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
820pages tracked
773 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 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
9 Sep 2026
129 pages
+2461 −1114 lines
api
managed-agents/self-hosted-sandboxes
±changed
+2−2
apichanged
managed-agents/self-hosted-sandboxes
VERSION=1.29.0
VERSION=1.30.0
ARG ANT_VERSION=1.29.0
ARG ANT_VERSION=1.30.0
+2 −2 lines
Recorded here 9 Sep 2026 17:37 UTC
api
managed-agents/quickstart
±changed
+19−8
apichanged
managed-agents/quickstart
VERSION=1.29.0
VERSION=1.30.0
Save the returned `agent.id` (the CLI's [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/scripting#version-controlling-api-resources) prints it and reco
Save the returned `agent.id` (the CLI's [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) prints it and records it in `claude-lock.json`). You'll
print(block.text, end="")
+19 −8 lines
Recorded here 9 Sep 2026 17:37 UTC
api
managed-agents/multiagent-orchestration
±changed
+3−2
apichanged
managed-agents/multiagent-orchestration
In an [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/scripting#version-controlling-api-resources) agent file (the CLI tab), a roster entry can also be the
In an [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) agent file (the CLI tab), a roster entry can also be the path to another agent's file, such as
console.log(`[${thread.agent.name}] ${thread.status}`);
const name = thread.agent.type === "agent" ? thread.agent.name : "advisor";
console.log(`[${name}] ${thread.status}`);
+3 −2 lines
Recorded here 9 Sep 2026 17:37 UTC
api
managed-agents/migration
±changed
+3−1
apichanged
managed-agents/migration
Console.WriteLine(string.Concat(message.Content.Select(block => block.Text)));
var text = string.Concat(message.Content.Select(block =>
block.Value is BetaManagedAgentsTextBlock textBlock ? textBlock.Text : ""));
Console.WriteLine(text);
+3 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
managed-agents/files
±changed
+51−20
apichanged
managed-agents/files
```json cURL
"resources": [
{ "type": "file", "file_id": "file_abc123", "mount_path": "/data.csv" },
{ "type": "file", "file_id": "file_def456", "mount_path": "/config.json" },
{ "type": "file", "file_id": "file_ghi789", "mount_path": "/src/main.py" }
+51 −20 lines
Recorded here 9 Sep 2026 17:37 UTC
api
managed-agents/events-and-streaming
±changed
+23−7
apichanged
managed-agents/events-and-streaming
Console.Write(block.Text);
if (block.Value is BetaManagedAgentsTextBlock textBlock)
{
Console.Write(textBlock.Text);
}
+23 −7 lines
Recorded here 9 Sep 2026 17:37 UTC
api
manage-claude/api-and-data-retention
±changed
+1−1
apichanged
manage-claude/api-and-data-retention
Several retention models sit outside the ZDR and HIPAA arrangements described on this page. Data accessible through the [Compliance API](https://platform.claude.com/docs/en/manage-
Several retention models sit outside the ZDR and HIPAA arrangements described on this page. Data accessible through the [Compliance API](https://platform.claude.com/docs/en/manage-
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
build-with-claude/vision-coordinates
±changed
+1−1
apichanged
build-with-claude/vision-coordinates
The [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint honors `transformations` too, rejecting an embedded image exactly as the Message
The [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) endpoint honors `transformations` too, rejecting an embedded image exactly as the Message
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
build-with-claude/token-counting
±changed
+4−2
apichanged
build-with-claude/token-counting
This endpoint returns an `invalid_request_error` for a few inputs that the Messages API accepts: [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server
[Server tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) token counts only apply to the first sampling call.
Token counting supports client tools and the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool). Requests that include other [server tools
Token counting supports PDFs with the same [PDF support limitations](https://platform.claude.com/docs/en/build-with-claude/pdf-support#pdf-support-limitations) as the Messages AP
+4 −2 lines
Recorded here 9 Sep 2026 17:37 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+1−1
apichanged
build-with-claude/mid-conversation-system-messages
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` tur
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` tur
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/tool-use/browser-use-tool
±changed
+7−5
apichanged
agents-and-tools/tool-use/browser-use-tool
The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. It works with the page both through its structure (the accessib
Choose browser use over computer use when the task stays inside webpages: Claude can read a page's structure, act on an element by reference in addition to by coordinate, set form
The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. Claude works with the page both through its structure (the acce
+7 −5 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/troubleshooting
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/troubleshooting
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/security
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/security
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/reference
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/reference
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/quickstart
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/quickstart
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/overview
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/overview
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them. They are provided "as-is" without any uptime, support, or contin
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them. They are provided "as-is" without any uptime, support, or continuity commi
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/deploy-helm
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/deploy-helm
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/deploy-compose
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/deploy-compose
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/console
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/console
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-tunnels/concepts
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/concepts
MCP tunnels are in research preview. [Request access](https://claude.com/form/claude-managed-agents) to try them.
MCP tunnels are in research preview. [Request access](https://claude.com/form/mcp-tunnels) to try them.
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
about-claude/use-case-guides/overview
±changed
+9−1
apichanged
about-claude/use-case-guides/overview
description: "Explore production guides for building common Claude use cases: ticket routing, customer support agents, content moderation, and legal summarization."
description: "Explore production guides for building common Claude use cases: ticket routing, customer support agents, content moderation, legal summarization, and commerce agents.
