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
28 Aug 2026
94 pages
+2083 −1399 lines
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
| [`allowAllClaudeAiMcps`](/docs/en/settings-reference#allowallclaudeaimcps) | Load the claude.ai connectors alongside a deployed `m
| [`allowAllClaudeAiMcps`](/docs/en/settings-reference#allowallclaudeaimcps) | Load the claude.ai connectors Claude Code fetches its
+1 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
managed-mcp
±changed
+34−32
claude-codechanged
managed-mcp
These restrictions cover the servers Claude Code loads itself, including the connectors it fetches from claude.ai. Connectors the desktop app delivers to its local and SSH sessions
| Pattern | What it does | Configure
| :---------------------- | :-------------------------------------------------------------------------------------------------------------------- | :-------------------------------
| **Disable MCP** | No servers load, apart from the [VS Code extension's own in-process server](#exclusive-control-with-managed-mcp-json) | `managed-mcp.json` with an empty
+34 −32 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
hooks-guide
±changed
+4−4
claude-codechanged
hooks-guide
| `elicitation_complete` | An MCP elicitation form is submitted or dismissed
| `elicitation_complete` | An MCP server reports that a [URL-mode elicitation](/docs/en/hooks#elicitation-input) is complete
* **Exit 2**: Claude Code blocks the action. Write a reason to stderr. Where it lands depends on the event: some events feed it to Claude as feedback so it can adjust, others show
* **Exit 2**: Claude Code blocks the action. Write a reason to stderr. Where it lands depends on the event: some events feed it to Claude as feedback so it can adjust, others show
* `"allow"`: skip the interactive permission prompt. Deny and ask rules, including enterprise managed deny lists, still apply, as do prompts for connector tools [your organization
+4 −4 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
hooks
±changed
+39−58
claude-codechanged
hooks
* Claude Code also disables plugins with a [`command` source](/docs/en/plugin-marketplaces#command-sources), including plugins force-enabled in managed settings `enabledPlugins`, u
* Claude Code also disables plugins with a [`command` source](/docs/en/plugin-marketplaces#command-sources), including plugins force-enabled in managed settings `enabledPlugins`, u
| Field | Required | Description
| :-------------- | :------- | :----------------------------------------------------------------------------------------------------------------------------------------------------
| `type` | yes | `"command"`, `"http"`, `"mcp_tool"`, `"prompt"`, or `"agent"`
+39 −58 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
The session reached the API client without any credential. This appears in [background sessions](/docs/en/agent-view), cloud sessions, and Agent SDK contexts where the interactive
The session reached the API client without any credential. [Background sessions](/docs/en/agent-view) and cloud sessions show this message when the worker starts without a credenti
+1 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to disable [claude.ai MCP servers](/docs/en/mcp#use-mcp-servers-from-claude-ai) in Claude Code. Enabled b
| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to stop Claude Code from fetching [claude.ai MCP servers](/docs/en/mcp#use-mcp-servers-from-claude-ai). E
+1 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
desktop-scheduled-tasks
±changed
+1−1
claude-codechanged
desktop-scheduled-tasks
Connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools) and MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approv
MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approval-for-a-specific-tool) prompt on every call and don't offer an always-allow option. Runs that call these to
+1 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
desktop
±changed
+2−0
claude-codechanged
desktop
In local and SSH sessions, the desktop app delivers each user's connected claude.ai connectors to Claude Code directly. No MCP setting or `managed-mcp.json` reaches those connector
+2 −0 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
deep-links
±changed
+5−1
claude-codechanged
deep-links
## How it works
## How deep links work
On success, a new terminal window opens with Claude Code running and the prompt pre-filled.
+5 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
agent-sdk/quickstart
±changed
+1−1
claude-codechanged
agent-sdk/quickstart
If you see "API key not found", make sure you've set the `ANTHROPIC_API_KEY` environment variable in the shell where you run your agent. The SDK doesn't load `.env` files automat
If you see an authentication error such as `Not logged in` or `Invalid API key`, make sure you've set the `ANTHROPIC_API_KEY` environment variable in the shell where you run your
+1 −1 lines
Recorded here 28 Aug 2026 02:37 UTC
claude-code
worktrees
±changed
+2−2
claude-codechanged
worktrees
While an agent is running, Claude runs `git worktree lock` on its worktree so that concurrent cleanup cannot remove it. The lock is released when the agent finishes.
While an agent is running, Claude Code holds a `git worktree lock` on its worktree so that concurrent cleanup can't remove it, and releases the lock when the agent finishes. Claude
To clean up a worktree that the sweep keeps, run `git worktree remove`, adding `--force` if the worktree has uncommitted changes or untracked files.
