import pandas as pd
import numpy as np

def run_rl_inference(model, env):
    obs, _ = env.reset()
    done = False
    history = []

    while not done:
        # action is [market_choice, charge_fraction]
        action, _ = model.predict(obs, deterministic=True)
        
        # Capture state BEFORE the step for the dashboard
        current_step_idx = env.current_step
        prices = env.input_data.iloc[current_step_idx]
        
        # Step the environment
        obs, reward, terminated, truncated, _ = env.step(action)
        done = terminated or truncated
        
        # Logic for the dashboard
        market = "Ancillary (FCR)" if action[0] >= 0.5 else "Arbitrage"
        decision = "Idle"
        if market == "Arbitrage":
            if action[1] > 0.1: decision = "Sell (Discharge)"
            elif action[1] < -0.1: decision = "Buy (Charge)"

        history.append({
            "Timestamp": prices.name,
            "Market_Choice": market,
            "Decision": decision,
            "Action_Value": action[1],
            "Energy_Price": prices.get("energy", 0),
            "FCR_Price": prices.get("fcr", 0),
            "SoC": env.battery.soc,
            "Hourly_Revenue": reward
        })

    return pd.DataFrame(history)