dsh-reasoning-efforts给第三方 provider 的模型按关键词自动挂上思考强度档位(off/low/medium/high/max),新增模型后无需手动配置
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YumenoSayuri/dsh-reasoning-efforts최고의 DSH 플러그인을 만나보세요
27094개 결과
DeepSeek Harness 커뮤니티 플러그인을 검색하세요. 기능, 설치 방법, 호환성을 비교해 AI 워크플로에 맞는 확장 기능을 찾을 수 있습니다.
dsh-reasoning-efforts给第三方 provider 的模型按关键词自动挂上思考强度档位(off/low/medium/high/max),新增模型后无需手动配置
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YumenoSayuri/dsh-reasoning-effortsdsh-reasoning-foldCodex-style folding for the DeepSeek Harness web transcript: a running turn keeps only its last few actions visible, folded behind one row that opens the whole turn.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Iwwww/dsh-reasoning-folddsh-reasoning-languageMake the DSH agent's thinking process (reasoning) use a language you choose — Simplified Chinese by default — and expand thinking rows by default. / 让 DSH 的思考过程用指定语言(默认简体中文)输出,并把思考行默认展开。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jide315/dsh-reasoning-languagedsh-reasoning-loop-guardDetect and abort repeating reasoning (thinking-loop stalls) in DSH, plus a fire journal and maintenance tool.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:himi-li/dsh-reasoning-loop-guarddsh-reasoning-optionsDeepSeek Harness 推理强度与网关增强插件:自动为 llm-pi-ai 下所有模型补齐推理强度档位(off→max 全七档),并自动为 OpenCode Go 网关注入必需的 x-opencode-session 路由 Header,写入 settings 由 dsh 原生解析生效。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Scorp1o117/dsh-reasoning-optionsdsh-reasoning-plus推理等级++:为 API 地址非官方的自定义提供方补齐与官方同形的推理等级,且每一档在上游真实生效(经实测探测,不可区分的档位不出现)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:polan-prologue/dsh-reasoning-plusdsh-reasoning-rulerA minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zisen123/dsh-reasoning-rulerdsh-reasoning-setupReasoning-effort setup page for DeepSeek Harness: detects models that expose no thinking levels and edits their llm-pi-ai reasoningEfforts declaration from a settings page
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Ayelsh/reasoning-setupdsh-reasoning-sliderDSH Web plugin: replace the composer reasoning-effort (推理等级) picker with an inline slider card.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aci825223/dsh-reasoning-sliderdsh-reasoning-slider四档推理强度滑块与模型选择器 · DeepSeek Harness UI 插件
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Xylocarpro/dsh-reasoning-sliderdsh-reasoning-zhDeepSeek Harness 插件: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),所选档位写入出站请求体。
dsh-reauditReaudit MCP for DeepSeek Harness: mounts the hosted Reaudit MCP server (https://mcp.reaudit.io/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:RoseSamaras/reaudit-ai-plugin#a664d0d07538f2d8faa83ddaef26d4853eb94b25&path:packages/dsh-reauditdsh-recallDeepSeek Harness 跨会话记忆(按需):列出并加载之前会话干了什么,不自动污染上下文。Cross-session memory for DSH, loaded on demand.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:imtwa/dsh-recalldsh-recall把 DSH 的每个 turn 归档为一条 Run:后台生成摘要,并让 Agent 检索自己的执行历史。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:liu-zhengdong/dsh-recalldsh-recall-liteDSH 消息撤回(轻量第一方实现):工作区文件与对话历史一起回到那条消息之前,消息文本与附件放回输入框。相对上游 dsh-recall-plugin 的核心改动——启动期不再对所有历史工作目录做 eager 预热,改为用到哪个工作区才初始化哪个。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AEmbers/dsh-first-party#d31a1cbb99af47662ae8dec24d474e7080fae574&path:packages/recall-litedsh-recall-sessions轻量级解压并读取历史会话,让新会话读取之前会话的内容,单次操作毫秒级。A lightweight plugin that decompresses and reads past sessions, in milliseconds per read.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:imtwa/dsh-recall-sessionsdsh-recapReturn to a DeepSeek Harness session with a trustworthy, non-intrusive recap.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lolipop-1x1/dsh-recapdsh-receiptTurn one DSH session into a shareable receipt: duration, turns, tool calls, files touched, tokens — read-only, redacted by default, zero dependencies.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:louisyeaaah/dsh-receiptdsh-receipt角落一张卡片,大字只写这场会话白烧了多少钱。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sevyn-Star/dsh-receiptdsh-receiptsMine local DSH session logs (JSONL) into personal 'usage & impact' receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log. Zero-network mining, privacy-first (reads only your own dshHome).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:988hj7tczd-oss/dsh-receiptsdsh-recentDSH web GUI plugin: a Codex-style 最近 (Recent) section in the left sidebar that flattens the newest sessions of every workspace into one jump list, directly below the workspace tree.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ttmouse/dsh-recentdsh-recent-promptsA DeepSeek Harness plugin: browse, search, copy, and hide the prompts you sent to the AI across all your sessions.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hujiyo/dsh-recent-promptsdsh-recent-sessionsRecent sessions across every workspace in one panel — plus a place to jot a thought now and have it come back when you reopen that conversation.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:huangxp12/dsh-recent-sessionsdsh-recent-tasksAn always-last, collapsible Recent tasks workspace group in the DSH sidebar: chats with no workspace land there instead of piling up in 未分组 / DSH 侧边栏常驻末位、可折叠的「最近任务」工作区分组:没有工作区的对话自动归到这里。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winditer/dsh-recent-tasks기능 키워드나 카테고리로 범위를 좁히고 최근 업데이트 또는 GitHub Star로 정렬하세요.
소개, AI 분석, 원본 README를 읽고 플러그인의 기능을 확인하세요.
호환성과 의존성 범위, 설치 안내를 확인한 뒤 제공된 설치 명령을 복사하세요.
DeepSeek Harness 커뮤니티 플러그인 디렉터리입니다. 소개, 소스 링크, 설치 안내를 모아 확장 기능 검색과 비교를 돕습니다.
아니요. 상세 페이지는 기록된 호환성과 의존성 범위를 표시합니다. 알 수 없음은 호환을 의미하지 않으므로 설치 전 프로젝트 문서를 확인하세요.
상세 페이지의 설치 영역을 확인하세요. 명령이 있으면 Harness 환경에 복사해 실행하고, 없으면 프로젝트 README를 따르세요.