servers load except the few that [load under exclusive control](#exclusive-control-with-managed-mcp-json) | `managed-mcp.json` with an empty server map |
* The built-in [Claude in Chrome](/docs/en/chrome) server, if you [allow it alongside the managed set](#allow-claude-in-chrome-alongside-the-managed-set)
Deploy a `managed-mcp.json` containing an empty server map to block every MCP server apart from [in-process servers the app that started the session registers](#exclusive-control-w
Deploy a `managed-mcp.json` containing an empty server map to block every MCP server except the ones that [load under exclusive control](#exclusive-control-with-managed-mcp-json):
+14 −3 lines
Upstream edited 30 Sep 2026 01:53 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
chrome
±changed
+4−1
claude-codechanged
chrome
If your organization blocks the `claude-in-chrome` MCP server with the [`deniedMcpServers` managed setting](/docs/en/managed-mcp#policy-based-control-with-allowlists-and-denylists)
Two managed MCP policies turn the prompt off:
* If your organization blocks the `claude-in-chrome` MCP server with the [`deniedMcpServers` managed setting](/docs/en/managed-mcp#policy-based-control-with-allowlists-and-denylist
* If your organization deploys a [`managed-mcp.json`](/docs/en/managed-mcp#exclusive-control-with-managed-mcp-json) file without [allowing Claude in Chrome alongside the managed se
+4 −1 lines
Upstream edited 30 Sep 2026 01:53 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
third-party-integrations
±changed
+1−1
claude-codechanged
third-party-integrations
<td><strong>Teams:</strong> \$150/seat (Premium) with PAYG available<br /><strong>Enterprise:</strong> <a href="https://claude.com/contact-sales?utm_source=claude_code&utm_me
<td><strong>Teams:</strong> per-seat subscription with PAYG available, see <a href="https://claude.com/pricing?utm_source=claude_code&utm_medium=docs&utm_content=third_party_
+1 −1 lines
Upstream edited 30 Sep 2026 01:52 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A live, interactive web page Claude Code publishes from your session to a private URL on claude.ai, so you can see output visually or share it instead of reading terminal text. The
A live, interactive web page Claude Code publishes from your session to a private URL on claude.ai, so you can see output visually or share it instead of reading terminal text. The
+1 −1 lines
Upstream edited 30 Sep 2026 01:38 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
| [Artifacts](/docs/en/artifacts) | ✓ | ✓ | ✓ | Admin-enabled |
| [Artifacts](/docs/en/artifacts) | ✓ | ✓ | ✓ | ✓ |
+1 −1 lines
Upstream edited 30 Sep 2026 01:38 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
artifacts
±changed
+11−11
claude-codechanged
artifacts
* **Publicly**: share a link that anyone on the internet can open, with no claude.ai sign-in required. On Pro and Max plans, a public link is the only way to share an artifact. On
* **Publicly**: share a link that anyone on the internet can open, with no claude.ai sign-in required. On Team and Enterprise plans, public sharing is off until an Owner [enables i
When you share an artifact within your organization, the people you share it with can leave comments on the page, and you can have Claude read those comments and reply to them. You
When you share an artifact within your organization, the people you share it with can leave comments on the page, and you can have Claude read those comments and reply to them. You
If you share an artifact publicly, viewers can't comment on it: the page says `Comments aren't available while this Artifact is shared publicly.` To switch an artifact that already
+11 −11 lines
Upstream edited 30 Sep 2026 01:38 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
* **Files that would turn your working directory into a bare git repository**: `HEAD`, `objects`, and `refs` at the top level, plus `config` and `hooks` there when a `HEAD` sits be
* **Files that would turn your working directory into a bare git repository**: `HEAD`, `objects`, and `refs` at the top level, plus existing `config` and `hooks` entries there when
+1 −1 lines
Upstream edited 30 Sep 2026 01:37 UTC Recorded here 30 Sep 2026 02:07 UTC
claude-code
claude-tag
±changed
+2982−7
claude-codechanged
claude-tag
No line of the body moved in this read.
+2982 −7 lines
Recorded here 30 Sep 2026 01:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Desktop app**: **Settings > Claude Code > Enable remote control by default**.
* **Desktop app**: **Settings > Claude Code > Connect new sessions to Remote Control**.
