Plugins

DSH-TUI: a lightweight and fast terminal plugin connected directly to the DSH runtime.

Durable background child agents on the official subagent seam: start from any session, watch progress in the Web UI sidebar, message and interrupt any time, with per-child tool scoping, persona and delegation-depth caps.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

Hermes-style tool search & slimming: progressive disclosure, semantic search, describe, and call long-tail tools on demand while core tools stay eager.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Import claude-code / codex / reasonix / zcode chat history into dsh sessions: workspace binding, tool calls preserved, oversized-session protection, zcode compaction restore.

LAN mobile gateway: isolated child-process reverse proxy with first-visit approval, per-device token binding, rate limiting, and mobile layout injection (compact composer pills, randomUUID polyfill).

Conversation navigator panel: turn-folded outline of the current session with per-step kind badges (assistant, tool, command, compaction, error), a hover bubble showing the full user question, a minimal mode that hides turn numbers for an all-badge view, keyword filter over user questions and assistant replies, click-to-jump with reading-position tracking, and load-earlier/load-all history paging.

Embeds the AIsChat social-agent platform into the DSH web UI as a native sidebar board — contact panel, real-time chat over a same-origin HTTP/WS proxy, and Markdown/LaTeX rendering. The plugin is the front end only; it proxies to an AIsChat backend you run yourself (default http://127.0.0.1:5228, from the same repository).

DeepSeek Harness plugin that locks the web chat composer Enter-send. Toggle with a lock button or Ctrl+Alt+L to prevent accidental sends while typing or editing long prompts; unlock to send. IME-safe and per-session.

Local-first code knowledge graph for coding agents: 10 MCP tools for layered context compression, DAG planning, incremental AST indexing, a cross-session skill flywheel, diagnostics, and graph artifact import/export.

Use Kimi Code as the DSH agent loop over ACP, with approvals, slash commands, and local/remote (ssh+tmux) session attach.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

DSH web-GUI pet runtime that renders any Codex spritesheet-atlas pet (v1/v2) as a draggable overlay: drag/wave/jump, v2 mouse-tracking eyes that follow the active mouse, live agent-status poses, progress bubbles, and an in-GUI atlas importer; ships one original CC BY-NC demo pet (nastya), and user pets live in ~/.dsh/pets.

Mobile remote control for the dsh web GUI: scan-to-pair QR entry with one-time pairing tokens.

Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).

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.

Settings -> Plugins switchboard: every loaded plugin card shows its package description and runtime phase, with fuzzy search and start/stop toggles that never rewrite config files.

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.

Feishu (Lark) bridge for DeepSeek Harness: one-command install, streaming progress cards with a tool panel, ask/approval button cards, attachments, and proactive feishu_send pushes.

Official Remotion skill ported to DSH: programmatic video with React (animation/audio/captions/3D/charts/fonts, 38 rule files).

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.