inference.py

from fastapi import FastAPI
from env import DeliveryEnv
import random

app = FastAPI()
env = DeliveryEnv()

ACTIONS = ["up", "down", "left", "right", "pickup", "drop"]

@app.get("/")
def home():
    return {"message": "Environment running"}

@app.get("/reset")
def reset():
    return env.reset()

@app.get("/step")
def step():
    action = random.choice(ACTIONS)
    state, reward, done, _ = env.step(action)
    return {
        "state": state,
        "reward": reward,
        "done": done
    }