DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

System1 — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-system1

System1

面向 DeepSeek Harness 插件的类型化 System One 决策服务

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-system1@0.3.0
README兼容性版本

兼容性与来源证明

System1 以 dsh-system1 发布,当前版本为 0.3.0。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
npm
Registry 更新时间
2026/10/15

版本

0.3.0stable
2026/10/15
0.2.2stable
2026/10/11
0.1.1stable
2026/10/6
查看其余 1 个版本收起版本
0.1.0stable
2026/9/23

相关插件

正在加载相关插件…

最新版
0.3.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
350.8 kB
文件数
115
Surface
web
许可证
Apache-2.0
发布源
npm
GitHub
★ 0
周下载
0
最近提交
2026/10/15
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 agents-orchestration 分类下经过校验的插件。

Hindsight Coding Agents@vectorize-io/hindsight-coding-agents面向编程代理的仅反思式 Hindsight 长期记忆(可插拔支持多种运行框架:opencode、……),自动在后台导入(无需设置 CLI)。Ds Botds-botDS Bot:DeepSeek Harness 的一组长期运行的 Bot,支持主 Bot、Bot 间消息和群聊Agency Agents@michengai/dsh-agency-agentsDSH Agency Agents — 为 DeepSeek Harness 提供 331 名可召唤的领域专家DSCODE Desktop@toddzheng024/dscode-desktop为 Harness Desktop 提供编码协作、记忆、浏览器工作流和任务管理功能。

README

dsh-system1

A typed System One decision service for DeepSeek Harness plugins. Consumer plugins call ctx.system1.decide(), interpret the results, and choose their own actions.

English | 简体中文

PrimitiveResult
noulProbability that a proposition is true (probabilityTrue)
choiceCandidate key and the full probability distribution
scoreExpected zero-based level and the probability distribution
boxNormalized image coordinates for a located object

The service provides request and response validation, per-question results, cancellation, timeouts, provider registration, and execution metadata. TypeSafe/Jev and Cloudflare Clef accept shared image attachments; Jev 1.14 also supports box answers and optional extended context. Other backends can implement the public provider contract.

Install from npm

Install the package in a project that uses System One:

npm install dsh-system1

To activate the bundled service and providers in dsh, add the npm package to the profile you run. Replace <profile> with your profile name:

dsh plugin --profile <profile> add dsh-system1

The dsh plugin command requires a profile; installing into one profile does not activate the bundle in other profiles. To use the GitHub repository as the package source, replace dsh-system1 in that command with github:exoticknight/dsh-system1.

The bundled patch mounts the service and built-in providers. Defaults are model jev-latest, provider id typesafe, and an 800 ms timeout per model attempt. Use the plugin settings to choose a default service and model, add fallback models in the order they should be tried, configure connections, and store keys in DSH credentials; environment variables are also supported. Each fallback gets the full timeout budget, so total request time can grow with the chain length. Adjust timeoutMs to fit backend latency, especially for local CPU inference.

Cloudflare uses provider cloudflare with clef, clef-flash, or clef-omni. See provider setup for configuration.

Agent tool

Once installed, the agent can call the system1_decide tool without a consumer plugin. The main model can hand yes/no checks, classification, and scoring to System One and decide the next step from the returned probabilities. The tool uses the default service and model configured above.

The bundle's system1-tool component provides the tool and is enabled by default. Turn the component off on the Plugins page to remove the tool, or set disabled: true on its entry in a headless profile. See the API reference for arguments and results.

Use from a consumer plugin

In your consumer plugin project, install the package with the npm command above. Then declare inject: ['system1'] and import this package's Cordis type augmentation:

import type { Context } from '@deepseek-ai/cordis'
import type {} from 'dsh-system1'

export const inject = ['system1']

export async function apply(ctx: Context) {
  const result = await ctx.system1.decide({
    state: 'The user asked about a refund.',
    questions: {
      refund: {
        type: 'noul',
        instructions: 'Is the user asking about a refund?',
      },
      topic: {
        type: 'choice',
        instructions: 'Choose a topic.',
        criteria: { billing: 'Billing', technical: 'Technical support' },
      },
      urgency: {
        type: 'score',
        instructions: 'Rate urgency.',
        criteria: ['Normal', 'Urgent', 'Critical'],
      },
    },
  })

  if (result.answers.topic.status === 'ok') {
    return result.answers.topic.answer.value // 'billing' | 'technical'
  }
  return result.answers.topic.error
}

noul returns probabilityTrue; choice returns a candidate key and its full distribution; score returns an expected level and probabilities ordered by criteria; box returns normalized image edges. These are model outputs, so consumer plugins choose their own decision thresholds and actions. Runtime failures are reported per question with status: 'error'; malformed call structures throw System1InputError.

See API and provider development for the full contract and the consumer example. TypeSafe supports jev-latest, jev-preview, jev-1.14.0, and jev-1.13.0; see provider setup for other services and their limits.

Development

Use the Node.js and pnpm versions declared in package.json:

pnpm install --frozen-lockfile
pnpm verify

pnpm test runs the plugin and provider tests with local fixtures, as CI does; pnpm test <plugin|providers|provider name> runs a subset. Live model probes, pnpm probe <typesafe|cloudflare|laya|clef-local>, read credentials from .env.local, and local targets set up their own service on first use; see testing and live model validation.

See the contribution guide and release process.

License

Licensed under the Apache License 2.0.