TypeScript SDK

Highflame TypeScript SDK overview with an ordered path for setup, Shield wrappers, low-level client usage, and advanced topics.

JavaScript and TypeScript SDK for the Highflame guardrails service. The TypeScript package gives you two main ways to integrate Shield:

• Shield wrappers for the fastest path around prompts, tools, and model outputs

• the Highflame client when you want full request and response control

Read This Section in Order

1. Getting Started: install @highflame/sdk, authenticate, and wire up your first guarded function

2. Shield Wrappers: choose the right wrapper and configure it correctly

3. Low-Level Client: use client.guard.*, client.detect.*, client.detectors.*, and client.debug.*

4. Advanced Topics: debugging, optimization, streaming, context objects, sessions, and runtime options

Choosing the Right API

I want to...	Use
Guard a prompt before my LLM runs	shield.prompt(fn)
Guard a tool call before it executes	shield.tool(fn)
Guard a tool's return value before it's used	shield.toolResponse(fn)
Guard the LLM's output before returning to the caller	shield.modelResponse(fn)
Guard a file read or write	shield.wrap({ contentType: "file", action: "write_file" })(fn)
Evaluate with full control and inspect the full response	client.guard.evaluate()
Evaluate a prompt with minimal code	client.guard.evaluatePrompt()
Evaluate a tool call with minimal code	client.guard.evaluateToolCall()
Run detectors without Cedar policy evaluation	client.detect.run()
Observe traffic without blocking	pass mode: "monitor"
Understand why a decision was made	pass explain: true
See per-detector breakdowns	pass debug: true
Only run detectors referenced by active policies	pass optimize: true

BlockedError is only thrown by Shield wrappers. Direct client.guard.evaluate() calls always resolve, even when the decision is deny.

Create one Highflame client per process, not per request. The client maintains an internal token cache.

Framework Support

The TypeScript SDK ships first-class framework integrations for LangGraph, CrewAI, AWS Strands, and Azure AI Foundry — matching the Python SDK. Import them from their subpaths:

import { HighflameMiddleware } from "@highflame/sdk/integrations/langgraph";
import { HighflameCrewHooks } from "@highflame/sdk/integrations/crewai";
import { HighflameStrandsHooks } from "@highflame/sdk/integrations/strands";
import { HighflameFoundryMiddleware } from "@highflame/sdk/integrations/foundry";

See the Framework Integrations reference for full usage. For custom integrations or call sites not covered by a framework adapter, integrate Shield at your model and tool boundaries with Shield wrappers or direct client.guard.* calls.