To clean up a worktree that the sweep keeps, run `git worktree remove`, adding `--force` if the worktree has uncommitted changes or untracked files. If git refuses because the work
+2 −2 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
Make managed settings the only source of `allow`, `ask`, and `deny` permission rules. Claude Code then ignores rules in user, project, local, and `--settings` files, ignores `--all
Make managed settings the only source of `allow`, `ask`, and `deny` permission rules. Claude Code then ignores rules in user, project, local, and `--settings` files, ignores `--all
* `true`: managed settings are the only source of `allow`, `ask`, and `deny` rules; Claude Code ignores rules from other files and `--allowedTools`, hides always-allow choices, a
* `true`: managed settings are the only source of `allow`, `ask`, and `deny` rules; Claude Code ignores rules from other files and `--allowedTools`, drops the `allow` rules and `
+2 −2 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
server-managed-settings
±changed
+2−0
claude-codechanged
server-managed-settings
In a [Cowork](https://claude.com/docs/cowork/overview) session in the Claude Desktop app, Claude Code doesn't fetch server-managed settings from the claude.ai admin console, even w
+2 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
scheduled-tasks
±changed
+1−0
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
+1 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
To confirm which TTL your cache writes used, run `claude -p "hello" --output-format json` and read `usage.cache_creation` in the result. Claude Code reports one-hour cache writes u
To confirm which TTL your main conversation's cache writes used, run `claude -p "hello" --output-format json` and read `usage.cache_creation` in the result. Claude Code reports one
+1 −1 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
plugins-reference
±changed
+2−2
claude-codechanged
plugins-reference
Enable a disabled plugin. If the plugin declares [dependencies](/docs/en/plugin-dependencies), Claude Code enables them transitively at the same scope, and the command fails when a
Enable a disabled plugin. When the target is installed from a marketplace and declares [dependencies](/docs/en/plugin-dependencies), Claude Code enables them transitively at the sa
Disable a plugin without uninstalling it. Fails when another enabled plugin [depends on](/docs/en/plugin-dependencies#enable-or-disable-a-plugin-with-dependencies) the target. The
Disable a plugin without uninstalling it. When the target is installed from a marketplace, the command fails if another enabled plugin [depends on](/docs/en/plugin-dependencies#ena
+2 −2 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
plugins
±changed
+2−0
claude-codechanged
plugins
To test a plugin together with a plugin it depends on, see [Test a plugin and its dependency locally](/docs/en/plugin-dependencies#test-a-plugin-and-its-dependency-locally).
+2 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
plugin-dependencies
±changed
+17−0
claude-codechanged
plugin-dependencies
## Test a plugin and its dependency locally
If you're developing a plugin and the plugin it depends on at the same time, load both with `--plugin-dir`:
```bash theme={null}
+17 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
permissions
±changed
+2−0
claude-codechanged
permissions
In a [Cowork](https://claude.com/docs/cowork/overview) session in the Claude Desktop app, Claude runs shell commands through Cowork's `mcp__workspace__bash` tool rather than the bu
+2 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
* Cowork, the agentic-work tab in the Claude Desktop app, is not a Claude Code surface and does not receive server-managed settings by design. A managed settings file applies to Co
* Cowork, the agentic-work tab in the Claude Desktop app, runs its sessions on Claude Code but, by design, does not receive server-managed settings from the claude.ai admin console
+1 −1 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
managed-settings
±changed
+27−1
claude-codechanged
managed-settings
* **Surfaces**: every surface that runs Claude Code on the machine reads these sources: the terminal, the VS Code and JetBrains extensions, the desktop app, and [Agent SDK](/docs/e
* **Surfaces**: on the developer's machine, the terminal, the VS Code and JetBrains extensions, the desktop app's Code tab, and [Agent SDK](/docs/en/agent-sdk/typescript) sessions
* **Cowork sessions**: [Cowork](https://claude.com/docs/cowork/overview) in the Claude Desktop app runs its sessions on Claude Code. In a Cowork session, Claude Code never fetches
* **On the user's machine**: by default, Claude Code in a Cowork session reads the MDM or OS-level policy and the managed settings file on that device, so deploy policy there.
+27 −1 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
errors
±changed
+68−0
claude-codechanged
errors
| `Can't open — this session is running in another terminal`
| `This conversation is already open in another running Claude session`
| `This session's saved conversation is no longer on disk`
| `kept <id> — worktree has commits that are not pushed anywhere`
<h3 id="this-session-is-running-in-another-terminal">
+68 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
desktop
±changed
+1−0
claude-codechanged
desktop
* **[Cowork](https://claude.com/docs/cowork/overview) sessions**: in a Cowork session on this machine, Claude Code never fetches admin-console settings, even when the user signs in
+1 −0 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
agent-view
±changed
+37−12
claude-codechanged
agent-view
| Stopped | Grey | The session was stopped with `Ctrl+X` or `claude stop`, or [its process was ended from outside Claude Code](#the-supervisor-process)
| Stopped | Grey | You stopped the session with `Ctrl+X` or `claude stop`, [its process was ended from outside Claude Code](#the-supervisor-process), or [it ended whil
When a [`PermissionRequest`](/docs/en/hooks#permissionrequest) or [`PreToolUse`](/docs/en/hooks#pretooluse) hook returns output Claude Code can't validate for the call the session
| `Shift+Enter` | Dispatch and attach immediately
+37 −12 lines
Recorded here 28 Aug 2026 02:07 UTC
claude-code
ultrareview
±changed
+4−0
claude-codechanged
ultrareview
For repositories on `github.com`, the sandbox clones with the GitHub account connected to your Claude account, so the account must be able to read the PR's repository. Claude Code
Run [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal) to connect your GitHub CLI login to your Claude account.
+4 −0 lines
Recorded here 28 Aug 2026 01:37 UTC
claude-code
tools-reference
±changed
+19−3
claude-codechanged
tools-reference
On Linux and WSL, set [`CLAUDE_CODE_TOOL_MEMORY_LIMIT`](/docs/en/env-vars#variables) to a size such as `4G` to cap the memory that Bash and PowerShell tool commands can use, so one
On Linux and WSL, set [`CLAUDE_CODE_TOOL_MEMORY_LIMIT`](/docs/en/env-vars#variables) to a size such as `4G` to cap the memory that Bash, PowerShell, and [Monitor](#monitor-tool) to
* Claude Code counts all of a session's Bash and PowerShell commands against the one cap, not each command on its own.
* Claude Code counts all of a session's Bash, PowerShell, and Monitor commands against the one cap, not each command on its own.
