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
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
5,287 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
21 Aug 2026
114 pages
+8034 −1455 lines
claude-code
agent-sdk/skills
±changed
+1−1
claude-codechanged
agent-sdk/skills
Skills are discovered through the filesystem setting sources. With default `query()` options, the SDK loads user and project sources, so skills in `~/.claude/skills/`, `<cwd>/.cl
Skills are discovered through the filesystem setting sources. With default `query()` options, the SDK loads user and project sources, so skills in `~/.claude/skills/`, `<cwd>/.cl
+1 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/sessions
±changed
+1−1
claude-codechanged
agent-sdk/sessions
If you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR`, look under that name in `projects/` instead. Requir
If you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR`, look under that name in `projects/` instead. Requir
+1 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/session-storage
±changed
+1−1
claude-codechanged
agent-sdk/session-storage
Because `projectKey` encodes the working directory, resume or continue from the store from a working directory matching the original run's. In TypeScript, if you set [`CLAUDE_CODE_
Because `projectKey` encodes the working directory, resume or continue from the store from a working directory matching the original run's. In TypeScript, if you set [`CLAUDE_CODE_
+1 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
| `add_dirs` | `list[str \| Path]` | `[]` | Additional directorie
| `add_dirs` | `list[str \| Path]` | `[]` | Additional directorie
+1 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/hosting
±changed
+1−1
claude-codechanged
agent-sdk/hosting
* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory, you can a
* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory and you do
+1 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/hooks
±changed
+4−1
claude-codechanged
agent-sdk/hooks
* **`hookSpecificOutput`** controls the current operation. The fields inside depend on the hook event type. For `PreToolUse` hooks, this is where you set `permissionDecision` (`"al
* **`hookSpecificOutput`** controls the current operation. The fields you set inside depend on the hook event type:
* For `PreToolUse` hooks, this is where you set `permissionDecision` (`"allow"`, `"deny"`, `"ask"`, or `"defer"`), `permissionDecisionReason`, and `updatedInput`. If you return `
* For `PostToolUse` hooks, you can set `additionalContext` to append information to the tool result. To replace the tool's output before Claude sees it, set `updatedToolOutput`,
* In the TypeScript SDK, a `PostToolUse` callback can also return `classifierContext`, a short note about the tool call's result for the [auto mode](/docs/en/permission-modes#eli
+4 −1 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+5−5
claude-codechanged
agent-sdk/claude-code-features
| Source | What it loads | Location
| :---------- | :---------------------------------------------------------------------------------------------- | :-----------------------------------------------------------------
| `"project"` | Project CLAUDE.md, `.claude/rules/*.md`, project skills, project hooks, project `settings.json` | `<cwd>/.claude/` for `settings.json` and hooks; `<cwd>` and every
| `"user"` | User CLAUDE.md, `~/.claude/rules/*.md`, user skills, user settings | `~/.claude/`
| `"local"` | CLAUDE.local.md, `.claude/settings.local.json` | `<cwd>/.claude/` for `settings.local.json`; `<cwd>` and every pare
+5 −5 lines
Recorded here 21 Aug 2026 04:37 UTC
claude-code
agent-sdk/sessions
±changed
+8−8
claude-codechanged
agent-sdk/sessions
| What you're building | What to use
| :------------------------------------------------------ | :-----------------------------------------------------------------------------------------------------------------------
| One-shot task: single prompt, no follow-up | Nothing extra. One `query()` call handles it.
| Multi-turn chat in one process | [`ClaudeSDKClient` (Python) or `continue: true` (TypeScript)](#automatic-session-management). The SDK tracks the session
| Pick up where you left off after a process restart | `continue_conversation=True` (Python) / `continue: true` (TypeScript). Resumes the most recent session in the directory,
+8 −8 lines
Upstream edited 21 Aug 2026 04:31 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
remote-control
±changed
+5−1
claude-codechanged
remote-control
When you connect, the device shows any subagents and workflows the session already has running in the background.
When you connect, the device shows any subagents and workflows the session already has running in the background. Stop one of them from the device, and Claude Code stops that task
* **Prompts you send mid-turn**: when you send a prompt from a connected device before the current turn ends, Claude Code queues it and keeps it in the device's transcript after th
* **Model**: when you pick a [model](/docs/en/model-config) from a connected device, Claude Code runs the session on that model. The terminal's `/model` picker, `/status`, and `/co
* **Crashed sessions in server mode**: if a session served by `claude remote-control` crashes, send it a message from a connected device. Claude Code serves it again. You don't hav
+5 −1 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
permissions
±changed
+9−1
claude-codechanged
permissions
Sometimes a permission prompt offers only a one-time approval, with no "don't ask again" option and no option to allow the action for the rest of the session. Claude Code offers th
Sometimes a permission prompt offers only a one-time approval, with no "don't ask again" option and no option to allow the action for the rest of the session. Claude Code offers th
When the directory you started Claude Code in is what makes the option's label too long, Claude Code shortens it in the label, replacing your home directory with `~` and then the e
+9 −1 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
mcp
±changed
+32−0
claude-codechanged
mcp
### MCP client runtimes
Claude Code connects to MCP servers through one of two client runtimes. The v1 runtime is built on MCP TypeScript SDK 1.x. The v2 runtime is the same code on [MCP TypeScript SDK 2.
