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
v2.1.281pluginConfigs Documentation arrivedA small documentation edit on All settings touched a line naming pluginConfigs after this was published.
the line in the docs

Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load) setting that controls whether Claude Code reads `AGENTS.md`…

v2.1.277instructionFiles Documentation arrivedA small documentation edit on All settings touched a line naming instructionFiles after this was published.
the line in the docs

Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load) setting that controls whether Claude Code reads `AGENTS.md`…

v2.1.277instructionFiles Documentation arrivedA small documentation edit on All settings touched a line naming instructionFiles after this was published.
the line in the docs

Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load) setting that controls whether Claude Code reads `AGENTS.md`…

v2.1.275NODE_EXTRA_CA_CERTS Documentation arrivedA small documentation edit on Enterprise network configuration touched a line naming NODE_EXTRA_CA_CERTS after this was published.
the line in the docs

By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertificates`: the native installer always has it, and npm instal…

v2.1.273NODE_EXTRA_CA_CERTS Documentation arrivedA small documentation edit on Enterprise network configuration touched a line naming NODE_EXTRA_CA_CERTS after this was published.
the line in the docs

By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertificates`: the native installer always has it, and npm instal…

v2.1.287pluginConfigs Documentation arrivedAnthropic's documentation has since written up pluginConfigs, on How Claude remembers your project.
the line in the docs

You can also set the value in a settings file instead of `/config`. Add it to [`pluginConfigs`](/docs/en/settings-reference#pluginconfigs) under `cc-plugin-agents-md@builtin`, the ID of the built-in plugin that reads `AGENTS.md`. Claude Co…

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

* Improved Claude in Chrome: a `browser_batch` call now gets 90 seconds, up from 60, before it is reported as timed out

v2.1.288ConfigChange Documentation arrivedAnthropic's documentation has since written up ConfigChange, on Claude Code changelog.
the line in the docs

* Fixed sandboxed Bash commands on Linux running `ConfigChange` hooks and reloading settings mid-command when `.claude/settings.json` or `.claude/settings.local.json` does not exist

v2.1.288settings.local.json Documentation arrivedAnthropic's documentation has since written up settings.local.json, on Claude Code changelog.
the line in the docs

* Fixed sandboxed Bash commands on Linux running `ConfigChange` hooks and reloading settings mid-command when `.claude/settings.json` or `.claude/settings.local.json` does not exist

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

* Fixed some permission rules and safety checks not being applied to a tool call after a PreToolUse hook rewrote its input

v2.1.288--continue Documentation arrivedAnthropic's documentation has since written up --continue, on Claude Code changelog.
the line in the docs

* Fixed plan mode not being restored when resuming a session with `--continue` or `--resume <session-id>` in the terminal

v2.1.273typeset Documentation arrivedAnthropic's documentation has since written up typeset, on Claude Code changelog.
the line in the docs

* Fixed a deny or ask rule missing a command or path whose name came from a variable set as a prefix on `declare`, `typeset`, `export` or `readonly`

v2.1.273typeset Documentation arrivedAnthropic's documentation has since written up typeset, on Claude Code changelog.
the line in the docs

* Fixed a deny or ask rule missing a command or path whose name came from a variable set as a prefix on `declare`, `typeset`, `export` or `readonly`

v2.1.288/loop Documentation arrivedAnthropic's documentation has since written up /loop, on Claude Code changelog.
the line in the docs

* Fixed scheduled tasks (`/loop` with an interval, reminders) silently not coming back on resume once the conversation was compacted; covers compactions made from this version on

v2.1.288/loop Documentation arrivedAnthropic's documentation has since written up /loop, on Claude Code changelog.
the line in the docs

* Fixed scheduled tasks (`/loop` with an interval, reminders) silently not coming back on resume once the conversation was compacted; covers compactions made from this version on

v2.1.288allowRead Documentation arrivedAnthropic's documentation has since written up allowRead, on Claude Code changelog.
the line in the docs

* Added a /status and doctor warning when managed settings ignore user-configured sandbox allowRead paths or allowed domains