* After a Bash or PowerShell tool command has turned the cap on, or has turned it off because of an off value or a failed cgroup setup, Claude Code holds that result until you rela
+19 −3 lines
Recorded here 28 Aug 2026 01:37 UTC
claude-code
errors
±changed
+40−0
claude-codechanged
errors
| `Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected`
| `Your connected GitHub account can't see <owner>/<repo>`
<h3 id="no-github-account-is-connected-to-your-claude-account">
No GitHub account is connected to your Claude account
</h3>
+40 −0 lines
Recorded here 28 Aug 2026 01:37 UTC
claude-code
env-vars
±changed
+2−1
claude-codechanged
env-vars
| `CLAUDE_CODE_TOOL_MEMORY_LIMIT` | On Linux and WSL, set to a size such as `4G` to [cap the memory that Bash and PowerShell tool commands can use](/docs/en
| `CLAUDE_CODE_TOOL_MEMORY_CGROUP_EXCLUDE` | On Linux and WSL, set to a comma-separated list of the kinds of processes Claude Code [excludes from the tool memory cap
| `CLAUDE_CODE_TOOL_MEMORY_LIMIT` | On Linux and WSL, set to a size such as `4G` to [cap the memory that Bash and PowerShell tool commands can use](/docs/en
+2 −1 lines
Recorded here 28 Aug 2026 01:37 UTC
claude-code
changelog
±changed
+4−0
claude-codechanged
changelog
<Update label="2.1.250" description="August 28, 2026">
* Bug fixes and reliability improvements
</Update>
+4 −0 lines
Recorded here 28 Aug 2026 01:07 UTC
claude-code
worktrees
±changed
+4−3
claude-codechanged
worktrees
Worktrees are one of several ways to run Claude in parallel. They isolate file edits, while [subagents](/docs/en/sub-agents) and [agent teams](/docs/en/agent-teams) coordinate the
Worktrees are one of several ways to run Claude in parallel. They isolate file edits. [Subagents](/docs/en/sub-agents) split work up inside one session, and [cross-session messagin
* **Permission approvals**: choosing "Yes, and don't ask again" for a Bash command in a worktree session saves the rule to the main checkout's `.claude/settings.local.json`, so it
* **Permission approvals**: choosing "Yes, and don't ask again" for a Bash command in a worktree session saves the rule to the main checkout's `.claude/settings.local.json`, so it
Worktrees handle file isolation. The related pages below cover delegating work into those isolated checkouts and switching between the sessions you create:
+4 −3 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
For tasks that need sustained parallelism or exceed your context window, [agent teams](/docs/en/agent-teams) give each worker its own independent context.
For work that needs to keep running in parallel or won't fit in one context window, run it in [separate sessions](/docs/en/agents) and let Claude [pass findings between them](/docs
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
Project skills load from `.claude/skills/` in the directory where you start Claude Code and in every parent directory up to the repository root. Starting Claude in a subdirectory s
Project skills load from `.claude/skills/` in the directory where you start Claude Code and in every parent directory up to the repository root. Starting Claude in a subdirectory s
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
settings-reference
±changed
+1−0
claude-codechanged
settings-reference
* After you [move the session with `/cd`](/docs/en/permissions#move-the-session-to-another-directory) on v2.1.246 or later: the new directory's project and local `env` values, on t
+1 −0 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
prompt-caching
±changed
+5−2
claude-codechanged
prompt-caching
Claude Code applies a plugin change when you run [`/reload-plugins`](/docs/en/discover-plugins#apply-plugin-changes-without-restarting) or start a new session. You pay the cost, wh
Claude Code applies a plugin change when you run [`/reload-plugins`](/docs/en/discover-plugins#apply-plugin-changes-without-restarting) or start a new session. You pay the cost, wh
* When you [move the session with `/cd`](/docs/en/permissions#move-the-session-to-another-directory) on v2.1.246 or later, Claude Code applies the plugins the new directory's setti
The one-hour TTL isn't available through the [Claude apps gateway](/docs/en/claude-apps-gateway#availability-and-limitations). On Amazon Bedrock, prompt caching support, minimum ca
To confirm which TTL your cache writes used, run `claude -p "hello" --output-format json` and read `usage.cache_creation` in the result. Claude Code reports one-hour cache writes u
+5 −2 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
plugins-reference
±changed
+1−1
claude-codechanged
plugins-reference
Project-scope `@skills-dir` plugins load only from the `.claude/skills/` of the directory where you start Claude Code. They don't [walk up to the repository root](/docs/en/skills
Project-scope `@skills-dir` plugins load only from the `.claude/skills/` of the session's [primary working directory](/docs/en/permissions#working-directories). They don't [walk
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
permissions
±changed
+34−19
claude-codechanged
permissions
When you choose "Yes, and don't ask again" and the approval saves permanently, such as for a Bash command or a WebFetch domain, Claude Code saves the rule to `.claude/settings.loca
When you choose "Yes, and don't ask again" and the approval saves permanently, such as for a Bash command or a WebFetch domain, Claude Code saves the rule to `.claude/settings.loca
| Pattern | Meaning | Example | Matches |
| ------------------ | ------------------------------------ | -------------------------------- | ------------------------------------------------ |
| `//path` | Absolute path from filesystem root | `Read(//Users/alice/secrets/**)` | `/Users/alice/secrets/**` |
+34 −19 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
mcp
±changed
+5−3
claude-codechanged
mcp
* When you [move the session with `/cd`](/docs/en/permissions#move-the-session-to-another-directory) on v2.1.246 or later, Claude Code connects the servers of plugins the new dir
Claude Code picks the `headersHelper` command's working directory from the configuration that declares the server. A `cd` later in the session doesn't move it. Each row below gives
Claude Code picks the `headersHelper` command's working directory from the configuration that declares the server. A `cd` that Claude runs in Bash doesn't move it, and [`/cd`](/doc
| A project `.mcp.json`, a [local-scope](#local-scope) server, an agent file in your project, a server from the SDK's `mcpServers` option or `setMcpServers()` method, or [`--mcp-co
