projectAIpopular/router_system/knowledge.py

"""知识库：专家系统风格的规则与知识表示（零依赖，纯标准库）。

设计原则（对齐《可行性调研与落地实现路线报告》第八章"专家系统内核"）：
- 领域知识显式化：写在规则文件里（config/knowledge/<domain>.yaml），不藏在模型参数中
- 确定性：规则匹配 = 子串包含（大小写不敏感），同输入同输出
- 可解释：每次命中都记录规则 id，形成推理轨迹
- 最小参数：L0 模式零模型参数，规则即知识

规则文件格式（YAML；若 pyyaml 不可用，可提供同名 .json）：
    domain: code
    rules:
      - id: code-sort
        priority: 90                  # 越大越先触发
        patterns: ["排序", "sort"]    # 任一子串命中即触发
        template: code-implement      # 可选：Planner 任务模板 id
        output: |                     # 可选：输出模板（{query} 等占位符）
          （规则输出）...
    facts:                            # 领域事实表（Judge 校验 / retrieve 执行器用）
      - id: legal-nc
        keywords: ["竞业"]
        statement: "竞业限制期限不得超过二年"

任务模板（config/knowledge/tasks.yaml）：
    task_templates:
      code-implement:
        steps:
          - {id: analyze, kind: analyze, domain: code}
          - {id: design, kind: design, domain: code, deps: [analyze]}

加载顺序：内置默认规则（代码内兜底）→ 文件规则按 id 合并覆盖。
"""
from __future__ import annotations

import json
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any, Dict, List, Optional

DEFAULT_RULES_DIR = Path(__file__).resolve().parent.parent / "config" / "knowledge"


@dataclass
class Rule:
    """一条领域规则。"""
    id: str
    domain: str
    priority: int = 50
    patterns: List[str] = field(default_factory=list)
    template: Optional[str] = None      # 引用的任务模板 id
    output: Optional[str] = None        # 输出模板
    actions: List[str] = field(default_factory=list)  # 保留字段：动作扩展
    subdomain: Optional[str] = None     # 二级子领域（如 investing/labor/calculus）
    subdomain2: Optional[str] = None    # 三级子领域（如 fund/overtime/sorting）

    def matches(self, text: str) -> bool:
        """任一 pattern 是 text 的子串即命中（大小写不敏感）。"""
        if not self.patterns:
            return False
        q = text.lower()
        return any(p.lower() in q for p in self.patterns)


# ---------------------------------------------------------------
# 三级子领域映射（rule_id -> subdomain2）
# 集中维护：新增规则时在此加一行即可完成三级细化标注
# ---------------------------------------------------------------
SUBDOMAIN2_MAP: Dict[str, str] = {
    # ---- code ----
    "code-sort": "sorting",
    "code-debug": "error-analysis",
    "code-algorithm": "algorithm-general",
    "code-refactor": "code-quality",
    "code-database": "sql",
    "code-explain": "code-reading",
    "code-test": "unit-test",
    "code-web": "web-dev",
    "code-implement-general": "implementation",
    "code-git-knowledge": "git",
    "code-docker-knowledge": "container",
    "code-python-knowledge": "python-env",
    # ---- math ----
    "math-equation": "equation",
    "math-calculus": "calculus",
    "math-algebra": "algebra",
    "math-geometry": "geometry",
    "math-proof": "proof",
    "math-probability": "probability",
    "math-number-theory": "number-theory",
    "math-trigonometry": "trigonometry",
    "math-optimization": "optimization",
    "math-general": "math-general",
    # ---- legal ----
    "legal-contract": "contract",
    "legal-labor": "labor",
    "legal-ip": "intellectual-property",
    "legal-housing": "housing",
    "legal-marriage": "family-law",
    "legal-tax": "tax",
    "legal-consumer": "consumer-rights",
    "legal-litigation": "litigation",
    "legal-compliance": "compliance",
    "legal-general": "legal-general",
    # ---- medical ----
    "medical-hypertension": "hypertension",
    "medical-drug": "medication",
    "medical-common": "common-illness",
    "medical-chronic": "chronic-disease",
    "medical-digestive": "digestive",
    "medical-nutrition": "nutrition",
    "medical-mental": "mental-health",
    "medical-firstaid": "first-aid",
    "medical-pediatrics": "pediatrics",
    "medical-general": "medical-general",
    # ---- finance ----
    "finance-investing": "investing",
    "finance-saving": "saving",
    "finance-loan": "loan",
    "finance-insurance": "insurance",
    "finance-credit-card": "credit",
    "finance-personal-budget": "budgeting",
    "finance-general": "finance-general",
    # ---- life ----
    "life-food": "cooking",
    "life-travel": "travel",
    "life-home": "home",
    "life-pet": "pet",
    "life-fitness": "fitness",
    "life-weather": "weather",
    "life-general": "life-general",
    # ---- education ----
    "edu-study-method": "study-method",
    "edu-exam": "exam",
    "edu-language": "language",
    "edu-course": "course",
    "edu-career": "career",
    "edu-general": "education-general",
    # ---- general ----
    "general-explain": "explain",
    "general-writing": "writing",
    "general-compare": "compare",
    "general-translate": "translate",
    "general-knowledge": "explain",
}

