permissions 15

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档：例行沙箱升级由分类模型一次性放行，危险或不确定的操作仍转人工审批。An auto-approval permission preset for DeepSeek Harness between workspace-write and full access: routine sandbox escalations are granted once by a classifier

CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode na

dsh-yolo-mode —— DeepSeek Harness 双面包插件：当会话处于可写沙箱模式且审批策略为 ask 时，用大模型自动裁决沙箱升权申请，支持内置预设与自定义权限层级，并提供宿主 settings + 自发布设置桥（/yolo-mode）与 Web 客户端 UI。

DeepSeek Harness plugin exposing AIFeed tools: verify signed content permissions, fetch token-budgeted markdown, select delta-index entries, and decide usage.

Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.

不把整台机器交出去，只送出挡路的决定和下一步：DeepSeek Harness 的审批、ask_user_question 提问与结果回复，以飞书卡片发到手机——桌面优先、只出站；执行过程实时可见，下一段任务一键即开。

DeepSeek Harness 权限规则引擎：hard/deny/ask/allow 四级规则（hard 高于全访问）、全局与 workspace 作用域、通配符路径保护、可视化草稿式编辑器，规则持久化于自管 JSON

Fine grained per tool permission rules for DeepSeek Harness (DSH). deny/ask lists in Claude Code rule syntax, enforced at the tools/pre-execute gate. Works standalone.

Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.

Consequence analysis for DeepSeek Harness: it says what an extra-permission call costs you — the device, your delegated authority, your wider interests. State-based, not guessed.

dsh 插件 · 登录门 + 账号 / 权限 / 配额 / 审计台账（dsh-passwords 的功能已并入）：HTTPS 登录网关与自签证书、用户增删改查（可一并创建工作区）、工作区白名单与归属跟踪、每小时 token 与每日时长配额、沙盒档位下限、上传/git 开关、三本审计台账（登录/访问/操作）、IP 封禁、TOTP 两步验证。

Four-mode file-permission fence for DeepSeek Harness (workspace read/write x outside read/write), enforced at the tool layer, with a read-only composer mode indicator and a locale-aware UI.

Declarative tool-call permission control for DeepSeek Harness — allow/deny/ask rules over tools, paths and commands, fail-closed by default, with JSONL audit log.

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.