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 |
|---|---|---|
v2.1.299/sandbox |
Documentation arrivedAnthropic's documentation has since written up /sandbox, on Error reference.
the line in the docs* To sandbox the sessions the server starts, turn on [sandboxing](/docs/en/sandboxing) by setting [`sandbox.enabled`](/docs/en/settings-reference#sandbox-enabled) to `true` in a [settings file](/docs/en/settings#where-settings-live) |
|
v2.1.299/sandbox |
Documentation arrivedAnthropic's documentation has since written up /sandbox, on Error reference.
the line in the docs* To sandbox the sessions the server starts, turn on [sandboxing](/docs/en/sandboxing) by setting [`sandbox.enabled`](/docs/en/settings-reference#sandbox-enabled) to `true` in a [settings file](/docs/en/settings#where-settings-live) |
|
v2.1.300claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Error reference.
the line in the docs| `--sandbox is not supported by claude remote-control` / `--no-sandbox is not supported by claude remote-control` | [Command-line errors](#sandbox-is-not-supported-by-claude-remote-control) | |
|
v2.1.300claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Error reference.
the line in the docs| `--sandbox is not supported by claude remote-control` / `--no-sandbox is not supported by claude remote-control` | [Command-line errors](#sandbox-is-not-supported-by-claude-remote-control) | |
|
v2.1.292prompt.suggest |
Documentation arrivedAnthropic's documentation has since written up prompt.suggest, on Draw in the interface with a mod.
the line in the docs* **Prompt suggestions**: `$.prompt.suggest` resolves with `isShown: false` and shows nothing, because the panel keeps the prompt box's dim suggestion text for Claude's own suggestions. |
|
v2.1.275prompt.suggest |
Documentation arrivedAnthropic's documentation has since written up prompt.suggest, on Draw in the interface with a mod.
the line in the docs* **Prompt suggestions**: `$.prompt.suggest` resolves with `isShown: false` and shows nothing, because the panel keeps the prompt box's dim suggestion text for Claude's own suggestions. |
|
v2.1.299/code |
Documentation arrivedAnthropic's documentation has since written up /code, on Configuration reference.
the line in the docsApplies only to **tool calls**, in Cowork, Code and Chat. In Cowork it covers the sandbox's web fetch, shell commands and package installs. In Chat it covers web fetch and commands in the file-analysis sandbox. In Code it's [translated int… |
|
v2.1.292api_error |
Documentation arrivedAnthropic's documentation has since written up api_error, on Configure a custom OpenTelemetry collector.
the line in the docs| `office_agent.api_error` | Each model call that is refused, fails, is cut off, or that the user stops | |
|
v2.1.292api_error |
Documentation arrivedAnthropic's documentation has since written up api_error, on Configure a custom OpenTelemetry collector.
the line in the docs| `office_agent.api_error` | Each model call that is refused, fails, is cut off, or that the user stops | |
|
v2.1.285api_error |
Documentation arrivedAnthropic's documentation has since written up api_error, on Configure a custom OpenTelemetry collector.
the line in the docs| `office_agent.api_error` | Each model call that is refused, fails, is cut off, or that the user stops | |
|
v2.1.299user.email |
Documentation arrivedAnthropic's documentation has since written up user.email, on Configure a custom OpenTelemetry collector.
the line in the docsrecords also name the signed-in member as `user.email` and |
|
v2.1.299edits |
Documentation arrivedA small documentation edit on User identity and local data touched a line naming edits after this was published.
the line in the docs[Chat](/docs/third-party/claude-desktop/chat) conversations follow the same storage model as Cowork sessions: each conversation is a session state file plus a working directory under `local-agent-mode-sessions/`, in the layout described in… |
|
v2.1.299edits |
Documentation arrivedA small documentation edit on User identity and local data touched a line naming edits after this was published.
the line in the docs[Chat](/docs/third-party/claude-desktop/chat) conversations follow the same storage model as Cowork sessions: each conversation is a session state file plus a working directory under `local-agent-mode-sessions/`, in the layout described in… |
|
v2.1.300/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Chat in Claude Desktop on 3P.
the line in the docsCommands that Claude runs in the advanced file analysis sandbox can reach the hosts in [`coworkEgressAllowedHosts`](/docs/third-party/claude-desktop/configuration#coworkegressallowedhosts). A command-line tool that a [plugin](/docs/third-p… |
|
v2.1.299shell |
Documentation arrivedAnthropic's documentation has since written up shell, on Chat in Claude Desktop on 3P.
the line in the docs* **Run code on the host.** There is no shell access. With advanced file analysis off (the default), the sandbox VM is never started for Chat; with it on, code runs only inside the sandbox described under [Advanced file analysis](#advanced… |
|
v2.1.299/env |
Documentation arrivedAnthropic's documentation has since written up /env, on claude-platform-on-aws-iam-actions.
the line in the docs| `POST` | `/v1/environments` | `CreateEnvironment` | Data | |
|
v2.1.299/model |
Documentation arrivedAnthropic's documentation has since written up /model, on claude-platform-on-aws-iam-actions.
