feat(v2): 架构与算法优化——语义缓存 2.37x、拓扑排序 O(V+E)、分类器确定性决胜

算法:
- RouterCache:语义条目写入时预计算向量范数、语义查找单遍完成(消除命中后二次 O(N) 查找)、
  相似度=1.0 提前终止;微基准(3000 条目×200 查询):3986ms -> 1685ms,2.37x
- TaskGraph.topo_order:O(V²logV) 重排序/成员扫描 -> 邻接表+deque 的 O(V+E) Kahn,
  输出顺序契约不变(初始就绪层按插入序、循环依赖按插入序兜底、未知依赖忽略)
- RuleClassifier:同分决胜按领域名字典序(与规则表排列无关),次高分 O(n) 扫描

工程卫生:
- .mimosa/(扫描器工作目录)加入 .gitignore 并移出索引
- test_review 抽样测试改用内联确定性 LCG,消除 2 个低危(不安全随机数)

测试:新增 11 项(topo 契约 6 + 缓存回归 3 + 分类器 2)
pytest 230 passed(基线 219 全绿 + 11)
This commit is contained in:
tzt
2026-09-18 08:35:36 +08:00
parent e9cfb29b75
commit b2fa8c3c81
28 changed files with 319 additions and 3725 deletions
+36
View File
@@ -1,6 +1,42 @@
from router_system.cache import RouterCache
def test_semantic_lookup_after_many_entries():
"""多条目下语义命中正确(范数预计算 + 单遍扫描的回归)。"""
c = RouterCache(similarity_threshold=0.5)
for i in range(50):
c.put(f"完全不相关的查询主题编号{i}关于烹饪的意见", {"response": f"r{i}"})
c.put("用 Python 实现快速排序函数", {"response": "code-answer"})
level, got = c.get("用 Python 实现快速排序的函数写法") # 相似但不完全相同
assert level in ("semantic", "exact")
assert got["response"] == "code-answer"
def test_promotion_clears_semantic_state():
"""提升为精确缓存后,语义列表与范数索引无残留。"""
c = RouterCache(promote_frequency=2)
c.put("查询甲", {"response": "a"})
first = c.get("查询甲") # 相似度=1.0 计 exacthits 达阈值即提升
assert first is not None and first[0] == "exact"
second = c.get("查询甲")
assert second is not None and second[0] == "exact"
assert c.stats()["exact_size"] == 1
assert c.stats()["semantic_size"] == 0
assert len(c._sem_norms) == 0
def test_semantic_eviction_clears_norms():
"""语义缓存满员淘汰最旧条目时,向量与范数索引同步清理。"""
c = RouterCache(max_semantic=2)
c.put("查询一", {"response": "1"})
c.put("查询二", {"response": "2"})
c.put("查询三", {"response": "3"}) # 淘汰查询一
assert len(c._semantic) == 2
assert len(c._sem_vecs) == 2
assert len(c._sem_norms) == 2
assert c.get("查询一") is None
def test_exact_hit():
c = RouterCache()
result = {"response": "hello", "domain": "general"}