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

* Added `agentId` to the `tool.check` event of plugin hooks, so a hook can tell a subagent's permission check from the main session's

v2.1.285read_file Documentation arrivedAnthropic's documentation has since written up read_file, on inference-hooks-endpoint.
the line in the docs

"tool_name": "read_file",

v2.1.271read_file Documentation arrivedAnthropic's documentation has since written up read_file, on inference-hooks-endpoint.
the line in the docs

"tool_name": "read_file",

v2.1.288claude --version Documentation arrivedAnthropic's documentation has since written up claude --version, on Mods overview.
the line in the docs

* **Terminal**: in your shell, run `claude --version`. If yours is older, [update Claude Code](/docs/en/setup#update-claude-code).

v2.1.288claude --version Documentation arrivedA small documentation edit on Create a mod touched a line naming claude --version after this was published.
the line in the docs

Use Claude Code v2.1.287 or later. In your shell, run `claude --version` to check. To see whether mods can load for you, see [Check whether mods can load](/docs/en/plugins/mods/troubleshoot#check-whether-mods-can-load).

v2.1.283acceptEdits Documentation arrivedA small documentation edit on Hooks reference touched a line naming acceptEdits after this was published.
the line in the docs

| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alias for `default` |

v2.1.286bypassPermissions Documentation arrivedA small documentation edit on Hooks reference touched a line naming bypassPermissions after this was published.
the line in the docs

| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alias for `default` |

v2.1.285bypassPermissions Documentation arrivedA small documentation edit on Hooks reference touched a line naming bypassPermissions after this was published.
the line in the docs

| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alias for `default` |

v2.1.281setMode Documentation arrivedA small documentation edit on Hooks reference touched a line naming setMode after this was published.
the line in the docs

| `setMode` | `mode`, `destination` | Changes the permission mode. Valid modes are `default`, `auto`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`, and `manual` as an alias for `default` |

v2.1.288claude purge Documentation arrivedAnthropic's documentation has since written up claude purge, on Set up Claude Code (local mode) for a HIPAA-ready organization.
the line in the docs

On Claude Code v2.1.288 or later, run `claude purge`:

v2.1.288CLAUDE.md Documentation arrivedA small documentation edit on Debug your configuration touched a line naming CLAUDE.md after this was published.
the line in the docs

If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md` files load on demand rather than at session start, so they…

v2.1.288CLAUDE.md Documentation arrivedA small documentation edit on Debug your configuration touched a line naming CLAUDE.md after this was published.
the line in the docs

If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md` files load on demand rather than at session start, so they…

v2.1.288CLAUDE.md Documentation arrivedA small documentation edit on Debug your configuration touched a line naming CLAUDE.md after this was published.
the line in the docs

If a memory file is missing from the `/context` breakdown, check its location against [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). Subdirectory `CLAUDE.md` files load on demand rather than at session start, so they…

v2.1.289/reload-plugins Documentation arrivedA small documentation edit on Scan your codebase for vulnerabilities touched a line naming /reload-plugins after this was published.
the line in the docs

Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate the plugin in your current session.

v2.1.289/reload-plugins Documentation arrivedA small documentation edit on Scan your codebase for vulnerabilities touched a line naming /reload-plugins after this was published.
the line in the docs

Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate the plugin in your current session.

v2.1.285/reload-plugins Documentation arrivedA small documentation edit on Scan your codebase for vulnerabilities touched a line naming /reload-plugins after this was published.
the line in the docs

Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate the plugin in your current session.

v2.1.284/reload-plugins Documentation arrivedA small documentation edit on Scan your codebase for vulnerabilities touched a line naming /reload-plugins after this was published.
the line in the docs

Check the install summary. If it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without restarting](/docs/en/plugins/cli-reference#reload-plugins) to activate the plugin in your current session.

v2.1.284CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS, on Agent SDK reference - TypeScript.
the line in the docs

Emitted when Claude Code reports the session's state. To receive these messages, set [`CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1`](/docs/en/env-vars#variables). Claude Code can report the same state more than once, so read a message as the s…

v2.1.284CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS after this was published.
the line in the docs

Subtypes that have no dataclass of their own arrive as `SystemMessage`. To follow the session between turns, set [`CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1`](/docs/en/env-vars#variables) and read `message.data["state"]` on each message whos…

v2.1.281inferenceCredentialKind Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming inferenceCredentialKind after this was published.
the line in the docs

