ExecutionContext

CORE · interface · Type contract

Required execution facts available inside a running call.

Import

TypeScript

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

JavaScript

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

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

Definition

interface ExecutionContext

Field structure

Field	Type	Required	Description
logger	SubFlowLog | undefined	Optional	Read-only. Explicit optional recorder for this operation; never inferred from diagnostics.
signal	AbortSignal	Required	Read-only. Non-optional cancellation signal; never undefined once execution has started.
diagnostics	DiagnosticContext | undefined	Optional	Read-only. Diagnostic scope of the enclosing call, when recording is enabled.

Examples

• Agent: run first, then bind tools and dependencies step by step: The Engine executes a bounded loop; after a Workflow is bound, each run only receives the data that changed in state.
• 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.
• Actual request measurement and same-call preparation snapshot: Use prepare only when context must be handled ahead of time; multiple measurements and the final send reuse the same transport preparation.
• Child execution: isolated records, shared ancestor quota: A child Runner does not inherit conversation or the output receiver, but cannot bypass parent budget, cancellation, or deadlines.
• SSE, JSON frames, and bounded event streams: Reuse transport mechanics while preserving cancellation and backpressure; protocol parsing and business validation remain separate.
• Context policy: validate, reduce, and audit: Support provides replaceable policy implementations while Core keeps the final input contract and budget checks.
• Compressors and selectors: recommended implementations and custom algorithms: Bind prompts, output parsing, and algorithms as handlers; model I/O goes through callModel of the same request.
• Support: the aggregate entry for recommended usage: Support aggregates recommended construction, policies, and same-source configuration generation; Core execution does not depend on this namespace.
• Presentation: field ownership and final output: The model fills only the fields it is assigned; fixed text, bound values, and semantic keys are owned by the program.
• Reply events: text chunks and bubble boundaries: Turn an accepted reply into awaitable text/bubble events while preserving cancellation and delivery backpressure.

A single ordinary step is enough to run

Beginner · Node.js

TypeScript

import { AgentCoreEngine } from '@jangts/agent-core/engine';

const agent = new AgentCoreEngine<string>();
const answer = await agent.run(() => ({ type: 'complete', value: '你好，Core' }));
console.log(answer);

JavaScript

import { AgentCoreEngine } from '@jangts/agent-core/engine';
const agent = new AgentCoreEngine();
const answer = await agent.run(() => ({ type: 'complete', value: '你好，Core' }));
console.log(answer);

Add an explicit Workflow and still call run

Configuration · Node.js

TypeScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';

type State = { name: string; answer?: string };
const workflow = defineWorkflow<State, string>({
  id: 'greeting',
  nodes: [{
    id: 'greet', description: '根据本次姓名生成问候', startsRound: true,
    run: state => ({ answer: '你好，' + state.name }),
    routes: [route.deliver('answer')],
  }],
});

const agent = new AgentCoreEngine({ workflow });
console.log(await agent.run({ name: 'Ivan' }));
console.log(await agent.run({ name: '访客' }));

JavaScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
const workflow = defineWorkflow({
    id: 'greeting',
    nodes: [{
            id: 'greet', description: '根据本次姓名生成问候', startsRound: true,
            run: state => ({ answer: '你好，' + state.name }),
            routes: [route.deliver('answer')],
        }],
});
const agent = new AgentCoreEngine({ workflow });
console.log(await agent.run({ name: 'Ivan' }));
console.log(await agent.run({ name: '访客' }));

Related policy source

• Execution implementation of the bounded loop, commit, and cancellation
• Core default budget values
• Same-call preparation and real input measurement
• Single-slot handoff and backpressure in event streams
• Real scheduling catalog for policies and reduction operations
• Default selection instruction and excerpt range
• Compression request and the real callModel contract
• Field ownership, model Schema, and composition
• Reply format declarations, shared checks, and bubble normalization
• Chunking, bubbles, and total duration limit

Related definitions

• DiagnosticContext
• SubFlowLog