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 |
|---|---|---|
v2.1.269CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.268CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.265CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.246.gitignore |
Documentation arrivedAnthropic's documentation has since written up .gitignore, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.269/context |
Documentation arrivedAnthropic's documentation has since written up /context, on thinking-troubleshooting.
the line in the docsOn Claude Fable 5.1, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are unchanged. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/p… |
|
v2.1.248nudge |
Documentation arrivedAnthropic's documentation has since written up nudge, on preserved-thinking.
the line in the docsA common prefix edit is the per-turn nudge: a line such as "request independent reads together" or "you haven't updated the user in a while" that your code appends after each batch of tool results. To keep reminders from piling up, send ea… |
|
v2.1.261thinking-binding-controls-2026-08-01 |
Documentation arrivedAnthropic's documentation has since written up thinking-binding-controls-2026-08-01, on preserved-thinking.
the line in the docsThen confirm against the API. Add the `thinking-binding-controls-2026-08-01` beta header, set `prefix_mismatch_behavior` to `"drop_block"`, and run a normal multi-turn session through your integration on claude-fable-5-1. The following exa… |
|
v2.1.261thinking-binding-controls-2026-08-01 |
Documentation arrivedAnthropic's documentation has since written up thinking-binding-controls-2026-08-01, on preserved-thinking.
the line in the docsThen confirm against the API. Add the `thinking-binding-controls-2026-08-01` beta header, set `prefix_mismatch_behavior` to `"drop_block"`, and run a normal multi-turn session through your integration on claude-fable-5-1. The following exa… |
|
v2.1.268seq |
Documentation arrivedAnthropic's documentation has since written up seq, on preserved-thinking.
the line in the docsEarlier thinking blocks aren't in the prefix, but each thinking block records which thinking block came before it, across turns. You can remove thinking blocks from the start of the history (oldest first), from the end, or all of them. Wha… |
|
v2.1.269/pr |
Documentation arrivedAnthropic's documentation has since written up /pr, on preserved-thinking.
the line in the docs* [Rebuilds the `system` prompt](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions): the date, a mode flag, re-read project instructions, or a plugin or MCP server that connects after the first turn |
|
v2.1.269/pr |
Documentation arrivedAnthropic's documentation has since written up /pr, on preserved-thinking.
the line in the docs* [Rebuilds the `system` prompt](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions): the date, a mode flag, re-read project instructions, or a plugin or MCP server that connects after the first turn |
|
v2.1.267Client |
Documentation arrivedA small documentation edit on Local touched a line naming Client after this was published.
the line in the docs- `provenance: ContentUnavailable or ClientAsserted or SyntheticMarker or null` |
|
v2.1.267Text |
Documentation arrivedA small documentation edit on Chats touched a line naming Text after this was published.
the line in the docs- `content: array of Text or ToolUse or ToolResult` |
|
v2.1.246pages |
Documentation arrivedA small documentation edit on Deploy with Enterprise Admin Console touched a line naming pages after this was published.
the line in the docsSave the **Connection** page, where you choose your inference provider, before the other pages. The console doesn't accept **Save changes** on any other page until a connection is saved. A user who signs in to Claude Desktop and clicks **R… |
|
v2.1.268tail |
Documentation arrivedA small documentation edit on Get started touched a line naming tail after this was published.
the line in the docsIf Slack says "You don't have permission to invite people to this channel", the channel or workspace limits who can add people. In Slack, open **Channel details** → **Agents & apps** (called **Integrations** in some Slack versions), select… |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.269/config |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming /config after this was published.
the line in the docsWith `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. … |
|
v2.1.267usage |
Documentation arrivedA small documentation edit on Legal and compliance touched a line naming usage after this was published.
the line in the docsAn organization managed from the Enterprise Admin Console can also turn on usage analytics. Users' apps then report session, token, and estimated-cost counts to Anthropic, and the organization's administrators can see each user's sessions,… |
|
v2.1.268managed |
Documentation arrivedA small documentation edit on Legal and compliance touched a line naming managed after this was published.
the line in the docsThe Claude Desktop application sends operational telemetry (crash reports and product analytics) to Anthropic by default. This telemetry contains no prompt or response content. You can fully disable it through managed configuration, or fro… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.269/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Deploy with Enterprise Admin Console.
the line in the docs| An estimated cost in US dollars for each conversation and model. The app calculates the estimate on the device, at Anthropic list prices or at the rates you set under **Models** on the **Connection** page, and labels which it used (`list… |
|
v2.1.268admin |
Documentation arrivedAnthropic's documentation has since written up admin, on Claude for Government changelog.
the line in the docs* Added tenant-level Compliance API keys: tenant administrators can create, list, and revoke them on the tenant portal's **Compliance API keys** page under Settings, and a tenant-level key returns the events of every organization in the te… |
|
v2.1.235color |
Documentation arrivedA small documentation edit on Specification Enhancement Proposals (SEPs) touched a line naming color after this was published.
the line in the docs| [SEP-2640](/seps/2640-skills-extension) | Skills Extension | <Badge color="green" shape="pill">Final</Badge> | Extensions Track | 2026-04-23 | |
|
v2.1.268icon |
Documentation arrivedAnthropic's documentation has since written up icon, on Extensions Overview.
the line in the docs<Card title="modelcontextprotocol/ext-skills" icon="github" href="https://github.com/modelcontextprotocol/ext-skills"> |
|
v2.1.268icon |
Documentation arrivedAnthropic's documentation has since written up icon, on Extensions Overview.
the line in the docs<Card title="modelcontextprotocol/ext-skills" icon="github" href="https://github.com/modelcontextprotocol/ext-skills"> |
|
v2.1.251/fast |
Documentation arrivedAnthropic's documentation has since written up /fast, on Extension Support Matrix.
the line in the docs| [fast-agent](https://github.com/evalstate/fast-agent) | | | | [Partial](https://github.com/evalstate/fast-agent/blob/main/docs/docs/mcp/skills-over-mcp.md) | |
|
v2.1.248/fast |
Documentation arrivedAnthropic's documentation has since written up /fast, on Extension Support Matrix.
the line in the docs| [fast-agent](https://github.com/evalstate/fast-agent) | | | | [Partial](https://github.com/evalstate/fast-agent/blob/main/docs/docs/mcp/skills-over-mcp.md) | |
|
v2.1.267Client |
Documentation arrivedAnthropic's documentation has since written up Client, on Extension Support Matrix.
the line in the docs| [OAuth Client Credentials](/extensions/auth/oauth-client-credentials) | `io.modelcontextprotocol/oauth-client-credentials` | Machine-to-machine auth without interactive user login | |
|
v2.1.267Input |
Documentation arrivedAnthropic's documentation has since written up Input, on Use Claude Code in VS Code.
the line in the docs| Focus Input | `Cmd+Esc` (Mac) / `Ctrl+Esc` (Windows/Linux) | Toggle focus between editor and Claude | |
|
v2.1.265Tab |
Documentation arrivedAnthropic's documentation has since written up Tab, on Use Claude Code in VS Code.
the line in the docs* **Group a session from its tab**: run **Claude Code: Add Session Tab to Group** from the Command Palette, then pick or create a group. Requires Claude Code v2.1.257 or later. |
|
v2.1.268managed |
Documentation arrivedAnthropic's documentation has since written up managed, on Use Claude Code in VS Code.
the line in the docs* Select **Hooks** in the Customize section to view the [hooks](/docs/en/hooks) loaded in the session, grouped by event. You can add, edit, or remove hooks saved in your user, project, and local settings files. Hooks from other sources, su… |
|
v2.1.267Select |
Documentation arrivedAnthropic's documentation has since written up Select, on Use Claude Code in VS Code.
