An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.301--mcp-config |
Documentation arrivedAnthropic's documentation has since written up --mcp-config, on Control MCP server access for your organization.
the line in the docsA `managed-mcp.json` server that uses `${VAR}` expansion in its command, arguments, URL, or headers is still checked. Claude Code also checks every server a user, a plugin, or claude.ai adds, and every server a user passes with `--mcp-conf… |
|
v2.1.300--mcp-config |
Documentation arrivedAnthropic's documentation has since written up --mcp-config, on Control MCP server access for your organization.
the line in the docsA `managed-mcp.json` server that uses `${VAR}` expansion in its command, arguments, URL, or headers is still checked. Claude Code also checks every server a user, a plugin, or claude.ai adds, and every server a user passes with `--mcp-conf… |
|
v2.1.299--mcp-config |
Documentation arrivedAnthropic's documentation has since written up --mcp-config, on Control MCP server access for your organization.
the line in the docsA `managed-mcp.json` server that uses `${VAR}` expansion in its command, arguments, URL, or headers is still checked. Claude Code also checks every server a user, a plugin, or claude.ai adds, and every server a user passes with `--mcp-conf… |
|
v2.1.299--mcp-config |
Documentation arrivedAnthropic's documentation has since written up --mcp-config, on Control MCP server access for your organization.
the line in the docsA `managed-mcp.json` server that uses `${VAR}` expansion in its command, arguments, URL, or headers is still checked. Claude Code also checks every server a user, a plugin, or claude.ai adds, and every server a user passes with `--mcp-conf… |
|
v2.1.305allowedMcpServers |
Documentation arrivedAnthropic's documentation has since written up allowedMcpServers, on Control MCP server access for your organization.
the line in the docsThe servers in `managed-mcp.json` need no `allowedMcpServers` entry, with one exception: Claude Code checks a server against the allowlist when it uses [`${VAR}` expansion](/docs/en/mcp#environment-variable-expansion-in-mcp-json) outside `… |
|
v2.1.293clientSecretHelper |
Documentation arrivedAnthropic's documentation has since written up clientSecretHelper, on Configuration changelog.
the line in the docs* A `managedMcpServers` entry accepts `headersHelperArgs` (remote and web search entries) or `envHelperArgs` (local entries): arguments for its helper script. Its helpers, `oauth.clientSecretHelper` included, also get the entry's `name` in… |
|
v2.1.293clientSecretHelper |
Documentation arrivedAnthropic's documentation has since written up clientSecretHelper, on Configuration changelog.
the line in the docs* A `managedMcpServers` entry accepts `headersHelperArgs` (remote and web search entries) or `envHelperArgs` (local entries): arguments for its helper script. Its helpers, `oauth.clientSecretHelper` included, also get the entry's `name` in… |
|
v2.1.304otelHeadersHelper |
Documentation arrivedAnthropic's documentation has since written up otelHeadersHelper, on Configuration reference.
the line in the docs> Absolute path to an executable that prints a single JSON object of HTTP headers on stdout, e.g. `{"Authorization": "Bearer …"}`. The desktop runs it (no arguments; output cached for a few minutes, and a failure is not retried for 30 seco… |
|
v2.1.305allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Changelog.
the line in the docs* Changed plugins that the app loads to ask before using the tools they pre-approve when your organization's Claude Code managed settings, such as `managed-settings.json`, set `allowManagedPermissionRulesOnly`. |
|
v2.1.305allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Changelog.
the line in the docs* Changed plugins that the app loads to ask before using the tools they pre-approve when your organization's Claude Code managed settings, such as `managed-settings.json`, set `allowManagedPermissionRulesOnly`. |
|
v2.1.305/effort |
Documentation arrivedA small documentation edit on prompting-claude-opus-5 touched a line naming /effort after this was published.
the line in the docs* **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens and latency of higher settings. Start with the default (`high`) … |
|
v2.1.305/usage |
Documentation arrivedA small documentation edit on overview touched a line naming /usage after this was published.
the line in the docsYou can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits) and your spend limits on the Console's [Billing](https://platform.claude.com/settings/billing) page. For higher rate limits o… |
|
v2.1.305/usage |
Documentation arrivedA small documentation edit on overview touched a line naming /usage after this was published.
