Agent 협업 · DeepSeek Harness 플러그인 — 261 페이지

纯文本死循环断路器：检测单条 assistant 消息内部的重复退化并注入破环提醒，自带设置页。

多智能体监工：一个独立模型实时审阅推理文本与工具调用，检测死循环 / 空转 / 偷懒，并按 WARN / BLOCK / STOP 三档落地。

LinShang LS125 UV irradiance meter / UVALED-X3 probe: fully reverse-engineered 9600 8N1 protocol (28-byte frames, CRC-16/MODBUS, poll + clear commands) provided as a DSH skill, together with the capture/decode toolchain and a verified STM32F103 host firmware.

DSH Web 鲁迅先生桌宠插件：右下角 GIF 桌宠，按 Agent 工作状态换动作，任务完成与点击时播放鲁迅音频。

DSH host-side plugin: real macOS Calendar integration (create/list/query/delete events via AppleScript) for DeepSeek Harness agents

DeepSeek Harness plugin: native macOS Notification Center banners (osascript) when an agent turn ends or a permission request arrives, with a per-operation sound picker on the web settings page

DSH runtime adapter for maestro-flow: guard, workflow context, KG sync, delegate notifications, team heartbeat, and coordinator bridge.

Microsoft Agent Framework (MAF) integration for DeepSeek Harness: validate, run and scaffold declarative agents and workflows defined in YAML, through native dsh tools.

DSH plugin for agent email tools: send, mass send (CSV-personalised), send-later (scheduled queue), read/fetch inbox, list domains. Multi-provider: Lettermint, AgentMail, Resend, OVH (SMTP/IMAP), Manual SMTP+IMAP/POP, Local self-host (expert). Settings UI + sidebar tab + agent tools.

Standards-based IMAP/SMTP mail assistant for DeepSeek Harness with explicit read/send controls and approval-aware delivery

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。

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

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).

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