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
821pages tracked
774 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
148 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
82 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
22 Sep 2026
274 pages
+8048 −4478 lines
claude-code
env-vars
±changed
+2−1
claude-codechanged
env-vars
| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Set to `1` to remove built-in commit and PR workflow instructions and the git status snapshot from Claude's system promp
| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Set to `1` to remove built-in commit and PR workflow instructions and the git status snapshot from Claude's context. Use
* Have Claude [treat large pastes as pasted rather than typed text](/docs/en/terminal-config#how-claude-treats-pasted-text); the content behind a `[Pasted text #N]` placeholder rea
+2 −1 lines
Recorded here 22 Sep 2026 03:07 UTC
claude-code
discover-plugins
±changed
+2−2
claude-codechanged
discover-plugins
To add one from your shell, run `claude plugin marketplace add` with the `--claudeai` flag and the name shown in the list:
To add a marketplace from that list in your shell instead, run `claude plugin marketplace add` with the `--claudeai` flag and the name the list shows:
If you haven't added that marketplace yet, Claude Code shows the source it resolved and asks you to confirm before adding it. Declining cancels the install and adds nothing. Once t
Claude Code shows the source it resolved and asks you to confirm before adding the marketplace. Declining cancels the install and adds nothing. Once the marketplace is added, the p
+2 −2 lines
Recorded here 22 Sep 2026 03:07 UTC
claude-code
context-window
±changed
+2−1
claude-codechanged
context-window
desc: 'Working directory, platform, shell, OS version, and whether this is a git repo. Git branch, status, and recent commits load as a separate block at the very end of the sy
desc: 'Working directory, platform, shell, OS version, and whether this is a git repo. Git branch, status, and recent commits load as a separate block.',
| [Git status snapshot](/docs/en/settings-reference#includegitinstructions) | Claude Code reads
+2 −1 lines
Recorded here 22 Sep 2026 03:07 UTC
claude-code
vs-code
±changed
+3−1
claude-codechanged
vs-code
The extension withholds selected text from some files. When the file is inside your workspace and matches your `files.exclude` or `search.exclude` settings, Claude receives at most
| `respectGitIgnore` | `true` | Exclude .gitignore patterns from file searches
| `respectGitIgnore` | `true` | Exclude .gitignore patterns from file searches and from [selection context](#reference-files-and-folders)
+3 −1 lines
Recorded here 22 Sep 2026 02:37 UTC
claude-code
commands
±changed
+1−0
claude-codechanged
commands
| `/update-config [request]` | **[Skill](/docs/en/skills#bundled-skills).** Describe a settings ch
+1 −0 lines
Recorded here 22 Sep 2026 02:37 UTC
claude-code
claude-directory
±changed
+6−6
claude-codechanged
claude-directory
| File | Location | Purpose
| ----------------------- | ------------------------------------------ | -----------------------------------------------------------------------------------------------------------
| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that you can't override, apart from [narrow exceptions](/docs/en/settings#secu
| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.g
| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) o
+6 −6 lines
Recorded here 22 Sep 2026 02:37 UTC
claude-code
advisor
±changed
+14−12
claude-codechanged
advisor
Claude Code doesn't invoke a saved advisor that your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist excludes. To use the advisor, pick
Claude Code doesn't invoke a saved advisor that your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist excludes. To use the advisor, pick
Claude Code still saves an advisor that your current main model doesn't support. That advisor activates after you switch to a [compatible main model](#choose-an-advisor-model) with
| Main model | Accepted advisors | Notes |
+14 −12 lines
Recorded here 22 Sep 2026 02:37 UTC
claude-code
worktrees
±changed
+11−6
claude-codechanged
worktrees
When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, and new commits.
