ModelStrategyOptions

SUPPORT · type · Type contract

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

Import

TypeScript

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

JavaScript

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

Other public entry points:@jangts/agent-core/support, @jangts/agent-core/support/model.

Definition

Type: ModelStrategyOptions<Transports, Execution>

Type expression

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;
};

Type parameters

Type parameter	Constraint	Default type
Transports	readonly ModelTransportDefinition[]	readonly ModelTransportDefinition[]
Execution	—	ExecutionOptions

Field structure

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

Examples

• Model strategy: explicit selection and recommended budgets: Select from registered models and reasoning configurations, complete Core settings with local budget tiers, and keep per-field exact overrides.

Use a small budget for a short task and keep the same Core construction as needs grow

Beginner · 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);

Refer to an existing model by ID and register the reasoning scheme explicitly

Configuration · Node.js

The example Providers are fully offline. Reasoning parameters for real providers are implemented through each Provider's explicit configuration.

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);

Related policy source

• Recommended budgets, same-contract completion, and override order

Related definitions

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