CompatibleModelConfig

SUPPORT · interface · 类型合同

Configuration of one OpenAI-compatible endpoint.

导入

TypeScript

import type { CompatibleModelConfig } from '@jangts/agent-core/support';

JavaScript

/** @typedef {import('@jangts/agent-core/support').CompatibleModelConfig} CompatibleModelConfig */

其他公开入口：@jangts/agent-core、@jangts/agent-core/types、@jangts/agent-core/structs、@jangts/agent-core/support、@jangts/agent-core/support/model。

定义

interface CompatibleModelConfig

字段结构

字段	类型	必需	说明
baseUrl	string	必需	Endpoint base URL, for example the chat-completions root.
apiKey	string	必需	Credential sent as a bearer token; must be non-empty at request time.
model	string	必需	Model name sent with the request.
maxOutputTokens	number | undefined	可省略	Optional provider ceiling; otherwise use the call's limit or the Core default.
requestBody	(Readonly<Record<string, unknown>> & { readonly model?: never; readonly messages?: never; readonly stream?: never; readonly max_tokens?: never; readonly max_completion_tokens?: never; readonly toJSON?: never; }) | undefined	可省略	Provider extensions. Identity, input, streaming and budget stay in the adapter.
temperature	number | undefined	可省略	Sampling temperature forwarded to the provider.
reasoning	ProviderReasoningStrategy | undefined	可省略	Generated reasoning fields are overridden by explicit requestBody fields.

使用示例

• 兼容 Provider 与自定义 Provider：Support 负责常见 Chat Completions HTTP/SSE 生命周期；App 可替换为自己的 ChatProvider。

真实服务端配置接入常见协议

入门 · Node.js

运行此例需要提供可用模型服务的连接配置。

TypeScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = new Support.CompatibleModelProvider({ config: {
  baseUrl: process.env.MODEL_BASE_URL!, apiKey: process.env.MODEL_API_KEY!, model: process.env.MODEL_NAME!,
} });
const runner = new ModelRunner({ provider });
console.log((await runner.invoke('你好')).value);

JavaScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = new Support.CompatibleModelProvider({ config: {
        baseUrl: process.env.MODEL_BASE_URL, apiKey: process.env.MODEL_API_KEY, model: process.env.MODEL_NAME,
    } });
const runner = new ModelRunner({ provider });
console.log((await runner.invoke('你好')).value);

直连工具线程的声明字段与 wire 映射

配置 · Node.js

只演示消息转换，无网络请求或工具执行。原始 tool_calls、tool_call_id 和宿主附加数据不透传。

TypeScript

import { Support } from '@jangts/agent-core';
const messages: Support.ProviderMessage[] = [
  { role: 'user', content: '查询资料' },
  { role: 'assistant', content: '', toolCalls: [
    { id: 'call-1', name: 'lookup', arguments: '{"query":"资料"}' },
  ] },
  { role: 'tool', content: '{"found":true}', toolCallId: 'call-1' },
];
console.log(Support.chatCompletionMessages(messages));

JavaScript

import { Support } from '@jangts/agent-core';
const messages = [
    { role: 'user', content: '查询资料' },
    { role: 'assistant', content: '', toolCalls: [
            { id: 'call-1', name: 'lookup', arguments: '{"query":"资料"}' },
        ] },
    { role: 'tool', content: '{"found":true}', toolCallId: 'call-1' },
];
console.log(Support.chatCompletionMessages(messages));

相关策略源码

• HTTP 失败映射和受控请求字段

相关定义

• ProviderReasoningStrategy