tzt
c072a1a237
- 新增 router_system/llm_client.py：OpenAICompatClient 统一 experts/judge/fallback
三处复制的懒建 AsyncClient + /chat/completions + choices/usage 解析（~60 行去重）；
密钥解析统一走 config.get_api_key（激活原死代码，顺带消除 experts 默认环境名不一致）
- 语义缓存 L2：条目容器 list→OrderedDict（提升/淘汰 O(n)→O(1)），按 query 天然去重；
n-gram 向量 lru_cache 复用（同一次 miss 的 get/put 免重复分词）；
A/B：淘汰路径 0.040→0.034s，miss→put 往返 9.41→8.57s（-9%）
- RuleJudge 覆盖度：response.lower() 提出逐词循环（原 O(terms×len) 重复复制）
- extract_content_terms 纯函数 lru_cache 化（专家与 Judge 对同一查询免重复分词），返回 tuple
- RuleClassifier：_score 去掉败者领域白建的命中词 list（胜出后单独收集）；
修复 code 规则 ("api",0.7) 重复登记（原命中计 1.4 分）
- difficulty：正则模块级预编译
- tests：恢复上一轮引入的乱码中文 docstring；网关测试输入串恢复为可判 code 的中文查询
57 lines
2.2 KiB
Python
57 lines
2.2 KiB
Python
"""查询难度估计器（启发式，纯标准库）。
|
||
|
||
依据：RouterArena 用 Bloom 分类法把问题分为 easy/medium/hard。
|
||
这里用查询长度、指令动词、数学/推理标记做轻量估计。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import re
|
||
from typing import Tuple
|
||
|
||
# 触发 hard 的指令动词 / 推理标记
|
||
_HARD_MARKERS = [
|
||
"证明", "推导", "为什么", "如何", "对比", "比较", "分析", "评估", "设计", "优化",
|
||
"复杂度", "时间复杂度", "空间复杂度", "原理", "机制", "优缺点", "区别", "推论", "定理",
|
||
"proof", "prove", "derive", "explain why", "why", "how", "compare", "contrast",
|
||
"analy", "evaluate", "design", "optimize", "refactor", "architect",
|
||
"implement", "debug", "review", "plan", "synthesize",
|
||
"int", "sum", "sqrt", "lim", "log", "derivative", "integral",
|
||
]
|
||
# 触发 medium 的标记
|
||
_MEDIUM_MARKERS = [
|
||
"用", "写", "计算", "求解", "生成", "翻译", "总结", "解释",
|
||
"注意", "建议", "是否", "实现", "步骤",
|
||
"write", "code", "function", "script", "calculate", "solve", "summarize",
|
||
"translate", "fix", "explain", "describe", "list",
|
||
]
|
||
|
||
# 预编译正则（模块级一次，避免每次调用走 re 内部缓存查找）
|
||
_RE_CODE_EXPR = re.compile(r"\b(def|class|function|import)\b")
|
||
_RE_ARITH_EXPR = re.compile(r"[0-9]+\s*[+\-*/^=]\s*[0-9xya-z]")
|
||
|
||
|
||
def estimate_difficulty(query: str) -> Tuple[str, float]:
|
||
"""返回 (difficulty, score)，score 属于 [0,1]。"""
|
||
q = query.lower()
|
||
hard_hits = sum(1 for m in _HARD_MARKERS if m in q)
|
||
medium_hits = sum(1 for m in _MEDIUM_MARKERS if m in q)
|
||
length = len(query)
|
||
|
||
score = 0.0
|
||
score += min(0.30, length / 600.0) # 长度贡献
|
||
score += min(0.55, hard_hits * 0.25) # 推理标记贡献
|
||
score += min(0.30, medium_hits * 0.08) # 一般指令贡献
|
||
|
||
# 额外：代码 / 数学表达式（多步骤信号）
|
||
if "```" in query or _RE_CODE_EXPR.search(q):
|
||
score += 0.15
|
||
if _RE_ARITH_EXPR.search(q):
|
||
score += 0.15
|
||
|
||
score = max(0.0, min(1.0, score))
|
||
if score >= 0.55:
|
||
return "hard", score
|
||
if score >= 0.25:
|
||
return "medium", score
|
||
return "easy", score
|