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 |
|---|---|---|
v2.1.301CLAUDE_CODE_SHELL_PREFIX |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SHELL_PREFIX, on Run Claude Code behind a corporate launcher.
the line in the docs`CLAUDE_CODE_PROCESS_WRAPPER` wraps Claude Code's own processes and passes the command through as separate argv tokens for the launcher to `exec`. [`CLAUDE_CODE_SHELL_PREFIX`](https://code.claude.com/docs/en/env-vars) wraps the shell comma… |
|
v2.1.301CLAUDE_CODE_SHELL_PREFIX |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SHELL_PREFIX, on Run Claude Code behind a corporate launcher.
the line in the docs`CLAUDE_CODE_PROCESS_WRAPPER` wraps Claude Code's own processes and passes the command through as separate argv tokens for the launcher to `exec`. [`CLAUDE_CODE_SHELL_PREFIX`](https://code.claude.com/docs/en/env-vars) wraps the shell comma… |
|
v2.1.288CLAUDE_CODE_SHELL_PREFIX |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SHELL_PREFIX, on Run Claude Code behind a corporate launcher.
the line in the docs`CLAUDE_CODE_PROCESS_WRAPPER` wraps Claude Code's own processes and passes the command through as separate argv tokens for the launcher to `exec`. [`CLAUDE_CODE_SHELL_PREFIX`](https://code.claude.com/docs/en/env-vars) wraps the shell comma… |
|
v2.1.290/simplify |
Documentation arrivedAnthropic's documentation has since written up /simplify, on Review locally with /code-review.
the line in the docs* **Use a neighboring command**: [`/simplify`](https://code.claude.com/docs/en/commands) reviews for cleanup only and applies its fixes, and [`/verify`](https://code.claude.com/docs/en/commands) runs your app to confirm a change works |
|
v2.1.305enabledPlugins |
Documentation arrivedAnthropic's documentation has since written up enabledPlugins, on Configure cloud environments.
the line in the docs| Plugins and marketplaces declared in your repo's `.claude/settings.json` | No | A cloud session doesn't install the plugins a repository turns on under [`enabledPlugins`](https://code.claude.com/docs/en/settings-reference#enabledplugins)… |
|
v2.1.300/remote-env |
Documentation arrivedAnthropic's documentation has since written up /remote-env, on Configure cloud environments.
the line in the docs* From the CLI, Claude Code uses your [`/remote-env` pick](#select-an-environment-from-the-cli), or falls back to the Anthropic-hosted environment when your list has one, and otherwise to the first environment in your list that isn't a bri… |
|
v2.1.295/remote-env |
Documentation arrivedAnthropic's documentation has since written up /remote-env, on Configure cloud environments.
the line in the docs* From the CLI, Claude Code uses your [`/remote-env` pick](#select-an-environment-from-the-cli), or falls back to the Anthropic-hosted environment when your list has one, and otherwise to the first environment in your list that isn't a bri… |
|
v2.1.299CLAUDE_CODE_SAFE_MODE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SAFE_MODE, on CLI reference.
the line in the docs| `--safe-mode` | Start with all customizations disabled to troubleshoot a broken configuration: CLAUDE.md, skills, plugins, hooks, MCP servers, custom commands and agents, output styles, workflows, custom themes, custom keybindings, statu… |
|
v2.1.301CLAUDE_CODE_DEBUG_LOGS_DIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DEBUG_LOGS_DIR, on CLI reference.
the line in the docs| `--debug-file <path>` | Write debug logs to a specific file path. Implicitly enables debug mode. Takes precedence over `CLAUDE_CODE_DEBUG_LOGS_DIR` | `claude --debug-file /tmp/claude-debug.log` | |
|
v2.1.283CLAUDE_CODE_DEBUG_LOGS_DIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DEBUG_LOGS_DIR, on CLI reference.
the line in the docs| `--debug-file <path>` | Write debug logs to a specific file path. Implicitly enables debug mode. Takes precedence over `CLAUDE_CODE_DEBUG_LOGS_DIR` | `claude --debug-file /tmp/claude-debug.log` | |
|
v2.1.288claude auto-mode config |
Documentation arrivedAnthropic's documentation has since written up claude auto-mode config, on CLI reference.
the line in the docs| `claude auto-mode defaults` | Print the built-in [auto mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) classifier rules as JSON. Use `claude auto-mode config` to see your effective config with … |
|
v2.1.288claude auto-mode defaults |
Documentation arrivedAnthropic's documentation has since written up claude auto-mode defaults, on CLI reference.
the line in the docs| `claude auto-mode defaults` | Print the built-in [auto mode](https://code.claude.com/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) classifier rules as JSON. Use `claude auto-mode config` to see your effective config with … |
|
v2.1.307claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Use Claude Code in the cloud.
the line in the docs> `--cloud` requires an Anthropic account. It's not available when Claude Code is configured for Amazon Bedrock, Google Cloud's Agent Platform, or another third-party provider. An [LLM gateway](https://code.claude.com/docs/en/llm-gateway) … |
|
v2.1.307claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Use Claude Code in the cloud.
the line in the docs> `--cloud` requires an Anthropic account. It's not available when Claude Code is configured for Amazon Bedrock, Google Cloud's Agent Platform, or another third-party provider. An [LLM gateway](https://code.claude.com/docs/en/llm-gateway) … |
|
v2.1.307claude auth logout |
Documentation arrivedAnthropic's documentation has since written up claude auth logout, on Claude apps gateway deployment and operations.
the line in the docs| Startup exits with `Administrator policy requires a Cloud gateway sign-in on this machine` | The developer's environment sets `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`, their settings configure an [`apiKeyHelper`](https://code.claude… |
|
v2.1.285CLAUDE_GATEWAY_ALLOW_LOOPBACK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_ALLOW_LOOPBACK, on Claude apps gateway configuration.
the line in the docs| `issuer` | Yes | OIDC discovery base. Must serve discovery at `/.well-known/openid-configuration`. Use HTTPS in production; the gateway accepts an `http://` issuer. A loopback issuer such as `http://localhost:8081` is rejected by the [SS… |
|
v2.1.284telemetry.forward_to |
Documentation arrivedAnthropic's documentation has since written up telemetry.forward_to, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs* **Telemetry destination**: in sessions signed in through `/login`, the CLI sends its OTLP/HTTP exports to the gateway rather than to a locally set `OTEL_EXPORTER_OTLP_ENDPOINT`, unless a policy [names your collector as the endpoint](http… |
|
v2.1.284telemetry.forward_to |
Documentation arrivedAnthropic's documentation has since written up telemetry.forward_to, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs* **Telemetry destination**: in sessions signed in through `/login`, the CLI sends its OTLP/HTTP exports to the gateway rather than to a locally set `OTEL_EXPORTER_OTLP_ENDPOINT`, unless a policy [names your collector as the endpoint](http… |
|
v2.1.304--bare |
Documentation arrivedAnthropic's documentation has since written up --bare, on Authentication.
the line in the docs[Bare mode](https://code.claude.com/docs/en/headless.md#start-faster-with-bare-mode) does not read `CLAUDE_CODE_OAUTH_TOKEN`. If your script passes `--bare`, authenticate with `ANTHROPIC_API_KEY` or an `apiKeyHelper` instead. |
|
v2.1.292resumeFromRunId |
Documentation arrivedAnthropic's documentation has since written up resumeFromRunId, on Agent SDK reference - TypeScript.
the line in the docs| `resumeFromRunId` | `string` | Run ID of a prior `Workflow` invocation to resume. Completed `agent()` calls with unchanged inputs usually return cached results; the rest run live. [Resume after a pause](https://code.claude.com/docs/en/wo… |
|
v2.1.286CLAUDE_CODE_CHILD_SESSION |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_CHILD_SESSION, on Agent SDK reference - TypeScript.
the line in the docsIf your application runs prompts on its own schedule, declare each run so Claude Code frames the turn to the model as a scheduled task rather than as live input from the user. Start the session with `CLAUDE_CODE_HOST_SCHEDULED_RUN` set to … |
|
v2.1.284CLAUDE_CODE_CHILD_SESSION |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_CHILD_SESSION, on Agent SDK reference - TypeScript.
the line in the docsIf your application runs prompts on its own schedule, declare each run so Claude Code frames the turn to the model as a scheduled task rather than as live input from the user. Start the session with `CLAUDE_CODE_HOST_SCHEDULED_RUN` set to … |
|
v2.1.307CLAUDE_CODE_RESUME_INTERRUPTED_TURN |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_RESUME_INTERRUPTED_TURN, on Agent SDK reference - TypeScript.
the line in the docs* **The prompt Claude Code generates to continue an interrupted turn under [`CLAUDE_CODE_RESUME_INTERRUPTED_TURN`](https://code.claude.com/docs/en/env-vars)**: when the interrupted turn's last prompt is a regular message you sent, whether … |
|
v2.1.307CLAUDE_CODE_RESUME_INTERRUPTED_TURN |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_RESUME_INTERRUPTED_TURN, on Agent SDK reference - TypeScript.
the line in the docs* **The prompt Claude Code generates to continue an interrupted turn under [`CLAUDE_CODE_RESUME_INTERRUPTED_TURN`](https://code.claude.com/docs/en/env-vars)**: when the interrupted turn's last prompt is a regular message you sent, whether … |
|
v2.1.307autoCompactWindow |
Documentation arrivedAnthropic's documentation has since written up autoCompactWindow, on Agent SDK reference - TypeScript.
the line in the docs| `autoCompactWindow` | No | Lower the [auto-compact window](https://code.claude.com/docs/en/sub-agents.md#subagent-auto-compact-window) for this agent when it runs as a subagent, to a token count from `100000` to `1000000`. Requires TypeS… |
|
v2.1.307/output-style |
Documentation arrivedAnthropic's documentation has since written up /output-style, on Agent SDK reference - TypeScript.
the line in the docs| `reloadOutputStyles()` | Re-reads [output styles](https://code.claude.com/docs/en/output-styles.md) from disk, so a style file you add or edit mid-session becomes available to the running session. Resolves with an [`SDKControlReloadOutpu… |
|
v2.1.307CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, on Agent SDK reference - TypeScript.
the line in the docs| `managedSettings` | `Settings` | `undefined` | Policy-tier settings your host process supplies to the spawned session. On machines with admin-deployed managed settings, Claude Code ignores these unless the admin's highest-priority manage… |
|
v2.1.307CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, on Agent SDK reference - TypeScript.
the line in the docs| `managedSettings` | `Settings` | `undefined` | Policy-tier settings your host process supplies to the spawned session. On machines with admin-deployed managed settings, Claude Code ignores these unless the admin's highest-priority manage… |
|
v2.1.290--strict-mcp-config |
Documentation arrivedAnthropic's documentation has since written up --strict-mcp-config, on Agent SDK reference - Python.
the line in the docs| `strict_mcp_config` | `bool` | `False` | When `True`, use only the servers passed in `mcp_servers` and ignore project `.mcp.json`, user settings, plugin-provided MCP servers, and [claude.ai connectors](https://code.claude.com/docs/en/mcp… |
|
v2.1.288--strict-mcp-config |
Documentation arrivedAnthropic's documentation has since written up --strict-mcp-config, on Agent SDK reference - Python.
the line in the docs| `strict_mcp_config` | `bool` | `False` | When `True`, use only the servers passed in `mcp_servers` and ignore project `.mcp.json`, user settings, plugin-provided MCP servers, and [claude.ai connectors](https://code.claude.com/docs/en/mcp… |
|
v2.1.307set_model |
Documentation arrivedAnthropic's documentation has since written up set_model, on Configure permissions.
the line in the docsIf you switch a session that's in auto mode to a model that auto mode doesn't support, using [`set_model()`](https://code.claude.com/docs/en/agent-sdk/python#claudesdkclient), [`setModel()`](https://code.claude.com/docs/en/agent-sdk/typesc… |
|
v2.1.295BETA_TRACING_ENDPOINT |
Documentation arrivedAnthropic's documentation has since written up BETA_TRACING_ENDPOINT, on Observability with OpenTelemetry.
the line in the docs* **`claude_code.hook`:** wraps each [hook](https://code.claude.com/docs/en/agent-sdk/hooks.md) execution. Requires detailed beta tracing (`ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`), a pair that also [changes where your … |
|
v2.1.295ENABLE_BETA_TRACING_DETAILED |
Documentation arrivedAnthropic's documentation has since written up ENABLE_BETA_TRACING_DETAILED, on Observability with OpenTelemetry.
the line in the docs* **`claude_code.hook`:** wraps each [hook](https://code.claude.com/docs/en/agent-sdk/hooks.md) execution. Requires detailed beta tracing (`ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`), a pair that also [changes where your … |
|
v2.1.304CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC, on Set up Claude Code for your organization.
the line in the docs| [Telemetry opt-out](https://code.claude.com/docs/en/data-usage.md#telemetry-services) | Turn off Anthropic-bound usage metrics, error reports, and surveys on every device | `env` with `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` set to `1`… |
|
v2.1.295minimumVersion |
Documentation arrivedAnthropic's documentation has since written up minimumVersion, on Set up Claude Code for your organization.
the line in the docs| [Version floor](https://code.claude.com/docs/en/settings-reference.md#minimumversion) | Prevent auto-update from installing below an org-wide minimum | `minimumVersion` | |
|
v2.1.300allowedProviders |
Documentation arrivedAnthropic's documentation has since written up allowedProviders, on Set up Claude Code for your organization.
the line in the docs| [Provider restrictions](https://code.claude.com/docs/en/settings-reference.md#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next co… |
|
v2.1.296allowedProviders |
Documentation arrivedAnthropic's documentation has since written up allowedProviders, on Set up Claude Code for your organization.
the line in the docs| [Provider restrictions](https://code.claude.com/docs/en/settings-reference.md#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next co… |
|
v2.1.288disableCommandPluginSources |
Documentation arrivedAnthropic's documentation has since written up disableCommandPluginSources, on Set up Claude Code for your organization.
the line in the docs| [Plugin marketplace control](https://code.claude.com/docs/en/plugins/org.md#restrict-what-users-can-install) | Restrict which marketplace sources users can add and install from, reject the CLI flags that sideload plugins, agents, and MCP… |
|
v2.1.288CLAUDE_CODE_ACCESSIBILITY |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_ACCESSIBILITY, on Use Claude Code with a screen reader.
the line in the docsScreen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersReducedMotion`, or `theme` from the [Accessibility settings](#… |
|
v2.1.307NO_PROXY |
Documentation arrivedAnthropic's documentation has since written up NO_PROXY, on Network proxy.
the line in the docs* **Cowork's sandboxed shell when every host is allowed.** With a list of hosts in [`coworkEgressAllowedHosts`](https://claude.com/docs/third-party/claude-desktop/web-tools), the shell's commands reach the network only through a filter ins… |
|
v2.1.307NO_PROXY |
Documentation arrivedAnthropic's documentation has since written up NO_PROXY, on Network proxy.
the line in the docs* **Cowork's sandboxed shell when every host is allowed.** With a list of hosts in [`coworkEgressAllowedHosts`](https://claude.com/docs/third-party/claude-desktop/web-tools), the shell's commands reach the network only through a filter ins… |
|
v2.1.300selfHosted |
Documentation arrivedAnthropic's documentation has since written up selfHosted, on Configuration implementation.
the line in the docsEach key's entry in the reference gives its label and a one-line reason. The [published schemas](https://claude.com/docs/third-party/claude-desktop/bootstrap.md#response-schema) carry the self-hosted word (`server`, `reported`, `client`, o… |
|
v2.1.307forceLoginOrgUUID |
Documentation arrivedAnthropic's documentation has since written up forceLoginOrgUUID, on Deploy with Enterprise Admin Console.
the line in the docs* **Allow only your organization:** set [`forceLoginOrgUUID`](https://claude.com/docs/cowork/hipaa-setup#what-each-claude-desktop-key-does) to your Claude organization's ID. This ID isn't [`deploymentOrganizationUuid`](https://claude.com/d… |
|
v2.1.305headersHelper |
Documentation arrivedA small documentation edit on Web search and web fetch touched a line naming headersHelper after this was published.
the line in the docsSet the per-entry `toolPolicy` to `"allow"` so users aren't prompted to approve each search. `headersHelper` is an executable that prints the auth header as a JSON object to stdout; it follows the same execution model as [`inferenceCredent… |
|
v2.1.300headersHelper |
Documentation arrivedA small documentation edit on Web search and web fetch touched a line naming headersHelper after this was published.
the line in the docsSet the per-entry `toolPolicy` to `"allow"` so users aren't prompted to approve each search. `headersHelper` is an executable that prints the auth header as a JSON object to stdout; it follows the same execution model as [`inferenceCredent… |
|
v2.1.299headersHelper |
Documentation arrivedA small documentation edit on Web search and web fetch touched a line naming headersHelper after this was published.
the line in the docsSet the per-entry `toolPolicy` to `"allow"` so users aren't prompted to approve each search. `headersHelper` is an executable that prints the auth header as a JSON object to stdout; it follows the same execution model as [`inferenceCredent… |
|
v2.1.307/update |
Documentation arrivedAnthropic's documentation has since written up /update, on Connect Claude Code to tools via MCP.
the line in the docs| `input_required` | Reads `inputRequests`, an object that maps a key you choose to `{ method, params }`. Claude Code answers each key once through `tasks/update` with `{ taskId, inputResponses }`, where `inputResponses` maps the same key … |
|
v2.1.296CLAUDE_AUTO_BACKGROUND_TASKS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_AUTO_BACKGROUND_TASKS, on Connect Claude Code to tools via MCP.
the line in the docs* [`CLAUDE_AUTO_BACKGROUND_TASKS`](/docs/en/env-vars) at `1` |
|
v2.1.292CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS, on Connect Claude Code to tools via MCP.
the line in the docs* Set the [`CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS`](/docs/en/env-vars) environment variable in milliseconds to change the threshold, or set it to `0` to turn automatic backgrounding off. With `0`, Claude also [waits for MCP tasks](#make-claud… |
|
v2.1.288CLAUDE_CODE_DISABLE_BACKGROUND_TASKS |
Documentation arrivedA small documentation edit on Review locally with /code-review touched a line naming CLAUDE_CODE_DISABLE_BACKGROUND_TASKS after this was published.
the line in the docs* Set [`CLAUDE_CODE_DISABLE_BACKGROUND_TASKS`](/docs/en/env-vars) to `1`, which also turns off other background task features |