DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Llm Agentrouter — DSH Plugin for DeepSeek Harness
← Plugins

@lynn123411/dsh-llm-agentrouter

Llm Agentrouter

AgentRouter relay aggregation: one pi-ai route supports multiple models (fetch from the relay service within the settings card, then edit models and parameters individually) + one-click switching between domestic/international endpoints + an outbound request User-Agent/402-quota rewrite boundary. Th

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add @lynn123411/dsh-llm-agentrouter@0.5.0
READMECompatibilityVersions

Description

AgentRouter relay aggregation: one pi-ai route supports multiple models (fetch from the relay service within the settings card, then edit models and parameters individually) + one-click switching between domestic/international endpoints + an outbound request User-Agent/402-quota rewrite boundary. The model list is written to the same llm-pi-ai route data edited on the core “Settings - Models” page.

Compatibility and provenance

Llm Agentrouter is published as @lynn123411/dsh-llm-agentrouter and currently resolves to version 0.5.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
10/16/2026

Versions

0.5.0stable
10/6/2026
0.4.1stable
9/29/2026
0.4.0stable
9/26/2026
Show 6 more versionsCollapse versions
0.3.1stable
9/20/2026
0.3.0stable
9/12/2026
0.2.3stable
9/11/2026
0.2.2stable
9/10/2026
0.2.1stable
9/8/2026
0.2.0stable
9/3/2026

Related plugins

Loading related plugins…

Latest
0.5.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
71.7 kB
Files
8
Surface
web
License
MIT
Source
npm
GitHub
★ 3
Weekly downloads
115
Security scan
✓ v0.5.0 scan passed
Last push
10/5/2026
View source ↗Project homepage ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in models-usage.

Whale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinUsage@linxin666/dsh-usageUsage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with a compact price glance card above the sidebar's Settings rowClient Ui Model Capabilities@linxin666/dsh-client-ui-model-capabilitiesPer-model capability declarations (image input and reasoning efforts) for custom pi-ai providers, edited in place on the Models settings cards; writes the official llm-pi-ai settings namespace, no DSH source changes.Plugin@opencode2dsh/dsh-pluginFree OpenCode Zen models for DeepSeek Harness (DSH): native dsh-llm adapter plugin, no API key.

README

@lynn123411/dsh-llm-agentrouter

AgentRouter 中转聚合插件:把同一家中转的多个模型收拢为一条 pi-ai 路由(模型选择器只出现一个 AgentRouter 分组),国内 / 国际端点在本插件的配置页一键切换、下一请求即生效,外加出站请求的 User-Agent 改写与 402 配额耗尽提示围栏。模型列表在卡片内直接编辑,写入内核「设置 - 模型」页所编辑的同一份 llm-pi-ai 路由数据。

特性

  • 单路由多模型:Claude Opus 5、GPT-5.6-sol 等走同一 agentrouter 路由,reasoningEfforts 各档位与 compat 开关按实测探针手写声明,模型列表不翻倍。
  • 模型列表可编辑:设置卡片里直接列出这条路由的模型,更新 向中转站询问它现有的模型 ID(只补缺失的、不动已有条目),每个模型的 ID / 显示名 / 上下文窗口 / 最大输出 / 输入模态 / 各推理档位与线上取值都可改,保存后下一个请求即生效;新补入的模型默认 1048576 上下文、131072 输出、text+image、off..max 七档。改的就是路由自己的 models——llm-pi-ai 这条 profile 插件配置里的 providers.agentrouter.models,内核「设置 - 模型」页对该路由注册的写入地址也正是这里,两边同一份数据;patch 里手写的那几条是「重置」的基线。
  • 端点一键切换:设置卡片两个大选项(国内端点 / 国际端点,附带真实 host 展示),点击即写即生效,无需重启;API Key 只存 $DSH_HOME/.credentials.yaml 的 AGENTROUTER_API_KEY 引用。
  • 配置页挂在宿主「插件」页:本插件的端点卡片注册进 plugins.bundle.config(key 为包名 @lynn123411/dsh-llm-agentrouter),路径是「插件」→本插件详情页 —— 配置直接铺在描述之下、行列表之上。页面由宿主画标题、图标与面包屑;设置页里不再有任何本插件的入口。做法与约束见仓库 docs/rules/plugin-config-page.md。
  • 请求围栏:重写 relay 要求的 User-Agent(适配器强制署名下沉到 fetch 层替换),哨兵 host(.internal 不可解析)兜底防裸奔,402 配额耗尽的 JSON 错误体改写为可读提示。
  • 内核设置接入:本插件 Config 里需要实时生效的字段都声明为 .volatile(),设置面据此派生表单、并把配置写回同一批引用(ctx.inject(['settings']) + ctx.settings.configure({ auto: false }) 记下「本插件自带 UI」);客户端卡片挂在插件页的 plugins.bundle.config 上(key 为包名),读写的是 llm-agentrouter 这条 profile 插件配置,条目 id 即设置命名空间。

安装

dsh plugin --profile web add @lynn123411/dsh-llm-agentrouter