zhuchengde0214-ctrl/dsh-llm-databricks

Name: zhuchengde0214-ctrl/dsh-llm-databricks
Author: zhuchengde0214-ctrl

Plugin插件 Native原生 ⭐ 2 MIT Models & Routing模型与路由 Notifications & Remote通知与远程

Databricks AI Gateway 的 DeepSeek Harness 模型提供商插件

Project Overview项目介绍

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

This is a community-maintained native plugin built exclusively for DeepSeek Harness, which adds support for conversational models hosted on Databricks AI Gateway. It is not an official product from either DeepSeek AI or Databricks, and installs cleanly without modifying Harness core code or node_modules. It currently supports four common Databricks gateway route protocols, all of which enable streaming responses and tool calling for compatible models. To install the plugin, you can use one of three methods: install from npm, pull directly from the public GitHub repository, or build a local tarball and install from your local file system.

Before you get started, you need to have Node.js version 22.19.0 or newer, as well as a compatible DeepSeek Harness 0.1.0-rc.7 or newer install. You also need a valid Databricks bearer token for your target workspace, which is stored securely via Harness' built-in credentials service. After installation, you just add a llm-databricks configuration section to your user profile, then define one or more providers, each with their workspace URL, protocol, credential reference, and list of available models. Native Gemini embeddings are not implemented in the current 0.1.0 release, though Gemini conversation models work via the MLflow Chat Completions route.

The plugin enforces strict security boundaries by default, only allowing HTTPS requests to official Databricks subdomains on port 443. If you need to connect to a custom private DNS or non-standard port, you must explicitly enable the corresponding allow flags in your configuration, which should only be done for trusted private gateways. It properly maps common Databricks error statuses to Harness error types, and uses Harness' built-in retry policy for transient failures. Uninstalling the plugin is straightforward, and all configuration settings are portable between different Harness installations. The plugin is released under the open source MIT license.

这是一个由社区维护、专为DeepSeek Harness开发的原生插件，用于接入通过Databricks AI Gateway部署的对话大模型。它支持多种Databricks路由协议，包括MLflow Chat Completions、MLflow Responses、原生Anthropic Messages和原生OpenAI Responses，均支持流式输出和工具调用。它以独立包形式安装，不会修改DeepSeek Harness核心代码或node_modules，不涉及官方产品支持。

插件需要Node.js 22.19.0以上版本，以及兼容接口的DeepSeek Harness 0.1.0-rc.7以上版本，用户还需要准备Databricks的访问令牌。可以通过npm、GitHub或本地压缩包三种方式安装，安装后只需要在用户配置文件中添加llm-databricks配置段，声明服务商、工作区地址、协议和模型信息即可使用。

插件内置严格的安全边界，默认只允许官方Databricks域名的HTTPS请求，自定义域名和非标准端口需要手动开启授权。它会正确映射各类错误状态码，遵循Harness本身的重试策略，配置可迁移，卸载只需要移除插件和对应配置段，采用MIT开源许可授权。

View on GitHub在 GitHub 查看

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-databricks（zhuchengde0214-ctrl/dsh-llm-databricks）
仓库：https://github.com/zhuchengde0214-ctrl/dsh-llm-databricks
本站详情页：https://www.yhbd.top/plugins/zhuchengde0214-ctrl-dsh-llm-databricks/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-18 · 主语言 TypeScript

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-databricks

把 zhuchengde0214-ctrl/dsh-llm-databricks 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

7.7 KB · 缓存于 2026-08-27 05:41:43 · 7.7 KB

dsh-llm-databricks

中文

An independent, community-maintained DeepSeek Harness bundle for conversation models served through Databricks AI Gateway. It installs out of tree, uses the public Harness LLM/settings/credentials seams, and does not patch Harness or node_modules.

This package is not an official DeepSeek AI or Databricks product.

Support matrix

Databricks route	`protocol`	Streaming	Tools	Notes
MLflow Chat Completions `/ai-gateway/mlflow/v1/chat/completions`	`mlflow-chat`	Yes	Yes	OpenAI Chat wire format. Removes unsupported `store` and tool `strict`. Covers Databricks-served Claude, GPT, Gemini, Llama, DeepSeek, and other conversation models.
MLflow Responses `/ai-gateway/mlflow/v1/responses`	`mlflow-responses`	Yes	Yes	OpenAI Responses/OpenResponses behavior available through the Harness/pi-ai vocabulary. Removes unsupported `store` and tool `strict`.
Native Anthropic Messages `/ai-gateway/anthropic/v1/messages`	`anthropic-messages`	Yes	Yes	Uses only `Authorization: Bearer`; suppresses `x-api-key`. Preserves text, tool use, and thinking blocks supported by the model.
Native OpenAI Responses `/ai-gateway/openai/v1/responses`	`openai-responses`	Yes	Yes	Uses bearer authentication and the native Responses wire format.

Native Gemini API and embeddings are not implemented in 0.1.0. Gemini conversation models are already usable through MLflow Chat Completions. Harness's current LLM seam does not consume embeddings. Native Gemini is a roadmap item.

Requirements

Node.js ^22.19.0 or >=24
DeepSeek Harness 0.1.0-rc.7 compatible seams
A Databricks personal access token, OAuth access token, or other bearer token accepted by the configured workspace gateway

Install

From npm after a public release:

dsh plugin --profile web add dsh-llm-databricks

From the public GitHub repository:

dsh plugin --profile web add github:zhuchengde0214-ctrl/dsh-llm-databricks

For a packed local release:

pnpm pack
dsh plugin --profile web add ./dsh-llm-databricks-0.1.0.tgz

The package's dsh.bundle.patch adds a dormant llm-databricks plugin row. It registers routes only after configuration supplies providers.

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 zhuchengde0214-ctrl/dsh-llm-databricks 的 README.md。在 GitHub 查看原文 →