fix: batch_size=128 in production TOML — 1024 causes training hang

batch_size=1024 has never been tested on H100. It was always
overridden by the CLI default (128) in all previous runs.
Our changes exposed this latent bug by conditional batch_size
override logic.

Root cause of the hang is unknown (likely CUDA Graph capture
with batch_size=1024 buffers). Setting to known-working 128
while we investigate. The batch_size=1024 hang investigation
is tracked in the mega-graph refactor plan.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

config/training/dqn-production.toml

@@ -8,7 +8,7 @@
 
 [training]
 epochs = 200
-batch_size = 1024
+batch_size = 128
 learning_rate = 0.0001
 gamma = 0.99
 weight_decay = 0.0001