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 |
|---|---|---|
v2.1.283AskUserQuestion |
Documentation arrivedAnthropic's documentation has since written up AskUserQuestion, on Hooks reference.
the line in the docs| `permissionDecision` | `"allow"` skips the permission prompt, except for the [actions no mode auto-approves](/docs/en/permission-modes#actions-no-mode-auto-approves) and for `AskUserQuestion` and `ExitPlanMode`, which need [`updatedInput… |
|
v2.1.280run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Hooks reference.
the line in the docs| `run_in_background` | boolean | `false` | Whether to run the command in background | |
|
v2.1.257run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Hooks reference.
the line in the docs| `run_in_background` | boolean | `false` | Whether to run the command in background | |
|
v2.1.257allowedEnvVars |
Documentation arrivedAnthropic's documentation has since written up allowedEnvVars, on Hooks reference.
the line in the docs| `headers` | no | Additional HTTP headers as key-value pairs. Values support environment variable interpolation using `$VAR_NAME` or `${VAR_NAME}` syntax. Only variables listed in `allowedEnvVars` are resolved | |
|
v2.1.269mcp__memory__ |
Documentation arrivedAnthropic's documentation has since written up mcp__memory__, on Hooks reference.
the line in the docs| Contains any other character | JavaScript regular expression, unanchored | `^Notebook` matches any tool whose name starts with `Notebook`; `mcp__memory__.*` matches every tool from the `memory` server | |
|
v2.1.280register_repo_root |
Documentation arrivedAnthropic's documentation has since written up register_repo_root, on Hooks reference.
the line in the docs| `DirectoryAdded` | When a working directory is added mid-session via `/add-dir` or the SDK `register_repo_root` control request | |
|
v2.1.280claude --cloud |
Documentation arrivedAnthropic's documentation has since written up claude --cloud, on Claude Code with GitHub Enterprise Server.
the line in the docs| Cloud sessions | ✅ Supported | An Owner connects the GHES instance once; developers use `claude --cloud` or [claude.ai/code](https://claude.ai/code) as usual | |
|
v2.1.283otelHeadersHelper |
Documentation arrivedAnthropic's documentation has since written up otelHeadersHelper, on Error reference.
the line in the docs| `otelHeadersHelper failed; telemetry is not being exported. See /status: ...` | [Configuration warnings](#otelheadershelper-failed) | |
|
v2.1.280CLAUDE_CODE_CHILD_SESSION |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_CHILD_SESSION, on Error reference.
the line in the docs| `Transcript saving is off — inherited CLAUDE_CODE_CHILD_SESSION marker` | [Session saving warnings](#transcript-saving-is-off-child-session-marker) | |
|
v2.1.283/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on Desktop application.
the line in the docs| `--resume`, `--continue` | Click a session in the sidebar, or type `/resume` in the prompt box to pick up a session you started from the CLI | |
|
v2.1.283DISABLE_TELEMETRY |
Documentation arrivedAnthropic's documentation has since written up DISABLE_TELEMETRY, on Data usage.
the line in the docs| **Metrics** | Default on.<br />`DISABLE_TELEMETRY=1` to disable. | Default off.<br />`CLAUDE_CODE_USE_VERTEX` must be 1. | Default off.<br />`CLAUDE_CODE_USE_BEDROCK` must be 1. | Default off.<br />`CLAUDE_CODE_USE_FOUNDRY` must be 1. | … |
|
v2.1.283forward_user_identity |
Documentation arrivedAnthropic's documentation has since written up forward_user_identity, on Claude apps gateway deployment and operations.
the line in the docs| Identity (email, groups, sub) | IdP → gateway → JWT → CLI; the CLI stamps it on OTLP exports. If you turn on [`forward_user_identity`](/docs/en/claude-apps-gateway-config#per-user-identity-headers-for-a-proxy-you-run), the gateway also s… |
|
v2.1.278litellm |
Documentation arrivedAnthropic's documentation has since written up litellm, on Claude apps gateway configuration.
