ModelCallRecord
CORE · interface · 类型合同
Receipt of a model call that returned successfully.
导入
ts
import type { ModelCallRecord } from '@jangts/agent-core';js
/** @typedef {import('@jangts/agent-core').ModelCallRecord} ModelCallRecord */其他公开入口:@jangts/agent-core、@jangts/agent-core/types、@jangts/agent-core/structs。
定义
ts
interface ModelCallRecord继承或实现: InvocationMetadata。
字段结构
| 字段 | 类型 | 必需 | 说明 |
|---|---|---|---|
status | "success" | 必需 | 只读。Records are only emitted for successful calls; failures are thrown instead. |
stageId | string | undefined | 可省略 | 只读。Workflow stage that requested the call. |
modelId | string | undefined | 可省略 | 只读。Configured model binding used for the call. |
callSequence | number | 必需 | 只读。One-based position of the call within its runner's lifetime. |
usage | Readonly<ModelUsage> | undefined | 可省略 | 只读。Provider-reported token usage; present only when the provider supplied it. |
runId | string | undefined | 可省略 | 只读。Root run this invocation belongs to, when the host runs inside a diagnostics scope. |
spanId | string | undefined | 可省略 | 只读。Diagnostics span of this invocation. |
parentSpanId | string | undefined | 可省略 | 只读。Span that caused this invocation; absent for a root invocation. |
parentInvocationId | string | undefined | 可省略 | 只读。Enclosing invocation when one call triggers another. |
invocationId | string | 必需 | 只读。Opaque per-invocation id shared by receipt, events and diagnostic records. |
startedAtMs | number | 必需 | 只读。Start instant in epoch milliseconds. |
durationMs | number | 必需 | 只读。Elapsed milliseconds from start to completion. |
使用示例
- ModelRunner:输入可以省写,输出合同保持一致:用真实 Provider 端口执行一次模型交互,返回 value 和本次 invocation。
同一输出的两种输入
入门 · Node.js
ts
import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
async *stream(messages: readonly { content: string }[]) {
yield '收到:' + messages.at(-1)!.content;
},
};
const runner = new ModelRunner({ provider });
const first = await runner.invoke('你好');
const second = await runner.invoke({ input: '你好' });
console.log(first.value, second.value);
console.log(first.invocation.invocationId);js
import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
async *stream(messages) {
yield '收到:' + messages.at(-1).content;
},
};
const runner = new ModelRunner({ provider });
const first = await runner.invoke('你好');
const second = await runner.invoke({ input: '你好' });
console.log(first.value, second.value);
console.log(first.invocation.invocationId);增加预算与请求取消
配置 · Node.js
ts
import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
async *stream(messages: readonly { content: string }[]) {
yield '收到:' + messages.at(-1)!.content;
},
};
const runner = new ModelRunner({ provider, maxCalls: 2, maxInputChars: 4000,
maxOutputChars: 2000, callTimeoutMs: 15000,
execution: { signal: AbortSignal.timeout(20000) },
});
const result = await runner.invoke({ input: '你好', stageId: 'reply', maxOutputTokens: 600 });
console.log(result.value, runner.remainingCalls);js
import { ModelRunner } from '@jangts/agent-core/model';
const provider = {
async *stream(messages) {
yield '收到:' + messages.at(-1).content;
},
};
const runner = new ModelRunner({ provider, maxCalls: 2, maxInputChars: 4000,
maxOutputChars: 2000, callTimeoutMs: 15000,
execution: { signal: AbortSignal.timeout(20000) },
});
const result = await runner.invoke({ input: '你好', stageId: 'reply', maxOutputTokens: 600 });
console.log(result.value, runner.remainingCalls);