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 |
|---|---|---|
v2.1.301tools |
Documentation arrivedAnthropic's documentation has since written up tools, on Tools and environments.
the line in the docs* **With any of these tools, change the environment yourself.** In a terminal outside Claude Science, use the tool's own commands to add, update, or remove packages. |
|
v2.1.301tools |
Documentation arrivedA small documentation edit on Core concepts touched a line naming tools after this was published.
the line in the docsOn Linux, a uv, conda, mamba, or pixi environment in a folder you've granted **Read & write** can still be read-only to Claude. See [Environments in granted folders](/docs/claude-science/tools-and-environments#environments-in-granted-folde… |
|
v2.1.301rows |
Documentation arrivedAnthropic's documentation has since written up rows, on compliance-faq.
the line in the docsYes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 sessions (in Excel,… |
|
v2.1.301rows |
Documentation arrivedAnthropic's documentation has since written up rows, on compliance-faq.
the line in the docsYes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 sessions (in Excel,… |
|
v2.1.301rows |
Documentation arrivedAnthropic's documentation has since written up rows, on compliance-faq.
the line in the docsYes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 sessions (in Excel,… |
|
v2.1.295strictKnownMarketplaces |
Documentation arrivedA small documentation edit on Code in Claude Desktop on 3P touched a line naming strictKnownMarketplaces after this was published.
the line in the docs| `userPluginMarketplacesEnabled` | When `false`, a `strictKnownMarketplaces` allowlist. See [Controlling user extensions](/docs/third-party/claude-desktop/extensions#controlling-user-extensions) for what the key does. | |
|
v2.1.300/mcp |
Documentation arrivedA small documentation edit on Edit docker-compose.yaml: increment the integer in the setup service's touched a line naming /mcp after this was published.
the line in the docsThe **Needs certificate** badge next to the tunnel's name goes away once a certificate is registered. See [Add a CA certificate](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/console#add-a-ca-certificate). |
|
v2.1.299/mcp |
Documentation arrivedA small documentation edit on Edit docker-compose.yaml: increment the integer in the setup service's touched a line naming /mcp after this was published.
the line in the docsThe **Needs certificate** badge next to the tunnel's name goes away once a certificate is registered. See [Add a CA certificate](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/console#add-a-ca-certificate). |
|
v2.1.300forceLoginOrgUUID |
Documentation arrivedAnthropic's documentation has since written up forceLoginOrgUUID, on Deploy with Enterprise Admin Console.
the line in the docs* **Allow only your organization:** set [`forceLoginOrgUUID`](/docs/cowork/hipaa-setup#what-each-claude-desktop-key-does) to your Claude organization's ID. This ID isn't [`deploymentOrganizationUuid`](/docs/third-party/claude-desktop/confi… |
|
v2.1.300forceLoginOrgUUID |
Documentation arrivedAnthropic's documentation has since written up forceLoginOrgUUID, on Deploy with Enterprise Admin Console.
the line in the docs* **Allow only your organization:** set [`forceLoginOrgUUID`](/docs/cowork/hipaa-setup#what-each-claude-desktop-key-does) to your Claude organization's ID. This ID isn't [`deploymentOrganizationUuid`](/docs/third-party/claude-desktop/confi… |
|
v2.1.299forceLoginOrgUUID |
Documentation arrivedAnthropic's documentation has since written up forceLoginOrgUUID, on Deploy with Enterprise Admin Console.
the line in the docs* **Allow only your organization:** set [`forceLoginOrgUUID`](/docs/cowork/hipaa-setup#what-each-claude-desktop-key-does) to your Claude organization's ID. This ID isn't [`deploymentOrganizationUuid`](/docs/third-party/claude-desktop/confi… |
|
v2.1.300/config |
Documentation arrivedA small documentation edit on Windows fleet checklist touched a line naming /config after this was published.
the line in the docs* **Two registry values.** Push the two values described under [Windows](/docs/government/deploy-desktop/configure#windows) as machine policy under `HKLM\SOFTWARE\Policies\Claude`: `bootstrapUrl` and `disableDeploymentModeChooser`, both re… |
|
v2.1.299CLAUDE_CODE_MAX_CONTEXT_TOKENS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_CONTEXT_TOKENS, on Model configuration.
