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 |
|---|---|---|
v2.1.317/logout |
Documentation arrivedAnthropic's documentation has since written up /logout, on Claude Code changelog.
the line in the docs* Fixed `/logout`, `claude auth logout` and `claude mcp remove` reporting success, and changes to trust, consent or MCP settings being dropped with no word, when the config file could not be updated on a shared network home directory |
|
v2.1.295ENABLE_BETA_TRACING_DETAILED |
Documentation arrivedA small documentation edit on Monitoring touched a line naming ENABLE_BETA_TRACING_DETAILED after this was published.
the line in the docs> Set `ENABLE_BETA_TRACING_DETAILED` only for debugging, not in production. Detailed beta tracing has a high export volume, and its [content attributes](#new-context-gates) aren't part of the stable span schema. |
|
v2.1.315acceptEdits |
Documentation arrivedAnthropic's documentation has since written up acceptEdits, on Orchestrate teams of Claude Code sessions.
the line in the docs> An in-process teammate that isn't in [plan mode](#have-teammates-plan-before-implementing) runs in the lead's mode while the lead is in [`acceptEdits`](https://code.claude.com/docs/en/permission-modes#auto-approve-file-edits-with-accepte… |
|
v2.1.315dontAsk |
Documentation arrivedAnthropic's documentation has since written up dontAsk, on Orchestrate teams of Claude Code sessions.
the line in the docsYou can't set per-teammate permission modes at spawn time. A new teammate starts with the lead's mode, including `bypassPermissions` mode, which `--dangerously-skip-permissions` turns on. If the lead is in [`dontAsk` mode](https://code.cla… |
|
v2.1.315dontAsk |
Documentation arrivedAnthropic's documentation has since written up dontAsk, on Orchestrate teams of Claude Code sessions.
the line in the docsYou can't set per-teammate permission modes at spawn time. A new teammate starts with the lead's mode, including `bypassPermissions` mode, which `--dangerously-skip-permissions` turns on. If the lead is in [`dontAsk` mode](https://code.cla… |
|
v2.1.299onFailure |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming onFailure after this was published.
the line in the docsonFailure?: "continue" | "block"; // "block" blocks the action when a callback fails |
|
v2.1.296onFailure |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming onFailure after this was published.
the line in the docsonFailure?: "continue" | "block"; // "block" blocks the action when a callback fails |
|
v2.1.295onFailure |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming onFailure after this was published.
the line in the docsonFailure?: "continue" | "block"; // "block" blocks the action when a callback fails |
|
v2.1.295onFailure |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming onFailure after this was published.
the line in the docsonFailure?: "continue" | "block"; // "block" blocks the action when a callback fails |
|
v2.1.314PreCompact |
Documentation arrivedAnthropic's documentation has since written up PreCompact, on Intercept and control agent behavior with hooks.
the line in the docsA callback that exceeds its timeout follows [Hook timeout](#hook-timeout). With `"block"` set, a timeout also blocks `PreCompact`, `Elicitation`, and `WorktreeCreate`. |
|
v2.1.296on_failure |
Documentation arrivedAnthropic's documentation has since written up on_failure, on Intercept and control agent behavior with hooks.
the line in the docs| `onFailure` | `"continue" \| "block"` | `undefined` | What a failed callback does. Set `"block"` to [block the action when a callback fails](#block-the-action-when-a-callback-fails). In Python, use `on_failure` | |
|
v2.1.314effortLevel |
Documentation arrivedA small documentation edit on CLI reference touched a line naming effortLevel after this was published.
the line in the docs| `--effort` | Set the [effort level](https://code.claude.com/docs/en/model-config.md#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ul… |
|
v2.1.295--effort |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --effort after this was published.
the line in the docs| `--effort` | Set the [effort level](https://code.claude.com/docs/en/model-config.md#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ul… |
|
v2.1.304/workflows |
Documentation arrivedA small documentation edit on CLI reference touched a line naming /workflows after this was published.
the line in the docs| `--effort` | Set the [effort level](https://code.claude.com/docs/en/model-config.md#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ul… |
|
v2.1.314fable |
Documentation arrivedA small documentation edit on Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: touched a line naming fable after this was published.
the line in the docs2. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://platform.claude.com/docs/en/build-with-claude/mid-conversati… |
|
v2.1.314CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS, on Deploy Claude Desktop on 3P with an LLM gateway.
the line in the docs| `not_requested`, `betas_disabled`, `switch` is `on` | The device's own Claude Code managed settings or a compliance policy turn experimental betas off, which takes priority. | If a `requested` line follows, ignore this line. If none foll… |
|
v2.1.315NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Changelog.
the line in the docs* Fixed certificate settings such as `NODE_EXTRA_CA_CERTS` in the `env` of Claude Code's `managed-settings.json` not taking effect in some sessions, such as Chat and Cowork. Settings already in that file now take effect, so review them bef… |
|
v2.1.315autoMode |
Documentation arrivedAnthropic's documentation has since written up autoMode, on Changelog.
