HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
5,591 of the ledger's changes in claude-code. Show every change
ReadSourcePageWhatLines
18 Sep 2026
29 pages
+484 −138 lines
claude-code
overview
±changed
+1−1
claude-codechanged
overview
[`CLAUDE.md`](/docs/en/memory) is a markdown file you add to your project root that Claude Code reads at the start of every session. Use it to set coding standards, architectur
[`CLAUDE.md`](/docs/en/memory) is a markdown file you add to your project root that Claude Code reads at the start of every session. Use it to set coding standards, architectur
+1 −1 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
memory
±changed
+135−33
claude-codechanged
memory
> Give Claude persistent instructions with CLAUDE.md files, and let Claude accumulate learnings automatically with auto memory.
> Give Claude persistent instructions with CLAUDE.md or AGENTS.md files, and let Claude accumulate learnings automatically with auto memory.
* **CLAUDE.md files**: instructions you write to give Claude persistent context
* **CLAUDE.md files**: instructions you write to give Claude persistent context. Claude can also read a repository's [`AGENTS.md` files](#agents-md), on their own or alongside CLAU
* [Use an existing AGENTS.md](#agents-md) as your project instructions, on its own or alongside CLAUDE.md
+135 −33 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
* **Your [CLAUDE.md](/docs/en/memory).** A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session.
* **Your [CLAUDE.md](/docs/en/memory).** A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session. If your repo
+1 −1 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
hooks
±changed
+2−0
claude-codechanged
hooks
This event doesn't fire when Claude [reads `AGENTS.md` directly](/docs/en/memory#agents-md) through the **Project instructions** setting. It does fire when a `CLAUDE.md` imports yo
+2 −0 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
glossary
±changed
+7−1
claude-codechanged
glossary
### AGENTS.md
A markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions with
Learn more: [AGENTS.md](/docs/en/memory#agents-md)
+7 −1 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
feature-availability
±changed
+3−2
claude-codechanged
feature-availability
Three of these have provider-specific differences:
These have provider-specific differences:
* **CLAUDE.md memory**: `CLAUDE.md` files load on every provider. Reading [`AGENTS.md` files](/docs/en/memory#agents-md) as project instructions also requires a session that [fetch
+3 −2 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
* Have Claude Code [read `AGENTS.md` files](/docs/en/memory#agents-md) as project instructions; it loads `CLAUDE.md` files only
+1 −0 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
corporate-launcher
±changed
+2−2
claude-codechanged
corporate-launcher
A launcher that wraps the `claude` command on your `PATH` can't reach these processes, because they start from the binary's direct path without looking up `claude`.
A launcher that wraps the `claude` command on your `PATH` can't reach the background service or the sessions it hosts, because they start from the binary's direct path without look
* A session you start yourself in a terminal, which runs however you invoked it. To cover these sessions, put a script named `claude` in a directory earlier on `PATH` that runs you
* A session you start yourself in a terminal, which runs however you invoked it. To cover these sessions, put a script named `claude` in a directory earlier on `PATH` that runs you
+2 −2 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. Your own setup may add more here, like an [output style](/docs
* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on
+1 −1 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
claude-directory
±changed
+8−7
claude-codechanged
claude-directory
tips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific task
tips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific task
Most users only edit `CLAUDE.md` and `settings.json`. The rest of the directory is optional: add skills, rules, or subagents as you need them.
Most users only edit `CLAUDE.md` and `settings.json`. If your repository already has an `AGENTS.md` for other coding agents, Claude Code [can read that](/docs/en/memory#agents-md)
| File | Location | Purpose
+8 −7 lines
Recorded here 18 Sep 2026 20:37 UTC
claude-code
changelog
±changed
+90−0
claude-codechanged
changelog
<Update label="2.1.277" description="September 18, 2026">
* Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in `/config` (not yet on Bedrock, Vertex or
* Added `CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1` for Claude apps gateways whose only egress is a forward proxy: every outbound request hands the proxy the hostname instead of
* Added an optional `headers:` map on Claude apps gateway upstreams, to send static headers to a proxy you run in front of a provider
+90 −0 lines
Recorded here 18 Sep 2026 18:37 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
Turn off the [claude.ai MCP connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) [Claude Code fetches itself](/docs/en/mcp#how-connectors-reach-claude-code), so it neither fetc
Turn off the [claude.ai MCP connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) [Claude Code fetches itself](/docs/en/mcp#how-connectors-reach-claude-code), so it neither fetc
Servers you pass explicitly with `--mcp-config` are unaffected. To block individual connectors instead of all of them, use [`deniedMcpServers`](#deniedmcpservers). See [Disable cla
Servers you pass explicitly with `--mcp-config` are unaffected. To block individual connectors instead of all of them, use [`deniedMcpServers`](#deniedmcpservers). See [Disable cla
+2 −2 lines
Recorded here 18 Sep 2026 17:37 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
* To change a setting, pass `key=value` to `/config`, for example `/config thinking=false`. Requires Claude Code v2.1.181 or later.
* To change a setting, pass `key=value` to `/config`, for example `/config thinking=false`.
