Plugins

Adds a Desktop card to the settings page that detects the DeepSeek Harness Desktop app and launches it with one click.

Content-addressed artifact, fact, action and report lineage for DeepSeek Harness

DSH port of TaskPlane: dependency-ordered waves run in parallel git-worktree lanes, with task packets, cross-model review, and crash recovery.

Superpowers (obra/superpowers) for DeepSeek Harness: the software-development methodology skills plus their session bootstrap, as a dsh plugin

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

Turbo Vision-style character-cell window manager for dsh agents: overlapping framed windows with drop shadows, a Borland menu bar, a function-key strip, mouse drag and resize, approvals as modal dialogs, and five skins including the classic Borland blue.

DeepSeek Harness (DSH) 推理等级自动选择插件：由 Jev System One 模型判断每条消息值多少思考量，按模型声明的等级自动推导档位，上下文信封让「继续」这类追问继承话题深度，低置信度向上取，任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Native side-by-side chat beside the main conversation: an independent archived DSH session with full native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

QA orchestrator plugin for DeepSeek Harness: an agent explores your app and leaves evidence, then the explored path replays deterministically. Drives the browser, macOS desktop, iOS and Android drivers.

TypeSafe Jev (System One decision model) for DeepSeek Harness, end to end: jev_decision (choice/score/noul, parallel, typed answers + confidence), a Settings > Plugins card for the API key and switches, inline tool views showing every decision in the conversation (answer, confidence, latency, cost), an auto-guard (deterministic + Jev risk/loop checks), a local /jev dashboard, and an online verification benchmark (96.3% on 27 labeled questions, median ~283 ms on jev-latest, 2026-09-21). Honest by design: real API only, no mock fallback.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Runs a thesis-antithesis-seal debate whose verdict is computed from real command exit codes and case counts, never from agent prose.

DSH RedTeam 模式：一句话拉起红队作战智能体（资产测绘 / 攻击链 / 得分目标 / 报告 / POC 知识库），含四个角色、13 个原生技能与常驻右侧控制台

Full-screen terminal TUI for DeepSeek Harness with Web-GUI parity, live streaming, agent presets, and DeepSeek blue styling.

Orchestrates durable multi-agent teams from one DSH session: a captain spawns member subagents, drives a dependency-aware task DAG with quality gates, and coordinates through persistent mailboxes, with a live activity panel.

A better approach to editing files in DSH.

AI form filling and spreadsheet autofill for XLSX in DeepSeek Harness, using authorized Qichacha MCP facts with cell previews, user confirmation and export to a new copy.

Installs a Web-profile helper that diagnoses and writes MCP config so Codex, Cursor, or Claude Code can spawn dsh --profile codex.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Track the origin of local development ports on Windows and safely manage verified DSH services.

MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.