Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.319 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.

Events22,638dated, and never edited afterwards
Newestthe last time anything moved
Flag readings moved17,280a reading is one sample, for one account
Documentation arrived5,248a docs edit touched an entry's names
WhenEntryWhat happened
v2.1.285/login Documentation arrivedA small documentation edit on Voice dictation touched a line naming /login after this was published.
the line in the docs

* **`Unknown command: /voice`**: `/voice` is available only while a claude.ai account is your active sign-in. If you aren't signed in with one, run `/login`. If `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, an `apiKeyHelper` setting, or a […

v2.1.277reserved-name Documentation arrivedA small documentation edit on Marketplace reference touched a line naming reserved-name after this was published.
the line in the docs

| `name` | string | Marketplace identifier: letters, digits, `.`, `_`, and `-`, starting with a letter or digit, and no `..`. `claude plugin validate` fails any other name, because Claude Code can't install plugins from a marketplace that …

v2.1.283claude plugin validate Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin validate after this was published.
the line in the docs

| `name` | string | Marketplace identifier: letters, digits, `.`, `_`, and `-`, starting with a letter or digit, and no `..`. `claude plugin validate` fails any other name, because Claude Code can't install plugins from a marketplace that …

v2.1.287alwaysLoad Documentation arrivedA small documentation edit on Scale to many tools with tool search touched a line naming alwaysLoad after this was published.
the line in the docs

Tool search applies to all registered tools, whether they come from remote MCP servers or [custom SDK MCP servers](/docs/en/agent-sdk/custom-tools). When you use `auto`, the SDK counts every definition that tool search can defer toward one…

v2.1.287alwaysLoad Documentation arrivedA small documentation edit on Scale to many tools with tool search touched a line naming alwaysLoad after this was published.
the line in the docs

Tool search applies to all registered tools, whether they come from remote MCP servers or [custom SDK MCP servers](/docs/en/agent-sdk/custom-tools). When you use `auto`, the SDK counts every definition that tool search can defer toward one…

v2.1.285alwaysLoad Documentation arrivedA small documentation edit on Scale to many tools with tool search touched a line naming alwaysLoad after this was published.
the line in the docs

Tool search applies to all registered tools, whether they come from remote MCP servers or [custom SDK MCP servers](/docs/en/agent-sdk/custom-tools). When you use `auto`, the SDK counts every definition that tool search can defer toward one…

v2.1.288tengu_reactive_zephyr Flag reading movedThe flag server now returns off for tengu_reactive_zephyr, read as this account.
v2.1.288tengu_reactive_zephyr Flag reading movedThe flag server now returns off for tengu_reactive_zephyr, read as this account.
v2.1.286/clear Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /clear after this was published.
the line in the docs

`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than del…

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

`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than del…

v2.1.284/clear Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /clear after this was published.
the line in the docs

`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than del…

v2.1.283/clear Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /clear after this was published.
the line in the docs

`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than del…

v2.1.283/clear Documentation arrivedA small documentation edit on Create custom subagents touched a line naming /clear after this was published.
the line in the docs

`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than del…

v2.1.285skillOverrides Documentation arrivedAnthropic's documentation has since written up skillOverrides, on Extend Claude with skills.
the line in the docs

`"off"` also hides the skill from the command lists advertised to [Remote Control](/docs/en/remote-control) clients and to [Agent SDK](/docs/en/agent-sdk/skills#discover-available-commands) callers, in addition to the terminal `/` menu. In…

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

An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, bec…

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

An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, bec…

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

An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, bec…

v2.1.268claude rm Documentation arrivedA small documentation edit on Manage sessions touched a line naming claude rm after this was published.
the line in the docs

Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude purge`](/docs/en/claude-directory#clear-local-data). If you…

v2.1.268claude rm Documentation arrivedA small documentation edit on Manage sessions touched a line naming claude rm after this was published.
the line in the docs

Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude purge`](/docs/en/claude-directory#clear-local-data). If you…

v2.1.260claude rm Documentation arrivedA small documentation edit on Manage sessions touched a line naming claude rm after this was published.
the line in the docs

Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude purge`](/docs/en/claude-directory#clear-local-data). If you…

v2.1.260claude rm Documentation arrivedA small documentation edit on Manage sessions touched a line naming claude rm after this was published.
the line in the docs

