Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesWhat has changed since
What has changed since

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.

Events22,542dated, and never edited afterwards
Newestthe last time anything moved
Flag readings moved17,190a reading is one sample, for one account
Documentation arrived5,242a docs edit touched an entry's names
WhenEntryWhat happened
v2.1.265pane:scrollDown Documentation arrivedAnthropic's documentation has since written up pane:scrollDown, on Customize keyboard shortcuts.
the line in the docs

| `pane:scrollDown` | Down | Scroll the pane down when it has more rows than it can show |

v2.1.271pane:previous Documentation arrivedAnthropic's documentation has since written up pane:previous, on Customize keyboard shortcuts.
the line in the docs

Actions for a pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive). The scroll, resize, and close actions apply in the `Pane` [context](#contexts). `pane:close` also applies in the `PaneField` context…

v2.1.271pane:next Documentation arrivedAnthropic's documentation has since written up pane:next, on Customize keyboard shortcuts.
the line in the docs

Actions for a pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive). The scroll, resize, and close actions apply in the `Pane` [context](#contexts). `pane:close` also applies in the `PaneField` context…

v2.1.269pane:close Documentation arrivedAnthropic's documentation has since written up pane:close, on Customize keyboard shortcuts.
the line in the docs

Actions for a pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive). The scroll, resize, and close actions apply in the `Pane` [context](#contexts). `pane:close` also applies in the `PaneField` context…

v2.1.265pane:scrollUp Documentation arrivedAnthropic's documentation has since written up pane:scrollUp, on Customize keyboard shortcuts.
the line in the docs

The `AbovePrompt` context also binds Up, Down, PageUp, PageDown, Home, and End to the [pane scroll actions](#pane-actions) `pane:scrollUp` through `pane:bottom`, so to change one of those keys for the band, bind the scroll action in an `Ab…

v2.1.265AbovePrompt Documentation arrivedAnthropic's documentation has since written up AbovePrompt, on Customize keyboard shortcuts.
the line in the docs

| `AbovePrompt` | The [band above the prompt](#above-prompt-actions), or a button in it, has keyboard focus |

v2.1.290/rename Documentation arrivedAnthropic's documentation has since written up /rename, on Manage multiple agents with agent view.
the line in the docs

* A session that's working: `/model`, `/effort`, `/rename`, and `/usage` run right away. Other replies join the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, an…

v2.1.290/usage Documentation arrivedAnthropic's documentation has since written up /usage, on Manage multiple agents with agent view.
the line in the docs

* A session that's working: `/model`, `/effort`, `/rename`, and `/usage` run right away. Other replies join the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, an…

v2.1.275tool.call Documentation arrivedA small documentation edit on Plugin commands reference touched a line naming tool.call after this was published.
the line in the docs

* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/events#handle-a-hook-that-fails). Each item gives `module`, `pat…

v2.1.292/plugin Documentation arrivedA small documentation edit on Plugin commands reference touched a line naming /plugin after this was published.
the line in the docs

* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/events#handle-a-hook-that-fails). Each item gives `module`, `pat…

v2.1.292/plugin Documentation arrivedA small documentation edit on Plugin commands reference touched a line naming /plugin after this was published.
the line in the docs

* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/events#handle-a-hook-that-fails). Each item gives `module`, `pat…

v2.1.267.catch Documentation arrivedA small documentation edit on Plugin commands reference touched a line naming .catch after this was published.
the line in the docs

* `gatingHooks`: whether each [mod](/docs/en/plugins/mods/overview) hook that can refuse an action, such as a `tool.call` hook, has a [`.catch` handler](/docs/en/plugins/mods/events#handle-a-hook-that-fails). Each item gives `module`, `pat…

v2.1.281/ide Documentation arrivedAnthropic's documentation has since written up /ide, on Connect to Microsoft 365.
the line in the docs

5. Open the **User consent** tab, which shows the permissions granted to individual users. The admin center can't revoke these grants. To remove a write scope listed here, use Microsoft Graph or PowerShell as described in Microsoft's [Revi…

v2.1.290blockReadsOutsideWorkingDirectories Documentation arrivedA small documentation edit on Code in Claude Desktop on 3P touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs

The network and filesystem sandboxes apply on macOS, and on Linux devices and [SSH hosts](/docs/third-party/claude-desktop/ssh-remote-sessions#managed-configuration-on-the-remote-host) with Claude Code's [sandbox dependencies](https://code…

v2.1.285blockReadsOutsideWorkingDirectories Documentation arrivedA small documentation edit on Code in Claude Desktop on 3P touched a line naming blockReadsOutsideWorkingDirectories after this was published.
the line in the docs

The network and filesystem sandboxes apply on macOS, and on Linux devices and [SSH hosts](/docs/third-party/claude-desktop/ssh-remote-sessions#managed-configuration-on-the-remote-host) with Claude Code's [sandbox dependencies](https://code…

v2.1.290/chrome Documentation arrivedAnthropic's documentation has since written up /chrome, on Troubleshoot Claude Science.
the line in the docs