+1 −1 lines
Upstream edited 30 Sep 2026 00:41 UTC Recorded here 30 Sep 2026 01:07 UTC
claude-code
plugins/loading
±changed
+7−0
claude-codechanged
plugins/loading
Claude Code neither downloads nor loads synced plugins in these terminal sessions, even after you sign in with `/login`:
* A session where `ANTHROPIC_AUTH_TOKEN`, `CLAUDE_CODE_OAUTH_TOKEN`, or an `apiKeyHelper` script supplies the credential in place of that sign-in
* A session that doesn't [fetch feature flags from Anthropic](/docs/en/env-vars#features-that-need-feature-flag-fetching), such as one where you set `CLAUDE_CODE_DISABLE_NONESSENTI
+7 −0 lines
Upstream edited 30 Sep 2026 00:14 UTC Recorded here 30 Sep 2026 00:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `fork` | A new session forked from an existing one: `--fork-session` with `--resume` or `--continue`, the `/fork` background copy, or `/branch` |
| `fork` | A new session forked from an existing one: `--fork-session` with `--resume` or `--continue`, the `/fork` background copy, `/branch`, or a conversation you [move to the b
+1 −1 lines
Upstream edited 30 Sep 2026 00:13 UTC Recorded here 30 Sep 2026 00:37 UTC
claude-code
troubleshoot-install
±changed
+6−1
claude-codechanged
troubleshoot-install
Errors like `curl: (35) TLS connect error`, `schannel: next InitializeSecurityContext failed`, or PowerShell's `Could not establish trust relationship for the SSL/TLS secure channe
Errors such as these mean the TLS handshake failed:
* `curl: (35) TLS connect error`
* `schannel: next InitializeSecurityContext failed`
+6 −1 lines
Upstream edited 30 Sep 2026 00:12 UTC Recorded here 30 Sep 2026 00:37 UTC
29 Sep 2026
60 pages
+1333 −1202 lines
claude-code
monitoring-usage
±changed
+2−0
claude-codechanged
monitoring-usage
In the Claude Desktop app, Code tab sessions read these managed settings from the sources that [reach each kind of Desktop session](/docs/en/desktop#managed-settings). The OpenTele
+2 −0 lines
Upstream edited 29 Sep 2026 21:43 UTC Recorded here 29 Sep 2026 22:07 UTC
claude-code
desktop
±changed
+6−0
claude-codechanged
desktop
<Note>
The OpenTelemetry form for Cowork under **Monitoring** in the admin console's [Data and privacy settings](https://claude.ai/admin-settings/data-privacy-controls) applies to Cowor
To export telemetry from Code tab sessions, set `CLAUDE_CODE_ENABLE_TELEMETRY` and the `OTEL_*` variables in the `env` block of your Claude Code managed settings, as shown in [ad
</Note>
+6 −0 lines
Upstream edited 29 Sep 2026 21:43 UTC Recorded here 29 Sep 2026 22:07 UTC
claude-code
settings-reference
±changed
+7−6
claude-codechanged
settings-reference
* When the Claude Desktop app or a [self-hosted environment](/docs/en/self-hosted-environments) runner starts the session, the launch environment it builds takes precedence instead
Allowlist the MCP servers people can add. Claude Code blocks any server that doesn't match an entry wherever it's defined, including plugin servers, servers passed with `--mcp-conf
Built-in servers such as Claude in Chrome, the `ide` server Claude Code connects to in a running [VS Code](/docs/en/vs-code#the-built-in-ide-mcp-server) or [JetBrains](/docs/en/jet
Allowlist the MCP servers people can add. Claude Code blocks any server that doesn't match an entry wherever it's defined, including plugin servers, servers a user passes with `--m
+7 −6 lines
Upstream edited 29 Sep 2026 21:32 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
| [`disableSideloadFlags`](/docs/en/settings-reference#disablesideloadflags) | Reject the `--plugin-dir`, `--plugin-url`, `--agents`, and `--mcp-config` flags at startup. In cloud
| [`disableSideloadFlags`](/docs/en/settings-reference#disablesideloadflags) | Reject the `--plugin-dir`, `--plugin-url`, `--agents`, and `--mcp-config` flags at startup. In cloud
+1 −1 lines
Upstream edited 29 Sep 2026 21:32 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
managed-mcp
±changed
+9−5
claude-codechanged
managed-mcp
To deploy servers to users, use [`managed-mcp.json`](#exclusive-control-with-managed-mcp-json) or [`managedMcpServers`](#provide-servers-through-managed-settings). Both lists also
To deploy servers to users, use [`managed-mcp.json`](#exclusive-control-with-managed-mcp-json) or [`managedMcpServers`](#provide-servers-through-managed-settings). Both lists also
| `allowedMcpServers` | All servers allowed | No servers allowed, apart from [the organization's own](#how-a-server-is-evaluated) | Only matching servers allowed, apart from [the o
| `allowedMcpServers` | All servers allowed | No servers allowed, apart from [those that skip the allowlist check](#how-a-server-is-evaluated) | Only matching servers allowed, apar
