LeemanCheung/dsh-image-gen

Name: LeemanCheung/dsh-image-gen
Author: LeemanCheung

Plugin插件 Native原生 ⭐ 3 MIT Vision & Media视觉与多媒体 Models & Routing模型与路由

基于 GPT Image 2 的生成，带有渐进式 Codex 风格预览，适用于 DeepSeek Harness

Project Overview项目介绍

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

This is a native plugin built exclusively for the DeepSeek Harness (DSH) ecosystem, designed to add OpenAI GPT image generation capabilities directly into DSH workflows. It supports three OpenAI image models: gpt-image-2, gpt-image-2.5-flare, and gpt-image-2.5-sunburst, and follows the Codex-compatible image_gen tool naming convention for seamless integration. By default, it reuses the existing refreshable OAuth credentials from the active DSH Profile’s dsh-codex-connect connection, so most users do not need to manually configure an OpenAI API key to use it. It can also be configured to use a manually provided OpenAI API key instead of the Codex subscription, which gives users more flexibility in how they access the image generation API.

To generate an image, users simply call the image_gen tool from within a DSH conversation with a text prompt describing the desired output. The plugin supports progressive display of the generation process: API key mode streams up to three partial images from OpenAI, while Codex subscription mode shows a loading animation until the full image is ready. Once generation completes, the final image is saved as an immutable DSH attachment that can be previewed, downloaded, and replayed even after the conversation session is reloaded. This plugin is ideal for any DSH user that wants to add image generation directly to their AI coding or conversation workflow.

This plugin is released under the permissive MIT open source license, so it can be used, modified, and distributed freely with no restrictions beyond the license terms. It has several documented limitations: it does not currently support editing existing images, the Codex subscription endpoint ignores explicit size and quality parameters, remote web clients cannot access previews directly, and it cannot interrupt stalled provider requests. When first running the plugin, users must ensure they have either an active signed-in Codex subscription or a valid OpenAI API key configured, otherwise the image generation calls will fail before they start.

这是一个专为DeepSeek Harness (DSH) 打造的原生图像生成插件，支持调用OpenAI的多个GPT图像生成模型生成图片，默认使用用户已登录的Codex订阅凭证，也支持手动配置OpenAI API密钥使用。它支持gpt-image-2、gpt-image-2.5-flare、gpt-image-2.5-sunburst多个模型，兼容Codex的image_gen工具调用格式，可复用DSH Profile内的Codex Connect凭证，无需额外配置密钥就能直接使用。

用户在DSH的对话中调用这个插件，只需输入生成图片的提示词，就能触发图像生成流程。插件支持渐进式显示生成过程，API密钥模式下会显示最多三张部分生成的图片，订阅模式会显示加载动画直到生成完成。生成的图片会作为永久附件保存在DSH中，支持后续预览、下载和对话重放，适合需要在DSH工作流中直接生成图像的开发人员和普通用户。

这个插件采用MIT许可证开源，可免费使用和修改。它存在一些已知限制，比如目前不支持编辑已有图片，订阅端点返回的图片尺寸和质量由OpenAI决定，可能和API密钥模式的参数要求不一致。首次使用需要确保已登录Codex订阅或者配置好有效的OpenAI API密钥，否则无法正常调用生成接口。

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-image-gen（LeemanCheung/dsh-image-gen）
仓库：https://github.com/LeemanCheung/dsh-image-gen
本站详情页：https://www.yhbd.top/plugins/leemancheung-dsh-image-gen/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-09-27 · 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 3 stars - very few users, little community feedback星标只有 3，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-codex-connect

把 LeemanCheung/dsh-image-gen 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

24.1 KB · 缓存于 2026-09-26 22:10:47 · 24.1 KB

dsh-image-gen

Generate images in DeepSeek Harness with OpenAI gpt-image-2.5-flare (or gpt-image-2.5-sunburst and gpt-image-2), using a signed-in Codex subscription by default or an API key when explicitly configured.

Linked development installs also resolve Codex Connect from the active DSH Profile. This uses the connector's public store, including its selected account in the current multi-account format, instead of mistaking an inaccessible optional dependency for a signed-out account. The same path has been verified against the installed Profile without displaying credential values.

中文说明

Animated dsh-image-gen progressive preview

dsh-image-gen completed durable image card

These illustrations mirror the shipped developing and completed card states. API-key mode can replace the light field with real streamed drafts; Codex subscription mode animates until its non-streaming response arrives. The completed state remains available as a durable DSH attachment with preview and download controls.

Capability map

Area	Delivered behavior
Tool and access paths	Exposes the Codex-compatible `image_gen` tool for `gpt-image-2.5-flare`, `gpt-image-2.5-sunburst`, and `gpt-image-2`; defaults to refreshable `dsh-codex-connect` subscription OAuth and can explicitly use a DSH API-key credential.
Progressive experience	Subscription requests show a developing animation until their non-streaming result; API-key requests can show up to three provider-sent partial images, cross-faded in place.
Durable results	Saves only the completed image as a DSH immutable attachment, so the same card can replay, preview in a lightbox, and download after a session reload.
Conversation compatibility	Returns text-only tool output to the model while retaining the image reference in UI metadata, including for nested Code Mode calls.
Safety boundaries	Resolves credentials per request, pins the subscription endpoint, rejects redirects, bounds response sizes and concurrency, validates image bytes through DSH, and retries only transient failures.

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 LeemanCheung/dsh-image-gen 的 README.md。在 GitHub 查看原文 →