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 |
|---|---|---|
v2.1.307base_url |
Documentation arrivedAnthropic's documentation has since written up base_url, on Build an MCP client.
the line in the docs> let base_url = |
|
v2.1.314/btw |
Documentation arrivedAnthropic's documentation has since written up /btw, on Claude Code changelog.
the line in the docs* \[VSCode] Fixed saved `/btw` side-question history being deleted too early while a settings file has errors |
|
v2.1.314/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Claude Code changelog.
the line in the docs* Fixed a rare case where resuming a conversation did not restore its plan, when `/clear` or `/resume` had been run while part of that conversation was still being saved |
|
v2.1.312/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Claude Code changelog.
the line in the docs* Fixed a rare case where resuming a conversation did not restore its plan, when `/clear` or `/resume` had been run while part of that conversation was still being saved |
|
v2.1.311/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Claude Code changelog.
the line in the docs* Fixed a rare case where resuming a conversation did not restore its plan, when `/clear` or `/resume` had been run while part of that conversation was still being saved |
|
v2.1.314/permissions |
Documentation arrivedAnthropic's documentation has since written up /permissions, on Claude Code changelog.
the line in the docs* Fixed a managed `autoMode.allow` list without `"$defaults"` getting the built-in exceptions back from a host app's `--settings`, a first rule added in `/permissions`, or `/auto-mode-setup` |
|
v2.1.309--restricted |
Documentation arrivedAnthropic's documentation has since written up --restricted, on Claude Code changelog.
the line in the docs* Fixed `--restricted` sessions uploading files from outside the working directories when a Read allow rule covered them |
|
v2.1.314claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Claude Code changelog.
the line in the docs* Fixed `claude auth login` refusing to run where managed settings require a Claude apps gateway; in a terminal it now shows the gateway sign-in |
|
v2.1.314availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Claude Code changelog.
the line in the docs* Fixed the Claude apps gateway not checking every model a request names against `availableModels`, `deniedModels` and `models`; a request that names a blocked model now gets a 400 naming the field |
|
v2.1.311SHELL |
Documentation arrivedAnthropic's documentation has since written up SHELL, on Claude Code changelog.
the line in the docs* Fixed bash scripts started from the Bash tool stopping after their first command when `SHELLOPTS` is exported |
|
v2.1.311SHELL |
Documentation arrivedAnthropic's documentation has since written up SHELL, on Claude Code changelog.
the line in the docs* Fixed bash scripts started from the Bash tool stopping after their first command when `SHELLOPTS` is exported |
|
v2.1.314/ultrareview |
Documentation arrivedAnthropic's documentation has since written up /ultrareview, on Claude Code changelog.
the line in the docs* Improved the messages shown when `/ultrareview`, a cloud session or a cloud agent finds no GitHub remote: they now say to create a repository at [https://github.com/new](https://github.com/new), and `/ultrareview` no longer suggests a `g… |
|
v2.1.311/diff |
Documentation arrivedAnthropic's documentation has since written up /diff, on Claude Code changelog.
the line in the docs* Improved `/diff` on large repositories: each refresh usually runs one fewer full-repository git command, and refreshes are spaced out when git is slow |
|
v2.1.314/config |
Documentation arrivedAnthropic's documentation has since written up /config, on MCP, plugins, skills, and hooks.
the line in the docsTokens are stored on the device, encrypted with the operating system's secure storage (see [Credentials](https://claude.com/docs/third-party/claude-desktop/data-storage.md#credentials)), and refreshed in the background before they expire. … |
|
v2.1.314fable |
Documentation arrivedAnthropic's documentation has since written up fable, on dreams.
the line in the docs| Research preview | Claude API | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.c… |
|
v2.1.288output_config.format |
Documentation arrivedA small documentation edit on structured-outputs touched a line naming output_config.format after this was published.
