/** The HTTP client used for API communication. */
    protected CloseableHttpClient httpClient;

    /** Cached availability status of the LLM provider. */
    protected volatile Boolean cachedAvailability = null;

    /** The scheduled task for periodic availability checks. */
    protected TimeoutTask availabilityCheckTask;

    /** Semaphore for limiting concurrent LLM requests. Initialized lazily in init(). */

     */
    public boolean isAvailable() {
        final boolean available = llmClientManager.available();
        if (logger.isTraceEnabled()) {
            logger.trace("[RAG] ChatClient availability check. available={}", available);
        }
        return available;
    }

    /**
     * Performs a chat request with RAG.
     *
     * @param sessionId the session ID (can be null for new sessions)

     *
     * * **Unreachable IP addresses.** If the URL's host has multiple IP addresses,
     *   failure to reach any individual IP address doesn't fail the overall request. This can
     *   increase availability of multi-homed services.
     *
     * * **Stale pooled connections.** The [ConnectionPool] reuses sockets
     *   to decrease request latency, but these connections will occasionally time out.
     *

    * This ensures that attachment and detachment of volumes is independent of any single nodes’ availability. Meaning, if a node or kubelet becomes unavailable for any reason, the volumes attached to that node will be detached so they are free to be attached to other nodes.

                    return false;
                }
            }

            return true;
        } catch (Exception e) {
            System.err.println("Docker availability check failed: " + e.getMessage());
            return false;
        }
    }