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 |
|---|---|---|
v2.1.268local_command |
Documentation arrivedAnthropic's documentation has since written up local_command, on Agent SDK reference - TypeScript.
the line in the docslocal_command?: string; |
|
v2.1.259user_message_uuids |
Documentation arrivedAnthropic's documentation has since written up user_message_uuids, on Agent SDK reference - TypeScript.
the line in the docsClaude Code sets `user_message_uuid` and `user_message_uuids` on the turn's first assistant message, under the conditions in [`user_message_uuid`](#user_message_uuid). When Claude Code re-runs a turn that a restart interrupted, the re-run'… |
|
v2.1.259user_message_uuids |
Documentation arrivedAnthropic's documentation has since written up user_message_uuids, on Agent SDK reference - TypeScript.
the line in the docsClaude Code sets `user_message_uuid` and `user_message_uuids` on the turn's first assistant message, under the conditions in [`user_message_uuid`](#user_message_uuid). When Claude Code re-runs a turn that a restart interrupted, the re-run'… |
|
v2.1.268resume_reason |
Documentation arrivedAnthropic's documentation has since written up resume_reason, on Agent SDK reference - TypeScript.
the line in the docsresume_reason?: string; |
|
v2.1.268resume_reason |
Documentation arrivedAnthropic's documentation has since written up resume_reason, on Agent SDK reference - TypeScript.
the line in the docsresume_reason?: string; |
|
v2.1.268resume_reason |
Documentation arrivedAnthropic's documentation has since written up resume_reason, on Agent SDK reference - TypeScript.
the line in the docsresume_reason?: string; |
|
v2.1.281updatedPermissions |
Documentation arrivedAnthropic's documentation has since written up updatedPermissions, on Agent SDK reference - TypeScript.
the line in the docs| `suggestions` | [`PermissionUpdate`](#permissionupdate)`[]` | Suggested permission updates so the user is not prompted again for this tool. Bash prompts include a suggestion with the `localSettings` [destination](#permissionupdatedestina… |
|
v2.1.268suppressAlwaysAllowRule |
Documentation arrivedAnthropic's documentation has since written up suppressAlwaysAllowRule, on Agent SDK reference - TypeScript.
the line in the docssuppressAlwaysAllowRule?: boolean; |
|
v2.1.268defaultToNo |
Documentation arrivedAnthropic's documentation has since written up defaultToNo, on Agent SDK reference - TypeScript.
the line in the docsdefaultToNo?: boolean; |
|
v2.1.261reloadOutputStyles |
Documentation arrivedAnthropic's documentation has since written up reloadOutputStyles, on Agent SDK reference - TypeScript.
the line in the docsreloadOutputStyles(): Promise<SDKControlReloadOutputStylesResponse>; |
|
v2.1.282bypassPermissions |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming bypassPermissions after this was published.
the line in the docsIn the TypeScript SDK, if you set `allowDangerouslySkipPermissions: true` alongside `permissionMode: 'plan'`, file edits and shell commands that modify files still reach your `canUseTool` callback. The option lets you switch to `bypassPerm… |
|
v2.1.274OTEL_LOG_RAW_API_BODIES |
Documentation arrivedAnthropic's documentation has since written up OTEL_LOG_RAW_API_BODIES, on Modifying system prompts.
the line in the docs* **Raw request logging**: set [`OTEL_LOG_RAW_API_BODIES`](/docs/en/monitoring-usage#api-request-body-event) to `file:<dir>`. Claude Code writes each request body to that directory. |
|
v2.1.274OTEL_LOG_RAW_API_BODIES |
Documentation arrivedAnthropic's documentation has since written up OTEL_LOG_RAW_API_BODIES, on Modifying system prompts.
the line in the docs* **Raw request logging**: set [`OTEL_LOG_RAW_API_BODIES`](/docs/en/monitoring-usage#api-request-body-event) to `file:<dir>`. Claude Code writes each request body to that directory. |
|
v2.1.267process.env |
Documentation arrivedAnthropic's documentation has since written up process.env, on Modifying system prompts.
the line in the docsPass settings keys through the [`settings`](/docs/en/agent-sdk/typescript#options) option in TypeScript or [`settings`](/docs/en/agent-sdk/python#claudeagentoptions) in Python, and environment variables through the `env` option. In TypeScr… |
|
v2.1.282CLAUDE_CONFIG_DIR |
Documentation arrivedA small documentation edit on Hosting the Agent SDK touched a line naming CLAUDE_CONFIG_DIR after this was published.