the line in the docs| `x-litellm-end-user-id` | The developer's email, when the IdP supplied one. | |
|
v2.1.283HTTP_PROXY |
Documentation arrivedAnthropic's documentation has since written up HTTP_PROXY, on Claude apps gateway configuration.
the line in the docs| `use_proxy` | No | Send the gateway's own IdP requests through the forward proxy in `HTTPS_PROXY` or `HTTP_PROXY`, honoring `NO_PROXY`. `false` keeps those requests direct. Requires v2.1.227 or later; see [IdP requests through a forward … |
|
v2.1.283managed.policies |
Documentation arrivedAnthropic's documentation has since written up managed.policies, on Claude apps gateway configuration.
the line in the docs| `google_groups` | No | Look up the signed-in user's groups through the Google Workspace Admin SDK Directory API, because Google's id\_token carries no groups claim. Set `service_account_json_path` to a service-account key file with domai… |
|
v2.1.281CLAUDE_GATEWAY_ALLOW_LOOPBACK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_ALLOW_LOOPBACK, on Claude apps gateway configuration.
the line in the docs| `issuer` | Yes | OIDC discovery base. Must serve discovery at `/.well-known/openid-configuration`. Use HTTPS in production; the gateway accepts an `http://` issuer. A loopback issuer such as `http://localhost:8081` is rejected by the [SS… |
|
v2.1.277/design-login |
Documentation arrivedAnthropic's documentation has since written up /design-login, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs| [`/design-sync`](/docs/en/commands#all-commands) and `/design-login` | Not available | Both need claude.ai, which the CLI doesn't contact on gateway sessions, so neither command appears there | |
|
v2.1.277/design-login |
Documentation arrivedAnthropic's documentation has since written up /design-login, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs| [`/design-sync`](/docs/en/commands#all-commands) and `/design-login` | Not available | Both need claude.ai, which the CLI doesn't contact on gateway sessions, so neither command appears there | |
|
v2.1.271/design-login |
Documentation arrivedAnthropic's documentation has since written up /design-login, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs| [`/design-sync`](/docs/en/commands#all-commands) and `/design-login` | Not available | Both need claude.ai, which the CLI doesn't contact on gateway sessions, so neither command appears there | |
|
v2.1.271/design-sync |
Documentation arrivedAnthropic's documentation has since written up /design-sync, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs| [`/design-sync`](/docs/en/commands#all-commands) and `/design-login` | Not available | Both need claude.ai, which the CLI doesn't contact on gateway sessions, so neither command appears there | |
|
v2.1.277NO_PROXY |
Documentation arrivedAnthropic's documentation has since written up NO_PROXY, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs| Private-network address | At `/login`, Claude Code requires the gateway's hostname or IP address to resolve only to private addresses: RFC 1918, link-local, CGNAT `100.64.0.0/10`, IPv6 ULA `fc00::/7`, or loopback. For a gateway you host,… |
|
v2.1.277severity |
Documentation arrivedAnthropic's documentation has since written up severity, on Channels reference.
the line in the docs| `meta` | `Record<string, string>` | Optional. Each entry becomes an attribute on the `<channel>` tag for routing context like chat ID, sender name, or alert severity. Keys must be identifiers: letters, digits, and underscores only. Keys … |
|
v2.1.271ANTHROPIC_ORGANIZATION_ID |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_ORGANIZATION_ID, on Authentication.
the line in the docs| Federation variables | `ANTHROPIC_FEDERATION_RULE_ID` and `ANTHROPIC_ORGANIZATION_ID`, both set | Above | |
|
v2.1.271ANTHROPIC_FEDERATION_RULE_ID |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_FEDERATION_RULE_ID, on Authentication.
the line in the docs| Federation variables | `ANTHROPIC_FEDERATION_RULE_ID` and `ANTHROPIC_ORGANIZATION_ID`, both set | Above | |
|
v2.1.281WorktreeCreate |
Documentation arrivedAnthropic's documentation has since written up WorktreeCreate, on Manage multiple agents with agent view.
