aiagent/backend/app/models/knowledge_entry.py

"""
知识条目模型 — Agent 执行经验的结构化沉淀
"""
import uuid
from datetime import datetime
from sqlalchemy import Column, String, Text, Integer, DateTime, Boolean, JSON, Float, Index, ForeignKey
from sqlalchemy.dialects.mysql import CHAR
from app.core.database import Base


class KnowledgeEntry(Base):
    """从 Agent 执行日志中提取的可复用知识条目"""
    __tablename__ = "knowledge_entries"

    id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
    agent_id = Column(String(36), nullable=True, index=True, comment="所属 Agent ID（NULL=全Agent共享）")
    workspace_id = Column(CHAR(36), ForeignKey("workspaces.id"), nullable=True, index=True, comment="工作区ID")
    title = Column(String(500), nullable=False, comment="知识标题（一句话概括）")
    category = Column(String(30), nullable=False, index=True,
                      comment="类别: bug_fix/best_practice/workaround/optimization/insight")
    tags = Column(JSON, nullable=True, comment="标签列表: ['mysql','deadlock','retry']")

    # 知识内容
    situation = Column(Text, nullable=True, comment="适用场景")
    solution = Column(Text, nullable=True, comment="解决方案")
    caveats = Column(Text, nullable=True, comment="注意事项/踩坑记录")

    # 来源追溯
    source_execution_ids = Column(JSON, nullable=True, comment="原始执行日志ID列表")
    source_agent_name = Column(String(200), nullable=True, comment="来源 Agent 名称")
    source_model = Column(String(100), nullable=True, comment="来源模型")

    # RAG 检索
    embedding_text = Column(Text, nullable=True, comment="用于生成 embedding 的合并文本")
    embedding = Column(Text, nullable=True, comment="JSON 序列化的 embedding 向量")

    # 效果度量
    retrieval_count = Column(Integer, default=0, comment="被检索次数")
    success_rate = Column(Float, nullable=True, comment="应用成功率")

    # 提取信息
    extracted_by = Column(String(100), nullable=True, comment="提取方式: llm_auto/manual/reviewed")
    confidence = Column(Float, default=0.5, comment="提取置信度(0-1)")

    is_active = Column(Boolean, default=True, comment="是否启用")
    created_at = Column(DateTime, default=datetime.now, comment="创建时间")
    updated_at = Column(DateTime, default=datetime.now, onupdate=datetime.now, comment="更新时间")

    __table_args__ = (
        Index("ix_knowledge_entries_active", "is_active"),
    )

    def __repr__(self):
        return f"<KnowledgeEntry(id={self.id}, title={self.title}, category={self.category})>"

    def to_dict(self) -> dict:
        return {
            "id": self.id,
            "agent_id": self.agent_id,
            "workspace_id": self.workspace_id,
            "title": self.title,
            "category": self.category,
            "tags": self.tags or [],
            "situation": self.situation,
            "solution": self.solution,
            "caveats": self.caveats,
            "source_agent_name": self.source_agent_name,
            "retrieval_count": self.retrieval_count,
            "confidence": self.confidence,
            "created_at": self.created_at.isoformat() if self.created_at else None,
        }