ModelStrategyOptions

SUPPORT · type · 类型合同

Input of createModelStrategy: model selection, optional reasoning and budget plus explicit Core overrides. Explicit Core fields win over every generated value.

导入

TypeScript

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

JavaScript

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

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

定义

类型： ModelStrategyOptions<Transports, Execution>

类型表达式

type ModelStrategyOptions<Transports extends readonly ModelTransportDefinition[] = readonly ModelTransportDefinition[], Execution = ExecutionOptions> = Partial<StrategyModel<Transports, Execution>> & {
  /** An existing definition, or an ID in the explicitly supplied model catalog. */
  readonly model: StrategyModel<Transports, Execution> | string;
  /** Named model definitions; required when `model` is a string ID. */
  readonly models?: Readonly<Record<string, StrategyModel<Transports, Execution>>>;
  /** Names and supplier-specific implementations are declared by the App, never guessed. */
  readonly reasoning?: string;
  /** Per-reasoning overrides; entries are applied only when `reasoning` names them. */
  readonly reasoningOptions?: Readonly<
    Record<string, Partial<StrategyModel<Transports, Execution>>>
  >;
  /** Preset name, or an explicit partial budget; defaults to `medium`. */
  readonly budget?: ModelBudgetStrategy;
};

泛型参数

类型参数	约束	默认类型
Transports	readonly ModelTransportDefinition[]	readonly ModelTransportDefinition[]
Execution	—	ExecutionOptions

字段结构

字段	类型	必需	说明
maxOutputTokens	number | undefined	可省略	Default output reservation; invoke can override it for one call.
maxCalls	number | undefined	可省略	Calls allowed for the whole request, including descendant runners' reservations.
callTimeoutMs	number | undefined	可省略	Deadline for one provider call, in milliseconds.
maxOutputChars	number | undefined	可省略	Cap on streamed output characters; exceeding it fails the call.
usage	boolean | undefined	可省略	Request and record provider usage for each call.
children	ModelChildPolicy | undefined	可省略	只读。见类型定义及调用场景。
maxInputChars	number | undefined	可省略	Character budget for the assembled input.
maxSchemaChars	number | undefined	可省略	Character allowance for registered capability schemas.
tokenBudget	ModelTokenBudget | undefined	可省略	见类型定义及调用场景。
provider	ChatProvider | undefined	可省略	见类型定义及调用场景。
transports	Transports | undefined	可省略	见类型定义及调用场景。
sink	{ output?: ModelRunnerPorts["onOutput"]; } | undefined	可省略	见类型定义及调用场景。
errors	{ inputBudget?: ModelRunnerPorts["inputBudgetError"]; outputBudget?: ModelRunnerPorts["outputBudgetError"]; } | undefined	可省略	见类型定义及调用场景。
execution	Execution | undefined	可省略	见类型定义及调用场景。
model	string | StrategyModel<Transports, Execution>	必需	只读。An existing definition, or an ID in the explicitly supplied model catalog.
models	Readonly<Record<string, StrategyModel<Transports, Execution>>> | undefined	可省略	只读。Named model definitions; required when model is a string ID.
reasoning	string | undefined	可省略	只读。Names and supplier-specific implementations are declared by the App, never guessed.
reasoningOptions	Readonly<Record<string, Partial<StrategyModel<Transports, Execution>>>> | undefined	可省略	只读。Per-reasoning overrides; entries are applied only when reasoning names them.
budget	ModelBudgetStrategy | undefined	可省略	只读。Preset name, or an explicit partial budget; defaults to medium.

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);

相关策略源码

• 推荐预算、同合同补全和覆盖顺序

相关定义

• ChatProvider
• ExecutionOptions
• ModelBudgetStrategy
• ModelChildPolicy
• ModelRunnerSettings
• ModelTokenBudget
• ModelTransportDefinition