Plugins

Control the user's own Chrome (or Edge/Brave/Vivaldi/Opera) from DeepSeek Harness by reusing the OpenAI Codex `chrome` plugin's browser runtime: tabs, logged-in sessions, accessibility trees, screenshots and input, exposed as native DSH MCP tools plus a b

Session billing pill for DeepSeek Harness: shows what the current session cost, priced with the official per-model peak/idle rates.

溢出兜底与续命：上下文超限、内置压缩放弃后自动再压一次并重试；仍失败时把原会话整理成交接包，在新会话接着聊。不换引擎、不加界面；续命默认显式触发，原会话只读。 · Overflow fallback and session revival for DeepSeek Harness: one last compaction retry, then continue the dead session in a fresh one with a handoff. No engine swap, no UI, o

See the context a Session submits to its model in the DeepSeek Harness Web UI: the system prompt, the tool schemas and every message, drawn as a grid of token squares.

Skills, MCP and installable assistant packages with session-scoped capabilities on official DSH services

DeepSeek Harness plugin: a native session_rename agent tool backed by the Cordis sessionTitle service, so the agent can keep each conversation's title honest.

DeepSeek Harness 插件：Session header 的 "Open In..." 按钮组底座，提供注册契约供同类插件补充目标软件。

DSH plugin: delete sessions from the sidebar (row menu + hover button) and via slash commands and agent tools. Trash-first, workspace-accounting aware.

Delete a DeepSeek Harness conversation from the sidebar: a recoverable trash with restore and purge, or permanent removal, with a path-safety guard and an audit trail. | 在 DeepSeek Harness 侧边栏删除对话：可恢复的回收站（支持还原与彻底删除），或永久删除，并带有路径安全校验与审计日志。

Chrome-style tabs for DSH chat sessions: a vertical or horizontal tab strip in your order, collapsible tab groups, each tab one session or a split of up to four live panes.

ChatGPT-style notification overlay on the DSH taskbar button: a black/white badge whose centre sits on the icon's top-right corner with the number of UNREAD completed sessions (matching DSH's own green completion dot), plus a column of attention dots cent

Shows the owning workspace name on a second line under each session title in the DeepSeek Harness sidebar's In one list view.

Persistent pwsh session tool (pwsh_run) for DeepSeek Harness: run PowerShell scripts with zero escaping, no 32K command-line cap, and state that survives across calls.

Role-based model manager for DeepSeek Harness: assign models to planning, execution, vision and main roles, route subagent work by role, escalate sessions that invoke a planning skill (grilling / grill-me) to the planning role, report which model every su

DSH 里的 feynman 会话台：只读浏览 ~/.feynman/sessions 的会话，一键在右侧栏终端里全屏续跑。

Read a BMAD v7 project in the Session sidebar: initiatives, epics, tickets and the gaps between them

瞭望哨：盯着你的每个会话——谁跑完了、谁出错了、谁卡住了、谁在等你审批，用浏览器图标角标、红点/黄点和邮件通知你；顺带显示当前会话 ID。· Lookout: watches every session — who finished, who errored, who is stuck, and who is waiting for your approval — and notifies you through the browser favicon badge, red/yellow dots, an

Treat the session as a mainland-China user: consistent persona (ID region code, phone prefix, carrier ASN, locale, time zone), a landing checklist and a self-check, plus one command that packages it for a friend.

Cross-workspace long-term memory for DeepSeek Harness: one machine-local store shared by every workspace, a compact index injected at session start, and a searchable tool for the details.

Zen mode for DeepSeek Harness: a full-screen minimal timer that hides DSH while tasks run, showing only the elapsed or remaining time, the sessions that finished during the round, and an exit button.

Adds a draggable, zoomable radial map of your session tree to the DSH conversation view, so you can see which conversation branched off which, and switch by clicking a node.

Cross-session memory for DeepSeek Harness. Local memory store by default, optional GitHub-backed sync (git), with primary/child roles for multi-device setups.

Token usage analytics for DeepSeek Harness: scans the host's own session logs and reports consumption by provider and model, cache hit rates, daily trends and a capability leaderboard for every model you can currently call.

Cross-model continuity for DeepSeek Harness: memory, skills and rules live in local files, so judgement survives session and model changes. Not about storing more memory — about using it well after the model changes.