"""
Exp 21: Parallel DummyVecEnv — generated_road + generated_track, warm-started.

Rationale:
  - generated_road specialist already exists and drives road markings well.
  - generated_road and generated_track share the same road semantics.
  - Background adaptation is the goal here, not mountain physics.

Design:
  - Warm-start from Phase 2 champion (generated_road specialist).
  - Train in parallel on TWO sim instances:
      Sim 1: generated_road  on port 9091
      Sim 2: generated_track on port 9093
  - Use the old v4 reward that worked for the flat road tracks.
  - Keep the wrapper chain minimal: ThrottleClamp + V4 reward only.
"""
import sys, os, time
from collections import deque
from datetime import datetime

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

from donkeycar_sb3_runner import ThrottleClampWrapper
from multitrack_runner import StuckTerminationWrapper
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv, VecTransposeImage
from stable_baselines3.common.utils import get_schedule_fn
import gymnasium as gym
import numpy as np


HOST             = 'localhost'
THROTTLE_MIN     = 0.2
LR               = 0.000225
TOTAL_STEPS      = 150_000
CHECKPOINT_EVERY = 10_000
SAVE_DIR         = '/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/exp21-generated-pair-warm-v4'
WARM_PATH        = '/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/champion/model.zip'
os.makedirs(SAVE_DIR, exist_ok=True)


class V4RewardWrapper(gym.Wrapper):
    """
    v4 reward from the successful flat-road experiments:
      reward = base_cte * efficiency * (1 + speed_scale * speed)
    """
    def __init__(self, env, speed_scale=0.1, window_size=60,
                 min_efficiency=0.05, max_cte=8.0):
        super().__init__(env)
        self.speed_scale    = speed_scale
        self.min_efficiency = min_efficiency
        self.max_cte        = max_cte
        self._pos_history   = deque(maxlen=window_size + 1)

    def reset(self, **kwargs):
        self._pos_history.clear()
        return self.env.reset(**kwargs)

    def step(self, action):
        result = self.env.step(action)
        if len(result) == 5:
            obs, _sim_reward, terminated, truncated, info = result
            done = terminated or truncated
        else:
            obs, _sim_reward, done, info = result
            terminated, truncated = done, False

        reward = self._compute_reward(done, info)

        if len(result) == 5:
            return obs, reward, terminated, truncated, info
        return obs, reward, done, info

    def _compute_reward(self, done, info):
        if done:
            return -1.0

        pos = info.get('pos', None)
        if pos is not None:
            try:
                self._pos_history.append(np.array(list(pos)[:3], dtype=np.float64))
            except (TypeError, ValueError):
                pass

        try:
            cte = float(info.get('cte', 0.0) or 0.0)
        except (TypeError, ValueError):
            cte = 0.0
        base = 1.0 - min(abs(cte) / self.max_cte, 1.0)

        efficiency = self._compute_efficiency()
        eff = max(0.0, (efficiency - self.min_efficiency) / (1.0 - self.min_efficiency))

        try:
            speed = max(0.0, float(info.get('speed', 0.0) or 0.0))
        except (TypeError, ValueError):
            speed = 0.0

        return base * eff * (1.0 + self.speed_scale * speed)

    def _compute_efficiency(self):
        if len(self._pos_history) < 3:
            return 1.0
        positions = list(self._pos_history)
        net = np.linalg.norm(positions[-1] - positions[0])
        total = sum(
            np.linalg.norm(positions[i + 1] - positions[i])
            for i in range(len(positions) - 1)
        )
        return float(net / total) if total > 1e-6 else 1.0


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=12.0,
            max_episode_seconds=30.0,
        )
        env = V4RewardWrapper(env, speed_scale=0.1, window_size=60,
                              min_efficiency=0.05, max_cte=8.0)
        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 21: generated_road + generated_track, warm-started, v4 reward')
log(f'  Warm start: {WARM_PATH}')
log(f'  Sim 1: {HOST}:9091 -> generated_road')
log(f'  Sim 2: {HOST}:9093 -> generated_track')
log(f'  throttle_min={THROTTLE_MIN}, lr={LR}, total={TOTAL_STEPS:,}')
log('  Termination: StuckTerminationWrapper enabled')
log(f'  Checkpoints: every {CHECKPOINT_EVERY:,} steps')
log('=' * 60)

log('Creating DummyVecEnv with the two road tracks...')
env = DummyVecEnv([
    make_env('donkey-generated-roads-v0', 9091),
    make_env('donkey-generated-track-v0', 9093),
])
env = VecTransposeImage(env)
log(f'  VecEnv num_envs={env.num_envs}, obs={env.observation_space.shape}')

if not os.path.exists(WARM_PATH):
    raise FileNotFoundError(WARM_PATH)

model = PPO.load(WARM_PATH, env=env, device='cpu')
model.learning_rate = LR
try:
    model.lr_schedule = get_schedule_fn(LR)
except Exception:
    model.lr_schedule = None
try:
    for pg in model.policy.optimizer.param_groups:
        pg['lr'] = LR
except Exception:
    pass

log('Warm-start model attached. Starting training...')