For the steps, see the help for [Chrome](https://support.google.com/chrome/answer/2693767), [Safari](https://support.apple.com/guide/safari/customize-settings-per-website-ibrw7f78f7fe/mac), [macOS](https://support.apple.com/guide/mac-help/…

v2.1.285maxTurns Documentation arrivedA small documentation edit on Create custom subagents touched a line naming maxTurns after this was published.
the line in the docs

* When a subagent stops at its [`maxTurns`](#supported-frontmatter-fields) limit, Claude Code marks the returned output as partial, and Claude can resume the subagent to continue its work.

v2.1.285maxTurns Documentation arrivedA small documentation edit on Create custom subagents touched a line naming maxTurns after this was published.
the line in the docs

* When a subagent stops at its [`maxTurns`](#supported-frontmatter-fields) limit, Claude Code marks the returned output as partial, and Claude can resume the subagent to continue its work.

v2.1.292timeout Documentation arrivedA small documentation edit on inference-hooks-configuration touched a line naming timeout after this was published.
the line in the docs

Inference hooks activity is recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed): configuration changes, denials, circuit breaker trips, and requests that proceeded wit…

v2.1.284/upgrade Documentation arrivedAnthropic's documentation has since written up /upgrade, on optimizing-for-cost-and-intelligence.
the line in the docs

![Two charts of cost per solved task against tasks solved: on SWE-bench Pro every model solves most tasks and the upgrade steps are small; on Terminal-Bench 3 the Opus ladder falls from $183 USD to $63 USD to $28 USD per solved task](https…

v2.1.292/plugin Documentation arrivedAnthropic's documentation has since written up /plugin, on SSH remote sessions in Claude Desktop on 3P.
the line in the docs

| `~/.claude/remote/plugins/<id>/` | Plugins synced from the device, in one folder for each Claude Desktop installation that connects |

v2.1.292/plugin Documentation arrivedAnthropic's documentation has since written up /plugin, on SSH remote sessions in Claude Desktop on 3P.
the line in the docs

| `~/.claude/remote/plugins/<id>/` | Plugins synced from the device, in one folder for each Claude Desktop installation that connects |

v2.1.292/workflows Documentation arrivedAnthropic's documentation has since written up /workflows, on Orchestrate subagents at scale with dynamic workflows.
the line in the docs

* `/workflows`, the workflow commands, and the `/workflow-authoring` skill are unavailable

v2.1.292/loop Documentation arrivedAnthropic's documentation has since written up /loop, on Claude Code changelog.
the line in the docs

* Reverted the 2.1.290 fix for cloud sessions staying asleep after a container restart lost a pending `/loop` wakeup or scheduled task; Claude is no longer told, and the session stays asleep

v2.1.292/feedback Documentation arrivedAnthropic's documentation has since written up /feedback, on Claude Code changelog.
the line in the docs

* Fixed `/feedback` returning to the drafts list after Ctrl+O or Ctrl+Z while a report was sending, leaving the send impossible to cancel

v2.1.292/feedback Documentation arrivedAnthropic's documentation has since written up /feedback, on Claude Code changelog.
the line in the docs

* Fixed `/feedback` returning to the drafts list after Ctrl+O or Ctrl+Z while a report was sending, leaving the send impossible to cancel

v2.1.289claude plugin eval Documentation arrivedAnthropic's documentation has since written up claude plugin eval, on Claude Code changelog.
the line in the docs

* Fixed `claude plugin eval` refusing every Bash-granting run on Macs with Docker Desktop (links under `~/.docker/bin`); the refusal now names which part of a credential store held the link

v2.1.292claude plugin Documentation arrivedAnthropic's documentation has since written up claude plugin, on Claude Code changelog.
the line in the docs

* Fixed `claude plugin test` failing for mods that call `$.session.append`; tests can read the appended rows back with the new `mock.session`

v2.1.290claude remote-control Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Claude Code changelog.
the line in the docs

* Fixed PushNotification reporting "Remote Control inactive" in sessions started with `claude remote-control`

v2.1.290claude logs Documentation arrivedAnthropic's documentation has since written up claude logs, on Claude Code changelog.
the line in the docs

* Fixed `claude logs`, `stop`, `kill`, `rm` and `claude daemon status`, `stop`, `uninstall` sometimes signing you out when your login had expired or was about to

v2.1.290claude logs Documentation arrivedAnthropic's documentation has since written up claude logs, on Claude Code changelog.
the line in the docs

* Fixed `claude logs`, `stop`, `kill`, `rm` and `claude daemon status`, `stop`, `uninstall` sometimes signing you out when your login had expired or was about to

v2.1.285--tools Documentation arrivedAnthropic's documentation has since written up --tools, on Claude Code changelog.
the line in the docs

* Fixed Claude being told to continue or message subagents with `SendMessage` in sessions, including resumed ones, where a host, a permission rule or a `--tools` list removed that tool

v2.1.285--tools Documentation arrivedAnthropic's documentation has since written up --tools, on Claude Code changelog.
the line in the docs

* Fixed Claude being told to continue or message subagents with `SendMessage` in sessions, including resumed ones, where a host, a permission rule or a `--tools` list removed that tool

v2.1.284subagentStatusLine Documentation arrivedAnthropic's documentation has since written up subagentStatusLine, on Claude Code changelog.
the line in the docs

