from typing import TypeVar

import anyio.to_thread
from anyio import CapacityLimiter
from starlette.concurrency import iterate_in_threadpool as iterate_in_threadpool  # noqa
from starlette.concurrency import run_in_threadpool as run_in_threadpool  # noqa
from starlette.concurrency import (  # noqa
    run_until_first_complete as run_until_first_complete,
)

_T = TypeVar("_T")


@asynccontextmanager

import java.time.Duration;
import java.util.concurrent.BlockingQueue;
import java.util.concurrent.CancellationException;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Future;
import java.util.concurrent.Semaphore;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

### Concurrency and Burgers { #concurrency-and-burgers }

This idea of **asynchronous** code described above is also sometimes called **"concurrency"**. It is different from **"parallelism"**.

**Concurrency** and **parallelism** both relate to "different things happening more or less at the same time".

But the details between *concurrency* and *parallelism* are quite different.

import java.util.concurrent.Callable;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Future;
import java.util.concurrent.TimeUnit;
import junit.framework.TestCase;
import org.jspecify.annotations.NullUnmarked;
import org.jspecify.annotations.Nullable;

/**
 * Unit test for {@link FakeTicker}.
 *
 * @author Jige Yu
 */
@GwtCompatible

import java.util.concurrent.Callable;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Future;
import java.util.concurrent.TimeUnit;
import junit.framework.TestCase;
import org.jspecify.annotations.NullUnmarked;
import org.jspecify.annotations.Nullable;

/**
 * Unit test for {@link FakeTicker}.
 *
 * @author Jige Yu
 */
@GwtCompatible

    public int getHistoryAssistantSummaryMaxChars() {
        return 800;
    }

    // --- Concurrency control ---

    /**
     * Gets the maximum number of concurrent requests to the LLM provider.
     * Default is 5. Override or configure via rag.llm.{provider}.max.concurrent.requests.
     *
     * @return the maximum concurrent requests
     */
    protected int getMaxConcurrentRequests() {

  }

  /**
   * Guides the allowed concurrency among update operations. Used as a hint for internal sizing. The
   * table is internally partitioned to try to permit the indicated number of concurrent updates
   * without contention. Because assignment of entries to these partitions is not necessarily
   * uniform, the actual concurrency observed may vary. Ideally, you should choose a value to

 * Map<K, V> syncMap = Collections.synchronizedMap(new LruHashMap<>(100));
 * </pre>
 * <p>
 * Alternatively, for high-concurrency scenarios, consider implementing a custom
 * LRU cache using {@link java.util.concurrent.ConcurrentHashMap} with an eviction strategy.
 * </p>
 *
 * @author koichik
 * @param <K> the key type
 * @param <V> the value type
 */
public class LruHashMap<K, V> extends LinkedHashMap<K, V> {

import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;
import java.util.concurrent.SynchronousQueue;
import java.util.concurrent.TimeoutException;
import junit.framework.AssertionFailedError;
import org.jspecify.annotations.NullUnmarked;
import org.jspecify.annotations.Nullable;

/**
 * A helper for concurrency testing. One or more {@code TestThread} instances are instantiated in a

# ==============================================================================
name: CI

on:
  pull_request:
    branches:
      - master
      - r2.**

permissions:
  contents: read

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
  # Don't cancel in-progress jobs for master branches.
  cancel-in-progress: ${{ github.ref != 'master' }}

jobs:
  #build-and-test-linux-x86-cpu: