LLM-as-judge auto-approve mode (Autopilot 2.0?)

Coming from ChatGPT Codex and Claude Code, the biggest feature I miss in Copilot Desktop is an LLM-as-judge auto-approval mode. If I understand the docs, "Autopilot" mode simply auto-*denies* all tool calls that are not permitted by the user's sandbox configuration, so that the agent can attempt to route around these obstacles autonomously. What I'd prefer is for a relatively inexpensive model to review such tool calls and approve them if they seem safe.

---
| Field | Value |
| --- | --- |
| App version | 1.1.8 |
| OS | macOS 26.6.1 |
| Theme | GitHub |
| Path | / |
| Tenure | Day 1 |

Start by reading the Autopilot and sandbox documentation, then trace how tool calls are currently denied or approved in the desktop app. Define the safety review flow, model and permission boundaries, and tests needed to show that safe calls are approved while unsafe calls remain blocked.

Written by the indexing model from the issue text.