When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, uncommitted work inside checked-out submod
* **The worktree's state can't be verified**: when Claude Code can't count the worktree's changes or can't inspect its submodule checkouts, it prompts you rather than removing the
* **Command shape**: Claude Code blocks a Bash or Monitor command when it can't verify from the command text that any git the command runs stays inside the worktree, for example wh
* **Command shape**: Claude Code blocks a Bash or Monitor command when it can't verify from the command text that any git the command runs stays inside the worktree. That happens,
+11 −6 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
workflows
±changed
+4−2
claude-codechanged
workflows
In a monorepo with several `.claude/` directories, you can keep workflows alongside the package they apply to. As of v2.1.178, saving to the project location writes to the closest
In a monorepo with several `.claude/` directories, you can keep workflows alongside the package they apply to. Saving to the project location writes to the closest `.claude/workflo
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), the c
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. `pipeline()` keeps each `null` in the results array, which is why the example end
+4 −2 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
vs-code
±changed
+6−7
claude-codechanged
vs-code
Each turn in the transcript starts with a visually hidden heading labeled with the prompt that started the turn, so you can jump between turns with your screen reader's heading nav
Two more actions are available from the keyboard:
* **Jump to the newest message**: run **Claude Code: Focus last message** from the [Command Palette](#vs-code-commands-and-shortcuts) to move focus straight to the newest message,
+6 −7 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
ultrareview
±changed
+10−3
claude-codechanged
ultrareview
A commit id or tag also works as the base, and the review then covers the changes on your branch since that commit.
* **Nothing to review**: when the diff against the base is empty, Claude Code says so and suggests staging or committing local edits, or passing a different base
* **No merge base**: when your branch shares no history with the base branch, Claude Code falls back to reviewing every tracked file in the repository instead; the fallback require
* **Nothing to review**: when the diff against the base is empty, ultrareview refuses and names the branch or commit it compared against and the case you're in, such as being on th
+10 −3 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
troubleshooting
±changed
+5−1
claude-codechanged
troubleshooting
If a session's heap memory passes 2.5GB, a critical memory usage warning appears. To free the memory, restart Claude Code and run [`claude --continue`](/docs/en/cli-reference#cli-f
Outside [fullscreen rendering](/docs/en/fullscreen), running `/compact` frees memory too. The warning disappears once memory use drops back below 2.5GB.
To let a piped command reach the clipboard directly instead, add `pbcopy *`, `wl-copy *`, or `xclip *` to [`excludedCommands`](/docs/en/settings-reference#sandbox-excludedcommands)
+5 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
troubleshoot-install
±changed
+3−3
claude-codechanged
troubleshoot-install
| `irm is not recognized` or `&& is not valid` | [Use the right command for your shell](#wrong-install-command-on-wind
| `irm is not recognized` or `The token '&&' is not a valid statement separator` | [Use the right command for your shell](#wrong-install-command-on-wind
If you see `'irm' is not recognized`, `The token '&&' is not valid`, `A parameter cannot be found that matches parameter name 'fsSL'`, or `'bash' is not recognized as the name of a
If you see `'irm' is not recognized`, `The token '&&' is not a valid statement separator`, `A parameter cannot be found that matches parameter name 'fsSL'`, or `'bash' is not recog
* **`&&` not valid**: you're in PowerShell but ran the CMD installer command. Use the PowerShell installer:
+3 −3 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
terminal-config
±changed
+2−0
claude-codechanged
terminal-config
If the paste carries [invisible Unicode characters](/docs/en/interactive-mode#invisible-characters-in-prompts), Claude Code removes them when you press Enter and puts the cleaned p
+2 −0 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
sub-agents
±changed
+14−4
claude-codechanged
sub-agents
| `tools` | No | [Tools](#available-tools) the subagent can use. Inherits every tool available to subagents if omitted. If no entry in the list resolves to a tool,
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. An entry with a specifier, such as `Bash(git push *)`, still [removes the whole tool](#ava
| `tools` | No | [Tools](#available-tools) the subagent can use, as a comma-separated string such as `Read, Grep, Bash` or a YAML list. Inherits every tool availabl
| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. Same format as `tools`. An entry with a specifier, such as `Bash(git push *)`, still [remo
In two cases, a family alias such as `opus` in the per-invocation parameter or the frontmatter resolves to the main conversation's model instead of the [version the alias points to
+14 −4 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
statusline
±changed
+2−2
claude-codechanged
statusline
| `cost.total_duration_ms` | Total wall-clock time since the session started, in milliseconds
| `cost.total_duration_ms` | Total wall-clock time the session has been running, in milliseconds. Accumulates across resumes
Track your session's API costs and elapsed time. The `cost.total_cost_usd` field accumulates the estimated cost of all API calls in the current session. The `cost.total_duration_ms
Track your session's API costs and elapsed time. The `cost.total_cost_usd` field accumulates the estimated cost of all API calls in the current session. The `cost.total_duration_ms
+2 −2 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
skills
±changed
+5−1
claude-codechanged
skills
In a session running in a linked [git worktree](/docs/en/worktrees), Claude Code searches parent directories only up to the worktree root. On Claude Code v2.1.277 or later, when th
* For cloud sessions, you can instead commit the skill to the repository's `.claude/skills/`, or ship it in a plugin declared in the repository's `.claude/settings.json`. Repo-decl
* For cloud sessions, you can instead commit the skill to the repository's `.claude/skills/`. Plugins declared in the repository's `.claude/settings.json` and plugins enabled only
+5 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
settings-reference
±changed
+28−20
claude-codechanged
settings-reference
| [`sandbox.excludedCommands`](#sandbox-excludedcommands) | Name commands that always run outside the [sandbox](/docs/en/sandboxing)
| [`sandbox.excludedCommands`](#sandbox-excludedcommands) | Name commands Claude Code can run outside the [sandbox](/docs/en/sandboxin
| [`taskOutputMaxChars`](#taskoutputmaxchars) | Set how much of a [background task's](/docs/en/tools-reference#background-
| [`taskOutputMaxChars`](#taskoutputmaxchars) | Removed in v2.1.277, together with the `TaskOutput` tool it sized
Normally, running `/fast` saves [`fastMode`](#fastmode) to a person's user settings, so fast mode is on at the start of every later session. Set this key to `true` to stop that: a
+28 −20 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
sessions
±changed
+7−1
claude-codechanged
sessions
* Generated title: if you don't name a session, Claude Code generates a session title for it. The title is a short summary of your first prompt, written by a background request to
* Generated title: if you don't name a session, Claude Code generates a session title for it. The title is a short summary of your first prompt, written by a background request to
Accepting a plan replaces the generated title with a title based on the plan. Naming the session replaces it as well.
+7 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+2−2
claude-codechanged
self-hosted-environments-deploy
The runner also reports the opt-in to Anthropic when it registers, printing `Registering as opted in to Anthropic-managed git (--use-anthropic-git-proxy)` at startup. Each session
The runner also reports the opt-in to Anthropic when it registers, printing `Registering as opted in to Anthropic-managed git (--use-anthropic-git-proxy)` at startup. Reporting the
docker build --build-arg CLAUDE_CODE_VERSION=2.1.224 -t <your-registry>/claude-runner:latest .
docker build --build-arg CLAUDE_CODE_VERSION=2.1.267 -t <your-registry>/claude-runner:latest .
+2 −2 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
security-guidance
±changed
+4−4
claude-codechanged
security-guidance
* **Cloud sessions**: declare the plugin in `.claude/settings.json` as shown under [Enable in cloud sessions](#enable-in-cloud-sessions-and-shared-repositories)
* **Cloud sessions**: enable the plugin for your claude.ai account so Claude Code loads it as a [synced plugin](/docs/en/plugins-reference#synced-plugins). A cloud session doesn't
### Enable in cloud sessions and shared repositories
User-scoped plugins do not carry into [cloud sessions](/docs/en/claude-code-on-the-web), because those sessions don't run on your machine. To enable the plugin there, or to turn it
+4 −4 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
sandboxing
±changed
+12−6
claude-codechanged
sandboxing
The session temp directory is writable inside the sandbox by default, alongside the working directory. Unless you [disable filesystem isolation](#disable-filesystem-isolation), Cla
The session temp directory is writable inside the sandbox by default, alongside the working directory. Unless you [disable filesystem isolation](#disable-filesystem-isolation), Cla
Unsandboxed commands inherit your shell's `$TMPDIR` when it is set, so while filesystem isolation is on, sandboxed and unsandboxed commands resolve `$TMPDIR` to different directori
On Linux the variable is often unset in the parent shell, so it can expand empty inside sandboxed commands; Claude Code tells Claude through its Bash tool guidance to create scra
