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 |
|---|---|---|
v2.1.265str_replace |
Documentation arrivedAnthropic's documentation has since written up str_replace, on text-editor-tool.
the line in the docscase "str_replace": |
|
v2.1.268navigate |
Documentation arrivedA small documentation edit on browser-use-tool touched a line naming navigate after this was published.
the line in the docs4. In your `navigate` handler, accept the history keywords `"back"`, `"forward"`, and `"reload"`, treat a URL without a scheme as `https://`, then parse the URL and refuse any scheme other than `http` or `https` (`javascript:`, `file:`, `d… |
|
v2.1.265policyHelper |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming policyHelper after this was published.
the line in the docsWhen a [`policyHelper`](/docs/en/settings-reference#policyhelper) supplies managed settings, its output is the only source these checks read, apart from [`forceRemoteSettingsRefresh`](/docs/en/settings-reference#forceremotesettingsrefresh)… |
|
v2.1.265policyHelper |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming policyHelper after this was published.
the line in the docsWhen a [`policyHelper`](/docs/en/settings-reference#policyhelper) supplies managed settings, its output is the only source these checks read, apart from [`forceRemoteSettingsRefresh`](/docs/en/settings-reference#forceremotesettingsrefresh)… |
|
v2.1.257policyHelper |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming policyHelper after this was published.
the line in the docsWhen a [`policyHelper`](/docs/en/settings-reference#policyhelper) supplies managed settings, its output is the only source these checks read, apart from [`forceRemoteSettingsRefresh`](/docs/en/settings-reference#forceremotesettingsrefresh)… |
|
v2.1.273disableClaudeAiConnectors |
Documentation arrivedAnthropic's documentation has since written up disableClaudeAiConnectors, on Deploy managed settings.
the line in the docs* `deniedMcpServers` and [`disableClaudeAiConnectors`](/docs/en/settings-reference#disableclaudeaiconnectors): an entry or a `true` in any admin source applies. Requires Claude Code v2.1.273 or later |
|
v2.1.248MCP_CONNECTION_NONBLOCKING |
Documentation arrivedAnthropic's documentation has since written up MCP_CONNECTION_NONBLOCKING, on Environment variables.
the line in the docs| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default: servers connect in the background and their tools become available as they finish. S… |
|
v2.1.248MCP_CONNECTION_NONBLOCKING |
Documentation arrivedAnthropic's documentation has since written up MCP_CONNECTION_NONBLOCKING, on Environment variables.
the line in the docs| `MCP_CONNECTION_NONBLOCKING` | Controls whether startup waits for MCP servers to connect before the first query. MCP startup is non-blocking by default: servers connect in the background and their tools become available as they finish. S… |
|
v2.1.273allowManagedMcpServersOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedMcpServersOnly, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs* **`allowedMcpServers`**: Claude Code honors a parent-supplied allowlist when no admin list is in force. `allowManagedMcpServersOnly` doesn't block it, because the lock enforces whichever list wins as the managed value, including a parent… |
|
v2.1.273allowManagedMcpServersOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedMcpServersOnly, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs* **`allowedMcpServers`**: Claude Code honors a parent-supplied allowlist when no admin list is in force. `allowManagedMcpServersOnly` doesn't block it, because the lock enforces whichever list wins as the managed value, including a parent… |
|
v2.1.273allowedMcpServers |
Documentation arrivedAnthropic's documentation has since written up allowedMcpServers, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsFrom an admin source below the winner, the two sandbox locks still apply, and `allowManagedPermissionRulesOnly` still blocks parent-supplied allow rules and `additionalDirectories`. On Claude Code v2.1.273 or later, the MCP server lock als… |
|
v2.1.273allowedMcpServers |
Documentation arrivedAnthropic's documentation has since written up allowedMcpServers, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsFrom an admin source below the winner, the two sandbox locks still apply, and `allowManagedPermissionRulesOnly` still blocks parent-supplied allow rules and `additionalDirectories`. On Claude Code v2.1.273 or later, the MCP server lock als… |
|
v2.1.265policyHelper |
Documentation arrivedAnthropic's documentation has since written up policyHelper, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThe hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own rules need the winning source by default; under the `managedSourcesBehavior` merge opt-in in [how Claude Code combines managed sources](/docs/en/managed-s… |
|
v2.1.265managedSourcesBehavior |
Documentation arrivedAnthropic's documentation has since written up managedSourcesBehavior, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThe hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own rules need the winning source by default; under the `managedSourcesBehavior` merge opt-in in [how Claude Code combines managed sources](/docs/en/managed-s… |
|
v2.1.265managedSourcesBehavior |
Documentation arrivedAnthropic's documentation has since written up managedSourcesBehavior, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThe hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own rules need the winning source by default; under the `managedSourcesBehavior` merge opt-in in [how Claude Code combines managed sources](/docs/en/managed-s… |
|
v2.1.248managedSourcesBehavior |
Documentation arrivedAnthropic's documentation has since written up managedSourcesBehavior, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThe hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own rules need the winning source by default; under the `managedSourcesBehavior` merge opt-in in [how Claude Code combines managed sources](/docs/en/managed-s… |
|
v2.1.242managedSourcesBehavior |
Documentation arrivedAnthropic's documentation has since written up managedSourcesBehavior, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThe hooks lock and `allowManagedPermissionRulesOnly`'s effect on the developer's own rules need the winning source by default; under the `managedSourcesBehavior` merge opt-in in [how Claude Code combines managed sources](/docs/en/managed-s… |
|
v2.1.246command: |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming command: after this was published.
the line in the docsA `/<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, with a note that the command didn't run, so the query spend… |
|
v2.1.259permissionPromptToolName |
Documentation arrivedAnthropic's documentation has since written up permissionPromptToolName, on Connect to external tools with MCP.
the line in the docsIf you set `permissionPromptToolName`, the first turn also waits for that tool's server in every case, up to `MCP_TIMEOUT`. |
|
v2.1.273/install-github-app |
Documentation arrivedAnthropic's documentation has since written up /install-github-app, on Error reference.
the line in the docsYou ran [`/install-github-app`](/docs/en/github-actions#quick-setup) and chose a repository whose organization enforces SAML single sign-on. Before setup, Claude Code checks your access to the repository with the GitHub CLI, and GitHub ref… |
|
v2.1.273NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Error reference.
the line in the docsUnable to connect to API: SSL certificate verification failed (UNABLE_TO_GET_ISSUER_CERT_LOCALLY). The certificate comes from an authority Claude Code doesn't trust, usually a TLS-inspecting corporate proxy or a gateway signed by a private… |
|
v2.1.273declare |
Documentation arrivedAnthropic's documentation has since written up declare, on Configuration reference.
the line in the docsWhen set, Cowork, Chat and Code sessions connect the managed list above and the servers the desktop serves from the administrator's org-plugins directory, plus only servers declared by other plugins (user-installed or marketplace) that mat… |
|
v2.1.273declare |
Documentation arrivedAnthropic's documentation has since written up declare, on Configuration reference.
the line in the docsWhen set, Cowork, Chat and Code sessions connect the managed list above and the servers the desktop serves from the administrator's org-plugins directory, plus only servers declared by other plugins (user-installed or marketplace) that mat… |
|
v2.1.265Salesforce |
Documentation arrivedAnthropic's documentation has since written up Salesforce, on Changelog.
the line in the docs* Added a Salesforce preset to the plugin marketplace picker in the Setup window. |
|
v2.1.267safeguards |
Documentation arrivedA small documentation edit on Claude Science changelog touched a line naming safeguards after this was published.
the line in the docs* If your organization is in Anthropic's Life Sciences Verification Program (beta), you can now [choose a use case](/docs/claude-science/safeguards#choose-a-use-case) for your sessions |
|
v2.1.267safeguards |
Documentation arrivedA small documentation edit on Claude Science changelog touched a line naming safeguards after this was published.
the line in the docs* If your organization is in Anthropic's Life Sciences Verification Program (beta), you can now [choose a use case](/docs/claude-science/safeguards#choose-a-use-case) for your sessions |
|
v2.1.273export |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming export after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, and [`modelCatalogEnabled`](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) se… |
|
v2.1.242gh auth token |
Documentation arrivedA small documentation edit on Get started with Claude Code in the cloud touched a line naming gh auth token after this was published.
the line in the docsWhen 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 claude.ai account, and your cloud sessions use it for GitHub… |
|
v2.1.268claude mcp |
Documentation arrivedA small documentation edit on Automate work with routines touched a line naming claude mcp after this was published.
the line in the docsConnectors 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 on your machine rather than your claude.ai account, so they… |
|
v2.1.273declare |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming declare after this was published.
the line in the docs[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 with one repository and the plugins it declares in any sess… |
|
v2.1.273declare |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming declare after this was published.
the line in the docs[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 with one repository and the plugins it declares in any sess… |
|
v2.1.273SessionStart |
Documentation arrivedAnthropic's documentation has since written up SessionStart, on Configure cloud environments.
the line in the docs* **One repository per session**: a session with several repositories doesn't load hooks from any repository's `.claude/settings.json`, so a SessionStart hook you define there doesn't run. Install dependencies for those sessions with a [se… |
|
v2.1.239/agents |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming /agents after this was published.
the line in the docsTo 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; to have Claude start and track parallel sessions in the cl… |
|
v2.1.267Select |
Documentation arrivedA small documentation edit on Get started touched a line naming Select after this was published.
