hydra953/invoice-processing-env

1"""Pydantic models for the Invoice Processing OpenEnv environment."""2 3from typing import Optional4from pydantic import BaseModel, Field5 6 7class InvoiceAction(BaseModel):8    """Action submitted by the agent — a JSON answer string and optional explanation."""9    answer: str = Field(..., description="JSON string with extracted/processed invoice data")10    explanation: str = Field(default="", description="Optional reasoning text")11 12 13class InvoiceObservation(BaseModel):14    """Observation returned to the agent after each step or reset."""15    invoice_text: str = Field(default="", description="The raw invoice content to process")16    context: str = Field(default="", description="Additional context (PO data, exchange rates, historical invoices)")17    task_description: str = Field(default="", description="What the agent must accomplish")18    task_id: str = Field(default="", description="easy | medium | hard")19    difficulty: str = Field(default="", description="Difficulty level")20    attempt_number: int = Field(default=0, description="Current attempt count")21    max_attempts: int = Field(default=5, description="Maximum allowed attempts")22    feedback: str = Field(default="", description="Grader feedback from prior attempt")23    hint: str = Field(default="", description="Hint revealed after 2 failed attempts")24    error_message: str = Field(default="", description="Error message if agent JSON was malformed")25    done: bool = Field(default=False, description="Whether the episode is over")26    reward: float = Field(default=0.0, description="Score 0.0-1.0")27 28 29class InvoiceState(BaseModel):30    """Internal environment state tracked across steps."""31    episode_id: str = Field(default="")32    step_count: int = Field(default=0)33    task_id: str = Field(default="")34    difficulty: str = Field(default="")35    max_attempts: int = Field(default=5)36    last_score: float = Field(default=0.0)37    completed: bool = Field(default=False)38