the line in the docs* **Any other window**: set [`CLAUDE_CODE_MAX_CONTEXT_TOKENS`](/docs/en/env-vars) to the window size in tokens in the environment that starts Claude Code, such as `CLAUDE_CODE_MAX_CONTEXT_TOKENS=400000`. For an unrecognized ID that doesn't… |
|
v2.1.299/feedback |
Documentation arrivedAnthropic's documentation has since written up /feedback, on Error reference.
the line in the docsAPI Error: Opus 4.8's safeguards flagged this message. Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate cybersecurity work. Send feedback with /feedback or learn more: https… |
|
v2.1.299CLAUDE_CODE_MAX_OUTPUT_TOKENS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_OUTPUT_TOKENS, on Error reference.
the line in the docsAPI Error: Claude's response exceeded the ... output token maximum. To configure this behavior, set the CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable. |
|
v2.1.300PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Error reference.
the line in the docs| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) | |
|
v2.1.300PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Error reference.
the line in the docs| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) | |
|
v2.1.299PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Error reference.
the line in the docs| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) | |
|
v2.1.299PermissionRequest |
Documentation arrivedAnthropic's documentation has since written up PermissionRequest, on Error reference.
the line in the docs| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) | |
|
v2.1.295/rewind |
Documentation arrivedAnthropic's documentation has since written up /rewind, on Claude Code changelog.
the line in the docs- Fixed skills no longer being listed to the model after using `/rewind` |
|
v2.1.289claude auth status |
Documentation arrivedAnthropic's documentation has since written up claude auth status, on Claude Code changelog.
the line in the docs- Fixed sign-in refresh timeouts and unexpected sign-outs after a short command such as `claude auth status` or `claude plugin list` exited in the middle of a token refresh |
|
v2.1.300awsAuthRefresh |
Documentation arrivedAnthropic's documentation has since written up awsAuthRefresh, on Claude Code changelog.
the line in the docs- Fixed switching to a model whose name contains `application-inference-profile` running your `awsAuthRefresh` command and delaying model-switch hooks when the provider is not Bedrock |
|
v2.1.300PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Claude Code changelog.
the line in the docs- Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call |
|
v2.1.300PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Claude Code changelog.
the line in the docs- Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call |
|
v2.1.300WorktreeCreate |
Documentation arrivedAnthropic's documentation has since written up WorktreeCreate, on Claude Code changelog.
the line in the docs- Fixed quitting removing a worktree made by a `WorktreeCreate` hook without asking when it may hold unpushed commits |
|
v2.1.300WorktreeCreate |
Documentation arrivedAnthropic's documentation has since written up WorktreeCreate, on Claude Code changelog.
the line in the docs- Fixed quitting removing a worktree made by a `WorktreeCreate` hook without asking when it may hold unpushed commits |
|
v2.1.299--name |
Documentation arrivedAnthropic's documentation has since written up --name, on user-management.
the line in the docsant beta:organization:rbac-groups create --name Engineering |
|
v2.1.299headers |
Documentation arrivedA small documentation edit on api touched a line naming headers after this was published.
the line in the docsA create request takes the Console's settings except **Provider**, so enter your observability platform's endpoint URL and headers yourself. Set `traces.max_content_bytes` (csharp, go: `Traces.MaxContentBytes`; java, php: `traces.maxConten… |
|
v2.1.299edits |
Documentation arrivedAnthropic's documentation has since written up edits, on mid-conversation-effort-example.
the line in the docs"description": "Orchestrate a multiagent workflow: split a large task into independent subtasks and run them as parallel agents, then collect their results. Opt-in: only use this tool when the user explicitly asks for a workflow, or when a… |
|
v2.1.299edits |
Documentation arrivedAnthropic's documentation has since written up edits, on mid-conversation-effort-example.
the line in the docs"description": "Orchestrate a multiagent workflow: split a large task into independent subtasks and run them as parallel agents, then collect their results. Opt-in: only use this tool when the user explicitly asks for a workflow, or when a… |
|
v2.1.299/fast |
Documentation arrivedAnthropic's documentation has since written up /fast, on fast-mode.
the line in the docsFast mode for Claude Opus 5.5 doesn't need the `fast-mode-2026-02-01` beta header or an access request. Requests that still send the header keep working. Fast mode for Claude Opus 5 and Claude Opus 4.8 is in research preview: contact your … |
|
v2.1.299headers |
Documentation arrivedAnthropic's documentation has since written up headers, on claude-platform-on-aws.
the line in the docs# Request-Id headers, to stderr |
|
v2.1.299ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on claude-in-microsoft-foundry.
the line in the docsenv -u ANTHROPIC_API_KEY ANTHROPIC_AUTH_TOKEN="$ACCESS_TOKEN" ant messages create \ |
|
v2.1.299/fast |
Documentation arrivedA small documentation edit on choosing-a-model touched a line naming /fast after this was published.
the line in the docs* **Speed:** How quickly does the model need to respond in your application? [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) delivers up to 2.5x higher output speed at premium pricing on [supported models](http… |
|
v2.1.274/review |
Documentation arrivedA small documentation edit on Week 32 · August 3–7, 2026 touched a line naming /review after this was published.
the line in the docs<div><code>/review</code> is now an alias of <a href="/docs/en/code-review-local"><code>/code-review</code></a>, and <code>/code-review</code> with no effort level reuses the level you typed last</div> |
|
v2.1.296/login |
Documentation arrivedA small documentation edit on Find bugs with ultrareview touched a line naming /login after this was published.
the line in the docsUltrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/login` and authenticate with claude.ai first. Ultrareview is no… |
|
v2.1.295/rewind |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming /rewind after this was published.
the line in the docsA forked skill that runs in the background applies its edits outside your session's [checkpoints](/docs/en/checkpointing#subagent-edits-not-restored). After one, `/rewind` restores only the files Claude had already edited in your conversat… |
|
v2.1.286/rewind |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming /rewind after this was published.
the line in the docsA forked skill that runs in the background applies its edits outside your session's [checkpoints](/docs/en/checkpointing#subagent-edits-not-restored). After one, `/rewind` restores only the files Claude had already edited in your conversat… |
|
v2.1.283/rewind |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming /rewind after this was published.
the line in the docsA forked skill that runs in the background applies its edits outside your session's [checkpoints](/docs/en/checkpointing#subagent-edits-not-restored). After one, `/rewind` restores only the files Claude had already edited in your conversat… |
|
v2.1.299/code |
Documentation arrivedA small documentation edit on Track team usage with analytics touched a line naming /code after this was published.
the line in the docsCode Review has its own dashboard. For review activity and spend, see [View usage](/docs/en/code-review-costs#view-usage). |
|
v2.1.290/code-review |
Documentation arrivedA small documentation edit on Track team usage with analytics touched a line naming /code-review after this was published.
the line in the docsCode Review has its own dashboard. For review activity and spend, see [View usage](/docs/en/code-review-costs#view-usage). |
|
v2.1.299/env |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming /env after this was published.
the line in the docsDescriptions and instructions from some of the MCP servers that Anthropic hosts at `api.anthropic.com` reach Claude in full. To change the limits for the other MCP servers in your session, set [`CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH`](/do… |
|
v2.1.280CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH after this was published.
the line in the docsDescriptions and instructions from some of the MCP servers that Anthropic hosts at `api.anthropic.com` reach Claude in full. To change the limits for the other MCP servers in your session, set [`CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH`](/do… |
|
v2.1.299WebFetch |
Documentation arrivedAnthropic's documentation has since written up WebFetch, on Error reference.
the line in the docsFor the network lock, the warning names `sandbox.network.allowedDomains` and `allowManagedDomainsOnly`, and says `only allowed domains (and WebFetch domain rules) from managed settings are honored`. |
|
v2.1.299WebFetch |
Documentation arrivedAnthropic's documentation has since written up WebFetch, on Error reference.
the line in the docsFor the network lock, the warning names `sandbox.network.allowedDomains` and `allowManagedDomainsOnly`, and says `only allowed domains (and WebFetch domain rules) from managed settings are honored`. |
|
v2.1.299sandbox.filesystem.allowRead |
Documentation arrivedAnthropic's documentation has since written up sandbox.filesystem.allowRead, on Error reference.
the line in the docssandbox.filesystem.allowRead is ignored — managed settings set allowManagedReadPathsOnly, so only allowRead paths from managed settings are honored. The 3 entries in /home/you/.claude/settings.json will NOT apply (see https://code.claude.c… |
|
v2.1.300/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Error reference.
the line in the docs* For other reserved names to avoid, see [MCP configuration warnings](/docs/en/mcp#configuration-warnings) |
|
v2.1.299/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Error reference.
the line in the docs* For other reserved names to avoid, see [MCP configuration warnings](/docs/en/mcp#configuration-warnings) |
|
v2.1.299/share |
Documentation arrivedAnthropic's documentation has since written up /share, on Error reference.
the line in the docspath: .claude/rules/shared.md |
|
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) |