normalizeDiagnosticEvent

CORE · function · Runtime value

Validate a persisted diagnostic record and return a detached copy.

Persisted data is untrusted, so the envelope version, event type, identity, ordering and the bounded sub-step shape are checked; the payload itself is not interpreted. The copy is deep cloned, so a store cannot hand back a record that later shares structure with the caller.

Import

TypeScript

import { normalizeDiagnosticEvent } from '@jangts/agent-core/diagnostics';

JavaScript

import { normalizeDiagnosticEvent } from '@jangts/agent-core/diagnostics';

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

Definition

Call

normalizeDiagnosticEvent(input: unknown): import("../structs/diagnostics.js").CoreDiagnosticRecord

Validate a persisted diagnostic record and return a detached copy.

Persisted data is untrusted, so the envelope version, event type, identity, ordering and the bounded sub-step shape are checked; the payload itself is not interpreted. The copy is deep cloned, so a store cannot hand back a record that later shares structure with the caller.

Parameter	Type	Passing	Description
input	unknown	Required	—

Returns: CoreDiagnosticRecord.

Return value structure

Field	Type	Required	Description
version	2	Required	Read-only. Envelope version this record was written with.
eventId	string	Required	Read-only. See the type definition and usage context.
type	keyof CoreEventPayloads	Required	Read-only. See the type definition and usage context.
producerSequence	number	Required	Read-only. Per-producer monotonic sequence; at least 1.
occurredAtMs	number	Required	Read-only. See the type definition and usage context.
payload	unknown	Required	Read-only. Unvalidated payload; only the envelope above is checked during normalization.
usedModel	boolean | undefined	Optional	Read-only. See the type definition and usage context.
subSteps	readonly RecordedSubStep[]	Required	Read-only. See the type definition and usage context.
subStepsDropped	number	Required	Read-only. See the type definition and usage context.
subStepsTruncated	boolean	Required	Read-only. See the type definition and usage context.
runId	string	Required	Read-only. Root run id shared by every fact of one logical run.
spanId	string	Required	Read-only. Span that produced the fact.
parentSpanId	string | undefined	Optional	Read-only. Enclosing span; absent for a root span.
invocationId	string | undefined	Optional	Read-only. Invocation that produced the fact, when the fact belongs to one.
parentInvocationId	string | undefined	Optional	Read-only. Enclosing invocation, when one invocation triggers another.
nodeRole	"invocation" | "workflow-node" | "workflow-boundary" | "loop-step" | undefined	Optional	Read-only. Role the emitting span plays in the execution graph.
agentId	string | undefined	Optional	Read-only. App-owned agent identity.
branchId	string | undefined	Optional	Read-only. App-owned branch identity.
agentVersionId	string | undefined	Optional	Read-only. App-owned immutable version identity of the agent definition.
parentBranchId	string | undefined	Optional	Read-only. Branch this branch was forked from, when applicable.
parentAgentVersionId	string | undefined	Optional	Read-only. Version of the parent branch at the fork point.
forkPointId	string | undefined	Optional	Read-only. App-owned fork marker shared by the forked branch and its origin.
workflowInvocationId	string | undefined	Optional	Read-only. Workflow invocation the fact belongs to.
workflowNodeId	string | undefined	Optional	Read-only. Workflow node invocation the fact belongs to.
definitionKind	string | undefined	Optional	Read-only. Kind of the workflow/agent definition that dispatched the node.
definitionId	string | undefined	Optional	Read-only. Id of that definition.
definitionRevision	string | undefined	Optional	Read-only. Revision of that definition; distinguishes executions of different definition states.
nodeId	string | undefined	Optional	Read-only. Node id inside the workflow.
nodeName	string | undefined	Optional	Read-only. Human-readable node name.
nodeKind	string | undefined	Optional	Read-only. Node kind as declared by the App.
nodeDescription	string | undefined	Optional	Read-only. Optional node description for diagnostics display.
stageId	string | undefined	Optional	Read-only. Model stage that produced the fact.
modelId	string | undefined	Optional	Read-only. Model binding used, when the fact concerns a model call.

