Plugins

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

dsh web 插件：自动配置模型思考档位与能力，并按 provider+model 记住最后选择的思考档位

Read-only MCP server over the DSH plugin-certification registry, exposing a plugin certification grade, its snapshot and the five-dimension evidence behind it.

MCP server management panel in Settings: add, edit, enable/disable and delete servers across user and workspace scopes with form or JSON editing, and auto-register discovered MCP tools as native conversation tools.

Three-party collaboration protocol for dsh: Step List state machine, five-tier review chain (Gemini/web/Claude Code/dialog/manual), alternatives adjudication, cross-restart resume with heartbeat, and capability persistence.

Send files or folders over the local network via the LocalSend v2 protocol, or generate a temporary browser download link that the receiver opens with no software installed.

Hands DSH reset requests to an external ops agent via a versioned JSON protocol: preflight snapshot, pre-restart maturity gate (no pending approvals, free disk, cooldown), restart, health check, and interrupted-work recovery, with the result delivered back to the requesting session.

Input prediction for the DSH composer: your next prompt suggested as ghost text after each turn, accepted with Tab. (autocomplete / input prediction / prompt suggestion)

WebMCP bridge: your agent discovers & calls site tools exposed over the W3C WebMCP protocol via a built-in headless Chromium.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Turns the dsh web UI into a native Windows desktop window, with a system tray, autostart option and a protocol file that the bundled client reads.

Live MCP server status in the DeepSeek Harness conversation composer — see which MCP servers are actually connected before you hit send.

DeepSeek Harness (DSH) plugin: frame-safe session/workspace migration — mv_session tool plus a zero-dependency CLI (dry-run, backup, one-restart protocol, read-only verify)

dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)

Use AI agents from the DSH session UI.

Run live iOS simulators and your real iPhone over USB inside DeepSeek Harness conversations with 22 agent tools, MJPEG previews, and SwiftUI hot reload.

DeepSeek Harness 的 MCP 服务管理器：在 设置 → 插件 → MCP 标签页中发现 GitHub 上的 MCP 服务仓库（topic:mcp-server / modelcontextprotocol），探测 npm / PyPI 发布状态与 README 启动线索，详情查看后一键安装 / 移除。服务以 @deepseek-ai/dsh-mcp-client 行登记进 cordis.patch.yml，HMR 热重载，无需重启。支持 GitHub 代理。

The `debug` tool for DeepSeek Harness — a model-facing Debug Adapter Protocol tool with 28 operations (launch/attach, breakpoints, continue/pause/step, threads/stackTrace/scopes/variables/evaluate, disassembly, memory, modules, output, terminate) over the

Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, using a stock DSH Conversation tab or a global Shell page when its slots are available.

Native DeepSeek Harness plugin for IsingQ guided QUBO modeling and solving

Comfort layer for the DSH Web UI: gentler phase/composer transitions, fused composer+stats card, auto-collapsed tool cards. Every rule is gated on <html data-dsh-comfort>; the in-UI pill toggles that attribute, so off == the stock UI exactly.

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

Sparkles finance evidence tools with a host-native DeepSeek Harness shell and browser client

Anthropic Model Context Protocol (MCP) client bridge plugin for DeepSeek Harness (dsh).