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 |
|---|---|---|
v2.1.246fable-5 |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming fable-5 after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.260/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.252/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.248/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.248/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.232/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.232/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.232/context |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming /context after this was published.
the line in the docsTo keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) ([turn-s… |
|
v2.1.259pin |
Documentation arrivedA small documentation edit on errors touched a line naming pin after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.259pin |
Documentation arrivedA small documentation edit on errors touched a line naming pin after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.259pin |
Documentation arrivedA small documentation edit on errors touched a line naming pin after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.259pin |
Documentation arrivedA small documentation edit on errors touched a line naming pin after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.261thinking-binding-controls-2026-08-01 |
Documentation arrivedA small documentation edit on errors touched a line naming thinking-binding-controls-2026-08-01 after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.261thinking-binding-controls-2026-08-01 |
Documentation arrivedA small documentation edit on errors touched a line naming thinking-binding-controls-2026-08-01 after this was published.
the line in the docsWithout the `thinking-binding-controls-2026-08-01` beta header the message also names that header. Keep the conversation history append-only, or send the beta header with `prefix_mismatch_behavior: "drop_block"` to drop the block and conti… |
|
v2.1.236disallowedTools |
Documentation arrivedAnthropic's documentation has since written up disallowedTools, on Create custom subagents.
the line in the docs| `disallowedTools` | No | Tools to deny, removed from inherited or specified list. An entry with a specifier, such as `Bash(git push *)`, still [removes the whole tool](#available-tools) | |
|
v2.1.234allowUnsandboxedCommands |
Documentation arrivedAnthropic's documentation has since written up allowUnsandboxedCommands, on Configure the sandboxed Bash tool.
the line in the docsclaude --settings '{"sandbox": {"enabled": true, "allowUnsandboxedCommands": false}}' |
|
v2.1.261--scope |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming --scope after this was published.
the line in the docs* To add or change the secret later, remove the server with `claude mcp remove <name>`, then add it again with `--client-secret` and the same `--scope` |
|
v2.1.259claude mcp remove |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming claude mcp remove after this was published.
the line in the docs* To add or change the secret later, remove the server with `claude mcp remove <name>`, then add it again with `--client-secret` and the same `--scope` |
|
v2.1.257skipDangerousModePermissionPrompt |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming skipDangerousModePermissionPrompt after this was published.
the line in the docsIn `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped servers without asking. Claude Code also skips the prompt in a… |
|
v2.1.257bypassPermissions |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming bypassPermissions after this was published.
the line in the docsIn `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped servers without asking. Claude Code also skips the prompt in a… |
|
v2.1.247bypassPermissions |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming bypassPermissions after this was published.
the line in the docsIn `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped servers without asking. Claude Code also skips the prompt in a… |
|
v2.1.246claude -p |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming claude -p after this was published.
the line in the docsIn `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web), Claude Code can't show that prompt: it loads project-scoped servers without asking. Claude Code also skips the prompt in a… |
|
v2.1.265Esc |
Documentation arrivedA small documentation edit on Glossary touched a line naming Esc after this was published.
the line in the docsA restore point created at each prompt you send that starts a turn. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code, conversation, or both to an earlier poin… |
|
v2.1.233/rewind |
Documentation arrivedA small documentation edit on Glossary touched a line naming /rewind after this was published.
the line in the docsA restore point created at each prompt you send that starts a turn. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code, conversation, or both to an earlier poin… |
|
v2.1.233/rewind |
Documentation arrivedA small documentation edit on Glossary touched a line naming /rewind after this was published.
the line in the docsA restore point created at each prompt you send that starts a turn. Claude Code snapshots files before every edit so a checkpoint can revert them. Press `Esc` twice or run `/rewind` to restore code, conversation, or both to an earlier poin… |
|
v2.1.257--all |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --all after this was published.
the line in the docs* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags |
|
v2.1.257allowed-tools |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming allowed-tools after this was published.
the line in the docs* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags |
|
v2.1.242--append-system-prompt |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --append-system-prompt after this was published.
the line in the docs* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags |
|
v2.1.234--append-system-prompt |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --append-system-prompt after this was published.
the line in the docs* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags |
|
v2.1.234--agents |
Documentation arrivedA small documentation edit on Fullscreen rendering touched a line naming --agents after this was published.
the line in the docs* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags |
|
v2.1.267/copy |
Documentation arrivedAnthropic's documentation has since written up /copy, on Troubleshooting.
the line in the docsWhen Claude Code runs on a remote machine over SSH, it can't run a clipboard tool on your local machine. Outside tmux, when you select text in [fullscreen rendering](/docs/en/fullscreen) or run `/copy`, Claude Code sends the text to your t… |
|
v2.1.260m365 |
Documentation arrivedAnthropic's documentation has since written up m365, on Features.
the line in the docs| [Microsoft 365](/docs/third-party/claude-desktop/connectors-m365) and [GitHub](/docs/third-party/claude-desktop/connectors-github) connectors | ✓ | ✓ | |
|
v2.1.238headers |
Documentation arrivedA small documentation edit on extended-thinking touched a line naming headers after this was published.
