ModelCallRequest

CORE · type · Type contract

One model call request. The input shape selects prompt mode or message mode.

Import

TypeScript

import type { ModelCallRequest } from '@jangts/agent-core/model';

JavaScript

/** @typedef {import('@jangts/agent-core/model').ModelCallRequest} ModelCallRequest */

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

Definition

Type: ModelCallRequest<Transport>

Type parameters

Type parameter	Constraint	Default type
Transport	—	string

Union branch structure

Optional shapes of ModelCallRequest: choose one shape; required fields for each branch are listed separately.

Branch 1

Field	Type	Required	Description
logger	SubFlowLogger | undefined	Optional	Read-only. Record this call in the supplied logger; omission adds no sub-flow record.
signal	AbortSignal | undefined	Optional	Read-only. Additional cancellation can shorten, never replace, the Runner lifetime.
diagnostics	DiagnosticContext | undefined	Optional	Read-only. Parent observation scope for this invocation; never changes execution budget or signal.
prepared	PreparedModelCall<unknown> | undefined	Optional	Read-only. Reuse a prepared call; its stage, transport and output reservation then take precedence.
maxOutputTokens	number | undefined	Optional	Read-only. See the type definition and usage context.
stageId	string | undefined	Optional	Read-only. See the type definition and usage context.
transport	Transport | undefined	Optional	Read-only. See the type definition and usage context.
input	string	Required	See the type definition and usage context.
instructions	string | undefined	Optional	See the type definition and usage context.

Branch 2

Field	Type	Required	Description
logger	SubFlowLogger | undefined	Optional	Read-only. Record this call in the supplied logger; omission adds no sub-flow record.
signal	AbortSignal | undefined	Optional	Read-only. Additional cancellation can shorten, never replace, the Runner lifetime.
diagnostics	DiagnosticContext | undefined	Optional	Read-only. Parent observation scope for this invocation; never changes execution budget or signal.
prepared	PreparedModelCall<unknown> | undefined	Optional	Read-only. Reuse a prepared call; its stage, transport and output reservation then take precedence.
maxOutputTokens	number | undefined	Optional	Read-only. See the type definition and usage context.
stageId	string | undefined	Optional	Read-only. See the type definition and usage context.
transport	Transport | undefined	Optional	Read-only. See the type definition and usage context.
input	readonly ModelMessage[] | BuiltContext | ContextPlan	Required	See the type definition and usage context.
instructions	undefined	Optional	See the type definition and usage context.

Examples

• ModelRunner: input can be shortened while the output contract stays the same: Execute one model interaction through the real Provider port and return a value plus the invocation for this call.

Two inputs for the same output

Beginner · Node.js

TypeScript

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);

JavaScript

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);

Add budget and request cancellation

Configuration · Node.js

TypeScript

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);

JavaScript

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);

Related policy source

• Core default budget values

Related definitions

• BuiltContext
• ContextPlan
• DiagnosticContext
• ModelMessage
• PreparedModelCall
• SubFlowLogger