the line in the docs* Changed how `autoMode` lists in Claude Code's `managed-settings.json` apply in local Code sessions and Cowork tasks: an `allow` list without `"$defaults"` replaces the built-in exceptions, and a `soft_deny` or `environment` list without … |
|
v2.1.314PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on MCP, plugins, skills, and hooks.
the line in the docs* **The hook fails or times out**: a [`PreToolUse`](https://code.claude.com/docs/en/hooks#pretooluse) or [`PermissionRequest`](https://code.claude.com/docs/en/hooks#permissionrequest) command hook that has no `args` and no `onFailure` fiel… |
|
v2.1.309--setting-sources |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming --setting-sources after this was published.
the line in the docs* For `useAutoModeDuringPlan`, a `false` in a user or local file the developer leaves out with an option such as [`--setting-sources`](https://code.claude.com/docs/en/cli-reference#cli-flags) doesn't count. Ignoring a left-out file require… |
|
v2.1.312/memory |
Documentation arrivedA small documentation edit on claude-in-amazon-bedrock touched a line naming /memory after this was published.
the line in the docs* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Browser use tool](https://platform.claude.com/docs/e… |
|
v2.1.304CLAUDE_CODE_OAUTH_REFRESH_TOKEN |
Documentation arrivedA small documentation edit on All settings touched a line naming CLAUDE_CODE_OAUTH_REFRESH_TOKEN after this was published.
the line in the docs* Variables that set your claude.ai sign-in, such as [`CLAUDE_CODE_OAUTH_TOKEN`, `CLAUDE_CODE_OAUTH_REFRESH_TOKEN`, and `CLAUDE_CODE_OAUTH_SCOPES`](https://code.claude.com/docs/en/env-vars#variables). |
|
v2.1.311CLAUDE_CODE_RESUME_INTERRUPTED_TURN |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_RESUME_INTERRUPTED_TURN, on Claude Code changelog.
the line in the docs* Self-hosted runner: Fixed Claude not seeing the interrupted tool call when a session moves to a new runner and the turn is older than `CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS` |
|
v2.1.312/feedback |
Documentation arrivedAnthropic's documentation has since written up /feedback, on Claude Code changelog.
the line in the docs* Fixed /feedback showing "Enter to confirm" while a report is being sent |
|
v2.1.312/feedback |
Documentation arrivedAnthropic's documentation has since written up /feedback, on Claude Code changelog.
the line in the docs* Fixed /feedback showing "Enter to confirm" while a report is being sent |
|
v2.1.315/remote-control |
Documentation arrivedAnthropic's documentation has since written up /remote-control, on Claude Code changelog.
the line in the docs* Fixed `/remote-control` answering "Unknown command" instead of saying that Remote Control is turned off by the `disableRemoteControl` setting |
|
v2.1.314effortLevel |
Documentation arrivedAnthropic's documentation has since written up effortLevel, on Claude Code changelog.
the line in the docs* Fixed a project's `effortLevel` setting being ignored by sessions that an app starts ahead of time and then opens in the project, such as new sessions in the desktop app's Code tab |
|
v2.1.315--chrome |
Documentation arrivedAnthropic's documentation has since written up --chrome, on Claude Code changelog.
the line in the docs* Improved the "Resume this session with" hint shown at exit to repeat the flags you launched with (for example `--chrome --debug`) ahead of `--resume` |
|
v2.1.314claude setup-token |
Documentation arrivedA small documentation edit on Authentication touched a line naming claude setup-token after this was published.
the line in the docs5. `CLAUDE_CODE_OAUTH_TOKEN` environment variable. A long-lived OAuth token generated by [`claude setup-token`](#generate-a-long-lived-token). Use this for CI pipelines and scripts where browser login isn't available. If you run `/login` w… |
|
v2.1.314CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Authentication touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs5. `CLAUDE_CODE_OAUTH_TOKEN` environment variable. A long-lived OAuth token generated by [`claude setup-token`](#generate-a-long-lived-token). Use this for CI pipelines and scripts where browser login isn't available. If you run `/login` w… |
|
v2.1.314CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Authentication touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs5. `CLAUDE_CODE_OAUTH_TOKEN` environment variable. A long-lived OAuth token generated by [`claude setup-token`](#generate-a-long-lived-token). Use this for CI pipelines and scripts where browser login isn't available. If you run `/login` w… |
|
v2.1.314CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Authentication touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs5. `CLAUDE_CODE_OAUTH_TOKEN` environment variable. A long-lived OAuth token generated by [`claude setup-token`](#generate-a-long-lived-token). Use this for CI pipelines and scripts where browser login isn't available. If you run `/login` w… |
|
v2.1.315/login |
Documentation arrivedA small documentation edit on Authentication touched a line naming /login after this was published.
the line in the docs5. `CLAUDE_CODE_OAUTH_TOKEN` environment variable. A long-lived OAuth token generated by [`claude setup-token`](#generate-a-long-lived-token). Use this for CI pipelines and scripts where browser login isn't available. If you run `/login` w… |
|
v2.1.314/config |
Documentation arrivedA small documentation edit on Security and data handling touched a line naming /config after this was published.
