dsh-diff-approval
DeepSeek Harness plugin: pending-edit review with whole-file diff and Keep/Revert
179 results
DeepSeek Harness plugin: pending-edit review with whole-file diff and Keep/Revert
System-level task notifications for DeepSeek Harness (DSH): approval requests, awaited replies, and finished background jobs / subagents / workflows — pushed to the OS notification center with chimes, plus an in-app bell panel, toasts, and a clear button.
Aggregate and natively control DeepSeek Harness sessions across multiple remote dsh web servers from one pane: server registry, merged session list, history, prompt, cancel, rename, fork, model selection and approval/question answering.
DSH web GUI notification alerts: distinct synthesized tones or a spoken voice (zh/en) for 'needs approval', 'needs answer', 'output complete' and 'error', with per-type sound, enable, volume, repeat, browser notifications and an i18n interface-language setting.
L1-L2-L3 three-tier memory agent harness: gate approval, zero-judgement event log, weekly distillation, TDD execution loop. Claude Code plugin and DeepSeek Harness (dsh) bundle.
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。
Codex conversation backend for DeepSeek Harness, powered by the Codex App Server with approvals and DSH tool support.
Neovim-style TUI for DeepSeek Harness (dsh): nvim renders the terminal, a Node runner bridges DSH agent events over msgpack-RPC — sessions, tool cards, reasoning panel, approvals, markdown tables
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。
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 native integration.
Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards
Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent SDK, with model selection, approvals, questions, tools, and session continuation.
Session buddy for the dsh web GUI: notify you when the AI finishes replying, needs your answer, or asks for command approval while the tab is hidden, and provide an in-conversation ladder outline (question index) for quick navigation
Feishu (Lark) IM bot channel for DeepSeek Harness agents — per-chat sessions, native thinking process, interactive approval cards, WebSocket long connection.
LLM-assisted auto approval with timeout fallback for DeepSeek Harness
DeepSeek Harness 自动审批插件:在 workspace-write 沙箱之上增加 Auto 档——确定性规则放行/拒绝,模糊操作由 LLM 裁决,危险操作转人工。保留工作区沙箱边界,不放宽为 full-access。
统一 IM 桥插件家族(monorepo):核心 dsh-im + 渠道适配器(telegram / feishu)。让 DeepSeek Harness 通过 IM 可指挥、可通知、可审批。
Cross-session memory with governance, self-evolution and an approval-gated write path for DeepSeek Harness. Heat-ranked recall, environment conventions, forgetting lifecycle, supersession chains, poisoning defense, auto-distillation, and an open measurement ABI.
AI approval answerer using the unified ctx.llm route with fail-closed local policy checks
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.
Require a one-shot user approval before configured tools execute
DeepSeek Harness plugin: panel hotkeys for every interaction panel — Enter presses the confirm (primary) button, Esc presses the cancel button (approval, question/choice, plan review; Claude Code habits).
Automode for DeepSeek Harness: a fourth permission preset that runs on full access with an LLM classifier as the only gate before every tool call
DeepSeek Harness plugin: per-edit approval with a red/green line diff before write/edit/str_replace_editor — approve once or reject (Claude Code behavior).