EvaluationScore (eval/models.py)

Module exposing: EvaluationScore, PerformanceRunResult, ToolCallCheck, AccuracyEvaluationResult, PerformanceEvaluationResult, ReliabilityEvaluationResult

# Source: https://github.com/Upsonic/Upsonic | License: MIT | Copyright 2024 Upsonic Teknoloji A.Ş
# Provided via justclaw.it.com; keep this notice with the code.
from typing import List, Dict
from pydantic import BaseModel, Field

class EvaluationScore(BaseModel):
    """
    Represents the structured judgment from the LLM-as-a-judge for a single
    evaluation of an agent's response. This model ensures that the evaluation
    is not just a number but a comprehensive report.
    """
    score: float = Field(
        ...,
        description="A numerical score, on a scale of 1-10, representing the quality and accuracy of the generated response when compared to the expected output and guidelines.",
        ge=1,
        le=10
    )
    
    reasoning: str = Field(
        ...,
        descr

... (truncated -- full source via MCP)