defaultCompletionPolicy

SUPPORT · constant · Runtime value

Import

TypeScript

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

JavaScript

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

Other public entry points:@jangts/agent-core/support, @jangts/agent-core/support/model.

Definition

Field structure

Field	Type	Required	Description
id	string	Required	Read-only. Registered identifier; the catalog key must match it.

Member index

Member	Purpose
begin	Start one request. Throwing here rejects the request before it is sent, which is how a policy refuses a request shape it cannot judge after the fact.

Member details

begin

Start one request.

Throwing here rejects the request before it is sent, which is how a policy refuses a request shape it cannot judge after the fact.

defaultCompletionPolicy.begin(facts: CompletionRequestFacts, fail: CompletionFailure): CompletionSession

Start one request.

Throwing here rejects the request before it is sent, which is how a policy refuses a request shape it cannot judge after the fact.

Parameter	Type	Passing	Description
facts	CompletionRequestFacts	Required	—
fail	CompletionFailure	Required	—

Fields of facts

Field	Type	Required	Description
functions	boolean	Required	Read-only. Whether the call declared native functions through Core options.
toolChoice	unknown	Optional	Read-only. Effective tool_choice of the request body; an absent field reads as undefined.
allowEmptyText	boolean	Required	Read-only. Whether an empty response is allowed because JSON mode permits it.

Returns: CompletionSession.

Return value structure

Field	Type	Required	Description
part	(part: ModelPart) => void	Required	Observe one part immediately before the provider yields it.
finish	(reason: string) => void	Required	Observe the stream's single finish_reason.
end	() => void	Required	Complete the response when the end-of-stream marker arrives.

Examples

• Compatible Provider and custom Providers: Support owns the common Chat Completions HTTP/SSE lifecycle; an App can substitute its own ChatProvider.

Connect a common protocol with real server-side configuration

Beginner · Node.js

Running this example requires connection configuration for an available model service.

TypeScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = new Support.CompatibleModelProvider({ config: {
  baseUrl: process.env.MODEL_BASE_URL!, apiKey: process.env.MODEL_API_KEY!, model: process.env.MODEL_NAME!,
} });
const runner = new ModelRunner({ provider });
console.log((await runner.invoke('你好')).value);

JavaScript

import { ModelRunner, Support } from '@jangts/agent-core';
const provider = new Support.CompatibleModelProvider({ config: {
        baseUrl: process.env.MODEL_BASE_URL, apiKey: process.env.MODEL_API_KEY, model: process.env.MODEL_NAME,
    } });
const runner = new ModelRunner({ provider });
console.log((await runner.invoke('你好')).value);

Declared fields and wire mapping for a direct tool thread

Configuration · Node.js

This only demonstrates message conversion, with no network request or tool execution. Raw tool_calls, tool_call_id, and host-attached data are not forwarded.

TypeScript

import { Support } from '@jangts/agent-core';
const messages: Support.ProviderMessage[] = [
  { role: 'user', content: '查询资料' },
  { role: 'assistant', content: '', toolCalls: [
    { id: 'call-1', name: 'lookup', arguments: '{"query":"资料"}' },
  ] },
  { role: 'tool', content: '{"found":true}', toolCallId: 'call-1' },
];
console.log(Support.chatCompletionMessages(messages));

JavaScript

import { Support } from '@jangts/agent-core';
const messages = [
    { role: 'user', content: '查询资料' },
    { role: 'assistant', content: '', toolCalls: [
            { id: 'call-1', name: 'lookup', arguments: '{"query":"资料"}' },
        ] },
    { role: 'tool', content: '{"found":true}', toolCallId: 'call-1' },
];
console.log(Support.chatCompletionMessages(messages));

Connect an offline object implementation to the same contract

Configuration · Node.js

TypeScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = { async *stream(messages: readonly { content: string }[]) {
  yield '离线回答：' + messages.at(-1)!.content;
} };
console.log((await new ModelRunner({ provider }).invoke('你好')).value);

JavaScript

import { ModelRunner } from '@jangts/agent-core/model';
const provider = { async *stream(messages) {
        yield '离线回答：' + messages.at(-1).content;
    } };
console.log((await new ModelRunner({ provider }).invoke('你好')).value);

Related policy source

• HTTP failure mapping and controlled request fields

Related definitions

• CompletionFailure
• CompletionPolicy
• CompletionRequestFacts
• CompletionSession