+1 −1 lines
Recorded here 18 Sep 2026 17:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/config [key=value ...]` | Open the [Settings](/docs/en/settings) interface to adjust theme, m
| `/config [key=value ...]` | Open the [Settings](/docs/en/settings) interface to adjust theme, m
+1 −1 lines
Recorded here 18 Sep 2026 17:37 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
Commits that Claude creates in a cloud session include a `Claude-Session: <url>` git trailer, and PR bodies include the session URL on its own line. To omit the trailer and the PR-
Commits that Claude creates in a cloud session include a `Claude-Session: <url>` git trailer, and PR bodies include the session URL on its own line. To omit the trailer and the PR-
+1 −1 lines
Recorded here 18 Sep 2026 17:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
Claude applies a built-in design skill when it builds an artifact, so pages get a deliberate palette, typography, and layout without extra prompting. Requires Claude Code v2.1.182
Claude applies a built-in design skill when it builds an artifact, so pages get a deliberate palette, typography, and layout without extra prompting. That skill also looks for an e
+1 −1 lines
Recorded here 18 Sep 2026 17:37 UTC
claude-code
tools-reference
±changed
+4−4
claude-codechanged
tools-reference
| Result | What Claude gets
| :------ | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Valid | Inline up to roughly 30,000 characters by default; past that, the path of a file saved to the session directory and truncated past 64 MiB, plus a short preview from the
| Failure | Inline up to roughly 10,000 characters; past that, a head-and-tail excerpt of that size cut from the read-back window, with no file path
| Result | What Claude gets
+4 −4 lines
Recorded here 18 Sep 2026 16:37 UTC
claude-code
hooks
±changed
+6−2
claude-codechanged
hooks
Hook output strings, including `additionalContext`, `systemMessage`, and plain stdout, are capped at 10,000 characters. Output that exceeds this limit is saved to a file and replac
A hook's `additionalContext`, `systemMessage`, and `initialUserMessage` strings, and its plain stdout, are capped at 10,000 characters:
* **Scope**: Claude Code measures each string on its own, even when several hooks run for the same event. For JSON output, each field is measured separately; plain stdout is measur
* **Over the limit**: Claude Code saves the output to a file in the session directory and replaces it with the file path and a preview of up to the first 2,000 characters. A large
+6 −2 lines
Recorded here 18 Sep 2026 16:37 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.276" description="September 18, 2026">
* Fixed every request failing with `400 … Input tag 'advisor_20260301'` when `ANTHROPIC_BASE_URL` points at a proxy or gateway (2.1.275 regression)
</Update>
+4 −0 lines
Recorded here 18 Sep 2026 02:37 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
* **Files that would turn your working directory into a bare git repository**: `HEAD`, `objects`, and `refs` at the top level, plus `config` and `hooks` there when they already exi
* **Files that would turn your working directory into a bare git repository**: `HEAD`, `objects`, and `refs` at the top level, plus `config` and `hooks` there when a `HEAD` sits be
+1 −1 lines
Recorded here 18 Sep 2026 01:37 UTC
claude-code
plugins-reference
±changed
+9−5
claude-codechanged
plugins-reference
`hooks/hooks.json` can carry a top-level `$schema` key that names a JSON Schema URL for editor autocomplete and validation. Claude Code ignores the key at load time.
If a plugin contains more than one of these lockfiles, Claude Code uses the first match, checking in order: `bun.lock`, `bun.lockb`, `npm-shrinkwrap.json`, `package-lock.json`. Cla
If a plugin contains more than one of these lockfiles, Claude Code uses the first match, checking in order: `bun.lock`, `bun.lockb`, `npm-shrinkwrap.json`, `package-lock.json`.
+9 −5 lines
Recorded here 18 Sep 2026 01:37 UTC
claude-code
plugin-marketplaces
±changed
+27−6
claude-codechanged
plugin-marketplaces
You also can't name a marketplace `npm`, `pip`, `uv`, `cargo`, `github`, or `gh`, in any casing. This check requires Claude Code v2.1.275 or later.
| `npm` | object | `package`, `version?`, `registry?` | Installed via `npm install`
| `npm` | object | `package`, `version?`, `registry?` | npm package, fetched with your npm client and unpacked without running install scripts
Plugins distributed as npm packages are installed using `npm install`. This works with any package on the public npm registry or a private registry your team hosts.
+27 −6 lines
Recorded here 18 Sep 2026 01:37 UTC
claude-code
plugin-dependencies
±changed
+1−1
claude-codechanged
plugin-dependencies
To add a tool to the standard set later, publish a new `backend-standard` version with the extra dependency. Auto-update is off by default for non-Anthropic marketplaces, so engine
To add a tool to the standard set later, publish a new `backend-standard` version with the extra dependency. Unless the marketplace [auto-updates](/docs/en/discover-plugins#configu
+1 −1 lines
Recorded here 18 Sep 2026 01:37 UTC
claude-code
discover-plugins
±changed
+33−2
claude-codechanged
discover-plugins
* **claude.ai**: marketplaces hosted on claude.ai for your account, such as your organization's plugin library, which you [add by name from the **Marketplaces** tab or your shell](
### Add from claude.ai
In terminal sessions where [plugins sync from your claude.ai account](/docs/en/plugins-reference#synced-plugins), claude.ai can also list marketplaces for you, such as your organiz
+33 −2 lines
Recorded here 18 Sep 2026 01:37 UTC
17 Sep 2026
51 pages
+1388 −267 lines
claude-code
workflows
±changed
+9−9
claude-codechanged
workflows
| Constraint | Why
| :-------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------
| No mid-run user input | A run pauses on its own only for agent permission prompts
| No direct filesystem or shell access from the workflow itself | Agents read, write, and run commands. The script coordinat
| No module loading: a script that contains `import()` fails before the run starts | The script body is plain JavaScript. Put work that needs a
+9 −9 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
ultrareview
±changed
+10−3
claude-codechanged
ultrareview
Claude Code doesn't post from your machine. It sends the findings to a [cloud session](/docs/en/claude-code-on-the-web), which posts the comment through the GitHub account you've c
Claude Code doesn't post from your machine. It sends the review's session ID to the Anthropic API, which posts the review's stored findings as the comment through the GitHub accoun
When the post can't start while your session is open, Claude tells you that nothing went to the PR and why, and the findings stay in your terminal so you can post them by hand.
When the post finishes, Claude tells you the outcome:
+10 −3 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
tools-reference
±changed
+1−0
claude-codechanged
tools-reference
* WebFetch refuses `localhost` and any other hostname without a dot, such as a bare intranet name, before making a request. The [error it returns](/docs/en/errors#webfetch-cannot-f
+1 −0 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
settings-reference
±changed
+2−4
claude-codechanged
settings-reference
Render screen-reader friendly output: flat text without decorative borders or animations. Screen-reader mode uses the classic renderer, so the `tui` setting has no effect while it
Render screen-reader friendly output: flat text without decorative borders or animations. Screen-reader mode uses the classic renderer, so the `tui` setting has no effect while it
Requires Claude Code v2.1.181 or later.
