Back to home@QLM1234

dsh-dynamic-assembler

Natural-language driven, security-gated dynamic assembly plugin for DeepSeek Harness (dsh)

Stars
0
Language
TypeScript
Created
Aug 17, 2026
Updated
Aug 17, 2026
GitHub repo

Introduction

dsh-plugin-dynamic-assembler

Natural-language driven, security-gated dynamic assembly for DeepSeek Harness (dsh).

Tell your dsh agent what you want to build in plain language — it discovers the plugins it needs at runtime (official-first, third-party optional), generates an assembly plan, asks for your confirmation, then loads them through the Cordis runtime. Any unofficial plugin passes a built-in static security audit before it is ever loaded.

For self-evolving agents, security gates are not a feature — they are a prerequisite.


Why

dsh is built on "everything is a plugin". The natural next step is self-assembly: an agent that can compose its own toolchain from what's installed — which is exactly the "self-evolving agent harness" direction DeepSeek's spatiotemporal composability paper calls out as the next validation target.

This plugin makes that practical and safe:

  • Runtime discovery — available plugins are read from ctx.registry at runtime. No hardcoded plugin lists to maintain.
  • Official-first@deepseek-ai/* plugins are preferred for any capability; third-party plugins are only considered when no official plugin matches.
  • User consent, not silence — plans that involve third-party plugins surface them explicitly and require your allow_unofficial confirmation (policy configurable: ask / allow / deny).
  • Audit before load — every unofficial plugin is statically scanned (dangerous patterns + metadata) and scored 0-100. red (<60) plugins are rejected by default.

Features

🧭 Runtime discoveryctx.registry traversal — see everything loaded, nothing hardcoded
🥇 Official-first policyPrefer @deepseek-ai/*; third-party only as fallback, always surfaced
🔐 Third-party gateunofficialPolicy: ask (default) / allow / deny
🛡️ Built-in security auditassemble_inspect — pattern scan + metadata check → score → green / yellow / red
⚠️ Sensitive-op confirmationNetwork / fs / shell / subagent / MCP / code / credentials require explicit confirm
🗑️ Cascade unloadEverything dynamically loaded is disposed when the plugin unloads (Cordis time-composability)
🧩 4 toolsassemble_inspect · assemble_plan · assemble_execute · assemble_unload

Install

# from the dsh repository (WSL/Linux)
pnpm dsh plugin --profile web add /path/to/dsh-plugin-dynamic-assembler
# restart the web service afterwards
pnpm dsh web

Config (optional)

Add to your profile's cordis.patch.yml (new entries must be wrapped in - insert:):

- insert:
    - id: dynamic-assembler
      name: dsh-plugin-dynamic-assembler
      config:
        autoConfirmSensitive: false   # set true to skip sensitive confirmation (not recommended)
        denyList: []                  # capability name substrings never assembled
        unofficialPolicy: ask         # ask | allow | deny
        pluginSources: []             # third-party plugins to consider (npm name or local dir)

pluginSources is how you tell the assembler about not-yet-loaded third-party plugins:

      config:
        pluginSources:
          - my-dsh-plugin            # npm package name
          - /path/to/local-plugin    # local directory

Already-loaded plugins (official or third-party) are discovered automatically — no config needed.

Tools

ToolWhat it doesKey parameters
assemble_inspectAudit a plugin package (official or not): pattern scan + metadata → score & gradeplugin
assemble_planAnalyze a natural-language requirement, discover matching capabilities (official-first), produce an assembly plan (loads nothing)requirement
assemble_executeLoad and start the planned plugins via Cordis. Requires confirmation; unofficial plugins require allow_unofficial; red audits require forcenames, confirm, confirm_sensitive, allow_unofficial, force?, configs?
assemble_unloadDispose everything this plugin dynamically loaded (safety rollback)

Example conversation

User: "I need a robot that can search the web and turn results into a Markdown document."

  1. Model calls assemble_plan({ requirement: "search the web and write a Markdown document" }) → runtime discovers loaded plugins, matches capabilities official-first, returns plan + recommended order.
  2. User confirms; model calls assemble_execute({ names: ["tool-web","web-search-deepseek"], confirm: true, confirm_sensitive: true, allow_unofficial: false }) → loaded plugins are activated; unloaded official plugins are dynamically imported by convention name @deepseek-ai/dsh-<name>.
  3. Rollback anytime: assemble_unload().

Security model

assemble_inspect performs a static audit with two layers:

  1. Metadata — npm scope (official vs third-party), license, repository, install/postinstall scripts (high risk), peer dependency completeness.
  2. Source — the entry file (plus adjacent source files, size-capped) is scanned for dangerous patterns:
SeverityPatterns
🔴 higheval / new Function, child_process/exec/spawn, install scripts, hardcoded secrets
🟡 mediumfs write/delete, network requests, dynamic import, base64 decode, char obfuscation
🔵 infoprocess.env access, pre-release version, missing license/repo, non-official scope

Scoring: start at 100, subtract per finding → green ≥ 80 / yellow ≥ 60 / red < 60.

  • green — loadable.
  • yellow — loadable with visibility (still requires allow_unofficial for third-party).
  • redrejected by default; only a deliberate force: true (high risk) can override.

⚠️ Boundary — read this. A static audit is a risk signal, not a security guarantee. Plugins are JS modules: once ctx.plugin() loads one, it has full Node process privileges, and malicious code can trivially evade regex scanning. Only install plugins from sources you trust, and stay alert with third-party plugins. Isolated sandbox execution is planned as a v2 direction.

Extending the capability dictionary

The intent-to-capability mapping lives in CAPABILITY_RULES (src/dynamic-assembler.ts). Each rule maps natural-language keywords → candidate plugin-name substrings:

{ keywords: ['搜索', 'search', '联网', 'fetch', '网页', '抓取'],
  label: '联网搜索/抓取',
  match: ['tool-web', 'web-search', 'web-fetch-http', 'web'],
  dependsOn: ['web'],
  sensitive: true }
  • match entries are plugin-name substrings matched against runtime-discovered plugins (official-first).
  • Unmatched, unloaded official plugins are dynamically imported via the convention name @deepseek-ai/dsh-<name>.
  • sensitive: true requires explicit confirmation before loading.
  • Open a PR to add rules — the dictionary is a heuristic, never a hardcoded list.

Development

npm install
npm test        # vitest — audit engine + official-first logic
  • src/inspect.ts — pure audit engine (no cordis dependency, fully unit-testable)
  • src/dynamic-assembler.ts — plugin entry, 4 tools, official-first planning
  • test/ — vitest suites (cordis/dsh-tools stubbed; they only exist inside the dsh monorepo)

License

MIT © 2026 Lishu (黎叔玩AI)