the line in the docsYou can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits) and your spend limits on the Console's [Billing](https://platform.claude.com/settings/billing) page. For higher rate limits o… |
|
v2.1.305/usage |
Documentation arrivedA small documentation edit on overview touched a line naming /usage after this was published.
the line in the docsYou can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits) and your spend limits on the Console's [Billing](https://platform.claude.com/settings/billing) page. For higher rate limits o… |
|
v2.1.304/reload-plugins |
Documentation arrivedAnthropic's documentation has since written up /reload-plugins, on Troubleshoot a mod.
the line in the docsIf the reason ends with `; the version loaded before is unloaded`, no version of the mod is running now. Once you fix the error, run [`/reload-plugins`](/docs/en/plugins/cli-reference#reload-plugins) in the session to load the mod again. I… |
|
v2.1.304network.tlsTerminate |
Documentation arrivedAnthropic's documentation has since written up network.tlsTerminate, on Configure server-managed settings.
the line in the docs* **Sandbox network and isolation settings**: [sandbox](/docs/en/sandboxing) settings that let the sandbox proxy read, reroute, or authenticate traffic, or that weaken the sandbox's isolation: `sandbox.network.tlsTerminate`, `sandbox.netwo… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedAnthropic's documentation has since written up sandbox.allowNestedUserNamespaces, on Configure the sandboxed Bash tool.
the line in the docs* To keep Chromium's or Electron's own sandbox, or to run a nested bubblewrap or `unshare`, set [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedusernamespaces) to `true` in `~/.claude/settings.json`, no… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedAnthropic's documentation has since written up sandbox.allowNestedUserNamespaces, on Configure the sandboxed Bash tool.
the line in the docs* To keep Chromium's or Electron's own sandbox, or to run a nested bubblewrap or `unshare`, set [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedusernamespaces) to `true` in `~/.claude/settings.json`, no… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedAnthropic's documentation has since written up sandbox.allowNestedUserNamespaces, on Configure the sandboxed Bash tool.
the line in the docs* To keep Chromium's or Electron's own sandbox, or to run a nested bubblewrap or `unshare`, set [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedusernamespaces) to `true` in `~/.claude/settings.json`, no… |
|
v2.1.304allowAllUnixSockets |
Documentation arrivedAnthropic's documentation has since written up allowAllUnixSockets, on Configure the sandboxed Bash tool.
the line in the docs* `unshare -U true` prints `unshare: unshare failed: Operation not permitted`. With [`allowAllUnixSockets`](/docs/en/settings-reference#sandbox-network-allowallunixsockets) on, it can print `No space left on device` instead |
|
v2.1.305/sandbox |
Documentation arrivedAnthropic's documentation has since written up /sandbox, on Configure the sandboxed Bash tool.
the line in the docsTo see most of these paths resolved for your machine, run `/sandbox` and open the **Config** tab, which lists them under **Denied within allowed**, mixed in with your own `denyWrite` entries. |
|
v2.1.305/sandbox |
Documentation arrivedAnthropic's documentation has since written up /sandbox, on Configure the sandboxed Bash tool.
the line in the docsTo see most of these paths resolved for your machine, run `/sandbox` and open the **Config** tab, which lists them under **Denied within allowed**, mixed in with your own `denyWrite` entries. |
|
v2.1.302strictKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up strictKnownMarketplaces, on Plugin loading reference.
the line in the docs* **Marketplace sources restricted**: a [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) allowlist without a `{ "source": "skills-dir" }` entry, or a [`blockedMarketplaces`](/docs/en/settings-reference#block… |
|
v2.1.305--plugin-dir |
Documentation arrivedAnthropic's documentation has since written up --plugin-dir, on Plugin loading reference.
the line in the docsFor how to write `--plugin-dir` and skills-directory plugins, see [Create plugins](/docs/en/plugins/create). |
|
v2.1.304claude mcp serve |
Documentation arrivedAnthropic's documentation has since written up claude mcp serve, on Connect Claude Code to tools via MCP.
the line in the docsA `backgroundOutputPath` field in a Bash or PowerShell result from `claude mcp serve` means the call left its command running [in the background](/docs/en/tools-reference#background-commands). A command runs in the background when your cli… |
|
v2.1.302claude mcp serve |
Documentation arrivedAnthropic's documentation has since written up claude mcp serve, on Connect Claude Code to tools via MCP.
the line in the docsA `backgroundOutputPath` field in a Bash or PowerShell result from `claude mcp serve` means the call left its command running [in the background](/docs/en/tools-reference#background-commands). A command runs in the background when your cli… |
|
v2.1.302claude mcp serve |
Documentation arrivedAnthropic's documentation has since written up claude mcp serve, on Connect Claude Code to tools via MCP.
the line in the docsA `backgroundOutputPath` field in a Bash or PowerShell result from `claude mcp serve` means the call left its command running [in the background](/docs/en/tools-reference#background-commands). A command runs in the background when your cli… |
|
v2.1.305acceptEdits |
Documentation arrivedAnthropic's documentation has since written up acceptEdits, on Connect Claude Code to tools via MCP.
the line in the docs* **Tool set to `ask`**: Claude Code prompts on every call with the reason `Your organization requires approval for this tool`. The prompt appears even in `acceptEdits`, `auto`, and `bypassPermissions` [permission modes](/docs/en/permissio… |
|
v2.1.305headersHelper |
Documentation arrivedAnthropic's documentation has since written up headersHelper, on Connect Claude Code to tools via MCP.
the line in the docs* **A server whose [configuration](#mcp-installation-scopes) you can edit**: set it in [`headers`](#example-with-variable-expansion) or return it from a [`headersHelper`](#use-dynamic-headers-for-custom-authentication) |
|
v2.1.305/config |
Documentation arrivedA small documentation edit on Use Claude Code in the cloud touched a line naming /config after this was published.
the line in the docs* **`/config`**: in your browser at claude.ai/code, opens the Claude Code section of your settings instead of setting a value, and text after the command, including `key=value`, is ignored. To change a setting for a cloud session, set an [… |
|
v2.1.305claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Authentication.
the line in the docs* **Earlier sign-in**: you ran [`claude auth login`](/docs/en/cli-reference#cli-commands) in your shell before your first session, or you rebuilt a dev container that keeps your credentials in a [volume](/docs/en/devcontainer#persist-authe… |
|
v2.1.305claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Authentication.
the line in the docs* **Earlier sign-in**: you ran [`claude auth login`](/docs/en/cli-reference#cli-commands) in your shell before your first session, or you rebuilt a dev container that keeps your credentials in a [volume](/docs/en/devcontainer#persist-authe… |
|
v2.1.292--add-dir |
Documentation arrivedA small documentation edit on Error reference touched a line naming --add-dir after this was published.
the line in the docs* On Windows, map the share to a drive letter and pass the drive at launch. In PowerShell, for example, run `net use Z: \\server\share` and then `claude --add-dir Z:\`. |
|
v2.1.287--add-dir |
Documentation arrivedA small documentation edit on Error reference touched a line naming --add-dir after this was published.
the line in the docs* On Windows, map the share to a drive letter and pass the drive at launch. In PowerShell, for example, run `net use Z: \\server\share` and then `claude --add-dir Z:\`. |
|
v2.1.287--add-dir |
Documentation arrivedA small documentation edit on Error reference touched a line naming --add-dir after this was published.
the line in the docs* On Windows, map the share to a drive letter and pass the drive at launch. In PowerShell, for example, run `net use Z: \\server\share` and then `claude --add-dir Z:\`. |
|
v2.1.299CLAUDE_CODE_DISABLE_FILE_MENTIONS |
Documentation arrivedA small documentation edit on Common workflows touched a line naming CLAUDE_CODE_DISABLE_FILE_MENTIONS after this was published.
the line in the docsTo stop `@` references from including file contents and directory listings, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS`](/docs/en/env-vars#variables) to `1` in your shell or in the [`env` block](/docs/en/env-vars#set-variables-in-settings-fil… |
|
v2.1.295timeouts.upstream_ttfb_ms |
Documentation arrivedAnthropic's documentation has since written up timeouts.upstream_ttfb_ms, on Claude apps gateway deployment and operations.
the line in the docs| On `provider: anthropic`, a turn with a long thinking pause fails. The proxy logs one request open for about 20 minutes, then `502` or `504` errors | Claude Code ended a stream that had delivered its first response event and then carried… |
|
v2.1.295store.postgres_url |
Documentation arrivedAnthropic's documentation has since written up store.postgres_url, on Claude apps gateway deployment and operations.
the line in the docs| Log: `could not connect to Postgres at boot, attempt 1 of 3`, with a reason other than `remaining connection slots are reserved` | The database wasn't reachable yet when the gateway started, for example on a cold instance whose network i… |
|
v2.1.305API_TIMEOUT_MS |
Documentation arrivedAnthropic's documentation has since written up API_TIMEOUT_MS, on Claude apps gateway deployment and operations.
the line in the docs### Keep `API_TIMEOUT_MS` above the gateway's time to first byte |
|
v2.1.305CLAUDE_CODE_CERT_STORE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_CERT_STORE, on Claude Code changelog.
the line in the docs* \[VSCode] Fixed dictation failing behind a TLS-inspecting proxy when `NODE_EXTRA_CA_CERTS` is set only in `~/.claude/settings.json`; it now also follows `CLAUDE_CODE_CERT_STORE` |
|
v2.1.305claude -p |
Documentation arrivedAnthropic's documentation has since written up claude -p, on Claude Code changelog.
the line in the docs* Fixed MCP servers showing "needs authentication" in `claude -p` on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in |
|
v2.1.305NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Claude Code changelog.
the line in the docs* \[VSCode] Changed the extension's own requests to filter their trusted certificates as the CLI does, and to trust the `NODE_EXTRA_CA_CERTS` file named in the environment or in user settings |
|
v2.1.305CLAUDE_AX_SCREEN_READER |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_AX_SCREEN_READER, on Claude Code changelog.
the line in the docs* Changed the `axScreenReader` setting and `CLAUDE_AX_SCREEN_READER` in a settings `env` block to apply only from user, managed or `--settings` settings (since 2.1.305) |
|
v2.1.305axScreenReader |
Documentation arrivedAnthropic's documentation has since written up axScreenReader, on Claude Code changelog.
the line in the docs* Changed the `axScreenReader` setting and `CLAUDE_AX_SCREEN_READER` in a settings `env` block to apply only from user, managed or `--settings` settings (since 2.1.305) |
|
v2.1.305axScreenReader |
Documentation arrivedAnthropic's documentation has since written up axScreenReader, on Claude Code changelog.
the line in the docs* Changed the `axScreenReader` setting and `CLAUDE_AX_SCREEN_READER` in a settings `env` block to apply only from user, managed or `--settings` settings (since 2.1.305) |
|
v2.1.290--file |
Documentation arrivedA small documentation edit on quickstart touched a line naming --file after this was published.
the line in the docs--file-id "$file_id" \ |
|
v2.1.305disallowedTools |
Documentation arrivedAnthropic's documentation has since written up disallowedTools, on Create custom subagents.
the line in the docs* **In `disallowedTools`**: look for `mcp__reports` or `mcp__reports__*`, the entries that withhold a server named `reports`. With either entry, the subagent loses every `reports__v2` tool as well, because those tool names also begin with … |
|
v2.1.293--no-chrome |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --no-chrome after this was published.
the line in the docs* A `--chrome` or `--no-chrome` flag you launched with, so [Chrome integration](/docs/en/chrome) stays on or off as you chose for this session |
|
v2.1.293--chrome |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --chrome after this was published.
the line in the docs* A `--chrome` or `--no-chrome` flag you launched with, so [Chrome integration](/docs/en/chrome) stays on or off as you chose for this session |
|
v2.1.304allowedDomains |
Documentation arrivedA small documentation edit on session-operations touched a line naming allowedDomains after this was published.
the line in the docsYou can update a session's `agent.tools` (csharp, go: `Agent.Tools`) and `agent.mcp_servers` (java, php: `agent.mcpServers`; csharp: `Agent.McpServers`; go: `Agent.MCPServers`), including permission policies and per-tool web settings such … |