*
 * In addition to low-level chat operations, this interface defines
 * high-level RAG workflow methods that allow each provider to optimize
 * prompt construction, parameter tuning, and response parsing.
 */
public interface LlmClient {

    /**
     * Performs a chat completion request.
     *
     * @param request the chat request containing messages and parameters
     * @return the chat response from the LLM

automation tool designed to handle everything from large, multi-project enterprise builds to quick development tasks across various languages. Gradle’s modular, performance-oriented architecture seamlessly integrates with development environments, making it a go-to solution for building, testing, and deploying applications on **Java**, **Kotlin**, **Scala**, **Android**, **Groovy**, **C++**, and **Swift**.

> For a comprehensive overview, please visit the [official Gradle project homepage...

        context.addHighlightedQuery(text);
        return QueryBuilders.wildcardQuery(urlField, queryString).boost(boost);
    }

    /**
     * Converts a term query ending with asterisk to a prefix query.
     *
     * @param fessConfig the Fess configuration
     * @param context the query context
     * @param termQuery the term query to convert

      },
      {
        "subprojects": [
          "base-services-groovy",
          "build-cache-packaging",
          "build-operations",
          "build-state",
          "daemon-services",
          "hashing",
          "precondition-tester",
          "report-rendering",
          "service-registry-builder",
          "test-suites-base",
          "testing-jvm"
        ],
        "parallelizationMethod": {

This can save everyone a lot of time and frustration.

For any non-trivial change, we need to be able to answer these questions:

* Why is this change done? What's the use case?
* For user-facing features, what will the API look like?
* What test cases should it have? What could go wrong?
* How will it roughly be implemented? We'll happily provide code pointers to save you time.

            assertNotNull(results);
        }
    }

    /**
     * Test with documents having duplicate IDs across searchers.
     */
    @Test
    public void test_duplicateDocumentIds() throws Exception {
        try (RankFusionProcessor processor = new RankFusionProcessor()) {

        }
    }

    @Test
    public void test_setError_withNullException() {
        // Test setError with null exception
        // Note: WebApiException constructor calls e.getMessage() on null exception, causing NullPointerException
        try {
            WebApiUtil.setError(500, (Exception) null);
            fail("setError should throw NullPointerException when passed null exception");
        } catch (NullPointerException e) {

        protected boolean prevPage;
        /**
         * The starting record number for the current page of search results.
         */
        protected long startRecordNumber;
        /**
         * The ending record number for the current page of search results.
         */
        protected long endRecordNumber;
        /**
         * The list of page numbers for pagination.
         */

            <option value="$PROJECT_DIR$/platforms/core-execution/file-watching" />
            <option value="$PROJECT_DIR$/platforms/core-execution/hashing" />
            <option value="$PROJECT_DIR$/platforms/core-execution/persistent-cache" />
            <option value="$PROJECT_DIR$/platforms/core-execution/request-handler-worker" />

        }
        getAvailableClient().streamGenerateAnswer(userMessage, documents, history, callback);
    }

    /**
     * Generates a response asking user for clarification.
     *
     * @param userMessage the user's message
     * @param history the conversation history
     * @param callback the streaming callback
     * @throws LlmException if LLM is not available