On Claude Code v2.1.232 or later, Claude Code uses the v2 runtime. It picks a runtime each time you start it and keeps it until you exit. It uses v1 when you run it:
+32 −0 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
headless
±changed
+6−4
claude-codechanged
headless
Add `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. Without it, `claude -p` loads the same [context](
Bare mode is useful for CI and scripts where you need the same result on every machine. A hook in a teammate's `~/.claude` or an MCP server in the project's `.mcp.json` won't run,
Add `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), plugins, MCP servers, auto memory, and CLAUDE.md
+6 −4 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
glossary
±changed
+3−3
claude-codechanged
glossary
A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks
A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks
With `--bare`, Claude Code starts without loading hooks, skills, plugins, MCP servers, auto memory, or CLAUDE.md. Recommended for CI and scripted calls where you need the same resu
With `--bare`, Claude Code starts without loading hooks, skills, custom commands, subagents, plugins, MCP servers, auto memory, or CLAUDE.md, apart from skills in a directory you p
Hostile instructions embedded in a file, web page, or tool result that attempt to redirect Claude toward actions you never asked for. Claude Code's defenses include the permission
+3 −3 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags)
* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, and `--append-system-prompt` flags
+1 −1 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
errors
±changed
+27−0
claude-codechanged
errors
| `proxy refused the connection`
<h3 id="the-proxy-refused-the-connection">
The proxy refused the connection
</h3>
+27 −0 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
env-vars
±changed
+5−3
claude-codechanged
env-vars
| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from `--mcp-
| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from `--mcp-
| `CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS` | Deadline in milliseconds for dialogs Claude Code forwards to a remote client, such as a [Remote Control](/docs/en/remote
| `CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS` | Deadline in milliseconds for dialogs Claude Code forwards to a remote client, such as a [Remote Control](/docs/en/remote
| `MCP_PROTOCOL_NEGOTIATION` | On the [v2 MCP client runtime](/docs/en/mcp#mcp-client-runtimes) only, whether Claude Code probes servers for MCP protoc
+5 −3 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
* Claude Code checks each message from this surface against the receiving session's [inbound controls](/docs/en/cross-session-messaging#control-inbound-messages). If you set [`cros
* Claude Code checks each message from this surface against the receiving session's [inbound controls](/docs/en/cross-session-messaging#control-inbound-messages), even when the rec
+1 −1 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
cross-session-messaging
±changed
+6−6
claude-codechanged
cross-session-messaging
* **Your other local sessions**: Claude Code sessions running on the same machine, including [background sessions](/docs/en/agent-view). A session appears only when it binds an [in
* **Your other local sessions**: Claude Code sessions running on the same machine, including [background sessions](/docs/en/agent-view). A session appears only when it binds an [in
* If a change makes `refuse` apply while messages are held, Claude Code drops every held message and reports a denial to each sender it can reach.
When the sender runs on the same machine, Claude Code tells the sending session what happened. A notice appears there when the message is held, and a follow-up reports the outcome
+6 −6 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md so scripted calls start fas
| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, custom commands, subagents, plugins, MCP servers, auto memory, and CLAUDE.md
+1 −1 lines
Recorded here 21 Aug 2026 02:07 UTC
claude-code
sub-agents
±changed
+13−2
claude-codechanged
sub-agents
Use the `mcpServers` field to give a subagent access to [MCP](/docs/en/mcp) servers that aren't available in the main conversation. Inline servers defined here are connected when t
Use the `mcpServers` field to give a subagent access to [MCP](/docs/en/mcp) servers that aren't available in the main conversation. Inline servers defined here are connected when t
When the agent is the main session, inline server definitions connect at startup alongside servers from [`.mcp.json`](/docs/en/mcp) and settings files. In `/mcp`, a remote (HTTP
When the agent is the main session, inline server definitions connect at startup alongside servers from [`.mcp.json`](/docs/en/mcp) and settings files, under the same [trust rule
+13 −2 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
self-hosted-environments-reference
±changed
+32−29
claude-codechanged
self-hosted-environments-reference
| Flag | Env var | Default | Description
| :------------------------------------ | :------------------------------------------------ | :---------------------------- | :-----------------------------------------------------
| `--api-url <url>` | none | `https://api.anthropic.com` | API base URL. Override only for testing.
| `--base-dir <path>` | `SELF_HOSTED_RUNNER_BASE_DIR` | `/workspace`; none on Windows | Directory for repository checkouts and per-session wor
| `--capacity <n>` | none | `1` | Maximum concurrent sessions this runner handles. All s
+32 −29 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+54−3
claude-codechanged
self-hosted-environments-deploy
### Authenticate to an egress proxy
Some corporate egress proxies require a `Proxy-Authorization` header on every connection. The token in that header often rotates too fast to write into the proxy URL you set in `HT
+54 −3 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
self-hosted-environments
±changed
+6−2
claude-codechanged
self-hosted-environments
The runner gives each poll request 10 seconds. When a request times out or is lost, the runner retries after a second or two instead of waiting for the next scheduled poll. Each fu
The first session a runner picks up locks the runner to the account of the user who started that session, and the runner runs up to `--capacity` concurrent sessions for that accoun
The first session a runner picks up locks the runner to the account of the user who started that session, and the runner runs up to `--capacity` concurrent sessions for that accoun
A kill that delivers `SIGTERM` needs no flag: the runner drains as [Shutdown timing](/docs/en/self-hosted-environments-deploy#shutdown-timing) describes. If your infrastructure ins
+6 −2 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
permissions
±changed
+10−8
claude-codechanged
permissions
| What the repository supplies
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| [Hooks](/docs/en/hooks) in settings files, the [`env`](/docs/en/settings#available-settings) block and helper commands such as [`apiKeyHelper`](/docs/en/settings#available-settin
| `permissions.allow` rules and `additionalDirectories` in `.claude/settings.json`
| Frontmatter hooks in a project [subagent](/docs/en/sub-agents#hooks-in-subagent-frontmatter), a project [`@skills-dir` plugin](/docs/en/plugins-reference#skills-directory-plugins
+10 −8 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
mcp
±changed
+39−11
claude-codechanged
mcp
* The command runs in a shell with a 10-second timeout, from the session's current working directory. Use an absolute path or a command on `PATH` for the script
* Claude Code runs the command in a shell and gives up on it after 10 seconds
* Claude Code picks the command's working directory by [where you configured the server](#where-the-helper-runs), so give the script as an absolute path or put it on `PATH`
The helper runs fresh on each connection, at session start and on reconnect. There is no caching, so your script is responsible for any token reuse.
