refactor: map instruction/input/output to chat roles

- RolloutGenerator._instruction_to_messages builds system/user/assistant list (instruction->system, input->user, output->assistant), replacing single-user-turn concatenation
- Remove _iter_samples helper; _prepare_prompts zips parallel list-of-strings fields directly per the collate_fn contract
- Tests adopt a system-aware chat template and pin the three-field role mapping
- Drop unused imports caught by ruff F401 (torch.Tensor in scheduler.py, iter_raw_records in pipeline.py, Tuple in evaluate_rouge.py)

astrai/inference/core/scheduler.py

@@ -4,7 +4,6 @@ import uuid
 from typing import Any, Dict, List, Optional, Tuple
 
 import torch
-from torch import Tensor
 
 from astrai.inference.core.cache import ContiguousCache, KVCache
 from astrai.inference.core.executor import Executor