精选
为什么选中它
待人工精选——以下事实来自源码仓库。
它能做什么
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall + LLM capability matching + auto-persisted lessons
适合谁
想用 DSH 获得这项能力的用户;装前建议先看源码和文档。
风险提示
- 未发现明显风险信号;安装前仍建议查看源码。
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall + LLM capability matching + auto-persisted lessons
待人工精选——以下事实来自源码仓库。
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall + LLM capability matching + auto-persisted lessons
想用 DSH 获得这项能力的用户;装前建议先看源码和文档。
dsh plugin --profile web add github:ztl34245881-commits/dsh-task-planner 作者没有声明支持的平台。
dsh). Give a task → the agent recalls past similar solutions (condition reflex), evaluates whether they fit, and produces a dynamic plan matched against its capabilities — never hard-coded combos. Every plan auto-drafts a lesson into the experience library; when the task closes, the agent updates the outcome. The more you work, the smarter the reflex. ## Features - 🧠 Experience library (task_memory save/recall/list): persistent lessons as plain Markdown with signature keywords. Recall uses a 2–3-char sliding-window tokenizer, so "weekly report" still hits a "daily report" lesson. - ⚡ Condition-reflex planning (plan_task): recall → LLM evaluates fit (reuse & improve, or explain why not and plan fresh) → decomposed steps with capability matching → risks → next actions. - 🤖 LLM-driven, not rule-driven: the model decides what to use per task; the plugin only supplies context (past experiences + optional capability catalog). - ✍️ De-AI deliverable standard: any textual output step (docs/sheets/slides/copy/scripts) must include a humanize-then-review pass before delivery. - 🗂️ Auto-persist: plan_task drafts the lesson automatically (status: draft); the agent marks it verified with the outcome at loop close. - 🔒 Zero keys, zero absolute paths: everything is configurable; the experience library lives in ~/.dsh/planner-lessons by default. ## Install sh dsh plugin --profile web add github:<your-user>/dsh-task-planner or copy the repo and add it as a local bundle: sh dsh plugin --profile web add /path/to/dsh-task-planner ## Config (optional, in your profile's cordis.patch.yml) yaml - id: dsh-task-planner name: dsh-task-planner config: lessonsDir: /path/to/your/lessons # default: ~/.dsh/planner-lessons capabilityFile: /path/to/capability-map.md # optional catalog fed to the LLM Point capabilityFile at a markdown catalog of your skills/plugins (e.g. an awesome list) and plan_task will match each step against it. ## Usage - plan_task { task, goal?, constraints? } — plan before starting complex work. - task_memory save { task, plan, outcome } — persist a lesson (auto-called by plan_task for the draft). - task_memory recall { task } — condition-reflex lookup. - task_memory list — show all lessons. ### Lesson lifecycle 1. plan_task writes a draft lesson (status: draft) automatically. 2. When the task closes, the agent updates it with the outcome (status: verified). 3. A lesson reused successfully 3× → promote to a formal skill. A lesson rejected 2× → mark obsolete. ## Notes - Requires the llm, shell, tools services (all present in the standard harness). - The model call uses the harness default model (agentDefaultModel); reasoning models need a generous maxTokens (8k is used internally). - Lessons are plain Markdown — human-editable, greppable, portable. ## License MIT不看 Star,人工一条条挑的。
把 DSH 的 settings.yaml 做成可视化看板:所有已注册的 settings namespace——包括官方界面从未覆盖的第三方插件配置——都渲染成可编辑表单。项目还早,但方向很对:告别手改 YAML。
给 DSH 的 DIY 轨迹可视化:把 agent 的计划与执行画成图,不用翻原始日志也能看清它在干嘛。项目还早,但补上了「一眼看懂 agent 在做什么」这个真实缺口。
从 Claude Code / Codex 把活派给 DSH:在宿主内拉起带分级预设的 DSH agent 会话,看原生子代理进度,还能借它的多模态桥给纯文本的 DSH 补上视觉和生图。编排型插件,把 DSH 变成其他编码 agent 的后端。