cap terminal reward scale (bounded score bonus) and restore single-battle campaigns

computeRoundReward used cumulative totalScore/50 — unbounded in long battles
(vLoss 353 at round 3160 → 25745 by 3871 in the 5841-round attempt). Cap the
score term at 400 before /50: bonus ∈ [0,8], so the critic's value scale stays
stable regardless of battle length and across battle boundaries.

Reverts the 60-round battle chunking (186e005/da2f825): one battle per
campaign for the whole remaining budget; keeps the crash-restart loop, the
mid-battle freeze guard and the end-of-battle counter completeness check.

Cert (5211, single 60-round battle): 59/60 wins (sole loss = cold-start round
1, score 61), vLoss avg 36.1 / max 148.5, gNorm max 596, zero NaN, zero
restarts, counter check passed. Weights persist to round 5211.

tools/training_runner/run.sh

@@ -79,13 +79,11 @@ while true; do
     sleep 2
   fi
 
-  # ponytail: cap each battle at 60 rounds — matches the certified config.
-  # Round-end reward is cumulative totalScore/50; long battles grow it unboundedly
-  # and blow up the critic's value scale (seen at round 3160, vLoss 25745 by 3871).
-  # Short battles bound the reward, and fresh-process restarts clear thread state.
-  battle_rounds=$(( remaining > 60 ? 60 : remaining ))
-  echo ">>> Running $battle_rounds rounds (opponent: $OPPONENT)..."
-  java -cp ".:$JAR" RunTraining "$OPPONENT" "$battle_rounds" || {
+  # One battle for the whole remaining budget: round-end reward is a bounded
+  # terminal bonus (computeRoundReward caps totalScore at 400), so long battles
+  # keep the critic's value scale stable — no per-battle chunking needed.
+  echo ">>> Running $remaining rounds (opponent: $OPPONENT)..."
+  java -cp ".:$JAR" RunTraining "$OPPONENT" "$remaining" || {
     exit_code=$?
     echo ">>> Java runner exited with code $exit_code — checking if done..."
     remaining=$(remaining_rounds)