Plugins

Native conversational image generation for DeepSeek Harness: ask the agent to create an image, and it handles generation and keeps the result directly in the conversation.

Lark/Feishu bot channel for DeepSeek Harness: each chat drives its own agent, and tool approvals, model questions, and plan reviews return as cards answered by a button or a reply. Switch workspace and model from the chat (`/cd`, `/model`, `/new`), and run several bots that keep separate sessions and can hand turns to each other in one group.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

Codex-style Side Chat for DeepSeek Harness — select text, ask follow-up questions in a focused side conversation, and keep the main chat uninterrupted.

Ports all 34 opencode official themes (33 static JSON + 1 system) into DeepSeek Harness: data-driven pipeline (JSON → color resolve → DSH override), per-browser persistence, monospace/proportional choice, five code fonts, and a system fallback that keeps typography only.

Runtime requirement drift guard that keeps long-running DSH agents aligned with the user's approved goal, constraints, and decisions.

DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.

Secondary working directories for a DSH project: the agent keeps the primary workspace as cwd and gains equal read/write/exec permissions on configured secondary directories, configurable from the session header and the new-session page.

Codex-style turn folding for the DSH Web UI: keeps final answers visible, groups consecutive reasoning and tool activity, and shows configurable live duration, tool-call, and token metrics with multilingual summaries.

Turn a casually written sentence into a four-section (Role / Task / Context / Format) or plain-text professional prompt via the harness llm service. Situation-aware role / task / goal profiling keeps ##Role tied to the task; /dream appends a clearly labelled AI-inferred insights appendix; /template covers 21 sub-scenes with zero model calls; input-box ✨ one-click optimize / undo, prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

SSH ops terminal for DSH Web UI: drive a connected server from the main conversation (ssh_connect/ssh_exec/ssh_read/ssh_write/ssh_disconnect) while keeping an interactive xterm.js terminal on the right.

Archived-session manager for DSH Web UI: reopen an archived session and keep chatting, unarchive it back in place, or hard-delete a session — grouped panel with message search and native view sync.

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Select text in a committed DSH response to open an independent, persistent, read-only multi-turn Topic bound to source-session evidence and project files while the source Agent keeps running.

SSH terminal panel and AI connection manager for DeepSeek Harness: model-driven SSH connections (connect/exec/list/status/disconnect), auto-saved connection records, keep-alive + auto-reconnect, execution mutex, credential-safe auth, and an XShell-style m

REST + SSE gateway exposing running Harness sessions to third-party clients: API-key auth, token streaming, workspace grouping, and adopting GUI sessions to keep chatting.

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Smart form skill: structured record-keeping for bills, ledgers and logs with auto-categorization and periodic reports.

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Diagnose, unstick, and read DSH sessions: list sessions with agent status, read conversations, diagnose stuck agents, recover them with cancel+keepInbox, and send messages to other sessions.