DeepSeek Harness

The dsh trace compare agent exploration use case is the fastest way to see why a DeepSeek Harness agent does what it does: install the dsh-maze plugin (formerly dsh-trace-compare), load a session log or follow a live run, and you get the agent’s full exploration maze — main path, failed detours, and backtracking points — rendered on a single timeline with deterministic, LLM-free analysis you can drill back to the raw commands and outputs. It turns an invisible black-box trajectory into something you can actually read, compare across models, and fix. ...

dsh-vision-router is a DeepSeek Harness (DSH) plugin that gives text-only agents eyes by routing image turns to a separate vision model while DeepSeek stays the reasoning brain. It installs with one command, needs no Python and no API key, and ships 14 deep vision tools plus cached visual memory so a text-only agent genuinely remembers earlier images without re-spending vision calls. What is dsh-vision-router and why text-only DeepSeek agents need eyes DeepSeek Harness is a local agent framework built around DeepSeek models. Many of its most popular models, including deepseek-v4-flash, are text-only: they declare inputModalities: ["text"] and simply cannot accept image attachments. That is a real limitation for agent work, because a growing share of tasks — reading a screenshot, checking a rendered UI, verifying a chart, OCRing a receipt — are fundamentally visual. ...

dsh-auto-review is a DeepSeek Harness plugin that puts a read-only second model on the approval chain, deciding allow or deny for every tool request and returning a structured verdict with a reason. It fails closed by default, so any crash, timeout, or schema mismatch resolves to rejected rather than a silent grant, and it feeds deny reasons back to the calling model so the agent learns instead of retrying blindly. ...

DeepSeek Harness (dsh) is an open-source agent harness by DeepSeek AI, built on an everything-is-a-plugin architecture powered by Cordis, where the model adapter, tool registry, session log, and even the agent loop itself are replaceable plugins. You can launch it in seconds with npx @deepseek-ai/dsh web, connect a DeepSeek API key in Settings, and start delegating file edits, command runs, and multi-agent workflows. This 2026 handbook is a source-backed guide to its agents, plugins, and runbooks. ...

DeepSeek Harness (dsh) records every agent run as a durable series of session events — reasoning deltas, tool calls, tool results, step starts and ends, and turn boundaries — and dsh trace compare is the workflow for visualizing and contrasting those exploration paths side by side. Instead of staring at linear chat logs, you render agent execution as a graph (a DAG) where parallel tool calls fan out from a single reasoning step and results fan back in, letting you pinpoint exactly where two runs diverge, stall, retry, or branch. This guide walks you through the session-event format, the native trajectory view, community comparison tools, and the pitfalls to avoid. ...

A DeepSeek Harness desktop app gives you a local AI workspace for DSH sessions without touching Node.js, pnpm, or Docker. The leading Tauri-based wrapper ships a ~5MB installer for Windows, macOS, and Linux, bundles the latest Harness core, and keeps your API key and sessions on your own machine. This guide reviews the top desktop apps in 2026 and helps you pick the right one. What Is DeepSeek Harness and Why a Desktop App? DeepSeek Harness (dsh) is DeepSeek’s open-source agent harness where “everything is a plugin.” Every capability — models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and even the UI — is a swappable plugin built on the Cordis kernel, which manages plugin mounting, unmounting, and dependencies. The main repository has grown to 209,475 stars and 24,455 forks as of 2026-09-02, making it one of the most-watched agent frameworks in the ecosystem. ...

The Rapid-MLX DSH Provider is a native npm plugin for the DeepSeek Harness (dsh) that lets the agent read its model configuration straight from a running Rapid-MLX server’s /v1/models endpoint instead of hand-written settings.yaml. Instead of copying context windows, reasoning efforts, and max_model_len values by hand — and re-copying them every time you switch models — the provider serves those facts directly from Rapid-MLX’s JSON schema, keeps reasoning control truthful, and compacts the context at the real memory limit of your Apple Silicon machine. ...

A DSH Lark bridge is a plugin that connects DeepSeek Harness (DSH) coding agents to Feishu or Lark group chats, so you can send a task from your phone, DM, or a group and the bridge runs it in the correct Harness project and session. You do not need a public IP, domain, webhook, or NAT tunnel: the bridge keeps a WebSocket long connection to the Feishu/Lark Open Platform and relays tool-call approvals, questions, files, and status updates back to a single native card. ...

The DeepSeek Harness iOS Simulator plugin is a live, interactive iOS simulator that runs inside a DeepSeek Harness (DSH) conversation — plus your real iPhone over USB — so your coding agent can see, tap, and verify the app it just changed. It ships 22 agent tools covering devices, screenshots, semantic UI navigation, build-and-run, SwiftUI preview hot reload, processes, and backtraces. This guide explains how it works, how to install it, and how it closes the verify gap that keeps coding agents from trusting their own Swift. ...

The DeepSeek Harness Agent Workflow plugin (dsh-plugin-agent-workflow) is a standalone, installable Web UI plugin that adds a dedicated “Workflow” tab to DeepSeek Harness, letting you orchestrate and inspect multi-step agent runs as a clear execution chain. It renders your real recorded Session events — model requests, model responses, and tool calls — in chronological order, split by user conversation turn, with token and cache statistics that reveal exactly how context is reused across steps. Because it is read-only and non-invasive, it never adds messages, prompts, or tools to your requests, making it a trustworthy observability layer for anyone running complex, multi-step agent workflows on DeepSeek Harness. ...