Agent Core

简体中文

English

简体中文

English

外观

English

createContextReductionNode ​

SUPPORT · function · 运行时值

Create a node that applies exactly one registered reduction step.

Partial plans keep the full budget until final assembly, so intermediate nodes do not shrink the allowance reserved for the reply.

导入 ​

ts
import { createContextReductionNode } from '@jangts/agent-core/support';
js
import { createContextReductionNode } from '@jangts/agent-core/support';

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

定义 ​

泛型参数 ​

类型参数约束默认类型
State——
Result——
App—undefined

调用 ​

ts
createContextReductionNode<State, Result, App = undefined>(definition: ContextReductionNodeDefinition<State, Result, App>): WorkflowNode<State, Result, App>

Create a node that applies exactly one registered reduction step.

Partial plans keep the full budget until final assembly, so intermediate nodes do not shrink the allowance reserved for the reply.

类型参数约束默认类型
State——
Result——
App—undefined
参数类型传递说明
definitionContextReductionNodeDefinition<State, Result, App>必需—
definition 的字段
字段类型必需说明
idstring必需只读。Stable node id referenced by routes and error handling.
descriptionstring必需只读。Required explanation of what the node does; also used in diagnostics.
namestring | undefined可省略只读。Display name; defaults to id when omitted.
requiresreadonly (keyof State & string)[] | undefined可省略只读。State keys that must be present before this node runs; enforced by the engine.
providesreadonly (keyof State & string)[] | undefined可省略只读。State keys this node is expected to produce; validated after run.
routesreadonly WorkflowRoute<State, Result, App>[]必需只读。Candidate successors, evaluated in order. A getter must be pure; registration reads it once.
startsRoundboolean | undefined可省略只读。Reserves a fresh round on entry. Use it for steps that may legitimately repeat; entering such a node when the round budget is exhausted fails with the configured exhausted error.
onErrorNodeIdstring | undefined可省略只读。Node entered when run/provides/route fails; contract errors always propagate instead.
onErrorRouteIdstring | undefined可省略只读。Route id reported with the recovery transition.
prepared((state: Readonly<State>, context: WorkflowContext<App>) => PreparedModelCall) | undefined可省略只读。Optional prebuilt model call, used instead of preparing request.
plan(state: Readonly<State>, context: WorkflowContext<App>) => ContextPlan必需只读。Builds the context plan; must be synchronous so budget failures surface before any I/O.
request(ModelPrepareRequest<string | ModelTransportDefinition<unknown>> & { modelId?: string; }) | ((state: Readonly<State>, context: WorkflowContext<App>) => ModelPrepareRequest<string | ModelTransportDefinition> & { modelId?: string; }) | undefined可省略只读。Model preparation request, either static or derived from the current node state.
policyContextPolicy | undefined可省略只读。Processing policy; omitted means validate (no reduction, audit checks only).
timeoutMsnumber | undefined可省略只读。Per-node timeout in milliseconds; defaults to the Core call timeout.
compressorsreadonly ContextCompressor[] | undefined可省略只读。Compressors referenced by compression steps; validated against the policy at creation.
selectorsreadonly ContextSelector[] | undefined可省略只读。Selectors referenced by model-driven selection; validated against the policy at creation.
stepIdstring | ((state: Readonly<State>) => string)必需只读。ID of the reduction step to run, fixed or derived from state.
update(result: ContextStageResult, state: Readonly<State>) => Partial<State>必需只读。Receives the stage result after one reduction has been applied.

返回： WorkflowNode<State, Result, App>。

返回值结构
字段类型必需说明
idstring必需只读。Stable node id referenced by routes and error handling.
descriptionstring必需只读。Required explanation of what the node does; also used in diagnostics.
namestring | undefined可省略只读。Display name; defaults to id when omitted.
report((update: void | Readonly<Partial<State>>, context: NodeReportingContext) => WorkflowNodeReport) | undefined可省略只读。Optional application-reported detail, collected only when content logging is enabled.
startsRoundboolean | undefined可省略只读。Reserves a fresh round on entry. Use it for steps that may legitimately repeat; entering such a node when the round budget is exhausted fails with the configured exhausted error.
onErrorNodeIdstring | undefined可省略只读。Node entered when run/provides/route fails; contract errors always propagate instead.
onErrorRouteIdstring | undefined可省略只读。Route id reported with the recovery transition.
requiresreadonly (keyof State & string)[] | undefined可省略只读。State keys that must be present before this node runs; enforced by the engine.
providesreadonly (keyof State & string)[] | undefined可省略只读。State keys this node is expected to produce; validated after run.
routesreadonly WorkflowRoute<State, Result, App>[]必需只读。Candidate successors, evaluated in order. A getter must be pure; registration reads it once.
run((state: Readonly<State>, context: WorkflowContext<App>) => void | Partial<State> | Promise<void | Partial<State>>) | undefined可省略只读。Return only changed fields. Core commits them after cancellation and output checks.

使用示例 ​

只验证与装配，先不增加压缩 ​

入门 · Node.js

ts
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？' }));
js
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。

ts
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);
js
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 ​

相关定义 ​

接口参考、使用示例与开发指南。

Jangts Agent Core