The organization's own servers skip this check: every `managedMcpServers` entry, and any `managed-mcp.json` entry whose values use no `${VAR}` expansion. Built-in servers skip i
+9 −5 lines
Upstream edited 29 Sep 2026 21:32 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
model-config
±changed
+9−11
claude-codechanged
model-config
When you switch models through the [Agent SDK](/docs/en/agent-sdk/overview) `setModel()` method or from a device connected through [Remote Control](/docs/en/remote-control), or an
* a model alias
* an entry from the `/model` picker
* any name that starts with `claude-`
+9 −11 lines
Upstream edited 29 Sep 2026 21:30 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
errors
±changed
+33−12
claude-codechanged
errors
| `Couldn't confirm model ... with the API` | [Request errors](#couldnt-confirm-model-with-the-api) |
The model string you passed to a model switch isn't a model alias, a model ID this Claude Code version knows, or an ID that starts with `claude-`. The usual causes are a typo in th
```text theme={null}
Model "claud-sonnet-5" is not a recognized model id. Did you mean 'claude-sonnet-5'?
+33 −12 lines
Upstream edited 29 Sep 2026 21:30 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
workflows
±changed
+1−1
claude-codechanged
workflows
Workflows run in the background, so the session stays responsive while agents work. Run `/workflows` at any time to list running and completed workflows, then select one to open it
Workflows run in the background, so the session stays responsive while agents work. Run `/workflows` at any time to list running and completed workflows, then select one to open it
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
troubleshooting
±changed
+1−1
claude-codechanged
troubleshooting
The command also prints a summary in the conversation, showing resident set size, JS heap, array buffers, and unaccounted native memory, plus any leak indicators it detected, such
The command also prints a summary in the conversation, showing the process's total memory, how much of it is in the JS heap, and how much sits outside the heap. The summary also li
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
* Context percentage may differ from `/context` output due to when each is calculated
* The status line reports the counts from the last API response, while `/context` adds an estimate for messages added since that response, so `/context` can read higher until the n
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
permissions
±changed
+1−0
claude-codechanged
permissions
* **Writes to special shell variables**: a command that sets, unsets, or loops over certain special shell variables, such as `PATH` or `IFS`, prompts even when the rest of the comm
+1 −0 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
4. If the classifier blocks, Claude receives the reason and tries an alternative. In most sessions the reason names the rule the classifier matched, such as `[Data Exfiltration
4. If the classifier blocks, Claude receives the reason. In most sessions the reason names the rule the classifier matched, such as `[Data Exfiltration]`, rather than giving a
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
github-actions
±changed
+2−0
claude-codechanged
github-actions
To stop setup partway through, press Esc. A step already in progress finishes, and no later step starts. The closing message lists what already happened in the repository, such as
+2 −0 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
fast-mode
±changed
+2−0
claude-codechanged
fast-mode
In the browser at [claude.ai/code](https://claude.ai/code), you can also turn fast mode on and off from the model menu on the message box. The menu shows the switch when your plan
+2 −0 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
deep-links
±changed
+1−1
claude-codechanged
deep-links
Every deep link starts with `claude-cli://open`, which is the only path the handler accepts, followed by optional query parameters. The minimal form opens Claude Code in your home
A deep link starts with `claude-cli://open`, followed by optional query parameters. The minimal form opens Claude Code in your home directory with an empty prompt:
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
costs
±changed
+2−0
claude-codechanged
costs
When [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) is available to the session and your recent sessions mostly ran without it, the report can also include
+2 −0 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
Site-level permissions are inherited from the Chrome extension. Manage permissions in the Chrome extension settings to control which sites Claude can browse, click, and type on.
