import random
import torch
import torch.nn.functional as F
from model.brain import model, tokenizer, DEVICE, score_sentence
from model.trainer import train_on_message
from model.dreams import save_dream, load_dreams
from model.journal import record_to_journal
from model.dynamic_expand import expand_model_if_needed
from context.context import load_context

recent_dreams = []


def daydream():
    model.eval()
    seed = torch.tensor([random.randint(0, tokenizer.next_id - 1)], device=DEVICE).unsqueeze(0)
    dream = []

    for _ in range(12):
        out = model(seed)
        logits = out[:, -1, :]
        probs = F.softmax(logits, dim=-1)
        token = torch.multinomial(probs, num_samples=1)
        dream.append(token.item())
        seed = torch.cat([seed, token], dim=1)

    sentence = tokenizer.detokenize(dream)
    score = score_sentence(sentence)

    if score > 0.5:
        save_dream(sentence, score)
        record_to_journal(sentence)
        train_on_message(sentence)

    if len(recent_dreams) > 10:
        recent_dreams.pop(0)


def replay_dreams():
    expand_model_if_needed()

    dreams = load_dreams()
    context = load_context()

    if not dreams or not context:
        return

    selected_dreams = random.sample(dreams, min(len(dreams), 5))
    selected_contexts = random.sample(context, min(len(context), 5))

    # