Skip to main content

​
Instrument an LLM client

instrumentLLM() returns a proxy with the same public shape as the original client. Known generation methods are captured automatically. 
const openai = lynx.instrumentLLM(new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
}));

await lynx.run("SupportAgent", async () => {
  const response = await openai.chat.completions.create({
    model: "gpt-4.1-mini",
    messages: [{ role: "user", content: "Summarize this ticket" }],
  });

  lynx.decision("summarized ticket for support triage");
  return response;
});
Lynx records model metadata, latency, token usage when available, span IDs, and errors.

​
Instrument a tool

Use instrumentTool() for normal telemetry. Use guardTool() when you also need a policy check. 
const searchOrders = lynx.instrumentTool(
  "search_orders",
  async ({ userId }: { userId: string }) => {
    return db.orders.findMany({ where: { userId } });
  },
  {
    toolVersion: "2026-06-01",
    sideEffect: false,
    riskLevel: "LOW",
  },
);

await lynx.run("SupportAgent", async () => {
  const orders = await searchOrders({ userId: "usr_123" });
  lynx.context("orders", orders);
});

​
Custom LLM interception

If your client uses non-standard method names, pass a custom rule. 
const model = lynx.instrumentLLM(customClient, {
  modelLabel: "custom.llm",
  customRule: {
    isTargetMethod: (path) => path.join(".") === "responses.generate",
    extractInput: (args) => args[0],
    extractOutput: (result) => result.text,
    extractUsage: (result) => result.usage,
  },
});