# ---------------------------------------------------------------
# 二级子领域映射（rule_id -> subdomain）
# 三级 subdomain2 的父级类别；与 SUBDOMAIN2_MAP 按 rule_id 对齐维护。
# ---------------------------------------------------------------
SUBDOMAIN_MAP: Dict[str, str] = {
    # ---- code ----
    "code-sort": "algorithm",
    "code-debug": "debugging",
    "code-algorithm": "algorithm",
    "code-refactor": "quality",
    "code-database": "data",
    "code-explain": "reading",
    "code-test": "quality",
    "code-web": "web",
    "code-implement-general": "implementation",
    "code-git-knowledge": "tooling",
    "code-docker-knowledge": "tooling",
    "code-python-knowledge": "tooling",
    # ---- math ----
    "math-equation": "algebra",
    "math-calculus": "analysis",
    "math-algebra": "algebra",
    "math-geometry": "geometry",
    "math-proof": "proof",
    "math-probability": "probability",
    "math-number-theory": "number-theory",
    "math-trigonometry": "trigonometry",
    "math-optimization": "optimization",
    "math-general": "general",
    # ---- legal ----
    "legal-contract": "contract",
    "legal-labor": "labor",
    "legal-ip": "ip",
    "legal-housing": "civil",
    "legal-marriage": "civil",
    "legal-tax": "tax",
    "legal-consumer": "consumer",
    "legal-litigation": "procedure",
    "legal-compliance": "compliance",
    "legal-general": "general",
    # ---- medical ----
    "medical-hypertension": "chronic",
    "medical-drug": "medication",
    "medical-common": "common",
    "medical-chronic": "chronic",
    "medical-digestive": "common",
    "medical-nutrition": "nutrition",
    "medical-mental": "mental",
    "medical-firstaid": "emergency",
    "medical-pediatrics": "pediatrics",
    "medical-general": "general",
    # ---- finance ----
    "finance-investing": "investing",
    "finance-saving": "personal-finance",
    "finance-loan": "credit",
    "finance-insurance": "insurance",
    "finance-credit-card": "credit",
    "finance-personal-budget": "personal-finance",
    "finance-general": "general",
    # ---- life ----
    "life-food": "daily",
    "life-travel": "daily",
    "life-home": "daily",
    "life-pet": "daily",
    "life-fitness": "health",
    "life-weather": "daily",
    "life-general": "general",
    # ---- education ----
    "edu-study-method": "learning",
    "edu-exam": "learning",
    "edu-language": "language",
    "edu-course": "learning",
    "edu-career": "development",
    "edu-general": "general",
    # ---- general ----
    "general-explain": "explanation",
    "general-writing": "writing",
    "general-compare": "analysis",
    "general-translate": "language",
    "general-knowledge": "explanation",
}


