#include <algorithm>
#include <array>
#include <atcoder/modint>
#include <bitset>
#include <cassert>
#include <cctype>
#include <chrono>
#include <climits>
#include <cmath>
#include <cstdint>
#include <cstdio>
#include <deque>
#include <fstream>
#include <functional>
#include <iomanip>
#include <iostream>
#include <iterator>
#include <limits>
#include <map>
#include <numeric>
#include <queue>
#include <regex>
#include <set>
#include <sstream>
#include <stack>
#include <string>
#include <tuple>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>

#define rep(i, n) for (int i = 0; i < (int)(n); i++)
#define rep1(i, n) for (int i = 1; i <= (int)(n); i++)
#define all(a) a.begin(), a.end()
using namespace std;

template <class T> inline bool chmin(T &a, T b) {
	if (a > b) {
		a = b;
		return true;
	}
	return false;
}
template <class T> inline bool chmax(T &a, T b) {
	if (a < b) {
		a = b;
		return true;
	}
	return false;
}

template <class T1, class T2>
std::ostream &operator<<(std::ostream &out, const pair<T1, T2> &A) {
	cout << "{" << A.first << "," << A.second << "}";
	return out;
}

template <class T1, class T2>
std::ostream &operator<<(std::ostream &out, const map<T1, T2> &M) {
	for (const auto &A : M) {
		cout << "{" << A.first << "," << A.second << "}";
	}
	return out;
}

template <class T1>
std::ostream &operator<<(std::ostream &out, const set<T1> &M) {
	cout << "{";
	for (const auto &A : M) {
		cout << A << ", ";
	}
	cout << "}" << endl;
	return out;
}

template <class T1>
std::ostream &operator<<(std::ostream &out, const multiset<T1> &M) {
	cout << "{";
	for (const auto &A : M) {
		cout << A << ", ";
	}
	cout << "}" << endl;
	return out;
}

template <class T>
std::ostream &operator<<(std::ostream &out, const vector<T> &A) {
	for (const T &a : A) {
		cout << a << " ";
	}
	return out;
}

void print() { cout << endl; }

template <typename Head, typename... Tail> void print(Head H, Tail... T) {
	cout << H << " ";
	print(T...);
}

template <class T> std::istream &operator>>(std::istream &in, vector<T> &A) {
	for (T &a : A) {
		std::cin >> a;
	}
	return in;
}

using ll = long long;
constexpr int INF = numeric_limits<int>::max() / 2;
constexpr ll LINF = numeric_limits<ll>::max() / 2;

ll modpow(ll a, ll b, ll mod) {
	ll res = 1;
	while (b > 0) {
		if (b & 1) {
			res = res * a % mod;
		}
		a = a * a % mod;
		b >>= 1;
	}
	return res;
}

using mint = atcoder::modint998244353;
mint sumlr(ll l, ll r) {
	// lからrまでの和
	mint n = r - l + 1;
	mint ans = n * (mint(l) + mint(r)) / 2;
	return ans;
}
void solve() {
	/*
	int N = 100;
	int A = 3;
	vector<int> dp(N + 1, INF);
	dp[N] = 0;
	for (int i = N - 1; i >= 1; i--) {
		chmin(dp[i], dp[i + 1] + 1);
		if (i * A <= N)
			chmin(dp[i], dp[i * A] + 1);
	}
	for (int i = 1; i <= N; i++) {
		cout << i << ": " << dp[i] << endl;
	}
	*/

	ll N, A;
	cin >> N >> A;
	if (A == 1) {
		cout << sumlr(1, N - 1).val() << endl;
		return;
	}
	mint sum = 0;
	// Aの倍数を探す
	ll n = N;
	ll cost = 0; // nのコスト
	while (n > 0) {
		// n以下でAの倍数を探す
		ll a = n / A;
		// a+1以上n以下のスコアを計算
		// nのスコアは0
		sum += sumlr(cost, cost + n - a - 1);
		cost = cost + n - a * A + 1;
		n = a;
	}
	cout << sum.val() << endl;
}

int main(void) {
	std::cin.tie(0)->sync_with_stdio(0);
	int T;
	cin >> T;
	while (T--)
		solve();
	return 0;
}