GenerationContext

KIT · interface · 类型合同

Everything a rule or generator may read for one accepted call.

The context is frozen; the only mutable side channel is report, and only while the call is still pending.

导入

TypeScript

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

JavaScript

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

其他公开入口：@jangts/agent-core/mock。

定义

interface GenerationContext

字段结构

字段	类型	必需	说明
request	ModelRequest	必需	只读。Frozen snapshot of the normalized request that matched.
prompt	string	必需	只读。Prompt selected by selectPrompt; default is the text of the last user message.
match	RegExpMatchArray | null	必需	只读。Match of the matched rule's regular expression, or null for string/fallback rules.
callIndex	number	必需	只读。1-based sequence number of this call across the instance lifetime; reset by reset.
ruleIndex	number	必需	只读。1-based hit count of the matched rule, or the fallback hit count for fallback calls.
signal	AbortSignal	必需	只读。Signal for the current call; also aborts when the transport is cancelled.
random	() => number	必需	只读。Per-call deterministic PRNG in [0, 1), derived from the instance seed and call order.
clock	() => number	必需	只读。Millisecond timestamp from the configured clock; throws if the clock is not synchronous.
report	(metadata: Record<string, JsonValue>) => void	必需	只读。Bounded diagnostic data; never inserted into model content.

成员目录

成员	用途
random	Per-call deterministic PRNG in [0, 1), derived from the instance seed and call order.
clock	Millisecond timestamp from the configured clock; throws if the clock is not synchronous.
report	Bounded diagnostic data; never inserted into model content.

成员详情

random

Per-call deterministic PRNG in [0, 1), derived from the instance seed and call order.

GenerationContext.random(): number

无调用参数。

返回： number。

clock

Millisecond timestamp from the configured clock; throws if the clock is not synchronous.

GenerationContext.clock(): number

无调用参数。

返回： number。

report

Bounded diagnostic data; never inserted into model content.

GenerationContext.report(metadata: Record<string, JsonValue>): void

参数	类型	传递	说明
metadata	Record<string, JsonValue>	必需	—

返回： void。

使用示例

• MockGPT：响应描述与场景生成器：固定结果用于严格回归，输入相关生成器用于探索接线，显式响应描述用于故障和流式场景。
• MockGPT Web：可信来源与本地摘要：从真实网页或可信 load 取得正文，再交给输入相关生成器。

编码已校验的模型结果

扩展 · Node.js

适配器负责请求校验、首包前延迟和生命周期；编码器不执行规则或修改 MockGPT 调用记录。

TypeScript

import { encodeModelResponse } from '@jangts/agent-core/mock';
const controller = new AbortController();
const response = encodeModelResponse(
  { model: 'demo', messages: [{ role: 'user', content: '状态' }], stream: false },
  { content: '服务在线。' }, 'mock-1', 1700000000, controller.signal,
  (error, cancelled) => console.log({ error, cancelled }),
);
console.log(await response.json());

JavaScript

import { encodeModelResponse } from '@jangts/agent-core/mock';
const controller = new AbortController();
const response = encodeModelResponse({ model: 'demo', messages: [{ role: 'user', content: '状态' }], stream: false }, { content: '服务在线。' }, 'mock-1', 1700000000, controller.signal, (error, cancelled) => console.log({ error, cancelled }));
console.log(await response.json());

从输入生成可检查的摘要

入门 · Node.js

TypeScript

import { MockGPT, generators } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ generator: generators.summary({ maxChars: 120, count: 2 }) }] });
console.log(await mock.generate({ model: 'demo', messages: [{ role: 'user', content: '服务刚完成维护。健康检查通过。用户可以查询状态。' }] }));
console.log(mock.records);

JavaScript

import { MockGPT, generators } from '@jangts/agent-core/mock';
const mock = new MockGPT({ rules: [{ generator: generators.summary({ maxChars: 120, count: 2 }) }] });
console.log(await mock.generate({ model: 'demo', messages: [{ role: 'user', content: '服务刚完成维护。健康检查通过。用户可以查询状态。' }] }));
console.log(mock.records);

相关定义

• JsonValue
• ModelRequest