Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-plugin-recall
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:truelove-dreamer/dsh-plugin-recall
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
DeepSeek Harness 插件:给模型跨会话记忆 —— 全文检索所有历史会话,把最强匹配片段带回当前上下文。
背景
DSH 已经把每个会话持久化,并用 SQLite FTS5 建了全文索引(ctx.sessionQuery.searchSessions),但没有任何面向模型的工具去读它 —— 新会话对旧会话的决策、命令、踩过的坑一无所知。recall 把这个现成索引变成模型的能力:开新会话先 recall 一下,接着上次的进度继续。
使用
模型工具 recall:
recall query: "we decided to use sqlite" # 默认返回最多 5 个会话
recall query: "publish script" limit: 3
recall query: "权限绕过" sessionIds: ["s_xxx"] # 限定会话范围
返回每个命中会话:session id、时间、事件类型、live/persisted 标记、最强匹配片段。查询按字面短语处理(永不解释为 FTS 可执行语法)。
人类命令 /recall <查询>: 同样输出。
安装
dsh plugin --profile web add dsh-plugin-recall
挂载(标准 web profile 已含 dsh-session-query-sqlite,无需额外配置):
- insert:
- id: recall
name: dsh-plugin-recall
设计说明
- 复用官方基建:直接调用
ctx.sessionQuery.searchSessions(SQLite FTS5),不改任何官方包;sessionQuery未挂载时工具给出明确提示,而不是让组合加载失败。 - 纯逻辑可单测:参数校验 / 请求构建 / 命中映射 / 渲染在
lib/recall.js,npm test零依赖。 - 只拷贝叶字段:命中结果从 live 服务对象提取为纯 JSON(sessionId / time / type / snippet),绝不引用内部对象。
诚实边界
- 依赖
ctx.sessionQuery存在;openAt: never配置下全文检索被禁用时,recall会报错提示。 - 命中片段是 FTS5 的高亮摘录(unicode61 分词器,
AI匹配不到 tokenBRAID这类子串),不是精确回溯;需要精确读取请配合 session 工具。 - 检索范围为当前 DSH_HOME 的持久化会话语料,不含其他机器/部署的历史。
本地开发
cd plugins/dsh-plugin-recall
npm test # node --test,零依赖
接线集成测试(真实 Cordis + mock sessionQuery):见仓库根 test-wiring.mjs。
Links
More in this category
vectorize-io/hindsight#coding-agents★ 60140
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 41884
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
MemTensor/MemOS#memos-local-plugin★ 12364
Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.
agentscope-ai/ReMe#dsh★ 3794
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2849
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1472
Reads the session files forty-two other coding agents on this machine already wrote (Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more), including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.