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

DSH-Think-zhLen7183/DSH-Think-zhCatalog AnalyzedDeepSeek Harness 默认的思考语言为英文,这不利于中文使用者阅读推理过程与复核结论。本Plugin通过在每次Request的 system prompt 中注入一条精简的强制语言指令,使: 思考过程强制简体中文,无论用户用什么语言提问。Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals17 starsdsh-thinking-efforta1141171521/dsh-thinking-effortCatalog Analyzeddsh 工作区可添加多文件夹/第三方厂商模型可开启推理等级PluginTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-thinking-effort@hytime/dsh-thinking-effortCatalog AnalyzedConfigure reasoning-effort levels and sub-agent defaults for custom DSH models.Models & ProvidersnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.2.0Evidence updated2026-09-06Public signals23 stars · 2677 downloadsdsh-thinking-languageqingmomo233/dsh-thinking-languageCatalog AnalyzedSwitch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.Sessions & MessagesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-thinking-levelsdsh-thinking-levelsCatalog AnalyzedPer-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.Models & ProvidersnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.6.0Evidence updated2026-09-07Public signals5 stars · 1827 downloadsdsh-ui-models-reasoningqmy777/dsh-ui-models-reasoningCatalog AnalyzedDeepSeek Harness 可插拔推理等级设置分节——为第三方模型逐模型配置思考力度与线格式映射,不动源码、即插即用。UI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-ultracodeBackMountainBird/dsh-ultracodeCatalog AnalyzedDSH plugin from BackMountainBird/dsh-ultracodeTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-weneedfirstXiaoWind/dsh-weneedfirstCatalog AnalyzedDeepSeek Harness plugin: make the chain of thought open with We need instead of Let meTools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsGLM-5.3-Flash-J-Space-Capability-Realization-ReportTiger3807861189/GLM-5.3-Flash-J-Space-Capability-Realization-ReportCatalog AnalyzedGLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition SuiteUI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1023 starsJ-Space-Cognition-Suite-V3.7Tiger3807861189/J-Space-Cognition-Suite-V3.7Catalog AnalyzedJ-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩:Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675UI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3020 starsluxueliu-reasoning-effortsluxueliu/luxueliu-reasoning-effortsCatalog AnalyzedDSH里只有ds能选推理强度?20个常用模型推理强度按钮已就位!涵盖grok/Gemini / Kimi/glm……20个模型仅预设,实际槽位无上限!可以任意添加你的本地网关模型!(非 ds 系网关模型推理强度档位Plugin + 路由级 llm-pi-ai 补丁)Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsthinking-level-overridemy-dsh-plugin/thinking-level-overrideCatalog Analyzed自主覆盖与调整第三方模型的思考等级,修复工具内置预设缺失或不匹配的问题。Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starstokens-as-parametersBruceLoveLee000/tokens-as-parametersCatalog AnalyzedDSH plugin from BruceLoveLee000/tokens-as-parametersUsage & BillingGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starswe-need-keeperUsamiEru/we-need-keeperCatalog AnalyzedDeepSeek Harness plugins that keep the model's reasoning in the We-need style for multi-turn conversation.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 stars

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