FEATURE: risk appetite setting to run commands without confirmation

[merefield]

• clai already assesses command risk
• choose for lower risk commands to run without review/confirmation

[Copilot]

Pull request overview

Adds a configurable “risk appetite” setting to allow CLAI to automatically execute lower-risk model-suggested commands without prompting, while preserving confirmation for higher-risk commands.

Changes:

• Introduces risk_appetite config (default 0) with setup-wizard support and normalization.
• Adds execution gating logic to skip confirmation prompts based on command risk + risk_appetite.
• Updates README documentation and expands smoke tests to cover auto-run vs prompt behavior.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
clai.sh	Adds risk_appetite config handling, setup prompt, and confirmation-skipping logic for lower-risk commands.
test/smoke.bats	Updates setup-wizard IO expectations and adds new smoke tests validating risk-appetite behavior.
README.md	Documents the new risk_appetite setting and how it affects confirmation flow.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.