the line in the docs| v2.1.203 | A gateway `ANTHROPIC_BASE_URL` exported in the dispatching shell reaches the sessions dispatched from it into that same directory when the supervisor shares that gateway environment, instead of being dropped while the API key … |
|
v2.1.277highlights |
Documentation arrivedAnthropic's documentation has since written up highlights, on Manage multiple agents with agent view.
the line in the docs| v2.1.225 | `claude agents` in a directory you haven't trusted shows the same [workspace trust dialog](/docs/en/permissions#project-allow-rules-and-workspace-trust) that `claude` shows on startup, before agent view opens. Accepting saves … |
|
v2.1.257daemon.lock |
Documentation arrivedAnthropic's documentation has since written up daemon.lock, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | Starting the [background service](#the-supervisor-process) recovers from two failure causes. On a macOS npm installation, a start during a self-update [waits for the install](/docs/en/errors#eacces-when-starting-a-background-s… |
|
v2.1.257agents:togglePin |
Documentation arrivedAnthropic's documentation has since written up agents:togglePin, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.257agents:togglePin |
Documentation arrivedAnthropic's documentation has since written up agents:togglePin, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.257agents:togglePin |
Documentation arrivedAnthropic's documentation has since written up agents:togglePin, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.257agents:switchView |
Documentation arrivedAnthropic's documentation has since written up agents:switchView, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.257agents:switchView |
Documentation arrivedAnthropic's documentation has since written up agents:switchView, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.257agents:switchView |
Documentation arrivedAnthropic's documentation has since written up agents:switchView, on Manage multiple agents with agent view.
the line in the docs| v2.1.257 | `Ctrl+S`, `Ctrl+T`, and `Ctrl+G` in agent view [follow your `keybindings.json`](#keyboard-shortcuts): `Ctrl+S` and `Ctrl+T` through the `Agents` context's `agents:switchView` and `agents:togglePin` actions, and `Ctrl+G` throug… |
|
v2.1.283claude daemon |
Documentation arrivedAnthropic's documentation has since written up claude daemon, on Manage multiple agents with agent view.
the line in the docs| `claude daemon status` | Print the [supervisor's](#the-supervisor-process) state, version, socket directory, and worker count | |
|
v2.1.283--plugin-dir |
Documentation arrivedAnthropic's documentation has since written up --plugin-dir, on Manage multiple agents with agent view.
the line in the docs| [`--plugin-dir <path>`](/docs/en/plugins/create#load-a-directory-or-archive-for-one-session) | Load a plugin from a local directory | |
|
v2.1.280readMcpResource |
Documentation arrivedAnthropic's documentation has since written up readMcpResource, on Agent SDK reference - TypeScript.
the line in the docs| `readMcpResource(serverName, uri)` | *Alpha.* Reads one MCP Apps `ui://` resource from a connected MCP server so your application can render a tool's widget. Resolves with an [`SDKControlMcpReadResourceResponse`](#sdkcontrolmcpreadresour… |
|
v2.1.259permissionPrompts |
Documentation arrivedAnthropic's documentation has since written up permissionPrompts, on Agent SDK reference - TypeScript.
the line in the docs| `permissionPrompts` | `'host' \| 'none'` | `'host'` | Who answers permission prompts: `'host'` routes them to your [`canUseTool`](#canusetool) callback or the `permissionPromptToolName` tool, and `'none'` [denies the calls that would hav… |
|
v2.1.281CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, on Agent SDK reference - TypeScript.
the line in the docs| `managedSettings` | `Settings` | `undefined` | Policy-tier settings your host process supplies to the spawned session. On machines with admin-deployed managed settings, Claude Code ignores these unless the admin's highest-priority manage… |
|
v2.1.283fallbackModel |
Documentation arrivedAnthropic's documentation has since written up fallbackModel, on Agent SDK reference - TypeScript.