the line in the docs* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory and you don't pass a [`SessionStore`](/docs/en/agent-sdk/session-stor… |
|
v2.1.281CLAUDE_CONFIG_DIR |
Documentation arrivedA small documentation edit on Hosting the Agent SDK touched a line naming CLAUDE_CONFIG_DIR after this was published.
the line in the docs* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory and you don't pass a [`SessionStore`](/docs/en/agent-sdk/session-stor… |
|
v2.1.281CLAUDE_CONFIG_DIR |
Documentation arrivedA small documentation edit on Hosting the Agent SDK touched a line naming CLAUDE_CONFIG_DIR after this was published.
the line in the docs* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory and you don't pass a [`SessionStore`](/docs/en/agent-sdk/session-stor… |
|
v2.1.274CLAUDE_CONFIG_DIR |
Documentation arrivedA small documentation edit on Hosting the Agent SDK touched a line naming CLAUDE_CONFIG_DIR after this was published.
the line in the docs* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory and you don't pass a [`SessionStore`](/docs/en/agent-sdk/session-stor… |
|
v2.1.283models |
Documentation arrivedAnthropic's documentation has since written up models, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283models |
Documentation arrivedAnthropic's documentation has since written up models, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283/model |
Documentation arrivedAnthropic's documentation has since written up /model, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.283/model |
Documentation arrivedAnthropic's documentation has since written up /model, on Set up Claude Code for your organization.
the line in the docs| [Model restrictions](/docs/en/model-config#restrict-model-selection) | `availableModels` filters which models appear in the picker. Adding `enforceAvailableModels` also constrains the auto-selected default model. See [surface coverage](/… |
|
v2.1.282/install-github-app |
Documentation arrivedAnthropic's documentation has since written up /install-github-app, on Set up Claude Code for your organization.
the line in the docs| [Login enforcement](/docs/en/settings-reference#forceloginmethod) | Restrict login to a specific method or Anthropic organization. The method restriction applies across the VS Code extension, Agent SDK, `claude setup-token`, and `/instal… |
|
v2.1.283/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Set up Claude Code for your organization.
the line in the docs| [Login enforcement](/docs/en/settings-reference#forceloginmethod) | Restrict login to a specific method or Anthropic organization. The method restriction applies across the VS Code extension, Agent SDK, `claude setup-token`, and `/instal… |
|
v2.1.282strictPluginOnlyCustomization |
Documentation arrivedAnthropic's documentation has since written up strictPluginOnlyCustomization, on Set up Claude Code for your organization.
the line in the docs| [Customization lockdown](/docs/en/settings-reference#strictpluginonlycustomization) | Block skills, agents, hooks, and MCP servers from user and project sources, so they can only come from plugins or managed settings. Locking skills also… |
|
v2.1.282strictPluginOnlyCustomization |
Documentation arrivedAnthropic's documentation has since written up strictPluginOnlyCustomization, on Set up Claude Code for your organization.
the line in the docs| [Customization lockdown](/docs/en/settings-reference#strictpluginonlycustomization) | Block skills, agents, hooks, and MCP servers from user and project sources, so they can only come from plugins or managed settings. Locking skills also… |
|
v2.1.283/skills |
Documentation arrivedAnthropic's documentation has since written up /skills, on Set up Claude Code for your organization.
the line in the docs| [Customization lockdown](/docs/en/settings-reference#strictpluginonlycustomization) | Block skills, agents, hooks, and MCP servers from user and project sources, so they can only come from plugins or managed settings. Locking skills also… |
|
v2.1.283/memory |
Documentation arrivedAnthropic's documentation has since written up /memory, on Set up Claude Code for your organization.
the line in the docs| [Managed policy CLAUDE.md](/docs/en/memory#deploy-organization-wide-claude-md) | Org-wide instructions loaded in every session, can't be excluded | File at the managed policy path | |
|
v2.1.283sandbox.enabled |
Documentation arrivedAnthropic's documentation has since written up sandbox.enabled, on Set up Claude Code for your organization.
the line in the docs| [Sandboxing](/docs/en/sandboxing) | OS-level filesystem and network isolation with domain allowlists | `sandbox.enabled`, `sandbox.network.allowedDomains` | |
|
v2.1.283sandbox.network |
Documentation arrivedAnthropic's documentation has since written up sandbox.network, on Set up Claude Code for your organization.
the line in the docs| [Sandboxing](/docs/en/sandboxing) | OS-level filesystem and network isolation with domain allowlists | `sandbox.enabled`, `sandbox.network.allowedDomains` | |
|
v2.1.283permissions.defaultMode |
Documentation arrivedAnthropic's documentation has since written up permissions.defaultMode, on Set up Claude Code for your organization.
the line in the docs| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. [Switch … |
|
v2.1.282allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Set up Claude Code for your organization.
the line in the docs| [Permission lockdown](/docs/en/permissions#managed-only-settings) | Make managed settings the [only settings source of permission rules](/docs/en/settings-reference#allowmanagedpermissionrulesonly). Disable `--dangerously-skip-permission… |
|
v2.1.282allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Set up Claude Code for your organization.
the line in the docs| [Permission lockdown](/docs/en/permissions#managed-only-settings) | Make managed settings the [only settings source of permission rules](/docs/en/settings-reference#allowmanagedpermissionrulesonly). Disable `--dangerously-skip-permission… |
|
v2.1.282permissions.deny |
Documentation arrivedAnthropic's documentation has since written up permissions.deny, on Set up Claude Code for your organization.
the line in the docs| [Permission rules](/docs/en/permissions) | Allow, ask, or deny specific tools and commands | `permissions.allow`, `permissions.deny` | |
|
v2.1.283DISABLE_TELEMETRY |
Documentation arrivedA small documentation edit on Data usage touched a line naming DISABLE_TELEMETRY after this was published.
the line in the docsClaude Code sends two kinds of operational telemetry: usage metrics and error reports. You can turn each off individually with the environment variables below, or disable all non-essential traffic at once by setting `CLAUDE_CODE_DISABLE_NO… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedA small documentation edit on Claude apps gateway spend limits touched a line naming store.readiness_grace_seconds after this was published.
the line in the docsFail-open only helps while your load balancer or orchestrator still routes traffic to the gateway. See [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior) for `store.readiness_grace_seconds`, which keeps replicas passing… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedA small documentation edit on Claude apps gateway spend limits touched a line naming store.readiness_grace_seconds after this was published.
the line in the docsFail-open only helps while your load balancer or orchestrator still routes traffic to the gateway. See [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior) for `store.readiness_grace_seconds`, which keeps replicas passing… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedA small documentation edit on Claude apps gateway spend limits touched a line naming store.readiness_grace_seconds after this was published.
the line in the docsFail-open only helps while your load balancer or orchestrator still routes traffic to the gateway. See [Outage behavior](/docs/en/claude-apps-gateway-deploy#outage-behavior) for `store.readiness_grace_seconds`, which keeps replicas passing… |
|
v2.1.282enforcement.fail_closed_on_error |
Documentation arrivedAnthropic's documentation has since written up enforcement.fail_closed_on_error, on Claude apps gateway deployment and operations.
the line in the docsTo keep signed-in developers working through a short Postgres outage such as a database failover, set [`store.readiness_grace_seconds`](/docs/en/claude-apps-gateway-config#store) to longer than the failover takes, for example `300`. With s… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedAnthropic's documentation has since written up store.readiness_grace_seconds, on Claude apps gateway deployment and operations.
the line in the docsThe gateway serves `GET /healthz` as a liveness probe and `GET /readyz` as a readiness probe. `/readyz` verifies the store is reachable. If you set [`store.readiness_grace_seconds`](/docs/en/claude-apps-gateway-config#store), `/readyz` kee… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedAnthropic's documentation has since written up store.readiness_grace_seconds, on Claude apps gateway deployment and operations.
the line in the docsThe gateway serves `GET /healthz` as a liveness probe and `GET /readyz` as a readiness probe. `/readyz` verifies the store is reachable. If you set [`store.readiness_grace_seconds`](/docs/en/claude-apps-gateway-config#store), `/readyz` kee… |
|
v2.1.282store.readiness_grace_seconds |
Documentation arrivedAnthropic's documentation has since written up store.readiness_grace_seconds, on Claude apps gateway deployment and operations.
the line in the docsThe gateway serves `GET /healthz` as a liveness probe and `GET /readyz` as a readiness probe. `/readyz` verifies the store is reachable. If you set [`store.readiness_grace_seconds`](/docs/en/claude-apps-gateway-config#store), `/readyz` kee… |
|
v2.1.283acceptEdits |
Documentation arrivedAnthropic's documentation has since written up acceptEdits, on Choose a permission mode.
the line in the docsIn addition to file edits, `acceptEdits` mode auto-approves common filesystem Bash commands: `mkdir`, `touch`, `rm`, `rmdir`, `mv`, `cp`, and `sed`. These commands are also auto-approved when prefixed with safe environment variables such a… |
|
v2.1.283skillOverrides |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming skillOverrides after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |
|
v2.1.282skillOverrides |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming skillOverrides after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |
|
v2.1.282skillOverrides |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming skillOverrides after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |