ModelRunnerPorts

CORE · interface · Type contract

Host ports a model runner needs in addition to its provider and transports.

Import

TypeScript

import type { ModelRunnerPorts } from '@jangts/agent-core/model';

JavaScript

/** @typedef {import('@jangts/agent-core/model').ModelRunnerPorts} ModelRunnerPorts */

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

Definition

interface ModelRunnerPorts

Field structure

Field	Type	Required	Description
onOutput	((event: ModelOutputEvent) => void | Promise<void>) | undefined	Optional	Ordered delivery of model events; awaits each call before continuing.
transports	readonly ModelTransportDefinition<unknown>[] | undefined	Optional	Transports available by id and instance.
diagnostics	DiagnosticContext | undefined	Optional	See the type definition and usage context.
maxSchemaChars	number | undefined	Optional	Separate allowance for registered schemas; existing context budgets keep their meaning.
tokenBudget	ModelTokenBudget | undefined	Optional	See the type definition and usage context.
inputBudgetError	((limit: number) => Error) | undefined	Optional	Builds the error for an input that exceeds the character or token limit.
outputBudgetError	(() => Error) | undefined	Optional	Builds the error for output that exceeds the character limit.

Examples

• ModelRunner: input can be shortened while the output contract stays the same: Execute one model interaction through the real Provider port and return a value plus the invocation for this call.

Two inputs for the same output

Beginner · 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);

Add budget and request cancellation

Configuration · 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);

Related policy source

• Core default budget values

Related definitions

• DiagnosticContext
• ModelOutputEvent
• ModelTokenBudget
• ModelTransportDefinition