dsh-tool-workspace
DeepSeek Harness 工作区管理工具集:查看、创建注册、重命名、删除工作区记录(纯注册,不触碰磁盘目录);破坏性操作(删除注册、改注册路径)走用户审批 fail-closed。
77 results
DeepSeek Harness 工作区管理工具集:查看、创建注册、重命名、删除工作区记录(纯注册,不触碰磁盘目录);破坏性操作(删除注册、改注册路径)走用户审批 fail-closed。
Workspace Only switch for DeepSeek Harness: confine file access of every sandbox mode to the session workspace
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.
DSH Web GUI plugin: session-scoped "Allow for this session" option in the approval dialog (per-mode standing grants, localStorage)
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
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.
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.
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)
Stops the DSH sandbox-escalation fields being offered to a model when the calling session cannot grant them, fixing the GPT-family retry loop at danger-full-access where every advertised enum value is rejected before the command runs.
UI-level access gate + process-wide agent tool brake for DeepSeek Harness: shared session, strict 60-minute idle lock, native settings module. NOT server-side authentication.
Unified Agent control for DeepSeek Harness: gate every agent-class tool behind one composer switch, preset subagents with per-entry persona/permission/model, and let the model author its own agents.
DSH plugin: auto mode that routes permission-gated tool calls through an LLM review before approving, blocking, or asking for confirmation.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
Codex-style auto reviewer (approve for me) permission mode for DSH
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)
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
Enhanced DSH workspace directory picker: cross-drive/root browsing, breadcrumb jumps, and risk/permission visual indicators
Standalone DeepSeek Harness access-mode plugin with Default, No Edit, and Auto modes
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.
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。
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。