the line in the docs* Projects you created under another sign-in on this computer don't appear automatically, for example, after you move from a personal plan to your organization's Team plan: your earlier projects are still in that sign-in's folder. Select t… |
|
v2.1.273export |
Documentation arrivedAnthropic's documentation has since written up export, on Create and distribute a plugin marketplace.
the line in the docsIn CI/CD environments, configure a git credential helper before installing plugins from private repositories. On GitHub Actions, export a token with read access to the marketplace repository as `GH_TOKEN`, then run `gh auth setup-git`. The… |
|
v2.1.261CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, on Connect Claude Code to tools via MCP.
the line in the docs* Sessions 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_BY_HOST`](/docs/en/env-vars) |
|
v2.1.247XDG_CONFIG_HOME |
Documentation arrivedAnthropic's documentation has since written up XDG_CONFIG_HOME, on Claude Code changelog.
the line in the docs* \[VSCode] Changed the default global gitignore file to `$XDG_CONFIG_HOME/git/ignore` when `XDG_CONFIG_HOME` is an absolute path |
|
v2.1.236OTEL_LOG_RAW_API_BODIES |
Documentation arrivedAnthropic's documentation has since written up OTEL_LOG_RAW_API_BODIES, on Claude Code changelog.
the line in the docs* Improved `OTEL_LOG_RAW_API_BODIES=file:<dir>` output: a new `index.jsonl` and `request_body_id` / `message.id` event attributes link each response to its request file and transcript message |
|
v2.1.273/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code changelog.
the line in the docs* Fixed `/status` not showing the `apiKeyHelper` failure that its own error banner told you to check |
|
v2.1.273/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code changelog.
the line in the docs* Fixed `/status` not showing the `apiKeyHelper` failure that its own error banner told you to check |
|
v2.1.273/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on Claude Code changelog.
the line in the docs* Fixed error hints in Claude Desktop sessions to suggest slash commands like `/usage-credits` instead of CLI flags that cannot be used there |
|
v2.1.273/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on Claude Code changelog.
the line in the docs* Fixed error hints in Claude Desktop sessions to suggest slash commands like `/usage-credits` instead of CLI flags that cannot be used there |
|
v2.1.273CLAUDE_CODE_RESUME_INTERRUPTED_TURN |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_RESUME_INTERRUPTED_TURN, on Claude Code changelog.
the line in the docs* Fixed a local `claude -p --resume` started with `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` not reporting background tasks the previous process left unfinished |
|
v2.1.273/mcp |
Documentation arrivedA small documentation edit on MCP, plugins, skills, and hooks touched a line naming /mcp after this was published.
the line in the docsWith `"oauth": true`, Claude Desktop registers its own public client through dynamic client registration and lists this URI as the client's only redirect URI, so the authorization server must offer a registration endpoint and accept an `ht… |
|
v2.1.273/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Deploy with Enterprise Admin Console.
the line in the docs| Provider credentials, API keys, bearer tokens, and MCP secrets | **No**, except the client secret of a Google Desktop-app OAuth client, which Google doesn't treat as confidential. You can enter one for [Google sign-in to your provider](#… |
|
v2.1.273design |
Documentation arrivedAnthropic's documentation has since written up design, on Personal connectors in channels.
the line in the docsWhile Claude works on your connector task, it is designed to take direction from you. Other people's messages in the thread reach Claude as information about the task, not as instructions. A message that tells Claude to change course or sh… |
|
v2.1.257tool.output |
Documentation arrivedAnthropic's documentation has since written up tool.output, on Monitoring.
the line in the docs| `OTEL_LOG_TOOL_CONTENT` | Enable logging of tool content in the [`tool.output` span event](#tool-output-span-event) (default: disabled). Span attributes carry tool content under [their own gates](#new-context-gates). Requires [tracing](#… |
|
v2.1.265retries |
Documentation arrivedA small documentation edit on Claude Code gateway compatibility guide touched a line naming retries after this was published.
the line in the docs* When the upstream rejects a [thinking signature](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), including with a `400` whose message says the block is `bound to a different conversation`, Claude Code removes ea… |
|
v2.1.265retries |
Documentation arrivedA small documentation edit on Claude Code gateway compatibility guide touched a line naming retries after this was published.
the line in the docs* When the upstream rejects a [thinking signature](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), including with a `400` whose message says the block is `bound to a different conversation`, Claude Code removes ea… |
|
v2.1.257tool.output |
Documentation arrivedA small documentation edit on Observability with OpenTelemetry touched a line naming tool.output after this was published.
the line in the docs| `OTEL_LOG_TOOL_CONTENT=1` | A [`tool.output` span event](/docs/en/monitoring-usage#tool-output-span-event) on `claude_code.tool` with file contents and Bash output, truncated at 60 KB by default, configurable via `CLAUDE_CODE_OTEL_CONTEN… |