dsh-approval-mode
Approval mode control for DeepSeek Harness: default approval (ask) or bypass approval (auto-approve every tool call), next to the permission selector. DSH 审批模式插件。
9 results
Approval mode control for DeepSeek Harness: default approval (ask) or bypass approval (auto-approve every tool call), next to the permission selector. DSH 审批模式插件。
A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.
Tiered auto-review for DeepSeek Harness (DSH): static-rule safety net + LLM reviewer + human fallback. Auto-approve safe actions, auto-deny irreversible ones, ask a human for the rest. PURE VIBE CODING - not audited, use at your own risk.
Auto 自动审批插件:DSH 中间档权限——信任目录内自动放行、危险操作人工确认(类别开关可调)
Configurable auto-approval for DeepSeek Harness: intercepts approval/request and answers allowed-once/rejected by policy (allow-all / allowlist / deny-always), with a full audit log — so the human is only asked when the policy says so.
Approval-free writes into whitelisted directories: wraps ctx.fs.checkedTarget for write/edit, auto-approves bash escalations that touch whitelisted paths, with a Settings GUI. 白名单目录写入免审批(write/edit + bash),设置页可视化调整。
Permission matrix for DeepSeek Harness: 3 sandbox modes x 4 approval strategies = 9 selectable presets, with a global default, a separate LLM-robot default, four-tier risk policies, password-gated approval for high-risk operations, audit log and git checkpoint.
Automatic review of sandbox escalation requests for DeepSeek Harness, plus an /approve slash command for manually approving auto-denied actions (Codex Guardian-style)
Model-reviewed Auto Approve permission preset: only review-passed actions are auto-approved, everything else is handed back to the user, with an approval-log panel