# ---------------------------------------------------------------
# 内置默认规则（兜底：即使规则文件缺失/损坏，系统仍可运行）
# ---------------------------------------------------------------
BUILTIN_RULES: List[Dict[str, Any]] = [
    # ---- code ----
    {"id": "code-sort", "domain": "code", "priority": 90,
     "patterns": ["排序", "快速排序", "排序算法", "sort", "quicksort"],
     "template": "code-implement"},
    {"id": "code-debug", "domain": "code", "priority": 85,
     "patterns": ["报错", "错误", "调试", "bug", "debug", "typeerror", "异常", "报 TypeError"],
     "template": "code-debug"},
    {"id": "code-implement-general", "domain": "code", "priority": 50,
     "patterns": ["实现", "编写", "写一个", "函数", "代码", "编程", "用 python", "用 java",
                  "用 javascript", "sql", "接口", "算法"],
     "template": "code-implement"},
    # ---- math ----
    {"id": "math-equation", "domain": "math", "priority": 90,
     "patterns": ["方程", "求解", "求根", "solve", "equation", "解方程"],
     "template": "math-solve"},
    {"id": "math-calculus", "domain": "math", "priority": 85,
     "patterns": ["积分", "导数", "微积分", "求导", "integral", "derivative", "∫"],
     "template": "math-solve"},
    {"id": "math-general", "domain": "math", "priority": 50,
     "patterns": ["数学", "证明", "定理", "概率", "统计", "计算", "等于", "math", "不等式"],
     "template": "math-solve"},
    # ---- legal ----
    {"id": "legal-contract", "domain": "legal", "priority": 90,
     "patterns": ["合同", "条款", "违约", "离职", "竞业", "劳动", "contract", "clause", "赔偿"],
     "template": "legal-advice"},
    {"id": "legal-ip", "domain": "legal", "priority": 85,
     "patterns": ["专利", "版权", "商标", "知识产权", "patent", "copyright", "trademark"],
     "template": "legal-advice"},
    {"id": "legal-general", "domain": "legal", "priority": 50,
     "patterns": ["法律", "合规", "诉讼", "仲裁", "法条", "law", "legal", "法规"],
     "template": "legal-advice"},
    # ---- medical ----
    {"id": "medical-hypertension", "domain": "medical", "priority": 90,
     "patterns": ["高血压", "hypertension", "血压"],
     "template": "medical-advice"},
    {"id": "medical-drug", "domain": "medical", "priority": 85,
     "patterns": ["药物", "吃药", "剂量", "副作用", "退烧药", "降压药", "dosage", "prescription"],
     "template": "medical-advice"},
    {"id": "medical-general", "domain": "medical", "priority": 50,
     "patterns": ["医疗", "症状", "诊断", "治疗", "感冒", "发烧", "糖尿病", "医生", "患者",
                  "体检", "疫苗", "medical", "symptom", "disease"],
     "template": "medical-advice"},
    # ---- finance ----
    {"id": "finance-investing", "domain": "finance", "priority": 90,
     "patterns": ["基金", "定投", "收益率", "股票", "投资", "炒股", "证券", "invest", "stock"]},
    {"id": "finance-saving", "domain": "finance", "priority": 85,
     "patterns": ["存款", "储蓄", "利息", "零钱通", "余额宝", "saving"]},
    {"id": "finance-loan", "domain": "finance", "priority": 80,
     "patterns": ["贷款", "房贷", "借款", "按揭", "loan"]},
    {"id": "finance-insurance", "domain": "finance", "priority": 75,
     "patterns": ["保险", "理赔", "保单", "投保", "insurance"]},
    {"id": "finance-credit-card", "domain": "finance", "priority": 70,
     "patterns": ["信用卡", "花呗", "白条", "credit card"]},
    {"id": "finance-personal-budget", "domain": "finance", "priority": 60,
     "patterns": ["预算", "记账", "开销", "省钱", "budget"]},
    {"id": "finance-general", "domain": "finance", "priority": 50,
     "patterns": ["金融", "财务", "外汇", "汇率", "finance"]},
    # ---- life ----
    {"id": "life-food", "domain": "life", "priority": 90,
     "patterns": ["做饭", "做菜", "菜谱", "食谱", "烹饪", "cooking"]},
    {"id": "life-travel", "domain": "life", "priority": 85,
     "patterns": ["旅游", "旅行", "攻略", "景点", "签证", "travel"]},
    {"id": "life-home", "domain": "life", "priority": 80,
     "patterns": ["装修", "租房", "家电", "清洁", "搬家", "home"]},
    {"id": "life-pet", "domain": "life", "priority": 75,
     "patterns": ["宠物", "养猫", "养狗", "撸猫", "pet"]},
    {"id": "life-fitness", "domain": "life", "priority": 70,
     "patterns": ["健身", "减肥", "跑步", "锻炼", "fitness"]},
    {"id": "life-weather", "domain": "life", "priority": 65,
     "patterns": ["天气", "下雨", "台风", "降温", "weather"]},
    {"id": "life-general", "domain": "life", "priority": 50,
     "patterns": ["生活", "日常", "家居", "life"]},
    # ---- education ----
    {"id": "edu-study-method", "domain": "education", "priority": 90,
     "patterns": ["学习方法", "记忆", "做笔记", "笔记法", "专注力"]},
    {"id": "edu-exam", "domain": "education", "priority": 85,
     "patterns": ["考试", "考研", "复习", "真题", "四六级", "exam"]},
    {"id": "edu-language", "domain": "education", "priority": 80,
     "patterns": ["英语", "单词", "口语", "语法", "english"]},
    {"id": "edu-course", "domain": "education", "priority": 75,
     "patterns": ["课程", "网课", "慕课", "选修", "course"]},
    {"id": "edu-career", "domain": "education", "priority": 70,
     "patterns": ["职业规划", "求职", "面试", "简历", "校招", "career"]},
    {"id": "edu-general", "domain": "education", "priority": 50,
     "patterns": ["教育", "大学", "专业选择", "education"]},
    # ---- general ----
    {"id": "general-explain", "domain": "general", "priority": 30,
     "patterns": ["总结", "介绍", "解释", "为什么", "优缺点", "是什么", "翻译", "邮件",
                  "summarize", "explain", "what is", "写一封"],
     "template": "general-explain"},
]