Site-level permissions are inherited from the Chrome extension. Manage permissions in the Chrome extension settings to control which sites Claude can browse, click, and type on. In
+1 −1 lines
Upstream edited 29 Sep 2026 21:13 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
self-hosted-environments-quickstart
±changed
+1−1
claude-codechanged
self-hosted-environments-quickstart
The runner exits by design once its active sessions finish; see [Runner lifecycle](/docs/en/self-hosted-environments#runner-lifecycle). For production, deploy it under an orchestra
The runner exits by design once its active sessions finish; see [Runner lifecycle](/docs/en/self-hosted-environments#runner-lifecycle). For production, deploy it under an orchestra
+1 −1 lines
Upstream edited 29 Sep 2026 21:11 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+71−1
claude-codechanged
self-hosted-environments-deploy
<Warning>
The [Kubernetes](#kubernetes) and [Docker Compose](#docker-compose) recipes on this page use `--capacity 4`. If you add `--use-anthropic-git-proxy` or `CLAUDE_RUNNER_USE_GIT_PROX
</Warning>
The recipes below use `--capacity 4`, so one container serves up to four concurrent sessions from the same locked owner. That doesn't provide the per-session container isolation in
+71 −1 lines
Upstream edited 29 Sep 2026 21:11 UTC Recorded here 29 Sep 2026 21:37 UTC
claude-code
memory
±changed
+6−0
claude-codechanged
memory
To import a file whose path contains spaces, put a backslash before each space. Without the backslashes, the path ends at the first space, even when the import is on a line of its
```text theme={null}
- API conventions @Design\ Docs/api-conventions.md
+6 −0 lines
Upstream edited 29 Sep 2026 20:34 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+27−0
claude-codechanged
self-hosted-environments-deploy
Keep any program you name in `GIT_SSH_COMMAND` or `GIT_ASKPASS` where sessions can't write to it, the way the [hardening checklist](#harden-your-deployment) asks for the hooks dire
#### Trust a private certificate authority with Anthropic-managed git
+27 −0 lines
Upstream edited 29 Sep 2026 20:32 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
channels-reference
±changed
+3−1
claude-codechanged
channels-reference
<channel source="webhook" path="/" method="POST">build failed on main: https://ci.example.com/run/1234</channel>
<channel source="webhook" path="/" method="POST">
build failed on main: https://ci.example.com/run/1234
</channel>
+3 −1 lines
Upstream edited 29 Sep 2026 20:26 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
sub-agents
±changed
+5−5
claude-codechanged
sub-agents
Claude Code includes built-in subagents that Claude automatically uses when appropriate. Each inherits the parent conversation's permissions; most run with a restricted tool set.
Claude Code includes built-in subagents that Claude automatically uses when appropriate. Each inherits the parent conversation's permission rules; most run with a restricted tool s
command: "./scripts/validate-command.sh $TOOL_INPUT"
command: "./scripts/validate-command.sh"
* **Session-wide**: the whole session uses that subagent's system prompt, tool restrictions, and model via the `--agent` flag or the `agent` setting
+5 −5 lines
Upstream edited 29 Sep 2026 20:23 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
claude-apps-gateway
±changed
+3−1
claude-codechanged
claude-apps-gateway
A plugin marketplace allowlist also reaches embedded sessions only as parent settings. When you turn user-added plugin marketplaces off in Claude Desktop's managed configuration, C
* **`strictKnownMarketplaces`**: Claude Code honors a parent-supplied plugin marketplace allowlist when the winning managed source doesn't set one. If your fleet restricts marketpl
* **`strictKnownMarketplaces`**: Claude Code honors a parent-supplied plugin marketplace allowlist when the winning managed source doesn't set one. Claude Desktop 2.16120.0 or late
+3 −1 lines
Upstream edited 29 Sep 2026 20:23 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
cloud-environments
±changed
+5−0
claude-codechanged
cloud-environments
* claude.com
* support.claude.com
* anthropic.com
* [www.anthropic.com](http://www.anthropic.com)
* production.cloudfront.docker.com
+5 −0 lines
Upstream edited 29 Sep 2026 20:20 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
| `agent_needs_input` | A background session starts waiting on your input while [agent view](/docs/en/agent-view) is open, or the current session asks you an [agent team teammate's
| `agent_needs_input` | A background session starts waiting on your input while [agent view](/docs/en/agent-view) is open. Also fires when a terminal session shows you an [agent te
+1 −1 lines
Upstream edited 29 Sep 2026 20:17 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
hooks
±changed
+2−2
claude-codechanged
hooks
Enterprise administrators can use `allowManagedHooksOnly` to restrict which hooks run:
Administrators can use [`allowManagedHooksOnly`](/docs/en/settings-reference#allowmanagedhooksonly) in [managed settings](/docs/en/managed-settings) to restrict which hooks run:
| `agent_needs_input` | A background session starts waiting on your input while [agent view](/docs/en/agent-view) is open in a terminal, or the current session asks you an [agent t
| `agent_needs_input` | A background session starts waiting on your input while [agent view](/docs/en/agent-view) is open in a terminal. Also fires when a terminal session shows yo
+2 −2 lines
Upstream edited 29 Sep 2026 20:17 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
model-config
±changed
+2−2
claude-codechanged
model-config
Sonnet 5.5 requires Claude Code v2.1.284 or later, and Opus 5.5 requires v2.1.280 or later. Run `claude update` to upgrade.