| A project `.mcp.json` or a [local-scope](#local-scope) server
+5 −3 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
large-codebases
±changed
+4−4
claude-codechanged
large-codebases
Project settings in `.claude/settings.json` load only from your starting directory and are not inherited from parent directories the way CLAUDE.md files are: a `.claude/settings.js
Project settings in `.claude/settings.json` aren't inherited from parent directories the way CLAUDE.md files are. For which directory's `.claude/settings.json` a session reads, see
* **Everyone working in the repository**: commit the rules to `.claude/settings.json`. Like other project settings on this page, that file loads only from your starting directory,
* **Yourself only**: use `.claude/settings.local.json` at the repository root, which loads in every CLI session inside the repository regardless of starting directory, except in th
* **Everyone working in the repository**: commit the rules to `.claude/settings.json`, at the repository root if you start Claude there, or in each package's `.claude/` if you star
+4 −4 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A specialized AI assistant that runs in its own context window with a custom system prompt, specific tool access, and independent permissions. It works on a delegated task and retu
A specialized AI assistant that runs in its own context window with a custom system prompt, specific tool access, and independent permissions. It works on a delegated task and retu
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
When the same variable is set in both your shell and a settings file `env` block, the settings file value applies. Claude Code writes each `env` entry into the process environment
When the same variable is set in both your shell and a settings file `env` block, the settings file value applies. Claude Code writes each `env` entry into the process environment,
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/cd <path>` | Move this session to a new working directory, keeping the conversation and its pro
| `/cd <path>` | Move this session to a new working directory, keeping the conversation. Type a par
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
best-practices
±changed
+2−1
claude-codechanged
best-practices
Pick the parallel approach that fits how much coordination you want to do yourself:
Pick the parallel approach that fits how much coordination you want to do yourself, and add messaging when the sessions need to pass findings between them:
* [Cross-session messaging](/docs/en/cross-session-messaging): let the sessions you run yourself pass findings to each other
+2 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* **Do the workers need to talk to each other?** Subagents report results back to the conversation that spawned them, and agent view sessions report only to you, though separate se
* **Do the workers need to talk to each other?** Claude can pass findings with [cross-session messaging](/docs/en/cross-session-messaging) between sessions you run yourself, includ
+1 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
agent-view
±changed
+2−1
claude-codechanged
agent-view
For other ways to run Claude in parallel, see:
For other ways to run Claude in parallel, and for passing findings between the sessions you run, see:
* [Cross-session messaging](/docs/en/cross-session-messaging): have your sessions pass findings to each other
+2 −1 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
agent-teams
±changed
+4−3
claude-codechanged
agent-teams
Agent teams let you coordinate multiple Claude Code instances working together. One session acts as the team lead, coordinating work, assigning tasks, and synthesizing results. Tea
Unlike [subagents](/docs/en/sub-agents), which run within a single session, you can also interact with individual teammates directly without going through the lead.
Agent teams let you coordinate multiple Claude Code instances working together. One session acts as the team lead, coordinating work, assigning tasks, and synthesizing results. Tea
+4 −3 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+0−4
claude-codechanged
agent-sdk/claude-code-features
<Tip>
**Subagents versus agent teams:** Subagents are ephemeral and isolated: fresh conversation, one task, summary returned to parent. Agent teams coordinate multiple independent Clau
</Tip>
+0 −4 lines
Recorded here 28 Aug 2026 00:37 UTC
claude-code
workflows
±changed
+12−14
claude-codechanged
workflows
If you stop a run, you can resume it. Agents that already completed usually return their cached results, and the rest run live.
Two rules decide which results survive:
* An agent that was still running when you stopped isn't saved, so it starts over on resume.
+12 −14 lines
Recorded here 28 Aug 2026 00:07 UTC
claude-code
mcp
±changed
+13−0
claude-codechanged
mcp
## Tools with invalid input schemas
The Claude API checks every tool's input schema in a request and rejects the whole request when any one schema fails, so a single MCP tool with a malformed schema would make every
* Top-level property names must be 1 to 64 characters long and use only ASCII letters and digits, `_`, `.`, and `-`
+13 −0 lines
Recorded here 28 Aug 2026 00:07 UTC
claude-code
errors
±changed
+19−0
claude-codechanged
errors
| `API Error: 400 ... tools.N.custom.input_schema: JSON schema is invalid`
### Tool input schema is invalid
A tool in the request declared an `input_schema` that fails the API's JSON Schema validation, so the API rejected the whole request. The number after `tools.` is the failing tool's
+19 −0 lines
Recorded here 28 Aug 2026 00:07 UTC
claude-code
cross-session-messaging
±changed
+6−2
claude-codechanged
cross-session-messaging
A message is a piece of text one Claude writes to another, never conversation history or files. To move a whole conversation or its context, [resume the session](/docs/en/sessions#
A message is a piece of text one Claude writes to another, never the sender's conversation history or files. To move a whole conversation or its context, [resume the session](/docs
When a message that starts a new turn mentions a file as an `@` immediately followed by its path, Claude Code [attaches that file](/docs/en/common-workflows#reference-files-and-dir
A message that Claude reads during an active turn arrives as plain text with nothing attached, even if it mentions files or MCP resources with `@`.
