DSH Auto Review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approva.
Project overview
dsh-auto-review puts a second model on the approval/request answerer chain:
Every decision reconstructs from the session log: approval/asked → autoReview/verdict (or autoReview/rejection) → approval/decided. Why a second model instead of rules?
In the Web GUI (web profile), the package contributes a session-header action (AI Review) that opens a panel with the session's auto-review state: the switch with on/off buttons (they execute /auto-review on|off), both per-turn budgets, cumulative statistics (including hard-disable rejections), the circuit trip, the recent verdicts, and one-shot approve buttons for recent denials (they execute /auto-review approve [n]).