packages

@loop-engine/adapter-openai

Overview

@loop-engine/adapter-openai wraps the OpenAI API as a Loop Engine AI actor using response_format: { type: "json_object" } for structured output. Same governance model as adapter-anthropic — identical guard enforcement, same audit trail, drop-in pattern for multi-model loops.

Installation

1npm install @loop-engine/adapter-openai openai

Peer dependencies

1openai  ^4.0.0

Basic usage

1import OpenAI from 'openai'
2import { createOpenAIActorAdapter } from '@loop-engine/adapter-openai'
3import { createLoopSystem } from '@loop-engine/sdk'
4 
5const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY })
6 
7const adapter = createOpenAIActorAdapter(openai, {
8  modelId: 'gpt-4o',
9  confidenceThreshold: 0.75,
10})
11 
12const loopSystem = await createLoopSystem({ loops: [] })
13const aggregateId = 'procurement-1'
14 
15"cmt">// Get the AI actor's decision for the current loop state
16const { actor, decision } = await adapter.createSubmission({
17  loopId: 'procurement',
18  loopName: 'SCM Procurement',
19  currentState: 'pending_analysis',
20  availableSignals: [
21    {
22      signalId: 'submit_recommendation',
23      name: 'Submit Recommendation',
24      description: 'Submit a purchase order recommendation',
25      allowedActors: ['ai-agent', 'automation'],
26    },
27  ],
28  instruction: 'Analyze the demand data and recommend whether to issue a purchase order.',
29  evidence: { demandForecast: 0.89, currentStock: 42, reorderPoint: 50 },
30})
31 
32"cmt">// Submit to the runtime — guards evaluate after this point
33const result = await loopSystem.transition({
34  aggregateId,
35  signal: decision.signalId,
36  actor,
37  evidence: decision,
38})

Configuration reference

| Option | Type | Default | Description | |--------|------|---------|-------------| | modelId | string | gpt-4o | OpenAI model to use | | maxTokens | number | 1024 | Max tokens in response | | systemPrompt | string | — | Optional system prompt prepended to loop context | | confidenceThreshold | number | 0.7 | Minimum confidence required (0–1) |

What the adapter produces

The adapter returns an AIAgentActor with:

type: "ai-agent"
provider: "openai"
modelId — the model used
confidence — extracted from the model response
promptHash — SHA-256 of the prompt sent (for audit trail)

Guard enforcement note

The confidence guard runs at the runtime level — not inside the adapter. If you configure a confidence-threshold guard on the transition, the runtime will block the transition if the model's confidence falls below the threshold regardless of what the adapter returns.