Quick Start
When approval is required
Approval runs when any of these apply:- The agent has
approval=True(or a CLI--approvalbackend) - The tool is in the default dangerous-tools list (e.g.
bash,write,delete) - The tool has
trust_level == "external"in the tool registry
Approval modes
| CLI flag | PermissionMode | Value | Behaviour |
|---|---|---|---|
--approval console | DEFAULT | default | Prompt for each sensitive call |
--approval plan | PLAN | plan | Block write, edit, delete, bash, shell |
--approval accept-edits | ACCEPT_EDITS | accept_edits | Auto-approve edit/write tools |
--approval bypass | BYPASS | bypass_permissions | Skip all checks |
Persistence
Press[A] or [D] to write a PermissionRule to .praisonai/permissions/rules.json (priority 100, scoped to the project directory). Manage rules with:
| File | Shared? |
|---|---|
rules.json | Yes — commit for team rules |
approvals.json | No — local session data |
Non-interactive and CI
Best practices
Start with plan for new repos
Start with plan for new repos
Use
--approval plan until you trust the agent’s behaviour in a codebase.Review external tools
Review external tools
Tools marked
external always prompt — verify third-party integrations before allowing.Share rules.json in git
Share rules.json in git
Related
Permissions CLI
praisonai permissions referencePermission Modes
All modes for agents and CLI
Permissions Module
Python SDK API

