Files
deepseek-harness/docs/user/develop/practice/llm-adapter.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

191 lines
6.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# LLM 适配器
[English](llm-adapter.md) | 中文
本文介绍如何为 Harness 接入新的模型提供方。
## 概述
LLM 适配器是一个继承 `LlmAdapter` 并实现 `stream()` 方法的类,它会将 Harness 的提供方无关请求转换为具体提供方的 API 调用,并将响应转换回 Harness 分片。
## 最小实现
```ts
import type { Context } from '@deepseek-ai/cordis'
import Schema from '@deepseek-ai/schemastery'
import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm'
class MyAdapter extends LlmAdapter {
private apiKey: string
constructor(apiKey: string) {
super()
this.apiKey = apiKey
}
async *stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
// 1. Convert options.messages to the provider format.
// 2. Call the streaming API.
// 3. Convert the response into StreamChunk values.
}
}
export interface Config {
apiKey: string
models: string[]
}
export const Config: Schema<Config> = Schema.object({
apiKey: Schema.string().required(),
models: Schema.array(Schema.string()).required(),
})
export const name = 'my-llm-adapter'
export const inject = ['llm']
export function apply(ctx: Context, config: Config) {
const adapter = new MyAdapter(config.apiKey)
ctx.llm.registerAdapter(config.models, adapter)
}
```
## StreamChunk 协议
`stream()` 必须按以下协议生成分片:
```ts
import { CallId, type StreamChunk } from '@deepseek-ai/dsh-llm'
async function* exampleChunks(): AsyncIterable<StreamChunk> {
// 1. Start each content block with block-start.
yield { type: 'block-start', index: 0, blockType: 'text' }
// 2. Stream text through text-delta.
yield { type: 'text-delta', index: 0, text: 'Hello' }
yield { type: 'text-delta', index: 0, text: ' world' }
// 3. End each content block with block-end and the complete block.
yield {
type: 'block-end',
index: 0,
block: { type: 'text', text: 'Hello world' },
}
// 4. Tool-call block.
yield { type: 'block-start', index: 1, blockType: 'tool-call' }
yield {
type: 'tool-call-delta',
index: 1,
id: CallId('call-123'),
name: 'bash',
argumentsDelta: '{"command":"ls"}',
}
yield {
type: 'block-end',
index: 1,
block: {
type: 'tool-call',
id: CallId('call-123'),
name: 'bash',
arguments: '{"command":"ls"}',
},
}
// 5. Token usage.
yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } }
// 6. Finish reason.
yield { type: 'finish', reason: { kind: 'stop' } }
// Alternatively, { kind: 'tool-calls' } requests tool execution.
}
```
### 关键规则
- 每个 `block-start` 都必须有与之对应的 `block-end`
- `index` 从 0 开始递增,用于标识内容块的顺序。
- `tool-call-delta``argumentsDelta` 是原始 JSON 文本的增量,可以在一个分片中完整生成,也可以分多个分片生成。
- `finish` 必须是最后一个分片。
- `usage` 必须在 `finish` 之前生成。
## GenerateOptions
`stream()` 接收仓库导出的 `GenerateOptions`。它包含模型、适配器拥有的推理强度 ID、对话历史、系统提示词、工具 schema、生成参数、停止序列和中止信号完整字段以 `@deepseek-ai/dsh-llm` 导出的 TypeScript 类型为准。适配器必须将支持的字段映射到具体 API如果无法支持某个字段应抛出带稳定 code 的 `LlmError`,不得静默丢弃。
请覆写 `resolveModel(provider, model, signal?)`,在一次查询中返回确切的提供方/模型身份以及可选的 `context``reasoning` 元数据。推理元数据包含有序的不透明 ID、展示名称以及可选的配置默认值请保留适配器给出的权威可选列表包括其上游能力 API 返回的 `off`,不要将这些值提升为核心枚举。异步查询必须响应该可选信号,使取消和资源释放过程完全停稳。服务会校验聚合结果,并在调用 `stream()` 前拒绝显式指定但不受支持的推理强度;省略 `reasoning` 表示该模型没有可选的推理强度能力。
## 注册适配器
```ts ignore-check
ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter)
```
第一个参数是该适配器支持的模型名列表。当用户在 `cordis.yml` 中配置 `model: model-name-1` 时,框架会将请求路由到该适配器。
## 在 cordis.yml 中使用
```yaml
- id: my-llm
name: './src/my-llm-adapter.ts'
config:
apiKey: !!js process.env.MY_API_KEY
models:
- my-model-v1
- my-model-v2
- id: agent-loop
name: '@deepseek-ai/dsh-agent-loop'
config:
agents:
- id: main
provider: my-llm
model: my-model-v1 # References the model registered above.
workspaceContext: false
```
## 实战参考
仓库中包含以下两个完整实现:
- `packages/llm/llm-deepseek/` — DeepSeek API 适配器OpenAI 兼容格式)
- `packages/llm/llm-pi-ai/` — Pi AI 适配器(不同的 API 格式)
对比这两个已交付的适配器,可以看到同一套 harness 约定如何在不同提供方 SDK 之上实现。
## 错误处理
适配器应通过带稳定 code 的 `LlmError` 抛出传输和协议故障agent loop智能体循环会保留该错误及其 code用于诊断和策略处理。不要依赖普通 `Error` 被自动转换。每个提供方 HTTP 请求还必须合并 `attributionHeaders()`,并传递 `options.signal`。
```ts
import {
attributionHeaders,
LlmAdapter,
LlmError,
type GenerateOptions,
type StreamChunk,
} from '@deepseek-ai/dsh-llm'
class HttpAdapter extends LlmAdapter {
constructor(private readonly endpoint: string) {
super()
}
async *stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const response = await fetch(this.endpoint, {
method: 'POST',
headers: {
'content-type': 'application/json',
...attributionHeaders(),
},
body: JSON.stringify({ model: options.model, messages: options.messages }),
...options.signal ? { signal: options.signal } : {},
})
if (!response.ok) {
throw new LlmError(`Provider API error: ${response.status}`, 'PROVIDER_HTTP_ERROR')
}
// A real adapter parses the response and emits the complete chunk sequence.
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
```