Fix #34: ASW_Basic 兜底恒出方案; 搬移效率下限不满足降级为 warning (不判违规)

- constraints.py: ASW_Basic/ASW_Basic_降核 的 dValue 效率下限不再计违规
  (DMA 仍能工作只是效率低; 真正不可行的只有容量/核数硬约束);
  IterBatch/MergeBatch/StreamK 等有替代分支的分支仍按违规处理 (不满足条件不该进)
- asw_basic 枚举尾部: 严格 256B 偏好无解 -> 放开约束4 按 128B 硬下限给最优可行 tile,
  note 标注"效率降级"; 128B 硬下限也不满足的极端形状 (如 N=8 int8, B 侧 dValue=8B
  物理不可满足) 仍给 Base tile 方案 + 标注效率降级 (搬移效率崩塌)
- evaluator advice / router 仲裁文案含"效率降级"提示 (plan.note 同步)
- docs/06 Step1 增加"兜底分支恒出方案"段落 (效率降级 vs 违规的语义分层)
- 回归: b32_m16_n8192_k7168 分解 = Base 16x1024 + tile 16x1024 + k_l1=112
  (L1 双缓冲 ⌊L1/(2·(16+1024)·2)⌋16=112 反推) 入测试; 极端形状 feasible=True +
  效率降级标注; 压力 10000 例 0 崩溃/0 NaN/0 硬违规/0 GM<V_in; examples 重生成 0 diff

BMM/BMM_Theory/tests/test_branches.py

@@ -760,19 +760,42 @@ class TestIssue33(unittest.TestCase):
         self.assertEqual((p.single_core_m, p.single_core_n), (512, 512))
         self.assertEqual((p.m_cnt, p.n_cnt), (8, 8))
 
-    def test_pathological_shape_flagged_infeasible(self):
-        # 极端形状 (N=8 int8, 大 K): B 侧 dValue = sN*dt = 8B 物理上不可能满足
-        # 256B/128B 下限 -> 方案必须被自检标注违规 (不再静默产出伪可行方案)
-        from bmm_theory.constraints import check_plan_constraints
+    def test_issue34_k_l1_decomposition_derived(self):
+        # b32_m16_n8192_k7168: 分解 = Base 16x1024 (例外: M=16<256; N 侧受 L0B 单边
+        # 上限收敛), SingleCore 16x1024 (mCnt=1,nCnt=8), k_l1 = L1 双缓冲反推
+        # ⌊L1/(2·(sM+sN)·dt)⌋16 = ⌊524288/(2·1040·2)⌋16 = 112 (v1.91 §5.2)
         from bmm_theory.branches.asw_basic import AswBasicBranch
+        case = mkcase(32, 16, 8192, 7168)
+        p = AswBasicBranch().make_plan(case)
+        self.assertEqual((p.base_m, p.base_n), (16, 1024))
+        self.assertEqual((p.single_core_m, p.single_core_n), (16, 1024))
+        self.assertEqual(p.k_l1, 112)
+
+    def test_pathological_shape_degraded_warning_always_plan(self):
+        # issue#34: 兜底分支恒出方案 —— 极端形状 (N=8 int8 大K, B 侧 dValue=8B
+        # 物理不可满足) 照常给方案 + 标注效率降级 (warning), 不判违规/不判不可行
+        from bmm_theory.constraints import check_plan_constraints
+        from bmm_theory.evaluator import PlanEvaluator
         case = mkcase(4096, 2048, 8, 1024, dtype_a="int8", dtype_b="int8")
         r = self.router.route(case)
         self.assertEqual(r["branch"], "ASW_Basic")
-        v = check_plan_constraints(case, r["plan"])
-        self.assertTrue(v, "极端形状应被自检标注违规 (搬移效率崩塌)")
-        self.assertIn("自检违规", r["arbitration"])
-        # 时延仍应给出 (供人工评估), 但不为 0 / NaN
-        self.assertGreater(r["timing"].t_total, 0.0)
+        self.assertEqual(check_plan_constraints(case, r["plan"]), [])
+        self.assertIn("效率降级", r["plan"].note)
+        er = PlanEvaluator().evaluate(case, r["plan"])
+        self.assertTrue(er.feasible)
+        self.assertIn("效率降级", er.advice)
+        self.assertGreater(er.timing.t_total, 0.0)
+
+    def test_pathological_n8_hard_floor_fallback(self):
+        # 更极端: N=8 int8 连 128B 硬下限也不满足 -> 仍恒出方案, 效率降级标注
+        from bmm_theory.evaluator import PlanEvaluator
+        case = mkcase(512, 4096, 1, 8192, dtype_a="int8", dtype_b="int8")
+        r = self.router.route(case)
+        self.assertEqual(r["branch"], "ASW_Basic")
+        self.assertIsNotNone(r["plan"])
+        self.assertIn("效率降级", r["plan"].note)
+        er = PlanEvaluator().evaluate(case, r["plan"])
+        self.assertTrue(er.feasible)
 
 
 if __name__ == "__main__":