<Card title="Commerce agent" icon="building" href="https://platform.claude.com/docs/en/about-claude/use-case-guides/commerce-agents">
Build shopping and merchant agents from an open-source blueprint that runs on the Messages API, the Claude Agent SDK, and Claude Managed Agents.
+9 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
api
about-claude/use-case-guides/commerce-agents
+new page
+84−0
apinew page
about-claude/use-case-guides/commerce-agents
No line of the body moved in this read.
+84 −0 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-code
remote-control
±changed
+7−1
claude-codechanged
remote-control
You're not authenticated with a claude.ai account. Run `claude auth login` and choose the claude.ai option. If `ANTHROPIC_API_KEY` is set in your environment, unset it first.
You're not signed in with a claude.ai account, or another credential is taking precedence over your login. The message takes one of these forms:
* Signed out, from `/remote-control` or `--remote-control`: `Remote Control requires a claude.ai subscription.`
* Signed out, from `claude remote-control`: `You must be logged in to use Remote Control. Remote Control is only available with claude.ai subscriptions.`
+7 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
| `Your apiKeyHelper script is failing`
| `Your apiKeyHelper script is failing`, or `apiKeyHelper failed:` on stderr in non-interactive mode
+1 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-code
keybindings
±changed
+26−1
claude-codechanged
keybindings
| `EffortSlider` | Effort slider opened by `/effort` |
| `Agents` | [Agent view](/docs/en/agent-view) (`claude agents`) |
| `chat:externalEditor` | Ctrl+G, Ctrl+X Ctrl+E | Open in external editor
| `chat:externalEditor` | Ctrl+G, Ctrl+X Ctrl+E | Open in external editor. The [agent view dispatch input](/docs/en/agent-view#keyboard-shortcuts) follows this action's
### Effort slider actions
+26 −1 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-code
errors
±changed
+47−22
claude-codechanged
errors
| `API Error: 400 ... tools.N.custom.input_schema: JSON schema is invalid`
| `API Error: 400 ... tools.N.custom.input_schema: JSON schema is invalid` / `Property keys should match pattern`
| `Claude Code is being updated by npm on this machine (still not runnable after 2 min, ...)`
In [non-interactive mode](/docs/en/headless), stderr also carries the specific reason, prefixed with `apiKeyHelper failed:`.
+47 −22 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-code
agent-view
±changed
+89−24
claude-codechanged
agent-view
To read session state from a script or another program, use [`claude agents --json`](#read-session-state-from-a-script) rather than the files under `~/.claude/jobs/`.
`←` also detaches while the [`/btw` overlay](/docs/en/interactive-mode#side-questions-with-%2Fbtw) is open. Requires Claude Code v2.1.257 or later. A side question that's still ans
`Ctrl+S`, `Ctrl+T`, and `Ctrl+G` follow your [`keybindings.json`](/docs/en/keybindings). Rebind or unbind `Ctrl+S` and `Ctrl+T` with the `agents:switchView` and `agents:togglePin`
+89 −24 lines
Recorded here 9 Sep 2026 17:37 UTC
claude-docs
government/changelog
±changed
+5−0
claude-docschanged
government/changelog
<Update label="2026.09.08.1">
* Fixed web fetch failing in Claude Desktop's Code sessions on networks that block `api.anthropic.com`: sessions no longer contact that host before fetching a page, which takes e
* Fixed the sign-in page Claude Desktop opens in the browser showing an error instead of a field to enter the code when it is opened without a code or with an expired one.
</Update>
+5 −0 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
worktrees
±changed
+12−4
claude-codechanged
worktrees
A directory with no git metadata at all, such as one your [`WorktreeCreate` hook](#non-git-version-control) creates, passes the check only when no git repository contains it. If th
When an interactive resume can't return the session to its worktree, Claude Code says so with one of the messages below.
When you resume a session interactively and Claude Code can't return it to its worktree, Claude Code says so with one of the messages below. When Claude Code clears the worktree bi
In [non-interactive mode](/docs/en/headless) with `-p`, and on resumes the [Agent SDK](/docs/en/agent-sdk/sessions) runs, Claude Code stops the resume with a stderr error for every
+12 −4 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
sub-agents
±changed
+5−3
claude-codechanged
sub-agents
A background subagent that completes stays listed in [`/tasks`](/docs/en/commands), marked done and sorted below running work, for the same window as the footer hint above. Its det
A background subagent that completes stays listed in [`/tasks`](/docs/en/commands), marked done and sorted below running work, for the same 30 seconds as the footer hint. Its detai
Resumed subagents retain their full conversation history, including all previous tool calls, results, and reasoning. The subagent picks up exactly where it stopped rather than star
Resumed subagents retain their full conversation history, including all previous tool calls, results, and reasoning. If the subagent spawned [background subagents of its own](#let-
A completed subagent that receives a `SendMessage` auto-resumes in the background without a new `Agent` invocation. The same applies to a subagent that Claude stopped with the `Tas
+5 −3 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
settings-reference
±changed
+9−3
claude-codechanged
settings-reference
When you run `/effort low`, `medium`, `high`, or `xhigh` in an interactive session on your machine, Claude Code saves the level for the active model under [`modelSettings`](#models
When you run `/effort low`, `medium`, `high`, or `xhigh` in an interactive session on your machine, Claude Code saves the level for the active model under [`modelSettings`](#models
Within the same settings file, Claude Code uses a model's saved level rather than this key. [`modelSettings`](#modelsettings) states the cross-file precedence.
