dsh-codex-effort-slider
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
GITHUB TOPIC
24projects include this topic
The "reasoning-effort" topic on GitHub groups 24 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-codex-effort-slider with 150 GitHub stars. dsh-codex-effort-slider — 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. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
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
HanaAyane
Codex-style reasoning-effort slider for DSH, plus a big fat fish running slider. Codex-style model and reasoning-effort slider for DeepSeek Harness
HaoyueQin
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.
regrevia
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。
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.
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.
JuneLearn
Add Low, Medium, High and other reasoning levels to DeepSeek Harness third-party APIs, with model selection for each subagent call | Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call
supersealwqas
DeepSeek Harness third-party API and custom model settings plugin: supports request headers, User-Agent, model list, image input and reasoning levels | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
forestbiankiii
Unofficial DSH Desktop provider extension: composer provider/account/model controls with per-account subscription quota
Mutx163
🧠 DSH plugin for custom model reasoning effort management & persistent preference memory | Custom model reasoning effort management & cross-session memory for DeepSeek Harness
peterwangze
DSH (DeepSeek Harness) plugin: unified default reasoning level (thinking effort) for all models — per-model defaults with capability probing, live call statistics, one-command install via dsh plugin
Shuffle-1992
DSH 上下文智能压缩 + 智能思考:每轮注入用量、模型自主决定压缩并自动续跑;可选让模型按任务难度自主调整思考强度档位
Vast-Unhurried
DeepSeek Harness utility toolbox: notes, API balance and cost, delete sessions, third-party model reasoning level, conversation node navigation bar, light neumorphic skin
AI-Galaxy-GPU
DeepSeek Harness plugin: choose the model's reasoning effort for a session in the Web GUI; the Starlight reasoning selector switches Off / Default / High / Max with one click.
neo805
DSH plugin: context-aware per-step reasoning-effort routing — classify → escalate → hysteresis → capability clamp; Auto mask in the native selector; default effort fill + wire mapping for custom llm-pi-ai models. AI-authored (kimi-k3), produced by @neo805. No Issues/PRs; forks welcome (MIT).
Model-aware reasoning effort slider for DeepSeek Harness, with a Claude-inspired WebGL energy field, native themes, and a live demo.
AndyZh0
Claude-style Ultra mode for DSH: the top reasoning effort plus Claude's standing multi-agent orchestration.
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.
frederico-kluser
DeepSeek Harness plugin: pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.
icekale
Automatically add reasoning-level controls to compatible DeepSeek Harness provider models
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.
raomaiping-hash
DSH plugin: per-model reasoning-effort levels and input modalities for custom llm-pi-ai providers — fields the official Models page does not expose. Cordis plugin, install via dsh plugin --profile web add github:raomaiping-hash/dsh-model-caps
Triple3h
DSH Web plugin: per-model reasoning-effort configuration and selection — settings page + slider embedded in the model picker.