/**
     * Applies per-prompt-type parameters to the request from configuration.
     * Reads temperature, max.tokens, and thinking.budget from config using
     * the pattern: {configPrefix}.{promptType}.{paramName}
     *
     * Subclasses can override to add provider-specific parameters (e.g. reasoning_effort, top_p).
     *
     * @param request the LLM chat request