+9 −3 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
sessions
±changed
+4−2
claude-codechanged
sessions
| `claude --continue` | Resumes the most recent interactive session in the current directory |
| `claude --continue` | Reopens the most recent conversation in the current directory |
Claude Code leaves sessions created with [`claude -p`](/docs/en/headless) or the [Agent SDK](/docs/en/agent-sdk/overview) out of the session picker and out of `claude --continue`.
Claude Code leaves sessions created with [`claude -p`](/docs/en/headless) or the [Agent SDK](/docs/en/agent-sdk/overview) out of the session picker and out of `claude --continue`.
+4 −2 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
remote-control
±changed
+11−4
claude-codechanged
remote-control
Until you accept Remote Control's one-time confirmation, `claude remote-control` explains what it does and asks `Enable Remote Control? (y/n)` before starting the server. Answe
Until you accept Remote Control's one-time confirmation, a dialog appears before `/remote-control` connects. Select **Enable Remote Control** to accept and connect. If you sele
* **Pulling a session with `/teleport`**: when you pull a [Claude Code on the web session](/docs/en/claude-code-on-the-web#from-web-to-terminal) into your terminal with `/teleport`
+11 −4 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
model-config
±changed
+51−28
claude-codechanged
model-config
| **`best`** | Uses the latest Fable model where it's available to you, otherwise the same model as `opus`
| **`fable`** | Uses the latest Fable model for your hardest and longest-running tasks
| **`best`** | Uses the model the [`fable` alias resolves to](#fable-alias-resolution) where Fable is available to you, otherwise the same model as `opus`
| **`fable`** | Uses the [Fable model for your provider](#fable-alias-resolution) for your hardest and longest-running tasks
Unless you set `ANTHROPIC_DEFAULT_FABLE_MODEL`, the `fable` alias resolves to Fable 5.1. Before v2.1.255, it resolved to Fable 5.
+51 −28 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
managed-mcp
±changed
+5−5
claude-codechanged
managed-mcp
* In [cloud sessions](/docs/en/claude-code-on-the-web) on a host where the file is deployed, such as a [self-hosted runner](/docs/en/self-hosted-environments-configuration#mcp-serv
* In [cloud sessions](/docs/en/claude-code-on-the-web) on a host where the file is deployed, such as a [self-hosted runner](/docs/en/self-hosted-environments-configuration#mcp-serv
Claude Desktop has a managed setting with the same name whose value is an array of a different entry shape, so don't copy one into the other. Claude Code doesn't accept the array f
Claude Desktop has a managed setting with the same name whose value is an array of a different entry shape, so don't copy one into the other. Claude Code doesn't accept the array f
* A server a user passes with `--mcp-config` under the same name replaces the provided one for that run and is checked against `allowedMcpServers` like any server the user adds.
+5 −5 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
interactive-mode
±changed
+14−11
claude-codechanged
interactive-mode
* On macOS and Linux, Claude Code terminates running background tasks when the operating system signals memory pressure, provided the session has been idle for at least 30 minutes
* On macOS and Linux, Claude Code terminates running background tasks when the operating system signals memory pressure, provided the session has been idle for at least 30 minutes
* Background commands owned by a [subagent](/docs/en/sub-agents) have no time limit, except that a command owned by a subagent running in the foreground ends when that subagent giv
To return to the overlay after dismissing it, run `/btw` with no question. The overlay reopens on your most recent exchange. Press `Left` to step back through earlier answers. Befo
To return to the overlay after dismissing it, run `/btw` with no question. The overlay reopens on your most recent exchange. Before v2.1.212, `/btw` without a question printed a us
+14 −11 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
Use `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. `--continue` skips [background sessions](/docs/en/se
Use `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. On Claude Code v2.1.257 or later, when you pass `--c
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is
A setting that controls adaptive reasoning, which lets the model decide whether and how much to think on each step. Higher effort means more thinking tokens and deeper reasoning; l
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
errors
±changed
+20−1
claude-codechanged
errors
| `Model switch ... blocked by a PreModelSwitch hook`
The messages name the session's Fable model, so on Fable 5 they read `continuing on Fable 5` and `Fable 5 now uses usage credits`. Before v2.1.255, the first message began `Fable 5
The messages name the session's Fable model, so on Fable 5 they read `continuing on Fable 5` and `Fable 5 now uses usage credits`. Before v2.1.257, the first message began `Fable 5
### Model switch was blocked by a PreModelSwitch hook
+20 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
env-vars
±changed
+2−2
claude-codechanged
env-vars
| `CLAUDE_SUBAGENT_BG_SHELL_MAX_MS` | Maximum lifetime in milliseconds for a [background shell command](/docs/en/interactive-mode#background-bash-commands) th
| `CLAUDE_SUBAGENT_BG_SHELL_MAX_MS` | Removed in v2.1.260 and now a no-op. Previously capped how long a [background shell command](/docs/en/interactive-mode#b
| `VERTEX_REGION_CLAUDE_FABLE_5_1` | Override region for Claude Fable 5.1 when using Google Cloud's Agent Platform. Added in v2.1.255
| `VERTEX_REGION_CLAUDE_FABLE_5_1` | Override region for Claude Fable 5.1 when using Google Cloud's Agent Platform. Added in v2.1.257
+2 −2 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
costs
±changed
+5−1
claude-codechanged
costs
Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the
Extended thinking is enabled by default because it significantly improves performance on complex planning and reasoning tasks. Thinking tokens are billed as output tokens, and the
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
+5 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
context-window
±changed
+3−1
claude-codechanged
context-window
If you need a larger window rather than a smaller conversation, Fable 5.1, Fable 5, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Exte
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended c
Sonnet 5 runs with the 1M context window and has no `[1m]` variant to select. See [Sonnet 5 context window](/docs/en/model-config#sonnet-5-context-window) for its auto-compaction t
+3 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
communications-kit
±changed
+4−2
claude-codechanged
communications-kit
formatting, and mechanical edits where speed wins. *Fable* is the most
formatting, and mechanical edits where speed wins.
*Fable* is the most
| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content [falls back to Opus](/docs/en/model-config#automatic-mod
+4 −2 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--continue`, `-c` | Load the most recent conversation in the current directory, skipping [background sessions, sessions created with `claude -p` or
| `--continue`, `-c` | Load the most recent conversation in the current directory, including a [background session that has finished](/docs/en/sessions
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
claude-security
±changed
+1−1
claude-codechanged
claude-security
**You may see "Fable 5.1's safeguards flagged this message" or "Fable 5's safeguards flagged this message" when using a Fable model.** Due to Fable's cybersecurity safety classifie
**You may see a "safeguards flagged this message" notice when scanning on a Fable model.** The message names the model, for example "Fable 5.1's safeguards flagged this message". F
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
After the first publish, Claude prints the URL, and your browser opens to the new page. Press `Ctrl+]` at any time to reopen the most recent artifact from the terminal.
After the first publish, Claude prints the URL, and your browser opens to the new page. If you sent the prompt through [Remote Control](/docs/en/remote-control) from claude.ai, Cla
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
advisor
±changed
+1−1
claude-codechanged
advisor
Fable 5.1 requires Claude Code v2.1.255 or later and Fable 5 requires v2.1.170 or later, plus [Fable access](/docs/en/model-config#work-with-fable).
Fable 5.1 requires Claude Code v2.1.257 or later, and Fable 5 requires v2.1.170 or later. Both require [Fable access](/docs/en/model-config#work-with-fable).
+1 −1 lines
Recorded here 9 Sep 2026 17:07 UTC
claude-code
vs-code
±changed
+17−13
claude-codechanged
vs-code
* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same pick
* **Model**: select **Switch model…** from the command menu to change the model mid-session. You can also click the model name at the bottom of the prompt box to open the same pick
To create a custom style instead, select **Build a custom style** from the **Output styles** menu. Claude Code writes the [style file](/docs/en/output-styles#create-a-custom-ou
When you flip the toggle, the change applies to the sessions already open in VS Code, not only to sessions you start afterwards. If you turn it off, the open sessions disconnec
+17 −13 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
settings-reference
±changed
+34−5
claude-codechanged
settings-reference
| [`allowedMcpServers`](#allowedmcpservers) | Allowlist which [MCP servers](/docs/en/mcp) people can use
| [`allowedMcpServers`](#allowedmcpservers) | Allowlist which [MCP servers](/docs/en/mcp) users can add
| [`managedMcpServers`](#managedmcpservers) | Provide remote [MCP servers](/docs/en/managed-mcp#provide-servers-through-
Lock the `mcp` surface. Claude Code stops loading MCP servers from `~/.claude.json` and `.mcp.json`, and keeps loading plugin MCP servers and [`managed-mcp.json`](/docs/en/managed-
Lock the `mcp` surface. Claude Code stops loading MCP servers from `~/.claude.json` and `.mcp.json`, and keeps loading plugin MCP servers, [`managed-mcp.json`](/docs/en/managed-mcp
+34 −5 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
settings-example
±changed
+3−3
claude-codechanged
settings-example
// name any server "github". Servers that don't match don't load, which includes every
// stdio server when the list has only URL entries; the lock below makes this managed
// list the only allowlist that counts
// name any server "github". User-added servers that don't match don't load, including
// every stdio server when the list has only URL entries. The allowManagedMcpServersOnly
+3 −3 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
sessions
±changed
+8−7
claude-codechanged
sessions
| Command | What it does |
| :-------------------------- | :------------------------------------------------------------------------ |
| `claude --continue` | Resumes the most recent interactive session in the current directory |
| `claude --resume` | Opens the [session picker](#use-the-session-picker) |
| `claude --resume <name>` | Resumes the named session directly |
+8 −7 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
server-managed-settings
±changed
+21−16
claude-codechanged
server-managed-settings
* A [`managed-mcp.json`](/docs/en/managed-mcp) file can't be distributed through server-managed settings. Deliver the `allowedMcpServers` and `deniedMcpServers` policy keys there i
* You can't distribute a [`managed-mcp.json`](/docs/en/managed-mcp) file through server-managed settings. Deliver the `allowedMcpServers` and `deniedMcpServers` policy keys there i
Claude Code reads a `managed-mcp.json` deployed at its [system path](/docs/en/managed-mcp#exclusive-control-with-managed-mcp-json) separately from the managed settings tier, so t
* **Cross-source lock keys**: a small set of keys, such as the sandbox allowlist locks, [listed on the managed settings page](/docs/en/managed-settings#precedence-within-the-manage
+21 −16 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+15−14
claude-codechanged
self-hosted-environments-configuration
| Variable | Description
| :--------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------
| `CLAUDE_RUNNER_SESSION_ID` | Session ID in the tagged `session_...` form
| `CLAUDE_RUNNER_SESSION_UUID` | The same session ID in canonical UUID form
| `CLAUDE_RUNNER_EXIT_REASON` | How the session ended; see the values below the table
+15 −14 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
prompt-caching
±changed
+8−2
claude-codechanged
prompt-caching
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5.1, Fable 5, and Opus 5 is also a model switch. When a safety classifier flags a request and th
[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models and Opus 5 is also a model switch. When a safety classifier flags a request in a category
When a skill or command's frontmatter names a [`model`](/docs/en/skills#frontmatter-reference) other than the session's current model, that turn is also a model switch: the next re
+8 −2 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
plugins-reference
±changed
+3−1
claude-codechanged
plugins-reference
When a plugin updates mid-session, hook commands, monitors, MCP servers, and LSP servers keep using the previous version's path. Run `/reload-plugins` to switch hooks, MCP servers,
When a plugin updates mid-session, hook commands, monitors, MCP servers, and LSP servers keep using the previous version's path. Run `/reload-plugins` to switch hooks, MCP servers,
For a plugin with a `command` source, Claude Code [can reload the plugin itself](/docs/en/plugin-marketplaces#when-claude-code-re-runs-the-command).
