Function print_eval_specific

ds4_help.c:356–370

    para(fp, c, "Model endpoint aliases include deepseek-v4-flash and deepseek-v4-pro; both serve the loaded GGUF.");
    fputc('\n', fp);
}

static void print_server_thinking(FILE *fp, const help_colors *c) {
    title(fp, c, "Server Thinking Defaults");
    para(fp, c, "DeepSeek-compatible chat requests default to high-effort thinking.");
    para(fp, c, "reasoning_effort=max or output_config.effort=max requests Think Max.");
    para(fp, c, "Think Max requires --ctx >= 393216; smaller contexts use high.");
    para(fp, c, "thinking={type:disabled}, think=false, or model=deepseek-chat selects non-thinking mode.");
    para(fp, c, "In thinking mode, client sampling knobs are ignored like the official API.");
    fputc('\n', fp);
}

static void print_kv_cache(FILE *fp, const help_colors *c) {
    title(fp, c, "Disk KV Cache");
    opt(fp, c, "--kv-disk-dir DIR", "Enable disk KV checkpoints in DIR.");
    opt(fp, c, "--kv-disk-space-mb N", "Disk budget. Default when enabled: 4096");
    opt(fp, c, "--kv-cache-min-tokens N", "Do not save/load checkpoints shorter than N. Default: 512");
    opt(fp, c, "--kv-cache-cold-max-tokens N", "Save cold first prompts up to N tokens. 0 disables. Default: 30000");