+12 −6 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
plugins-reference
±changed
+10−3
claude-codechanged
plugins-reference
You can put plugin agent files in subfolders of `agents/`. Claude Code [loads them recursively](/docs/en/sub-agents#choose-the-subagent-scope) and joins the plugin name, each subfo
* Frontmatter `name`: it replaces only the file name, so `name: audit` in `agents/review/security.md` loads as `my-plugin:review:audit`
* Manifest [`agents`](#component-path-fields) field: a file you list there loads without subfolder names, so `"agents": "./custom/review/security.md"` loads as `my-plugin:security`
+10 −3 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
plugin-evals
±changed
+3−1
claude-codechanged
plugin-evals
Runs never stop to ask for permission. Built-in tools that need a grant you didn't give, such as `Bash`, `Write`, `Edit`, `WebFetch`, and `WebSearch`, are removed from the session,
Runs never stop to ask for permission. Built-in tools that need a grant you didn't give, such as `Bash`, `Write`, `Edit`, `WebFetch`, and `WebSearch`, are removed from the session,
The allowlist is the read-only tools the case lists in `allowed_tools`, from `Read`, `Glob`, `Grep`, `NotebookRead`, `Skill`, `Agent`, `TodoWrite`, and the task tools `TaskCreate`,
+3 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
permission-modes
±changed
+15−2
claude-codechanged
permission-modes
### Approvals you state in conversation
If you tell Claude that a blocked action is allowed, the classifier reads that as your approval and can clear the block. How you worded it decides whether the action runs, and how
* **Name the action and its specifics**: your message has to name the action and the specific thing that makes it dangerous, such as the branch of a force push. Naming the verb alo
+15 −2 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
On the Anthropic API, the `/model` picker lists a Fable model only after the server reports it available for your organization. When you type `/model fable` or a Fable model ID, Cl
On the Anthropic API, a Fable model appears in the `/model` picker unless [`availableModels`](#restrict-model-selection) or [organization model restrictions](#organization-model-re
+1 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
llm-gateway-rollout
±changed
+1−0
claude-codechanged
llm-gateway-rollout
| `CLAUDE_CODE_GATEWAY_HINT_HEADERS`
+1 −0 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
List directories in `sparsePaths`, not individual files. Root-level files like `package.json`, `tsconfig.base.json`, and lock files are always checked out alongside the directories
List directories in `sparsePaths`, not individual files. Root-level files like `package.json`, `tsconfig.base.json`, and lock files are always checked out alongside the directories
+1 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
keybindings
±changed
+4−0
claude-codechanged
keybindings
While a footer item is selected, such as a row in the agent panel below the prompt, `Enter` opens it even when you rebind `Enter` in the `Chat` context to `chat:queueSubmit` or `ch
`Chat` bindings on keys the `Footer` context doesn't bind, such as `Shift+Tab` for `chat:cycleMode`, keep working while an item is selected.
+4 −0 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
interactive-mode
±changed
+8−0
claude-codechanged
interactive-mode
## Invisible characters in prompts
Pasted text can carry Unicode characters that a terminal draws as nothing at all, such as tag characters, bidirectional controls, and zero-width spaces, so a prompt can contain tex
If Claude Code removed anything, that Enter sends nothing. The cleaned prompt goes back into the input box with a notice such as `Removed 3 invisible characters · review and press
+8 −0 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
hooks
±changed
+5−1
claude-codechanged
hooks
[Cloud sessions](/docs/en/claude-code-on-the-web) don't read your local `~/.claude/settings.json`; hooks there come from the repo, meaning its `.claude/settings.json` in a session
[Cloud sessions](/docs/en/claude-code-on-the-web) don't read your local `~/.claude/settings.json`; hooks there come from the repo's `.claude/settings.json` in a session with one re
Not every SubagentStop event comes from a subagent Claude spawned. Claude Code also runs internal agents for some of its own features, such as [prompt suggestions](/docs/en/interac
A `matcher` that names agent types doesn't match an empty `agent_type`. A hook whose matcher is omitted, `""`, or `"*"`, or is a regular expression that matches an empty string, ru
+5 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
discover-plugins
±changed
+1−1
claude-codechanged
discover-plugins
* **Cloud sessions**: declare the plugin under [`enabledPlugins`](/docs/en/settings-reference#enabledplugins) in `.claude/settings.json`.
* **Cloud sessions**: enable the plugin for your claude.ai account so Claude Code loads it as a [synced plugin](/docs/en/plugins-reference#synced-plugins).
