"""
Exp 23: Clean slate — generated_road, solid barriers, simple reward.

What changed from exp22:
  - Single track: generated_road on port 9091 only (diagnose one track first)
  - Simulator now uses BoxCollider barriers + CCD on the car Rigidbody.
    The car physically cannot escape. No Python-side exploit patches needed.
  - Reward wrapper v7: speed × CTE_quality + efficiency gate + no-progress kill.
    Removed: CTE-patience termination, solid_hit detection, wedge detection,
             MAX_EPISODE_SECONDS hard cap.
  - StuckTerminationWrapper: max_episode_seconds raised to 120s (genuine safety
    net only — physics handles the actual containment).
  - No warm-start: fresh PPO weights. Previous warm-starts were trained under
    broken reward/barrier conditions and add more noise than signal.
  - Total steps: 200k (more room to learn with clean signal).
"""
import os
import sys
import time
from datetime import datetime

sys.path.insert(0, '/home/paulh/projects/donkeycar-rl-autoresearch/agent')

import gymnasium as gym
import numpy as np
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv, VecTransposeImage

from donkeycar_sb3_runner import ThrottleClampWrapper
from multitrack_runner import StuckTerminationWrapper
from reward_wrapper import SpeedRewardWrapper


HOST             = 'localhost'
THROTTLE_MIN     = 0.2
LR               = 0.0003
TOTAL_STEPS      = 200_000
CHECKPOINT_EVERY = 10_000
SAVE_DIR = '/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/exp23-generated-road-clean'
os.makedirs(SAVE_DIR, exist_ok=True)

# Reward wrapper v7 params — clean and minimal
EFFICIENCY_WINDOW   = 30
MIN_EFFICIENCY      = 0.15
MAX_CTE             = 8.0
MIN_LAP_TIME        = 12.0
PROGRESS_PATIENCE   = 100   # steps without new waypoint → terminate

# StuckTerminationWrapper — generous limit, physics does the real work now
MAX_STUCK_SECONDS   = 5.0
MAX_EPISODE_SECONDS = 120.0  # safety net only


def log(msg):
    print(f'[{datetime.now().strftime("%H:%M:%S")}] {msg}', flush=True)


def make_env(track_id, port):
    def _init():
        raw = gym.make(track_id, conf={'host': HOST, 'port': port})
        env = ThrottleClampWrapper(raw, throttle_min=THROTTLE_MIN)
        env = StuckTerminationWrapper(
            env,
            stuck_steps=40,
            min_displacement=0.5,
            max_stuck_seconds=MAX_STUCK_SECONDS,
            max_episode_seconds=MAX_EPISODE_SECONDS,
        )
        env = SpeedRewardWrapper(
            env,
            window_size=EFFICIENCY_WINDOW,
            min_efficiency=MIN_EFFICIENCY,
            max_cte=MAX_CTE,
            min_lap_time=MIN_LAP_TIME,
            progress_patience=PROGRESS_PATIENCE,
        )
        return env
    return _init


def make_eval_env(track_id, port):
    inner = make_env(track_id, port)()
    return VecTransposeImage(DummyVecEnv([lambda e=inner: e]))


log('=' * 60)
log('Exp 23: generated_road — clean barriers, clean reward')
log(f'  Sim: {HOST}:9091 -> generated_road')
log(f'  throttle_min={THROTTLE_MIN}, lr={LR}, total={TOTAL_STEPS:,}')
log(f'  Reward: v7 (speed×CTE, efficiency gate, no-progress kill)')
log(f'  Max stuck: {MAX_STUCK_SECONDS}s, episode cap: {MAX_EPISODE_SECONDS}s (safety net)')
log(f'  Progress patience: {PROGRESS_PATIENCE} steps')
log(f'  Checkpoints every {CHECKPOINT_EVERY:,} steps')
log('=' * 60)

log('Creating DummyVecEnv on generated_road...')
env = DummyVecEnv([make_env('donkey-generated-roads-v0', 9091)])
env = VecTransposeImage(env)
log(f'  VecEnv num_envs={env.num_envs}, obs={env.observation_space.shape}')

model = PPO(
    'CnnPolicy',
    env,
    learning_rate=LR,
    n_steps=2048,
    batch_size=64,
    n_epochs=10,
    gamma=0.99,
    gae_lambda=0.95,
    clip_range=0.2,
    ent_coef=0.01,
    verbose=1,
    device='cpu',
)

