> ## Documentation Index
> Fetch the complete documentation index at: https://docs.captar.aurat.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Wrapping

> How wrapOpenAI keeps your existing client while attaching policy, estimation, spend reconciliation, and spans.

# OpenAI Wrapping

`wrapOpenAI()` preserves the client shape you already use, then inserts Captar's
runtime control steps around each model request.

The main benefit is adoption speed: you keep your existing OpenAI integration,
but you get budget checks, policy enforcement, trace spans, and usage
reconciliation without rebuilding your request layer.

```ts theme={null}
const openai = captar.wrapOpenAI(new OpenAI({ apiKey }), { session });

await openai.responses.create({
  model: "gpt-4.1-mini",
  input: "Summarize this support thread.",
  max_output_tokens: 180,
});
```

## What Captar adds

* Model and retry validation against call policy
* Estimated spend checks before execution
* Timeout-aware provider execution
* Request spans with provider, model, method, and request metadata
* Spend reconciliation after the provider response returns

## Good wrapping habits

* Wrap the client once, near your app runtime.
* Pass the active session explicitly instead of relying on hidden globals.
* Keep request metadata descriptive enough to debug a bad trace later.
* Use the same wrapper for jobs, API routes, and background tasks when possible.

## Call policy example

```ts theme={null}
policy: {
  call: {
    allowedModels: ["gpt-4.1-mini"],
    maxEstimatedCostUsd: 0.35,
    maxOutputTokens: 300,
    retriesCeiling: 1,
    timeoutMs: 15_000,
  },
}
```

<Callout type="warning" title="Current provider scope">
  The v1 docs and SDK surface are optimized for OpenAI and OpenAI-compatible
  request flows. Do not treat this as a general multi-provider abstraction yet.
</Callout>