Anthropic / Claude

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

What it does

@loop-engine/adapter-anthropic wraps the Anthropic Messages API as a Boss AI actor. The adapter calls Claude with loop context, parses the structured response, and returns an AIAgentActor plus AIActorDecision ready for runtime submission. Guards run after the adapter returns — Claude cannot bypass them.

Quick setup

1. Install

   ⧉

   1npm install @loop-engine/adapter-anthropic
   2npm install @anthropic-ai/sdk

2. Create the actor

   ⧉

   1import { createAnthropicActorAdapter } from "@loop-engine/adapter-anthropic";
   2 
   3const adapter = createAnthropicActorAdapter({
   4  apiKey: process.env.ANTHROPIC_API_KEY!,
   5  model: "claude-opus-4-6"
   6});

3. Submit to a loop transition

   ⧉

   1"cmt">// @no-typecheck
   2const { actor, decision } = await adapter.createSubmission({
   3  loopId: "procurement",
   4  loopName: "SCM Procurement",
   5  currentState: "pending_analysis",
   6  availableSignals: [
   7    {
   8      signalId: "submit_recommendation",
   9      name: "Submit Recommendation",
   10      allowedActors: ["ai-agent"]
   11    }
   12  ],
   13  instruction: "Analyze demand data and recommend a purchase order.",
   14  evidence: { demandForecast: 0.91, currentStock: 38 }
   15});
   16 
   17await loopSystem.engine.transition({
   18  aggregateId: "procurement-1",
   19  transitionId: decision.transitionId,
   20  actor,
   21  evidence: decision
   22});

How it works

1. Builds a structured prompt from LoopActorPromptContext
2. Calls client.messages.create(...) with loop context
3. Parses JSON and validates signalId + confidence
4. Computes SHA-256 promptHash
5. Returns AIAgentActor (provider: "anthropic") + AIActorDecision
6. Caller submits to runtime and guards evaluate after submission

Configuration reference

| Option | Type | Default | Description | |---|---|---|---| | modelId | string | claude-opus-4-6 | Anthropic model ID | | 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) |

Troubleshooting

• ActorDecisionError: INVALID_SIGNAL — Model returned a signal not present in availableSignals; tighten instruction language around allowed signals.
• ActorDecisionError: INVALID_CONFIDENCE — Confidence was outside 0–1; include "confidence must be between 0 and 1" in systemPrompt.
• ActorDecisionError: API_ERROR — Check ANTHROPIC_API_KEY and model ID validity.

Related

• AI as Actor
• Confidence + Evidence
• Human Approval Gates
• OpenAI adapter, Grok adapter, Gemini adapter