2026.10.26 更新:ChatGPT Plus 国内订阅教程,涵盖 Gmail 注册、美区 Apple ID 礼品卡充值、Codex 手机号验证与二次验证、接码、CC Switch、中转、性价比对比,以及模型与推理强度选择。
reasoning-effort 开源项目推荐(152 个)
reasoning-effort 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 152 个仓库DSH适用的大肥鱼跑步思考强度滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness
Codex 风格的推理等级滑条(DeepSeek Harness 插件):可拖动连续滑条 + 高档位渐变星尘特效
Use GPT, DeepSeek, GLM, Gemini, Kimi and 400+ models in Claude Desktop's own model picker and in Claude Code, while staying signed in to your Claude subscription (1P, no gateway mode). Auto reasoning effort per prompt, subagents routed by difficulty, cache and limit warnings. Claude inside Codex too.
Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.
把 WorkBuddy(多账号/企业版)、Trae CN / TRAE SOLO CN、Qoder CN 三家订阅聚合进同一个 DSH 模型选择器:会话内换模型不丢历史、积分倍率、逐模型思考档位、每日自动签到、读图与 Agent 工具调用。One DSH plugin aggregating WorkBuddy / Trae / Qoder subscriptions into one model picker: mid-session switching, credit multipliers, reasoning effort, daily check-in, vision, tools.
A DeepSeek Harness plugin for reasoning-effort defaults and protocol-aware gateway compatibility settings for llm-pi-ai models.
Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).
科幻推理等级滑条 for DeepSeek Harness:Ultra 档 + 闪电编排模式 + 子代理 tok/s 读数 / A sci-fi reasoning-effort slider for DSH
Open-source model and reasoning effort router for Claude Code and Codex, using Jev or experimental self-hosted Laya.
ZCode 桌面客户端增强插件:思考档位配置(3.14+ 原生 optionSpecs)、用量图表全量、TPS 状态栏、思考强度滑条、一键增强提示词、设置页模型拉取。纯 Python 标准库,全部可检查、可精确还原、可在插件详情页逐项开关。
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness deps, no YAML.
DSH Web 客户端的 Codex 风格「思考强度」电源滑块 —— 拖一下就切换会话的真实推理强度;紫色扫描、漂浮星尘、拖柄墨点全部手写,零构建零依赖。
Superseded by robertn702/reasoning-router
DeepSeek Harness 自己的 fast 模式:按步骤自适应思考档位 + 按档位批量并行工具调用,零依赖;只使用当前路由真正声明过的档位,官方 API 与自建网关都支持。
Spend 20–50% fewer tokens and get responses ~1.5× faster in Claude Code: automatic reasoning effort for every turn — xhigh for plans, medium for building, low for questions and trivial tasks like git commits.
DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.
Codex 桌面版为 DeepSeek-V4-Flash 开启 Max 推理档位的完整排障与配置指南 / Complete guide to enable Max reasoning effort for DeepSeek-V4-Flash in Codex desktop
Automatic model and effort router for Claude Code. A free plugin that picks Haiku, Sonnet or Opus for each prompt, adds risk floors and a review workflow, and shows cache and context state. No key, no server.
DeepSeek Harness 第三方 API 与自定义模型设置插件:支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/reasoning-effort。
- 该话题在 GitHub 上共有 152 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1272 Star,覆盖 5 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。