definePolicySet

KIT · function · 运行时值

Compile a policy set that reports every matching reason.

Collect every matching reason; a configured mode cannot silently override a mandatory policy. assess returns the matched ids and deduplicated kinds rather than a single verdict, so callers keep the ordering information they need for messages and diagnostics.

导入

TypeScript

import { definePolicySet } from '@jangts/agent-core/kits/policies';

JavaScript

import { definePolicySet } from '@jangts/agent-core/kits/policies';

其他公开入口：@jangts/agent-core、@jangts/agent-core/types、@jangts/agent-core/kits/policies、@jangts/agent-core/kits。

定义

泛型参数

类型参数	约束	默认类型
Input	—	—
Kind	string	—

调用

definePolicySet<Input, Kind extends string>(definitions: readonly PolicyDefinition<Input, Kind>[]): Readonly<{ assess(input: Input): { required: boolean; reasons: string[]; kinds: Kind[]; }; definitions: readonly Readonly<PolicyDefinition<Input, Kind>>[]; ids(): readonly string[]; values(): IterableIterator<Readonly<PolicyDefinition<Input, Kind>>>; entries(): IterableIterator<readonly [string, Readonly<PolicyDefinition<Input, Kind>>]>; has(id: string): boolean; get(id: string): Readonly<PolicyDefinition<Input, Kind>> | undefined; require(id: string): Readonly<PolicyDefinition<Input, Kind>>; }>

Compile a policy set that reports every matching reason.

Collect every matching reason; a configured mode cannot silently override a mandatory policy. assess returns the matched ids and deduplicated kinds rather than a single verdict, so callers keep the ordering information they need for messages and diagnostics.

类型参数	约束	默认类型
Input	—	—
Kind	string	—

参数	类型	传递	说明
definitions	readonly PolicyDefinition<Input, Kind>[]	必需	—

返回： Readonly<{ assess(input: Input): { required: boolean; reasons: string[]; kinds: Kind[]; }; definitions: readonly Readonly<PolicyDefinition<Input, Kind>>[]; ids(): readonly string[]; values(): IterableIterator<Readonly<PolicyDefinition<Input, Kind>>>; entries(): IterableIterator<readonly [string, Readonly<PolicyDefinition<Input, Kind>>]>; has(id: string): boolean; get(id: string): Readonly<PolicyDefinition<Input, Kind>> \| undefined; require(id: string): Readonly<PolicyDefinition<Input, Kind>>; }>。

返回值结构

字段	类型	必需	说明
assess	(input: Input) => { required: boolean; reasons: string[]; kinds: Kind[]; }	必需	见类型定义及调用场景。
definitions	readonly Readonly<PolicyDefinition<Input, Kind>>[]	必需	只读。Definitions in registration order; each entry is frozen by the implementation.
ids	() => readonly string[]	必需	Ids in the same order as definitions.
values	() => IterableIterator<Readonly<PolicyDefinition<Input, Kind>>>	必需	见类型定义及调用场景。
entries	() => IterableIterator<readonly [string, Readonly<PolicyDefinition<Input, Kind>>]>	必需	见类型定义及调用场景。
has	(id: string) => boolean	必需	见类型定义及调用场景。
get	(id: string) => Readonly<PolicyDefinition<Input, Kind>> | undefined	必需	Returns the definition or undefined; the caller decides whether absence is an error.
require	(id: string) => Readonly<PolicyDefinition<Input, Kind>>	必需	Returns the definition or throws; use when the id is a required reference.

使用示例

• Policies：全部命中与首个恢复：策略集收集所有匹配理由；恢复链按顺序选择第一个显式 handled 结果。

为同一答复声明何时必须复核

入门 · Node.js

TypeScript

import { Policies } from '@jangts/agent-core/kits/policies';
const policy = Policies.definePolicySet([
  { id: 'has-write', description: '有写操作就复核', kind: 'review', when: (input: { wrote: boolean }) => input.wrote },
]);
console.log(policy.assess({ wrote: true }));

JavaScript

import { Policies } from '@jangts/agent-core/kits/policies';
const policy = Policies.definePolicySet([
    { id: 'has-write', description: '有写操作就复核', kind: 'review', when: (input) => input.wrote },
]);
console.log(policy.assess({ wrote: true }));

增加另一理由及有序恢复

配置 · Node.js

TypeScript

import { Policies } from '@jangts/agent-core/kits/policies';
type Input = { wrote: boolean; uncertain: boolean; cancelled: boolean };
const policy = Policies.definePolicySet<Input, 'review'>([
  { id: 'has-write', description: '有写操作就复核', kind: 'review', when: input => input.wrote },
  { id: 'uncertain', description: '证据不确定就复核', kind: 'review', when: input => input.uncertain },
]);
const recovery = Policies.defineRecoveryChain<Input, string>([
  { id: 'cancelled', description: '取消时不发布答案', tryRecover: input => input.cancelled ? { handled: true, value: '任务已取消' } : { handled: false } },
  { id: 'needs-review', description: '未通过复核时明确说明', tryRecover: input => policy.assess(input).required ? { handled: true, value: '结果还需要复核' } : { handled: false } },
]);
const input = { wrote: true, uncertain: true, cancelled: false };
console.log(policy.assess(input), recovery.tryRecover(input));

JavaScript

import { Policies } from '@jangts/agent-core/kits/policies';
const policy = Policies.definePolicySet([
    { id: 'has-write', description: '有写操作就复核', kind: 'review', when: input => input.wrote },
    { id: 'uncertain', description: '证据不确定就复核', kind: 'review', when: input => input.uncertain },
]);
const recovery = Policies.defineRecoveryChain([
    { id: 'cancelled', description: '取消时不发布答案', tryRecover: input => input.cancelled ? { handled: true, value: '任务已取消' } : { handled: false } },
    { id: 'needs-review', description: '未通过复核时明确说明', tryRecover: input => policy.assess(input).required ? { handled: true, value: '结果还需要复核' } : { handled: false } },
]);
const input = { wrote: true, uncertain: true, cancelled: false };
console.log(policy.assess(input), recovery.tryRecover(input));

相关策略源码

• 全命中与首个 handled

相关定义

• PolicyDefinition