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 |
|---|---|---|
v2.1.287extraKnownMarketplaces |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming extraKnownMarketplaces after this was published.
the line in the docsIf a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), Claude Code's attempt to add it at startup fails the same way, and the message appears on the **Errors** tab … |
|
v2.1.286extraKnownMarketplaces |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming extraKnownMarketplaces after this was published.
the line in the docsIf a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), Claude Code's attempt to add it at startup fails the same way, and the message appears on the **Errors** tab … |
|
v2.1.282extraKnownMarketplaces |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming extraKnownMarketplaces after this was published.
the line in the docsIf a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), Claude Code's attempt to add it at startup fails the same way, and the message appears on the **Errors** tab … |
|
v2.1.296prompt.submit |
Documentation arrivedA small documentation edit on Mods reference touched a line naming prompt.submit after this was published.
the line in the docsWhen another mod's hook calls a method on a namespace you added in `engine.create`, your method's `$` calls run in that hook's context until every hook on that event returns. For example, a relative path resolves against that hook's workin… |
|
v2.1.269prompt.submit |
Documentation arrivedA small documentation edit on Mods reference touched a line naming prompt.submit after this was published.
the line in the docsWhen another mod's hook calls a method on a namespace you added in `engine.create`, your method's `$` calls run in that hook's context until every hook on that event returns. For example, a relative path resolves against that hook's workin… |
|
v2.1.269prompt.submit |
Documentation arrivedA small documentation edit on Mods reference touched a line naming prompt.submit after this was published.
the line in the docsWhen another mod's hook calls a method on a namespace you added in `engine.create`, your method's `$` calls run in that hook's context until every hook on that event returns. For example, a relative path resolves against that hook's workin… |
|
v2.1.280ui:// |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming ui:// after this was published.
the line in the docs* A tool whose `tools/list` entry declares an [MCP Apps `ui://` resource](#mcpserverstatus) has a limit of 8,388,608 characters on Claude Code v2.1.295 or later, and versions before v2.1.295 exempt it. |
|
v2.1.280ui:// |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming ui:// after this was published.
the line in the docs* A tool whose `tools/list` entry declares an [MCP Apps `ui://` resource](#mcpserverstatus) has a limit of 8,388,608 characters on Claude Code v2.1.295 or later, and versions before v2.1.295 exempt it. |
|
v2.1.295structuredContent |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming structuredContent after this was published.
the line in the docs* An MCP tool whose `structuredContent` serializes to more than 1,048,576 characters of JSON: Claude Code leaves `structuredContent` off `tool_use_result` and sets `structuredContentOmitted: true` in its place, so your application can tell… |
|
v2.1.290--worktree |
Documentation arrivedA small documentation edit on Run parallel sessions with worktrees touched a line naming --worktree after this was published.
the line in the docsAll of these apply whether you create the worktree with `--worktree` or with `git worktree add`. |
|
v2.1.290--worktree |
Documentation arrivedA small documentation edit on Run parallel sessions with worktrees touched a line naming --worktree after this was published.
the line in the docsAll of these apply whether you create the worktree with `--worktree` or with `git worktree add`. |
|
v2.1.284forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsIf a managed source sets an empty array, or a value that isn't a string or an array of strings, users who sign in with an Anthropic account can't start Claude Code or complete a login. They see a message that names `forceLoginOrgUUID` and … |
|
v2.1.281forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsIf a managed source sets an empty array, or a value that isn't a string or an array of strings, users who sign in with an Anthropic account can't start Claude Code or complete a login. They see a message that names `forceLoginOrgUUID` and … |
|
v2.1.281/cd |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming /cd after this was published.
the line in the docsTo move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps the conversation, loads the new directory's `CLAUDE.md`, an… |
|
v2.1.277/cd |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming /cd after this was published.
the line in the docsTo move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps the conversation, loads the new directory's `CLAUDE.md`, an… |
|
v2.1.277/cd |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming /cd after this was published.
the line in the docsTo move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps the conversation, loads the new directory's `CLAUDE.md`, an… |
|
v2.1.295CLAUDE.md |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming CLAUDE.md after this was published.
the line in the docsTo move the session to a different primary working directory, rather than [adding a directory](#working-directories) alongside the current one, run `/cd <path>`. Claude Code keeps the conversation, loads the new directory's `CLAUDE.md`, an… |
|
v2.1.290--resume |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --resume after this was published.
the line in the docsUse `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. On Claude Code v2.1.257 or later, when you pass `--continue`, Claude Code opens a [background session](/docs/en… |
|
v2.1.290--resume |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --resume after this was published.
the line in the docsUse `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. On Claude Code v2.1.257 or later, when you pass `--continue`, Claude Code opens a [background session](/docs/en… |
|
v2.1.290--resume |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --resume after this was published.
the line in the docsUse `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. On Claude Code v2.1.257 or later, when you pass `--continue`, Claude Code opens a [background session](/docs/en… |
|
v2.1.288--continue |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --continue after this was published.
