# Permissions, plans & approvals

Choose Explore, Ask or Execute and review scope, files and external actions before approval.

Updated: 2026-10-11
Desktop 0.5.0-rc.42 · Web 0.5.0-rc.42
Canonical: https://ai.z-group.cn/docs/en/permissions/

## Three permission modes
| Mode | Suitable stage | Tool behavior |
|---|---|---|
| Explore | Research and planning | Read-only exploration within allowed rules; writes and commands are restricted |
| Ask / Ask to Edit | Changes requiring review | Requests approval according to permission rules |
| Execute | Implementation with a clear scope | Runs within authorized scope, usually without per-action prompts |
## Plan, review, then execute
1. Request a plan and explicitly ask the agent to wait for approval.
2. Check sources, output folders, affected files and external actions.
3. Request revisions if needed; otherwise select Approve and Execute (批准并执行).
4. Inspect progress and open the deliverables when complete.
A plan is a workflow, not a fourth permission mode. Approving it does not professionally validate the conclusions.
## Review a tool approval
Check the actual target, path and write or sending scope. Existing rules can reduce prompts; do not assume every external action will ask again. Execute mode remains constrained by account, server and operating-system permissions.
## Does Stop undo work?
No. Completed writes or external actions are not automatically reversed. Stop promptly if needed, then inspect what already happened. A remote approval must refer to the same computer, workspace and conversation, with the target online.

## Scope of remembered approvals
From RC44, file writes can be remembered for an explicit directory. Ambiguous relative paths do not offer Always Allow. Compound commands offer one-time Allow or Deny; arguments and network targets affect approval scope. Child tasks are capped by parent permissions, and activating a source does not bypass tool approval.