+1 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
desktop-linux
±changed
+1−1
claude-codechanged
desktop-linux
* Ubuntu 22.04 or later, or Debian 12 or later
* A Debian-based distribution: Ubuntu 22.04 or later, or Debian 12 or later
+1 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
The plugin browser is not available in cloud sessions, and plugins you install from the desktop app aren't available for cloud sessions. To use a plugin in a cloud session, either
The plugin browser is not available in cloud sessions, and plugins you install from the desktop app aren't available for cloud sessions. A cloud session also doesn't install plugin
+1 −1 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
commands
±changed
+3−3
claude-codechanged
commands
**Before you ship.** `/diff` shows what changed. `/code-review` checks the current diff for correctness bugs and cleanups and can apply the findings with `--fix`; pass a PR number,
**Before you ship.** `/diff` shows what changed. `/code-review` checks the current diff for correctness bugs and can apply the findings with `--fix`; pass a PR number, such as `/co
| `/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]` | **[Skill](/docs/en/skills#bundled-skills).** Review the current dif
| `/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]` | **[Skill](/docs/en/skills#bundled-skills).** Review the current dif
| `/ultrareview [PR or branch]` | Run a deep, multi-agent code review in a cloud sandbox with [ultrar
+3 −3 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
cloud-environments
±changed
+2−2
claude-codechanged
cloud-environments
| Plugins declared in `.claude/settings.json`
| Plugins and marketplaces declared in your repo's `.claude/settings.json`
| Plugins enabled only in your user settings
| Plugins enabled only in your user settings
+2 −2 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
claude-projects
±changed
+12−12
claude-codechanged
claude-projects
* The `CLAUDE.md`, skills, and plugins in [each of the project's repositories](#what-threads-pick-up-from-your-repositories), and in a project with one repository, that repositor
* The `CLAUDE.md` and skills in [each of the project's repositories](#what-threads-pick-up-from-your-repositories), and in a project with one repository, that repository's permis
Each thread clones every repository in the project and loads `CLAUDE.md`, skills, and plugins from all of them. Permission rules, hooks, and `env` come only from the `.claude/setti
| In each repository | One repository
+12 −12 lines
Recorded here 22 Sep 2026 02:07 UTC
claude-code
artifacts
±changed
+7−7
claude-codechanged
artifacts
| Requirement | Available when
| :------------------ | :-----------------------------------------------------------------------------------------------------------------------------------------------------------
| Plan | Pro, Max, Team, or Enterprise. On Pro and Max plans, artifacts are private to you until you share them, and no admin management applies. On Team plans, arti
| Authentication | The session is backed by a claude.ai account: sign in with `/login` in the CLI or desktop app. Claude Tag sessions are signed in through the agent's identit
| Model provider | Anthropic API. Not available on [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), or [Microsoft Foundry
+7 −7 lines
Recorded here 22 Sep 2026 02:07 UTC
api
managed-agents/webhooks
±changed
+6−4
apichanged
managed-agents/webhooks
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/vaults
±changed
+6−4
apichanged
managed-agents/vaults
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/tools
±changed
+6−4
apichanged
managed-agents/tools
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/skills
±changed
+6−4
apichanged
managed-agents/skills
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/sessions
±changed
+6−4
apichanged
managed-agents/sessions
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/session-operations
±changed
+6−4
apichanged
managed-agents/session-operations
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/self-hosted-sandboxes-security
±changed
+6−4
apichanged
managed-agents/self-hosted-sandboxes-security
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/self-hosted-sandboxes
±changed
+6−4
apichanged
managed-agents/self-hosted-sandboxes
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/scheduled-deployments
±changed
+6−4
apichanged
managed-agents/scheduled-deployments
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/reference
±changed
+6−4
apichanged
managed-agents/reference
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/quickstart
±changed
+26−8
apichanged
managed-agents/quickstart
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+26 −8 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/permission-policies
±changed
+6−4
apichanged
managed-agents/permission-policies
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/overview
±changed
+6−4
apichanged
managed-agents/overview
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/onboarding
±changed
+6−4
apichanged
managed-agents/onboarding
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/multiagent-orchestration
±changed
+6−4
apichanged
managed-agents/multiagent-orchestration
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/migration
±changed
+6−4
apichanged
managed-agents/migration
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/memory
±changed
+3−4
apichanged
managed-agents/memory
