* Additionally, LiteRT code base will decouple from TensorFlow repository, and `tf.lite` will be removed in future TensorFlow Python package. More details to follow in future release notes.

The normal (default) process, is as follows.

A `FastAPI` application (instance) has an `.openapi()` method that is expected to return the OpenAPI schema.

As part of the application object creation, a *path operation* for `/openapi.json` (or for whatever you set your `openapi_url`) is registered.

It just returns a JSON response with the result of the application's `.openapi()` method.

### Threads

#### Application's calling thread

The application-layer must block on writing I/O. We can't return from a write until we've pushed its bytes onto the socket. Otherwise, if the write fails we are unable to deliver its IOException to the application. We would have told the application layer that the write succeeded, but it didn't!

    #  The settings for Application Behavior.
    #  Elements of this map are as below:
    #   o isApplicationBehaviorProject: (NotRequired - Default false)
    #    Does the project is for application behaviors?
    #    This property is a main signal for Application Behavior.
    #    Other properties (for Application Behavior) work when this is true.

### Choosing between application and network interceptors

Each interceptor chain has relative merits.

**Application interceptors**

 * Don't need to worry about intermediate responses like redirects and retries.
 * Are always invoked once, even if the HTTP response is served from the cache.

  ) {
  }

  /**
   * Invoked when data from the response body is first available to the application.
   *
   * This is typically invoked immediately before bytes are returned to the application. If the
   * response body is empty this is invoked immediately before returning that to the application.
   *
   * If the application closes the response body before attempting a read, this is invoked at the
   * time it is closed.
   *

     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.
     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.
     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.

     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.
     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.
     <span style="background-color:#007166"><font color="#D3D7CF"> INFO </font></span>  Waiting for application startup.

import okhttp3.internal.platform.Platform
import okhttp3.internal.threadName
import okio.AsyncTimeout
import okio.Timeout

/**
 * Bridge between OkHttp's application and network layers. This class exposes high-level application
 * layer primitives: connections, requests, responses, and streams.
 *
 * This class supports [asynchronous canceling][cancel]. This is intended to have the smallest

                                "content": {"application/json": {"schema": {}}},
                            },
                            "422": {
                                "description": "Validation Error",
                                "content": {
                                    "application/json": {
                                        "schema": {