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

			// the concurrency make sure we choose only the "start"
			// concurrency to be equal to the lowest number of
			// local disks per server.
			for _, localDiskCount := range globalEndpoints.NLocalDisksPathsPerPool() {
				if localDiskCount < concurrency {
					concurrency = localDiskCount
				}
			}

			// Any concurrency less than '4' just stick to '4' concurrent
			// operations for now to begin with.

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.

  }

  /**
   * 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

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

  }

  /**
   * 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

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

     * Stored as a long value representing milliseconds since epoch.
     * Used for audit trail and concurrency control.
     */
    @ValidateTypeFailure
    public Long updatedTime;

    /**
     * The version number of the duplicate host configuration for optimistic locking.
     * This field is required to prevent concurrent modification conflicts
     * by ensuring the configuration hasn't been modified by another process.
     */

    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() {