the line in the docsUse `--continue` to continue the most recent conversation, or `--resume` with a session ID to continue a specific conversation. On Claude Code v2.1.257 or later, when you pass `--continue`, Claude Code opens a [background session](/docs/en… |
|
v2.1.296/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Manage multiple agents with agent view.
the line in the docsWithin [about a minute](#the-supervisor-process), run `claude agents` or `claude --bg` in your shell to start a fresh supervisor that reads your stored credentials. If you authenticate with an environment variable such as `ANTHROPIC_API_KE… |
|
v2.1.295/config |
Documentation arrivedA small documentation edit on All settings touched a line naming /config after this was published.
the line in the docsTurn off the [Artifact](/docs/en/artifacts) tool, which publishes session output as a private web page on claude.ai. When you turn the **Artifacts** row off in `/config`, Claude Code writes this key to your user settings, so you don't usua… |
|
v2.1.295/config |
Documentation arrivedA small documentation edit on All settings touched a line naming /config after this was published.
the line in the docsTurn off the [Artifact](/docs/en/artifacts) tool, which publishes session output as a private web page on claude.ai. When you turn the **Artifacts** row off in `/config`, Claude Code writes this key to your user settings, so you don't usua… |
|
v2.1.284authServerMetadataUrl |
Documentation arrivedAnthropic's documentation has since written up authServerMetadataUrl, on Connect Claude Code to tools via MCP.
the line in the docsWhen `oauth.scopes` isn't set, Claude Code doesn't request the full `scopes_supported` catalog from automatically discovered authorization server metadata. Metadata fetched from a configured `authServerMetadataUrl` still supplies its `scop… |
|
v2.1.288enableAllProjectMcpServers |
Documentation arrivedAnthropic's documentation has since written up enableAllProjectMcpServers, on Connect Claude Code to tools via MCP.
the line in the docs`claude mcp list` and `claude mcp get` read `.mcp.json` approvals only from settings files that aren't checked into the repository until you trust the workspace by running `claude` in it and accepting the workspace trust dialog. A cloned r… |
|
v2.1.281enabledMcpjsonServers |
Documentation arrivedAnthropic's documentation has since written up enabledMcpjsonServers, on Connect Claude Code to tools via MCP.
the line in the docs`claude mcp list` and `claude mcp get` read `.mcp.json` approvals only from settings files that aren't checked into the repository until you trust the workspace by running `claude` in it and accepting the workspace trust dialog. A cloned r… |
|
v2.1.296ANTHROPIC_BASE_URL |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming ANTHROPIC_BASE_URL after this was published.
the line in the docs[Remote Control](/docs/en/remote-control) and [voice dictation](/docs/en/voice-dictation) both rely on a claude.ai identity: Remote Control to pair a live session with your account, and voice dictation to reach the claude.ai transcription … |
|
v2.1.285ExitPlanMode |
Documentation arrivedA small documentation edit on Use Claude Code in VS Code touched a line naming ExitPlanMode after this was published.
the line in the docs* A [deny rule](/docs/en/permissions#manage-permissions) removes the [`ExitPlanMode`](/docs/en/tools-reference) tool |
|
v2.1.293skipDangerousModePermissionPrompt |
Documentation arrivedAnthropic's documentation has since written up skipDangerousModePermissionPrompt, on Choose a permission mode.
the line in the docs* With `skipDangerousModePermissionPrompt` set only in `.claude/settings.local.json`, the background session starts with the bypass request ignored and pins the notice `Bypass permissions was requested at launch and ignored · if that was y… |
|
v2.1.290blockReadsOutsideWorkingDirectories |
Documentation arrivedAnthropic's documentation has since written up blockReadsOutsideWorkingDirectories, on Choose a permission mode.
the line in the docsWhile [`permissions.blockReadsOutsideWorkingDirectories`](/docs/en/settings-reference#permissions-blockreadsoutsideworkingdirectories) is off, file reads other than [reads from network paths](/docs/en/permissions#network-paths) run without… |
|
v2.1.290PreCompact |
Documentation arrivedAnthropic's documentation has since written up PreCompact, on Hooks reference.
the line in the docsTo find a slow hook, search the log for `Hooks:` lines that end in a duration. In Claude Code v2.1.296 or later, each command hook on a tool event, `UserPromptSubmit`, `SessionStart`, `Stop`, and several other events leaves one when it fin… |
|
v2.1.295updatedInput |
Documentation arrivedAnthropic's documentation has since written up updatedInput, 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), for [reads from network paths](/docs/en/permissions#network-paths), an… |
|
v2.1.281permissions.allow |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming permissions.allow after this was published.
the line in the docs* **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs. Actions that need no approval in Manual mode still run, such as file reads in your working directories and the [read-only … |
|
v2.1.268permissions.allow |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming permissions.allow after this was published.
