@dsh-scholar/research-plugin
DSH Research OS — a fully automated scientific research plugin for DSH (DeepSeek Harness): survey, idea, experiment contract, durable runner jobs, claim-evidence ledger, manuscript and release bundle.
71 results
DSH Research OS — a fully automated scientific research plugin for DSH (DeepSeek Harness): survey, idea, experiment contract, durable runner jobs, claim-evidence ledger, manuscript and release bundle.
DSH 插件:全模式工具失败自动实录——把原生工具、PTC(Code Mode) run_code、代码内嵌工具调用的失败按错因去重计数,自动写入 skill 的机器维护区段,越用越少错。Auto-record tool failures from every execution mode into a skill's machine-maintained section (dedup + counts).
会话级自动上下文压缩插件:回合中每步前 + 回合结束检测上下文用量,超过会话阈值自动 compact,摘要注入上下文后自然继续(DeepSeek Harness / DSH)
DSH host plugin: cuts tool-call latency by auto-downgrading reasoning_effort for simple tool tasks, with per-tool timing telemetry.
LLM-assisted auto approval with timeout fallback for DeepSeek Harness
NovelCraft autonomous writing assistant for DeepSeek Harness
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
Clean desktop shell for DeepSeek Harness (DSH) as a DSH plugin — wraps your web profile in a native window, tray-managed backend, offline auto-reconnect, zero visual changes. DSH 插件形态的纯净桌面壳:复用现有 web profile,托盘管理后端,零视觉改造。
DSH host plugin: thinking-level (reasoning_effort) control for dsh — auto-adjust per tool round, with optional manual lock and per-tool timing telemetry.
为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩,解决极简模式长任务无法持续工作的问题。
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.
Start a DeepSeek Harness conversation without selecting a workspace: auto-provisions a default workspace and adds a "Chat without a workspace" option to the workspace picker
AI-driven partial wave analysis for DeepSeek Harness: physics-gated config editing, ctpwa fit execution, numeric evaluation, and goal-driven iterative convergence. Physics knowledge (PDG-2026) as pure functions; DSH integration as a thin pwa_* tool plugin.
Sticker/emoji expression plugin for DeepSeek Harness — assistants send stickers to express emotions, with library management, AI tagging, auto-matching, dialects and style mimicry. · DSH 表情包插件:让助手用表情包表达情绪,含图库管理、AI 识图、自动配图、方言口音与学我说话。
Canvas preview panel for DeepSeek Harness — live-preview HTML artifacts, auto-sync, save-as, PNG/JPG/SVG export. DSH 画板预览插件:实时预览、另存为、PNG/JPG/SVG 导出。
Weak-network adaptor for the DeepSeek Harness: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, degraded-mode token economy, and a bilingual (zh/en) settings page. / 弱网适配插件:模型流长退避重试、本地响应缓存、心跳自动重连(默认 10 分钟封顶)、降级省 token、双语设置页。
Draggable floating version capsule (restored from 0.3.7) + one-click update.
DeepSeek Harness plugin that autonomously overrides and adjusts third-party model thinking levels, fixing missing or mismatched built-in presets
Automated unit-test generation for DeepSeek Harness: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass.
DSH 插件:春笋(ChunSun)驱动的 AI 原生项目交付 —— 需求/Run/Step/场景/用例/工作记忆 + 验收闭环(pm = project management)
双模型 Auto 路由插件: flash 低成本直返 / pro 高成本升级 + 逃逸学习闭环 + 持久化互通
会话级自动上下文压缩插件:回合中每步前 + 回合结束检测上下文用量,超过会话阈值自动 compact,摘要注入上下文后自然继续(DeepSeek Harness / DSH)