Unclear It is not clear which tools this applies to.
What
A PermissionRequest hook is a command of your own that runs when a tool call needs a permission decision, and it can answer "allow". A tool call is Claude asking to run a command or edit a file. While auto mode is on, including when it sits behind plan mode, that allow answer is now ignored for certain tools. Claude Code records each time this happens.
Why
If you rely on a hook to approve tools automatically, some of those approvals will no longer take effect in auto mode, and the normal decision applies instead.
Names in the bundlePermissionRequest
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 Run Claude Code programmatically touched a line naming PermissionRequest after this was published.
Calls to tools you didn't list run if they need no approval. In a [Manual mode](/docs/en/permission-modes#available-modes) `claude -p` run, a call that needs approval is denied unless something approves it, such as a [`PermissionRequest` h…headless see the edit
Confirmed since
Anthropic's documentation has since written up PermissionRequest, on Error reference.
| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) |errors see the edit
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
It is not clear which tools this applies to.
Anthropic's documentation agrees
Anthropic's documentation has since written up PermissionRequest, on Error reference.
Anthropic's release notes agree
Changed auto mode in Cowork cloud sessions: a PermissionRequest hook can no longer approve shell commands or subagents; those prompts wait…