生産性ツール · DeepSeek Harness プラグイン — 132 ページ

DSH session migration plugin: drag-and-drop sessions between workspaces in the Web UI. Backed by the official workspaceRegistry service and a multi-frame-safe zstd header rewrite.

在每个 DSH 新会话的 system prompt 开头自动注入可自定义的固定提示词，并提供输入栏 UI 编辑入口

Predicts the remaining wall time of the live DeepSeek Harness turn from its step history and shows it as a progress bar with a live percentage under the composer.

Git review, terminal, and file workspace panel for DSH Web

DSH side temporary session: fork the main session (completed history + recent-context completion) into a side panel with main-session-quality UI (Claude Code /btw-style).

Skill usage statistics for DSH: counts every skill invocation across sessions (replay of existing logs + live session/event subscription), detects zombie skills, and helps decide which skills to keep.

剧情模式：一键开关，让深深以当前人格为身份进入角色扮演，并读取工作区文档作为场景与须知

让主会话模型从已配置模型里自主选择子代理模型

会话行「标记未读 / 取消标记」：小红点主动未读标记（用户钉住待处理），与系统绿点区分；绿点存在时两项禁用，红点仅手动取消才消失，服务端持久化

DeepSeek 用量面板：余额（API Key）+ Token 用量（平台会话令牌）仪表盘，注册在 设置 → DeepSeek 用量

DSH 用量页：本机跨会话 Token 使用统计（Codex 风格），纯只读、不出本机 | Local cross-session token usage statistics page for the DSH Web GUI (Codex-style), read-only and machine-local

用量统计：聚合所有会话的 token 使用总量与模型分布，设置页显示

DeepSeek Harness vision bridge: session screenshots route by model capability. Image-capable models receive attachments inline; text-only models see the standard placeholder, and the bridge reads the image through a vision-language model — on demand via the vision_bridge_read tool or automatically via agent/pre-step context injection. 会话截图按模型能力自动分流：多模态模型原样直读；纯文本模型经 VLM 代读（tool/auto 双模式）。

DSH profile bundle: auto-bridge images for text-only models (DeepSeek etc.) — instead of the native "model does not support images" rejection, the image is materialized into the workspace and the model is instructed to run the configured vision tool (vision_glance, fuzzy-selectable) and answer from its analysis. Works on WSL/Ubuntu and native Windows; sessions on excluded presets (default minimal) keep the original blocking behavior.

Lightweight DSH upload bridge: images and common documents become workspace paths so a text-only DeepSeek model can read them with Qwen-MM-Plugins vision tools.

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

dsh-voredteam —— 单模式（网络安全模式）DSH 插件合集：黑板书 Fact/Intent/Hint 引擎 + 总控派发专业子 agent + 作战面板/设置 两个面板 + 唯一门禁（禁 DDoS/禁爆破/模糊测试低频）。

webui：视图图块/消息导航 + 工具调用聚合 + Markdown 渲染 + 模型推理等级同步 + AnySearch 网页搜索（合并 dsh-tool-summary / dsh-better-markdown / dsh-web-search-anysearch）

Additive whale-maid persona and automatic near-limit session continuation for DeepSeek Harness

Virtual session folder grouping, move-to-folder menu, and nested workspace subproject manager for DeepSeek Harness (DSH).

A workspace-scoped DSH knowledge repository with explicit immutable local file backup.

DSH plugin: architecture-first project governance. v0.10.0 makes the model a TREE + GRAPH — the containment tree (who belongs to whom) now sits beside a dependency graph (who imports whom), and the graph is DERIVED from a static import scan: never registered, never hand-written, never stale. Seven gates (anchor / scope / mainline / impact / repeat-patch / decision / completion) are pure queries inside the single write entry point nav_commit, so there is no begin/done lifecycle and no orphan state: closure is decided by EVIDENCE (did the scope files change?), never by session identity — kill a session and its intent still closes (A1). Governance surface is minimal by construction: anything that would rot when code changes must be a PROJECTION, not a document — hand-written surface is two contracts (ARCHITECTURE.md / AGENTS.md), and .internal/arch/*.md dropped its sha1-fingerprint/freshness machinery to become an on-demand projection. ONE append-only event log (.internal/events.jsonl) remains the single source of truth; the runtime model (incl. the dependency graph) is disposable — delete runtime/ and governance loses nothing (I3). Tool face 6: nav_graph (read, incl. mode=impact) / nav_commit (intent) / nav_decide (ADR) / nav_node (nodes) / nav_render (projections) / nav_set (mainline vector).

Turn-level conversation and workspace rewind for DeepSeek Harness, powered by a persistent Change Ledger