Message

KIT · type · Type contract

One entry of an OpenAI chat conversation.

The runtime validates role against the OpenAI role set and validates the outer shape of content; every other field is retained verbatim so vendor extensions flow through.

Import

TypeScript

import type { Message } from '@jangts/agent-core/mock';

JavaScript

/** @typedef {import('@jangts/agent-core/mock').Message} Message */

Other public entry points:@jangts/agent-core/mock.

Definition

Type: Message

Type expression

type Message = Readonly<{
  /**
   * `system`, `developer`, `user`, `assistant`, `tool` or `function`; anything else is rejected.
   */
  role: string;
  /** Text, a multimodal content-block array or null; numbers and objects are rejected. */
  content?: unknown;
  /** Opaque tool-call array from a previous assistant turn; never interpreted here. */
  tool_calls?: unknown;
  /** Correlates a `tool` message with the assistant tool call it answers. */
  tool_call_id?: string;
  /** Vendor extensions are snapshotted and preserved but never interpreted by the runtime. */
  [key: string]: unknown;
}>;

Field structure

Field	Type	Required	Description
role	string	Required	system, developer, user, assistant, tool or function; anything else is rejected.
content	unknown	Optional	Text, a multimodal content-block array or null; numbers and objects are rejected.
tool_calls	unknown	Optional	Opaque tool-call array from a previous assistant turn; never interpreted here.
tool_call_id	string | undefined	Optional	Correlates a tool message with the assistant tool call it answers.

Index structure

Field	Type	Required	Description
[key: string]	unknown	Required	Read-only. Index entry.

Examples

• MockGPT: direct generation and Provider injection: Get a string or JSON directly; inject the same instance into a Provider when you need to exercise model communication.
• MockGPT: response descriptions and scenario generators: Fixed results serve strict regression, input-dependent generators explore wiring, and explicit response descriptions cover failure and streaming scenarios.

Generate native JSON directly

Beginner · Node.js

TypeScript

import { MockGPT } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ prompt: '服务状态', generator: { online: true, source: 'fixture' } }] });
const value = await mock.generate({ model: 'demo', messages: [{ role: 'user', content: '服务状态' }] });
console.log(value); // { online: true, source: 'fixture' }
console.log(mock.counts, mock.records);

JavaScript

import { MockGPT } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ prompt: '服务状态', generator: { online: true, source: 'fixture' } }] });
const value = await mock.generate({ model: 'demo', messages: [{ role: 'user', content: '服务状态' }] });
console.log(value); // { online: true, source: 'fixture' }
console.log(mock.counts, mock.records);

Inject the same instance into the real Core model boundary

Configuration · Node.js

TypeScript

import { ModelRunner, Support } from '@jangts/agent-core';
import { MockGPT, responses } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ prompt: '服务状态', generator: responses.text('服务在线。', { chunkSize: 2, wireChunkSize: 3 }) }] });
const provider = new Support.CompatibleModelProvider({
  config: { baseUrl: 'https://mock.local/v1', apiKey: 'offline-example', model: 'demo' },
  ports: { request: mock.fetch },
});
const result = await new ModelRunner({ provider, maxCalls: 1 }).invoke('服务状态');
console.log(result.value, result.invocation.status);

JavaScript

import { ModelRunner, Support } from '@jangts/agent-core';
import { MockGPT, responses } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ prompt: '服务状态', generator: responses.text('服务在线。', { chunkSize: 2, wireChunkSize: 3 }) }] });
const provider = new Support.CompatibleModelProvider({
    config: { baseUrl: 'https://mock.local/v1', apiKey: 'offline-example', model: 'demo' },
    ports: { request: mock.fetch },
});
const result = await new ModelRunner({ provider, maxCalls: 1 }).invoke('服务状态');
console.log(result.value, result.invocation.status);