the line in the docs> The desktop can also export OpenTelemetry events to a collector you specify: tool name, connector, outcome, duration, and approval status are sent. The export includes prompt text, Claude's responses, and tool inputs and results only for… |
|
v2.1.314permissions.blockReadsOutsideWorkingDirectories |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming permissions.blockReadsOutsideWorkingDirectories after this was published.
the line in the docs* **No, and block reads outside the working directories from now on**: the read is refused, and Claude Code sets [`permissions.blockReadsOutsideWorkingDirectories`](https://code.claude.com/docs/en/settings-reference#permissions-blockreadso… |
|
v2.1.315blockReadsOutsideWorkingDirectories |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs* **No, and block reads outside the working directories from now on**: the read is refused, and Claude Code sets [`permissions.blockReadsOutsideWorkingDirectories`](https://code.claude.com/docs/en/settings-reference#permissions-blockreadso… |
|
v2.1.315blockReadsOutsideWorkingDirectories |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs* **No, and block reads outside the working directories from now on**: the read is refused, and Claude Code sets [`permissions.blockReadsOutsideWorkingDirectories`](https://code.claude.com/docs/en/settings-reference#permissions-blockreadso… |
|
v2.1.315blockReadsOutsideWorkingDirectories |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs* **No, and block reads outside the working directories from now on**: the read is refused, and Claude Code sets [`permissions.blockReadsOutsideWorkingDirectories`](https://code.claude.com/docs/en/settings-reference#permissions-blockreadso… |
|
v2.1.314blockReadsOutsideWorkingDirectories |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs* **No, and block reads outside the working directories from now on**: the read is refused, and Claude Code sets [`permissions.blockReadsOutsideWorkingDirectories`](https://code.claude.com/docs/en/settings-reference#permissions-blockreadso… |
|
v2.1.305claude -p |
Documentation arrivedA small documentation edit on CLI reference touched a line naming claude -p after this was published.
the line in the docs| `--input-format` | Specify input format for print mode (options: `text`, `stream-json`) | `claude -p --input-format stream-json --output-format stream-json --verbose` | |
|
v2.1.314/btw |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /btw after this was published.
the line in the docsFor a question about something already in your conversation, use [`/btw`](https://code.claude.com/docs/en/interactive-mode#side-questions-with-%2Fbtw) instead of a subagent. It has no tool access, and the answer isn't added to history. |
|
v2.1.299/btw |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /btw after this was published.
the line in the docsFor a question about something already in your conversation, use [`/btw`](https://code.claude.com/docs/en/interactive-mode#side-questions-with-%2Fbtw) instead of a subagent. It has no tool access, and the answer isn't added to history. |
|
v2.1.309/rate-limit-options |
Documentation arrivedAnthropic's documentation has since written up /rate-limit-options, on Interactive mode.
the line in the docsAfter three automatic continuations, automatic continue stops and the `Automatic continue stopped after repeated usage-limit hits` notification appears. Run `/rate-limit-options` to choose what to do next. When you send another prompt, or … |
|
v2.1.309failure_reason |
Documentation arrivedAnthropic's documentation has since written up failure_reason, on Agent SDK reference - TypeScript.
the line in the docsThe `SDKStartupFailureReason` type lists the values `startup_failure_reason` can hold: |
|
v2.1.314sandbox_required_unavailable |
Documentation arrivedAnthropic's documentation has since written up sandbox_required_unavailable, on Agent SDK reference - TypeScript.
the line in the docs* A start that Claude Code refuses because [`failIfUnavailable`](#sandboxsettings) is on and the sandbox can't start, with `sandbox_required_unavailable`. |
|
v2.1.314guardrail_trace |
Documentation arrivedAnthropic's documentation has since written up guardrail_trace, on Claude apps gateway configuration.
the line in the docsTo find out which Amazon Bedrock guardrail filter blocked a developer's request, set `guardrail_trace: true` on the Bedrock upstream, restart the gateway, and have the developer send the request again. Then find the request's `guardrail.tr… |
|
v2.1.315--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Run parallel sessions with worktrees.
the line in the docsWhen you resume a session that ended inside a worktree without [exiting it](#clean-up-worktrees), Claude Code returns the session to that worktree. This holds for interactive resumes, for `--continue` and `--resume` in [non-interactive mod… |
|
v2.1.314/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Run parallel sessions with worktrees.
the line in the docsTo get the tools back, run `/status` in the session to list the [setting sources it loaded](https://code.claude.com/docs/en/settings.md#check-what-loaded), and remove the key from every file that sets it. Then restart Claude Code. If manag… |
|
v2.1.314--worktree |
Documentation arrivedAnthropic's documentation has since written up --worktree, on Run parallel sessions with worktrees.
the line in the docs* **Interactive sessions**: start the session in a worktree with `claude --worktree`. |
|
v2.1.314autoMemoryDirectory |
Documentation arrivedAnthropic's documentation has since written up autoMemoryDirectory, on All settings.
the line in the docs* **Auto memory in a directory the repository chose**: a directory that [`autoMemoryDirectory`](#automemorydirectory) names in repository settings |