Sonnet 5.5 requires Claude Code v2.1.284 or later, and Opus 5.5 requires v2.1.280 or later. If a request for one of them from an older version fails, see [Claude Code does not su
Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model fami
Administrators can use `availableModels` in [managed or policy settings](/docs/en/managed-settings) to restrict which models users can select. Entries match a model family such as
+2 −2 lines
Upstream edited 29 Sep 2026 20:17 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
errors
±changed
+14−4
claude-codechanged
errors
**What to do:**
* Run `claude update`, or update the Claude desktop app, then start a new session
* For the per-model wording, you can keep working in the current session by switching to another model with `/model`
The version the API checks is the one reported by the Claude Code binary that made the request.
+14 −4 lines
Upstream edited 29 Sep 2026 20:16 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
code-review
±changed
+1−1
claude-codechanged
code-review
Findings include a collapsible extended reasoning section you can expand to understand why Claude flagged the issue and how it verified the problem.
Findings include a collapsed **Why this was flagged** section that you can expand to read why Claude flagged the issue and how it verified the problem.
+1 −1 lines
Upstream edited 29 Sep 2026 20:07 UTC Recorded here 29 Sep 2026 20:37 UTC
claude-code
remote-control
±changed
+2−1
claude-codechanged
remote-control
| `-d`, `--debug[=<filter>]` | Turn on debug logging for the server, optionally filtered by category. Pass a filter only in the `=` form, such as `--debug=api,hooks`. Requires
| `--chrome` / `--no-chrome` | Turn [Chrome integration](/docs/en/chrome) on or off in the sessions the server creates, so Claude can use Chrome on your machine while you work
| `-d`, `--debug[=<filter>]` | Turn on debug logging for the server, optionally filtered by category. Pass a filter only in the `=` form, such as `--debug=api,hooks`. Requires
+2 −1 lines
Upstream edited 29 Sep 2026 20:04 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
sessions
±changed
+2−2
claude-codechanged
sessions
The [desktop app](/docs/en/desktop#work-in-parallel-with-sessions), [claude.ai/code](/docs/en/claude-code-on-the-web), and the [VS Code extension](/docs/en/vs-code#resume-past-conv
The [desktop app](/docs/en/desktop#work-in-parallel-with-sessions), [claude.ai/code](/docs/en/claude-code-on-the-web), and the [VS Code extension](/docs/en/vs-code#resume-past-conv
Once you name a session through a CLI route or from claude.ai, return to it with `claude --resume <name>` or `/resume <name>`; a desktop-app session resumes in the app, which keeps
Once you name a session through a CLI route or from claude.ai, return to it with `claude --resume <name>` or `/resume <name>`; a desktop-app session resumes in the [desktop app](/d
+2 −2 lines
Upstream edited 29 Sep 2026 20:04 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
desktop
±changed
+10−2
claude-codechanged
desktop
Enterprise organizations can require SSO for all users. See [authentication](/docs/en/authentication) for plan-level details and [Setting up SSO](https://support.claude.com/en/arti
Team and Enterprise organizations can require SSO for all users. See [authentication](/docs/en/authentication) for plan-level details and [Setting up SSO](https://support.claude.co
To pick up a CLI session from inside Desktop instead, type `/resume` in the prompt box. Desktop lists the sessions you started from the CLI, and you can search them by title, folde
You can also pick up a CLI session from inside Desktop with `/resume`. The command is available in local sessions, not in SSH, WSL, or cloud sessions.
+10 −2 lines
Upstream edited 29 Sep 2026 20:04 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
keybindings
±changed
+5−5
claude-codechanged
keybindings
This example binds `Ctrl+E` to open an external editor in the chat context, and unbinds `Ctrl+U`:
This example binds `Ctrl+E` to open an external editor in the chat context, and unbinds `Ctrl+S`:
"ctrl+u": null
"ctrl+s": null
| `Task` | Background task is running |
+5 −5 lines
Upstream edited 29 Sep 2026 20:03 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
permission-modes
±changed
+6−1
claude-codechanged
permission-modes
The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission
The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission
* **If you accept**: Claude Code sets `skipDangerousModePermissionPrompt` to `true` in `~/.claude/settings.json`, so later sessions skip the dialog. To see the dialog again, remove
* **If you decline**: Claude Code exits.