best_total_steps = float('-inf')
best_total_reward = float('-inf')
steps_done = 0

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'))
    log(f'[{steps_done:,}/{TOTAL_STEPS:,}] Checkpoint saved: {ckpt}.zip')

    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

        status0 = '✅' if ep_steps[0] >= 2000 else f'❌@{int(ep_steps[0])}'
        status1 = '✅' if ep_steps[1] >= 2000 else f'❌@{int(ep_steps[1])}'
        log(f'  Eval: gen_road={ep_rewards[0]:.1f}r/{int(ep_steps[0])}s {status0}  '
            f'gen_track={ep_rewards[1]:.1f}r/{int(ep_steps[1])}s {status1}')

        total_steps_eval = ep_steps.sum()
        total_reward = ep_rewards.sum()
        if (total_steps_eval > best_total_steps or
            (total_steps_eval == best_total_steps and total_reward > best_total_reward)):
            best_total_steps = total_steps_eval
            best_total_reward = total_reward
            model.save(os.path.join(SAVE_DIR, 'best_model'))
            log(f'  NEW BEST: combined steps={int(best_total_steps)} reward={best_total_reward:.1f}')
    except Exception as e:
        log(f'  Eval error: {e}')
        import traceback; traceback.print_exc()

model.save(os.path.join(SAVE_DIR, 'model'))
log(f'\nTraining complete. Best combined steps: {int(best_total_steps)}')

env.close()
time.sleep(5)

log('\n' + '=' * 60)
log('FINAL EVALUATION: best_model on generated_road, generated_track, mini_monaco')
log('=' * 60)

EVAL_TRACKS = [
    ('donkey-generated-roads-v0',  'generated_road'),
    ('donkey-generated-track-v0',  'generated_track'),
    ('donkey-minimonaco-track-v0', 'mini_monaco'),
]
EVAL_PORT      = 9091
EVAL_SETS      = 3
EVAL_MAX_STEPS = 2000

best_model_path = os.path.join(SAVE_DIR, 'best_model.zip')
results_by_track = {}

for track_id, track_name in EVAL_TRACKS:
    log(f'\n--- {track_name} ---')
    steps_list = []

    for s in range(1, EVAL_SETS + 1):
        try:
            eval_env = make_eval_env(track_id, EVAL_PORT)
            eval_model = PPO.load(best_model_path, env=eval_env, device='cpu')

            obs = eval_env.reset()
            total_r, total_s, done = 0.0, 0, False
            while not done and total_s < EVAL_MAX_STEPS:
                action, _ = eval_model.predict(obs, deterministic=True)
                result = eval_env.step(action)
                if len(result) == 4:
                    obs, r, d, info = result
                    done = bool(d[0])
                else:
                    obs, r, t, tr, info = result
                    done = bool(t[0] or tr[0])
                total_r += float(r[0])
                total_s += 1

            status = '✅' if total_s >= EVAL_MAX_STEPS else f'❌@{total_s}'
            log(f'  Set {s}: {total_r:.1f}r / {total_s}s {status}')
            steps_list.append(total_s)
            eval_env.close()
            time.sleep(3)
        except Exception as e:
            log(f'  Set {s}: ERROR - {e}')
            steps_list.append(0)
            time.sleep(3)

    mean_steps = np.mean(steps_list) if steps_list else 0
    results_by_track[track_name] = steps_list
    log(f'  Mean: {mean_steps:.0f} steps')

log('\n' + '=' * 60)
log('SUMMARY')
log('=' * 60)
for track_name, steps_list in results_by_track.items():
    steps_str = '/'.join(str(s) for s in steps_list)
    mean = np.mean(steps_list)
    verdict = '✅' if mean >= 1500 else '⚠️' if mean >= 500 else '❌'
    log(f'  {verdict} {track_name:20s}: {steps_str}  mean={mean:.0f}')

log('\n=== Exp 21 COMPLETE ===')