*
     * @param request the chat request containing messages and parameters
     * @return the chat response from the LLM
     * @throws LlmException if an error occurs during the request
     */
    LlmChatResponse chat(LlmChatRequest request);

    /**
     * Performs a streaming chat completion request.
     * The callback is invoked for each chunk of the response.
     *

     *
     * @param request the chat request
     * @return the chat response
     * @throws LlmException if too many concurrent requests or interrupted
     */
    protected LlmChatResponse chatWithConcurrencyControl(final LlmChatRequest request) {
        if (concurrencyLimiter == null) {
            return chat(request);
        }
        if (logger.isDebugEnabled()) {

     *
     * @param request the chat request
     * @return the chat response
     * @throws LlmException if LLM is not available or an error occurs
     */
    public LlmChatResponse chat(final LlmChatRequest request) {
        final long startTime = System.currentTimeMillis();
        final String llmType = getLlmType();
        if (logger.isDebugEnabled()) {

import org.codelibs.fess.entity.SearchRequestParams;
import org.codelibs.fess.helper.MarkdownRenderer;
import org.codelibs.fess.llm.ChatIntent;
import org.codelibs.fess.llm.IntentDetectionResult;
import org.codelibs.fess.llm.LlmChatResponse;
import org.codelibs.fess.llm.LlmClient;
import org.codelibs.fess.llm.LlmClientManager;
import org.codelibs.fess.llm.LlmException;
import org.codelibs.fess.llm.LlmMessage;
import org.codelibs.fess.llm.LlmStreamCallback;

            addIntentHistory(request, history);
        }

        // Implement abstract methods

        @Override
        public LlmChatResponse chat(final LlmChatRequest request) {
            // Capture the full request and user message for verification
            lastChatRequest = request;
            for (final LlmMessage msg : request.getMessages()) {