the line in the docs* Select **Hooks** in the Customize section to view the [hooks](/docs/en/hooks) loaded in the session, grouped by event. You can add, edit, or remove hooks saved in your user, project, and local settings files. Hooks from other sources, su… |
|
v2.1.260advisor |
Documentation arrivedA small documentation edit on All settings touched a line naming advisor after this was published.
the line in the docsPick which model answers when Claude calls the server-side [advisor tool](/docs/en/advisor). Unset it to turn the advisor off. The advisor must be at least as capable as your main model. See [Choose an advisor model](/docs/en/advisor#choos… |
|
v2.1.260/advisor |
Documentation arrivedA small documentation edit on All settings touched a line naming /advisor after this was published.
the line in the docsPick which model answers when Claude calls the server-side [advisor tool](/docs/en/advisor). Unset it to turn the advisor off. The advisor must be at least as capable as your main model. See [Choose an advisor model](/docs/en/advisor#choos… |
|
v2.1.234/advisor |
Documentation arrivedA small documentation edit on All settings touched a line naming /advisor after this was published.
the line in the docsPick which model answers when Claude calls the server-side [advisor tool](/docs/en/advisor). Unset it to turn the advisor off. The advisor must be at least as capable as your main model. See [Choose an advisor model](/docs/en/advisor#choos… |
|
v2.1.268scale |
Documentation arrivedAnthropic's documentation has since written up scale, on Keep Claude working toward a goal.
the line in the docsTo change the first interval, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars). Claude Code uses your value in place of the 30-minute interval and scales the later intervals with it. Set it to `0` to turn off check-ins and [auto… |
|
v2.1.242CLAUDE_CODE_GOAL_CHECKIN_MINUTES |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_GOAL_CHECKIN_MINUTES, on Keep Claude working toward a goal.
the line in the docsSend a message at any time to start the next turn immediately. To turn automatic retries off, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars) to `0`, which also turns [check-ins](#background-work-defers-evaluation) off. |
|
v2.1.234CLAUDE_CODE_GOAL_CHECKIN_MINUTES |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_GOAL_CHECKIN_MINUTES, on Keep Claude working toward a goal.
the line in the docsSend a message at any time to start the next turn immediately. To turn automatic retries off, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars) to `0`, which also turns [check-ins](#background-work-defers-evaluation) off. |
|
v2.1.267usage |
Documentation arrivedAnthropic's documentation has since written up usage, on Keep Claude working toward a goal.
the line in the docs* **Pause**: after a failure that a retry would only repeat, such as an API rate limit, a claude.ai [usage limit](/docs/en/errors#youve-hit-your-session-limit), or a hook that ended the turn, a notice starting with `Goal paused` names the … |
|
v2.1.248/goal clear |
Documentation arrivedAnthropic's documentation has since written up /goal clear, on Keep Claude working toward a goal.
the line in the docs| `/goal` | The previous turn finishes, or, in an interactive session, an [idle check-in](#background-work-defers-evaluation) or an [automatic retry](#other-errors-retry-or-pause-the-goal) comes due | A model confirms the condition is met … |
|
v2.1.248/goal clear |
Documentation arrivedAnthropic's documentation has since written up /goal clear, on Keep Claude working toward a goal.
the line in the docs| `/goal` | The previous turn finishes, or, in an interactive session, an [idle check-in](#background-work-defers-evaluation) or an [automatic retry](#other-errors-retry-or-pause-the-goal) comes due | A model confirms the condition is met … |
|
v2.1.269/goal |
Documentation arrivedAnthropic's documentation has since written up /goal, on Keep Claude working toward a goal.
the line in the docs| `/goal` | The previous turn finishes, or, in an interactive session, an [idle check-in](#background-work-defers-evaluation) or an [automatic retry](#other-errors-retry-or-pause-the-goal) comes due | A model confirms the condition is met … |