+6 −2 lines
Recorded here 28 Aug 2026 00:07 UTC
claude-code
agent-view
±changed
+16−8
claude-codechanged
agent-view
If a tool is running when you press `←`, Claude Code waits up to about ten seconds for it to finish before backgrounding, and the response continues in the background session. Pres
The ten-second limit doesn't apply while [subagents](/docs/en/sub-agents) are running. Claude Code keeps waiting so their work carries over, and shows a `Still backgrounding after
If a tool is running when you press `←`, Claude Code waits up to about ten seconds for it to finish before backgrounding, and Claude continues the response in the background sessio
+16 −8 lines
Recorded here 28 Aug 2026 00:07 UTC
27 Aug 2026
50 pages
+785 −217 lines
claude-code
workflows
±changed
+7−3
claude-codechanged
workflows
Claude Code highlights the keyword in your input and Claude writes a workflow script for the task instead of working through it turn by turn. The keyword only chooses how Claude st
Claude Code highlights the keyword in your input and Claude writes a workflow script for the task instead of working through it turn by turn. The keyword only chooses how Claude st
In `claude -p` and the Agent SDK, the workflow runs only when something else allows the Workflow tool call.
In `claude -p` and the Agent SDK, Claude Code never shows this prompt. It runs the Workflow tool call through the same [permission evaluation](/docs/en/agent-sdk/permissions#how-pe
+7 −3 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
sub-agents
±changed
+3−1
claude-codechanged
sub-agents
Those descriptions take up context, so keep them short. When the combined descriptions of your subagents, except the built-in ones, exceed 15,000 tokens, Claude Code shows a [warni
* **Write detailed descriptions:** Claude uses the description to decide when to delegate
* **Write specific descriptions:** Claude uses the description to decide when to delegate
+3 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
skills
±changed
+19−5
claude-codechanged
skills
The `--add-dir` flag and `/add-dir` command [grant file access](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) rather than configuration discovery
Subagents follow the same exception: when you add a directory, Claude Code loads its `.claude/agents/` folder too. It doesn't watch that folder, or the added directory's `.claude/c
The `--add-dir` flag and `/add-dir` command [grant file access](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) rather than configuration discovery
+19 −5 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
settings-reference
±changed
+1−0
claude-codechanged
settings-reference
* [`CLAUDE_CODE_RESTRICTED`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, is ignored from every file.
+1 −0 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
plugins-reference
±changed
+12−0
claude-codechanged
plugins-reference
Claude Code loads a plugin agent even when its frontmatter has no `name` or doesn't parse:
* No `name`: Claude Code names the agent after the file, so `agents/reviewer.md` in a plugin named `my-plugin` loads as `my-plugin:reviewer`
* Frontmatter that doesn't parse: Claude Code names the agent after the file, uses `Agent from my-plugin plugin` as its description, and ignores every field in the file
+12 −0 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
plugin-marketplaces
±changed
+1−1
claude-codechanged
plugin-marketplaces
The allowlist's exact matching doesn't normalize URLs: a trailing slash, `.git` suffix, or `ssh://` versus `https://` form are treated as different values. If your organization's m
The allowlist's exact matching treats URLs that differ only by a trailing slash, a `.git` suffix, or the `ssh://` and `https://` scheme as different values. If your organization's
+1 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
output-styles
±changed
+2−2
claude-codechanged
output-styles
* Claude Code adds each output style's custom instructions to the end of the system prompt.
* All output styles trigger reminders for Claude to adhere to the output style instructions during the conversation.
* Claude Code adds the output style's custom instructions to the system prompt.
* When you [select a style other than Default](#change-your-output-style), Claude Code also reminds Claude of the style during the conversation.
+2 −2 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
`bypassPermissions` only applies if the session was launched with bypass mode already available: `--dangerously-skip-permissions`, `--permission-mode bypassPermissions`, `--allow
`bypassPermissions` only applies if the session was launched with bypass mode already available: `--dangerously-skip-permissions`, `--permission-mode bypassPermissions`, `--allow
+1 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
`setMode` with `bypassPermissions` only takes effect if the session was launched with bypass mode already available: `--dangerously-skip-permissions`, `--permission-mode bypassPe
`setMode` with `bypassPermissions` only takes effect if the session was launched with bypass mode already available: `--dangerously-skip-permissions`, `--permission-mode bypassPe
+1 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
fast-mode
±changed
+1−1
claude-codechanged
fast-mode
* **Team and Enterprise**: your organization pays for your fast mode usage from its usage credits. For where your organization sees that spend, see [Claude for Teams and Enterprise
* **Team and Enterprise**: your organization pays for your fast mode usage from its usage credits. To see your own usage-credits spend, run [`/usage`](/docs/en/costs#check-your-usa
+1 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
errors
±changed
+17−1
claude-codechanged
errors
| `Agent descriptions are over the 15.0k-token limit`
Claude Code writes these messages to stderr rather than showing an error in the conversation, except where an entry notes that it writes the message to the debug log instead. It wr
Claude Code writes most of these messages to stderr, not into the conversation, and writes most of them at startup. An entry says so when its message appears somewhere else, such a
<h3 id="agent-descriptions-are-over-the-15000-token-limit">
+17 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
costs
±changed
+9−0
claude-codechanged
costs
#### Check your usage-credits spend
`/usage` also shows a usage-credits row while [usage credits](#add-usage-credits-to-your-subscription) are on. What the row shows depends on your plan:
+9 −0 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
claude-directory
±changed
+1−1
claude-codechanged
claude-directory
tips: ['Built-in styles Explanatory and Learning are included with Claude Code; custom styles go here', <>Set <C>keep-coding-instructions: true</C> in frontmatter to keep
tips: ['Built-in styles Default, Proactive, Concise, Explanatory, and Learning are included with Claude Code; custom styles go here', <>Set <C>keep-coding-instructions: t
+1 −1 lines
Recorded here 27 Aug 2026 23:07 UTC
claude-code
workflows
±changed
+1−1
claude-codechanged
workflows
Outside bypass permission mode, in `claude -p` and the Agent SDK, Claude Code denies the workflow unless a permission rule allows the Workflow tool or your host approves it through
In `claude -p` and the Agent SDK, the workflow runs only when something else allows the Workflow tool call.