the line in the docs* **[Citations](https://platform.claude.com/docs/en/build-with-claude/citations):** Citations require interleaving citation blocks with text, which conflicts with strict JSON schema constraints. The API returns a 400 error if citations are… |
|
v2.1.288ANTHROPIC_GOOGLE_CLOUD_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_GOOGLE_CLOUD_BASE_URL, on anthropic-managed.
the line in the docs| Base URL | `ANTHROPIC_GOOGLE_CLOUD_BASE_URL` | Derived from the project, location, and workspace ID | |
|
v2.1.310headersHelper |
Documentation arrivedA small documentation edit on Write a credential helper touched a line naming headersHelper after this was published.
the line in the docs> `inferenceCredentialHelper` supplies credentials for the inference connection only. An MCP server deployed through [`managedMcpServers`](https://claude.com/docs/third-party/claude-desktop/configuration#managedmcpservers) uses the separat… |
|
v2.1.311NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Troubleshoot installation and login.
the line in the docs> export NODE_EXTRA_CA_CERTS=/path/to/corporate-ca.pem |
|
v2.1.310NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Troubleshoot installation and login.
the line in the docs> export NODE_EXTRA_CA_CERTS=/path/to/corporate-ca.pem |
|
v2.1.310NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Troubleshoot installation and login.
the line in the docs> export NODE_EXTRA_CA_CERTS=/path/to/corporate-ca.pem |
|
v2.1.309HTTP_PROXY |
Documentation arrivedAnthropic's documentation has since written up HTTP_PROXY, on Troubleshoot installation and login.
the line in the docs> export HTTP_PROXY=http://proxy.example.com:8080 |
|
v2.1.311/doctor |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming /doctor after this was published.
the line in the docs* **Usage**: on a Pro, Max, Ultra, Team, or Enterprise plan, the [changes `/usage` recommends](https://code.claude.com/docs/en/costs#plan-usage-breakdown) to lower your plan usage, measured over the last 7 days. Claude proposes the changes… |
|
v2.1.311CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS, on Choose a permission mode.
the line in the docs> export CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS=1 |
|
v2.1.311CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS, on Choose a permission mode.
the line in the docs> export CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS=1 |
|
v2.1.312.claude/settings.local.json |
Documentation arrivedAnthropic's documentation has since written up .claude/settings.local.json, on Choose a permission mode.
the line in the docs> The extension never reads a project's `.claude/settings.json` or `.claude/settings.local.json` for the starting permission mode. When `claudeCode.claudeProcessWrapper` is set, items 3 and 4 don't apply: those conversations start in Manua… |
|
v2.1.311--all |
Documentation arrivedAnthropic's documentation has since written up --all, on Choose a permission mode.
the line in the docs> * `bypassPermissions`: appears after you start with `--permission-mode bypassPermissions`, `--dangerously-skip-permissions`, `--allow-dangerously-skip-permissions`, or `permissions.defaultMode: "bypassPermissions"` in [user, `--settings`… |
|
v2.1.311--permission-mode |
Documentation arrivedAnthropic's documentation has since written up --permission-mode, on Choose a permission mode.
the line in the docs> claude -p "Run the test suite and fix any failures" --permission-mode auto |
|
v2.1.309ANTHROPIC_VERTEX_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_VERTEX_BASE_URL, on Connect Claude Code to an LLM gateway.
the line in the docs> export ANTHROPIC_VERTEX_BASE_URL=https://llm-gateway.example.com/vertex |
|
v2.1.309ANTHROPIC_BEDROCK_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BEDROCK_BASE_URL, on Connect Claude Code to an LLM gateway.
the line in the docs> export ANTHROPIC_BEDROCK_BASE_URL=https://llm-gateway.example.com/bedrock |
|
v2.1.309ANTHROPIC_BEDROCK_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BEDROCK_BASE_URL, on Connect Claude Code to an LLM gateway.
the line in the docs> export ANTHROPIC_BEDROCK_BASE_URL=https://llm-gateway.example.com/bedrock |
|
v2.1.311--settings |
Documentation arrivedAnthropic's documentation has since written up --settings, on Interactive mode.
the line in the docs> Then pass the file to `--settings`. It applies to that session only: |
|
v2.1.311--settings |
Documentation arrivedAnthropic's documentation has since written up --settings, on Interactive mode.
the line in the docs> Then pass the file to `--settings`. It applies to that session only: |
|
v2.1.309CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.309CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.307CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.307CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.307CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.307CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.301CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedA small documentation edit on Claude Code GitHub Actions touched a line naming CLAUDE_CODE_OAUTH_TOKEN after this was published.
the line in the docs* `CLAUDE_CODE_OAUTH_TOKEN`: an OAuth token that authenticates with your Claude subscription, available on Pro, Max, Ultra, Team, and Enterprise plans. Generate one by running `claude setup-token` locally. See [Generate a long-lived token]… |
|
v2.1.311/code-review |
Documentation arrivedAnthropic's documentation has since written up /code-review, on Feature availability.
the line in the docs| [Code Review](https://code.claude.com/docs/en/code-review.md) | ✗ | ✗ | ✗ | ✓ | ✓ | |
|
v2.1.312dontAsk |
Documentation arrivedAnthropic's documentation has since written up dontAsk, on Desktop application.
the line in the docs| Permission modes | All modes including `dontAsk` | Manual, Accept edits, Plan, and Auto. Bypass permissions appears in the mode selector once enabled: through the Settings toggle on Pro, Max, and Ultra plans, or through organization poli… |
|
v2.1.311--dangerously-skip-permissions |
Documentation arrivedAnthropic's documentation has since written up --dangerously-skip-permissions, on Desktop application.
the line in the docs| **Bypass permissions** | `bypassPermissions` | Claude runs without permission prompts, except for the [actions no mode auto-approves](https://code.claude.com/docs/en/permission-modes.md#actions-no-mode-auto-approves), safety classifiers … |
|
v2.1.309hookSpecificOutput |
Documentation arrivedAnthropic's documentation has since written up hookSpecificOutput, on Manage costs effectively.
the line in the docs> '{hookSpecificOutput: {hookEventName: "PreToolUse", updatedInput: (.tool_input + {command: $filtered})}}' |
|
v2.1.311/ide |
Documentation arrivedAnthropic's documentation has since written up /ide, on Enterprise-Managed Authorization.
the line in the docs| [Janssen Project](https://docs.jans.io/stable/janssen-server/auth-server/endpoints/identity-assertion-authz-grant/) | Available | Available | Since 2.2.0, off by default behind the `identity_assertion_authz_grant` feature flag, targeting… |
|
v2.1.311/ide |
Documentation arrivedAnthropic's documentation has since written up /ide, on Enterprise-Managed Authorization.
the line in the docs| [Janssen Project](https://docs.jans.io/stable/janssen-server/auth-server/endpoints/identity-assertion-authz-grant/) | Available | Available | Since 2.2.0, off by default behind the `identity_assertion_authz_grant` feature flag, targeting… |
|
v2.1.309--setting-sources |
Documentation arrivedAnthropic's documentation has since written up --setting-sources, on Claude Code changelog.
the line in the docs* Fixed a settings file excluded with `--setting-sources` still supplying some settings, such as auto mode rules and saved permission consents |
|
v2.1.311--continue |
Documentation arrivedAnthropic's documentation has since written up --continue, on Claude Code changelog.
the line in the docs* Fixed sandbox protections not applying to a worktree entered by `claude -p --resume` or `--continue` |
|
v2.1.311/security-review |
Documentation arrivedAnthropic's documentation has since written up /security-review, on Claude Code changelog.
the line in the docs* Improved session auto-titles: a session that starts with a skill or a prompt-based command such as `/security-review` now gets a title from it instead of staying untitled |
|
v2.1.311/design-sync |
Documentation arrivedAnthropic's documentation has since written up /design-sync, on Claude Code changelog.
the line in the docs* Improved the `/design-sync` upload prompt to show the folder, the project and the files it will upload or delete |