DeepSeek Harness 플러그인 — 785 페이지

每轮回答结束后，把一条详略得当的中文摘要发到你的邮箱（QQ / 163 / 自建 SMTP），地址在 DSH 设置页里配置。

DeepSeek Harness 插件：agent 每结束一轮回答，就发一封通知邮件。零依赖，只用 Node 内置模块。

DeepSeek Harness 只读邮件插件：一个 email_read 工具读取 Gmail 与 Outlook，不实现发送、回复、删除、移动、标记或归档。 / Read-only mail for DSH: one email_read tool over Gmail and Outlook, with no send, reply, delete, move, mark, or archive capability.

Tencent Agent Mail (agent.qq.com) workbench plugin for DeepSeek Harness: background mail polling, rule+LLM classification & extraction, fullscreen workbench UI, archive/trash, attachment download, and a mail-to-agent command channel. 腾讯 Agent 邮箱的 DSH 插件

DeepSeek Harness (dsh) 任务通知：任务跑完自动发邮件到你手机，审批卡住超过 1 分钟也会提醒你，并且每封新通知会自动删掉上一封（邮箱永不堆积）。零依赖、零构建、不监听端口。

Keeps a long agent turn answerable to the user's actual request: a standing maintainer-document reminder, two pre-execute gates (read a same-basename precedent before editing infrastructure; say what a side-effecting step is for), an objective anchor that quotes the user's latest instruction plus an explicit precedence rule, and a nudge stage that corrects before it blocks. Details: (1) A standing system-prompt section that tells the model to read the workspace maintainer documents (plan.md / conventions.md / stack.md / state.md / maintainer/README.md) before every operation, so small-model context compaction cannot erase long-term project memory. (2) A `tools/pre-execute` precedent gate that denies a write/edit inside a guarded infrastructure area until a working same-basename precedent has been read. (3) A `tools/pre-execute` intent gate that polices the turn's side-effecting calls when the model never said what the step is for. (4) An OBJECTIVE ANCHOR: the user's latest instruction, quoted verbatim in a second prompt section with an explicit precedence rule (user's latest instruction > your own last stated plan > a lead you found yourself), so a long turn cannot silently redefine its own task. (5) A NUDGE stage that corrects before it blocks — the first unexplained action only injects a reminder the model reads at its next step, a drift reminder fires once per long turn, and only a repeated offence is denied. Plus a right-sidebar tab that views and edits those documents, and ten runtime knobs exposed in the harness settings page (设置 → 插件 → 插件配置).

妆容步骤

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction) and llama.cpp model-enrichment for the Models page

DSH Mall — GitHub #dsh-plugin topic browser with one-click install/uninstall and publish-your-plugin. · DSH 商店：GitHub #dsh-plugin 全量目录，浏览/搜索/排序/筛选 + 一键安装卸载 + 上传入口。

DeepSeek Harness (dsh) plugin: real AST-based scan of installed plugins for malicious-intent patterns, with an optional periodic schedule and auto-quarantine on critical findings. Advisory-by-default, not an antivirus signature database.

Keyboard shortcut that injects an encouraging message into the running dsh-TUI conversation: steer when a tool is in flight, interrupt-and-deliver when the model is only streaming text

Mana 作意：注意力门控 + JEV 筛选 + 注入审计

Mana 熏习：合并 + SOAR chunking（P1 骨架）

Mana（末那识）核心契约插件：S1 五类事件 + 领域模型 + mana_trace/inject_log schema + 存储开库器

Mana 种子衰减：艾宾浩斯衰减 + 间隔重复 + 归档（P1 骨架）

Mana JEV 适配层：判定、缓存、熔断、三级降级（本机 Ollama logprob 承载）

Mana 学习链：Hebbian 共激活 → 关联强度（L-03；不含 FSRS）

Mana LLM 通道：注册 mana 路由到宿主 ctx.llm，使 LLM 生成有唯一出口（L-01）

Mana 长时记忆：编码 + ACT-R 激活方程 + 三路混合检索（P1 骨架）

Mana 末那识·审：置信度 / 知识缺口 + 可移植 shoucang 判据阈值层（B5.1）

Mana 前五识：输入采集、分块、实体抽取

Mana Prompt 模板库：v10 §25 的 20 个 Prompt 常量（真源）

Mana 再巩固：去稳定化窗口（四类记忆窗口参数）+ 内容更新可追溯（L-02）

Mana 调度：SOAR 目标栈 + 三阶段循环（P1）