+39 −11 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
errors
±changed
+19−0
claude-codechanged
errors
| `headersHelper not run — this workspace has no persisted trust`
### headersHelper not run
Claude Code connected an MCP server with its static `headers` alone and skipped the server's [`headersHelper`](/docs/en/mcp#use-dynamic-headers-for-custom-authentication), because
+19 −0 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
| `CLAUDE_CODE_BS_AS_CTRL_BACKSPACE` | Set to `0` to make Claude Code read the `0x08` byte, also written `^H`, as plain Backspace, or `1` to read it as Ctrl+Ba
+1 −0 lines
Recorded here 21 Aug 2026 01:07 UTC
claude-code
terminal-config
±changed
+7−0
claude-codechanged
terminal-config
* [Backspace deletes a whole word on Windows](#fix-backspace-deleting-a-whole-word-on-windows)
## Fix Backspace deleting a whole word on Windows
On Windows, Claude Code reads a Backspace that arrives as `^H` as Ctrl+Backspace, which [deletes the previous word](/docs/en/interactive-mode#text-editing), except when `TERM_PROGR
+7 −0 lines
Recorded here 21 Aug 2026 00:37 UTC
claude-code
code-review
±changed
+5−5
claude-codechanged
code-review
* **`REVIEW.md`**: review-only instructions, injected directly into every agent in the review pipeline as highest priority. Use it to change what gets flagged, at what severity, an
* **`REVIEW.md`**: review-only instructions, given to the agents that find and verify findings and consulted by the agents that rank and report them. Use it to say what your team w
`REVIEW.md` is a file at your repository root that overrides how Code Review behaves on your repo. Its contents are injected into the system prompt of every agent in the review pip
Because it's pasted verbatim, `REVIEW.md` is plain instructions: [`@` import syntax](/docs/en/memory#import-additional-files) is not expanded, and referenced files are not read int
+5 −5 lines
Recorded here 21 Aug 2026 00:37 UTC
claude-code
agent-sdk/typescript
±changed
+22−3
claude-codechanged
agent-sdk/typescript
};
```
hooks_applied?: boolean;
};
```
+22 −3 lines
Recorded here 21 Aug 2026 00:37 UTC
claude-code
mcp
±changed
+12−3
claude-codechanged
mcp
In `/mcp`, a server's menu, and the [`/plugin`](/docs/en/plugins) manager, a remote (HTTP or SSE) server you've used before can show a `cached` status such as `cached 2h ago · conn
In `/mcp`, including a server's menu there, and in the [`/plugin`](/docs/en/plugins) manager, a remote HTTP or SSE server you've used before can show a `cached` status such as `cac
The discovery cache is off by default unless a gradual rollout has enabled it for your account. Set [`MCP_DISCOVERY_CACHE=1`](/docs/en/env-vars) to turn it on, or `0` to keep it of
+12 −3 lines
Recorded here 21 Aug 2026 00:07 UTC
claude-code
interactive-mode
±changed
+2−1
claude-codechanged
interactive-mode
* Your account is close to or at its usage limit. To keep suggestions on until you reach the limit, set [`CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION`](/docs/en/env-vars) to `true`. Befor
* Set the `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` environment variable to `false`, which takes precedence over the setting:
* Set the [`CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION`](/docs/en/env-vars) environment variable to `false`, which takes precedence over the setting:
+2 −1 lines
Recorded here 21 Aug 2026 00:07 UTC
claude-code
errors
±changed
+37−6
claude-codechanged
errors
Match the message you see in your terminal to a section below.
Match the message you see to a section below.
| `Signed out of Claude — run /login, then /remote-control`
| `Remote Control stopped — the app running this session is now signed in to a different Claude account`
| `Remote Control stopped — the app running this session is signed out of Claude`
+37 −6 lines
Recorded here 21 Aug 2026 00:07 UTC
claude-code
env-vars
±changed
+6−3
claude-codechanged
env-vars
| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out pr
| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to turn off prompt suggestions, the grayed-out predictions that appear in your prompt input. Takes preced
| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default
| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default
| `MCP_DISCOVERY_CACHE` | Set to `0` to turn off the cross-process MCP discovery cache, so every server connects at startup instead of showing the
+6 −3 lines
Recorded here 21 Aug 2026 00:07 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
| `promptSuggestions` | `boolean` | `false`
| `promptSuggestions` | `boolean` | `false`
Emitted after each turn when `promptSuggestions` is enabled. Contains a predicted next user prompt.
Emitted after a turn when [`promptSuggestions`](#options) is enabled and Claude Code generated a suggestion for that turn. Contains the predicted next user prompt. For the turns th
+2 −2 lines
Recorded here 21 Aug 2026 00:07 UTC
20 Aug 2026
61 pages
+986 −649 lines
claude-code
prompt-caching
±changed
+9−2
claude-codechanged
prompt-caching
* **Effort level**: each effort level has its own cache for the same model. Changing it mid-session recomputes the entire request, and Claude Code asks you to confirm before applyi
* **Effort level**: each effort level has its own cache for the same model. Changing effort mid-session recomputes the entire request. See [Changing effort level](#changing-effort-
When you run `/model` at the terminal, Claude Code asks you to confirm the switch only while the current cache hasn't expired. Whether the cache has expired depends on how long it
* **Less than one [cache TTL](#cache-lifetime) ago**: the cache is still warm.
