dsh-reasoning-effort
HanaAyane
DSH适用的Q版大模型娘跑步思考强度滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness
GITHUB TOPIC
20个项目包含此标签
20 个项目
GitHub Topic 精确匹配
HanaAyane
DSH适用的Q版大模型娘跑步思考强度滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness
Microqian2th
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
hytime
A DeepSeek Harness plugin for reasoning-effort defaults and protocol-aware gateway compatibility settings for llm-pi-ai models.
yuhub233
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
sanshanya
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.
NNNOOOMII
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。
justhalfbit
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.
karina2256
一个全新的为了dsh而准备的推理强度滑块,有chatgpt同款风格,改动自另外两位,现在已经是完全体
john-walks-slow
Through Jev or through its own tool calls, the agent switches model presets and thinking depth on its own. A DeepSeek Harness plugin: set_model/list_models and switch_preset/list_presets behind independent switches, Jev auto-switching, Plan Mode staging, and a Web settings page.
supersealwqas
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
Neptune810
Flash-only reasoning-effort routing for DeepSeek Harness, setting the DeepSeek flash model reasoning effort per step. The model never changes; effort max is opt-in.
edwardzhou21
DSH 插件 · 仿 Codex 的推理等级滑条,内嵌在模型选择器里 | Codex-style reasoning-effort slider embedded in the DSH model selector
peach0x33a
DSH plugin: fill custom-provider model metadata from models.dev through an explicit, pre-declared mapping — no guessing, fail-closed. Includes a graphical settings page.
TonyKingWJX
DeepSeek Harness 模型与推理等级选择器 · 自绘滑杆 UI · 六种视觉主题
bamboostrip
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
EchoEon5
Codex-style reasoning effort slider for DeepSeek-Harness that adapts to each model's own number of thinking levels.
Fyerl
2D Model Picker for DeepSeek Harness — select a model and reasoning effort in one drag.
Mutx163
🧠 DSH 自定义模型思考等级管理与偏好持久记忆插件 | Custom model reasoning effort management & cross-session memory for DeepSeek Harness
shuang-ying
"DSH bundle that syncs per-model thinking levels from each endpoint's own model listing
youqisibun
Claude Code–style six-stop reasoning-effort slider for DeepSeek Harness, with a pixel-texture Ultracode mode