assembleFragments

CORE · function · 运行时值

Build the model input from fragments.

Metadata remains program-side: data never becomes a system instruction.

导入

TypeScript

import { assembleFragments } from '@jangts/agent-core/context';

JavaScript

import { assembleFragments } from '@jangts/agent-core/context';

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

定义

调用

assembleFragments(fragments: ContextFragment[], maxInputChars: number): BuiltContext

Build the model input from fragments.

Metadata remains program-side: data never becomes a system instruction.

参数	类型	传递	说明
fragments	ContextFragment[]	必需	—
maxInputChars	number	必需	—

返回： BuiltContext。

返回值结构

字段	类型	必需	说明
messages	ModelMessage[]	必需	Messages in final model order.
fragmentUsage	ContextFragmentUsage[]	必需	Per-fragment accounting in the same order as the fragments were merged.
inputChars	number	必需	Total counted characters across messages and usage.
maxInputChars	number	必需	Budget the assembly was validated against; Infinity means unbounded.

使用示例

• 上下文片段：明确来源、信任和预算：Core 识别片段与装配合同，校验来源元数据和预算，不内置业务压缩算法。

用裸配置装配一份输入

入门 · Node.js

TypeScript

import { assembleFragments } from '@jangts/agent-core/context';
const input = assembleFragments([{ id: 'question', sourceId: 'request', trust: 'user',
  lifetime: 'turn', maxChars: 1000, role: 'user', value: '现在服务状态怎样？' }], 2000);
console.log(input.messages, input.fragmentUsage);

JavaScript

import { assembleFragments } from '@jangts/agent-core/context';
const input = assembleFragments([{ id: 'question', sourceId: 'request', trust: 'user',
        lifetime: 'turn', maxChars: 1000, role: 'user', value: '现在服务状态怎样？' }], 2000);
console.log(input.messages, input.fragmentUsage);

增加候选计划与最终审计

配置 · Node.js

可变片段列表为空，表示不允许修改原片段；不会自动授权一个压缩步骤。

TypeScript

import { assembleContextPlan } from '@jangts/agent-core/context';
import type { ContextFragment } from '@jangts/agent-core/types';
const fragments: ContextFragment[] = [{ id: 'question', sourceId: 'request', trust: 'user',
  lifetime: 'turn', maxChars: 1000, role: 'user', value: '现在服务状态怎样？' }];
const input = assembleContextPlan({ fragments, originalFragments: fragments, mutableFragmentIds: [], maxInputChars: 2000 });
console.log(input.inputChars);

JavaScript

import { assembleContextPlan } from '@jangts/agent-core/context';
const fragments = [{ id: 'question', sourceId: 'request', trust: 'user',
        lifetime: 'turn', maxChars: 1000, role: 'user', value: '现在服务状态怎样？' }];
const input = assembleContextPlan({ fragments, originalFragments: fragments, mutableFragmentIds: [], maxInputChars: 2000 });
console.log(input.inputChars);

相关策略源码

• 片段校验与预算拒绝

相关定义

• BuiltContext
• ContextFragment