+6 −1 lines
Upstream edited 29 Sep 2026 19:58 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
web-quickstart
±changed
+3−3
claude-codechanged
web-quickstart
### "Not available for the selected organization"
Enterprise organizations may need an Owner to enable cloud sessions. Contact your Anthropic account team.
### "Claude Code isn't available on your account"
+3 −3 lines
Upstream edited 29 Sep 2026 19:57 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
github-enterprise-server
±changed
+1−1
claude-codechanged
github-enterprise-server
Sign in with `/login` using your organization account. If you authenticate with an API key instead, cloud sessions fail earlier with a message asking you to run `/login`.
Claude Code couldn't read a claude.ai organization from your credentials. Sign in with `/login` using an account in your Team or Enterprise organization, since GitHub Enterprise Se
+1 −1 lines
Upstream edited 29 Sep 2026 19:57 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
communications-kit
±changed
+5−5
claude-codechanged
communications-kit
editing files or running commands. Under our Enterprise agreement, Anthropic
editing files or running commands. On our Team or Enterprise plan, Anthropic
🔒 Runs in your terminal, talks only to Anthropic's API. Under our
Enterprise plan your code and prompts are not used to train models.
🔒 Runs in your terminal, talks only to Anthropic's API. On our Team or
+5 −5 lines
Upstream edited 29 Sep 2026 19:57 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
artifacts
±changed
+5−10
claude-codechanged
artifacts
Unless you name a location, Claude writes the page to an HTML or Markdown file in a temporary directory outside your project, then publishes it. Publishing a new artifact goes thro
* **Auto mode**: the classifier reviews the publish instead of prompting you, so Claude can publish a page without you seeing a prompt. Which mode your sessions start in depends on
* **Manual and Accept edits modes**: Claude Code asks for permission; it might say something like `Claude wants to publish deploy-failures.html, uploading it to claude.ai (Anthropi
+5 −10 lines
Upstream edited 29 Sep 2026 19:56 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
changelog
±changed
+139−0
claude-codechanged
changelog
<Update label="2.1.285" description="September 29, 2026">
* Added `CLAUDE_CODE_DISABLE_WEB_FETCH` environment variable to turn off the WebFetch tool
* Added `claude --desktop` to open the Claude desktop app on the current directory, or on a session with `--continue` / `--resume <id>`
* Added `claude plugin configure <plugin>` to show a plugin's options and which are unset, or save new values read from stdin with `--values-stdin`
+139 −0 lines
Upstream edited 29 Sep 2026 19:37 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
model-config
±changed
+2−0
claude-codechanged
model-config
<a id="extended-context-with-1m" />
+2 −0 lines
Upstream edited 29 Sep 2026 19:37 UTC Recorded here 29 Sep 2026 20:07 UTC
claude-code
settings-reference
±changed
+42−13
claude-codechanged
settings-reference
Stop Claude from reading paths outside the session's [working directories](/docs/en/permissions#working-directories) with the Read, Grep, Glob, and LSP tools, in every permission m
Make Claude's file tools refuse reads outside your [working directories](/docs/en/permissions#working-directories) in every permission mode, including `bypassPermissions`. Claude C
Claude Code doesn't refuse shell commands the same way:
+42 −13 lines
Upstream edited 29 Sep 2026 19:33 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
sandboxing
±changed
+1−0
claude-codechanged
sandboxing
* **Read block**: with [`permissions.blockReadsOutsideWorkingDirectories`](/docs/en/settings-reference#permissions-blockreadsoutsideworkingdirectories) on, sandboxed commands also
+1 −0 lines
Upstream edited 29 Sep 2026 19:33 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
Claude Code recognizes a built-in set of Bash commands as read-only and runs them without a permission prompt in every mode, except for a path that [`permissions.blockReadsOutsideW