the line in the docs| `fallbackModel` | `string` | `undefined` | Model to use if the primary model fails. Accepts a comma-separated list. For the order and the cap, see [Fallback model chains](/docs/en/model-config#fallback-model-chains). For guidance, see [C… |
|
v2.1.280agentId |
Documentation arrivedAnthropic's documentation has since written up agentId, on Agent SDK reference - TypeScript.
the line in the docs| `parent_agent_id` | `string \| null` | For messages from a [nested subagent](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents), the `agentId` of the subagent that spawned it. `null` for main-session messages, messages from top… |
|
v2.1.280agentId |
Documentation arrivedAnthropic's documentation has since written up agentId, on Agent SDK reference - TypeScript.
the line in the docs| `parent_agent_id` | `string \| null` | For messages from a [nested subagent](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents), the `agentId` of the subagent that spawned it. `null` for main-session messages, messages from top… |
|
v2.1.275CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS, on Subagents in the SDK.
the line in the docs| Concurrency | [`CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS`](/docs/en/env-vars) | `20` subagents running at once, counting every subagent Claude spawns with the Agent tool | Refuses to spawn another subagent, returning `Concurrent subagent lim… |
|
v2.1.282sandbox.excludedCommands |
Documentation arrivedAnthropic's documentation has since written up sandbox.excludedCommands, on Agent SDK reference - Python.
the line in the docs| `excludedCommands` | `list[str]` | `[]` | Commands that bypass sandbox restrictions, such as `["docker *"]`. These run unsandboxed automatically without model involvement; [`sandbox.excludedCommands`](/docs/en/settings-reference#sandbox-… |
|
v2.1.282sandbox.excludedCommands |
Documentation arrivedAnthropic's documentation has since written up sandbox.excludedCommands, on Agent SDK reference - Python.
the line in the docs| `excludedCommands` | `list[str]` | `[]` | Commands that bypass sandbox restrictions, such as `["docker *"]`. These run unsandboxed automatically without model involvement; [`sandbox.excludedCommands`](/docs/en/settings-reference#sandbox-… |
|
v2.1.282sandbox.excludedCommands |
Documentation arrivedAnthropic's documentation has since written up sandbox.excludedCommands, on Agent SDK reference - Python.
the line in the docs| `excludedCommands` | `list[str]` | `[]` | Commands that bypass sandbox restrictions, such as `["docker *"]`. These run unsandboxed automatically without model involvement; [`sandbox.excludedCommands`](/docs/en/settings-reference#sandbox-… |
|
v2.1.283mantle |
Documentation arrivedAnthropic's documentation has since written up mantle, on Agent SDK reference - Python.
the line in the docs| `provider` | `str` | API provider that served this model, such as `firstParty`, `bedrock`, `vertex`, `foundry`, `anthropicAws`, `mantle`, or `gateway`. Not always present. | |
|
v2.1.257thinkingTokens |
Documentation arrivedAnthropic's documentation has since written up thinkingTokens, on Agent SDK reference - Python.
the line in the docs| `thinkingTokens` | `int` | Thinking tokens generated by this model, already counted in `outputTokens`. Absent until a turn runs on a Claude Code version that records it, and not declared on the TypedDict, so read it with `.get()`. Requir… |
|
v2.1.281setMode |
Documentation arrivedAnthropic's documentation has since written up setMode, on Agent SDK reference - Python.
the line in the docs| `mode` | `PermissionMode \| None` | Mode for setMode operation | |
|
v2.1.283max_thinking_tokens |
Documentation arrivedAnthropic's documentation has since written up max_thinking_tokens, on Agent SDK reference - Python.
the line in the docs| `max_thinking_tokens` | `int \| None` | `None` | *Deprecated* - Maximum tokens for thinking blocks. Use `thinking` instead | |
|
v2.1.281set_model |
Documentation arrivedAnthropic's documentation has since written up set_model, on Agent SDK reference - Python.
the line in the docs| `set_model(model)` | Change the model for the current session. Pass `None` to reset to [Claude Code's default model](/docs/en/model-config) | |