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.

Model Context Catalog — DSH Plugin for DeepSeek Harness
← Plugins

dsh-model-context-catalog

Model Context Catalog

Context-window metadata catalog and settings UI for configured DeepSeek Harness model routes.

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

npx -y @deepseek-ai/dsh plugin --profile web add dsh-model-context-catalog@0.2.1
READMECompatibilityVersions

Compatibility and provenance

Model Context Catalog is published as dsh-model-context-catalog and currently resolves to version 0.2.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
9/1/2026

Versions

0.2.1stable
9/1/2026
0.2.0stable
9/1/2026

Related plugins

Loading related plugins…

Latest
0.2.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
54.5 kB
Files
9
Surface
web
License
MIT
Source
npm
GitHub
★ 1
Weekly downloads
0
Last push
9/1/2026
View source ↗
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.

Usage@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 the current session provider's today usage on the sidebar entryWhale 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 Stats@ychris12138/dsh-usage-statsToken usage heatmap, provider balances, and subscription quotas for the dsh web GUICodex Connectdsh-codex-connectChatGPT OAuth and Codex models for DeepSeek Harness.

README

dsh-model-context-catalog

为 DeepSeek Harness(DSH)的 llm-pi-ai 模型维护准确的路由级 contextWindow,避免长会话被错误判定为上下文溢出。

效果展示

上下文窗口设置页面

解决什么问题

自定义模型路由未声明上下文窗口时,DSH/pi-ai 会使用 262,144 tokens 的兜底值。 当实际请求超过这个猜测值时,服务端即使成功返回,也可能被重新分类为:

pi-ai detected context overflow for model "glm-5.3-flash"

这会导致两种典型现象:

  • 工具调用可以继续,但最终自然语言回答失败;
  • /compact 使用同一路由生成摘要,也被误判为溢出,压缩无法提交。

本插件按精确的 provider/model 路由写入正确的 contextWindow,并通过 DSH 公开 Settings API 同步到 llm-pi-ai。它不修改 DSH/pi-ai 内部代码,也不接管 provider 凭据。

完整证据和上游代码路径见 ROOT_CAUSE.md。

安装

从 npm 安装

dsh plugin --profile web add dsh-model-context-catalog

从本地目录安装

dsh plugin --profile web add /absolute/path/to/dsh-model-context-catalog

安装后刷新 DSH Web 页面;如果 Host 尚未加载插件,请重启 DSH Host。

使用

  1. 打开 设置 → 上下文窗口。
  2. 点击 添加模型。
  3. 从已经配置的 llm-pi-ai 模型中选择路由。
  4. 输入该部署真实支持的上下文窗口,可选填写备注。
  5. 保存并确认状态变为 已生效。

模型选择器会原样显示 provider 和模型信息,包括 (Agent Plan) 等套餐后缀。 相同模型经不同 provider 或网关部署时,应分别配置。

上下文窗口必须以对应服务商文档或控制台为准。配置过小会继续造成误报;配置过大 可能掩盖真实溢出。

行为边界

  • 仅处理 llm-pi-ai 中已经配置的模型,不合成不存在的路由。
  • 仅维护 contextWindow,不写入未经验证的 maxTokens。
  • 只更新目标模型的上下文窗口,保留名称、endpoint、协议、凭据引用和其他字段。
  • provider 默认值只作为默认值显示,不会冒充模型的真实容量。
  • 已删除路由的旧目录条目仅在编辑自身时回显,方便清理。

开发

npm install
npm run check
npm test
npm pack --dry-run

贡献规范见 CONTRIBUTING.md,版本记录见 CHANGELOG.md。

License

MIT