Earlier app versions used `inferenceGatewayAuthScheme: "sso"` to select this mode. That value is deprecated; set `inferenceCredentialKind: "interactive"` instead. Existing deployments that still send `inferenceGatewayAuthScheme: "sso"` wor…

v2.1.280Space Documentation arrivedA small documentation edit on Connect to Microsoft 365 touched a line naming Space after this was published.
the line in the docs

| `scope` | No | Space-separated delegated Graph scopes to request instead of the default read set. A string array named `scopes` is also accepted only before 12:00 PM Pacific Time (19:00 UTC) on October 7, 2026. See [Configure scopes](#co…

v2.1.265Jira Documentation arrivedA small documentation edit on First request touched a line naming Jira after this was published.
the line in the docs

Usage and cost attribution to Jira work items

v2.1.288/artifacts Documentation arrivedAnthropic's documentation has since written up /artifacts, on cmek.
the line in the docs

* Claude Code cannot [publish artifacts](https://code.claude.com/docs/en/artifacts#availability). However, artifacts made in chat or Cowork can be shared within your organization, but not publicly.

v2.1.283/insights Documentation arrivedAnthropic's documentation has since written up /insights, on cmek.
the line in the docs

* Certain analytics are disabled, regardless of admin settings: Claude smart reports (beta, under claude.ai/analytics/insights) and Claude Code contribution metrics from GitHub (beta, under claude.ai/analytics/claude-code). Admin analytics…

v2.1.281/insights Documentation arrivedAnthropic's documentation has since written up /insights, on cmek.
the line in the docs

* Certain analytics are disabled, regardless of admin settings: Claude smart reports (beta, under claude.ai/analytics/insights) and Claude Code contribution metrics from GitHub (beta, under claude.ai/analytics/claude-code). Admin analytics…

v2.1.287fable Documentation arrivedAnthropic's documentation has since written up fable, on Beta.
the line in the docs

- `"fable"`

v2.1.287fable Documentation arrivedAnthropic's documentation has since written up fable, on Beta.
the line in the docs

- `"fable"`

v2.1.288/login Documentation arrivedA small documentation edit on Find bugs with ultrareview touched a line naming /login after this was published.
the line in the docs

Ultrareview 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…

v2.1.284/feedback Documentation arrivedA small documentation edit on Tools reference touched a line naming /feedback after this was published.
the line in the docs

In [organizations with Zero Data Retention](/docs/en/zero-data-retention#features-disabled-under-zdr), and in organizations with the [HIPAA configuration](/docs/en/hipaa-setup) applied, Claude Code leaves the tool out, as it does for `/fee…

v2.1.282/feedback Documentation arrivedA small documentation edit on Tools reference touched a line naming /feedback after this was published.
the line in the docs

In [organizations with Zero Data Retention](/docs/en/zero-data-retention#features-disabled-under-zdr), and in organizations with the [HIPAA configuration](/docs/en/hipaa-setup) applied, Claude Code leaves the tool out, as it does for `/fee…

v2.1.281/feedback Documentation arrivedA small documentation edit on Tools reference touched a line naming /feedback after this was published.
the line in the docs

In [organizations with Zero Data Retention](/docs/en/zero-data-retention#features-disabled-under-zdr), and in organizations with the [HIPAA configuration](/docs/en/hipaa-setup) applied, Claude Code leaves the tool out, as it does for `/fee…

v2.1.283/code-review ultra Documentation arrivedA small documentation edit on Code Review touched a line naming /code-review ultra after this was published.
the line in the docs

Ultrareview requires authentication with a claude.ai account and is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration…

v2.1.280/code-review ultra Documentation arrivedA small documentation edit on Code Review touched a line naming /code-review ultra after this was published.
the line in the docs

Ultrareview requires authentication with a claude.ai account and is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration…

v2.1.280/code-review ultra Documentation arrivedA small documentation edit on Code Review touched a line naming /code-review ultra after this was published.
the line in the docs

Ultrareview requires authentication with a claude.ai account and is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled or with the [HIPAA configuration…

Feedback