modelRunnerDefaults

CORE · constant · 运行时值

导入

TypeScript

import { modelRunnerDefaults } from '@jangts/agent-core';

JavaScript

import { modelRunnerDefaults } from '@jangts/agent-core';

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

定义

const modelRunnerDefaults: Readonly<{ maxCalls: 8; callTimeoutMs: 30000; maxInputChars: 32000; maxOutputChars: 16000; maxSchemaChars: 16000; maxOutputTokens: 1024; stage: "model"; children: Readonly<{ maxDepth: 1; maxConcurrentCalls: 1; maxChildren: 32; }>; }>

字段结构

字段	类型	必需	说明
maxCalls	8	必需	见类型定义及调用场景。
callTimeoutMs	30000	必需	见类型定义及调用场景。
maxInputChars	32000	必需	见类型定义及调用场景。
maxOutputChars	16000	必需	见类型定义及调用场景。
maxSchemaChars	16000	必需	见类型定义及调用场景。
maxOutputTokens	1024	必需	见类型定义及调用场景。
stage	"model"	必需	见类型定义及调用场景。
children	Readonly<{ maxDepth: 1; maxConcurrentCalls: 1; maxChildren: 32; }>	必需	见类型定义及调用场景。

使用示例

• ModelRunner：输入可以省写，输出合同保持一致：用真实 Provider 端口执行一次模型交互，返回 value 和本次 invocation。

同一输出的两种输入

入门 · Node.js

TypeScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
  async *stream(messages: readonly { content: string }[]) {
    yield '收到：' + messages.at(-1)!.content;
  },
};
const runner = new ModelRunner({ provider });
const first = await runner.invoke('你好');
const second = await runner.invoke({ input: '你好' });
console.log(first.value, second.value);
console.log(first.invocation.invocationId);

JavaScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
    async *stream(messages) {
        yield '收到：' + messages.at(-1).content;
    },
};
const runner = new ModelRunner({ provider });
const first = await runner.invoke('你好');
const second = await runner.invoke({ input: '你好' });
console.log(first.value, second.value);
console.log(first.invocation.invocationId);

增加预算与请求取消

配置 · Node.js

TypeScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
  async *stream(messages: readonly { content: string }[]) {
    yield '收到：' + messages.at(-1)!.content;
  },
};
const runner = new ModelRunner({ provider, maxCalls: 2, maxInputChars: 4000,
  maxOutputChars: 2000, callTimeoutMs: 15000,
  execution: { signal: AbortSignal.timeout(20000) },
});
const result = await runner.invoke({ input: '你好', stageId: 'reply', maxOutputTokens: 600 });
console.log(result.value, runner.remainingCalls);

JavaScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
    async *stream(messages) {
        yield '收到：' + messages.at(-1).content;
    },
};
const runner = new ModelRunner({ provider, maxCalls: 2, maxInputChars: 4000,
    maxOutputChars: 2000, callTimeoutMs: 15000,
    execution: { signal: AbortSignal.timeout(20000) },
});
const result = await runner.invoke({ input: '你好', stageId: 'reply', maxOutputTokens: 600 });
console.log(result.value, runner.remainingCalls);

增加独立的有序输出接收器

扩展 · Node.js

sink.output 按序等待。model.output 是尚未完整校验的提议，不能在此执行模型提出的工具操作。

TypeScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
  async *stream(messages: readonly { content: string }[]) {
    yield '收到：' + messages.at(-1)!.content;
  },
};
const events: string[] = [];
const runner = new ModelRunner({ provider, sink: {
  async output(event) { events.push(event.type); },
} });
const result = await runner.invoke('你好');
console.log(result.value, events);

JavaScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
    async *stream(messages) {
        yield '收到：' + messages.at(-1).content;
    },
};
const events = [];
const runner = new ModelRunner({ provider, sink: {
        async output(event) { events.push(event.type); },
    } });
const result = await runner.invoke('你好');
console.log(result.value, events);

相关策略源码

• Core 的基础预算缺省值