+9 −2 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
output-styles
±changed
+4−2
claude-codechanged
output-styles
There are three additional built-in output styles:
There are four additional built-in output styles:
* **Concise**: Claude leads with the result, skips preamble and narration, and keeps responses short by default, while doing the engineering work as thoroughly as in the Default st
Token usage depends on the style. Adding instructions to the system prompt increases input tokens, though prompt caching reduces this cost after the first request in a session. The
+4 −2 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
1. **During session**: use `/model <alias|name>` to switch immediately, or run `/model` with no argument to open the picker. The picker asks for confirmation when the conversation
1. **During session**: use `/model <alias|name>` to switch immediately, or run `/model` with no argument to open the picker. See [when Claude Code asks you to confirm the switch](/
+1 −1 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
keybindings
±changed
+2−2
claude-codechanged
keybindings
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input. In [fullscreen rendering](/docs/en/fullscreen#clear-the-conversation), p
| `chat:clearScreen` | Cmd+K | In [fullscreen rendering](/docs/en/fullscreen#clear-the-conversation), press twice within two seconds to run `/clear`
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation
| `chat:clearScreen` | Cmd+K | Force a full screen redraw, preserving input and conversation. See [Clear the conversation](/docs/en/fullscreen#clear-
+2 −2 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Ctrl+L` | Redraw screen
| `Ctrl+L` | Redraw screen
+1 −1 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A configuration that modifies Claude's system prompt to change response behavior, tone, or format. Output styles turn off the software-engineering-specific parts of the default sys
A configuration that modifies Claude's system prompt to change response behavior, tone, or format. Unlike [CLAUDE.md](#claude-md), which Claude Code delivers as a user message afte
+1 −1 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
fullscreen
±changed
+3−1
claude-codechanged
fullscreen
Press `Ctrl+L` twice within two seconds to run `/clear` and start a new conversation. The first press redraws the screen and shows a hint; the second press clears the conversation.
Run `/clear` to start a new conversation. Pressing `Ctrl+L` or `Cmd+K` doesn't clear the conversation; Claude Code redraws the screen and keeps it. Before v2.1.238, Claude Code ran
On iTerm2 and Terminal.app, your terminal handles `Cmd+K` itself and clears its own screen without telling Claude Code. Claude Code detects the cleared screen and repaints the conv
+3 −1 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/model [model]` | Switch the AI model and save it as your default for new sessions. For models that
| `/model [model]` | Switch the AI model and save it as your default for new sessions. For models that
+1 −1 lines
Recorded here 20 Aug 2026 23:07 UTC
claude-code
keybindings
±changed
+16−16
claude-codechanged
keybindings
| Action | Default | Description
| :-------------------- | :-------------------------------- | :---------------------------------------------------------------------------------------------------------------------
| `chat:cancel` | Escape | Cancel current input
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input. In [fullscreen rendering](/docs/en/fullscreen#clear-the-conversation), p
| `chat:clearScreen` | Cmd+K | In [fullscreen rendering](/docs/en/fullscreen#clear-the-conversation), press twice within two seconds to run `/clear`
+16 −16 lines
Recorded here 20 Aug 2026 22:37 UTC
claude-code
interactive-mode
±changed
+23−23
claude-codechanged
interactive-mode
| Shortcut | Description
| :------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------
| `Ctrl+C` | Interrupt, or clear input
| `Ctrl+X Ctrl+K` | Stop all running [background subagents](/docs/en/sub-agents#run-subagents-in-foregr
| `Ctrl+D` | Exit Claude Code session
+23 −23 lines
Recorded here 20 Aug 2026 22:37 UTC
claude-code
env-vars
±changed
+3−0
claude-codechanged
env-vars
| `CLAUDE_CODE_ARTIFACT_COMMENTS` | Set to `1` to let Claude read and reply to [comments on an artifact](/docs/en/artifacts#collect-comments-on-an-artifact)
| `CLAUDE_CODE_ARTIFACT_COMMENTS_AUTOREACT` | Set to `1` to let Claude [reply on its own to comments sent to it](/docs/en/artifacts#let-claude-reply-to-comments-on-it
* Read or reply to [comments on an artifact](/docs/en/artifacts#collect-comments-on-an-artifact), unless you set `CLAUDE_CODE_ARTIFACT_COMMENTS=1`; for Claude to reply to sent comm
+3 −0 lines
Recorded here 20 Aug 2026 22:37 UTC
claude-code
artifacts
±changed
+40−1
claude-codechanged
artifacts
A new artifact is visible only to you. To share it, open the artifact in your browser and use the **Share** control in the page header. The header names you as the artifact's autho
A new artifact is visible only to you. To share it, open the artifact in your browser and use the **Share** control in the page header. The header also links to your gallery at [cl
Viewers in your organization can see who published the page: on an artifact shared within your organization, your name is in the title menu, and on a public artifact it's in the pa
+40 −1 lines
Recorded here 20 Aug 2026 22:37 UTC
claude-code
changelog
±changed
+42−0
claude-codechanged
changelog
<Update label="2.1.238" description="August 20, 2026">
* Added a `keybindingFlavor` setting: set it to `"readline"` to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default (`"classic"`) is unchang
* Plugin marketplaces: `headersHelper` on a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archi
* A catalog entry's `headersHelper` runs only when you install or update that plugin, after its command is shown; `claude plugin install/update` ask `[y/N]` (or pass `-y`)
+42 −0 lines
Recorded here 20 Aug 2026 22:07 UTC
claude-code
routines
±changed
+1−1
claude-codechanged
routines
Create a routine from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud accou
Create a routine from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud accou
+1 −1 lines
Recorded here 20 Aug 2026 20:37 UTC
claude-code
desktop-scheduled-tasks
±changed
+2−2
claude-codechanged
desktop-scheduled-tasks
Click **Routines** in the sidebar, then click **New routine** and choose **Local**. Configure these fields:
In the [**Code** tab](/docs/en/desktop), click **Routines** in the sidebar, then click **New routine** and choose **Local**. Configure these fields:
Click a task in the **Routines** list to open its detail page. From here you can:
In the **Code** tab, click a task in the **Routines** list to open its detail page. From here you can:
+2 −2 lines
Recorded here 20 Aug 2026 20:37 UTC
claude-code
terminal-config
±changed
+1−1
claude-codechanged
terminal-config
Run `/tui fullscreen` to switch and save the preference. Your conversation relaunches intact and future sessions start in fullscreen. You can also set the `CLAUDE_CODE_NO_FLICKER`
Run `/tui fullscreen` to switch and save the preference. Your conversation relaunches intact and future sessions start in fullscreen unless a [fullscreen start fails](/docs/en/full
+1 −1 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
self-hosted-environments-reference
±changed
+1−1
claude-codechanged
self-hosted-environments-reference
* `interrupted`: the runner terminated the child for an operational reason that's neither a session success nor a runner fault, such as a drain, for example a Kubernetes rolling re
* `interrupted`: the runner terminated the child for an operational reason that's neither a session success nor a runner fault, such as a drain or the max-lifetime watchdog `--kill
+1 −1 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
self-hosted-environments-configuration
±changed
+10−1
claude-codechanged
self-hosted-environments-configuration
* `interrupted`: an idle release, startup timeout, server deassign, drain, watchdog kill, or the [`released=false` backstop](/docs/en/self-hosted-environments-reference#session-lif
* `interrupted`: an idle release, startup timeout, server deassign, drain, or watchdog kill.
#### Hook timing when the runner releases a session
+10 −1 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
remote-control
±changed
+8−4
claude-codechanged
remote-control
Remote Control is in research preview and available on all plans. On Team and Enterprise, it is off by default until an Owner enables the Remote Control toggle in [Claude Code ad
Remote Control is available on all plans. On Team and Enterprise, it is off by default until an Owner enables the Remote Control toggle in [Claude Code admin settings](https://cl
### "Remote Control is not yet enabled for your account"
The Remote Control rollout has not reached your account, or your cached entitlements are out of date. If you recently changed plans, run `claude auth logout` then `claude auth logi
+8 −4 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
permissions
±changed
+15−0
claude-codechanged
permissions
### Add a comment when you answer a permission prompt
You can attach a note to Claude when you approve or deny a single action. On most permission prompts, including Bash, PowerShell, file, and MCP tool prompts, move to **Yes** or **N
+15 −0 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
keybindings
±changed
+13−11
claude-codechanged
keybindings
| Action | Default | Description |
| :-------------------------- | :-------- | :--------------------------------------------------------------------------------------------------------------------------------- |
| `confirm:yes` | Y, Enter | Confirm action |
| `confirm:no` | N, Escape | Decline action |
| `confirm:previous` | Up | Previous option |
+13 −11 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
interactive-mode
±changed
+23−22
claude-codechanged
interactive-mode
| Shortcut | Description
| :------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------
| `Ctrl+C` | Interrupt, or clear input
| `Ctrl+X Ctrl+K` | Stop all running [background subagents](/docs/en/sub-agents#run-subagents-in-foregr
| `Ctrl+D` | Exit Claude Code session
+23 −22 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
fullscreen
±changed
+24−2
claude-codechanged
fullscreen
If you first used Claude Code before May 6, 2026 and haven't saved a `tui` setting, Claude Code may open a dialog at startup offering the switch. If you accept, Claude Code saves
If you first used Claude Code before May 6, 2026 and haven't saved a `tui` setting, Claude Code may open a dialog at startup offering the switch. If you accept, Claude Code relau
The `tui` setting and the environment variable are equivalent. The `/tui` command clears `CLAUDE_CODE_NO_FLICKER` from the relaunched process so the setting it writes takes effect.
Either one turns fullscreen rendering on. After a [failed fullscreen start](#fullscreen-renderer-didnt-finish-starting), Claude Code still honors the variable but not the setting.
<h3 id="fullscreen-renderer-didnt-finish-starting">
+24 −2 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* In a session started without those restrictions, run `/tui fullscreen`, or `/tui default` to switch back. Claude Code saves the [`tui` setting](/docs/en/settings#available-settin
* In a session started without those restrictions, run `/tui fullscreen`, or `/tui default` to switch back. Claude Code saves the [`tui` setting](/docs/en/settings#available-settin
+1 −1 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
env-vars
±changed
+2−2
claude-codechanged
env-vars
| `CLAUDE_CODE_ENABLE_TASKS` | Selects which task-tracking tools Claude Code provides in [sessions that have them](/docs/en/tools-reference#task-tool-a
| `CLAUDE_CODE_ENABLE_TASKS` | Selects which task-tracking tools Claude Code provides in [sessions that have them](/docs/en/tools-reference#task-tool-a
| `CLAUDE_CODE_NO_FLICKER` | Set to `1` to enable [fullscreen rendering](/docs/en/fullscreen), a research preview that reduces flicker and keeps memo
| `CLAUDE_CODE_NO_FLICKER` | Set to `1` to enable [fullscreen rendering](/docs/en/fullscreen), a research preview that reduces flicker and keeps memo
+2 −2 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in and [Migrate to Task tools](/docs/en/agent-sdk/todo-tracking#migrate-to-task-tools) to upd
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in.
