DTSFO/dsh-model-modes

Name: DTSFO/dsh-model-modes
Author: DTSFO

Plugin插件 Native原生 ⭐ 2 MIT Models & Routing模型与路由 Clients & Launchers客户端与启动器

面向DeepSeek Harness的能力感知推理控制与快速模型路由

Project Overview项目介绍

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

dsh-model-modes is a native plugin built exclusively for the DeepSeek Harness web composer, adding capability-aware reasoning profiles and support for provider-native fast mode routing. It integrates directly with DSH’s official model selector to keep reasoning selections up to date, and expands model matching to all llm-pi-ai providers that host the exact requested model ID. To install the latest release, run the command dsh plugin --profile web add https://github.com/DTSFO/dsh-model-modes/archive/refs/tags/v0.1.3.tar.gz in your terminal, then start DSH web with dsh web. For local development, clone the repository, run pnpm install and pnpm run check to validate, then add the local plugin path to your DSH instance.

It adds a clearly marked Fast mode toggle to the DSH web composer, and toggling it on injects the native fast or priority tier parameter directly into the current provider’s request without altering reasoning level, switching models, or changing the selected DSH provider. Fast mode is orthogonal to reasoning effort, so it never selects a lower-effort model or a flash/turbo sibling model to cut costs or reduce latency through a model change. All state is isolated per concurrent session using AsyncLocalStorage, and the plugin exposes GPT-5.6’s Max and Ultra as independent reasoning options for users to select.

The plugin currently supports over ten major LLM providers including OpenAI, OpenAI Codex, xAI, Google Gemini, OpenRouter, MiniMax, Vercel AI Gateway, and Fireworks, each with an explicit allowlist of models that support fast/priority tier. Fast state is process-local and defaults to off after a DSH Host restart, and it is bound to the provider/model selected when the toggle is enabled. The plugin is targeted to DSH rc.6 and llm-pi-ai 0.82.1, is released under the open-source MIT license, and any additional costs, entitlement requirements, or regional capacity limits are set entirely by the selected LLM provider.

这是专为DeepSeek Harness（DSH）网页编辑器开发的原生插件，主打能力感知推理配置和厂商原生极速模式支持。它能让推理选项选择保持和DSH官方模型选择器同步，将匹配规则扩展到所有带有对应模型ID的llm-pi-ai厂商，还把GPT-5.6的Max和Ultra暴露为独立可选选项。安装可通过执行dsh插件添加命令指向已标记的发布版本压缩包，之后启动DSH网页端即可完成配置使用。

它在DSH编辑器中添加了一个区分清晰的极速模式（Fast）开关，开启后会直接给当前厂商的请求注入原生极速/优先级参数，不会降低推理强度、更换模型或者切换DSH厂商。Fast选项和推理级别是正交独立的，它不会自动切换到更便宜的推理模型或者flash/turbo这类兄弟模型，而是在最终请求边界注入参数，每个并发会话通过AsyncLocalStorage保持状态隔离。

当前支持OpenAI、xAI、Google、OpenRouter、MiniMax、Vercel AI Gateway、Fireworks等十余个主流大模型厂商的极速模式参数适配，每个厂商都有明确的允许列表和默认策略。插件采用失败闭包设计，不支持的路由会显示不可用，现有手动配置的推理优先级仍然有效，仅会补充缺失的配置选项。它遵循MIT许可证，对账号权限、区域容量等额外限制由对应厂商决定。

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-model-modes（DTSFO/dsh-model-modes）
仓库：https://github.com/DTSFO/dsh-model-modes
本站详情页：https://www.yhbd.top/plugins/dtsfo-dsh-model-modes/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-16 · 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 \

把 DTSFO/dsh-model-modes 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

12.2 KB · 缓存于 2026-08-23 03:42:28 · 12.2 KB

dsh-model-modes

Capability-aware reasoning profiles and provider-native Fast mode for the DeepSeek Harness web composer.

What it does

Keeps reasoning selection in DSH's official model selector.
Expands reasoningProfiles.provider: '*' to every llm-pi-ai provider that actually contains the exact model id; no myself hardcoding.
Exposes Max and Ultra as independent choices for gpt-5.6.
Adds a clearly differentiated Fast ON/OFF switch to the composer.
Applies the current provider's native fast/priority request parameter without lowering reasoning, changing model, or changing the DSH provider.
Tracks the official per-session ModelDirectory; unsupported routes are visibly unavailable and rejected by the Host.

Max + Fast and Ultra + Fast are both supported combinations.

Fast semantics

Fast is orthogonal to reasoning. It never selects a cheaper reasoning effort, a flash/turbo sibling model, or another DSH provider. Injection happens at the final llm-pi-ai Models.streamSimple() boundary and is isolated per concurrent session with AsyncLocalStorage.

Built-in provider contracts

DSH provider	pi-ai API	Fast wire parameter	Default policy
`openai`	OpenAI Responses / Chat Completions	`service_tier: "fast"`	Exact official model allowlist
`openai-codex`	`openai-codex-responses`	`service_tier: "fast"`	Exact Codex allowlist: GPT-5.6 Luna/Sol/Terra, GPT-5.5, and GPT-5.4
`xai`	OpenAI Responses / Chat Completions	`service_tier: "priority"`	All text models on this exact provider
`google`	`google-generative-ai`	`config.serviceTier: "priority"`	Exact Gemini Developer API allowlist
`openrouter`	OpenAI-compatible text APIs	`service_tier: "fast"`	All models on this exact provider; upstream may fall back to Standard
`minimax` / `minimax-cn`	`anthropic-messages`	`service_tier: "priority"`	Exact MiniMax model allowlist
`vercel-ai-gateway`	`anthropic-messages`	`providerOptions.gateway.speed: "fast"` plus `allowFallbackFromFast: false`	Exact live Fast-model intersection; fast-or-fail, with no silent Standard fallback
`fireworks`	`anthropic-messages` / `openai-completions`	`service_tier: "priority"`	Exact nine-model allowlist; request-level Priority, not a Fireworks `*-fast` router/model switch
`azure-openai-responses`	`azure-openai-responses`	`service_tier: "priority"`	Explicit opt-in only: deployment, API version, SKU, and region are not visible to the matcher
`google-vertex`	`google-vertex`	`X-Vertex-AI-LLM-Shared-Request-Type: priority`	Explicit opt-in only: Priority PayGo requires a supported model and the `global` endpoint
`amazon-bedrock`	`bedrock-converse-stream`	`serviceTier: { type: "priority" }`	Explicit opt-in only: support varies by model card, inference profile, and region

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 DTSFO/dsh-model-modes 的 README.md。在 GitHub 查看原文 →