+1 −1 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
settings-reference
±changed
+22−14
claude-codechanged
settings-reference
Boolean keys take the value from the highest-precedence settings file that sets them, so a managed `enabled` or `failIfUnavailable` overrides anything a developer sets. Array keys
Claude Code takes a Boolean key's value from the highest-precedence settings file that sets it, so a managed `enabled` or `failIfUnavailable` overrides anything a developer sets. I
Excluded commands still go through the regular permission flow. Exclusion is a convenience, not a security boundary: prefer [`filesystem.allowWrite`](#sandbox-filesystem-allowwrite
Excluded commands still go through the regular permission flow. Exclusion is a convenience, not a security boundary: prefer [`filesystem.allowWrite`](#sandbox-filesystem-allowwrite
Claude Code enforces these lists at the OS sandbox boundary, so they apply to every subprocess a sandboxed command starts, such as `kubectl`, `terraform`, or `npm`, not only to Cla
+22 −14 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
sandboxing
±changed
+14−7
claude-codechanged
sandboxing
When the same filesystem array is defined in multiple [settings scopes](/docs/en/settings#settings-precedence), the arrays are merged: paths from every scope are combined, not repl
When you define the same filesystem array in multiple [settings scopes](/docs/en/settings#settings-precedence), Claude Code merges them, combining paths from every scope rather tha
When you edit these filesystem lists during a session, Claude Code [applies the change to the running session](/docs/en/settings#when-edits-take-effect), so the next sandboxed comm
File paths follow the same [prefix rules](/docs/en/settings-reference#sandbox-path-prefixes) as `sandbox.filesystem.*` settings, and `deny` entries from every [settings scope](/doc
+14 −7 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
The `--dangerously-skip-permissions` flag is equivalent.
The `--dangerously-skip-permissions` flag is equivalent. Claude Code refuses `bypassPermissions` in a session you start with [`--restricted`](/docs/en/cli-reference#cli-flags). `--
+1 −1 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
errors
±changed
+57−2
claude-codechanged
errors
| `Session <id> was stopped while the respawn was in flight`
| `EACCES: permission denied, posix_spawn`
| `exited before it became reachable`
### Session was stopped while the respawn was in flight
+57 −2 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
env-vars
±changed
+4−3
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
| `CLAUDE_CODE_ARTIFACT_COMMENTS` | Set to `0` to stop Claude reading and replying to [comments on an artifact](/docs/en/artifacts#collect-comments-on-an-ar
| `CLAUDE_CODE_ARTIFACT_COMMENTS_AUTOREACT` | Set to `0` to stop Claude [replying on its own to comments sent to it](/docs/en/artifacts#let-claude-reply-to-comments-o
| `CLAUDE_CODE_RESTRICTED` | Set to `1` to start the session in restricted mode, the same as passing [`--restricted`](/docs/en/cli-reference#cli-flag
+4 −3 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
cli-reference
±changed
+1−0
claude-codechanged
cli-reference
| `--restricted` | Start in restricted mode. Use it when an evaluation harness drives `claude` on a shared machine and Claude Code must not run com
+1 −0 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
changelog
±changed
+52−0
claude-codechanged
changelog
<Update label="2.1.248" description="August 27, 2026">
* Added `--restricted` (or `CLAUDE_CODE_RESTRICTED=1`): removes the built-in tools that run commands or code and `WebFetch` (unless named in `--tools`), keeps file tools inside t
* Added `experimental.cacheTtl` (`"5m"` or `"1h"`) to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured
* Added `claude self-hosted-runner --client-label <label>` (or `SELF_HOSTED_RUNNER_CLIENT_LABEL`) to override the label the runner registers with (default: hostname)
+52 −0 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
artifacts
±changed
+14−5
claude-codechanged
artifacts
Claude writes the page to an HTML or Markdown file in your project, then publishes it. Before publishing a new artifact, Claude Code asks for permission; it might say something lik
Select **Yes** to publish. Claude prints the URL, and your browser opens to the new page. Press `Ctrl+]` at any time to reopen the most recent artifact from the terminal.
Unless you name a location, Claude writes the page to an HTML or Markdown file in a temporary directory outside your project, then publishes it. Publishing a new artifact goes thro
+14 −5 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
agent-view
±changed
+10−0
claude-codechanged
agent-view
If a background session on the list already has the conversation's name, Claude Code numbers the new row's name, such as `my-session (2)`, and leaves the existing row's name alone.
| v2.1.246 | On an npm installation, when the [background service](#the-supervisor-process) fails to start while `npm install -g @anthropic-ai/claude-code` is replacing the binary,
| v2.1.246 | When the [background service](#the-supervisor-process) process dies after printing an error, Claude Code reports the failure and [quotes the service's first error line
| v2.1.246 | If your machine sleeps while the [background service](#the-supervisor-process) is starting, Claude Code retries the start once instead of failing.
+10 −0 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
agent-sdk/migration-guide
±changed
+2−2
claude-codechanged
agent-sdk/migration-guide
settingSources: [] // No filesystem settings loaded
settingSources: [] // Skip user, project, and local settings
options=ClaudeAgentOptions(setting_sources=[]), # No filesystem settings loaded
options=ClaudeAgentOptions(setting_sources=[]), # Skip user, project, and local settings
+2 −2 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
agent-sdk/hosting
±changed
+1−1
claude-codechanged
agent-sdk/hosting
* Pass `settingSources: []` in TypeScript or `setting_sources=[]` in Python so no filesystem settings load.
* Pass `settingSources: []` in TypeScript or `setting_sources=[]` in Python to skip user, project, and local settings.
