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.

Events22,540dated, and never edited afterwards
Newestthe last time anything moved
Flag readings moved17,188a reading is one sample, for one account
Documentation arrived5,242a docs edit touched an entry's names
WhenEntryWhat happened
v2.1.246/status Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code on Amazon Bedrock.
the line in the docs

Run `/status` to see the resolved region. When the region came from your AWS config files or the default fallback, Claude Code also notes the source in the `/status` output.
v2.1.243/status Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code on Amazon Bedrock.
the line in the docs

Run `/status` to see the resolved region. When the region came from your AWS config files or the default fallback, Claude Code also notes the source in the `/status` output.
v2.1.232/status Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code on Amazon Bedrock.
the line in the docs

Run `/status` to see the resolved region. When the region came from your AWS config files or the default fallback, Claude Code also notes the source in the `/status` output.
v2.1.231/status Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code on Amazon Bedrock.
the line in the docs

Run `/status` to see the resolved region. When the region came from your AWS config files or the default fallback, Claude Code also notes the source in the `/status` output.
v2.1.229/status Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code on Amazon Bedrock.
the line in the docs

Run `/status` to see the resolved region. When the region came from your AWS config files or the default fallback, Claude Code also notes the source in the `/status` output.
v2.1.232AWS_REGION Documentation arrivedAnthropic's documentation has since written up AWS_REGION, on Claude Code on Amazon Bedrock.
the line in the docs

* You only need to set `AWS_REGION` to override your AWS profile's region or when your profile has no region. Claude Code resolves the region in this order:
v2.1.232AWS_REGION Documentation arrivedAnthropic's documentation has since written up AWS_REGION, on Claude Code on Amazon Bedrock.
the line in the docs

* You only need to set `AWS_REGION` to override your AWS profile's region or when your profile has no region. Claude Code resolves the region in this order:
v2.1.232AWS_REGION Documentation arrivedAnthropic's documentation has since written up AWS_REGION, on Claude Code on Amazon Bedrock.
the line in the docs

* You only need to set `AWS_REGION` to override your AWS profile's region or when your profile has no region. Claude Code resolves the region in this order:
v2.1.251inherit Documentation arrivedAnthropic's documentation has since written up inherit, on Orchestrate teams of Claude Code sessions.
the line in the docs

Teammates start with the lead's permission mode, except [`dontAsk` mode](/docs/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode), which they don't inherit. If the lead runs with `--dangerously-skip-permissions`, all team…
v2.1.251inherit Documentation arrivedAnthropic's documentation has since written up inherit, on Orchestrate teams of Claude Code sessions.
the line in the docs

Teammates start with the lead's permission mode, except [`dontAsk` mode](/docs/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode), which they don't inherit. If the lead runs with `--dangerously-skip-permissions`, all team…
v2.1.251inherit Documentation arrivedAnthropic's documentation has since written up inherit, on Orchestrate teams of Claude Code sessions.
the line in the docs

Teammates start with the lead's permission mode, except [`dontAsk` mode](/docs/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode), which they don't inherit. If the lead runs with `--dangerously-skip-permissions`, all team…
v2.1.248dontAsk Documentation arrivedAnthropic's documentation has since written up dontAsk, on Orchestrate teams of Claude Code sessions.
the line in the docs

Teammates start with the lead's permission mode, except [`dontAsk` mode](/docs/en/permission-modes#allow-only-pre-approved-tools-with-dontask-mode), which they don't inherit. If the lead runs with `--dangerously-skip-permissions`, all team…
v2.1.257fable Documentation arrivedA small documentation edit on Escalate hard decisions with the advisor tool touched a line naming fable after this was published.
the line in the docs

Fable 5.1 requires Claude Code v2.1.257 or later. Both Fable models require [Fable access](/docs/en/model-config#work-with-fable).
v2.1.236configs Documentation arrivedA small documentation edit on tools touched a line naming configs after this was published.
the line in the docs

Enable the full toolset with `agent_toolset_20260401` when creating an agent. Use the `configs` array to disable specific tools or override their settings. Each config entry can also set a `permission_policy` that controls whether the tool…
v2.1.260interactive Documentation arrivedAnthropic's documentation has since written up interactive, on permission-policies.
the line in the docs

To answer interactively instead, use `ant beta:sessions connect`, which shows the waiting call and sends this event when you allow or deny it. See [Connect to a Managed Agents session from your terminal](https://platform.claude.com/docs/en…
v2.1.259addMcpServer Documentation arrivedAnthropic's documentation has since written up addMcpServer, on permission-policies.
the line in the docs

.addMcpServer(
v2.1.235language Documentation arrivedAnthropic's documentation has since written up language, on permission-policies.
the line in the docs

<MultiFileExample language="cli" label="CLI">
v2.1.234ANTHROPIC_API_KEY Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_API_KEY, on permission-policies.
the line in the docs

-H "x-api-key: $ANTHROPIC_API_KEY" \
v2.1.233ANTHROPIC_API_KEY Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_API_KEY, on permission-policies.
the line in the docs

-H "x-api-key: $ANTHROPIC_API_KEY" \
v2.1.239/agents Documentation arrivedAnthropic's documentation has since written up /agents, on permission-policies.
the line in the docs

agent=$(curl -fsSL https://api.anthropic.com/v1/agents \
v2.1.248deny Documentation arrivedA small documentation edit on multiagent-orchestration touched a line naming deny after this was published.
the line in the docs