* Added `agentType` to the `subagentStatusLine` payload, so scripts can tell custom subagent types apart

v2.1.285CLAUDE_CODE_SKIP_AWS_CRED_CACHE Documentation arrivedA small documentation edit on Claude Code on Amazon Bedrock touched a line naming CLAUDE_CODE_SKIP_AWS_CRED_CACHE after this was published.
the line in the docs

The resolve that fills the cache times out after 60 seconds. If a step in the chain stalls, for example a `credential_process` helper that waits for input it can't receive, the request fails with [`AWS default-chain credential resolve time…

v2.1.285CLAUDE_CODE_SKIP_AWS_CRED_CACHE Documentation arrivedA small documentation edit on Claude Code on Amazon Bedrock touched a line naming CLAUDE_CODE_SKIP_AWS_CRED_CACHE after this was published.
the line in the docs

The resolve that fills the cache times out after 60 seconds. If a step in the chain stalls, for example a `credential_process` helper that waits for input it can't receive, the request fails with [`AWS default-chain credential resolve time…

v2.1.288settings.local.json Documentation arrivedA small documentation edit on Glossary touched a line naming settings.local.json after this was published.
the line in the docs

The hierarchy Claude Code reads configuration from, in precedence order from highest to lowest: [managed policy](#managed-settings), settings you pass with the `--settings` flag, local settings at `.claude/settings.local.json`, project set…

v2.1.286managed-settings.json Documentation arrivedA small documentation edit on Explore the .claude directory touched a line naming managed-settings.json after this was published.
the line in the docs

| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that your own settings files and `--settings` values can't override, apart from [narrow exceptions](/docs/en/settings#exceptions-to-managed-settings-prec…

v2.1.288claude update Documentation arrivedAnthropic's documentation has since written up claude update, on Model configuration.
the line in the docs

Sonnet 5.5 requires Claude Code v2.1.284 or later, and Opus 5.5 requires v2.1.280 or later. If a request for one of them from an older version fails, see [Claude Code does not support this model](/docs/en/errors#claude-code-does-not-suppor…

v2.1.288ANTHROPIC_DEFAULT_SONNET_MODEL Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_DEFAULT_SONNET_MODEL, on Model configuration.
the line in the docs

Where `opus` or `sonnet` resolves to an older model, newer models are available by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.

v2.1.292/model Documentation arrivedA small documentation edit on Explore the context window touched a line naming /model after this was published.
the line in the docs

If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended context](/docs/en/model-config#extended…

v2.1.292/model Documentation arrivedA small documentation edit on Explore the context window touched a line naming /model after this was published.
the line in the docs

If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended context](/docs/en/model-config#extended…

v2.1.292/model Documentation arrivedAnthropic's documentation has since written up /model, on Escalate hard decisions with the advisor tool.
the line in the docs

Fable 5.1 requires Claude Code v2.1.257 or later. Fable models require [Fable access](/docs/en/model-config#work-with-fable). Sonnet 5.5 as the advisor for an Opus 4.7 or Opus 4.8 main model requires Claude Code v2.1.287 or later. Haiku 5.…

v2.1.292/model Documentation arrivedAnthropic's documentation has since written up /model, on Escalate hard decisions with the advisor tool.
the line in the docs

Fable 5.1 requires Claude Code v2.1.257 or later. Fable models require [Fable access](/docs/en/model-config#work-with-fable). Sonnet 5.5 as the advisor for an Opus 4.7 or Opus 4.8 main model requires Claude Code v2.1.287 or later. Haiku 5.…

v2.1.280output_config.effort Documentation arrivedA small documentation edit on mid-conversation-system-messages touched a line naming output_config.effort after this was published.
the line in the docs

A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level partway through a conversation. This is in beta on Claude Fable 5.1, Claude Mythos …

v2.1.290/effort Documentation arrivedAnthropic's documentation has since written up /effort, on claude-on-amazon-bedrock-legacy.
the line in the docs

A `role: "system"` message can also set `output_config.effort` to [change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) on Claude Fable 5.1 and Claude Opus 5.5. T…

v2.1.290--worktree Documentation arrivedAnthropic's documentation has since written up --worktree, on Hooks reference.
the line in the docs

* You exit a `--worktree` session and choose to remove the worktree

v2.1.290--worktree Documentation arrivedAnthropic's documentation has since written up --worktree, on Hooks reference.
the line in the docs

* You exit a `--worktree` session and choose to remove the worktree

v2.1.290/chrome Documentation arrivedA small documentation edit on Use Claude Code with Chrome touched a line naming /chrome after this was published.
the line in the docs

| "Browser extension is not connected" | Native messaging host cannot reach the extension, or your organization's IP allowlist rejects the connection to `bridge.claudeusercontent.com` | Check that the extension is signed in to the same cla…

v2.1.290claude auth login Documentation arrivedAnthropic's documentation has since written up claude auth login, on Use Claude Code in the cloud.
the line in the docs

* ``Cloud sessions need a claude.ai sign-in. Run `claude auth login` (or /login in a local session), then try again.``

Feedback