+1 −1 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+7−6
claude-codechanged
agent-sdk/claude-code-features
| Input | Behavior
| :----------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------
| Managed policy settings | Endpoint-managed policy, such as an MDM plist, registry policy, or managed settings file, loads from the host
| `~/.claude.json` global config | Always read
| Auto memory at `~/.claude/projects/<project>/memory/` | Loaded into the system prompt at session start. The agent writes new memories there with the standard `Write`
+7 −6 lines
Recorded here 27 Aug 2026 22:37 UTC
claude-code
tools-reference
±changed
+1−1
claude-codechanged
tools-reference
To cap how many turns a subagent runs, set `maxTurns` in the [subagent definition](/docs/en/sub-agents#supported-frontmatter-fields).
To cap how many turns a subagent runs, set `maxTurns` in the [subagent definition](/docs/en/sub-agents#supported-frontmatter-fields). When the subagent reaches the limit, Claude Co
+1 −1 lines
Recorded here 27 Aug 2026 21:07 UTC
claude-code
sub-agents
±changed
+3−2
claude-codechanged
sub-agents
| `maxTurns` | No | Maximum number of agentic turns before the subagent stops
| `maxTurns` | No | Maximum number of agentic turns before the subagent stops. When the subagent reaches the limit, Claude Code returns its output marked as partial, a
When a subagent completes, Claude receives its agent ID. The built-in Explore and Plan agents are one-shot and return no agent ID, so they can't be resumed; use `general-purpose` o
* When a subagent completes, Claude receives its agent ID. The built-in Explore and Plan agents are one-shot and return no agent ID, so they can't be resumed; use `general-purpose`
* When a subagent stops at its [`maxTurns`](#supported-frontmatter-fields) limit, Claude Code marks the returned output as partial. For subagents that return an agent ID, Claude Co
+3 −2 lines
Recorded here 27 Aug 2026 21:07 UTC
claude-code
keybindings
±changed
+1−1
claude-codechanged
keybindings
* Under a non-Latin layout such as Cyrillic, in a terminal that uses the Kitty keyboard protocol and reports the key's US-layout position, Claude Code matches Ctrl shortcuts by tha
* Under a non-Latin layout such as Cyrillic, Claude Code matches Ctrl shortcuts by the key's US-layout position when the terminal uses the Kitty keyboard protocol and reports that
+1 −1 lines
Recorded here 27 Aug 2026 21:07 UTC
claude-code
errors
±changed
+25−4
claude-codechanged
errors
| `Prompt is too long · this conversation is a single exchange` / `A single-exchange conversation cannot be compacted`
**What to do:**
* Run `/compact` to summarize earlier turns and free space, or `/clear` to start fresh
A single-exchange conversation has no earlier turns to summarize. When automatic compaction would have run on one, Claude Code skips the attempt and explains what fills the request
+25 −4 lines
Recorded here 27 Aug 2026 21:07 UTC
claude-code
agent-sdk/subagents
±changed
+17−15
claude-codechanged
agent-sdk/subagents
| Field | Type | Required | Description
| :---------------- | :---------------------------------------------------------- | :------- | :------------------------------------------------------------------------------------
| `description` | `string` | Yes | Natural language description of when to use this agent
| `prompt` | `string` | Yes | The agent's system prompt defining its role and behavior
| `tools` | `string[]` | No | Array of allowed tool names. If omitted, inherits every [tool available to subagents]
+17 −15 lines
Recorded here 27 Aug 2026 21:07 UTC
claude-code
workflows
±changed
+9−8
claude-codechanged
workflows
* **Yes, and don't ask again for `<name>` in `<path>`**: start, and skip this prompt for this workflow in this project from now on
* **Yes, and don't ask again for `<name>` in `<path>`**: start, and skip this prompt for this workflow in this project from now on. Claude Code offers this option when you run a bu
| Permission mode | When you're prompted
| :----------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------
| Auto | First launch only. Any **Yes** records consent in your user settings, and later launches start without prompting. Skipped entirely wh
+9 −8 lines
Recorded here 27 Aug 2026 20:07 UTC
claude-code
scheduled-tasks
±changed
+2−3
claude-codechanged
scheduled-tasks
To stop a `/loop` while it is waiting for the next iteration, press `Esc`. This clears the pending wakeup so the loop does not fire again. Tasks you scheduled by [asking Claude dir
To stop a [self-paced `/loop`](#let-claude-choose-the-interval) while it is waiting for the next iteration, press `Esc`. This clears the pending wakeup so the loop does not fire ag
Loops on a fixed interval keep running until you stop them or [seven days elapse](#seven-day-expiry).
Loops on a fixed interval keep running until you [cancel them like any other scheduled task](#manage-scheduled-tasks) or [seven days elapse](#seven-day-expiry).
* Claude Code stores the scheduled task list in the project's `.claude` directory, and scheduling a task fails with an error when that directory, or the task file inside it, is a s
+2 −3 lines
Recorded here 27 Aug 2026 20:07 UTC
claude-code
channels-reference
±changed
+5−5
claude-codechanged
channels-reference
// added to Claude's system prompt so it knows how to handle these events
// Claude Code delivers this to Claude as context when the server connects, so it knows how to handle these events
* **Server configuration**: creates the MCP server with `claude/channel` in its capabilities, which is what tells Claude Code this is a channel. The [`instructions`](#server-op
* **Server configuration**: creates the MCP server with `claude/channel` in its capabilities, which is what tells Claude Code this is a channel. Claude Code delivers the [`inst
* **`curl` succeeds but nothing reaches Claude**: run `/mcp` in your session to check the server's status. "Failed to connect" usually means a dependency or import error in you
+5 −5 lines
Recorded here 27 Aug 2026 20:07 UTC
claude-code
agent-teams
±changed
+10−13
claude-codechanged
agent-teams
* **Escape**: interrupt the selected teammate's current turn
* **Escape**: clear the selection. While you're viewing a teammate's transcript, Escape interrupts that teammate's current turn
### Require plan approval for teammates
For complex or risky tasks, you can require teammates to plan before implementing. The teammate works in read-only plan mode until the lead approves their approach:
+10 −13 lines
Recorded here 27 Aug 2026 20:07 UTC
claude-code
plugin-relevance
±changed
+0−2
claude-codechanged
plugin-relevance
This feature requires Claude Code v2.1.152 or later. Older clients ignore the `relevance` field.