# Write PID for external monitoring
pid_path = os.path.join(SAVE_DIR, 'current.pid')
with open(pid_path, 'w') as f:
    f.write(str(os.getpid()))

log(f'Fresh PPO model created. Starting training...')

best_total_steps  = float('-inf')
best_total_reward = float('-inf')
steps_done        = 0
run_tag           = datetime.now().strftime('%Y-%m-%d_%H%M%S') + '_clean'
log_path          = os.path.join(SAVE_DIR, f'run_{run_tag}.log')
best_model_path   = os.path.join(SAVE_DIR, 'best_model.zip')

import logging
logging.basicConfig(
    level=logging.INFO,
    format='%(message)s',
    handlers=[logging.FileHandler(log_path), logging.StreamHandler(sys.stdout)],
)
file_log = logging.getLogger('exp23')

def flog(msg):
    ts = datetime.now().strftime('%H:%M:%S')
    file_log.info(f'[{ts}] {msg}')

flog('=' * 60)
flog(f'Exp 23 started — PID {os.getpid()}')
flog(f'Log: {log_path}')
flog('=' * 60)

while steps_done < TOTAL_STEPS:
    seg_steps = min(CHECKPOINT_EVERY, TOTAL_STEPS - steps_done)
    model.learn(total_timesteps=seg_steps, reset_num_timesteps=False)
    steps_done += seg_steps

    ckpt = os.path.join(SAVE_DIR, f'checkpoint_{steps_done:07d}')
    model.save(ckpt)
    model.save(os.path.join(SAVE_DIR, 'model'))
    flog(f'[{steps_done:,}/{TOTAL_STEPS:,}] Checkpoint saved: {ckpt}.zip')

    # Mid-training eval on generated_road
    try:
        obs = env.reset()
        ep_rewards = np.zeros(env.num_envs)
        ep_steps   = np.zeros(env.num_envs)
        done_mask  = np.zeros(env.num_envs, dtype=bool)

        for _ in range(2000):
            action, _ = model.predict(obs, deterministic=True)
            obs, rewards, dones, infos = env.step(action)
            for i in range(env.num_envs):
                if not done_mask[i]:
                    ep_rewards[i] += rewards[i]
                    ep_steps[i]   += 1
                    if dones[i]:
                        done_mask[i] = True
            if done_mask.all():
                break

        total_steps_eval  = int(ep_steps.sum())
        total_reward_eval = float(ep_rewards.sum())

        status = '✅' if ep_steps[0] >= 2000 else f'❌@{int(ep_steps[0])}'
        flog(f'  Eval: gen_road={total_reward_eval:.1f}r/{int(ep_steps[0])}s {status}')

        if (total_steps_eval > best_total_steps
                or (total_steps_eval == best_total_steps
                    and total_reward_eval > best_total_reward)):
            best_total_steps  = total_steps_eval
            best_total_reward = total_reward_eval
            model.save(best_model_path)
            flog(f'  NEW BEST: steps={best_total_steps} reward={best_total_reward:.1f}')

    except Exception as e:
        flog(f'  Eval error: {e}')

env.close()

# ── Final evaluation ──────────────────────────────────────────────────────────
flog('=' * 60)
flog('FINAL EVALUATION: best_model on generated_road')
flog('=' * 60)

EVAL_SETS     = 3
EVAL_MAX_STEPS = 2000

steps_list  = []
reward_list = []

for s in range(1, EVAL_SETS + 1):
    try:
        eval_env   = make_eval_env('donkey-generated-roads-v0', 9091)
        eval_model = PPO.load(best_model_path, env=eval_env, device='cpu')
        obs        = eval_env.reset()
        done       = False
        total_s    = 0
        total_r    = 0.0

        while not done and total_s < EVAL_MAX_STEPS:
            action, _ = eval_model.predict(obs, deterministic=True)
            result    = eval_env.step(action)
            obs, r, done = result[0], result[1], result[2]
            if hasattr(done, '__len__'):
                done = bool(done[0])
            total_r += float(r) if not hasattr(r, '__len__') else float(r[0])
            total_s += 1

        status = '✅' if total_s >= EVAL_MAX_STEPS else f'❌@{total_s}'
        flog(f'  Set {s}: {total_r:.1f}r / {total_s}s {status}')
        steps_list.append(total_s)
        reward_list.append(total_r)
        eval_env.close()

    except Exception as e:
        flog(f'  Set {s} error: {e}')

if steps_list:
    flog(f'  Mean: {np.mean(steps_list):.0f} steps / {np.mean(reward_list):.1f} reward')

flog('Exp 23 complete.')