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in and [Migrate to Task tools](/docs/en/agent-sdk/todo-tracking#migrate-to-task-tools) to upd
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in.
+2 −2 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/todo-tracking
±changed
+272−247
claude-codechanged
agent-sdk/todo-tracking
# Todo Lists
> Track and display todos using the Claude Agent SDK for organized task management
The Claude Agent SDK includes built-in todo functionality that helps organize complex workflows and keep users informed about task progression.
+272 −247 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/subagents
±changed
+9−24
claude-codechanged
agent-sdk/subagents
### Context isolation
Each subagent runs in its own fresh conversation. Intermediate tool calls and results stay inside the subagent; only its final message returns to the parent. See [What subagents in
**Example:** a `research-assistant` subagent can explore dozens of files without any of that content accumulating in the main conversation. The parent receives a concise summary, n
+9 −24 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in and [Migrate to Task tools](/docs/en/agent-sdk/todo-tracking#migrate-to-task-tools) to upd
See [Model availability](/docs/en/agent-sdk/todo-tracking#model-availability) to opt in.
+1 −1 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/mcp
±changed
+31−52
claude-codechanged
agent-sdk/mcp
Use HTTP or SSE for cloud-hosted MCP servers and remote APIs:
<Tabs>
<Tab title="In code">
<CodeGroup>
+31 −52 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/hooks
±changed
+7−13
claude-codechanged
agent-sdk/hooks
| Option | Type | Default | Description
| --------- | ---------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------
| `matcher` | `string` | `undefined` | Pattern matched against the event's filter field, following the [rules for matchers in settings files](/docs/en/hooks#matcher-pattern
| `hooks` | `HookCallback[]` | - | Required. Array of callback functions to execute when the pattern matches
| `timeout` | `number` | `undefined` | Timeout in seconds. When omitted, Claude Code applies the [event's default timeout](#hook-timeout). Your SDK callbacks follow the `co
+7 −13 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/file-checkpointing
±changed
+0−6
claude-codechanged
agent-sdk/file-checkpointing
The checkpoint system tracks:
* Files created during the session
* Files modified during the session
+0 −6 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
agent-sdk/custom-tools
±changed
+0−7
claude-codechanged
agent-sdk/custom-tools
## Related documentation
* [TypeScript SDK Reference](/docs/en/agent-sdk/typescript)
* [Python SDK Reference](/docs/en/agent-sdk/python)
+0 −7 lines
Recorded here 20 Aug 2026 19:37 UTC
claude-code
worktrees
±changed
+7−0
claude-codechanged
worktrees
<Note>
**Hook paths don't follow the worktree.** After Claude enters a worktree, Claude Code keeps `${CLAUDE_PROJECT_DIR}` in your [hooks](/docs/en/hooks#reference-scripts-by-path) wher
* **`${CLAUDE_PROJECT_DIR}` stays put**: it still points at the project root where the session started, so a hook command such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/check-style
+7 −0 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
vs-code
±changed
+17−0
claude-codechanged
vs-code
## Use a screen reader
The extension's chat panel works with screen readers. You don't need to turn anything on: the extension announces conversation activity for every user, with no visual change. This
Screen reader support in the chat panel requires Claude Code v2.1.236 or later.
+17 −0 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
tools-reference
±changed
+46−46
claude-codechanged
tools-reference
| Tool | Description
| :--------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------
| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. With [agent teams](/docs/en/agent-teams) enabled, a call that carr
| `Artifact` | Publishes an HTML or Markdown file as an [artifact](/docs/en/artifacts): a private, interactive page on claude.ai. You can share it with a public link, o
| `AskUserQuestion` | Asks multiple-choice questions to gather requirements or clarify ambiguity. Questions stay open until you answer them by default. See [AskUserQuestion to
+46 −46 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
sub-agents
±changed
+5−1
claude-codechanged
sub-agents
To see the debug log, run Claude Code with `--debug`. A [plugin subagent](/docs/en/plugins-reference#agents) whose frontmatter has no `name` or doesn't parse still loads, under its
To see the debug log, run Claude Code with `--debug`.
A [plugin subagent](/docs/en/plugins-reference#agents) whose frontmatter has no `name` or doesn't parse still loads, under its filename.
+5 −1 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
skills
±changed
+0−2
claude-codechanged
skills
All three skills require Claude Code v2.1.145 or later. Check your version with `claude --version` or the `/status` command.
+0 −2 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
settings
±changed
+3−1
claude-codechanged
settings
| `filesystem.allowRead` | Paths to re-allow reading within `denyRead` regions. An `allowRead` path re-opens reading inside a broader `denyRead` region, and an ex
| `filesystem.allowRead` | Paths to re-allow reading within `denyRead` regions. An `allowRead` path re-opens reading inside a broader `denyRead` region. Claude Co
Claude Code blocks reads of the paths a wildcard `denyRead` entry such as `~/**/.env` matches, even inside a broader `allowRead` entry. When the wildcard matches a directory, Claud
+3 −1 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
security-guidance
±changed
+0−1
claude-codechanged
security-guidance
* Claude Code CLI version 2.1.144 or later
+0 −1 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
sandboxing
±changed
+5−4
claude-codechanged
sandboxing
| Example rules | Result
| :------------------------------------------------------ | :-----------------------------------------------------------------------------------------------------------------------
| `"denyRead": ["~/"]` with `"allowRead": ["~/projects"]` | `~/projects` is readable and the rest of the home directory stays blocked. The narrower allow re-opens that part of the
| `"allowRead": ["~/"]` with `"denyRead": ["~/.env"]` | `~/.env` stays blocked and the rest of the home directory is readable. An exact deny holds inside a wider allow, so a br
| Example rules | Result
+5 −4 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
plugin-marketplaces
±changed
+28−6
claude-codechanged
plugin-marketplaces
Pick the directory by what you want to check:
##### Pick the directory to name
Claude Code checks different files depending on which directory you name. Find what you want to check in the first column, and run that row's command:
A plugin run also warns about a `CLAUDE.md` at the plugin root. For paths you set through the [component path fields](/docs/en/plugins-reference#component-path-fields) in `plugin.j
+28 −6 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
permissions
±changed
+12−5
claude-codechanged
permissions
`.claude/settings.local.json` is normally your own file, so its allow rules and additional directories apply without the trust step. Claude Code treats the file as repository-suppl
Claude Code runs git to tell the two apart, and it runs git in a folder only after you accept a trust dialog for that folder or for a parent directory whose trust extends to it, or
Versions 2.1.196 through 2.1.199 held the file's rules in your configuration home and outside git repositories too, and printed the [`this workspace has not been trusted`](/docs/en
+12 −5 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
hooks
±changed
+10−3
claude-codechanged
hooks
* `${CLAUDE_PROJECT_DIR}`: the project root. Claude Code also sets this variable in the environment of [stdio MCP servers](/docs/en/mcp#option-3-add-a-local-stdio-server) and plugi
* `${CLAUDE_PROJECT_DIR}`: the project root where the session started. Claude Code also sets this variable in the environment of [stdio MCP servers](/docs/en/mcp#option-3-add-a-loc
<Note>
**Worktrees are different.** If Claude enters a [worktree](/docs/en/worktrees) during the session, Claude Code keeps `${CLAUDE_PROJECT_DIR}` where it was and passes the worktree
+10 −3 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
goal
±changed
+11−6
claude-codechanged
goal
| Approach | Next turn starts when | Stops when
| :------------------------------------------------------------------ | :------------------------- | :------------------------------------------------------------------------------
| `/goal` | The previous turn finishes | A model confirms the condition is met or judges it impossible, or a turn fails
| [`/loop`](/docs/en/scheduled-tasks#run-a-prompt-repeatedly-with-%2Floop) | A time interval elapses | You stop it, or Claude decides the work is done
| [Stop hook](/docs/en/hooks-guide#prompt-based-hooks) | The previous turn finishes | Your own script or prompt decides
+11 −6 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
cross-session-messaging
±changed
+30−1
claude-codechanged
cross-session-messaging
* **Get status from long-running work**: have a migration or test run report back to the session you're watching, or ask it yourself from there.
* **Get status from long-running work**: have a migration or test run report back to the session you're watching, or ask it yourself from there. If that session is on this machine,
### Get a notice when another session goes idle
+30 −1 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
costs
±changed
+1−0
claude-codechanged
costs
* **Goal check-ins**: while background work keeps an active [goal](/docs/en/goal) waiting, Claude Code [asks Claude to check on that work](/docs/en/goal#background-work-defers-eval
+1 −0 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
commands
±changed
+3−3
claude-codechanged
commands
| `/run` | **[Skill](/docs/en/skills#bundled-skills).** Launch and drive your project's app t
| `/run-skill-generator` | **[Skill](/docs/en/skills#bundled-skills).** Teach `/run` and `/verify` how to bui
| `/run` | **[Skill](/docs/en/skills#bundled-skills).** Launch and drive your project's app t
| `/run-skill-generator` | **[Skill](/docs/en/skills#bundled-skills).** Teach `/run` and `/verify` how to bui
| `/verify` | **[Skill](/docs/en/skills#bundled-skills).** Confirm a code change does what it sh
+3 −3 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
accessibility
±changed
+1−1
claude-codechanged
accessibility
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersRed
Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersRed
+1 −1 lines
Recorded here 20 Aug 2026 19:07 UTC
claude-code
workflows
±changed
+0−4
claude-codechanged
workflows
```text wrap theme={null}
/workflows
```
+0 −4 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
skills
±changed
+1−15
claude-codechanged
skills
Each skill is a directory with `SKILL.md` as the entrypoint:
```text theme={null}
my-skill/
├── SKILL.md # Main instructions (required)
+1 −15 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
plugin-hints
±changed
+1−0
claude-codechanged
plugin-hints
* **Main interactive session only**: Claude Code shows the prompt only in the terminal session the user is typing into. Claude Code never prompts for a command that a [subagent](/d
+1 −0 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
mcp
±changed
+0−6
claude-codechanged
mcp
### How it works
Tool search is enabled by default. MCP tools are deferred rather than loaded into context upfront, and Claude uses a search tool to discover relevant ones when a task needs them. O
If you prefer threshold-based loading, set `ENABLE_TOOL_SEARCH=auto`. Claude Code then loads every schema upfront while the definitions it would otherwise defer total less than 10%
+0 −6 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
