feat(SAC_LSTM_Bot): training harness (#49)

sac_train.sh orchestrates chunked self-play via tools/training_runner/
RunTraining.java: weighted opponent sampling per chunk, deterministic
eval (SACLSTM_EVAL_MODE=1) every N chunks with win-rate tracking, best
checkpoint (weights/sac_best.zip) by eval score, crash-restart loop on
the runner's liveness detection.

Supporting changes:
- integration.nim: opponentKey() keys the NewBattle buffer-clear rule on
  getBotName(id) with numeric-id fallback (#49 Q14 follow-up);
  bumpRoundCounter() emits the per-round liveness signal.
- SAC_LSTM_Bot.nim: onRoundEnded -> bumpRoundCounter().
- RunTraining.java: BOT_NAME env parameterizes result matching
  (default PPO_Bot, unchanged behavior for PPO).
- Launch packaging: root SAC_LSTM_Bot.json + .sh for the booter;
  src json name aligned to 'SAC_LSTM_Bot' so self-reported identity
  matches the booted identity (mismatch = runner connect timeout).

SAC_LSTM_Bot/src/SAC_LSTM_Bot.json

@@ -1,8 +1,8 @@
 {
-  "name": "Recurrent Royalty",
+  "name": "SAC_LSTM_Bot",
   "version": "0.1.0",
   "authors": ["Davide Cappellini"],
-  "description": "SAC+LSTM Tank Royale bot — skeleton with radar lock",
+  "description": "SAC+LSTM Tank Royale bot — self-reported identity; MUST match the name in ../SAC_LSTM_Bot.json (booter identity) or the training runner never sees this bot join",
   "homepage": "",
   "countryCodes": ["IT"],
   "gameTypes": ["classic", "melee", "1v1"],