the line in the docs* **`dontAsk`**: Claude Code denies every call that would otherwise prompt, which is useful for locked-down CI runs. Actions that need no approval in Manual mode still run, such as file reads in your working directories and the [read-only … |
|
v2.1.290--allow-dangerously-skip-permissions |
Documentation arrivedAnthropic's documentation has since written up --allow-dangerously-skip-permissions, on Manage multiple agents with agent view.
the line in the docsDirectories you added during the session with [`/add-dir`](/docs/en/permissions#additional-directories-grant-file-access-not-configuration) also carry through. Carrying `--allow-dangerously-skip-permissions` keeps `bypassPermissions` reach… |
|
v2.1.268can_use_tool |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming can_use_tool after this was published.
the line in the docs| `allowed_tools` | `list[str]` | `[]` | Tools to auto-approve without prompting, apart from reads from [network paths](/docs/en/permissions#network-paths). This does not restrict Claude to only these tools. If you name one of the [task-tr… |
|
v2.1.293bypassPermissions |
Documentation arrivedAnthropic's documentation has since written up bypassPermissions, on Configure permissions.
the line in the docsCoverage depends on the entry's form: a bare name like `Read` or `mcp__github__get_issue` auto-approves every call to that tool apart from those exceptions and [reads from network paths](/docs/en/permissions#network-paths), while a scoped … |
|
v2.1.288permissionDecision |
Documentation arrivedA small documentation edit on Intercept and control agent behavior with hooks touched a line naming permissionDecision after this was published.
the line in the docsBy default, the agent may prompt for permission before using certain tools. This example auto-approves read-only filesystem tools (Read, Glob, Grep) by returning `permissionDecision: 'allow'`, letting them run without user confirmation, ap… |
|
v2.1.284CLAUDE_CODE_DISABLE_TERMINAL_TITLE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_TERMINAL_TITLE, on Configure your terminal for Claude Code.
the line in the docs* **[`CLAUDE_CODE_DISABLE_TERMINAL_TITLE`](/docs/en/env-vars#variables)**: if you set this variable to `1`, Claude Code doesn't check for support or report status. Unset it. |
|
v2.1.295/config |
Documentation arrivedAnthropic's documentation has since written up /config, on All settings.
the line in the docsMake [`/copy`](/docs/en/commands) copy the full response every time, without showing the picker. Selecting **Always copy full response** in that picker sets this key to `true`. Appears in `/config` as **Skip the /copy picker**. |
|
v2.1.295/config |
Documentation arrivedAnthropic's documentation has since written up /config, on All settings.
the line in the docsMake [`/copy`](/docs/en/commands) copy the full response every time, without showing the picker. Selecting **Always copy full response** in that picker sets this key to `true`. Appears in `/config` as **Skip the /copy picker**. |
|
v2.1.295/copy |
Documentation arrivedAnthropic's documentation has since written up /copy, on All settings.
the line in the docs| [`copyFullResponse`](#copyfullresponse) | Make [`/copy`](/docs/en/commands) copy the full response without showing the picker | Global config settings | Global config | |
|
v2.1.295extraKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up extraKnownMarketplaces, on Troubleshoot plugins.
the line in the docs`claude plugin marketplace add` prints the message after `Failed to add marketplace:`. When a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), the add that Claude … |
|
v2.1.295claude-fable-5 |
Documentation arrivedA small documentation edit on overview touched a line naming claude-fable-5 after this was published.
the line in the docs[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [Migration guide](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-mythos-5-to-claude-mythos-5-1) |
|
v2.1.295claude-fable-5 |
Documentation arrivedAnthropic's documentation has since written up claude-fable-5, on overview.
the line in the docsAlthough Claude Fable 5 is still available, you should consider migrating to Claude Fable 5.1. [See Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) · [Migrate to Claude Fable 5.1](https://platform.claude.co… |
|
v2.1.295/model |
Documentation arrivedA small documentation edit on claude-prompting-best-practices touched a line naming /model after this was published.
the line in the docsFor an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [What's new in Claude Fable 5.1](https://platform.claude.com/docs… |
|
v2.1.295/model |
Documentation arrivedA small documentation edit on claude-prompting-best-practices touched a line naming /model after this was published.
the line in the docsFor an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [What's new in Claude Fable 5.1](https://platform.claude.com/docs… |
|
v2.1.295CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS, on Error reference.
the line in the docs| [`CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS`](/docs/en/env-vars) | unset | Maximum time in milliseconds that each API request spends waiting out `429` and `529` errors when `CLAUDE_CODE_RETRY_WATCHDOG` is set. When unset, the wait has no li… |
|
v2.1.295/loop |
Documentation arrivedAnthropic's documentation has since written up /loop, on Error reference.
the line in the docs| `This session restarted <time> after its next /loop wakeup was due, so that wakeup will not fire` | [Background session errors](#restarted-after-its-next-loop-wakeup-was-due) | |