DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-context-imports

Context Imports

Claude Code 风格的 DSH @path 导入:展开 AGENTS.md/CLAUDE.md 中的 @imports,并在会话开始时将引用的文件注入模型上下文

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-context-imports@0.3.1
README兼容性版本

兼容性与来源证明

Context Imports 以 dsh-context-imports 发布,当前版本为 0.3.1。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
npm
Registry 更新时间
2026/11/4

版本

0.3.1stable
2026/10/24
0.3.0stable
2026/10/24
0.2.3stable
2026/10/9
查看其余 6 个版本收起版本
0.2.2stable
2026/9/30
0.2.1stable
2026/9/26
0.1.4stable
2026/9/25
0.1.3stable
2026/9/23
0.1.2stable
2026/9/21
0.1.1stable
2026/9/17

相关插件

正在加载相关插件…

最新版
0.3.1
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
128.3 kB
文件数
10
Surface
web
许可证
MIT
发布源
npm
GitHub
★ 6
周下载
393
安全扫描
✓ v0.3.1 扫描通过
最近提交
2026/10/24
查看源码 ↗项目主页 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 memory-context 分类下经过校验的插件。

Experimental Session Search@deepseek-ai/dsh-experimental-session-search为 Agents 提供搜索和读取当前工作区早期会话的工具。Hindsight Coding Agents@vectorize-io/hindsight-coding-agents面向编程代理的仅反思式 Hindsight 长期记忆(可插拔支持多种运行框架:opencode、……),自动在后台导入(无需设置 CLI)。Mnemondsh-mnemon面向 DeepSeek Harness 的可组合、基于视图的上下文。开箱即用的可插拔来源与策略、分层记忆和自我演进技能。Ab Memorydsh-ab-memory--- description: "dsh-ab-memory 包:一种跨会话、基于文件的智能体记忆,提供五个工具(remember / recall / forget / load_skill / distill)以及始终启用的轻量注入。" kind: "package-reference" ---

README

dsh-context-imports

Inject the files referenced from AGENTS.md into model context at session start.

DeepSeek Harness injects AGENTS.md itself, but the @path references inside it stay as plain text and the model never sees them. This plugin expands those references the way Claude Code does: it reads each referenced file and adds the content to the session context.

English | 中文


Why

Without this pluginWith it
AGENTS.md itselfInjected by the stock agent-instructions pluginStill injected by it, no duplication
@docs/architecture.md referencesPlain text, ignoredFull file content in context
Nested importsNobody handles themExpanded recursively, depth limited
After compactionReferenced files are gone with the historyRe-injected automatically
Resumed sessionsMay stack a second copySkipped when one is already present

How it works

agent/session-start (startup / resume / clear / compact) records the scene
agent/pre-step (every step) decides whether to inject
  ├─ scan the instruction files (default AGENTS.md, CLAUDE.md) for @path imports
  │    ├─ fenced code blocks are skipped; the path must have a file extension
  │    ├─ relative paths resolve against the importing file's directory
  │    └─ duplicates collapse by resolved path, so import cycles are harmless
  ├─ merge the explicit files list (injected in full; instruction files are
  │    scanned but never re-injected)
  ├─ budgets: 64 KB per file (truncated with a note), 128 KB total (skipped
  │    with a note); a missing file becomes a one-line note instead of an error
  ├─ at most one injection stays in the active history: the full event log is
  │    fingerprint-scanned, and compaction that removes the block re-enables it
  └─ the bundle is appended to the end of the step messages, after AGENTS.md
       and every other context injection

The injected message is a <system-reminder> containing <file path="..."> blocks and nothing else. Set template if you want your own framing around it.