Transcripts age out under the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). To delete a project's transcripts and related state sooner, run [`claude purge`](/docs/en/claude-directory#clear-local-data). If you…

v2.1.285API_TIMEOUT_MS Documentation arrivedAnthropic's documentation has since written up API_TIMEOUT_MS, on Error reference.
the line in the docs

| [`CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES`](/docs/en/env-vars) | unset | Limit on re-sends of a [non-streaming request](#streaming-response-ended-before-any-complete-data-was-received) that times out. At the limit, the request fails. A …

v2.1.284/effort Documentation arrivedA small documentation edit on Claude Code gateway compatibility guide touched a line naming /effort after this was published.
the line in the docs

| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) and [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | The `output_config` body field carries effort, structured-output …

v2.1.284certificate_pem Documentation arrivedAnthropic's documentation has since written up certificate_pem, on Claude apps gateway configuration.
the line in the docs

| `client_assertion` | With `private_key_jwt` | A block with `private_key_pem` and `certificate_pem`: the private key and certificate for [certificate client authentication](#certificate-client-authentication). Requires v2.1.284 or later. |

v2.1.284private_key_pem Documentation arrivedAnthropic's documentation has since written up private_key_pem, on Claude apps gateway configuration.
the line in the docs

| `client_assertion` | With `private_key_jwt` | A block with `private_key_pem` and `certificate_pem`: the private key and certificate for [certificate client authentication](#certificate-client-authentication). Requires v2.1.284 or later. |

v2.1.284token_endpoint_auth_method Documentation arrivedAnthropic's documentation has since written up token_endpoint_auth_method, on Claude apps gateway configuration.
the line in the docs

| `client_secret` | Unless `token_endpoint_auth_method` is `private_key_jwt` | From your OAuth client registration. Leave it out when you use [certificate client authentication](#certificate-client-authentication). |

v2.1.187tengu_startup_announcements Flag reading movedThe flag server now returns [{"accentBar":false,"id":"opus-5-5-launch","maxImpressions":3,"priority":0,"requiresModel":"claude-opus-5-5","text":"Get to finished work sooner with Opus 5.5. Switch anytime with `/model`."},{"accentBar":true,"id":"anthropic-interviewer-2026-09-public","maxImpressions":6,"priority":-2,"text":"Take 15 min to share your experiences with Anthropic Interviewer. [Start now](https://clau.de/yourthoughts)","title":"Your voice can help guide AI"}] for tengu_startup_announcements, read as this account.
v2.1.287effortLevel Documentation arrivedAnthropic's documentation has since written up effortLevel, on All settings.
the line in the docs

* `effortLevel`: one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`

v2.1.287effortLevel Documentation arrivedAnthropic's documentation has since written up effortLevel, on All settings.
the line in the docs

* `effortLevel`: one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`

v2.1.287effortLevel Documentation arrivedAnthropic's documentation has since written up effortLevel, on All settings.
the line in the docs

* `effortLevel`: one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`

v2.1.187tengu_startup_announcements Flag reading movedThe flag server now returns [{"accentBar":false,"id":"opus-5-5-launch","maxImpressions":10,"priority":0,"requiresModel":"claude-opus-5-5","text":"Get to finished work sooner with Opus 5.5. Switch anytime with `/model`."},{"accentBar":true,"id":"anthropic-interviewer-2026-09-public","maxImpressions":6,"priority":-2,"text":"Take 15 min to share your experiences with Anthropic Interviewer. [Start now](https://clau.de/yourthoughts)","title":"Your voice can help guide AI"}] for tengu_startup_announcements, read as this account.
v2.1.286claude --bg Documentation arrivedAnthropic's documentation has since written up claude --bg, on Manage multiple agents with agent view.
the line in the docs

When you dispatch a background session from agent view or start one with `claude --bg`, the session starts in your working directory. Before editing files, Claude moves the session into an isolated [git worktree](/docs/en/worktrees) under …

v2.1.277apk Documentation arrivedAnthropic's documentation has since written up apk, on Advanced setup.
the line in the docs

Installations from the apt, dnf, and apk repositories choose a channel by repository instead of this setting. To switch one, follow [Install with Linux package managers](#install-with-linux-package-managers).

v2.1.285CLAUDE_CODE_USE_VERTEX Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_USE_VERTEX, on Customize sessions in self-hosted environments.
the line in the docs

export CLAUDE_CODE_USE_VERTEX=1

v2.1.284CLAUDE_CODE_USE_VERTEX Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_USE_VERTEX, on Customize sessions in self-hosted environments.
the line in the docs

export CLAUDE_CODE_USE_VERTEX=1

v2.1.287/hooks Documentation arrivedAnthropic's documentation has since written up /hooks, on Customize sessions in self-hosted environments.
the line in the docs

The shell commands Claude runs, your [Claude Code hooks](/docs/en/hooks), and stdio MCP servers inherit the session's environment and run as the same user as Claude Code. As a result, they can read credential variables and credential files.