featureMetadata:
status: beta
betaHeader: agent-memory-2026-07-22
## Compatibility
+3 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/mcp-connector
±changed
+6−4
apichanged
managed-agents/mcp-connector
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/github
±changed
+6−4
apichanged
managed-agents/github
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/files
±changed
+6−4
apichanged
managed-agents/files
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/events-and-streaming
±changed
+6−4
apichanged
managed-agents/events-and-streaming
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/environments
±changed
+6−4
apichanged
managed-agents/environments
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/define-outcomes
±changed
+6−4
apichanged
managed-agents/define-outcomes
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/cloud-sandboxes-reference
±changed
+6−4
apichanged
managed-agents/cloud-sandboxes-reference
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/budgets
±changed
+6−4
apichanged
managed-agents/budgets
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
managed-agents/agent-setup
±changed
+6−4
apichanged
managed-agents/agent-setup
featureMetadata:
topic:
title: Managed Agents
url: https://platform.claude.com/docs/en/managed-agents/overview
status: beta
+6 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
manage-claude/inference-hooks
±changed
+2−0
apichanged
manage-claude/inference-hooks
The Inference hooks system doesn't keep its own copy of prompt or response content. It stores only your hook configuration and metadata about hook activity, such as verdicts, times
+2 −0 lines
Recorded here 22 Sep 2026 00:37 UTC
api
manage-claude/compliance-sessions
±changed
+1−1
apichanged
manage-claude/compliance-sessions
* `synthetic_marker` marks records generated by the endpoint itself, such as the marker that stands in for the system prompt. When the client rewrites or compacts its conversation
* `synthetic_marker` marks records generated by the endpoint itself, such as the marker that stands in for the system prompt. When the client rewrites or compacts its conversation
+1 −1 lines
Recorded here 22 Sep 2026 00:37 UTC
api
manage-claude/compliance-faq
±changed
+1−1
apichanged
manage-claude/compliance-faq
<Accordion title="Do Cowork, Claude Code, Claude Science, and Claude for Microsoft 365 sessions appear in the Compliance API?">
<Accordion title="Do Cowork, Claude Code, Claude Science, Claude for Microsoft 365, and Claude in Chrome sessions appear in the Compliance API?">
+1 −1 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/token-counting
±changed
+11−4
apichanged
build-with-claude/token-counting
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+11 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/task-budgets
±changed
+11−5
apichanged
build-with-claude/task-budgets
featureMetadata:
status: beta
betaHeader: task-budgets-2026-03-13
supportedModels:
- claude-fable-5-1
+11 −5 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/structured-outputs
±changed
+28−6
apichanged
build-with-claude/structured-outputs
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+28 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/pdf-support
±changed
+11−4
apichanged
build-with-claude/pdf-support
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+11 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/overview
±changed
+1−1
apichanged
build-with-claude/overview
| [Compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) | Server-side context summarization for long-running conversati
| [Compaction at a token threshold](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) | Server-side context summarization for long-running conversati
+1 −1 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/files
±changed
+11−5
apichanged
build-with-claude/files
featureMetadata:
status: ga
zdr: not-eligible
supportedPlatforms:
Claude API: ga
+11 −5 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/effort
±changed
+24−5
apichanged
build-with-claude/effort
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+24 −5 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/compaction-threshold
±changed
+26−7
apichanged
build-with-claude/compaction-threshold
featureMetadata:
status: beta
betaHeader: compact-2026-01-12
zdr:
eligibility: eligible
+26 −7 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/compaction-thinking-blocks
±changed
+22−7
apichanged
build-with-claude/compaction-thinking-blocks
featureMetadata:
status: beta
betaHeader: compact-2026-09-04
supportedModels:
- claude-fable-5-1
+22 −7 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/compaction-on-demand
±changed
+23−6
apichanged
build-with-claude/compaction-on-demand
featureMetadata:
status: beta
betaHeader: compact-2026-09-04
supportedModels:
- claude-fable-5-1
+23 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/compaction-keep-recent-turns
±changed
+21−6
apichanged
build-with-claude/compaction-keep-recent-turns
featureMetadata:
status: beta
betaHeader: compact-2026-09-04
supportedModels:
- claude-fable-5-1
+21 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/compaction-background
±changed
+21−6
apichanged
build-with-claude/compaction-background
featureMetadata:
status: beta
betaHeader: compact-2026-09-04
supportedModels:
- claude-fable-5-1
+21 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/citations
±changed
+11−4
apichanged
build-with-claude/citations
