Files
deepseek-harness/docs/cordis-tutorial/07-into-the-harness.zh.md
imccyu ec601ca13d build(vendor): rescope the vendored Cordis packages into @deepseek-ai
Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it
prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`,
`verify-translation-pairing --write` for the touched bilingual pairs,
`gen-doc-graphs`, and one typert snapshot whose ids embed character offsets.
`pnpm run rescope-vendor --check` verifies the result.

Renames nine vendored packages (cordis, cosmokit, schemastery and the six
@cordisjs plugins) and every reference that resolves them: manifest names and
dependency keys, module specifiers including declare-module merges, cordis.yml
plugin names, tsconfig paths, every Markdown fence, and `docs/` prose.
Directory names, upstream versions, and dependency ranges are unchanged, so
vendor/README.md still reads as an upstream snapshot; its manifest table gains
an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed
at each fork's origin.

The tutorial tier follows the rename end to end: its yaml fences named plugins
the Loader can no longer resolve, its `ts ignore-check` fences disagreed with
the compiled fences beside them, and its prose quoted both. The contracts that
told readers to keep upstream names — the root convention and the vendoring
cookbook's tree comment and manifest invariant — now say to rescope instead.

Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle
purity gate now names the vendored libraries a browser bundle inlines, and the
files where a bare `cordis` is an agent-preset id keep that product data.
2026-08-10 22:04:13 +08:00

4.6 KiB
Raw Blame History

7. 进入 harness

English | 中文

本章会向 harness 的 tools 服务注册一个可由模型调用的工具,通过 harness 工具流水线执行它,并观察结果事件。整个示例无需密钥,也不会调用模型。

工具插件

创建 greet-tool.ts,将它放在 tmp/cordis-tutorial 中:

import type { Context } from '@deepseek-ai/cordis'
import { defineTool } from '@deepseek-ai/dsh-tools'
import { CallId } from '@deepseek-ai/dsh-llm'

export const name = 'greet-tool'
export const inject = ['tools']

export function apply(ctx: Context) {
  ctx.tools.register(defineTool({
    name: 'greet',
    description: 'Greet the named person.',
    parameters: {
      name: { type: 'string', required: true, description: 'Who to greet' },
    },
    output: {
      schema: { type: 'string' },
      render: (_args, value) => [{ type: 'text', text: value }],
    },
    async execute(args) {
      return `Hello, ${args.name}!`
    },
  }))

  // Drive one call through the real execution pipeline, standing in for
  // the model. CallId brands the correlation id a provider would issue.
  void (async () => {
    const result = await ctx.tools.execute({
      callId: CallId('demo-1'),
      name: 'greet',
      arguments: { name: 'Cordis' },
      signal: new AbortController().signal,
    })
    console.log('tool replied:', JSON.stringify(result.content))
  })()
}

这里的每个模式都来自前几章:inject: ['tools']第 3 章)会让插件等待工具注册表就绪;ctx.tools.register(...) 会把注册 disposer 附着到插件(第 2 章),因此卸载时会注销工具。defineToolparameters 规约转换为向模型展示的 JSON Schema推导 args 的类型,并在 execute 运行前校验模型提供的参数。工具返回由 output.schema 声明的规范值;output.render 则作为 Native renderer原生渲染器另行生成可持久化的结果内容。

观察插件

创建 tool-logger.ts。这是一个独立插件,通过 harness 的 tools/result 事件观察应用中的每次工具调用:

import type { Context } from '@deepseek-ai/cordis'
import type {} from '@deepseek-ai/dsh-tools'

export const name = 'tool-logger'
export const inject = ['tools']

export function apply(ctx: Context) {
  ctx.on('tools/result', (exec, result) => {
    const text = result.content
      .map(block => (block.type === 'text' ? block.text : ''))
      .join('')
    console.log(`[tool-logger] ${exec.name} -> ${text}`)
  })
}

import type {} from '@deepseek-ai/dsh-tools' 行会引入该包的声明合并,使 'tools/result' 及其 payload 具有类型。这与第 4 章导入 stats.ts 的做法相同,只是扩展到了包级别。

组合并运行

- name: '@deepseek-ai/dsh-system-prompt'
- name: '@deepseek-ai/dsh-tools'
- name: './tool-logger.ts'
- name: './greet-tool.ts'

@deepseek-ai/dsh-tools 会注入 systemPrompt 服务,因为工具需要向系统提示词贡献 schema所以组合中也要列出该服务的提供方。缺少提供方时工具插件会像第 6 章所述那样保持 PENDING。

node --import tsx ../../vendor/cordis/bin.js
[tool-logger] greet -> Hello, Cordis!
tool replied: [{"type":"text","text":"Hello, Cordis!"}]

logger 会先触发:tools/result 在结果物化过程中发出,发生在 execute 向调用方返回的 promise 兑现之前。两个插件都不知道另一个插件存在,它们由注册表服务和事件连接。

从这里走向完整 agent智能体

真实 agent 就是这套组合再加上更多插件LLM大语言模型适配器、agent loop智能体循环、持久化和运行入口。对照 examples/headless-agent/cordis.yml,你现在已经可以读懂其中每个配置项。将 greet-tool.ts 加入该文件的副本即可。

后续可以阅读:

  • 构建工具:深入了解 defineTool,包括呈现和更丰富的 schema。
  • 三层能力设计harness 如何组织可替换能力。
  • 子系统页面上生成的 cordis-surface 区块:可以注入和监听的所有内容,各在其所属页面上。
  • 架构:这些插件所处的系统地图。