Examples

• Process observation and node reports: The App subscribes to Core execution facts; nodes report their own usedModel and use an instance sub-logger to record intent first and then results, while the Loop owns identity and logging.

Observe the nodes and model events a task passes through

Beginner · 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, execution: {
  observe: { event(event) { console.log(event.type, event.eventId); } },
} });
console.log(await agent.run({ name: 'Ivan' }));

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, execution: {
        observe: { event(event) { console.log(event.type, event.eventId); } },
    } });
console.log(await agent.run({ name: 'Ivan' }));

Report a business stage while the node executes

Configuration · Node.js

The node only reports facts it knows; Core owns node identity and execution association.

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: '生成问候', startsRound: true,
  run(state, context) {
    context.report({ payload: { phase: 'formatting' } });
    return { answer: '你好，' + state.name };
  }, routes: [route.deliver('answer')],
}] });
const agent = new AgentCoreEngine({ workflow, execution: {
  observe: { event(event) { console.log(event.type); } },
} });
console.log(await agent.run({ name: 'Ivan' }));

JavaScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
const workflow = defineWorkflow({ id: 'greeting', nodes: [{
            id: 'greet', description: '生成问候', startsRound: true,
            run(state, context) {
                context.report({ payload: { phase: 'formatting' } });
                return { answer: '你好，' + state.name };
            }, routes: [route.deliver('answer')],
        }] });
const agent = new AgentCoreEngine({ workflow, execution: {
        observe: { event(event) { console.log(event.type); } },
    } });
console.log(await agent.run({ name: 'Ivan' }));

Record an async plan first, then fill in the result

Configuration · Node.js

A scoped logger binds the group and only fixes its own writes; readAll exposes the full ledger. Every fix appends an independent record linked to its original write, without logger submission.

TypeScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
type State = { result?: string };
const workflow = defineWorkflow<State, string>({ id: 'prepare', nodes: [{
  id: 'prepare', description: '准备资料', async run(_, context) {
    const subs = context.createSubFlowLogger();
    const read = subs.fork('material-read');
    const id = read.write({ name: '读取资料', kind: 'read', type: 'material.read' });
    read.fix(id, { status: 'running' });
    const result = await Promise.resolve('已准备');
    read.fix(id, { status: 'success', usedModel: false, payload: { result } });
    context.report({ usedModel: false });
    console.log(read.readAll());
    return { result };
  }, routes: [route.deliver('result')],
}] });
const agent = new AgentCoreEngine({ workflow, execution: { observe: {
  accepts: ({ event, content }) => content === 'metadata' || event === 'node.progress',
  event(event) { if (event.type === 'node.progress') console.log(event.payload.subStep, event.subSteps); },
} } });
console.log(await agent.run({}));

JavaScript

import { AgentCoreEngine, defineWorkflow, route } from '@jangts/agent-core/engine';
const workflow = defineWorkflow({ id: 'prepare', nodes: [{
            id: 'prepare', description: '准备资料', async run(_, context) {
                const subs = context.createSubFlowLogger();
                const read = subs.fork('material-read');
                const id = read.write({ name: '读取资料', kind: 'read', type: 'material.read' });
                read.fix(id, { status: 'running' });
                const result = await Promise.resolve('已准备');
                read.fix(id, { status: 'success', usedModel: false, payload: { result } });
                context.report({ usedModel: false });
                console.log(read.readAll());
                return { result };
            }, routes: [route.deliver('result')],
        }] });
const agent = new AgentCoreEngine({ workflow, execution: { observe: {
            accepts: ({ event, content }) => content === 'metadata' || event === 'node.progress',
            event(event) { if (event.type === 'node.progress')
                console.log(event.payload.subStep, event.subSteps); },
        } } });
console.log(await agent.run({}));

Related policy source

• Shared execution fact source and consumption isolation
• Sub-step statuses and their progression

Related definitions

• CoreDiagnosticRecord