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 |
|---|---|---|
v2.1.260disableAutoMode |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming disableAutoMode after this was published.
the line in the docs| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. [Switch … |
|
v2.1.260disableAutoMode |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming disableAutoMode after this was published.
the line in the docs| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. [Switch … |
|
v2.1.248disableAutoMode |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming disableAutoMode after this was published.
the line in the docs| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. [Switch … |
|
v2.1.248passthrough |
Documentation arrivedA small documentation edit on Voice dictation touched a line naming passthrough after this was published.
the line in the docs* **`Voice input is failing repeatedly and has been paused`**: voice dictation hit three failures within 10 seconds. Claude Code pauses dictation until 10 seconds have passed since the first of those failures. This usually means the microp… |
|
v2.1.281disallowedTools |
Documentation arrivedAnthropic's documentation has since written up disallowedTools, on Create custom subagents.
the line in the docs* **[Frontmatter fields](#supported-frontmatter-fields)**: `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `skills`, `initialPrompt`, `memory`, `effort`, `background`, `omitClaudeMd`… |
|
v2.1.281disallowedTools |
Documentation arrivedAnthropic's documentation has since written up disallowedTools, on Create custom subagents.
the line in the docs* **[Frontmatter fields](#supported-frontmatter-fields)**: `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `skills`, `initialPrompt`, `memory`, `effort`, `background`, `omitClaudeMd`… |
|
v2.1.280--safe-mode |
Documentation arrivedAnthropic's documentation has since written up --safe-mode, on Error reference.
the line in the docsThe value you passed to `--agents` is invalid, so `claude` exits with code 1 instead of starting the session. When you pass `--safe-mode` or set [`CLAUDE_CODE_SAFE_MODE`](/docs/en/env-vars#variables), Claude Code ignores `--agents` entirel… |
|
v2.1.280--safe-mode |
Documentation arrivedAnthropic's documentation has since written up --safe-mode, on Error reference.
the line in the docsThe value you passed to `--agents` is invalid, so `claude` exits with code 1 instead of starting the session. When you pass `--safe-mode` or set [`CLAUDE_CODE_SAFE_MODE`](/docs/en/env-vars#variables), Claude Code ignores `--agents` entirel… |
|
v2.1.282--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Error reference.
the line in the docs| `Error: --agents takes a JSON object, or a file path only with --print (-p)` | [Command-line errors](#invalid-agents-configuration) | |
|
v2.1.281--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Error reference.
the line in the docs| `Error: --agents takes a JSON object, or a file path only with --print (-p)` | [Command-line errors](#invalid-agents-configuration) | |
|
v2.1.281--agents |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --agents after this was published.
the line in the docs| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-the-subagent-scope). With `--print`, the value can instead be the path to a JSON file holding the… |
|
v2.1.281--agents |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --agents after this was published.
the line in the docs| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-the-subagent-scope). With `--print`, the value can instead be the path to a JSON file holding the… |
|
v2.1.281--agents |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --agents after this was published.
the line in the docs| `--agents` | Define custom subagents dynamically via JSON. Accepts the [fields listed for CLI-defined subagents](/docs/en/sub-agents#choose-the-subagent-scope). With `--print`, the value can instead be the path to a JSON file holding the… |
|
v2.1.277backgrounding |
Documentation arrivedAnthropic's documentation has since written up backgrounding, on Agent SDK reference - TypeScript.
the line in the docsFor a subagent task, the `summary` field carries a model-generated progress summary and is populated only when [`agentProgressSummaries`](#options) is enabled. For a [backgrounded MCP tool call](/docs/en/mcp#automatic-backgrounding-of-long… |
|
v2.1.277backgrounding |
Documentation arrivedAnthropic's documentation has since written up backgrounding, on Agent SDK reference - TypeScript.
the line in the docsFor a subagent task, the `summary` field carries a model-generated progress summary and is populated only when [`agentProgressSummaries`](#options) is enabled. For a [backgrounded MCP tool call](/docs/en/mcp#automatic-backgrounding-of-long… |
|
v2.1.277backgrounding |
Documentation arrivedAnthropic's documentation has since written up backgrounding, on Agent SDK reference - TypeScript.
the line in the docsFor a subagent task, the `summary` field carries a model-generated progress summary and is populated only when [`agentProgressSummaries`](#options) is enabled. For a [backgrounded MCP tool call](/docs/en/mcp#automatic-backgrounding-of-long… |
|
v2.1.259agentProgressSummaries |
Documentation arrivedAnthropic's documentation has since written up agentProgressSummaries, on Agent SDK reference - TypeScript.
the line in the docsFor a subagent task, the `summary` field carries a model-generated progress summary and is populated only when [`agentProgressSummaries`](#options) is enabled. For a [backgrounded MCP tool call](/docs/en/mcp#automatic-backgrounding-of-long… |
|
v2.1.282PostToolUse |
Documentation arrivedAnthropic's documentation has since written up PostToolUse, on Agent SDK reference - TypeScript.