the line in the docsOn Claude Opus 4.5, Claude Sonnet 4.5, and earlier Claude 4 models, add the `interleaved-thinking-2025-05-14` [beta header](https://platform.claude.com/docs/en/api/beta-headers) to your API request. |
|
v2.1.238headers |
Documentation arrivedA small documentation edit on extended-thinking touched a line naming headers after this was published.
the line in the docsOn Claude Opus 4.5, Claude Sonnet 4.5, and earlier Claude 4 models, add the `interleaved-thinking-2025-05-14` [beta header](https://platform.claude.com/docs/en/api/beta-headers) to your API request. |
|
v2.1.260sshHostAllowlist |
Documentation arrivedAnthropic's documentation has since written up sshHostAllowlist, on Configuration reference.
the line in the docs| <span id="sshhostallowlist" />SSH host allowlist<br />`sshHostAllowlist` | `string[]` | MDM + Bootstrap · Beta | — | SSH hosts users may connect to for Code sessions. Empty or unset: off unless the device’s Claude Code managed-settings a… |
|
v2.1.260isClaudeCodeForDesktopEnabled |
Documentation arrivedAnthropic's documentation has since written up isClaudeCodeForDesktopEnabled, on Configuration reference.
the line in the docs| <span id="isclaudecodefordesktopenabled" />Allow Code<br />`isClaudeCodeForDesktopEnabled` | `boolean` | MDM + Bootstrap | `true` | Enable Code. Claude writes and runs code. Defaults to `true`. | |
|
v2.1.260otlpTracesEnabled |
Documentation arrivedAnthropic's documentation has since written up otlpTracesEnabled, on Changelog.
the line in the docs* Fixed Claude Code's own settings on the device (a user's or project's settings file, or a `managed-settings.json`) being able to turn OpenTelemetry trace export back on after an administrator configured a collector with traces off; with … |
|
v2.1.248src |
Documentation arrivedAnthropic's documentation has since written up src, on Security and data handling.
the line in the docs<img className="block dark:hidden" src="https://mintcdn.com/claude-ai/oY6LusJt4c576Dc3/images/claude-tag/diagrams/request-path.svg?fit=max&auto=format&n=oY6LusJt4c576Dc3&q=85&s=a7f2e0f4303072b4c8e4f3197bf0cb12" alt="Diagram showing the req… |
|
v2.1.265format |
Documentation arrivedA small documentation edit on How agent identity works touched a line naming format after this was published.
the line in the docs<img className="block dark:hidden" src="https://mintcdn.com/claude-ai/oY6LusJt4c576Dc3/images/claude-tag/diagrams/request-path.svg?fit=max&auto=format&n=oY6LusJt4c576Dc3&q=85&s=a7f2e0f4303072b4c8e4f3197bf0cb12" alt="Diagram showing the req… |
|
v2.1.248src |
Documentation arrivedA small documentation edit on How agent identity works touched a line naming src after this was published.
the line in the docs<img className="block dark:hidden" src="https://mintcdn.com/claude-ai/oY6LusJt4c576Dc3/images/claude-tag/diagrams/request-path.svg?fit=max&auto=format&n=oY6LusJt4c576Dc3&q=85&s=a7f2e0f4303072b4c8e4f3197bf0cb12" alt="Diagram showing the req… |
|
v2.1.246sandbox.credentials |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming sandbox.credentials after this was published.
the line in the docsAn approval for `sandbox.credentials` or `sandbox.network.tlsTerminate` also covers the [`sandbox.network.allowedDomains`](/docs/en/settings-reference#sandbox-network-alloweddomains) entries in those same delivered settings, because both s… |
|
v2.1.232sandbox.network.allowedDomains |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming sandbox.network.allowedDomains after this was published.
the line in the docsAn approval for `sandbox.credentials` or `sandbox.network.tlsTerminate` also covers the [`sandbox.network.allowedDomains`](/docs/en/settings-reference#sandbox-network-alloweddomains) entries in those same delivered settings, because both s… |
|
v2.1.259pinned |
Documentation arrivedAnthropic's documentation has since written up pinned, on Connect Claude Code to an LLM gateway.
the line in the docs* **Model capabilities**: if you pin a model ID that your Claude Code version doesn't recognize, features such as effort levels or extended thinking can stay disabled on it. Declare what the model supports with [`ANTHROPIC_DEFAULT_OPUS_MOD… |
|
v2.1.232capabilities |
Documentation arrivedAnthropic's documentation has since written up capabilities, on Connect Claude Code to an LLM gateway.
the line in the docs* **Model capabilities**: if you pin a model ID that your Claude Code version doesn't recognize, features such as effort levels or extended thinking can stay disabled on it. Declare what the model supports with [`ANTHROPIC_DEFAULT_OPUS_MOD… |
|
v2.1.261ANTHROPIC_DEFAULT_HAIKU_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_DEFAULT_HAIKU_MODEL, on Connect Claude Code to an LLM gateway.
the line in the docs* **Model versions**: pin `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL` as in [Pin model versions](/docs/en/google-vertex-ai#5-pin-model-versions). Setting `ANTHROPIC_DEFAULT_HAIKU_MO… |
|
v2.1.260ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_HEADERS, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.260ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_HEADERS, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.251ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_HEADERS, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.248apiKeyHelper |
Documentation arrivedAnthropic's documentation has since written up apiKeyHelper, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.234apiKeyHelper |
Documentation arrivedAnthropic's documentation has since written up apiKeyHelper, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |