Plugins

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Adds a Branch Chat tab to dsh-better-sidebar that opens independent archived sessions with a head/middle/tail context digest and the same tools as the main agent.

Web UI plugin that folds each staged response's think and tool calls into per-segment bounded, scrollable slide windows with a configurable height, keeping every intermediate response visible.

64-entry external CLI catalog with bounded public discovery and guarded package-manager or manual official installation, exposed through DSH tools and a standalone command.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.

A developer toolkit for the DeepSeek Harness (DSH) web console: a real multi-tab PTY terminal docked under the composer plus an AI-output file browser sidebar with syntax highlighting, Markdown rendering and image preview.

Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimization plus multi-provider image generation with async background rendering.

Minimal snippet and command toolbox for DSH: five tools over a single human-editable JSONL file, zero UI, zero database, zero network, explicit save-only memory.

Adds catalog discovery, counterparty contact, deal signing, settlement coordination, human-task handoff, and signed receipt tools for agent-native trade.

Native DeepSeek Harness plugin for IsingQ: guided QUBO modeling and validation on-device, then user-confirmed remote solving.

Connects DeepSeek Harness to a deployment-owned AI Asset Hub MCP server and exposes eight reviewed read-only asset tools.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Registers /wrapped, which reads the session's own stats and renders a shareable dark SVG summary card — tool vs. thinking time, decode speed, and a tool/thinking-ratio verdict.

Exposes the DSH dynamic-Cordis toolset to Claude Code over MCP (streamable HTTP on the existing web port, no new listener): ten tools to list, inspect, define, run, stop and permanently remove dynamic plugins in a live DSH session, with the same approval flow the GUI uses for packages that ship a client half. Bearer auth is mandatory — the token is configured on a DSH settings page, the endpoint answers 503 rather than serve without one, accepts loopback only and never emits CORS headers.

Text-to-image and image-to-image generation inside DSH through OpenAI-compatible endpoints, with an agent tool, multi-provider fallback, and a side-panel workspace with history.

Memory Standard Protocol (mm) for DeepSeek Harness: layered MEMORY.md with hard budgets, frozen snapshots, mm:// URI interop, session-log digestion, mem_* tools and a standalone CLI.

Bridges the MemOS memory service over MCP: the agent gets add/search/update/delete memory, multi-cube sharing, and a memory scheduler as mcp__memos__* tools.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

macOS desk pet forked from anneheartrecord/dsh-desk-pet, in a real always-on-top window that covers fullscreen Spaces: the pose follows whatever the local DSH is doing across six states, the right-click menu is a real AppKit one carrying quiet mode and a session list, and seven skins ship with it. Two of the seven are drawn from geometry by a script in the repo rather than generated, so making a skin needs no image model and no API credits; the bundled skill still expands one photo into all eighteen poses on your own image tool and credentials. There is no Electron and nothing to install alongside it: the window is driven through ctypes on the Python that ships with macOS.

聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。