TypeSafe AI Tracing (TypeScript)

Looking for Python? See the Python guide.

This module provides OpenInference instrumentation for the TypeSafe AI Node.js SDK (@typesafe-ai/sdk). Each TypeSafeClient.systemOne call is captured as an OpenInference LLM span with JSON input.value / output.value, model, and token usage. Requires Node.js 20+. client.models.list() is not instrumented.

Install

npm install --save @arizeai/phoenix-otel @arizeai/openinference-instrumentation-typesafe @typesafe-ai/sdk

Setup

Use the register function from @arizeai/phoenix-otel to connect to Phoenix, then register the TypeSafe instrumentation. Create the instrumentation.ts file:

import { register } from "@arizeai/phoenix-otel";
import { TypeSafeInstrumentation } from "@arizeai/openinference-instrumentation-typesafe";

// Initialize Phoenix tracing
export const provider = register({
  projectName: "typesafe-app",
  // If Phoenix is running elsewhere:
  // url: "https://your-phoenix.example.com",
  // apiKey: process.env.PHOENIX_API_KEY,
  // If using self-hosted Phoenix:
  // url: "http://localhost:6006",
});

// Set up TypeSafe SDK instrumentation
const instrumentation = new TypeSafeInstrumentation({
  tracerProvider: provider,
});

Registering the instrumentation this way patches @typesafe-ai/sdk at load time, which requires instrumentation.ts to run before the SDK is imported (CommonJS only). For ESM, bundlers, or when the SDK is imported first, call manuallyInstrument instead:

import * as TypeSafe from "@typesafe-ai/sdk";
import { TypeSafeInstrumentation } from "@arizeai/openinference-instrumentation-typesafe";

const instrumentation = new TypeSafeInstrumentation({ tracerProvider: provider });
instrumentation.manuallyInstrument(TypeSafe);

Usage

import "./instrumentation.js";
import { TypeSafeClient, choice } from "@typesafe-ai/sdk";

const client = new TypeSafeClient();
const { data, requestId } = await client
  .systemOne({
    state: { document: "I was charged twice. Please fix this ASAP." },
    questions: {
      category: choice("What is this ticket about?", {
        billing: null,
        technical: null,
        other: null,
      }),
    },
  })
  .withResponse();

console.log(data.answers.category, requestId);

Spans are exported in batches. In short-lived scripts, call await provider.forceFlush() before the process exits so all spans are delivered to Phoenix.

Observe

With instrumentation enabled, each systemOne call shows up in Phoenix as an LLM span containing:

The full state and questions sent to TypeSafe as input.value (JSON)
The typed answers returned as output.value (JSON)
Model name and token usage, when reported by the SDK

Configuration

Pass traceConfig to mask sensitive request/response payloads before they leave your process:

const instrumentation = new TypeSafeInstrumentation({
  tracerProvider: provider,
  traceConfig: {
    hideInputs: true,
    hideOutputs: true,
  },
});

See the package README for the full list of traceConfig masking options and the SDK compatibility table.

Developer Tools

MCP

LLM Providers

TypeScript

Python

Java

Platform

Sandboxes

Evaluation Integrations

Coding Agents

TypeSafe AI Tracing (TypeScript)

Install

Setup

Usage

Observe

Configuration

Resources

​Install

​Setup

​Usage

​Observe

​Configuration

​Resources

Install

Setup

Usage

Observe

Configuration

Resources