* **Type**: array of objects, each with exactly one key: `serverName`, any non-empty string, so a claude.ai connector's display name such as `"claude.ai Slack"` works; `serverComma
+2 −4 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
remote-control
±changed
+2−1
claude-codechanged
remote-control
* `/config`, from v2.1.181: from the mobile app, pass `key=value` to set a setting, or run it with no argument to list the keys you can set. On the web, `/config` opens the Claud
* `/config`: from the mobile app, pass `key=value` to set a setting, or run it with no argument to list the keys you can set. On the web, `/config` opens the Claude Code section
* `/output-style`, from v2.1.269: pass the style name as an argument, for example `/output-style concise`, or run it with no argument to list the styles. From mobile and web, you
+2 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
When you switch [output styles](/docs/en/output-styles) mid-session with `/config` or the `outputStyle` setting, Claude uses the new style starting with your next message. Claude C
When you switch [output styles](/docs/en/output-styles) mid-session with [`/output-style`](/docs/en/output-styles#change-your-output-style), `/config`, or the `outputStyle` setting
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
output-styles
±changed
+4−3
claude-codechanged
output-styles
* **`/output-style` command**: run `/output-style <style>` to switch, for example `/output-style concise`. With no argument, the command lists the styles you can pick and marks the
The command also works in [non-interactive mode](/docs/en/headless) and Agent SDK sessions, and from the mobile app or web via [Remote Control](/docs/en/remote-control#limitation
<Note>The standalone `/output-style` command was deprecated in v2.1.73 and removed in v2.1.91. Use `/config` or edit the `outputStyle` setting directly.</Note>
+4 −3 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
managed-mcp
±changed
+3−3
claude-codechanged
managed-mcp
When a session receives servers through `--mcp-config` while `managed-mcp.json` is deployed, what the user sees differs between a workstation and a cloud session:
When a session receives servers through `--mcp-config` while a `managed-mcp.json` that Claude Code can read and parse is deployed, what the user sees differs between a workstation
If a user passes `--strict-mcp-config`, Claude Code exits at startup on a workstation and in a cloud session alike, because that flag asks to replace the managed set.
The `--strict-mcp-config` flag asks to replace the managed set. If a user passes it while such a file is deployed, Claude Code exits at startup on a workstation and in a cloud sess
* In `deniedMcpServers`, `serverName` accepts any non-empty string, so you can block [claude.ai connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) by their display name. For
+3 −3 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
llm-gateway-protocol
±changed
+3−1
claude-codechanged
llm-gateway-protocol
The request is `GET /v1/models?limit=1000` with a 3-second timeout, and any redirect is treated as failure so the credential can't leak to a redirect target. A gateway that respond
The request is `GET /v1/models?limit=1000` with a timeout of 3 seconds by default, and any redirect is treated as failure so the credential can't leak to a redirect target. A gatew
To give a slow gateway longer, set [`CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS`](/docs/en/env-vars#variables). The variable requires Claude Code v2.1.269 or later.
+3 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
* **No tool access**: side questions answer only from what is already in context. Claude can't read files, run commands, or search when answering a side question.
* **No tool access**: side questions answer only from what is already in context. Claude can't read files, run commands, or search when answering a side question. If Claude writes
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
headless
±changed
+7−1
claude-codechanged
headless
User-invoked [skills](/docs/en/skills) and custom commands work in `-p` mode: include `/skill-name` in the prompt string and Claude Code expands it before running. Built-in comma
Command support differs in `-p` mode:
* User-invoked [skills](/docs/en/skills) and custom commands work. Include `/skill-name` in the prompt string and Claude Code expands it before running.
* Built-in commands that only run in the terminal interface, such as `/login`, aren't available.
+7 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
errors
±changed
+40−1
claude-codechanged
errors
| `Custom output styles can't be selected over Remote Control or from a relayed message`
| `Output styles are saved to local settings (.claude/settings.local.json), which this session doesn't load`
When automatic compaction runs on this error, it normally summarizes your oldest exchanges and keeps the newest. As a last resort, Claude Code summarizes differently:
* When it can't summarize any whole exchange, Claude Code keeps your newest prompt word for word and summarizes everything before it.
