"""Embedding 模块的数据模型 (M5)。"""

from __future__ import annotations

from datetime import datetime
from enum import StrEnum
from typing import Self

from pydantic import BaseModel, Field, model_validator


class EmbeddingProviderType(StrEnum):
    """支持的 embedding provider 标识。"""

    DASHSCOPE = "dashscope"   # 远程 Qwen / 百炼
    LOCAL_BGE = "local-bge"   # 本地 BGE-M3


class EmbeddingResult(BaseModel):
    """单篇文章的嵌入结果(落盘格式)。"""

    url_hash: str = Field(..., description="主键,与 Article.url_hash 一致")
    source_id: str = Field(..., description="主来源源 id")
    sources: list[str] = Field(
        default_factory=list,
        description="该唯一新闻的全部来源(主源 source_id 居首),来自 M3 去重多源记录",
    )
    title: str = Field(..., description="原文标题(便于人工检索)")
    text: str = Field(
        ..., description="实际送入 embedder 的文本(已截断/拼接)"
    )
    vector: list[float] = Field(..., description="嵌入向量")
    dim: int = Field(..., gt=0, description="向量维度")

    provider: str = Field(..., description="dashscope / local-bge")
    model: str = Field(..., description="嵌入模型名")
    embedded_at: datetime = Field(default_factory=datetime.now)
    char_count: int = Field(default=0, ge=0, description="text 字符数,便于排查")
    publish_time: datetime | None = None

    @model_validator(mode="after")
    def _ensure_sources(self) -> Self:
        """保证 sources 非空、去重且以主源 source_id 开头(旧产物无字段时兜底)。"""
        seen: list[str] = []
        for s in [self.source_id, *self.sources]:
            if s and s not in seen:
                seen.append(s)
        self.sources = seen
        return self

    def short_summary(self) -> str:
        return (
            f"[{self.source_id}] {self.title[:30]} "
            f"dim={self.dim} provider={self.provider}"
        )


class EmbeddingError(Exception):
    """嵌入调用失败。"""

    def __init__(self, reason: str, *, attempts: int = 0) -> None:
        super().__init__(reason)
        self.reason = reason
        self.attempts = attempts