paulalesius/dsh-hindsight-advanced

Name: paulalesius/dsh-hindsight-advanced
Author: paulalesius

Plugin插件 Native原生 ⭐ 3 Memory & Knowledge记忆与知识库 Sessions & Context会话与上下文 Prompts & Skills提示词与技能

Long-term memory for DeepSeek Harness agents: automatic recall each turn, a retain/recall/reflect tool, standing rules, and visibility you scope to the whole bank, a preset, or a session.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

A DeepSeek Harness plugin that integrates the Hindsight memory system. It lets your agent store memories to your self-hosted Hindsight server and fetch relevant memories for conversations. Use it when you need persistent long-term memory for your agents. It requires a running, configured Hindsight server to work.

这是DeepSeek Harness的Hindsight记忆系统集成插件。AI代理可将记忆存储在你自己的Hindsight服务器，并在对话中拉取相关记忆。需要给AI代理添加持久化长期记忆时使用。注意需要自行配置运行中的Hindsight服务器才能正常工作。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-hindsight-advanced（paulalesius/dsh-hindsight-advanced）
仓库：https://github.com/paulalesius/dsh-hindsight-advanced
本站详情页：https://www.yhbd.top/plugins/paulalesius-dsh-hindsight-advanced/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证未声明 · ⭐ 3 · 最近提交 2026-09-20 · 主语言 JavaScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意

No license declared - all rights reserved by default; ask the author before commercial use or redistribution未声明开源许可证 —— 默认「保留所有权利」，商用或再分发前先问作者
Only 3 stars - very few users, little community feedback星标只有 3，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:paulalesius/dsh-hindsight-advanced

把 paulalesius/dsh-hindsight-advanced 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

11.0 KB · 缓存于 2026-09-20 19:41:59 · 11.0 KB

dsh-plugin-hindsight-advanced

A plugin for DeepSeek Harness (dsh) that integrates the Hindsight memory system: your agent stores memories in your own Hindsight server and brings the relevant ones back into the conversation.

Installation

With the dsh command:

dsh plugin --profile web add /path/to/hindsight-advanced

When running dsh from source:

pnpm dsh plugin --profile web add /path/to/hindsight-advanced

Then restart the server.

Configuration

The configuration is one hindsight row in your own DSH config — never an edit to the plugin's files. You place it in one of two spots (pick one, never both):

Every session. In your profile's patch layer (~/.dsh/profiles/web/cordis.patch.yml, append to your existing file):

- id: hindsight
  disabled: false
  config:
    bank: my-bank
    baseUrl: http://127.0.0.1:9177
    apiKeyRef: HINDSIGHT_API_KEY

One preset only. In that preset's own file (~/.dsh/.agent-presets/<preset>/agent.cordis.yml, append):

- id: hindsight
  name: dsh-plugin-hindsight-advanced
  config:
    bank: my-bank
    baseUrl: http://127.0.0.1:9177
    apiKeyRef: HINDSIGHT_API_KEY

Presets that point at the same bank don't need separate banks — the preset scope already keeps each preset's memories apart.

Two things to know about the row:

the config block replaces the plugin's defaults wholesale — list every key you want; only bank is strictly required, the rest fall back to the defaults in the table below (but baseUrl and apiKeyRef are worth repeating, since their defaults point at port 8888 and carry no key);
to switch the plugin off again, set disabled: true on the row (or remove the preset row) and restart.

The configuration keys

key	default	what it does
`bank`	—	Required. The name of the Hindsight bank to use (the server creates it on first use).
`baseUrl`	`http://127.0.0.1:8888`	Your Hindsight server's address.
`apiKeyRef`	—	The way to give the plugin its key — a name for the secret, not the secret itself. The value is looked up on every call (environment → `~/.dsh/.credentials.yaml` → `.env` files), so rotating the key needs no restart and the key never sits in a config file. See below.
`apiKey`	—	A plain key in the config, instead of a reference. Prefer `apiKeyRef`.
`autoContext`	`true`	Set `false` to turn off the automatic recall (each turn's first step, any human intervention claimed mid-turn, and the mid-step agent-output recall; the `hindsight` tool stays).
`prefetch`	`true`	`true` (default): the recall starts as the previous turn ends, so from the second turn on it targets the previous message. `false`: every turn queries the message you just sent and waits on the server for it — the memory is always relevant to what you just said, at the cost of the server's latency on every first model call.
`recallContextTurns`	`5`	How many of your recent turns ride along in the recall's query, so the bank can match memories against what the conversation was about, not just the last message. The query is the anchor message under a `Prior context:` block of the recent prior turns (one line per user/assistant message), capped at 1000 characters with the oldest lines dropped first. `1` (what the reference integrations ship) is the plain single-message query.
`recallPreserve`	`true`	`true` (the default): the model context is append-only — every committed recall snapshot stays in the conversation, so later turns see the memories that were recalled earlier. `false`: the model context carries only the latest full snapshot — each new one retires the previous full card in place (a one-line tombstone marker stays where that turn's recall fired, its full tokens metered out of the pricing) and lands as a fresh card at its own turn, while the durable session log keeps every full snapshot for replay and audit. The naming matches llama-server's `--no-reasoning-preserve`: with it off, a turn's snapshot, like its reasoning, lives for that turn only.
`recallAfterText`	`false`	`true`: a step past the first whose claim carries no human message recalls the bank anchored on the previous step's committed text - the words the agent wrote. Bounded by `autoContextTimeoutMs`, at most one recall per step; a human message in the claim takes the intervention path instead.
`recallAfterReasoning`	`false`	Like `recallAfterText`, but anchored on the previous step's committed reasoning. With both keys on, the two anchors are combined into ONE recall (the reasoning first, then the text) - never two lookups.
`actionLessons`	`false`	`true`: at a step past the first whose claim carries no human message, the plugin matches the previous step's committed tool calls against the bank's failure lessons (its `experience` memories) and commits a collapsed notice row (labeled `lesson:<tool> - 12ms`) listing the matches before the next model call. A previous step without tool calls anchors nothing (no bank call); each lesson shows at most once per turn; subagent sessions stay silent.
`actionLessonCandidates`	`10`	How many lesson lines the `actionLessons` notice row renders - the recall is unbounded by this key, the row keeps the first matches.
`retainScope`	`preset`	Where a stored memory lands when the agent doesn't say: `global` (everything in the bank), `preset` (this agent preset), or `session` (this session only).
`maxRecallTokens`	`4096`	How much memory to bring back per recall.
`autoContextTimeoutMs`	`2500`	How long a turn may wait on the memory server before moving on without it. Because the lookup runs ahead (below), most turns never pay this; a slow or stopped server never blocks the agent.
`retainAsync`	`false`	`false` (the default): storing waits until the bank has processed the memory, so the next turn already sees it. `true`: store acknowledges fast and the bank processes it in the background.
`bankConfig`	—	Optional instructions for the server's own memory extraction — for example `retain_mission: "Focus on decisions and durable project facts."` tells the Hindsight server what to pull out of what the agent stores.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 paulalesius/dsh-hindsight-advanced 的 README.md。在 GitHub 查看原文 →