SEMANTIC DIRECTORY · plugin-directory-semantic-v3-19
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。
Leaf membership
54 plugins
dsh-more-models-thinking-leveldsh-more-models-thinking-levelCatalog AnalyzedPer-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek HarnessCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-26Public signals311 downloadsdsh-open-effortsdsh-open-effortsCatalog AnalyzedChoose reasoning effort for additional models in DeepSeek Harness, with Off and five standard levels.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-24Public signals218 downloadsdsh-patch-reasoningTOBYCAI/dsh-patch-reasoningCatalog AnalyzedDSH 升级后幂等重打的模型调优补丁：DeepSeek 推理拓宽为 7 档、workflow/ralph 默认模型 deepseek-v4-flash。Idempotent DSH model-tuning patch. | Platforms: macOS/Linux (Bash); Windows: Git Bash/WSLCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-plugin-thinking-modedsh-plugin-thinking-modeCatalog AnalyzedDeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpointsCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-26Public signals92 downloadsdsh-plugins#think-level@creait/dsh-think-levelCatalog AnalyzedA thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-20Public signals5 stars · 280 downloadsdsh-qwen38-compaction-fixdsh-qwen38-ninfer-compaction-fixCatalog AnalyzedCompaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.1.0Evidence updated2026-09-21Public signals2 stars · 299 downloadsdsh-qwen38-local-qolYunado/dsh-qwen38-local-qolCatalog AnalyzedPer-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3.8 line (llama.cpp or NInfer).CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals8 starsdsh-reasoning-effortdsh-reasoning-effortCatalog AnalyzedConfigures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.8Evidence updated2026-09-21Public signals2 stars · 1641 downloadsdsh-reasoning-effortNexusAgentX/dsh-reasoning-effortCatalog AnalyzedHost-side dsh plugin that adds seven reasoning-effort levels to third-party llm-pi-ai models in the web composer.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals1 starsdsh-reasoning-effortTriple3h/dsh-reasoning-effortCatalog AnalyzedDSH Web plugin: per-model reasoning-effort configuration and selection — settings page + slider embedded in the model picker. DSH Web Plugin：逐模型推理力度配置与选择（设置页 + 模型选择器内嵌滑块）。CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-reasoning-effort-sliderlyaoliu/dsh-reasoning-effort-sliderCatalog AnalyzedDSH Desktop reasoning effort slider plugin - 7-level effort control with whale-mom skinCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-reasoning-optionsdsh-reasoning-optionsCatalog AnalyzedAdd missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.0Evidence updated2026-09-26Public signals0 stars · 485 downloadsdsh-reasoning-settingsJuneLearn/dsh-reasoning-settingsCatalog Analyzed让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent callCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals6 starsdsh-reasoning-tiersdsh-reasoning-tiersCatalog AnalyzedDeclares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.0Evidence updated2026-09-26Public signals0 stars · 632 downloadsdsh-reasoning-zhdsh-reasoning-zhCatalog AnalyzedDeepSeek Harness Plugin：把「推理等级」(reasoning effort) 档位名翻译成中文，并为接入的自定义第三方模型注入推理等级显示（官方 DSH 默认不注入），所选档位写入出站Request体。CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.4Evidence updated2026-09-26Public signals791 downloadsdsh-resoning-effortAsowerp/dsh-resoning-effortCatalog AnalyzedDSH plugin from Asowerp/dsh-resoning-effortCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-routing-suiteyjh051108/dsh-routing-suiteCatalog AnalyzedOne repository, three parts: a runtime injector for DSH plugin packages (inject, hot-reload, unload, promote a dev staging tool to the front, route self-heal, plus a settings-page plugin manager that lists, unloads and drags folders in to internalize), a task-aware reasoning-mode router agent preset (router-standard / router-spec / router-react), and a graded two-level task protocol whose six tools (commit_star, lock_stage, revise_do, edit_plan, mark_task, redteam_verdict) pin task state to disk. The injector implementation ships in-tree, so the install carries its own behaviour rather than a dependency list.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals7194 starsdsh-sampling-slidersSemidia/dsh-sampling-slidersCatalog AnalyzedModel sampling sliders (temperature / maxTokens) in the composer: override every model request for all providers via the agent/request hook, with hot/persist modes.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.