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+11 −4 lines
Recorded here 22 Sep 2026 00:37 UTC
api
build-with-claude/cache-diagnostics
±changed
+12−6
apichanged
build-with-claude/cache-diagnostics
featureMetadata:
status: beta
betaHeader: cache-diagnosis-2026-04-07
zdr:
eligibility: eligible
+12 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/tool-use/tool-runner
±changed
+1−1
apichanged
agents-and-tools/tool-use/tool-runner
For long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-sid
For long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-sid
+1 −1 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+27−8
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
featureMetadata:
status: ga
zdr: not-eligible
supportedModels:
- claude-fable-5-1
+27 −8 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+22−7
apichanged
agents-and-tools/tool-use/computer-use-tool
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+22 −7 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+28−8
apichanged
agents-and-tools/tool-use/code-execution-tool
featureMetadata:
status: ga
zdr: not-eligible
supportedModels:
- claude-fable-5-1
+28 −8 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/tool-use/browser-use-tool
±changed
+19−5
apichanged
agents-and-tools/tool-use/browser-use-tool
featureMetadata:
status: ga
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
+19 −5 lines
Recorded here 22 Sep 2026 00:37 UTC
api
agents-and-tools/mcp-connector
±changed
+10−6
apichanged
agents-and-tools/mcp-connector
featureMetadata:
status: beta
betaHeader: mcp-client-2025-11-20
zdr: not-eligible
supportedPlatforms:
+10 −6 lines
Recorded here 22 Sep 2026 00:37 UTC
21 Sep 2026
272 pages
+16599 −3054 lines
claude-docs
claude-tag/admins/federated-access/troubleshooting
±changed
+6−6
claude-docschanged
claude-tag/admins/federated-access/troubleshooting
When a request from a channel can't be sent with a federated credential, it fails with an HTTP status and a one-line reason, which Claude usually quotes. Reasons with HTTP 403 and
When a request can't be sent with a federated credential, it fails with an HTTP status and a one-line reason, which Claude usually quotes. Reasons with HTTP 403 and 502 end with th
Federated connections work only in Slack channels, where Claude acts under your organization's [agent identity](/docs/claude-tag/concepts/agent-identity). The request came from a d
**How to resolve**
+6 −6 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-docs
claude-tag/admins/federated-access/gcp
±changed
+4−0
claude-docschanged
claude-tag/admins/federated-access/gcp
[Federated connections](/docs/claude-tag/admins/federated-access/limits#where-federated-connections-work) work only in agent sessions, such as a Slack channel. A test from a person
If Claude reports HTTP 403 with a reason that starts with [`request blocked: this credential only works in channel sessions, not personal ones`](/docs/claude-tag/admins/federated-a
+4 −0 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-docs
claude-tag/admins/federated-access/connect-a-gateway
±changed
+4−0
claude-docschanged
claude-tag/admins/federated-access/connect-a-gateway
[Federated connections](/docs/claude-tag/admins/federated-access/limits#where-federated-connections-work) work only in agent sessions, such as a Slack channel. A test from a person
If Claude reports HTTP 403 with a reason that starts with [`request blocked: this credential only works in channel sessions, not personal ones`](/docs/claude-tag/admins/federated-a
+4 −0 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-docs
claude-tag/admins/federated-access/aws
±changed
+4−0
claude-docschanged
claude-tag/admins/federated-access/aws
[Federated connections](/docs/claude-tag/admins/federated-access/limits#where-federated-connections-work) work only in agent sessions, such as a Slack channel. A test from a person
If Claude reports HTTP 403 with a reason that starts with [`request blocked: this credential only works in channel sessions, not personal ones`](/docs/claude-tag/admins/federated-a
+4 −0 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-docs
claude-tag/admins/federated-access/authorization-server
±changed
+4−0
claude-docschanged
claude-tag/admins/federated-access/authorization-server
[Federated connections](/docs/claude-tag/admins/federated-access/limits#where-federated-connections-work) work only in agent sessions, such as a Slack channel. A test from a person
If Claude reports HTTP 403 with a reason that starts with [`request blocked: this credential only works in channel sessions, not personal ones`](/docs/claude-tag/admins/federated-a
+4 −0 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-code
vs-code
±changed
+25−17
claude-codechanged
vs-code
| Command | Shortcut | Description
| -------------------------- | -------------------------------------------------------- | ------------------------------------------------------------------------------------------
| Focus Input | `Cmd+Esc` (Mac) / `Ctrl+Esc` (Windows/Linux) | Toggle focus between editor and Claude
| Open in Side Bar | - | Open Claude in the sidebar
| Open in Terminal | - | Open Claude in terminal mode
+25 −17 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-code
agent-sdk/overview
±changed
+8−8
claude-codechanged
agent-sdk/overview
The Agent SDK, the CLI, the Client SDK, and Managed Agents each fit different needs. Use the table to find the one that matches what you're building.