+40 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
env-vars
±changed
+5−2
claude-codechanged
env-vars
| `CLAUDE_CODE_BG_TASKS_REPORT_RUNNING` | Set to `0` to make a non-interactive session report an idle status to its host at every turn end, even while background
| `CLAUDE_CODE_DISABLE_WINDOWS_SHELL_LAUNCHER` | Set to `1` to start [PowerShell tool](/docs/en/tools-reference#powershell-tool) commands on Windows directly instead of
| `CLAUDE_CODE_ENABLE_APPEND_SUBAGENT_PROMPT` | Set to `1` to enable appending extra text to the end of the system prompt of every [subagent](/docs/en/sub-agents) other
| `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` | Timeout in milliseconds for the [gateway model discovery](/docs/en/llm-gateway-protocol#model-discovery) request that `C
| `CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS` | Maximum age in milliseconds of the last transcript message for a session that ended mid-turn to continue automatically o
+5 −2 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
commands
±changed
+2−1
claude-codechanged
commands
| `/config [key=value ...]` | Open the [Settings](/docs/en/settings) interface to adjust theme, m
| `/config [key=value ...]` | Open the [Settings](/docs/en/settings) interface to adjust theme, m
| `/output-style [style]` | List [output styles](/docs/en/output-styles) or switch to one, for
+2 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
cloud-environments
±changed
+2−2
claude-codechanged
cloud-environments
MCP connectors you enable on a session or routine work without adding their hosts to **Allowed domains**, because connector traffic travels through Anthropic's servers rather tha
MCP connectors you enable on a session or routine work without adding their hosts to **Allowed domains**, because connector traffic travels through Anthropic's servers rather tha
Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. [Server-managed settings](/docs/en/s
Each environment has its own allowed-domains list; there's no organization-level allowlist that admins can push to every member's environments. [Server-managed settings](/docs/en/s
+2 −2 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
To see which connectors a running thread has at claude.ai/code, open the thread and select **Connectors** from the **+** menu beside its message box. Turning a connector off there
To see which connectors a running thread has at claude.ai/code, open the thread and select **Connectors** from the **+** menu beside its message box. Turning a connector off there
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
claude-directory
±changed
+1−1
claude-codechanged
claude-directory
description: [<>Each markdown file defines an output style: a set of instructions for Claude that, by default, also replaces the built-in software-engineering task instru
description: [<>Each markdown file defines an output style: a set of instructions for Claude that, by default, also replaces the built-in software-engineering task instru
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
claude-code-on-the-web
±changed
+6−0
claude-codechanged
claude-code-on-the-web
### Take back a queued message
If you send a message while Claude is working, the message queues until Claude reads it. To take a queued message back, click the ✕ on it. The text returns to the message box so yo
+6 −0 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
claude-apps-gateway-deploy
±changed
+1−0
claude-codechanged
claude-apps-gateway-deploy
| Startup exits with `Administrator policy requires a Cloud gateway sign-in on this machine` | The
+1 −0 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
channels-reference
±changed
+1−1
claude-codechanged
channels-reference
The verdict your server sends back is `notifications/claude/channel/permission` with two fields: `request_id` echoing the ID above, and `behavior` set to `'allow'` or `'deny'`. All
The verdict your server sends back is `notifications/claude/channel/permission` with two fields: `request_id` echoing the ID above, and `behavior` set to `'allow'` or `'deny'`. All
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
As of Claude Code v2.1.181, the flat output from `aws configure export-credentials --format process` is also accepted, with the same keys at the top level instead of nested under `
The flat output from `aws configure export-credentials --format process` is also accepted, with the same keys at the top level instead of nested under `Credentials`.
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
agent-teams
±changed
+4−0
claude-codechanged
agent-teams
When Claude messages an in-process teammate that is no longer running, Claude Code brings it back in the same session, restores any conversation saved for it, and gives it the mess
For a teammate it brings back, Claude Code re-applies a definition that came from a project's `.claude/agents/` directory or an `--add-dir` directory only if you've [trusted the fo
+4 −0 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+1−1
claude-codechanged
agent-sdk/modifying-system-prompts
* **CLI**: run `/config` and select an output style
* **CLI**: run `/output-style <style>`, for example `/output-style concise`, or run `/config` and select one. The `/output-style` command requires Claude Code v2.1.269 or later.
+1 −1 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
accessibility
±changed
+0−2
claude-codechanged
accessibility
Screen reader mode requires Claude Code v2.1.181 or later. Earlier versions reject the `--ax-screen-reader` flag with `error: unknown option '--ax-screen-reader'`.
+0 −2 lines
Recorded here 17 Sep 2026 23:37 UTC
claude-code
web-quickstart
±changed
+1−1
claude-codechanged
web-quickstart
Go to [claude.ai/code](https://claude.ai/code) and sign in with your claude.ai account. On macOS or Windows, the first screen offers the Claude Code desktop app and other ways
Go to [claude.ai/code](https://claude.ai/code) and sign in with your claude.ai account.
+1 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
vs-code
±changed
+2−0
claude-codechanged
vs-code
If your organization's policy turns product feedback off, **Report a problem** doesn't appear in the menu, and `/bug` and `/feedback` show a `Feedback is turned off by your org
+2 −0 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
skills
±changed
+2−0
claude-codechanged
skills
If your organization turns Skills off on claude.ai, Claude Code removes the downloaded skills and they stop loading. The removed skills move to `~/.claude/skills/.trash/`, where yo
+2 −0 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
If only a repository's checked-in settings file adds a directory, the block still applies to reads there. Files Claude Code itself needs stay readable, such as your skills, plugins
If only a repository's checked-in settings file adds a directory, the block still applies to reads there. When [`autoMemoryDirectory`](#automemorydirectory) comes from the project'
+1 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
scheduled-tasks
±changed
+1−1
claude-codechanged
scheduled-tasks
* With [feature-flag fetching off](/docs/en/env-vars#features-that-need-feature-flag-fetching), Claude Code stores a task you asked to keep across sessions in the project's `.claud
* With [feature-flag fetching off](/docs/en/env-vars#features-that-need-feature-flag-fetching), Claude Code stores a task you asked to keep across sessions in the project's `.claud
+1 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
routines
±changed
+6−6
claude-codechanged
routines
Go to [claude.ai/code/routines](https://claude.ai/code/routines), click the routine you want to trigger via API, then click the pencil icon to open **Edit routine**.
Go to [claude.ai/code/routines](https://claude.ai/code/routines), click the routine you want to trigger via API, then open the menu next to the routine's name and select **Edit
Go to [claude.ai/code/routines](https://claude.ai/code/routines), click the routine, then click the pencil icon to open **Edit routine**.
Go to [claude.ai/code/routines](https://claude.ai/code/routines), click the routine, then open the menu next to the routine's name and select **Edit**.
* Use the toggle in the **Repeats** section to pause or resume the schedule. Paused routines keep their configuration but don't run until you re-enable them.
+6 −6 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
plugin-relevance
±changed
+3−1
claude-codechanged
plugin-relevance
The `cli`, `hosts`, `filesRead`, and `manifestDeps` signals need session history, so they can only match on the spinner tip and the Discover tab. The `filesRead` and `manifestDeps`
The `cli`, `hosts`, `filesRead`, and `manifestDeps` signals need session history, so they can only match on the spinner tip and the Discover tab.
