logger.warn("[LLM] Request interrupted while waiting for concurrency permit. name={}", getName());
            Thread.currentThread().interrupt();
            throw new LlmException("Request interrupted", LlmException.ERROR_TIMEOUT);
        }
    }

    /**
     * Executes a streaming chat request with concurrency control via Semaphore.
     *
     * @param request the chat request
     * @param callback the streaming callback