Integrations

Google Gemini

Archetype: AI (Actor) — returns AIAgentActor + AIActorDecision for governed engine.transition(...) submission.

What it does

@loop-engine/adapter-gemini wraps Gemini API calls as Loop Engine actor submissions. It returns structured decisions for runtime guard enforcement, preserving attribution and evidence on every transition.

Quick setup

1. Install

   ⧉

   1npm install @loop-engine/adapter-gemini @google/generative-ai

2. Create the actor

   ⧉

   1import { createGeminiActorAdapter } from "@loop-engine/adapter-gemini";
   2 
   3const adapter = createGeminiActorAdapter(process.env.GOOGLE_AI_API_KEY!, {
   4  modelId: "gemini-1.5-pro"
   5});

3. Submit to a loop transition

   ⧉

   1const { actor, decision } = await adapter.createSubmission({
   2  loopId: "procurement",
   3  loopName: "SCM Procurement",
   4  currentState: "pending_analysis",
   5  availableSignals: [{ signalId: "submit_recommendation", name: "Submit Recommendation", allowedActors: ["ai-agent"] }],
   6  instruction: "Analyze demand data and recommend a purchase order.",
   7  evidence: { demandForecast: 0.93, currentStock: 36 }
   8});
   9 
   10await loopSystem.engine.transition({
   11  aggregateId: "procurement-1",
   12  transitionId: decision.transitionId,
   13  actor,
   14  evidence: decision
   15});

How it works

1. Formats context using Loop Engine actor prompt shape
2. Calls Gemini generate endpoint
3. Parses decision JSON and validates fields
4. Returns actor + decision for runtime guard evaluation

Configuration reference

| Option | Type | Default | Description | |---|---|---|---| | modelId | string | gemini-1.5-pro | Gemini model (gemini-1.5-flash, gemini-2.0-flash) | | maxOutputTokens | number | 1024 | Max output tokens | | systemPrompt | string | — | Optional system prompt prepended to loop context | | | | | Minimum confidence required (0–1) |