The `filesRead` and `manifestDeps` signals test the session's recorded file state, which also includes files Claude has written or edited and auto-loaded `CLAUDE.md` memory files.
+3 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
Hiding the removal inside command substitution with `$(...)` or backticks, or process substitution with `<(...)`, doesn't skip the check. Claude Code finds a critical-path removal
Hiding the removal inside a subshell with `(...)`, a brace group with `{ ...; }`, command substitution with `$(...)` or backticks, or process substitution with `<(...)`, doesn't sk
+1 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
memory
±changed
+3−1
claude-codechanged
memory
The value must be an absolute path or start with `~/`. When you set it in a project's `.claude/settings.json` or `.claude/settings.local.json`, Claude Code honors it under the same
The value must be an absolute path or start with `~/`.
When you set it in a project's `.claude/settings.json` or `.claude/settings.local.json`, Claude Code honors it under the same [workspace trust rule as hooks in settings files](/doc
+3 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
mcp
±changed
+1−1
claude-codechanged
mcp
* **In an interactive session**: `/mcp` shows the server as pending while Claude Code reconnects. After five failed attempts, Claude Code marks the server as failed, or as needing
* **In an interactive session**: `/mcp` shows the server as pending while Claude Code reconnects. After five failed attempts, Claude Code marks the server as failed, or as needing
+1 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
claude-projects
±changed
+5−1
claude-codechanged
claude-projects
The thread's card in the conversation shows a button for the pull request's next step when there is one, such as **Resolve conflicts**, **Fix CI**, **Address comments**, or **Merge
When a thread has pushed a branch or opened a pull request, its card in the conversation can show a button for the next step:
* **Resolve conflicts**, **Fix CI**, **Address comments**, and **Merge it** send that instruction to the thread as a message from you, so you can prompt the thread yourself instead
* **Review PR** opens the pull request on GitHub.
+5 −1 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
claude-directory
±changed
+19−17
claude-codechanged
claude-directory
| `skills/.trash/`, `plugins/.trash/` | [Skills](/docs/en/skills#how-synced-skills-behav
| Delete | You lose
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------
| `~/.claude/projects/` | Resume, continue, and rewind for
| `~/.claude/history.jsonl` | Up-arrow prompt recall, `Ctrl+R`
+19 −17 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
changelog
±changed
+99−0
claude-codechanged
changelog
<Update label="2.1.275" description="September 17, 2026">
* Added the signed-in account to Claude apps gateway sign-in: when the gateway names it, you confirm it before the credential is saved, and `/status` shows it
* Added a send-now key (ctrl+enter, or ctrl+x ctrl+s) that interrupts the current turn and sends all queued messages at once; sent and queued messages show in gray until the mode
* Added a startup warning when a configured `otelHeadersHelper` fails, so sessions that silently export no telemetry are noticed
+99 −0 lines
Recorded here 17 Sep 2026 23:07 UTC
claude-code
scheduled-tasks
±changed
+31−31
claude-codechanged
scheduled-tasks
| | [Cloud](/docs/en/routines) | [Desktop](/docs/en/desktop-scheduled-tasks) | [`/loop`](/docs/en/scheduled-tasks)
| :------------------------- | :---------------------------------- | :------------------------------------- | :---------------------------------------------------------------------
| Runs on | Cloud, Anthropic-managed by default | Your machine | Your machine
| Requires machine on | No | Yes | Yes
| Requires open session | No | No | Yes
+31 −31 lines
Upstream edited 17 Sep 2026 23:02 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
| "Reached the turn limit" | The thread hit the cap on steps for one message. Send another message with a smal
| "Reached the turn limit" | The thread reached the cap on agentic turns that [`CLAUDE_CODE_MAX_TURNS`](/docs/
+1 −1 lines
Recorded here 17 Sep 2026 21:07 UTC
claude-code
worktrees
±changed
+2−0
claude-codechanged
worktrees
In the stream-json result, [`startup_failure_reason`](/docs/en/agent-sdk/typescript#startup_failure_reason) is `worktree_unverified` for the `could not verify worktree` error and `
+2 −0 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
server-managed-settings
±changed
+3−1
claude-codechanged
server-managed-settings
* **Cross-source lock keys**: a small set of keys, such as the sandbox allowlist locks, [listed on the managed settings page](/docs/en/managed-settings#precedence-within-the-manage
* **Cross-source lock keys**: a small set of keys, such as the sandbox allowlist locks, [listed on the managed settings page](/docs/en/managed-settings#precedence-within-the-manage
When a [`policyHelper`](/docs/en/settings-reference#policyhelper) supplies managed settings, its output is the only source these checks read, apart from [`forceRemoteSettingsRefr
+3 −1 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
mobile
±changed
+9−8
claude-codechanged
mobile
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
The Claude app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude) is a clie
From the app you can start cloud sessions, drive a Claude Code session running on your computer, or message Dispatch a task. The app is the same for all three; they differ in where
From the app you can start cloud sessions, open a project, drive a Claude Code session running on your computer, or message Dispatch a task. The app is the same for each; they diff
| Feature | What you connect to | When to use
+9 −8 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
mcp
±changed
+3−1
claude-codechanged
mcp
If the server later returns a 403 `insufficient_scope` for a tool call, Claude Code re-authenticates with the same pinned scopes. Widen `oauth.scopes` when a tool you need requires
If the server later returns a 403 `insufficient_scope` for a tool call, the call fails with a [`needs additional permissions`](/docs/en/errors#mcp-server-needs-you-to-sign-in-again
If that scope isn't in your pinned `oauth.scopes`, add it, then run `/mcp` and authenticate the server again. Claude Code requests the pinned scopes rather than the scope the serve
+3 −1 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
managed-settings
±changed
+13−3
claude-codechanged
managed-settings
* `allowManagedMcpServersOnly`: a `true` in any admin source turns the MCP allowlist lock on. While the lock is on, the managed `allowedMcpServers` list comes from the highest-rank
If no admin source sets a list, every server that passes the denylist loads, unless [parent settings](#let-an-embedding-host-add-policy) supply a list.