+3 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
plugins
±changed
+1−1
claude-codechanged
plugins
As you make changes to your plugin, run `/reload-plugins` to pick up the updates without restarting. This reloads plugins, skills, agents, hooks, plugin MCP servers, and plugin LSP
As you make changes to your plugin, run `/reload-plugins` to pick up the updates without restarting. This reloads plugins, skills, agents, hooks, plugin MCP servers, and plugin LSP
+1 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
output-styles
±changed
+1−1
claude-codechanged
output-styles
A custom output style is a Markdown file: frontmatter for metadata, then the instructions to add to the system prompt.
A custom output style is a Markdown file: frontmatter for metadata, then the instructions to add to the system prompt. In the VS Code extension, you can also create the file from t
+1 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
mcp
±changed
+9−4
claude-codechanged
mcp
* `disabledMcpServers`: an opt-out list for user-configured servers, plugin servers, the claude.ai connectors Claude Code [fetches itself](#how-connectors-reach-claude-code), and b
* `disabledMcpServers`: an opt-out list for user-configured servers, plugin servers, servers your organization [provides through managed settings](/docs/en/managed-mcp#provide-serv
* If you enable or disable a plugin during a session, run `/reload-plugins` to connect or disconnect its MCP servers. When you reload, Claude Code keeps the live connections of p
* If you enable or disable a plugin during a session, run `/reload-plugins` to connect or disconnect its MCP servers. In a session without an interactive terminal, the reload doe
* When you reload, Claude Code keeps the live connections of plugin servers whose configuration is unchanged, and does the same when you [replace the session's MCP server list](/
+9 −4 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
managed-settings
±changed
+19−15
claude-codechanged
managed-settings
For managed MCP servers, which you deploy alongside any of these through `managed-mcp.json`, see [Managed MCP configuration](/docs/en/managed-mcp).
For managed MCP servers, which you deploy alongside any of these through `managed-mcp.json` or provide through the [`managedMcpServers`](/docs/en/settings-reference#managedmcpserve
* **[`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces)**: a later entry with the same name replaces the earlier one whole
* **[`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces) and [`managedMcpServers`](/docs/en/settings-reference#managedmcpservers)**: a later entry with th
| Provided MCP servers | Combines the server names from every source; when two sources set the same name, applies the higher-ranked source's whole entry
+19 −15 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
managed-mcp
±changed
+155−46
claude-codechanged
managed-mcp
> Restrict which MCP servers users can add or connect to with managed configuration files, allowlists, and denylists.
By default, anyone running Claude Code can connect any [MCP server](/docs/en/mcp) they choose. Anthropic reviews connectors against its [listing criteria](https://claude.com/docs/c
> Restrict which MCP servers users can add or connect to, or provide servers to every user, with managed configuration files, managed settings, allowlists, and denylists.
+155 −46 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
headless
±changed
+2−0
claude-codechanged
headless
In place of the session ID, you can pass `--resume` the absolute path to a session's `.jsonl` [transcript file](/docs/en/sessions#where-transcripts-are-stored), and Claude Code con
+2 −0 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
goal
±changed
+1−1
claude-codechanged
goal
When you resume a session, Claude Code restores a goal that was still active when the session ended. Claude Code restores it on every resume route: `--continue`, `--resume` with a
When you resume a session, Claude Code restores a goal that was still active when the session ended. Claude Code restores it on every resume route: `--continue`, `--resume` with a
+1 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
discover-plugins
±changed
+6−1
claude-codechanged
discover-plugins
Claude Code reloads all active plugins and shows counts for plugins, skills, agents, hooks, plugin MCP servers, and plugin LSP servers. In the skills count, Claude Code includes ev
`/reload-plugins` also runs in sessions without an interactive terminal, such as the desktop app, the Agent SDK, and [non-interactive mode](/docs/en/headless) with `-p`. Requires C
* The command runs only when you type it directly into the session, such as in the `-p` prompt or the desktop app's prompt box. When you send it over a remote connection instead, s
* The reload doesn't connect or disconnect plugin MCP servers. Those changes take effect in your next session.
