SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18

Pre-request Reasoning Strategy

在模型Request发出前配置或生成推理相关行为,包括推理档位声明、映射与持久化,按任务自适应调度推理强度,注入采样参数与思考预算,设置思考语言,切换模型思考模式,以及通过提示词引导推理风格与结构;不处理模型已经产生的思维链内容及其展示。

Use keyword search
Source catalog discovery.composite.2026-09-06.v1-0-5.b92b985e31dfCanonical structure · 823 nodes · 14829 plugins

Leaf membership

50 plugins

@bo_wu/dsh-reasoning@bo_wu/dsh-reasoningCatalog AnalyzedCodex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menuSessions & MessagesnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-08Public signals0 downloadsdsh-adaptive-effortimkingjh999/dsh-adaptive-effortCatalog AnalyzedDSH plugin: auto reasoning_effort (low/high/max) per turn via MiniMax complexity scorer + token ledger + per-reply metadata labelUsage & BillingGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-custom-provider-reasoning534119219/dsh-custom-provider-reasoningCatalog Analyzeddsh Plugin:让自定义提供方(pi-ai 手写路由)的所有模型都能选择思考强度(推理等级),选择经原厂适配器真正发往线上。A dsh plugin giving every custom-provider model selectable reasoning effort, wired through the stock pi-ai adapter.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-custom-reasoninggao-gao-zai/dsh-custom-reasoningCatalog AnalyzedDSH plugin from gao-gao-zai/dsh-custom-reasoningTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-effort-configbenzhoupo/dsh-effort-configCatalog Analyzeddsh plugin: configure reasoning-effort levels (wire spellings), route default level and Anthropic token budgets for third-party models from the settings page; selection reuses the native model-picker Effort panel.Usage & BillingGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-effort-tweakToukaiteio/dsh-effort-tweakCatalog AnalyzedA DeepSeek Harness plugin that allows you to change the reasoning effort of custom models in WebUI.UI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-language-controlwodongx123/dsh-language-controlCatalog AnalyzedForce the agent's chain-of-thought, planning, tool-invocation reasoning, and internal deliberation to stay in Chinese — the language constraint is injected at the top of the system prompt before every reasoning step, so it cannot be diluted by tool-returned content. A settings panel lets you edit the constraint text on the fly.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-llama-cpp-sampling-paramsdsh-llama-cpp-sampling-paramsCatalog AnalyzedDSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-08Public signalsNo public usage signalsdsh-llm-samplingkuma-loong/dsh-llm-samplingCatalog AnalyzedExact-model sampling policy bundle for DeepSeek HarnessTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-minimal-turboChangedenCZD/dsh-minimal-turboCatalog AnalyzedDeepseek Harness 极简模式 / 许愿模式 Windows 适配,享用满血 Deepseek-V4 系列模型。Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals41 starsdsh-model-memorydsh-model-memoryCatalog AnalyzedReasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.Models & ProvidersnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.12Evidence updated2026-09-07Public signals2 stars · 1875 downloadsdsh-model-modesDTSFO/dsh-model-modesCatalog AnalyzedCapability-aware reasoning controls and Fast model routing for DeepSeek HarnessTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-model-reasoning-defaultsdsh-model-reasoning-defaultsCatalog AnalyzedDSH (DeepSeek Harness) Plugin:为每个 LLM 模型配置默认推理等级(reasoningEffort),并在Request进入底层调用链前按路由规则自动补齐Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.0.2Evidence updated2026-09-09Public signals127 downloadsdsh-model-reasoning-intensityJD962/dsh-model-reasoning-intensityCatalog AnalyzedThis plugin complements DeepSeek Harness by fixing the problem where third-party platforms are unable to select the model's reasoning intensity.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-model-thinkingcyberlieflife/dsh-model-thinkingCatalog AnalyzedDSH (DeepSeek Harness) web plugin: thinking intensity / reasoning effort settings for custom OpenAI-compatible (pi-ai) modelsTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-models-dev-reasoningaerince/dsh-models-dev-reasoningCatalog AnalyzedAdds models.dev reasoning levels to unconfigured third-party DeepSeek Harness models.Themes & AppearanceGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-more-models-thinking-leveldsh-more-models-thinking-levelCatalog AnalyzedPer-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek HarnessTools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-09Public signals311 downloadsdsh-open-effortsdsh-open-effortsCatalog AnalyzedChoose reasoning effort for additional models in DeepSeek Harness, with Off and five standard levels.Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-08Public signals218 downloads

Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.