"""
Data models for the CI/CD Doctor RL environment.
"""

from pydantic import BaseModel, Field
from typing import Dict, Any, List


class PipelineAction(BaseModel):
    command: str  # raw string the agent types, e.g. "cat requirements.txt"2


class PipelineObservation(BaseModel):
    stdout: str
    exit_code: int
    pipeline_status: str  # "not_run" | "running" | "passed" | "failed"
    steps_remaining: int
    done: bool = False
    reward: float = 0.0


class PipelineState(BaseModel):
    episode_id: str
    task: str  # "easy" | "medium" | "hard"
    filesystem: Dict[str, str]
    pipeline_status: str
    step_count: int
    done: bool
    total_reward: float
    answer_key: Dict[str, Any]  # never sent to agent, used by grader
    milestones: List[str] = Field(default_factory=list)  # grader-only, tracks unlocked reward tiers