modelBudgetStrategies

SUPPORT · constant · 运行时值

导入

TypeScript

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

JavaScript

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

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

定义

const modelBudgetStrategies: Readonly<{ small: Readonly<{ maxCalls: 2; maxInputChars: 8000; maxOutputChars: 4000; maxOutputTokens: 512; callTimeoutMs: 15000; }>; medium: Readonly<{ maxCalls: 8; maxInputChars: 32000; maxOutputChars: 16000; maxOutputTokens: 1024; callTimeoutMs: 30000; }>; large: Readonly<{ maxCalls: 16; maxInputChars: 64000; maxOutputChars: 32000; maxOutputTokens: 4096; callTimeoutMs: 60000; }>; }>

字段结构

字段	类型	必需	说明
small	Readonly<{ maxCalls: 2; maxInputChars: 8000; maxOutputChars: 4000; maxOutputTokens: 512; callTimeoutMs: 15000; }>	必需	见类型定义及调用场景。
medium	Readonly<{ maxCalls: 8; maxInputChars: 32000; maxOutputChars: 16000; maxOutputTokens: 1024; callTimeoutMs: 30000; }>	必需	见类型定义及调用场景。
large	Readonly<{ maxCalls: 16; maxInputChars: 64000; maxOutputChars: 32000; maxOutputTokens: 4096; callTimeoutMs: 60000; }>	必需	见类型定义及调用场景。

使用示例

• 模型策略：显式选择与推荐预算：从已登记的模型和推理配置中选择，以本地预算档位补全 Core 设置，并保留逐字段精确覆盖。

短任务使用小预算，增加需求仍沿用同一 Core 构造

入门 · Node.js

TypeScript

import { AgentCoreEngine, ModelRunner, Support } from '@jangts/agent-core';
const provider = { async *stream() { yield '服务在线。'; } };
const config = Support.createModelStrategy({ model: { provider }, budget: 'small' });
const model = new ModelRunner(config);
console.log((await model.invoke('服务状态？')).value);
const agent = new AgentCoreEngine({ model: config });
console.log(agent.branch.agentId);

JavaScript

import { AgentCoreEngine, ModelRunner, Support } from '@jangts/agent-core';
const provider = { async *stream() { yield '服务在线。'; } };
const config = Support.createModelStrategy({ model: { provider }, budget: 'small' });
const model = new ModelRunner(config);
console.log((await model.invoke('服务状态？')).value);
const agent = new AgentCoreEngine({ model: config });
console.log(agent.branch.agentId);

已有模型用 ID 代指，推理方案显式登记

配置 · Node.js

示例 Provider 完全离线。实际供应商的推理参数由各 Provider 的显式配置实现。

TypeScript

import { ModelRunner, Support } from '@jangts/agent-core';
const fast = { async *stream() { yield '简短回答'; } };
const reasoned = { async *stream() { yield '经过复核的回答'; } };
const models = { fast: { provider: fast }, thorough: { provider: reasoned } };
const config = Support.createModelStrategy({ model: 'fast', models, budget: 'small',
  reasoning: 'high', reasoningOptions: { high: { provider: reasoned } },
  maxCalls: 1, maxOutputTokens: 1200,
});
console.log((await new ModelRunner(config).invoke('检查资料')).value);

JavaScript

import { ModelRunner, Support } from '@jangts/agent-core';
const fast = { async *stream() { yield '简短回答'; } };
const reasoned = { async *stream() { yield '经过复核的回答'; } };
const models = { fast: { provider: fast }, thorough: { provider: reasoned } };
const config = Support.createModelStrategy({ model: 'fast', models, budget: 'small',
    reasoning: 'high', reasoningOptions: { high: { provider: reasoned } },
    maxCalls: 1, maxOutputTokens: 1200,
});
console.log((await new ModelRunner(config).invoke('检查资料')).value);

自定义预算和原生 Core 端口保持有效

扩展 · Node.js

计数器仅为演示。生产环境注入与实际模型匹配的计数器，不用字符估算冒充真实 token 数。

TypeScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = { async *stream() { yield 'done'; } };
const transport = Support.createTextTransport({ id: 'app:text' });
const config = Support.createModelStrategy({ model: { provider, transports: [transport] },
  budget: { maxCalls: 3, maxInputChars: 24000, callTimeoutMs: 20000 },
  tokenBudget: { counterId: 'app-counter', contextWindowTokens: 4000,
    countTokens({ messages }) { return messages.reduce((sum, message) => sum + message.content.length, 0); } },
});
const result = await new ModelRunner(config).invoke({ input: 'hello', transport });
console.log(result.value);

JavaScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = { async *stream() { yield 'done'; } };
const transport = Support.createTextTransport({ id: 'app:text' });
const config = Support.createModelStrategy({ model: { provider, transports: [transport] },
    budget: { maxCalls: 3, maxInputChars: 24000, callTimeoutMs: 20000 },
    tokenBudget: { counterId: 'app-counter', contextWindowTokens: 4000,
        countTokens({ messages }) { return messages.reduce((sum, message) => sum + message.content.length, 0); } },
});
const result = await new ModelRunner(config).invoke({ input: 'hello', transport });
console.log(result.value);

相关策略源码

• 推荐预算、同合同补全和覆盖顺序