GPU sweep now multi-stage (up to 10 coils); raise max_stages to 10

The GPU batch sweep processes multi-stage configs round-by-round: at round
s every still-alive config with a stage s runs its discharge in one batch,
carrying the slug's global position/velocity forward to the next round.
Configs with fewer stages drop out of later rounds. Analytic
constant-velocity sensor trigger per stage. Validated vs CPU run_coilgun
for multi-stage configs (<=3% exit velocity). Default max_stages 4 -> 10.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

tests/test_batch_sweep.py

@@ -9,28 +9,30 @@ from gausse.storage.database import count_runs, fetch_runs, open_connection
 DB = ComponentDatabase.load()
 
 
-def test_gpu_sweep_records_all_and_writes_single_stage(tmp_path):
+def test_gpu_sweep_records_all_runs(tmp_path):
     db_path = tmp_path / "gpu.sqlite3"
     summary = run_gpu_sweep(db_path, n_runs=300, seed=3, prefer_gpu=False, batch_size=300)
     assert summary["n_runs"] == 300
     conn = open_connection(db_path)
     assert count_runs(conn) == 300
     rows = fetch_runs(conn)
-    # GPU-путь одноступенчатый
+    # многоступенчатые конфиги допустимы (до max_stages)
+    stage_counts = set()
     for r in rows:
         g = genome_from_dict(json.loads(r.genome_json))
-        assert len(g.stages) == 1
+        stage_counts.add(len(g.stages))
         assert r.search_mode.startswith("gpu-sweep")
+    assert max(stage_counts) >= 2, "должны встречаться многоступенчатые конфиги"
 
 
 def test_gpu_sweep_matches_cpu_within_tolerance(tmp_path):
-    """Честная сверка: GPU-батч должен давать те же exit_v, что CPU run_coilgun."""
+    """Честная сверка: GPU-батч (в т.ч. многоступ.) даёт те же exit_v, что CPU run_coilgun."""
     db_path = tmp_path / "gpu.sqlite3"
-    run_gpu_sweep(db_path, n_runs=1500, seed=5, prefer_gpu=False, batch_size=1500)
+    run_gpu_sweep(db_path, n_runs=2000, seed=5, prefer_gpu=False, batch_size=2000)
     conn = open_connection(db_path)
-    bounds = SearchBounds(min_stages=1, max_stages=1)
-    feasible = fetch_runs(conn, feasible=True, order_by_efficiency_desc=True, limit=10)
-    assert len(feasible) >= 3, "нужно несколько реализуемых для сверки"
+    bounds = SearchBounds()
+    feasible = fetch_runs(conn, feasible=True, order_by_efficiency_desc=True, limit=12)
+    assert len(feasible) >= 3
     checked = 0
     for r in feasible:
         g = genome_from_dict(json.loads(r.genome_json))
@@ -38,8 +40,8 @@ def test_gpu_sweep_matches_cpu_within_tolerance(tmp_path):
         cpu = run_coilgun(config)
         if not cpu.feasible:
             continue
-        # фикс.шаг батча vs адаптивный solve_ivp + аналитический триггер: ~2%
-        assert abs(r.exit_velocity_mps - cpu.exit_v_mps) <= 0.02 * abs(cpu.exit_v_mps) + 0.1, \
-            f"GPU {r.exit_velocity_mps:.2f} vs CPU {cpu.exit_v_mps:.2f}"
+        # фикс.шаг батча + аналитический триггер vs адаптивный solve_ivp: ~3%
+        assert abs(r.exit_velocity_mps - cpu.exit_v_mps) <= 0.03 * abs(cpu.exit_v_mps) + 0.2, \
+            f"GPU {r.exit_velocity_mps:.2f} vs CPU {cpu.exit_v_mps:.2f} ({len(g.stages)} ступ.)"
         checked += 1
     assert checked >= 3