Without the lock, Claude Code reads `allowedMcpServers` from the managed source it applies, so under `"first-wins"` an unselected admin source's list is ignored. Requires Claude
+13 −3 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
managed-mcp
±changed
+16−10
claude-codechanged
managed-mcp
To make the allowlist authoritative, set `allowedMcpServers` and `allowManagedMcpServersOnly: true` together in a [managed settings source](/docs/en/admin-setup#decide-how-settings
To make the allowlist authoritative, set `allowedMcpServers` and `allowManagedMcpServersOnly: true` together in a [managed settings source](/docs/en/admin-setup#decide-how-settings
The lock applies from every admin-controlled managed source, so a lockdown in a deployed file still applies when server-managed settings that don't mention MCP are also in use. Whi
+16 −10 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
hooks
±changed
+6−4
claude-codechanged
hooks
For an [MCP tool](#match-mcp-tools), the input also carries `mcp_server`, an object with the server's `name` and a `source` that says where the server's definition came from. The `
PermissionRequest hooks receive `tool_name` and `tool_input` fields like PreToolUse hooks, but without `tool_use_id`. An optional `permission_suggestions` array contains the [permi
PermissionRequest hooks receive `tool_name` and `tool_input` fields like PreToolUse hooks, but without `tool_use_id`. For an MCP tool, they also receive the [`mcp_server`](#pretool
`PostToolUse` hooks fire after a tool has already executed successfully. The input includes both `tool_input`, the arguments sent to the tool, and `tool_response`, the result it re
+6 −4 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
errors
±changed
+25−4
claude-codechanged
errors
| `MCP server "<name>" needs additional permissions (scope: "<scope>") — run /mcp to re-authenticate`
A remote [MCP server](/docs/en/mcp) rejected the credential on a tool call mid-session, usually because a sign-in or token expired. The tool call fails, and `/mcp` marks the server
A remote [MCP server](/docs/en/mcp) rejected the credential on a tool call mid-session, usually because a sign-in or token expired or because the token lacks a permission the tool
Before v2.1.273, all three cases showed `MCP server "<name>" requires re-authorization (token expired)`.
Before v2.1.273, the expired sign-in, `headersHelper`, and `Authorization` header cases all showed `MCP server "<name>" requires re-authorization (token expired)`.
+25 −4 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
env-vars
±changed
+4−1
claude-codechanged
env-vars
| `CLAUDE_CODE_AUTO_MODE_SERVER` | On Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, set to `1` to have the platform's server-side c
| `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` | How long in milliseconds the first turn of a [non-interactive](/docs/en/headless) session waits for MCP servers that are
| `CLAUDE_CODE_STARTUP_FAILURE_RESULTS` | Set to `1` to have a session started with `--output-format stream-json` write a [result message naming why Claude Code r
| `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
+4 −1 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
claude-projects
±changed
+3−3
claude-codechanged
claude-projects
A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task. Each thread is a
A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task. Each thread is a
You create and use projects at [claude.ai/code](https://claude.ai/code) or in the Code tab of the desktop app. There are two ways to start one:
You create and use projects at [claude.ai/code](https://claude.ai/code), in the Code tab of the desktop app, or in the Claude mobile app for [iOS](https://apps.apple.com/us/app/cla
* Projects are available at claude.ai/code and in the desktop app, not in the terminal CLI or through Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. The CLI's
+3 −3 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
claude-apps-gateway
±changed
+13−5
claude-codechanged
claude-apps-gateway
Setting one lock doesn't restrict the others; each key is documented in the [settings reference](/docs/en/settings-reference#all-settings). From an admin source below the winner, t
Each lock makes Claude Code ignore the developer's own entries for that setting, so include your organization's allowlists next to the locks. Locking network domains with an empty
Setting one lock doesn't restrict the others; each key is documented in the [settings reference](/docs/en/settings-reference#all-settings).
+13 −5 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
agent-sdk/typescript
±changed
+94−2
claude-codechanged
agent-sdk/typescript
mcpServer?: { name: string; source: string };
| `mcpServer` | `{ name: string; source: string }` | For an `mcp__*` tool, the MCP server that serves it and where that server's definition came from, with the fields
startup_failure_reason?: SDKStartupFailureReason;
* `startup_failure_reason`: why Claude Code refused to start, on the `error_during_execution` result it writes before exiting on a known startup failure. See [`startup_failure_reas
+94 −2 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
agent-sdk/skills
±changed
+4−0
claude-codechanged
agent-sdk/skills
A `/<name>` that matches neither a command in the session nor a built-in Claude Code command doesn't fail the query. Claude Code sends the prompt to Claude as an ordinary message,
A `/<name>` that matches a built-in Claude Code command that isn't available in the session, such as `/theme`, returns `/theme isn't available in this environment.` as the result w
+4 −0 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
agent-sdk/mcp
±changed
+12−1
claude-codechanged
agent-sdk/mcp
Claude Code registers the servers you pass in `options.mcpServers` at startup and emits the [init message](#error-handling) once the first-turn wait, if any, resolves. Without `opt
Claude Code registers the servers you pass in `options.mcpServers` at startup and emits the [init message](#error-handling) once the first-turn wait, if any, resolves. Whether each
Servers loaded from [settings files](#from-a-config-file) such as `.mcp.json` or from plugins commonly show `pending` in the init message. When `options.mcpServers` holds a stdio,
+12 −1 lines
Recorded here 17 Sep 2026 20:37 UTC
claude-code
errors
±changed
+199−27
claude-codechanged
errors
| `Claude login not accepted · Run /login, then try again`
| `MCP server "<name>" needs you to sign in again (run /mcp to re-authenticate)`
| `rejected the credential from its headersHelper` / `rejected the Authorization header in its config`
| `MCP server "<name>" requires re-authorization (token expired)`
| `Google Cloud credentials expired or invalid`
+199 −27 lines
Recorded here 17 Sep 2026 20:07 UTC
claude-code
claude-projects
±changed
+1−5
claude-codechanged
claude-projects
<Note>
[Projects in claude.ai chat and Cowork](https://support.claude.com/en/articles/9517075-what-are-projects), which group conversations and reference files, are a separate feature f
</Note>
* **Projects in claude.ai chat and Cowork**: a [separate feature](https://support.claude.com/en/articles/9517075-what-are-projects) that groups conversations and reference files, w
+1 −5 lines
Recorded here 17 Sep 2026 18:37 UTC
claude-code
web-quickstart
±changed
+4−4
claude-codechanged
web-quickstart
With this connection, a session can clone any public repository, but can work in a private repository only when the Claude GitHub App is installed on it. [Install the App](http
If onboarding prompts you to install the App at this point and you'd rather do it later, click **Skip**.
