feat: ISMCTS q-value as training label

C#: TrainingCollector新增q_value列, IsmctsBot传入winRate
CSV: reward→q_value, ISMCTS状态带真实评估值, Neural填0
Python: 优先取ISMCTS状态+评估值训练, 无q_value的Neural状态跳过
旧CSV格式(reward)自动fallback到Neural-only过滤

信号从'这局谁赢'改为'ISMCTS评估这步有多好'

PdkFriendServer/Logic/IsmctsBot.cs

@@ -392,7 +392,7 @@ namespace PdkFriendServer.Logic
                 int totalSims = allCandidates.Count * fastSims
                     + scoredCandidates.Count(c => c.winRate > 0.3) * (simsPerCandidate - fastSims);
                 Console.WriteLine($"[ISMCTS pos{view.MyPos}] {totalSims}sims => {desc}");
-                TrainingCollector.Record(view, _tracker, TrainingCollector.ActionToIdx(best.play), view.MyPos-1);
+                TrainingCollector.Record(view, _tracker, TrainingCollector.ActionToIdx(best.play), view.MyPos-1, (float)best.winRate);
                 return best.play;
             }