ContextStageResult

SUPPORT · interface · 类型合同

Result of a selection or reduction stage, before the node's update commits chosen fields.

导入

TypeScript

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

JavaScript

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

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

定义

interface ContextStageResult

字段结构

字段	类型	必需	说明
plan	ContextPlan	必需	只读。Plan describing current fragments at the full (unreduced) input limit.
prepared	PreparedModelCall<unknown>	必需	只读。Model call prepared for this stage.
report	ContextProcessingReport	必需	只读。Processing report accumulated by this and preceding steps.

使用示例

• 上下文处理是普通 Workflow 节点：通过正常节点与路由接入选择、裁切、压缩，Core 统一记录并调度它们。

只验证与装配，先不增加压缩

入门 · Node.js

TypeScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
import { Support } from '@jangts/agent-core';
import type { BuiltContext, PreparedModelCall } from '@jangts/agent-core/types';
type State = { question: string; input?: BuiltContext; prepared?: PreparedModelCall; answer?: string };
const builder = Support.defineContextFragments<State>([
  { id: 'question', sourceId: 'request', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 1000, format: state => state.question },
], { maxInputChars: 2000 });
const prepare = Support.createContextProcessingNode<State, string>({
  id: 'prepare', description: '装配并校验输入', startsRound: true,
  plan: state => builder.plan({ input: state }),
  update: result => ({ input: result.input, prepared: result.prepared }),
  routes: [route.to('reply')],
});
const workflow = defineWorkflow<State, string>({ id: 'chat', nodes: [prepare, {
  id: 'reply', description: '使用同次准备回答', requires: ['input', 'prepared'],
  async run(state, { model }) { const { value } = await model.invoke({ input: state.input!, prepared: state.prepared! }); return { answer: String(value) }; },
  routes: [route.deliver('answer')],
}] });
const agent = new AgentCoreEngine({ workflow, model: { provider: { async *stream() { yield '服务正常'; } } } });
console.log(await agent.run({ question: '状态？' }));

JavaScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
import { Support } from '@jangts/agent-core';
const builder = Support.defineContextFragments([
    { id: 'question', sourceId: 'request', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 1000, format: state => state.question },
], { maxInputChars: 2000 });
const prepare = Support.createContextProcessingNode({
    id: 'prepare', description: '装配并校验输入', startsRound: true,
    plan: state => builder.plan({ input: state }),
    update: result => ({ input: result.input, prepared: result.prepared }),
    routes: [route.to('reply')],
});
const workflow = defineWorkflow({ id: 'chat', nodes: [prepare, {
            id: 'reply', description: '使用同次准备回答', requires: ['input', 'prepared'],
            async run(state, { model }) { const { value } = await model.invoke({ input: state.input, prepared: state.prepared }); return { answer: String(value) }; },
            routes: [route.deliver('answer')],
        }] });
const agent = new AgentCoreEngine({ workflow, model: { provider: { async *stream() { yield '服务正常'; } } } });
console.log(await agent.run({ question: '状态？' }));

同一节点合同增加历史裁切策略

配置 · Node.js

将该节点放回前例相同 Workflow；每次 run 的 State 增加 history 即可，模型 reply 节点不换接口。完整流程里的 reply 目标必须存在。

TypeScript

import { Support } from '@jangts/agent-core';
import { route } from '@jangts/agent-core/engine';
import type { BuiltContext, PreparedModelCall } from '@jangts/agent-core/types';
type State = { question: string; history: { role: string; content: string }[]; input?: BuiltContext; prepared?: PreparedModelCall };
const builder = Support.defineContextFragments<State>([
  { id: 'question', sourceId: 'request', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 1000, format: state => state.question },
  { id: 'history', sourceId: 'conversation', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 10000, format: state => ({ messages: state.history }) },
], { maxInputChars: 1200 });
const prepare = Support.createContextProcessingNode<State, string>({
  id: 'prepare', description: '按需要裁切旧历史', startsRound: true,
  plan: state => builder.plan({ input: state }),
  policy: { mode: 'reduce', steps: [{ id: 'recent', kind: 'trim', fragmentId: 'history', field: 'messages',
    targetChars: 700, grouping: { kind: 'user-turn' }, keepGroups: 1 }] },
  update: result => ({ input: result.input, prepared: result.prepared }),
  routes: [route.to('reply')],
});
console.log(prepare.id);

JavaScript

import { Support } from '@jangts/agent-core';
import { route } from '@jangts/agent-core/engine';
const builder = Support.defineContextFragments([
    { id: 'question', sourceId: 'request', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 1000, format: state => state.question },
    { id: 'history', sourceId: 'conversation', trust: 'user', lifetime: 'turn', role: 'user', maxChars: 10000, format: state => ({ messages: state.history }) },
], { maxInputChars: 1200 });
const prepare = Support.createContextProcessingNode({
    id: 'prepare', description: '按需要裁切旧历史', startsRound: true,
    plan: state => builder.plan({ input: state }),
    policy: { mode: 'reduce', steps: [{ id: 'recent', kind: 'trim', fragmentId: 'history', field: 'messages',
                targetChars: 700, grouping: { kind: 'user-turn' }, keepGroups: 1 }] },
    update: result => ({ input: result.input, prepared: result.prepared }),
    routes: [route.to('reply')],
});
console.log(prepare.id);

相关策略源码

• 普通节点的配置绑定与阶段执行

相关定义

• ContextPlan
• ContextProcessingReport
• PreparedModelCall