The Agent SDK, the CLI, the Client SDK, and Managed Agents differ in who runs the agent, what comes built in, and how you reach it. Find the row that matches how you want to build
| If you're... | Use
| ------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------
| Building an agent without implementing the tool loop yourself | **Agent SDK**
+8 −8 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-code
agent-sdk/hosting
±changed
+1−1
claude-codechanged
agent-sdk/hosting
If you do not need infrastructure control, custom isolation, or your own data plane, consider [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) instead:
If you don't need to run the agent loop itself on your own infrastructure, consider [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) instead. Anthropic
+1 −1 lines
Recorded here 21 Sep 2026 23:07 UTC
claude-code
agent-sdk/overview
±changed
+18−18
claude-codechanged
agent-sdk/overview
An agent is an application that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [a
An agent is an application that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [a
| Do interactive development or run one-off tasks from a terminal | [**Claude Code CLI**](/docs/en/overview.md) | The terminal interface, built for daily interactive use. |
| Do interactive development or run one-off tasks from a terminal | [**Claude Code CLI**](https://code.claude.com/docs/en/overview.md) | The terminal interface, built for daily int
To drive the same agent loop from a language other than Python or TypeScript, [run the CLI as a subprocess](/docs/en/headless.md) with the `-p` flag and `--output-format json`.
+18 −18 lines
Upstream edited 21 Sep 2026 22:47 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
agent-sdk/overview
±changed
+18−18
claude-codechanged
agent-sdk/overview
An agent is an application that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [a
An agent is an application that completes a task by planning its own steps and calling tools that read files, run commands, or edit code. The Agent SDK gives you the same tools, [a
| Do interactive development or run one-off tasks from a terminal | [**Claude Code CLI**](/docs/en/overview) | The terminal interface, built for daily interactive use. |
| Do interactive development or run one-off tasks from a terminal | [**Claude Code CLI**](/docs/en/overview.md) | The terminal interface, built for daily interactive use. |
To drive the same agent loop from a language other than Python or TypeScript, [run the CLI as a subprocess](/docs/en/headless) with the `-p` flag and `--output-format json`.
+18 −18 lines
Upstream edited 21 Sep 2026 22:47 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/overview
±changed
+3−3
claude-codechanged
agent-sdk/overview
<Note>
Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 21 Sep 2026 22:47 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/overview
±changed
+15−15
claude-codechanged
agent-sdk/overview
| You want to | Use
| ------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------
| Embed Claude Code's agent in your own Python or TypeScript application, in a process you operate | **Agent SDK**
| Do interactive development or run one-off tasks from a terminal | [**Claude Code CLI**](/docs/en/overview)
| Call the Claude API directly from your own code | [**Client SDK**](https://platform.claude.com/docs/en/cli-sdks-libraries/overvie
+15 −15 lines
Upstream edited 21 Sep 2026 22:47 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
vs-code
±changed
+24−9
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
When the current model supports [effort levels](/docs/en/model-config#adjust-effort-level), the picker also shows an **Effort** row and the model name button shows the selected l
* To sign out of your Anthropic account, select **Sign out** in the Settings section, or type `/logout`. On a [third-party provider](#use-third-party-providers), the menu doesn't
+24 −9 lines
Recorded here 21 Sep 2026 22:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.