68 results
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 agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
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 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。
Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.
DSH Metafolder Plugin — visual meta-folders for the DeepSeek Harness sidebar workspaces: nest real workspace folders under named, collapsible groups, by drag and drop or the row menu. Paths, permissions, sessions and workspace ordering are untouched.
Normalize invalid non-widening sandbox escalation arguments before DSH tool dispatch.
Auto-reject unanswered permission requests with a model-visible timeout notice
Deny an AI agent access to .env files, credential stores, keys and any path you hide — across file tools, shell commands, search selectors and run_code. A DeepSeek Harness (dsh) plugin.
Tolerate redundant sandbox_permissions requests: a tool call asking to escalate to a mode that is not strictly wider than the session's standing mode runs as-is at the standing mode instead of failing with "not strictly wider". Genuine escalations still route through the approval flow.
Codex-style auto reviewer (approve for me) permission mode for DSH
Corner approval popup: answer pending permission requests from any session while the agent window is away
Explain what a pending dsh approval will actually do, with one LLM call: an Explain button beside Allow/Reject plus the Host /explain command behind it