With this connection, a session can clone any public repository, but can work in a private repository only when the Claude GitHub App is installed on it. [Install the Claude Gi
+4 −4 lines
Recorded here 17 Sep 2026 17:37 UTC
claude-code
claude-projects
±changed
+12−11
claude-codechanged
claude-projects
Projects are in public beta on Pro and Max plans and rolling out gradually, and aren't available on Team or Enterprise plans yet. If **Projects** doesn't appear in the sidebar at
Projects are in public beta on Pro and Max plans and rolling out gradually, starting with accounts that have used [cloud sessions](/docs/en/claude-code-on-the-web) and don't have
In any of them you can send a batch of tasks, walk away, and find the threads that need you under [**Waiting on you**](#see-what-needs-you-in-overview) when you're back, or ask Cla
In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, walk away, and find the threads that need you under [**Waiting on you**](#see-what
2. Send one small piece of the real work, or start one of the threads Claude suggested, and open the thread when it finishes to see how it reports back and what it did on its branc
+12 −11 lines
Recorded here 17 Sep 2026 17:37 UTC
claude-code
claude-code-on-the-web
±changed
+6−6
claude-codechanged
claude-code-on-the-web
| Method | How you connect | Repositories sessions can reach
| :--------------- | :----------------------------------------------------------------------------------------- | :-----------------------------------------------------------------
| **GitHub App** | Authorize the Claude GitHub App during [web onboarding](/docs/en/web-quickstart) | Any public repository, and private repositories that the Clau
| **`/web-setup`** | Run `/web-setup` in your terminal to send your local `gh` CLI token to your Claude account | Any repository your `gh` token can access, whether or not the App
| Method | How you connect | Repositories sessions can reach
+6 −6 lines
Recorded here 17 Sep 2026 17:37 UTC
claude-code
web-quickstart
±changed
+1−1
claude-codechanged
web-quickstart
When you run `/web-setup`, Claude Code reads the token that `gh auth token` prints, asks you to confirm, and sends the token to Anthropic. Anthropic stores it encrypted with your c
When you run `/web-setup`, Claude Code reads the token that `gh auth token` prints, asks you to confirm, and sends the token to Anthropic. Anthropic stores it encrypted with your c
+1 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
routines
±changed
+2−1
claude-codechanged
routines
Connectors are the [claude.ai integrations](/docs/en/mcp#use-mcp-servers-from-claude-ai) on your account. MCP servers you added locally in the CLI with `claude mcp add` are stored
Connectors are the [claude.ai integrations](/docs/en/mcp#use-mcp-servers-from-claude-ai) on your account. MCP servers you added locally in the CLI with `claude mcp add` are stored
* [Projects](/docs/en/claude-projects): ongoing work Claude coordinates across parallel cloud sessions; routines created from a project appear on its **Routines** tab
+2 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
platforms
±changed
+1−0
claude-codechanged
platforms
* [Projects](/docs/en/claude-projects): one conversation where Claude coordinates many cloud sessions for a body of work and reports back
+1 −0 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
overview
±changed
+1−1
claude-codechanged
overview
Run Claude Code in your browser with no local setup. Kick off long-running tasks and check back when they're done, work on repos you don't have locally, or run multiple tasks i
Run Claude Code in your browser with no local setup. Kick off long-running tasks and check back when they're done, work on repos you don't have locally, or run multiple tasks i
+1 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
mcp-quickstart
±changed
+1−1
claude-codechanged
mcp-quickstart
* **Cloud sessions**: commit a `.mcp.json` to your repository. See [Edit .mcp.json directly](#edit-mcp-json-directly).
* **Cloud sessions**: commit a `.mcp.json` to your repository; a session with one repository loads it. See [Edit .mcp.json directly](#edit-mcp-json-directly) and [What carries over
+1 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
hooks
±changed
+1−1
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 and from your organization's server-managed settin
[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
+1 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
desktop
±changed
+2−2
claude-codechanged
desktop
The desktop app sends an OS notification when a Code session finishes a task and you aren't currently viewing that session.
The desktop app sends an OS notification when a Code session finishes a task and you aren't currently viewing that session. For sessions that belong to a [project](/docs/en/claude-
See [Use Claude Code in the cloud](/docs/en/claude-code-on-the-web) for more on how cloud sessions work.
See [Use Claude Code in the cloud](/docs/en/claude-code-on-the-web) for more on how cloud sessions work. When one body of work needs many cloud sessions, select **Projects** in the
+2 −2 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
cloud-environments
±changed
+5−4
claude-codechanged
cloud-environments
* In the Desktop app, the mobile app, and at claude.ai/code, sessions use the environment shown in the [selector](#configure-your-environment). An [organization default](#organizat
* In the Desktop app, the mobile app, and at claude.ai/code, sessions you start yourself use the environment shown in the [selector](#configure-your-environment). An [organization
| Your repo's `.claude/settings.json` hooks
| Your repo's `.mcp.json` MCP servers
| Your repo's `.claude/settings.json` hooks and permission rules
+5 −4 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
claude-projects
+new page
+465−0
claude-codenew page
claude-projects
No line of the body moved in this read.
