DSH Plugin HubDSH 插件市场

Badakonpro/dsh-llm-volcengine

Bundle捆绑包 Native原生 ⭐ 2 MIT Migration & Compatibility迁移与兼容Runtime & Injection运行时与注入Models & Routing模型与路由

Plugin for integrating DeepSeek Harness (DSH) with Volcano Ark Agent Plan and Coding Plan, with thought intensity (low/medium/high/xhigh/max) compatibility verified through real-world testing.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This repository is a native DSH profile bundle built exclusively for DeepSeek Harness, that adds support for Volcengine Ark's Agent Plan and Coding Plan LLM providers. It resolves a number of common configuration issues that users run into when manually adding a Volcengine route to DSH’s settings.yaml, including incompatible request formats, incorrect max token caps that break or underutilize models, and missing support for thinking effort controls. To install, users run the dsh plugin --profile <profile-name> add dsh-llm-volcengine command from their DSH profile root, then restart DSH or reload their profile to activate the bundle.

It is targeted at DSH users who want to use popular large models like DeepSeek v4, GLM 5, Kimi K series, and Doubao Seed via Volcengine Ark’s service inside DSH. After installation, users just need to configure their Volcengine Ark API key, either via DSH’s built-in credential service or an environment variable, and can even override the default credential environment variable name in the bundle’s config if needed. Two new provider routes, volcengine-plan for Agent Plan and volcengine-coding for Coding Plan, will then appear in DSH’s model selector, and users can select any pre-configured model directly from the list.

The bundle leverages community-verified compatibility data from pi-ai’s existing Volcengine provider packages, and does not rely on the existing dsh-llm-pi-ai compatibility schema because all model-specific compatibility settings are built directly into the bundle. All per-model max token limits and thinking effort support are pre-configured based on community testing, so users do not need to adjust these settings manually. It is released under the open-source MIT license, so it is free to use for both personal and commercial projects, and users can adjust default reasoning effort via cordis.patch.yml to match their preferences.

这是一个专为DeepSeek Harness（DSH）开发的原生配置包，用于为DSH添加火山引擎方舟（Volcengine Ark）的Agent计划和编码计划LLM提供程序支持。它解决了手动在settings.yaml中声明火山引擎路由时遇到的诸多常见问题，比如错误的请求格式、不对的最大令牌限制，以及缺失的思考强度控制功能。用户可以通过DSH的CLI命令将其安装到现有DSH配置文件中，安装完成后需要重启DSH或者重新加载配置文件才能生效。

这个工具面向使用DSH且希望通过火山方舟调用DeepSeek、GLM、Kimi、Doubao等主流大模型的开发者。安装完成后，用户只需要配置好火山方舟的API密钥，两个新的提供程序路由volcengine-plan和volcengine-coding就会出现在DSH的模型选择器中。用户可以直接选择对应路由下的任意模型，插件会自动处理请求格式兼容和每款模型的参数限制。

该包基于pi-ai的社区验证兼容规则开发，本身不依赖dsh-llm-pi-ai的兼容配置schema，所有模型的兼容设置都内置在包中。它采用MIT许可协议开源，完全免费供个人和商业使用。用户可以通过环境变量或者DSH凭证服务配置API密钥，还可以在cordis.patch.yml中修改默认的密钥环境变量名和默认思考强度。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-llm-volcengine（Badakonpro/dsh-llm-volcengine）
仓库：https://github.com/Badakonpro/dsh-llm-volcengine
本站详情页：https://www.yhbd.top/plugins/badakonpro-dsh-llm-volcengine/
本站登记：类型 bundle · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-16 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 2 stars - very few users, little community feedback星标只有 2，几乎没人在用，遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add dsh-llm-volcengine

把 Badakonpro/dsh-llm-volcengine 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

7.7 KB · 缓存于 2026-09-01 05:12:18 · 7.7 KB

dsh-llm-volcengine

npm version MIT License

Volcengine Ark Agent Plan and Coding Plan providers for DeepSeek Harness (DSH), with verified thinking-effort compatibility.

A DSH profile bundle that registers two LLM provider routes through a self-contained pi-ai-backed LlmAdapter, so model catalogs and compatibility switches reach pi-ai without depending on the dsh-llm-pi-ai settings compat schema. Thinking levels low / medium / high / xhigh / max are exposed where the endpoint honors them.

Why

A hand-declared Volcengine Ark route in settings.yaml runs into several gotchas that this bundle resolves once and for all:

Gotcha What breaks This bundle
Agent Plan must be reached over openai-responses at /api/plan/v3 The Anthropic-style /api/plan path does not expose a thinking-effort control Uses the community-verified Responses path; reasoning.effort maps natively
Coding Plan gateway rejects the OpenAI developer role (HTTP 400) Every request with a system prompt fails once reasoning is enabled compat.supportsDeveloperRole: false on every Coding Plan model
Coding Plan gateway rejects store and needs max_tokens (not max_completion_tokens) Mis-shaped requests are 400'd compat.supportsStore: false, maxTokensField: "max_tokens"
Per-model maxTokens differs (DeepSeek 384000, GLM 128000, Kimi 32000, …) A single cap breaks some models or underuses others Each model carries its verified cap
The gateway's OutofContextError wording is not in pi-ai's overflow detection Long conversations crash instead of auto-compacting (downstream — see release notes)

Install

From the root of a DSH profile (e.g. ~/.dsh/profiles/web):

dsh plugin --profile web add dsh-llm-volcengine

Then restart DSH (or reload the profile) so the new bundle layer is composed. The two providers appear in the model selectors as:

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 Badakonpro/dsh-llm-volcengine 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev semantic-linter 下一个 Next RemoteOps →