the line in the docs| `GET` | `/v1/models` | `ListModels` | Data | |
|
v2.1.299/model |
Documentation arrivedAnthropic's documentation has since written up /model, on claude-platform-on-aws-iam-actions.
the line in the docs| `GET` | `/v1/models` | `ListModels` | Data | |
|
v2.1.299PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Orchestrate subagents at scale with dynamic workflows.
the line in the docs* **A hook**: return `"allow"` for the call from a [`PreToolUse`](/docs/en/hooks#pretooluse) hook. In [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), the workflow doesn't start on the hook's approval alone, s… |
|
v2.1.299PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Orchestrate subagents at scale with dynamic workflows.
the line in the docs* **A hook**: return `"allow"` for the call from a [`PreToolUse`](/docs/en/hooks#pretooluse) hook. In [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), the workflow doesn't start on the hook's approval alone, s… |
|
v2.1.290--bare |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --bare after this was published.
the line in the docsAdd `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), installed plugins, MCP servers, auto memory, and CLAUDE.md. Without it, `claude -p` discovers and loads the… |
|
v2.1.290--bare |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --bare after this was published.
the line in the docsAdd `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), installed plugins, MCP servers, auto memory, and CLAUDE.md. Without it, `claude -p` discovers and loads the… |
|
v2.1.286--bare |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --bare after this was published.
the line in the docsAdd `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), installed plugins, MCP servers, auto memory, and CLAUDE.md. Without it, `claude -p` discovers and loads the… |
|
v2.1.281--tmux |
Documentation arrivedAnthropic's documentation has since written up --tmux, on Claude Code changelog.
the line in the docs- Fixed plugin `WorktreeCreate` and `WorktreeRemove` hooks not running when Claude Code starts with `--worktree` (not yet with `--tmux`) |
|
v2.1.281--tmux |
Documentation arrivedAnthropic's documentation has since written up --tmux, on Claude Code changelog.
the line in the docs- Fixed plugin `WorktreeCreate` and `WorktreeRemove` hooks not running when Claude Code starts with `--worktree` (not yet with `--tmux`) |
|
v2.1.281--tmux |
Documentation arrivedAnthropic's documentation has since written up --tmux, on Claude Code changelog.
the line in the docs- Fixed plugin `WorktreeCreate` and `WorktreeRemove` hooks not running when Claude Code starts with `--worktree` (not yet with `--tmux`) |
|
v2.1.296forceLoginGatewayUrl |
Documentation arrivedAnthropic's documentation has since written up forceLoginGatewayUrl, on Claude Code changelog.
the line in the docs* Changed Claude Desktop's Code tab to apply managed settings when `forceLoginGatewayUrl` names an Anthropic-operated gateway that serves the session's hostname; that gateway must be reachable at start |
|
v2.1.281CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, on Claude Code changelog.
the line in the docs* Changed `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` sessions to ignore CA-bundle, tool-proxy, git TLS and git config variables like `SSL_CERT_FILE` in settings; under Claude Desktop, only in project settings |
|
v2.1.275SSL_CERT_FILE |
Documentation arrivedAnthropic's documentation has since written up SSL_CERT_FILE, on Claude Code changelog.
the line in the docs* Changed `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` sessions to ignore CA-bundle, tool-proxy, git TLS and git config variables like `SSL_CERT_FILE` in settings; under Claude Desktop, only in project settings |
|
v2.1.280Restart |
Documentation arrivedA small documentation edit on Deploy with Enterprise Admin Console touched a line naming Restart after this was published.
the line in the docsSetting `status` to `disabled` stops serving the configuration to users' apps, as if none had been saved. A running app isn't interrupted. At its next launch it shows a **Restart required** prompt whose **Restart** button returns the devic… |
|
v2.1.296autoCompactWindow |
Documentation arrivedAnthropic's documentation has since written up autoCompactWindow, on Create custom subagents.
the line in the docs* **[Frontmatter fields](#supported-frontmatter-fields)**: `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `autoCompactWindow`, `skills`, `initialPrompt`, `memory`, `effort`, `backgr… |
|
v2.1.296autoCompactWindow |
Documentation arrivedA small documentation edit on Subagents in the SDK touched a line naming autoCompactWindow after this was published.
the line in the docs| `autoCompactWindow` | `number` | No | Lower the [auto-compact window](/docs/en/sub-agents#subagent-auto-compact-window) for this agent when it runs as a subagent, to a token count from `100000` to `1000000`. Requires TypeScript Agent SDK… |
|
v2.1.290CLAUDE_CODE_DISABLE_ATTACHMENTS |
Documentation arrivedA small documentation edit on Modifying system prompts touched a line naming CLAUDE_CODE_DISABLE_ATTACHMENTS after this was published.
the line in the docsIf you set `CLAUDE_CODE_DISABLE_ATTACHMENTS`, Claude Code also sends `@` file mentions as plain text instead of expanding them into file content. The list of available subagents and background task notifications still arrive. To stop only … |
|
v2.1.296asyncRewake |
Documentation arrivedAnthropic's documentation has since written up asyncRewake, on Error reference.