+465 −0 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
claude-code-on-the-web
±changed
+4−1
claude-codechanged
claude-code-on-the-web
A session in your terminal, your IDE, or the Desktop app with **Local** selected runs on your own machine instead. To steer one of those local sessions from your phone or browser,
To have Claude start and keep track of many cloud sessions for one body of work, use a [project](/docs/en/claude-projects). A session in your terminal, your IDE, or the Desktop app
Threads in a [project](/docs/en/claude-projects) need the App installed on each repository they clone, whichever method you connected with. See [Set up GitHub access](/docs/en/clau
* [Projects](/docs/en/claude-projects): one conversation where Claude coordinates parallel cloud sessions on your repositories and reports back
+4 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
agents
±changed
+9−8
claude-codechanged
agents
> Compare the ways Claude Code can take on multiple tasks at once: subagents, agent view, agent teams, and dynamic workflows.
> Compare the ways Claude Code can take on multiple tasks at once: subagents, agent view, agent teams, dynamic workflows, and projects.
[Subagents](/docs/en/sub-agents), [agent view](/docs/en/agent-view), [agent teams](/docs/en/agent-teams), and [dynamic workflows](/docs/en/workflows) each parallelize work in a dif
Claude Code has five ways to work on several tasks at once: [subagents](/docs/en/sub-agents), [agent view](/docs/en/agent-view), [agent teams](/docs/en/agent-teams), [dynamic workf
| Approach | What it gives you
+9 −8 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
agent-view
±changed
+2−1
claude-codechanged
agent-view
To compare agent view with subagents, agent teams, and worktrees, see [Run agents in parallel](/docs/en/agents).
To compare agent view with subagents, agent teams, and worktrees, see [Run agents in parallel](/docs/en/agents). Agent view runs sessions on your machine and you dispatch each one;
* [Projects](/docs/en/claude-projects): have Claude coordinate parallel cloud sessions from one conversation and tell you which need you
+2 −1 lines
Recorded here 17 Sep 2026 17:07 UTC
claude-code
mcp-quickstart
±changed
+14−14
claude-codechanged
mcp-quickstart
| Status | Meaning
| :------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------
| `✔ Connected` | Ready to use. This is what you should see for `claude-code-docs`
| `! Connected · tools fetch failed` | The server connected but couldn't list its tools. Run `claude mcp get <name>` for the error detail
| `! Needs authentication` | The server is reachable but needs a browser sign-in, or a token passed with `--header`. See [Connect a server that requir
+14 −14 lines
Upstream edited 17 Sep 2026 17:01 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
worktrees
±changed
+3−2
claude-codechanged
worktrees
* Claude Code can't determine which filter drivers the repository config defines, in any of the [three cases that also block worktree creation](#git-lfs-content-is-missing-from-a-w
* One of the [four cases that also block worktree creation](#git-lfs-content-is-missing-from-a-worktree-claude-code-created) applies: Claude Code can't determine which filter drive
In three rare cases, Claude Code can't tell which filter drivers the repository's config defines, and creates no worktree at all. Match the error to its fix:
In four rare cases, Claude Code creates no worktree at all: it can't tell which filter drivers the repository's config defines, or it finds a setting there it can't switch off. Mat
* **`Git was not run: the repository's own git config sets <key>`**: the message names a key that points Git LFS at a program to run, such as `lfs.customtransfer.<name>.path` or `l
+3 −2 lines
Recorded here 17 Sep 2026 04:07 UTC
claude-code
settings-reference
±changed
+3−1
claude-codechanged
settings-reference
For `github` and `git` sources, set `"skipLfs": true` inside the `source` object, alongside `repo` or `url`, to skip Git LFS downloads when Claude Code clones or updates the market
For `github` and `git` sources, Claude Code never downloads [Git LFS](https://git-lfs.com) content when it clones the marketplace repository to add or update it. LFS-tracked files
The `skipLfs` field inside the `source` object is accepted and has no effect. Before v2.1.274, Claude Code downloaded LFS content unless you set `"skipLfs": true`.
+3 −1 lines
Recorded here 17 Sep 2026 04:07 UTC
claude-code
plugin-marketplaces
±changed
+28−18
claude-codechanged
plugin-marketplaces
When users add a marketplace hosted in a git repository, or install a git-based plugin it lists, Claude Code clones that marketplace or plugin repository onto their machine. The cl
By default, the background refresh disables git credential helpers for its `git pull`, so the pull can't authenticate to private repositories over HTTPS even when a helper is confi
By default, the background refresh disables git credential helpers when it checks the marketplace's remote for new commits, so the check can't authenticate to private repositories
+28 −18 lines
Recorded here 17 Sep 2026 04:07 UTC
claude-code
monitoring-usage
±changed
+9−1
claude-codechanged
monitoring-usage
* `request_body_id`: UUID that identifies this attempt's request body. The [`api_response_body` event](#api-response-body-event) for the attempt that succeeds carries the same valu
In file mode (`OTEL_LOG_RAW_API_BODIES=file:<dir>`), Claude Code also appends one JSON line to `<dir>/index.jsonl` for each successful response, with the fields `timestamp`, `sessi
* `request_body_id`: The `request_body_id` of the [`api_request_body` event](#api-request-body-event) that this response answers. Requires Claude Code v2.1.274 or later
* `message.id`: Message ID the API assigned to the response, the `id` field of the response body. Requires Claude Code v2.1.274 or later
+9 −1 lines
Recorded here 17 Sep 2026 04:07 UTC
claude-code
mcp
±changed
+9−7
claude-codechanged
mcp
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:
* On Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry, unless a host platform that embeds Claude Code sets [`CLAUDE_CODE_PROVIDER_MANAGED
* Signed in through a [Claude apps gateway](/docs/en/claude-apps-gateway)
* With [feature-flag fetching off](/docs/en/env-vars#features-that-need-feature-flag-fetching)
+9 −7 lines
Recorded here 17 Sep 2026 04:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.