Claude Code recognizes a built-in set of Bash commands as read-only and runs them without a permission prompt in every mode, except as [`permissions.blockReadsOutsideWorkingDirecto
+1 −1 lines
Upstream edited 29 Sep 2026 19:33 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
permission-modes
±changed
+81−45
claude-codechanged
permission-modes
* Except for Bypass permissions, the dropdown shows the permission mode the local session is in, including one set from the terminal. It updates when the permission mode chan
* Except for Bypass permissions, the dropdown shows the permission mode the local session is in, including one set from the terminal. It updates when the permission mode chan
* **A blocked action**: Claude Code shows a notification and lists the action in `/permissions` under the **Recently denied** tab, where you can press `r` to retry it with a manual
* **Repeated blocks**: if the classifier blocks an action 3 times in a row or 20 times total, auto mode pauses and Claude Code resumes prompting. Approving the prompted action resu
* **Sessions that can't prompt**: a [non-interactive](/docs/en/headless) `-p` run without a [`--permission-prompt-tool`](/docs/en/cli-reference#cli-flags) has no prompt to fall bac
+81 −45 lines
Upstream edited 29 Sep 2026 19:33 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
agent-sdk/file-checkpointing
±changed
+7−126
claude-codechanged
agent-sdk/file-checkpointing
File checkpointing tracks file modifications made through the Write, Edit, and NotebookEdit tools during an agent session, allowing you to rewind files to any previous state. Want
With checkpointing, you can:
* **Undo unwanted changes** by restoring files to a known good state
+7 −126 lines
Upstream edited 29 Sep 2026 19:08 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
errors
±changed
+28−0
claude-codechanged
errors
| `Cross-session message was dropped at the recipient session's inbox` | [Tool errors](#cross-session-message-dropped-at-the-inbox) |
<h3 id="cross-session-message-dropped-at-the-inbox">
Cross-session message was dropped at the recipient session's inbox
</h3>
+28 −0 lines
Upstream edited 29 Sep 2026 19:07 UTC Recorded here 29 Sep 2026 19:37 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
For large PDFs, you can ask Claude to read specific pages instead of the whole file: a single page, a range like pages 1-10, or an open-ended range like page 3 onward.
For large PDFs, you can ask Claude to read specific pages instead of the whole file: a single page, a range like pages 1-10, or an open-ended range like page 3 onward. Reading spec
+1 −1 lines
Upstream edited 29 Sep 2026 18:53 UTC Recorded here 29 Sep 2026 19:07 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
* **PDFs**: Claude reads short `.pdf` files whole. For PDFs longer than 10 pages, it reads in ranges with a `pages` parameter, such as `"1-5"`, up to 20 pages at a time.
* **PDFs**: Claude reads short `.pdf` files whole. For PDFs longer than 10 pages, it reads in ranges with a `pages` parameter, such as `"1-5"`, up to 20 pages at a time. Page-range
+1 −1 lines
Upstream edited 29 Sep 2026 18:53 UTC Recorded here 29 Sep 2026 19:07 UTC
claude-code
errors
±changed
+25−1
claude-codechanged
errors
| `Failed to start OAuth callback server` | [Authentication](#failed-to-start-oauth-callback-server) |
| `PDF too large` / `PDF is password protected` | [Request errors](#pdf-errors) |
| `PDF too large` / `PDF is password protected` / `pdftoppm is not installed` | [Request errors](#pdf-errors) |
### Failed to start OAuth callback server
+25 −1 lines
Upstream edited 29 Sep 2026 18:53 UTC Recorded here 29 Sep 2026 19:07 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
> Run Claude Code sessions in the cloud from your browser, phone, desktop app, or terminal, move them with --cloud and --teleport, and auto-fix pull requests.
> Run Claude Code sessions in the cloud from your browser, phone, Desktop app, or terminal, move them with `--cloud` and `--teleport`, and auto-fix pull requests.