the line in the docsThis notification in the conversation view means a hook's script didn't run because its path has a space and isn't quoted. That hook is an [`asyncRewake`](/docs/en/hooks#run-hooks-in-the-background) hook in shell form. In its `command`, an… |
|
v2.1.285maxTurns |
Documentation arrivedAnthropic's documentation has since written up maxTurns, on migration.
the line in the docs| `max_turns` (typescript: `maxTurns`) | Count turns client-side. | |
|
v2.1.285maxTurns |
Documentation arrivedAnthropic's documentation has since written up maxTurns, on migration.
the line in the docs| `max_turns` (typescript: `maxTurns`) | Count turns client-side. | |
|
v2.1.295claude-haiku-4-5-20251001 |
Documentation arrivedAnthropic's documentation has since written up claude-haiku-4-5-20251001, on claude-platform-on-aws.
the line in the docs| **Model IDs** | anthropic.claude-haiku-4-5 | anthropic.claude-haiku-4-5-20251001-v1:0(with a `us.` or `global.` inference profile prefix) | claude-haiku-4-5 | |
|
v2.1.295count_tokens |
Documentation arrivedA small documentation edit on advisor-tool touched a line naming count_tokens after this was published.
the line in the docs| [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) | Returns the executor's first-iteration input tokens only. For a rough advisor estimate, call `client.beta.messages.count_tokens()` (typescript: `cli… |
|
v2.1.296forceLoginMethod |
Documentation arrivedAnthropic's documentation has since written up forceLoginMethod, on Claude Code changelog.
the line in the docs* Fixed `forceLoginOrgUUID` and `forceLoginMethod` from MDM or the managed-settings file being hidden or replaced by server-managed settings |
|
v2.1.295--mcp-config |
Documentation arrivedAnthropic's documentation has since written up --mcp-config, on Claude Code changelog.
the line in the docs* Fixed self-hosted runner sessions shutting down MCP servers added through an `--exec-path` wrapper's own `--mcp-config` when connectors change mid-session |
|
v2.1.296prompt.submit |
Documentation arrivedAnthropic's documentation has since written up prompt.submit, on Claude Code changelog.
the line in the docs* Added `$.prompt.media` so a `prompt.submit` hook of a mod installed by managed settings can read the bytes of an image or document attached to the prompt |
|
v2.1.285disableBundledSkills |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming disableBundledSkills after this was published.
the line in the docsThe [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable or a [`skillOverrides`](#override-skill-visibility-from-settin… |
|
v2.1.296skillOverrides |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming skillOverrides after this was published.
the line in the docsThe [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable or a [`skillOverrides`](#override-skill-visibility-from-settin… |
|
v2.1.285skillOverrides |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming skillOverrides after this was published.
the line in the docsThe [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable or a [`skillOverrides`](#override-skill-visibility-from-settin… |
|
v2.1.295--effort |
Documentation arrivedAnthropic's documentation has since written up --effort, on All settings.
the line in the docs* **Per-session overrides**: `/effort ultracode` turns ultracode on for one session without this key, and `/effort ultracode off` turns it off for one session when this key is `true`. The `--effort ultracode` flag also turns it on for one … |
|
v2.1.292/workflows |
Documentation arrivedA small documentation edit on Monitoring touched a line naming /workflows after this was published.
the line in the docs* `workflow.run_id`: run identifier, prefixed `wf_`, on the API and tool events emitted by agents that belong to a [Workflow](/docs/en/workflows) tool run. Filtering events by one `workflow.run_id` reconstructs that run's API requests and … |
|
v2.1.290/doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor after this was published.
the line in the docsThe [`/doctor`](/docs/en/commands#all-commands) checkup proposes trims for a checked-in CLAUDE.md: it cuts content Claude can derive from the codebase, such as directory layouts, dependency lists, and architecture overviews, and keeps pitf… |
|
v2.1.287ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming ANTHROPIC_CUSTOM_HEADERS after this was published.
the line in the docsFor a gateway that injects its own `Authorization` header, set `CLAUDE_CODE_SKIP_FOUNDRY_AUTH=1` and leave both credential variables unset. Claude Code then sends requests without an Azure credential and preserves the `Authorization` heade… |
|
v2.1.287ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming ANTHROPIC_CUSTOM_HEADERS after this was published.
the line in the docsFor a gateway that injects its own `Authorization` header, set `CLAUDE_CODE_SKIP_FOUNDRY_AUTH=1` and leave both credential variables unset. Claude Code then sends requests without an Azure credential and preserves the `Authorization` heade… |
|
v2.1.284extensions.worktreeConfig |
Documentation arrivedA small documentation edit on Set up Claude Code in a monorepo or large codebase touched a line naming extensions.worktreeConfig after this was published.
the line in the docsSparse checkout requires git to enable `extensions.worktreeConfig` in the repository's shared `.git/config` while a sparse worktree exists. Claude Code removes that entry after the last worktree is removed, but only if Claude Code added it… |