"""
Agent 向量记忆模型。

存储对话片段的 embedding 向量，支持语义检索。
"""
from __future__ import annotations

import uuid
from datetime import datetime

from sqlalchemy import Column, String, Text, DateTime, Index
from sqlalchemy.dialects.mysql import JSON as MySQLJSON

from app.core.database import Base


class AgentVectorMemory(Base):
    """Agent 向量记忆 — 存储对话文本及 embedding"""

    __tablename__ = "agent_vector_memories"

    id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
    scope_kind = Column(String(16), nullable=False, index=True, comment="作用域类型: agent / bare")
    scope_id = Column(String(36), nullable=False, index=True, comment="作用域 ID: agent_id / user_id")
    session_key = Column(String(128), nullable=False, default="", comment="会话标识")
    content_text = Column(Text, nullable=False, comment="原始对话文本")
    embedding = Column(Text, nullable=True, comment="JSON 序列化的 embedding 向量")
    metadata_ = Column("metadata", MySQLJSON, nullable=True, comment="元数据: {type, iteration, ...}")
    created_at = Column(DateTime, default=datetime.utcnow, nullable=False)

    __table_args__ = (
        Index("ix_agent_vector_memory_scope", "scope_kind", "scope_id"),
    )

    def to_dict(self) -> dict:
        return {
            "id": self.id,
            "scope_kind": self.scope_kind,
            "scope_id": self.scope_id,
            "session_key": self.session_key,
            "content_text": self.content_text,
            "embedding": self.embedding,
            "metadata": self.metadata_ or {},
            "created_at": self.created_at.isoformat() if self.created_at else None,
        }