the line in the docsOn Claude Code v2.1.227 or later, a hook's [`systemMessage`](/docs/en/hooks#json-output) can arrive as this message, with each line prefixed by the hook's name, such as `PostToolUse:Bash says:`. Each [event's section](/docs/en/hooks#hook-e… |
|
v2.1.281--worktree |
Documentation arrivedAnthropic's documentation has since written up --worktree, on Run parallel sessions with worktrees.
the line in the docs* **The worktree has work in it**: Claude prompts you to keep or remove the worktree. Keeping preserves the directory and branch. To return later, run the `claude --worktree <name> --resume` command that Claude Code prints on exit. Removin… |
|
v2.1.281--worktree |
Documentation arrivedAnthropic's documentation has since written up --worktree, on Run parallel sessions with worktrees.
the line in the docs* **The worktree has work in it**: Claude prompts you to keep or remove the worktree. Keeping preserves the directory and branch. To return later, run the `claude --worktree <name> --resume` command that Claude Code prints on exit. Removin… |
|
v2.1.282ultracode |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming ultracode after this was published.
the line in the docsWhen workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu. A run that was already in… |
|
v2.1.282ultracode |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming ultracode after this was published.
the line in the docsWhen workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu. A run that was already in… |
|
v2.1.282/effort |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming /effort after this was published.
the line in the docsWhen workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu. A run that was already in… |
|
v2.1.280/effort |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming /effort after this was published.
the line in the docsWhen workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu. A run that was already in… |
|
v2.1.280/effort |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming /effort after this was published.
the line in the docsWhen workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu. A run that was already in… |
|
v2.1.261ANTHROPIC_SMALL_FAST_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_SMALL_FAST_MODEL, on How Claude Code uses prompt caching.
the line in the docsThe variable also covers a background model you set with the deprecated `ANTHROPIC_SMALL_FAST_MODEL` variable, when that model differs from your main model. |
|
v2.1.280--debug-file |
Documentation arrivedAnthropic's documentation has since written up --debug-file, on Monitoring.
the line in the docsIf nothing arrives, start Claude Code with `claude --debug-file <path>` and check the log it writes to that path. Claude Code reports failures from the exporters you configure as `[3P telemetry]` errors, where 3P means third-party. Lines p… |
|
v2.1.282/status |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /status after this was published.
the line in the docsIf one of your instruction files is over the recommended length, you see a warning at startup and when you run `/status`. You also see a warning when files that are each within that length add up past a combined limit at session start. Eac… |
|
v2.1.257/Network |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /Network after this was published.
the line in the docsIf you point a `.claude/rules/` or `CLAUDE.md` symlink at a network path such as the UNC share `\\server\share` or a path under `/net` or `/Network`, the linked instructions don't load. Claude Code doesn't follow the link, because looking … |
|
v2.1.268seq |
Documentation arrivedA small documentation edit on Claude Code gateway compatibility guide touched a line naming seq after this was published.
the line in the docsDeliver each response's full event sequence without dropping, duplicating, or reordering events. When an event references a content block whose `content_block_start` never arrived, or a block whose `content_block_stop` already arrived, Cla… |
|
v2.1.257background_tasks |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming background_tasks after this was published.
the line in the docsIn addition to the [common input fields](#common-input-fields), Stop hooks receive `stop_hook_active`, `last_assistant_message`, `background_tasks`, and `session_crons`. The `stop_hook_active` field is `true` when Claude Code is already co… |
|
v2.1.273SessionStart |
Documentation arrivedA small documentation edit on Use Claude Code in the cloud touched a line naming SessionStart after this was published.
the line in the docs* **Time limits**: commands Claude runs and SessionStart hooks have default timeouts you can change, and a setup script is cached only when it finishes in roughly five minutes. See [Time limits](/docs/en/cloud-environments#time-limits) |
|
v2.1.282/hooks |
Documentation arrivedA small documentation edit on Best practices for Claude Code touched a line naming /hooks after this was published.
the line in the docs* **As a deterministic gate**: a [Stop hook](/docs/en/hooks#stop) runs your check as a script and blocks the turn from ending until it passes. [Stop input](/docs/en/hooks#stop-input) covers the cap on consecutive blocks. |
|
v2.1.265plugin.json |
Documentation arrivedA small documentation edit on Manage your listing after publishing touched a line naming plugin.json after this was published.
the line in the docsA plugin listing's name and short description come from `plugin.json` and the README of the version that's live. To change them, edit those files and publish a new version, as [Plugin changes](#plugin-changes) describes. If an Anthropic re… |
|
v2.1.268sigv4 |
Documentation arrivedAnthropic's documentation has since written up sigv4, on Troubleshoot federated cloud access.