+0 −2 lines
Recorded here 27 Aug 2026 19:37 UTC
claude-code
plugin-marketplaces
±changed
+1−1
claude-codechanged
plugin-marketplaces
| `relevance` | object | Signals that tell Claude Code when to suggest this plugin to users. Takes effect only for marketplaces an administrator allowlists in managed setting
| `relevance` | object | Signals that tell Claude Code when to suggest this plugin to users. Takes effect only for marketplaces an administrator allowlists in managed setting
+1 −1 lines
Recorded here 27 Aug 2026 19:37 UTC
claude-code
mcp-quickstart
±changed
+2−1
claude-codechanged
mcp-quickstart
* You wrote a malformed entry in `.mcp.json`. Claude Code skips that entry and still loads the others. Run `claude mcp list` from your shell and look for the parse warning, whi
If your servers still don't appear, run `/mcp` and look for a parse warning. Claude Code skips malformed entries and shows the offending field there.
If your servers still don't appear, run `claude mcp list` and look for a parse warning. Claude Code skips malformed entries and shows the offending field there.
+2 −1 lines
Recorded here 27 Aug 2026 19:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/reload-skills` | Re-scan [skill](/docs/en/skills) and command directories so skills added or change
| `/reload-skills` | Re-scan [skill](/docs/en/skills) and command directories so skills added or change
+1 −1 lines
Recorded here 27 Aug 2026 19:37 UTC
claude-code
settings-reference
±changed
+1−0
claude-codechanged
settings-reference
@media (max-width: 1279px) { .bti-btn { bottom: 112px; } }
+1 −0 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
overview
±changed
+5−5
claude-codechanged
overview
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={n
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} th
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={
+5 −5 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
mcp
±changed
+28−7
claude-codechanged
mcp
If an HTTP or SSE server disconnects mid-session, Claude Code automatically reconnects with exponential backoff: up to five attempts, starting at a one-second delay and doubling ea
The same backoff applies when an HTTP or SSE server fails its initial connection at startup. Claude Code retries the initial connection up to three times on transient errors such a
When a configured server fails to connect, Claude Code tells Claude which server failed and its connection error, including in `ToolSearch` results that find no matching tool, so C
+28 −7 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
agent-sdk/mcp
±changed
+15−3
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. Servers load
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 emits a `system` message with subtype `init` at the start of each query. This message includes the connection status for each MCP server. The `status` field can be `"pe
Claude Code emits a `system` message with subtype `init` at the start of each query. This message includes the connection status for each MCP server. The `status` field can be `"pe
+15 −3 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
admin-setup
±changed
+10−1
claude-codechanged
admin-setup
On devices where managed settings are present, Desktop WSL sessions are unavailable by default. If your organization wants to enable them, contact your Anthropic account team. When
Claude Desktop turns off WSL sessions by default on devices it detects as organization-managed, for example when `C:\Program Files\ClaudeCode\managed-settings.json` exists. To turn
* Create a value named `disableWslSessions` under `HKLM\SOFTWARE\Policies\Claude` and set it to the `REG_SZ` string `false` or the `REG_DWORD` `0`. This value sits under the Claude
* Leave `C:\Program Files\ClaudeCode\managed-settings.json` in place if you deploy it. Once `disableWslSessions` is `false` under HKLM, Desktop allows WSL sessions even though that
+10 −1 lines
Recorded here 27 Aug 2026 19:07 UTC
claude-code
permissions
±changed
+10−4
claude-codechanged
permissions
Deny and ask rules can match a top-level input parameter on any tool with `Tool(param:value)`. The rule matches when Claude calls the tool with that parameter set to that exact val
Deny and ask rules can match a top-level input parameter on any built-in tool with `Tool(param:value)`.
To match a parameter on an MCP tool, pass a deny rule with [`--disallowedTools`](/docs/en/cli-reference#cli-flags). When Claude Code loads a settings file, it skips any `mcp__` rul
+10 −4 lines
Recorded here 27 Aug 2026 18:37 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertif
By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertif
+1 −1 lines
Recorded here 27 Aug 2026 18:37 UTC
claude-code
monitoring-usage
±changed
+8−8
claude-codechanged
monitoring-usage
* **Time series databases (for example, Prometheus)**: Rate calculations, aggregated metrics
* **Columnar stores (for example, ClickHouse)**: Complex queries, unique user analysis
* **Full-featured observability platforms (for example, Honeycomb, Datadog, Grafana Cloud)**: Advanced querying, visualization, alerting
* **Time series databases**: Rate calculations, aggregated metrics
* **Columnar stores**: Complex queries, unique user analysis
+8 −8 lines
Recorded here 27 Aug 2026 18:37 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
* **Telemetry**: each configured destination, such as Datadog, Splunk, or ClickHouse, receives [OpenTelemetry Protocol (OTLP) metrics](/docs/en/monitoring-usage) with token counts,
* **Telemetry**: each configured destination receives [OpenTelemetry Protocol (OTLP) metrics](/docs/en/monitoring-usage) with token counts, model, user identity, and latency by def
+1 −1 lines
Recorded here 27 Aug 2026 18:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.