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 |
|---|---|---|
v2.1.305/login |
Documentation arrivedA small documentation edit on Create the app registration that represents the Claude API audience. touched a line naming /login after this was published.
the line in the docsUse this path when your workload runs in an AKS pod. Entra Workload Identity federates a Kubernetes service account with a user-assigned managed identity: Kubernetes projects a service account token (signed by the AKS cluster's OIDC issuer… |
|
v2.1.304/login |
Documentation arrivedA small documentation edit on Create the app registration that represents the Claude API audience. touched a line naming /login after this was published.
the line in the docsUse this path when your workload runs in an AKS pod. Entra Workload Identity federates a Kubernetes service account with a user-assigned managed identity: Kubernetes projects a service account token (signed by the AKS cluster's OIDC issuer… |
|
v2.1.304/login |
Documentation arrivedA small documentation edit on Create the app registration that represents the Claude API audience. touched a line naming /login after this was published.
the line in the docsUse this path when your workload runs in an AKS pod. Entra Workload Identity federates a Kubernetes service account with a user-assigned managed identity: Kubernetes projects a service account token (signed by the AKS cluster's OIDC issuer… |
|
v2.1.304/login |
Documentation arrivedA small documentation edit on Create the app registration that represents the Claude API audience. touched a line naming /login after this was published.
the line in the docsUse this path when your workload runs in an AKS pod. Entra Workload Identity federates a Kubernetes service account with a user-assigned managed identity: Kubernetes projects a service account token (signed by the AKS cluster's OIDC issuer… |
|
v2.1.304/login |
Documentation arrivedA small documentation edit on Create the app registration that represents the Claude API audience. touched a line naming /login after this was published.
the line in the docsUse this path when your workload runs in an AKS pod. Entra Workload Identity federates a Kubernetes service account with a user-assigned managed identity: Kubernetes projects a service account token (signed by the AKS cluster's OIDC issuer… |
|
v2.1.305--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on WARNING: This operation PERMANENTLY deletes the chat, all of its messages,.
the line in the docsIn curl, the `--remote-header-name` (`-J`) option, which normally saves a download under the `Content-Disposition` file name, does not read the `filename*` form, so name the saved file yourself with `--output`. In a script, take the name f… |
|
v2.1.307base_url |
Documentation arrivedA small documentation edit on claude-in-amazon-bedrock touched a line naming base_url after this was published.
the line in the docsYou can also create the standard client with `Anthropic` (go: `anthropic.NewClient()`; java: `AnthropicOkHttpClient.builder()`; csharp: `AnthropicClient`; php: `Anthropic\Client`; ruby: `Anthropic::Client`): set `base_url` (typescript: `ba… |
|
v2.1.299CLAUDE_BYTE_STREAM_IDLE_TIMEOUT_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_BYTE_STREAM_IDLE_TIMEOUT_MS, on Enterprise network configuration.
the line in the docs* `CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MS` sets the first-byte deadline. In a Claude apps gateway session, set this variable to [turn the deadline on](/docs/en/claude-apps-gateway-deploy.md#retry-an-unanswered-request-sooner-with-the-first-by… |
|
v2.1.307/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on Manage sessions.
the line in the docs* **Start a new conversation**: switch to work that doesn't need the saved conversation. To reopen it later, run [`/resume`](#use-the-session-picker) at the prompt. The estimate doesn't apply to your first message in the new conversation. … |
|
v2.1.305--debug |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --debug after this was published.
the line in the docs> When a connection to a [plugin's stdio server](/docs/en/mcp.md#plugin-provided-mcp-servers) failed less than 15 minutes before you ran `claude --debug`, Claude Code [doesn't start the server](/docs/en/errors.md#skipping-connection-recent… |
|
v2.1.290--debug |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --debug after this was published.
the line in the docs> When a connection to a [plugin's stdio server](/docs/en/mcp.md#plugin-provided-mcp-servers) failed less than 15 minutes before you ran `claude --debug`, Claude Code [doesn't start the server](/docs/en/errors.md#skipping-connection-recent… |
|
v2.1.290--debug |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --debug after this was published.
the line in the docs> When a connection to a [plugin's stdio server](/docs/en/mcp.md#plugin-provided-mcp-servers) failed less than 15 minutes before you ran `claude --debug`, Claude Code [doesn't start the server](/docs/en/errors.md#skipping-connection-recent… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming sandbox.allowNestedUserNamespaces after this was published.
the line in the docs| `allowNestedUserNamespaces` | `boolean` | `false` | Let sandboxed commands on Linux and WSL2 create user namespaces. Before you set it to `true`, read [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedu… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming sandbox.allowNestedUserNamespaces after this was published.
the line in the docs| `allowNestedUserNamespaces` | `boolean` | `false` | Let sandboxed commands on Linux and WSL2 create user namespaces. Before you set it to `true`, read [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedu… |
|
v2.1.305sandbox.allowNestedUserNamespaces |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming sandbox.allowNestedUserNamespaces after this was published.
the line in the docs| `allowNestedUserNamespaces` | `boolean` | `false` | Let sandboxed commands on Linux and WSL2 create user namespaces. Before you set it to `true`, read [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedu… |
|
v2.1.304sandbox.allowNestedUserNamespaces |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming sandbox.allowNestedUserNamespaces after this was published.
the line in the docs| `allowNestedUserNamespaces` | `boolean` | `false` | Let sandboxed commands on Linux and WSL2 create user namespaces. Before you set it to `true`, read [`sandbox.allowNestedUserNamespaces`](/docs/en/settings-reference#sandbox-allownestedu… |
|
v2.1.307/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Draw in the interface with a mod.
the line in the docsThe band stays collapsed until the user expands it, even after `/clear`, and is expanded again the next time Claude Code starts. Your mod can't expand it or tell that it's collapsed: the `ui.render` hook keeps running, and nothing in `e.pr… |
|
v2.1.304ui.render |
Documentation arrivedAnthropic's documentation has since written up ui.render, on Draw in the interface with a mod.
the line in the docsThe band stays collapsed until the user expands it, even after `/clear`, and is expanded again the next time Claude Code starts. Your mod can't expand it or tell that it's collapsed: the `ui.render` hook keeps running, and nothing in `e.pr… |
|
v2.1.304/ultrareview |
Documentation arrivedAnthropic's documentation has since written up /ultrareview, on Error reference.
the line in the docsIn a folder you haven't trusted, when [`claude ultrareview`](/docs/en/ultrareview#trust-the-folder-before-the-review-runs) can't ask whether you trust it, the run exits with code 1 before the review starts: |
|
v2.1.305acceptEdits |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming acceptEdits after this was published.
the line in the docs> **Subagent inheritance:** If your main session is in [plan mode](/docs/en/permission-modes.md#analyze-before-you-edit-with-plan-mode), a subagent whose [`AgentDefinition`](/docs/en/agent-sdk/typescript#agentdefinition) sets `permissionMo… |
|
v2.1.307/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Authentication for connectors.
the line in the docs* **Create a confidential client**: create a client ID and secret for Claude in your authorization server, and register the redirect URI `https://claude.ai/api/mcp/auth_callback` |
|
v2.1.299user.email |
Documentation arrivedA small documentation edit on compliance-sessions touched a line naming user.email after this was published.
the line in the docsIn each session object, `user.id` is always set and survives account deletion; `user.email_address` is `null` when the user's account has been deleted or the user is no longer a member of an organization your key can read. `workspace_id` i… |
|
v2.1.307ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on java.
the line in the docs// Or configures using the `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, and `ANTHROPIC_BASE_URL` environment variables |
|
v2.1.307ANTHROPIC_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BASE_URL, on java.
the line in the docs// Or configures using the `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, and `ANTHROPIC_BASE_URL` environment variables |
|
v2.1.307ANTHROPIC_AUTH_TOKEN |
Documentation arrivedA small documentation edit on csharp touched a line naming ANTHROPIC_AUTH_TOKEN after this was published.
the line in the docs// Configured using the ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, and ANTHROPIC_BASE_URL environment variables |
|
v2.1.307ANTHROPIC_BASE_URL |
Documentation arrivedA small documentation edit on csharp touched a line naming ANTHROPIC_BASE_URL after this was published.
the line in the docs// Configured using the ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, and ANTHROPIC_BASE_URL environment variables |
|
v2.1.307ANTHROPIC_API_KEY |
Documentation arrivedA small documentation edit on csharp touched a line naming ANTHROPIC_API_KEY after this was published.
the line in the docs// Configured using the ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, and ANTHROPIC_BASE_URL environment variables |
|
v2.1.295budgetTokens |
Documentation arrivedAnthropic's documentation has since written up budgetTokens, on claude-prompting-best-practices.
the line in the docs.budgetTokens(10000L) |
|
v2.1.299new_str |
Documentation arrivedAnthropic's documentation has since written up new_str, on text-editor-tool.
the line in the docs"new_str", |
|
v2.1.307ANTHROPIC_API_KEY |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_API_KEY, on Process results programmatically.
the line in the docs-H "x-api-key: $ANTHROPIC_API_KEY" \ |
|
v2.1.307/mcp |
Documentation arrivedA small documentation edit on quickstart touched a line naming /mcp after this was published.
the line in the docsThis quickstart takes you from creating a tunnel to Claude calling a private MCP server through it. It uses Docker Compose with [manual](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/concepts#credential-provisioning) cre… |
|
v2.1.307/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Mods reference.
the line in the docs| [`Box`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `key`, flex layout, [`gap`, `padding`, `margin`](#box-spacing-steps), `width`, `height`, `minWidth`, `minHeight`, [`borderStyle`](#box-border-styles), `borderColor`, `… |
|
v2.1.307/clear |
Documentation arrivedA small documentation edit on Use Claude Code in the cloud touched a line naming /clear after this was published.
the line in the docs| `/clear` | Yes | Starts a fresh conversation with empty context in the same cloud session | |
|
v2.1.307--settings |
Documentation arrivedAnthropic's documentation has since written up --settings, on Orchestrate teams of Claude Code sessions.
the line in the docs* **`--allowedTools`**: Claude Code doesn't pass this flag to a split-pane teammate, so an action you allowed with it alone isn't pre-approved there. To approve those actions ahead of time, put the rules under `permissions.allow` in [`--se… |
|
v2.1.307PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Claude Code changelog.
the line in the docs* Fixed hooks that run in PowerShell not blocking when the hook's program exits with code 2, and on Windows `PreToolUse` and `PermissionRequest` hooks with `"shell": "powershell"` failing open when Git for Windows isn't installed |
|
v2.1.307PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Claude Code changelog.
the line in the docs* Fixed hooks that run in PowerShell not blocking when the hook's program exits with code 2, and on Windows `PreToolUse` and `PermissionRequest` hooks with `"shell": "powershell"` failing open when Git for Windows isn't installed |
|
v2.1.304PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Claude Code changelog.
the line in the docs* Fixed hooks that run in PowerShell not blocking when the hook's program exits with code 2, and on Windows `PreToolUse` and `PermissionRequest` hooks with `"shell": "powershell"` failing open when Git for Windows isn't installed |
|
v2.1.307PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Claude Code changelog.
the line in the docs* Fixed hooks that run in PowerShell not blocking when the hook's program exits with code 2, and on Windows `PreToolUse` and `PermissionRequest` hooks with `"shell": "powershell"` failing open when Git for Windows isn't installed |
|
v2.1.305--tools |
Documentation arrivedAnthropic's documentation has since written up --tools, on Claude Code changelog.
the line in the docs* Fixed split-pane agent teammates not inheriting the tool deny and `--tools` rules given on the leader's command line |
|
v2.1.295claude-haiku-4-5-20251001 |
Documentation arrivedA small documentation edit on handling-stop-reasons touched a line naming claude-haiku-4-5-20251001 after this was published.
the line in the docsIf you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) or Claude Opus 4.1 (the latter [retired, except on Bedrock and Claude Mode… |
|
v2.1.281egressProxyUrl |
Documentation arrivedA small documentation edit on Network proxy touched a line naming egressProxyUrl after this was published.
the line in the docsIn a macOS configuration profile the same key is a `<key>egressProxyUrl</key><string>http://proxy.example.com:8080</string>` pair in the `com.anthropic.claudefordesktop` payload, and on Windows it is a `REG_SZ` value named `egressProxyUrl`… |
|
v2.1.288modelOverrides |
Documentation arrivedA small documentation edit on Model configuration touched a line naming modelOverrides after this was published.
the line in the docs* **Not recognized**: any other ID, such as an application inference profile ARN or a model version Claude Code doesn't know, unless a [`modelOverrides`](#override-model-ids-per-version) entry maps a model to that ID. On Microsoft Foundry,… |
|
v2.1.283modelOverrides |
Documentation arrivedA small documentation edit on Model configuration touched a line naming modelOverrides after this was published.
the line in the docs* **Not recognized**: any other ID, such as an application inference profile ARN or a model version Claude Code doesn't know, unless a [`modelOverrides`](#override-model-ids-per-version) entry maps a model to that ID. On Microsoft Foundry,… |
|
v2.1.295disableAllHooks |
Documentation arrivedAnthropic's documentation has since written up disableAllHooks, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code.md#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them … |
|
v2.1.287/plugin directory |
Documentation arrivedAnthropic's documentation has since written up /plugin directory, on Plugin feature support across platforms.
the line in the docs| Browse the directory | **Discover** in **Customize > Plugins**, on Pro, Max, Team, and Enterprise plans. On Team and Enterprise plans, an Owner can [remove the directory as a source](/docs/plugins/admin.md#manage-synced-marketplaces) for… |
|
v2.1.285disableWorkflows |
Documentation arrivedAnthropic's documentation has since written up disableWorkflows, on Orchestrate subagents at scale with dynamic workflows.
the line in the docsTo turn workflows off for your whole organization, set `"disableWorkflows": true` in [managed settings](/docs/en/server-managed-settings.md), or use the toggle on the [Claude Code admin settings](https://claude.ai/admin-settings/claude-cod… |
|
v2.1.305--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Use Claude Code in VS Code.
the line in the docsInstalling the extension does not put `claude` on your shell PATH. The extension bundles a private copy of the CLI for its chat panel, but typing `claude` in a terminal requires the [standalone CLI install](/docs/en/setup.md). Run the inst… |
|
v2.1.288modelSettings |
Documentation arrivedAnthropic's documentation has since written up modelSettings, on Use Claude Code in VS Code.
the line in the docsWhen the current model supports [effort levels](/docs/en/model-config.md#adjust-effort-level), the picker also shows an **Effort** row and the model name button shows the selected level. When you pick a level other than `max`, Claude Code … |
|
v2.1.293managedMcpServers |
Documentation arrivedA small documentation edit on All settings touched a line naming managedMcpServers after this was published.
the line in the docsServers your organization delivers are also exempt from the allowlist, and the denylist still applies to them. The exemption covers every [`managedMcpServers`](#managedmcpservers) entry, and any [`managed-mcp.json`](/docs/en/managed-mcp#ex… |
|
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… |