the line in the docs* **A hostname with no usable region.** Agent Proxy reads the AWS service and signing region from the hostname, so the region must be the last label before `amazonaws.com`, as in `service.region.amazonaws.com`, `my-bucket.s3.us-east-1.amaz… |
|
v2.1.282ultracode |
Documentation arrivedAnthropic's documentation has since written up ultracode, on Orchestrate subagents at scale with dynamic workflows.
the line in the docsWith ultracode on, Claude decides when a task warrants a workflow. A single request can turn into several workflows in a row: one to understand the code, one to make the change, and one to verify it. This applies to every task in the sessi… |
|
v2.1.282ultracode |
Documentation arrivedAnthropic's documentation has since written up ultracode, on Orchestrate subagents at scale with dynamic workflows.
the line in the docsWith ultracode on, Claude decides when a task warrants a workflow. A single request can turn into several workflows in a row: one to understand the code, one to make the change, and one to verify it. This applies to every task in the sessi… |
|
v2.1.282--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Manage sessions.
the line in the docsA `claude -p --resume` or `claude -p --continue` run resumes in plan mode only when all of these conditions hold: |
|
v2.1.282--debug |
Documentation arrivedAnthropic's documentation has since written up --debug, on Model configuration.
the line in the docs`enforceAvailableModels` remaps the Default option only when `availableModels` is non-empty. When `availableModels` is non-empty but no entry resolves to an allowed and available model, enforcement is skipped with a warning visible only un… |
|
v2.1.282blockedMarketplaces |
Documentation arrivedAnthropic's documentation has since written up blockedMarketplaces, on Deploy managed settings.
the line in the docs| `blockedMarketplaces` | An individual invalid entry is stripped and the valid subset is enforced. An entry that parses but can never match, such as a `hostPattern` regex that doesn't compile, is kept with a warning. It blocks nothing unt… |
|
v2.1.282blockedMarketplaces |
Documentation arrivedAnthropic's documentation has since written up blockedMarketplaces, on Deploy managed settings.
the line in the docs| `blockedMarketplaces` | An individual invalid entry is stripped and the valid subset is enforced. An entry that parses but can never match, such as a `hostPattern` regex that doesn't compile, is kept with a warning. It blocks nothing unt… |
|
v2.1.282strictKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up strictKnownMarketplaces, on Deploy managed settings.
the line in the docs| `strictKnownMarketplaces` | Enforced as an empty allowlist until the value is fixed, so no [marketplace source](/docs/en/plugins/org#restrict-what-users-can-install) is admitted. An individual entry that is invalid or can't be enforced, … |
|
v2.1.282strictKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up strictKnownMarketplaces, on Deploy managed settings.
the line in the docs| `strictKnownMarketplaces` | Enforced as an empty allowlist until the value is fixed, so no [marketplace source](/docs/en/plugins/org#restrict-what-users-can-install) is admitted. An individual entry that is invalid or can't be enforced, … |
|
v2.1.282strictKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up strictKnownMarketplaces, on Deploy managed settings.
the line in the docs| `strictKnownMarketplaces` | Enforced as an empty allowlist until the value is fixed, so no [marketplace source](/docs/en/plugins/org#restrict-what-users-can-install) is admitted. An individual entry that is invalid or can't be enforced, … |
|
v2.1.282managed-mcp.json |
Documentation arrivedAnthropic's documentation has since written up managed-mcp.json, on Deploy managed settings.
the line in the docs| `allowedMcpServers` | Enforced as an empty allowlist until the value is fixed, so no MCP servers that users add are admitted. Servers your organization delivers through [`managedMcpServers`](/docs/en/settings-reference#managedmcpservers)… |
|
v2.1.282--resume |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming --resume after this was published.
the line in the docsTo resume a deferred session in plan mode, pass [`--permission-prompt-tool`](/docs/en/cli-reference#cli-flags) along with `--resume` so that Claude Code can present the plan for approval. If you pass certain other launch flags, the resumed… |
|
v2.1.281--resume |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming --resume after this was published.
the line in the docsTo resume a deferred session in plan mode, pass [`--permission-prompt-tool`](/docs/en/cli-reference#cli-flags) along with `--resume` so that Claude Code can present the plan for approval. If you pass certain other launch flags, the resumed… |
|
v2.1.265claude auto-mode |
Documentation arrivedAnthropic's documentation has since written up claude auto-mode, on Configure auto mode.
the line in the docs`claude auto-mode defaults` prints three kinds of environment entry. |
|
v2.1.282autoMode |
Documentation arrivedAnthropic's documentation has since written up autoMode, on Configure auto mode.
the line in the docsThe classifier doesn't read `autoMode` from project settings in `.claude/settings.json` or `.claude/settings.local.json`. Both files live in the repo directory, so a checked-in repo or a build step could otherwise inject its own allow rule… |
|
v2.1.280unverified |
Documentation arrivedAnthropic's documentation has since written up unverified, on Agent SDK reference - TypeScript.
the line in the docs| `worktree_unverified` | The session's worktree couldn't be verified right now, and retrying may succeed | |