dsh-auto-guard
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
72 results
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
DSH Web GUI plugin: session-scoped "Allow for this session" option in the approval dialog (per-mode standing grants, localStorage)
A DeepSeek Harness (DSH) plugin that adds an AI-adjudicated 'smart' approval mode: safe operations are auto-allowed via an isolated side-channel LLM judge, everything else falls back to the normal human approval popup.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
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)
Localize leftover DSH UI chrome to Chinese (command palette descriptions, permission presets, reasoning effort) at the display layer, and detect when the official build adapts them
DSH Full access 一次性开关:新工作区/新对话默认 full access,不再逐个确认(可安装 bundle + 补丁工具)
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.
DeepSeek Harness bundle for the official Wolfram/AgentTools MCP server: kernel discovery, a transparent stdio supervisor that owns only its own Wolfram process tree, and a native DSH permission policy over the Wolfram tools.
Enhanced DSH workspace directory picker: cross-drive/root browsing, breadcrumb jumps, and risk/permission visual indicators
Offline-first static admission scanner for DeepSeek Harness plugins.
Standalone DeepSeek Harness access-mode plugin with Default, No Edit, and Auto modes
dsh plugins ported from eco-agent: permission gate, audit chain, memory tree
修复 sandbox_permissions 和 justification 字段在 pwsh/bash/fs/dsh-sandbox 中的 no-op 升级报错。当会话已是 danger-full-access 模式时,模型携带空 justification 或重申同一模式被拒的问题。
Press Enter to approve the sandbox permission-escalation prompt in the DeepSeek Harness WebUI instead of clicking the Allow once button.
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.
Password-gated Sudo access permission mode for DeepSeek Harness
Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.
Plan 模式心智映射:read-only 权限显示为 "Plan",审批策略 never(拒绝即最终,不准申请权限),文件只读 + 网络搜索可用。
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.