Method init_routes

subprojects/llama.cpp/tools/server/server-context.cpp:3173–3895

}

void server_routes::init_routes() {
    // IMPORTANT: all lambda functions must start with create_response()
    // this is to ensure that the server_res_generator can handle sleeping case correctly

    this->get_health = [this](const server_http_req &) {
        // error and loading states are handled by middleware
        auto res = create_response(true);

        // this endpoint can be accessed during sleeping
        // the next LOC is to avoid someone accidentally use ctx_server
        bool ctx_server; // do NOT delete this line
        GGML_UNUSED(ctx_server);

        res->ok({{"status", "ok"}});
        return res;
    };

    this->get_metrics = [this](const server_http_req & req) {
        auto res = create_response();
        if (!params.endpoint_metrics) {
            res->error(format_error_response("This server does not support metrics endpoint. Start it with `--metrics`", ERROR_TYPE_NOT_SUPPORTED));
            return res;
        }

        // request slots data using task queue
        {
            server_task task(SERVER_TASK_TYPE_METRICS);
            task.id = res->rd.get_new_id();
            res->rd.post_task(std::move(task), true); // high-priority task
        }

        // get the result
        auto result = res->rd.next(req.should_stop);
        if (!result) {
            // connection was closed
            GGML_ASSERT(req.should_stop());
            return res;
        }

        if (result->is_error()) {
            res->error(result->to_json());
            return res;
        }

        // TODO: get rid of this dynamic_cast
        auto res_task = dynamic_cast<server_task_result_metrics*>(result.get());
        GGML_ASSERT(res_task != nullptr);

        // metrics definition: https://prometheus.io/docs/practices/naming/#metric-names
        json all_metrics_def = json {
            {"counter", {{
                    {"name",  "prompt_tokens_total"},
                    {"help",  "Number of prompt tokens processed."},
                    {"value",  (uint64_t) res_task->n_prompt_tokens_processed_total}
            }, {
                    {"name",  "prompt_seconds_total"},
                    {"help",  "Prompt process time"},
                    {"value",  (uint64_t) res_task->t_prompt_processing_total / 1.e3}