+6 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
desktop
±changed
+13−13
claude-codechanged
desktop
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a Fable model. Organization administrators can turn auto mod
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-config#work-with-fable). Orga
| Key | Description
| ------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------
| `permissions.disableBypassPermissionsMode` | set to `"disable"` to prevent users from enabling Bypass permissions mode.
+13 −13 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
commands
±changed
+114−114
claude-codechanged
commands
No line of the body moved in this read.
+114 −114 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
code-review
±changed
+5−1
claude-codechanged
code-review
* `--comment`: posts the findings as inline PR comments
* `--comment`: posts the findings on a GitHub pull request as inline comments, or on a GitLab merge request as a single note
When you pass `--comment` for a GitLab merge request, Claude Code posts the findings through GitLab's `glab` CLI. Requires Claude Code v2.1.257 or later. When `glab` isn't inst
+5 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--resume`, `-r` | Resume a specific session by ID or name, or show an interactive picker to choose a session. The picker and name search include s
| `--resume`, `-r` | Resume a specific session by ID or name, or show an interactive picker to choose a session. In place of an ID, you can pass the
+1 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
claude-apps-gateway-config
±changed
+70−56
claude-codechanged
claude-apps-gateway-config
| `trusted_proxies` | No | CIDRs or IPs of load balancers in front of the gateway. When set, the gateway trusts `X-Forwarded-For` only from these peers
| `trusted_proxies` | No | CIDRs or IPs of load balancers in front of the gateway. When set, the gateway trusts `X-Forwarded-For` only from these peers
| Field | Required | Description
| ------------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------
| `issuer` | Yes | OIDC discovery base. Must serve discovery at `/.well-known/openid-configuration`. Use HTTPS in production; the gateway accepts an `ht
+70 −56 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
admin-setup
±changed
+1−1
claude-codechanged
admin-setup
| [MCP server control](/docs/en/managed-mcp) | Restrict which MCP servers users can add or connect to, or deploy a fixed set
| [MCP server control](/docs/en/managed-mcp) | Restrict which MCP servers users can add or connect to, deploy a fixed set, or provi
+1 −1 lines
Recorded here 9 Sep 2026 16:37 UTC
claude-code
settings-reference
±changed
+13−12
claude-codechanged
settings-reference
| Kind of key | How Claude Code combines it
| :----------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------
| Lists | Combines entries from every source
| Locks | Applies the strictest value any source sets. When no source sets a strict value, applies a looser value only from the highest source
| Restriction allowlists | Takes the list whole from the highest source that sets it, without adding entries from lower sources. When the highest source doesn't
+13 −12 lines
Recorded here 9 Sep 2026 16:07 UTC
claude-docs
third-party/claude-desktop/bootstrap
±changed
+16−12
claude-docschanged
third-party/claude-desktop/bootstrap
Some bootstrap-deliverable values point at local commands and credential files, or change where a user signs in. Examples are `inferenceCredentialHelper` and its related keys, `inf
When a response delivers such a value for the first time, the app applies the rest of the response and then shows a dialog listing each pending value. Choosing **Allow** applies th
Some bootstrap-deliverable values point at local commands and credential files, change where a user signs in, or change where requests are sent. Examples are `inferenceCredentialHe
+16 −12 lines
Recorded here 9 Sep 2026 15:07 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.266" description="September 8, 2026">
* Fixed a 2.1.265 regression affecting LLM-gateway and proxy setups: the undocumented `CLAUDE_CODE_USE_GATEWAY` environment variable, previously ignored unless `ANTHROPIC_BASE_UR
</Update>
+4 −0 lines
Recorded here 9 Sep 2026 00:07 UTC
8 Sep 2026
56 pages
+767 −368 lines
claude-docs
claude-science/whats-not-available-yet
−removed
+0−27
claude-docsremoved
claude-science/whats-not-available-yet
No line of the body moved in this read.
+0 −27 lines
Recorded here 8 Sep 2026 21:07 UTC
claude-docs
claude-science/admin-controls
±changed
+6−6
claude-docschanged
claude-science/admin-controls
| Setting in claude.ai | Status for Claude Science | Note
| ---------------------------------------------------- | --------------------------- | ---------------------------------------------------------------------------------------------
| Usage > Extra usage and Spend limits | Supported in Claude Science | Claude Science usage counts toward each member's 5-hour and weekly usage limits, in the same
| Billing | Supported in Claude Science | Claude Science uses the same seat as the rest of claude.ai, so there is nothing separate to p
| Models > Model access and Default model (Enterprise) | Supported in Claude Science | Turning a model off on the **Models** page, for the whole organization or for a custom role,
+6 −6 lines
Recorded here 8 Sep 2026 21:07 UTC
claude-code
changelog
±changed
+53−0
claude-codechanged
changelog
<Update label="2.1.265" description="September 8, 2026">
* Added `user.email` and `user.groups` to the telemetry Claude Desktop and Cowork send through a Claude apps gateway, matching terminal sessions
* Added support for pointing `--plugin-dir` at a folder of plugins: each child folder with a manifest loads, and children added or removed while running are picked up
* Added a 1 GB cap on tool results saved to disk; the in-conversation preview says when a saved file was truncated
+53 −0 lines
Recorded here 8 Sep 2026 21:07 UTC
claude-code
web-changelog
−removed
+0−19
claude-coderemoved
web-changelog
No line of the body moved in this read.
+0 −19 lines
Recorded here 8 Sep 2026 19:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
Claude Code builds the style into the system prompt once per conversation. An edit to this key takes effect after you run `/clear` or start a new session.
If you change this key during a session, Claude uses the new style starting with your next message. That message rebuilds the [prompt cache](/docs/en/prompt-caching#changing-output
+1 −1 lines
Recorded here 8 Sep 2026 19:07 UTC
claude-code
prompt-caching
±changed
+15−13
claude-codechanged
prompt-caching
| Layer | Content | Changes when |
| --------------- | ------------------------------------------------- | ---------------------------------------------------------------------- |
| System prompt | Core instructions, tool definitions, output style | The set of loaded tool definitions changes, or Claude Code is upgraded |
| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |
| Conversation | Your messages, Claude's responses, tool results | Every turn |
+15 −13 lines
Recorded here 8 Sep 2026 19:07 UTC
claude-code
output-styles
±changed
+2−2
claude-codechanged
output-styles
Output style is part of the system prompt, which Claude Code reads once at session start. Changes take effect after `/clear` or a new session. See [How Claude Code uses prompt cach
When you switch styles mid-session, Claude uses the new style starting with your next message. The style is part of the system prompt, so that first message rebuilds the [prompt ca
Run `/config` in the terminal and select your style under **Output style**, or set `outputStyle` in a settings file to the style's name. It takes effect after `/clear` or the n
Run `/config` in the terminal and select your style under **Output style**. Claude uses the new style starting with your next message. In the terminal, Claude Code reads style
+2 −2 lines
Recorded here 8 Sep 2026 19:07 UTC
claude-code
claude-directory
±changed
+3−3
claude-codechanged
claude-directory
when: 'Applied at session start when selected via the outputStyle setting',
when: 'Files read at startup; the style you select with outputStyle is added to the system prompt every turn',
when: 'Applied at session start when selected via the outputStyle setting',
when: 'Files read at startup; the style you select with outputStyle is added to the system prompt every turn',
tips: ['Built-in styles Default, Proactive, Concise, Explanatory, and Learning are included with Claude Code; custom styles go here', <>Set <C>keep-coding-instructions: t
+3 −3 lines
Recorded here 8 Sep 2026 19:07 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+10−10
claude-docschanged
third-party/claude-desktop/connectors-m365
| Field | Required | Description
| ---------------------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------
| `name` | Yes | Unique display name, shown to users in connector settings.
| `server` | Yes | Must be `microsoft365`. Built-in entries use this field instead of `url`, `transport`, or `command`; an entry that mixes `server` wi
| `clientId` | Yes | The Application (client) ID of the local-mode app from step 1.
+10 −10 lines
Recorded here 8 Sep 2026 18:37 UTC
claude-docs
claude-science/connectors-and-skills
±changed
+2−0
claude-docschanged
claude-science/connectors-and-skills
The AlphaFold2, Boltz-2, Chai-1, and OpenFold3 skills can build sequence alignments on the public ColabFold server (api.colabfold.com), and AlphaFold2 and Boltz-2 do so unless you
+2 −0 lines
Recorded here 8 Sep 2026 18:37 UTC
claude-code
skills
±changed
+71−86
claude-codechanged
skills
### Where skills live
Where you store a skill determines who can use it:
| Location | Path | Applies to |
+71 −86 lines
Recorded here 8 Sep 2026 18:37 UTC
claude-code
features-overview
±changed
+1−1
claude-codechanged
features-overview
* **Skills and subagents** override by name: when the same name exists at multiple levels, one definition wins based on priority (managed > user > project for skills; managed > CLI
* **Skills and subagents** override by name: when the same name exists at multiple levels, one definition wins based on priority (managed > user > project for skills; managed > CLI
+1 −1 lines
Recorded here 8 Sep 2026 18:37 UTC
claude-code
agent-sdk/skills
±changed
+2−2
claude-codechanged
agent-sdk/skills
If you have existing custom command files in `.claude/commands/`, they keep working. A command file at `.claude/commands/deploy.md` creates `/deploy` and works the same way as a sk
If you have existing custom command files in `.claude/commands/`, they keep working. A command file at `.claude/commands/deploy.md` creates `/deploy` and works the same way as a sk
* [Where skills live](/docs/en/skills#where-skills-live): all discovery levels, plugin namespacing, and what happens when a skill and a command file share a name
* [Choose where skills load](/docs/en/skills#where-skills-live): every skill location, plugin namespacing, and which skill runs when two share a name
+2 −2 lines
Recorded here 8 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/legal
±changed
+1−1
claude-docschanged
third-party/claude-desktop/legal
If your organization manages Claude Desktop on 3P from the Enterprise Admin Console for Desktop 3P (**Organization settings** on claude.ai), rather than authoring the configuration
If your organization manages Claude Desktop on 3P from the [Enterprise Admin Console for Desktop 3P](/docs/third-party/claude-desktop/admin-console) (**Organization settings** on c
+1 −1 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+6−4
claude-docschanged
third-party/claude-desktop/gateway
[MCP tool search](https://code.claude.com/docs/en/mcp#scale-with-mcp-tool-search) loads MCP tool schemas on demand instead of inlining every schema into the context window. It redu
To turn tool search on for Claude Desktop, set the [`toolSearchEnabled`](/docs/third-party/claude-desktop/configuration#toolsearchenabled) configuration key. Requires app version 1
[MCP tool search](https://code.claude.com/docs/en/mcp#scale-with-mcp-tool-search) loads MCP tool schemas on demand instead of inlining every schema into the context window. It redu
+6 −4 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+13−10
claude-docschanged
third-party/claude-desktop/connectors-m365
| Field | Required | Description
| ------------ | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------
| `name` | Yes | Unique display name, shown to users in connector settings.
| `server` | Yes | Must be `microsoft365`. Built-in entries use this field instead of `url`, `transport`, or `command`; an entry that mixes `server` with those fields
| `clientId` | Yes | The Application (client) ID of the local-mode app from step 1.
