test: prune low-value and duplicate tests

- Remove tautological test_trainer assertions that never trained
- Drop grpo isfinite-only smokes and merge frozen-model checks via parametrize
- Merge duplicate tool_parser cases (find/streaming/factory) with parametrize
- Collapse duplicate dataset store/detect_format tests
- Remove misleading scheduler/task tests that asserted the opposite of their names
- Merge signal-handler SIGTERM/SIGINT into one parametrized case
- Drop cross-file grpo strategy duplication kept in online_strategy

tests/inference/test_scheduler.py

@@ -177,24 +177,6 @@ def test_scheduler_concurrent_get_stats(mock_model_and_tokenizer):
         assert stats["total_tasks"] >= 0
 
 
-def test_prefill_skips_fully_cached_tasks(mock_model_and_tokenizer):
-    """Tasks whose entire prompt is cached skip the prefill phase."""
-    mock_model, mock_tokenizer = mock_model_and_tokenizer
-
-    with patch("astrai.inference.core.scheduler.AutoModel"):
-        with patch("astrai.inference.core.scheduler.AutoTokenizer"):
-            scheduler = InferenceScheduler(
-                model=mock_model,
-                tokenizer=mock_tokenizer,
-                max_batch_size=4,
-                device="cpu",
-            )
-
-    task_id = scheduler.add_task("short prompt", stream_callback=lambda t: None)
-    scheduler.stop()
-    assert task_id.startswith("task_")
-
-
 def _make_real_scheduler(device):
     """Build a scheduler backed by a tiny real model for run_batch tests."""
     cfg = make_rollout_config(max_position_embeddings=64)