feat: add allowedUnrestricted mode for tool calling

[chenyuanrun]

Description

Add a new unrestricted mode for agent tool calling

AI Code Review

• Team members only: AI review runs automatically when PR is opened or marked ready for review
• Team members can also trigger a review by commenting @continue-review

Checklist

• I've read the contributing guide
• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created

Screen recording or screenshot

[ When applicable, please include a short screen recording or screenshot - this makes it much easier for us as contributors to review and understand your changes. See this PR as a good example. ]

Tests

[ What tests were added or updated to ensure the changes work as expected? ]

---

Summary by cubic

Add an “Unrestricted” tool policy that lets agents run terminal commands and access files without prompts or workspace checks. Exposes this option in the config UI and updates policy evaluation and tests.

• New Features
  • Added ToolPolicy value: allowedUnrestricted.
  • Terminal security: returns allowedUnrestricted and skips all checks when enabled.
  • File access: bypasses workspace boundary check when allowedUnrestricted.
  • Config UI: “Unrestricted” option added with label; cycle now goes Disabled → Unrestricted → Automatic → Ask First → Disabled.
  • Tests: coverage for unrestricted mode, including dangerous, obfuscated, multi-line, and empty commands.

^{Written for commit b1c903b. Summary will update on new commits.}

[github-actions]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[chenyuanrun]

I have read the CLA Document and I hereby sign the CLA

[cubic-dev-ai]

No issues found across 6 files