/** Error code for service unavailable (HTTP 502/503). */
    public static final String ERROR_SERVICE_UNAVAILABLE = "service_unavailable";

    /** Error code for request timeout. */
    public static final String ERROR_TIMEOUT = "timeout";

    /** Error code for context length exceeded. */
    public static final String ERROR_CONTEXT_LENGTH_EXCEEDED = "context_length_exceeded";

    /** Error code for model not found. */

            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