Settings-merge logic now allows permissions.defaultMode values of auto and bypassPermissions to be set from either project or local settings, whereas this was previously derived from a schema enum reference. Other default-mode values, such as acceptEdits, remain restricted to project only. This widens where these auto-approve modes can be configured from and is not behind a flag.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Set up Claude Code for your organization touched a line naming permissions.defaultMode after this was published.
| [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 …admin-setup see the edit
Confirmed since
Anthropic's documentation has since written up permissions.defaultMode, on All settings.
| Read from the highest-priority source only | Reads the key only from the highest-priority source that carries a policy key, so a lower source's value is ignored even when the highest source sets none | [`apiKeyHelper`](#apikeyhelper), [`…settings-reference see the edit
Confirmed since
Anthropic's documentation has since written up bypassPermissions, on Configure permissions.
Coverage depends on the entry's form: a bare name like `Read` or `mcp__github__get_issue` auto-approves every call to that tool apart from the exceptions above, while a scoped rule like `Bash(npm test *)` auto-approves only matching calls,…agent-sdk/permissions see the edit
Added since
A small documentation edit on Connect Claude Code to tools via MCP touched a line naming bypassPermissions after this was published.
In `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…mcp see the edit
Confirmed since
Anthropic's documentation has since written up auto, on Give Claude access to your tools.
A Datadog API key, for example, makes the API reachable, and a Datadog plugin tells Claude which endpoints answer which questions. Sessions in covered channels pick up attached plugins automatically, with nothing to install or enable. Chan…claude-tag/admins/add-connections see the edit
Added since
A small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming auto after this was published.
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), the classifier can block an `agent()` call before the subagent s…workflows see the edit
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agrees
A small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming auto after this was published.
Anthropic's release notes agree
Fixed sessions dispatched from an agent view opened with ← always starting in the original session's permission mode, overriding the target…