# 内置默认任务模板（兜底）
BUILTIN_TASKS: Dict[str, Dict[str, Any]] = {
    "code-implement": {"steps": [
        {"id": "analyze", "kind": "analyze", "domain": "code", "desc": "需求与约束分析"},
        {"id": "design", "kind": "design", "domain": "code", "deps": ["analyze"], "desc": "算法与数据结构设计"},
        {"id": "implement", "kind": "implement", "domain": "code", "deps": ["design"], "desc": "实现代码"},
        {"id": "verify", "kind": "verify", "domain": "code", "deps": ["implement"], "desc": "自测校验"},
    ]},
    "code-debug": {"steps": [
        {"id": "analyze", "kind": "analyze", "domain": "code", "desc": "错误现象与复现分析"},
        {"id": "diagnose", "kind": "diagnose", "domain": "code", "deps": ["analyze"], "desc": "定位错误根因"},
        {"id": "fix", "kind": "fix", "domain": "code", "deps": ["diagnose"], "desc": "给出修复方案"},
        {"id": "verify", "kind": "verify", "domain": "code", "deps": ["fix"], "desc": "修复后验证"},
    ]},
    "math-solve": {"steps": [
        {"id": "conditions", "kind": "analyze", "domain": "math", "desc": "明确已知条件与目标"},
        {"id": "solve", "kind": "solve", "domain": "math", "deps": ["conditions"], "desc": "选择方法并求解"},
        {"id": "verify", "kind": "verify", "domain": "math", "deps": ["solve"], "desc": "检查边界与验证"},
    ]},
    "legal-advice": {"steps": [
        {"id": "facts", "kind": "analyze", "domain": "legal", "desc": "梳理事实与法律问题"},
        {"id": "retrieve", "kind": "retrieve", "domain": "legal", "deps": ["facts"], "desc": "检索适用法规"},
        {"id": "conclude", "kind": "conclude", "domain": "legal", "deps": ["retrieve"], "desc": "给出法律意见"},
        {"id": "disclaimer", "kind": "disclaimer", "domain": "legal", "deps": ["conclude"], "desc": "免责提示"},
    ]},
    "medical-advice": {"steps": [
        {"id": "symptoms", "kind": "analyze", "domain": "medical", "desc": "梳理症状与背景"},
        {"id": "advise", "kind": "advise", "domain": "medical", "deps": ["symptoms"], "desc": "给出一般建议"},
        {"id": "warning", "kind": "disclaimer", "domain": "medical", "deps": ["advise"], "desc": "就医警示"},
    ]},
    "general-explain": {"steps": [
        {"id": "outline", "kind": "analyze", "domain": "general", "desc": "梳理主题要点"},
        {"id": "explain", "kind": "explain", "domain": "general", "deps": ["outline"], "desc": "展开解释"},
        {"id": "conclude", "kind": "conclude", "domain": "general", "deps": ["explain"], "desc": "总结"},
    ]},
}

# 内置默认事实表（兜底）
BUILTIN_FACTS: Dict[str, List[Dict[str, Any]]] = {
    "legal": [
        {"id": "legal-noncompete", "keywords": ["竞业", "离职", "同业"],
         "statement": "竞业限制期限不得超过二年，且用人单位应在限制期内按月给予经济补偿"},
        {"id": "legal-renew-compensation", "keywords": ["不续签", "经济补偿", "劳动合同"],
         "statement": "劳动合同期满用人单位不续签的，通常应支付经济补偿（每满一年一个月工资）"},
    ],
    "medical": [
        {"id": "medical-hypertension-diet", "keywords": ["高血压", "饮食"],
         "statement": "高血压患者应低盐低脂饮食、控制体重、规律运动、戒烟限酒，并在医生指导下用药"},
        {"id": "medical-fever-drug", "keywords": ["发烧", "退烧"],
         "statement": "体温超过 38.5℃ 可在药师指导下使用退烧药；持续发热或出现严重症状应及时就医"},
    ],
}