llm-gateway-rollout
±changed
+1−1
claude-codechanged
llm-gateway-rollout
Do not include `forceLoginMethod` or `forceLoginOrgUUID` in managed settings alongside a gateway credential. On Claude Code v2.1.146 and later, either key, with any value, blocks `
Do not include `forceLoginMethod` or `forceLoginOrgUUID` in managed settings alongside a gateway credential. Either key, with any value, blocks `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH
+1 −1 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
llm-gateway-connect
±changed
+1−1
claude-codechanged
llm-gateway-connect
| `This machine's managed settings require a first-party login`
| `This machine's managed settings require a first-party login`
+1 −1 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
google-vertex-ai
±changed
+2−2
claude-codechanged
google-vertex-ai
* When you select a primary model with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, background tasks use that model. Setting `ANTHROPIC_DEFAULT_OPUS_MODEL` without `ANTHRO
* When you select a primary model with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, background tasks use that model. When Claude Code starts the session on the model you s
When you start the session on a specific Sonnet or Opus version, with `--model`, `ANTHROPIC_MODEL`, or the [`model` setting](/docs/en/settings), that version acts as the session's
When you start the session on a specific Sonnet or Opus version, for example with `--model`, `ANTHROPIC_MODEL`, or the [`model` setting](/docs/en/settings), that version acts as th
+2 −2 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
deep-links
±changed
+1−3
claude-codechanged
deep-links
<Note>
The platform that displays the link must allow custom URL schemes. GitHub-rendered Markdown allows `http` and `https` but strips schemes like `claude-cli://` in READMEs, issues,
</Note>
The platform that displays the link must allow custom URL schemes. For what GitHub does with them and the workaround, see [The link renders as plain text instead of being clickable
+1 −3 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
code-review
±changed
+1−0
claude-codechanged
code-review
* [How Anthropic secures its AI-native software development lifecycle](https://claude.com/blog/how-anthropic-secures-its-ai-native-software-development-lifecycle): how automated re
+1 −0 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
authentication
±changed
+1−1
claude-codechanged
authentication
* **`ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper`**: blocked at startup, since organization membership can't be verified for an environment credential. Before v2.1
* **`ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper`**: blocked at startup, since organization membership can't be verified for an environment credential
+1 −1 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
amazon-bedrock
±changed
+2−2
claude-codechanged
amazon-bedrock
* When you select a primary model with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, background tasks use that model. Setting `ANTHROPIC_DEFAULT_OPUS_MODEL` without `ANTHRO
* When you select a primary model with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, background tasks use that model. When Claude Code starts the session on the model you s
When you start the session on a specific Sonnet or Opus version, with `--model`, `ANTHROPIC_MODEL`, or the [`model` setting](/docs/en/settings), that version acts as the session's
When you start the session on a specific Sonnet or Opus version, for example with `--model`, `ANTHROPIC_MODEL`, or the [`model` setting](/docs/en/settings), that version acts as th
+2 −2 lines
Recorded here 20 Aug 2026 18:37 UTC
claude-code
settings
±changed
+2−2
claude-codechanged
settings
When the helper emits `managedSettings`, that object becomes the only managed settings source for the run: Claude Code ignores remote, MDM, and file-based sources, reads the [cross
Claude Code reads `policyHelper` only from the source that wins [precedence within the managed tier](#precedence-within-the-managed-tier), so a helper configured in MDM or a manage
A [`policyHelper`](#compute-managed-settings-with-a-policy-helper) can replace every source in this list; that section says when. Otherwise, apart from the cross-source keys listed
Apart from the cross-source keys listed after the ranking, Claude Code uses the first of these sources that delivers a non-empty configuration and ignores the rest rather than merg
+2 −2 lines
Recorded here 20 Aug 2026 17:37 UTC
claude-code
server-managed-settings
±changed
+5−5
claude-codechanged
server-managed-settings
Within the managed tier, a configured [`policyHelper`](/docs/en/settings#compute-managed-settings-with-a-policy-helper) preempts every other managed source, including server-manage
Otherwise, Claude Code uses the first source that delivers a non-empty configuration. Server-managed settings are checked first, then endpoint-managed settings. Apart from the [exc
Within the managed tier, Claude Code uses the first source that delivers a non-empty configuration. Server-managed settings are checked first, then endpoint-managed settings. Apart
+5 −5 lines
Recorded here 20 Aug 2026 17:37 UTC
claude-code
claude-apps-gateway-config
±changed
+9−8
claude-codechanged
claude-apps-gateway-config
If a device also has a local `managed-settings.json` or MDM-delivered policy, the managed sources don't merge, with two per-key exceptions while no [policy helper](/docs/en/setting
If a device also has a local `managed-settings.json` or MDM-delivered policy, the managed sources don't merge, with two per-key exceptions:
1. The [policy helper](/docs/en/settings#compute-managed-settings-with-a-policy-helper)
2. Gateway-delivered settings
3. MDM, via the HKLM registry on Windows or a plist on macOS
+9 −8 lines
Recorded here 20 Aug 2026 17:37 UTC
claude-code
claude-apps-gateway
±changed
+2−2
claude-codechanged
claude-apps-gateway
Machines where developers sign in through `/login` don't need it; every Claude Code invocation fetches its policy from the gateway directly. Fleets that configure a [`policyHelper`
Machines where developers sign in through `/login` don't need it; every Claude Code invocation fetches its policy from the gateway directly. Machines where an MDM or file-based sou
Setting one lock doesn't restrict the others; each key is documented in the [settings reference](/docs/en/settings#available-settings). From an admin source below the winner, the t
Setting one lock doesn't restrict the others; each key is documented in the [settings reference](/docs/en/settings#available-settings). From an admin source below the winner, the t
+2 −2 lines
Recorded here 20 Aug 2026 17:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `managedSettings` | `Settings` | `undefined`
| `managedSettings` | `Settings` | `undefined`
+1 −1 lines
Recorded here 20 Aug 2026 17:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.