Features

  • Expands @path imports recursively. Default depth is 3; import cycles and duplicates are collapsed.
  • Follows the imports of every instruction file the harness loaded — including a project's AGENTS.md it picks up mid-session once the agent touches files under it.
  • Triggers on new sessions, resume, clear, and after compaction. Each scene can be turned off.
  • Never sends the same file twice: a file already in the model's context is left alone, and a newly loaded instruction file adds exactly its own imported files.
  • Six-language settings card (zh, en, ja, fr, ru, ko) under Settings, Plugins, Plugin configuration. Every option is editable there and applies without a reload.
  • Byte budgets per file and in total. Missing files are reported, never fatal.
  • Uses the official API surface only: cordis events, createUserMessage from dsh-llm, a schemastery config, and the optional dsh-settings namespace. No feature-plugin dependencies.

Configuration

FieldDefaultDescription
files[]Extra files to inject, relative to the session working directory or absolute
scanImportstrueScan AGENTS.md and the other instruction files for @imports
instructionFiles["AGENTS.md", "CLAUDE.md"]Files to scan. They are never re-injected themselves
expandLoadedInstructionstrueAlso follow the imports of the instruction files the harness itself loaded, including a project AGENTS.md it brought in mid-session
maxDepth3How many levels of nested imports to follow
maxFileBytes65536Per-file cap in bytes; larger files are truncated
maxTotalBytes131072Total budget; files beyond it are skipped with a note
injectOnall fourWhich session-start scenes trigger injection
template""Custom wrapper text. {{content}} marks where the files go; empty uses the plain wrapper

Install

dsh plugin --profile web add dsh-context-imports

It works with no configuration: AGENTS.md and CLAUDE.md are scanned and their imports injected. To build from source instead:

git clone https://github.com/ciskonc/dsh-context-imports.git
cd dsh-context-imports
npm install
DSH_CHECKOUT=<path-to-your-dsh-installation> npm run build
npm run build:client

Compatibility

Plugin versionDeepSeek HarnessNotes
0.3.1+≥ 0.2.0-rc.1(0.3.1 tested on 0.2.1-rc.2 and 0.2.1-rc.3)Current line. Adds expandLoadedInstructions: the imports of every instruction file the harness loaded are expanded, including a project AGENTS.md it brings in mid-session. Injection is incremental — a file already in the context is never sent twice. Needs the host's published instruction scopes (agent-instructions message source + agent.inbox.nextStep), so it targets DSH ≥ 0.2.0
0.3.0≥ 0.2.0-rc.1(tested on 0.2.1-rc.2)Same feature, but the inbox lookup read session.inbox instead of agent.inbox and therefore never fired — the step-batch path carried the feature on its own. Fixed in 0.3.1
0.2.3≥ 0.1.7-rc.1(tested on 0.2.0-rc.1, 0.2.0-rc.2 and 0.2.1-rc.2)Config access hardened: on DSH ≥ 0.2.0-rc.2 the volatile config projection no longer fills schema defaults, so every field is normalized at entry (0.2.2 could crash session creation or silently skip injection there). Note: on DSH ≥ 0.2.0-rc.2 install via dsh plugin add only — the loader verifies lockfile consistency, hand-copied node_modules are silently dropped
0.2.0 – 0.2.2≥ 0.1.7-rc.1(0.2.1 tested on 0.1.7-rc.2 and 0.2.0-rc.1; 0.2.2 tested on 0.2.0-rc.1)0.2.2 fixed re-injection after compaction and settings-page mounting, but on DSH ≥ 0.2.0-rc.2 it can crash session creation (injectOn.includes is not a function) or silently skip injection (cfg.files is not iterable) — upgrade to 0.2.3
0.1.x0.1.5-rc.1 – 0.1.5-rc.3(tested on 0.1.5-rc.2/rc.3)Legacy line. Does not work on 0.1.7 — it waits on the removed settingsScope service and the removed agent/session-start event

Each release note names the DSH version it was tested against.

Development

FileRole
src/index.tsHost side: session-start ledger, import expansion, budgets, pre-step injection, settings namespace
src/client/index.tsBrowser side: six-language dictionaries and the settings card slot
src/client/form.tsStaged form model behind the card
src/client/ContextImportsCard.tsxThe card component

License

MIT