← BACK_TO_LOG

OpenClaw adds auto approvals for exec commands

2026-06-04 · openclaw

OpenClaw is trialing an opt-in `auto` mode for host exec approvals. The goal is to keep trusted commands moving while still routing risky or ambiguous commands through review or humans.

Key Features or Updates

In auto mode, policy runs first, then low-risk misses can be reviewed by a model, and anything uncertain falls back to human approval. OpenClaw says the reviewer model is separate from the main agent model, and approval prompts can still resolve to `allow-once`, `allow-always`, or `deny`.

Impact on Developers

This is a practical attempt to reduce approval fatigue without giving up operator control. It also makes OpenClaw more usable for enterprise-style environments where routine automation should keep moving, but privileged actions still need a second look.

How to use it

On a gateway-host setup, OpenClaw documents `openclaw config set tools.exec.host gateway` followed by `openclaw config set tools.exec.mode auto` to enable the mode. If you want stronger review than the main agent, set a dedicated reviewer model such as `openai/gpt-5.5`.

Read Original Post →