Bundle
@dsh-external/dsh-llm-approver
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Xpectuer1
3 results
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Don't hand over the whole machine, just the decision blocking it: unattended DeepSeek Harness approvals and ask_user_question prompts reach your phone as Feishu cards, desktop first, outbound only.
Privacy protector for DeepSeek Harness: per-session toggle, syntactically pseudonymize PII before it reaches the model, restore after response.