v2.1.284haiku Documentation arrivedA small documentation edit on Claude Code on Amazon Bedrock touched a line naming haiku after this was published.
the line in the docs

Entries with the `anthropic.` prefix are added as custom picker options, and the ones that match the Mantle format are routed to Mantle. Replace `anthropic.claude-haiku-4-5` with the model ID your account has been granted. See [Restrict mo…

v2.1.281canUseTool Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming canUseTool after this was published.
the line in the docs

* **With neither**: a bare `-p` run, or `query()` that sets neither `canUseTool` nor `permissionPromptToolName`, denies any tool call that would have prompted unless a [`PermissionRequest` hook](/docs/en/hooks-guide#limitations) allows it,…

v2.1.281canUseTool Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming canUseTool after this was published.
the line in the docs

* **With neither**: a bare `-p` run, or `query()` that sets neither `canUseTool` nor `permissionPromptToolName`, denies any tool call that would have prompted unless a [`PermissionRequest` hook](/docs/en/hooks-guide#limitations) allows it,…

v2.1.206tengu_umber_kestrel Flag reading movedThe flag server now returns on for tengu_umber_kestrel, read as this account.
v2.1.239tengu_toasty_breeze Flag reading movedThe flag server now returns {"allowanceNote":"{percent} allowance left","budgetExhaustedCopy":"You've used this week's lower-priority allowance","cooloffMinutes":10,"enabled":true,"label":"Continue now at lower priority","noticeLine":"/low-priority to continue now at lower priority · uses your weekly limit","statusLine":"Lower priority until {reset}","version":3,"waitBanner":"Working at lower priority · waiting for capacity"} for tengu_toasty_breeze, read as this account.
v2.1.239tengu_toasty_breeze Flag reading movedThe flag server now returns {"allowanceNote":"{percent} allowance left","budgetExhaustedCopy":"You've used this week's lower-priority allowance","cooloffMinutes":10,"enabled":true,"label":"Continue now at lower priority","noticeLine":"/low-priority to continue now at lower priority · uses your weekly limit","statusLine":"Lower priority until {reset}","version":3,"waitBanner":"Working at lower priority · waiting for capacity"} for tengu_toasty_breeze, read as this account.
v2.1.273tengu_quiet_dolphin Flag reading movedThe flag server now returns on for tengu_quiet_dolphin, read as this account.
v2.1.248tengu_nifty_lemur Flag reading movedThe flag server now returns {"autoContinue":true,"enabled":true,"label":"Reset your session limit now","noticeLine":"/limit-reset to reset your session limit now · uses weekly limit · 1/week","spentLine":"Weekly reset used · available again {date}","successLine":"Session limit reset · next reset available {date} · your weekly limit still applies","unavailableLine":"Couldn't reset your session limit right now · try again in a moment","version":1} for tengu_nifty_lemur, read as this account.
v2.1.248tengu_nifty_lemur Flag reading movedThe flag server now returns {"autoContinue":true,"enabled":true,"label":"Reset your session limit now","noticeLine":"/limit-reset to reset your session limit now · uses weekly limit · 1/week","spentLine":"Weekly reset used · available again {date}","successLine":"Session limit reset · next reset available {date} · your weekly limit still applies","unavailableLine":"Couldn't reset your session limit right now · try again in a moment","version":1} for tengu_nifty_lemur, read as this account.
v2.1.284tengu_lantern_wick_text Flag reading movedThe flag server now returns "Usage limit reached; a short grace allowance remains, then this turn is cut off without warning. Judge what's left: if it's genuinely only a few steps, finish it properly, then stop and say so without extra polishing. Otherwise don't attempt it all: finish the piece in hand and at most two more like it, then stop. The allowance also pays for any subagents you have running: they don't get this message and will keep going, so it's up to you how to handle them. Either way, end by telling the user their usage limit was reached, what's done and what's left." for tengu_lantern_wick_text, read as this account.
v2.1.223tengu_juniper_relay Flag reading movedThe flag server now returns on for tengu_juniper_relay, read as this account.
v2.1.251tengu_juniper_relay Flag reading movedThe flag server now returns on for tengu_juniper_relay, read as this account.
v2.1.283AskUserQuestion Documentation arrivedA small documentation edit on All settings touched a line naming AskUserQuestion after this was published.
the line in the docs

Let an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when you step away and want Claude to continue without you. With…

v2.1.283AskUserQuestion Documentation arrivedA small documentation edit on All settings touched a line naming AskUserQuestion after this was published.
the line in the docs

Let an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when you step away and want Claude to continue without you. With…

Feedback