+1 −1 lines
Upstream edited 29 Sep 2026 17:27 UTC Recorded here 29 Sep 2026 17:37 UTC
claude-code
whats-new/2026-w22
±changed
+6−6
claude-codechanged
whats-new/2026-w22
Releases [v2.1.150 → v2.1.157](/docs/en/changelog#2-1-150)
Releases [v2.1.150 → v2.1.157](/docs/en/changelog.md#2-1-150)
[Model configuration](/docs/en/model-config#available-models)
[Model configuration](/docs/en/model-config.md#available-models)
[Dynamic workflows](/docs/en/workflows)
+6 −6 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w21
±changed
+3−3
claude-codechanged
whats-new/2026-w21
Releases [v2.1.143 → v2.1.149](/docs/en/changelog#2-1-143)
Releases [v2.1.143 → v2.1.149](/docs/en/changelog.md#2-1-143)
[Auto mode requirements](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
[Auto mode requirements](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode)
[Full changelog for v2.1.143–v2.1.149 →](/docs/en/changelog#2-1-143)
+3 −3 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w20
±changed
+5−5
claude-codechanged
whats-new/2026-w20
Releases [v2.1.139 → v2.1.142](/docs/en/changelog#2-1-139)
Releases [v2.1.139 → v2.1.142](/docs/en/changelog.md#2-1-139)
[Agent view](/docs/en/agent-view)
[Agent view](/docs/en/agent-view.md)
[Goals](/docs/en/goal)
+5 −5 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w19
±changed
+4−4
claude-codechanged
whats-new/2026-w19
Releases [v2.1.128 → v2.1.136](/docs/en/changelog#2-1-128)
Releases [v2.1.128 → v2.1.136](/docs/en/changelog.md#2-1-128)
[Plugins guide](/docs/en/plugins/overview)
[Plugins guide](/docs/en/plugins/overview.md)
[Interactive mode: command history](/docs/en/interactive-mode#command-history)
+4 −4 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w18
±changed
+6−6
claude-codechanged
whats-new/2026-w18
Releases [v2.1.120 → v2.1.126](/docs/en/changelog#2-1-120)
Releases [v2.1.120 → v2.1.126](/docs/en/changelog.md#2-1-120)
[CLI reference](/docs/en/cli-reference#cli-commands)
[CLI reference](/docs/en/cli-reference.md#cli-commands)
[CLI reference](/docs/en/cli-reference)
+6 −6 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w17
±changed
+7−7
claude-codechanged
whats-new/2026-w17
Releases [v2.1.114 → v2.1.119](/docs/en/changelog#2-1-114)
Releases [v2.1.114 → v2.1.119](/docs/en/changelog.md#2-1-114)
[Ultrareview guide](/docs/en/ultrareview)
[Ultrareview guide](/docs/en/ultrareview.md)
[Interactive mode: session recap](/docs/en/interactive-mode#session-recap)
+7 −7 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w16
±changed
+9−9
claude-codechanged
whats-new/2026-w16
Releases [v2.1.105 → v2.1.113](/docs/en/changelog#2-1-105)
Releases [v2.1.105 → v2.1.113](/docs/en/changelog.md#2-1-105)
[Model config: effort levels](/docs/en/model-config#adjust-effort-level)
[Model config: effort levels](/docs/en/model-config.md#adjust-effort-level)
[Routines guide](/docs/en/routines)
+9 −9 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w14
±changed
+7−7
claude-codechanged
whats-new/2026-w14
Releases [v2.1.86 → v2.1.91](/docs/en/changelog#2-1-86)
Releases [v2.1.86 → v2.1.91](/docs/en/changelog.md#2-1-86)
[Computer use guide](/docs/en/computer-use)
[Computer use guide](/docs/en/computer-use.md)
[Commands reference](/docs/en/commands)
+7 −7 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w13
±changed
+8−8
claude-codechanged
whats-new/2026-w13
Releases [v2.1.83 → v2.1.85](/docs/en/changelog#2-1-83)
Releases [v2.1.83 → v2.1.85](/docs/en/changelog.md#2-1-83)
[Permission modes guide](/docs/en/permission-modes)
[Permission modes guide](/docs/en/permission-modes.md)
[Computer use guide](/docs/en/desktop#let-claude-use-your-computer)
+8 −8 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w22
±changed
+43−82
claude-codechanged
whats-new/2026-w22
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-150">v2.1.150 → v2.1.157</a></span>
<span>4 features · May 25–29</span>
</div>
Releases [v2.1.150 → v2.1.157](/docs/en/changelog#2-1-150)
+43 −82 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w21
±changed
+13−34
claude-codechanged
whats-new/2026-w21
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-143">v2.1.143 → v2.1.149</a></span>
<span>1 feature · May 18–22</span>
</div>
Releases [v2.1.143 → v2.1.149](/docs/en/changelog#2-1-143)
+13 −34 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w20
±changed
+31−65
claude-codechanged
whats-new/2026-w20
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-139">v2.1.139 → v2.1.142</a></span>
<span>3 features · May 11–15</span>
</div>
Releases [v2.1.139 → v2.1.142](/docs/en/changelog#2-1-139)
+31 −65 lines
Upstream edited 29 Sep 2026 16:35 UTC Recorded here 20 Oct 2026 18:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.