Skip to content
中文

AnswerReader ​

KIT · interface · Type contract

App-owned reader that gathers evidence for one task.

Import ​

ts
import type { AnswerReader } from '@jangts/agent-core/kits/answering';
js
/** @typedef {import('@jangts/agent-core/kits/answering').AnswerReader} AnswerReader */

Other public entry points:@jangts/agent-core/types, @jangts/agent-core/kits/answering, @jangts/agent-core/kits.

Definition ​

ts
interface AnswerReader<Input, Evidence, App, Data>

Type parameters ​

Type parameterConstraintDefault type
Input——
Evidence——
App——
Data—unknown

Field structure ​

FieldTypeRequiredDescription
idstringRequiredRead-only. See the type definition and usage context.
read(input: Input, context: OperationContext<App> & { readonly task: Readonly<AnswerTaskDefinition<Input, Data>>; }) => MaybePromise<Evidence>RequiredProduces evidence for the validated input; the task is passed through for context.

Member index ​

MemberPurpose
readProduces evidence for the validated input; the task is passed through for context.

Member details ​

read ​

Produces evidence for the validated input; the task is passed through for context.

ts
AnswerReader.read(input: Input, context: OperationContext<App> & { readonly task: Readonly<AnswerTaskDefinition<Input, Data>>; }): MaybePromise<Evidence>

Produces evidence for the validated input; the task is passed through for context.

ParameterTypePassingDescription
inputInputRequired—
contextOperationContext<App> & { readonly task: Readonly<AnswerTaskDefinition<Input, Data>>; }Required—
Fields of context
FieldTypeRequiredDescription
appunknown extends App ? App : Readonly<App>RequiredRead-only. See the type definition and usage context.
loggerSubFlowLog | undefinedOptionalRead-only. Explicit optional recorder for this operation; never inferred from diagnostics.
signalAbortSignalRequiredRead-only. Non-optional cancellation signal; never undefined once execution has started.
diagnosticsDiagnosticContext | undefinedOptionalRead-only. Diagnostic scope of the enclosing call, when recording is enabled.
taskReadonly<AnswerTaskDefinition<Input, Data>>RequiredRead-only. See the type definition and usage context.

Returns: MaybePromise<Evidence>.

Awaited value: Awaited<Evidence>.

Examples ​

Register one read task for explanatory material ​

Beginner · Node.js

ts
import { Answering } from '@jangts/agent-core/kits/answering';
import { Presentation } from '@jangts/agent-core/kits/presentation';
const readers = Answering.defineAnswerReaderCatalog([{ id: 'manual', read: (input: string) => ({ question: input, source: 'Agent Core 允许普通对象节点。' }) }]);
const checks = Answering.defineAnswerCheckCatalog<string, {}>([]);
const outputs = Presentation.defineOutputCatalog([{ id: 'reply', kind: 'text', fields: [{ id: 'text', owner: 'generated' }] }]);
const tasks = Answering.defineAnswerTaskCatalog([
  { id: 'explain', description: '根据说明资料解释接口', readerId: 'manual', outputId: 'reply', goalIds: ['explain'], checkIds: [], metadata: {},
    inputSchema: { jsonSchema: { type: 'string' }, parse(value: unknown) { if (typeof value !== 'string') throw new Error('需要问题'); return value; } } },
], { readers, checks, outputs });
console.log(tasks.read({ taskId: 'explain', input: '如何定义节点?' }, { app: {}, signal: new AbortController().signal }));
js
import { Answering } from '@jangts/agent-core/kits/answering';
import { Presentation } from '@jangts/agent-core/kits/presentation';
const readers = Answering.defineAnswerReaderCatalog([{ id: 'manual', read: (input) => ({ question: input, source: 'Agent Core 允许普通对象节点。' }) }]);
const checks = Answering.defineAnswerCheckCatalog([]);
const outputs = Presentation.defineOutputCatalog([{ id: 'reply', kind: 'text', fields: [{ id: 'text', owner: 'generated' }] }]);
const tasks = Answering.defineAnswerTaskCatalog([
    { id: 'explain', description: '根据说明资料解释接口', readerId: 'manual', outputId: 'reply', goalIds: ['explain'], checkIds: [], metadata: {},
        inputSchema: { jsonSchema: { type: 'string' }, parse(value) { if (typeof value !== 'string')
                throw new Error('需要问题'); return value; } } },
], { readers, checks, outputs });
console.log(tasks.read({ taskId: 'explain', input: '如何定义节点?' }, { app: {}, signal: new AbortController().signal }));

Add check references to the same task and check the generated result ​

Configuration · Node.js

ts
import { Answering } from '@jangts/agent-core/kits/answering';
import { Presentation } from '@jangts/agent-core/kits/presentation';
const readers = Answering.defineAnswerReaderCatalog([{ id: 'manual', read: (input: string) => ({ question: input, source: 'Agent Core 允许普通对象节点。' }) }]);
const checks = Answering.defineAnswerCheckCatalog<string, {}>([
  { id: 'nonempty', check: value => ({ status: value.trim() ? 'passed' : 'failed', value: value.trim(), issues: value.trim() ? [] : [{ code: 'EMPTY', message: '答案为空' }] }) },
]);
const outputs = Presentation.defineOutputCatalog([{ id: 'reply', kind: 'text', fields: [{ id: 'text', owner: 'generated' }] }]);
const tasks = Answering.defineAnswerTaskCatalog([
  { id: 'explain', description: '根据说明资料解释接口', readerId: 'manual', outputId: 'reply', goalIds: ['explain'], checkIds: ['nonempty'], metadata: {},
    inputSchema: { jsonSchema: { type: 'string' }, parse(value: unknown) { if (typeof value !== 'string') throw new Error('需要问题'); return value; } } },
], { readers, checks, outputs });
const context = { app: {}, signal: new AbortController().signal };
const evidence = await tasks.readAsync({ taskId: 'explain', input: '如何定义节点?' }, context);
console.log(evidence, checks.check({ checkIds: tasks.require('explain').checkIds, value: ' 普通对象即可。 ' }, context));
js
import { Answering } from '@jangts/agent-core/kits/answering';
import { Presentation } from '@jangts/agent-core/kits/presentation';
const readers = Answering.defineAnswerReaderCatalog([{ id: 'manual', read: (input) => ({ question: input, source: 'Agent Core 允许普通对象节点。' }) }]);
const checks = Answering.defineAnswerCheckCatalog([
    { id: 'nonempty', check: value => ({ status: value.trim() ? 'passed' : 'failed', value: value.trim(), issues: value.trim() ? [] : [{ code: 'EMPTY', message: '答案为空' }] }) },
]);
const outputs = Presentation.defineOutputCatalog([{ id: 'reply', kind: 'text', fields: [{ id: 'text', owner: 'generated' }] }]);
const tasks = Answering.defineAnswerTaskCatalog([
    { id: 'explain', description: '根据说明资料解释接口', readerId: 'manual', outputId: 'reply', goalIds: ['explain'], checkIds: ['nonempty'], metadata: {},
        inputSchema: { jsonSchema: { type: 'string' }, parse(value) { if (typeof value !== 'string')
                throw new Error('需要问题'); return value; } } },
], { readers, checks, outputs });
const context = { app: {}, signal: new AbortController().signal };
const evidence = await tasks.readAsync({ taskId: 'explain', input: '如何定义节点?' }, context);
console.log(evidence, checks.check({ checkIds: tasks.require('explain').checkIds, value: ' 普通对象即可。 ' }, context));

API reference, usage examples and developer guides.