feat: add online ppo with value-model critic and gae advantages

- register online_ppo train type backed by PPOStrategy: token-level clipped surrogate over GAE advantages plus masked value regression against rollout-pinned returns, with explained-variance metrics
- fold the reference-KL penalty (k3 estimator) into per-token rewards before GAE and pin advantages/returns on RolloutResult so replayed gradient steps optimize fixed targets
- add self-contained ValueModel critic with a zero-initialized value head and backbone warm-started from policy weights; AutoRegressiveLM stays untouched and trunk parity is pinned by tests
- step the critic's own optimizer outside the policy-version lock with the same max_grad_norm clipping as the policy
- persist critic state as value_model.pt/value_optimizer.pt checkpoint extras; resume restores it, fails loudly when missing, and the train.sh completeness check requires the extras for online_ppo configs
- extract shared rollout sequence/logprob helpers from GRPO (behavior unchanged) and add ppo_gamma/ppo_gae_lambda/ppo_vf_coef CLI options

astrai/model/__init__.py

@@ -13,6 +13,7 @@ from astrai.model.components.mlp import MLP, DeepSeekMoE
 from astrai.model.components.norm import RMSNorm
 from astrai.model.encoder import EmbeddingEncoder
 from astrai.model.transformer import AutoRegressiveLM
+from astrai.model.value import ValueModel
 
 __all__ = [
     # Modules
@@ -26,6 +27,7 @@ __all__ = [
     "AutoRegressiveLM",
     "EmbeddingEncoder",
     "AutoModel",
+    "ValueModel",
     # LoRA
     "LoRAConfig",
     "inject_lora",