kb-skills/kb_pipeline/schemas.py

"""Core Pipeline Schemas

定义工作流管道的核心 Schema，包括 StepInput、StepOutput、StepResult、
StepStatus、StepRecord、WorkflowState 和 StepDefinition。
使用 Pydantic v2 确保类型安全和自动验证。
"""

from pydantic import BaseModel, Field
from typing import Optional, Dict, Literal, Any
from datetime import datetime
from enum import Enum


class StepStatus(str, Enum):
    """步骤执行状态枚举"""
    PENDING = "pending"
    RUNNING = "running"
    COMPLETED = "completed"
    FAILED = "failed"
    SKIPPED = "skipped"


class StepInput(BaseModel):
    """所有步骤输入的基类

    Attributes:
        content_id: 内容唯一标识，如 B站 BV号、知乎回答ID等
        platform: 平台名称，限定为 bilibili 或 zhihu
    """
    content_id: str = Field(..., min_length=1, description="内容唯一标识")
    platform: Literal["bilibili", "zhihu"] = Field(..., description="平台名称")


class StepOutput(BaseModel):
    """所有步骤输出的基类

    Attributes:
        success: 步骤是否成功执行
        error_message: 错误信息，成功时为 None
        completed_at: 完成时间，默认为当前时间
    """
    success: bool = Field(..., description="步骤是否成功")
    error_message: Optional[str] = Field(None, description="错误信息")
    completed_at: datetime = Field(default_factory=datetime.now, description="完成时间")


class StepResult(BaseModel):
    """步骤执行结果

    包含步骤的输入、输出和执行状态。

    Attributes:
        step_name: 步骤名称
        input_data: 步骤输入数据
        output_data: 步骤输出数据，可能为 None
        status: 步骤执行状态
    """
    step_name: str = Field(..., description="步骤名称")
    input_data: StepInput = Field(..., description="步骤输入数据")
    output_data: Optional[StepOutput] = Field(None, description="步骤输出数据")
    status: StepStatus = Field(default=StepStatus.PENDING, description="步骤执行状态")


class StepRecord(BaseModel):
    """单个步骤的执行记录

    记录步骤执行的状态、时间和结果摘要。

    Attributes:
        step_name: 步骤名称
        status: 步骤执行状态
        started_at: 开始时间
        completed_at: 完成时间
        error_message: 错误信息
        output_summary: 输出摘要
    """
    step_name: str = Field(..., description="步骤名称")
    status: StepStatus = Field(..., description="步骤执行状态")
    started_at: Optional[datetime] = Field(None, description="开始时间")
    completed_at: Optional[datetime] = Field(None, description="完成时间")
    error_message: Optional[str] = Field(None, description="错误信息")
    output_summary: Optional[str] = Field(None, description="输出摘要")


class WorkflowState(BaseModel):
    """工作流状态 - 存储在 workflow_state.json

    管理整个工作流的状态，包括内容信息、执行历史和步骤状态。

    Attributes:
        schema_version: Schema 版本号
        content_id: 内容唯一标识
        platform: 平台名称
        source_url: 原始链接
        created_at: 创建时间
        updated_at: 更新时间
        steps: 步骤执行记录字典
    """
    schema_version: str = Field(default="1.0", description="Schema 版本号")
    content_id: str = Field(..., description="内容唯一标识")
    platform: str = Field(..., description="平台名称")
    source_url: str = Field(..., description="原始链接")
    created_at: datetime = Field(default_factory=datetime.now, description="创建时间")
    updated_at: datetime = Field(default_factory=datetime.now, description="更新时间")
    steps: Dict[str, StepRecord] = Field(default_factory=dict, description="步骤执行记录")

    def is_step_completed(self, step_name: str) -> bool:
        """检查指定步骤是否已完成

        Args:
            step_name: 步骤名称

        Returns:
            如果步骤存在且状态为 COMPLETED 返回 True，否则返回 False
        """
        record = self.steps.get(step_name)
        return record is not None and record.status == StepStatus.COMPLETED

    def mark_step_started(self, step_name: str) -> None:
        """标记步骤开始执行

        Args:
            step_name: 步骤名称
        """
        self.steps[step_name] = StepRecord(
            step_name=step_name,
            status=StepStatus.RUNNING,
            started_at=datetime.now()
        )
        self.updated_at = datetime.now()

    def mark_step_completed(self, step_name: str, output_summary: Optional[str] = None) -> None:
        """标记步骤完成

        Args:
            step_name: 步骤名称
            output_summary: 输出摘要（可选）
        """
        if step_name in self.steps:
            self.steps[step_name].status = StepStatus.COMPLETED
            self.steps[step_name].completed_at = datetime.now()
            self.steps[step_name].output_summary = output_summary
        else:
            self.steps[step_name] = StepRecord(
                step_name=step_name,
                status=StepStatus.COMPLETED,
                completed_at=datetime.now(),
                output_summary=output_summary
            )
        self.updated_at = datetime.now()

    def mark_step_failed(self, step_name: str, error_message: str) -> None:
        """标记步骤失败

        Args:
            step_name: 步骤名称
            error_message: 错误信息
        """
        if step_name in self.steps:
            self.steps[step_name].status = StepStatus.FAILED
            self.steps[step_name].error_message = error_message
            self.steps[step_name].completed_at = datetime.now()
        else:
            self.steps[step_name] = StepRecord(
                step_name=step_name,
                status=StepStatus.FAILED,
                error_message=error_message,
                completed_at=datetime.now()
            )
        self.updated_at = datetime.now()


class StepDefinition(BaseModel):
    """步骤定义 - 描述步骤的前置条件、输出格式、成功标准

    Attributes:
        step_name: 步骤名称
        description: 步骤描述
        input_schema: 输入 Schema 类型
        output_schema: 输出 Schema 类型
        dependencies: 依赖的步骤列表
    """
    step_name: str = Field(..., description="步骤名称")
    description: str = Field(..., description="步骤描述")
    input_schema: type[StepInput] = Field(..., description="输入 Schema 类型")
    output_schema: type[StepOutput] = Field(..., description="输出 Schema 类型")
    dependencies: list[str] = Field(default_factory=list, description="依赖的步骤列表")