Disambiguate exact-capacity static masks

Follow-up: the exact-capacity static-mask case is now covered. When the mask width equals `past_length + input_length`, its final slot distinguishes a full prompt with unused cache capacity from a new-only token block. A mask with unused capacity at the end keeps the full-prompt path.

[GPT-QModel #3574](https://github.com/ModelCloud/GPTQModel/pull/3574) contains regression tests for both exact-capacity and longer padded masks, plus existing new-only block coverage. It builds on merged [GPT-QModel #3571](https://github.com/ModelCloud/GPTQModel/pull/3571). The Ripple suite passed **35 tests** against this upstream source (`tests/test_ricursive_support.py`).

modeling_ricursive.py

@@ -911,17 +911,19 @@ class RicursiveForCausalLM(RicursivePreTrainedModel, GenerationMixin):
             # A full prompt can include cached tokens, while verification may pass
             # only a new token block. A block no longer than the cache must be new;
             # for a longer block, a mask with exactly the cached prefix plus new
-            # tokens identifies new-only input. A longer mask may be padded to a
-            # static cache's capacity, so it cannot identify a new-only block.
+            # tokens identifies new-only input when its final slot is populated.
+            # A longer mask, or one with unused capacity at the end, may be padded
+            # to a static cache's capacity and describes a full prompt instead.
             input_length = input_ids.shape[1]
-            full_prompt = (
-                past_length > 0
-                and input_length > past_length
-                and (
-                    attention_mask is None
-                    or attention_mask.shape[-1] != past_length + input_length
-                )
+            candidate_full_prompt = past_length > 0 and input_length > past_length
+            new_block_mask = (
+                candidate_full_prompt
+                and attention_mask is not None
+                and attention_mask.dim() == 2
+                and attention_mask.shape[-1] == past_length + input_length
+                and bool(attention_mask[..., -1].any())
             )
+            full_prompt = candidate_full_prompt and not new_block_mask
             new_len = input_length - past_length if full_prompt else input_length
             cache_position = torch.arange(
                 past_length, past_length + new_len, device=input_ids.device