+13 −10 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
government/security/security-and-data-handling
±changed
+1−1
claude-docschanged
government/security/security-and-data-handling
For configuration and model inference, the application reaches the Claude for Government service hostname provided to your agency during onboarding. Sign-in happens in the user
For configuration and model inference, the application reaches the Claude for Government service hostname provided to your agency during onboarding. Sign-in happens in the user
+1 −1 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
government/deploy-desktop/windows-checklist
±changed
+1−1
claude-docschanged
government/deploy-desktop/windows-checklist
Claude Desktop's own traffic is HTTPS on port 443, and you can allowlist it by hostname. The [Security and data handling](/docs/government/security/security-and-data-handling#netwo
Claude Desktop's own traffic and the browser's traffic to the Claude for Government sign-in service use HTTPS on port 443. Claude for Government does not publish IP addresses for i
+1 −1 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
government/deploy-desktop/configure
±changed
+4−0
claude-docschanged
government/deploy-desktop/configure
On Linux, apt installs Claude Desktop updates, and the app does not download or install its own. By default, installing the `claude-desktop` package adds Anthropic's apt repository
To keep Linux devices on the versions your agency distributes, add the line `CLAUDE_DESKTOP_ADD_REPO=false` to `/etc/default/claude-desktop`, and create that file if it does not ex
+4 −0 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-docs
government/config/settings
±changed
+4−2
claude-docschanged
government/config/settings
Stops Claude Desktop from downloading and installing updates automatically. It is off by default, so Claude Desktop keeps itself updated. Turn it on only if your agency distributes
Stops Claude Desktop on macOS and Windows from downloading and installing updates automatically. It is off by default, so Claude Desktop keeps itself updated on those systems. Turn
Claude Desktop applies this setting once a member has signed in and the app has loaded their configuration from Claude for Government. With that configuration loaded, the app follo
Claude Desktop applies this setting once a member has signed in and the app has loaded their configuration from Claude for Government. With that configuration loaded, the app follo
+4 −2 lines
Recorded here 8 Sep 2026 18:09 UTC
claude-code
workflows
±changed
+1−1
claude-codechanged
workflows
To run a single task as a workflow without changing the session's effort level, include the keyword `ultracode` in your prompt. Asking in your own words, for example "use a workflo
To run a single task as a workflow without changing the session's effort level, include the keyword `ultracode` in your prompt. Asking in your own words, for example "use a workflo
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
web-changelog
+new page
+19−0
claude-codenew page
web-changelog
No line of the body moved in this read.
+19 −0 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
terminal-config
±changed
+1−1
claude-codechanged
terminal-config
In VS Code, Cursor, and Devin Desktop, `/terminal-setup` also updates two editor settings: it sets `terminal.integrated.gpuAcceleration` to `"off"` to prevent garbled text in the i
In VS Code, Cursor, and Devin Desktop, `/terminal-setup` also updates two editor settings: it sets `terminal.integrated.gpuAcceleration` to `"off"` to prevent garbled text in the i
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
settings-reference
±changed
+4−4
claude-codechanged
settings-reference
Choose whether typing the keyword `ultracode` in a prompt triggers a [dynamic workflow](/docs/en/workflows#ask-for-a-workflow-in-your-prompt). Set it to `false` to type the word wi
Choose whether typing the keyword `ultracode` in a prompt triggers a [dynamic workflow](/docs/en/workflows#ask-for-a-workflow-in-your-prompt). Set it to `false` to type the word wi
The `ultracode` effort setting, `/workflows`, and saved workflow commands are unaffected. Requires Claude Code v2.1.157 or later. Before v2.1.160, the trigger keyword was `workflow
The `ultracode` effort setting, `/workflows`, and saved workflow commands are unaffected.
Background auto-updates and `claude update` skip versions above the ceiling, so an installation inside the range stays inside it. `claude update`, `claude install`, and `claude doc
+4 −4 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
From v2.1.169, moving a session with [`/cd`](/docs/en/commands) relocates it to the new directory's project storage, so it appears in that directory's picker afterward. As of v2.1.
Moving a session with [`/cd`](/docs/en/commands) relocates it to the new directory's project storage, so it appears in that directory's picker afterward. As of v2.1.196, a moved se
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* `/mcp`, from v2.1.166: from the mobile app, returns a text summary of server status instead of opening the picker. On the web, `/mcp` on its own opens a directory of [claude.ai
* `/mcp`: from the mobile app, returns a text summary of server status instead of opening the picker. On the web, `/mcp` on its own opens a directory of [claude.ai connectors](/d
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
To move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps
To move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
The per-server `timeout` is a hard wall-clock limit per tool call, and progress notifications from the server don't extend it. Values below 1000 are ignored and fall through to `MC
The per-server `timeout` is a hard wall-clock limit per tool call, and progress notifications from the server don't extend it. Values below 1000 are ignored and fall through to `MC
+1 −1 lines
Recorded here 8 Sep 2026 18:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.