def _try_load_yaml(path: Path) -> Optional[Dict[str, Any]]:
    try:
        import yaml  # type: ignore
    except ImportError:
        return None
    try:
        with open(path, "r", encoding="utf-8") as f:
            data = yaml.safe_load(f)
        return data if isinstance(data, dict) else None
    except Exception:
        return None


def _try_load_json(path: Path) -> Optional[Dict[str, Any]]:
    json_path = path.with_suffix(".json")
    if not json_path.exists():
        return None
    try:
        with open(json_path, "r", encoding="utf-8") as f:
            data = json.load(f)
        return data if isinstance(data, dict) else None
    except Exception:
        return None


class KnowledgeBase:
    """知识库：加载规则文件，提供规则匹配、任务模板、事实表查询。"""

    def __init__(self, rules_dir: Optional[str | Path] = None):
        self.rules_dir = Path(rules_dir) if rules_dir else DEFAULT_RULES_DIR
        self._rules: Dict[str, Rule] = {}
        self._tasks: Dict[str, Dict[str, Any]] = {}
        self._facts: Dict[str, List[Dict[str, Any]]] = {}
        self.load()

    # ---- 加载 ----
    def load(self) -> None:
        """内置默认 + 规则文件合并（文件规则按 id 覆盖内置）。"""
        self._rules = {}
        self._tasks = dict(BUILTIN_TASKS)
        for item in BUILTIN_RULES:
            self._register_rule(item)
        self._facts = {d: [dict(f) for f in facts] for d, facts in BUILTIN_FACTS.items()}

        if self.rules_dir.is_dir():
            for f in sorted(self.rules_dir.glob("*.yaml")):
                data = _try_load_yaml(f)
                if data is not None:
                    self._load_file_data(f, data)
            for f in sorted(self.rules_dir.glob("*.json")):
                if f.name not in {p.name for p in self.rules_dir.glob("*.yaml")}:
                    data = _try_load_json(f)
                    if data is not None:
                        self._load_file_data(f, data)

    def _load_file_data(self, path: Path, data: Dict[str, Any]) -> None:
        name = path.stem
        if name == "tasks":
            for tid, tpl in (data.get("task_templates") or {}).items():
                if isinstance(tpl, dict) and isinstance(tpl.get("steps"), list):
                    self._tasks[tid] = tpl
            return
        domain = data.get("domain", name)
        for item in data.get("rules") or []:
            if isinstance(item, dict) and item.get("id"):
                self._register_rule({**item, "domain": domain})
        for fact in data.get("facts") or []:
            if isinstance(fact, dict) and fact.get("id"):
                self._facts.setdefault(domain, []).append(fact)

    def _register_rule(self, item: Dict[str, Any]) -> None:
        rule = Rule(
            id=str(item["id"]),
            domain=str(item.get("domain", "general")),
            priority=int(item.get("priority", 50)),
            patterns=[str(p) for p in item.get("patterns", [])],
            template=item.get("template"),
            output=item.get("output"),
            actions=[str(a) for a in item.get("actions", [])],
            subdomain=item.get("subdomain") or SUBDOMAIN_MAP.get(str(item["id"])),
            subdomain2=item.get("subdomain2") or SUBDOMAIN2_MAP.get(str(item["id"])),
        )
        self._rules[rule.id] = rule

    # ---- 查询 ----
    def match(self, text: str, domain: Optional[str] = None) -> List[Rule]:
        """返回命中的规则，按优先级降序。domain 为空则全领域匹配。"""
        hits = []
        for rule in self._rules.values():
            if domain is not None and rule.domain != domain:
                continue
            if rule.matches(text):
                hits.append(rule)
        hits.sort(key=lambda r: r.priority, reverse=True)
        return hits

    def rule(self, rule_id: str) -> Optional[Rule]:
        return self._rules.get(rule_id)

    def rules_count(self) -> int:
        return len(self._rules)

    def task_template(self, tid: str) -> Optional[Dict[str, Any]]:
        return self._tasks.get(tid)

    def task_ids(self) -> List[str]:
        return sorted(self._tasks.keys())

    def facts(self, domain: str) -> List[Dict[str, Any]]:
        return self._facts.get(domain, [])

    def domains(self) -> List[str]:
        return sorted({r.domain for r in self._rules.values()})