Under `auto`, your `user.message` events can lead the server to allow a call it would otherwise deny. Nothing in a subagent's thread counts as your intent: your client posts no messages there, and the coordinator's messages to the subagent…
v2.1.247origin Documentation arrivedA small documentation edit on multiagent-orchestration touched a line naming origin after this was published.
the line in the docs

If a subagent needs something from your client, such as [permission](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tool-confirmation) to run a tool call or the [result of a custom tool](https://platform.claude.com…
v2.1.234max_turns Documentation arrivedAnthropic's documentation has since written up max_turns, on migration.
the line in the docs

| `max_turns` | Count turns client-side. |
v2.1.257PreToolUse Documentation arrivedAnthropic's documentation has since written up PreToolUse, on migration.
the line in the docs

| `PreToolUse` / `PostToolUse` hooks | Your client already sees every `agent.custom_tool_use` event before responding; put the logic there. For built-in tools, use `permission_policy: always_ask` to review every call. [`auto`](https://plat…
v2.1.232timeout Documentation arrivedAnthropic's documentation has since written up timeout, on Batches.
the line in the docs

- `type: "timeout_error"`
v2.1.229timeout Documentation arrivedAnthropic's documentation has since written up timeout, on Batches.
the line in the docs

- `type: "timeout_error"`
v2.1.229timeout Documentation arrivedAnthropic's documentation has since written up timeout, on Batches.
the line in the docs

- `type: "timeout_error"`
v2.1.234regex Documentation arrivedAnthropic's documentation has since written up regex, on Batches.
the line in the docs

- `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"`
v2.1.259defer_loading Documentation arrivedAnthropic's documentation has since written up defer_loading, on Batches.
the line in the docs

- `defer_loading: optional boolean or null`
v2.1.257defer_loading Documentation arrivedAnthropic's documentation has since written up defer_loading, on Batches.
the line in the docs

- `defer_loading: optional boolean or null`
v2.1.257ToolSearch Documentation arrivedAnthropic's documentation has since written up ToolSearch, on Batches.
the line in the docs

- `ToolSearchToolResultBlockParam object`
v2.1.265str_replace Documentation arrivedAnthropic's documentation has since written up str_replace, on Batches.
the line in the docs

- `type: "text_editor_code_execution_str_replace_result"`
v2.1.265str_replace Documentation arrivedAnthropic's documentation has since written up str_replace, on Batches.
the line in the docs

- `type: "text_editor_code_execution_str_replace_result"`
v2.1.265str_replace Documentation arrivedAnthropic's documentation has since written up str_replace, on Batches.
the line in the docs

- `type: "text_editor_code_execution_str_replace_result"`
v2.1.265str_replace Documentation arrivedAnthropic's documentation has since written up str_replace, on Batches.
the line in the docs

- `type: "text_editor_code_execution_str_replace_result"`
v2.1.265str_replace Documentation arrivedAnthropic's documentation has since written up str_replace, on Batches.
the line in the docs

- `type: "text_editor_code_execution_str_replace_result"`
v2.1.267open Documentation arrivedAnthropic's documentation has since written up open, on Batches.
the line in the docs

- `type: "tab_opened"`
v2.1.247origin Documentation arrivedAnthropic's documentation has since written up origin, on Batches.
the line in the docs

Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`.
v2.1.246/permissions Documentation arrivedAnthropic's documentation has since written up /permissions, on Permissions.
the line in the docs

url: https://platform.claude.com/docs/en/api/compliance/organizations/roles/permissions
v2.1.234/permissions Documentation arrivedAnthropic's documentation has since written up /permissions, on Permissions.
the line in the docs

url: https://platform.claude.com/docs/en/api/compliance/organizations/roles/permissions
v2.1.247at_create Documentation arrivedAnthropic's documentation has since written up at_create, on Apps.
the line in the docs

`GET /v1/compliance/activities` with `activity_types[]=claude_chat_created`
v2.1.238initialize Documentation arrivedAnthropic's documentation has since written up initialize, on Credentials.
the line in the docs

The MCP method that failed (for example `initialize` or `tools/list`).
v2.1.234llm Documentation arrivedAnthropic's documentation has since written up llm, on User Profiles.
the line in the docs

- `type: "enrollment_url"`
v2.1.259pins Documentation arrivedAnthropic's documentation has since written up pins, on Delete Skill Version.
the line in the docs

paths and pins it in references.
v2.1.259pins Documentation arrivedAnthropic's documentation has since written up pins, on Delete Skill Version.
the line in the docs

paths and pins it in references.
v2.1.248/version Documentation arrivedAnthropic's documentation has since written up /version, on Versions.
the line in the docs

url: https://platform.claude.com/docs/en/api/beta/skills/versions
v2.1.260/memory Documentation arrivedAnthropic's documentation has since written up /memory, on Resources.
the line in the docs

Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only.
v2.1.236SessionEnd Documentation arrivedAnthropic's documentation has since written up SessionEnd, on List Events.
the line in the docs

- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached`
v2.1.236SessionEnd Documentation arrivedAnthropic's documentation has since written up SessionEnd, on List Events.
the line in the docs

- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached`
v2.1.234SessionEnd Documentation arrivedAnthropic's documentation has since written up SessionEnd, on List Events.
the line in the docs

- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or BetaManagedAgentsSessionBudgetReached`
Feedback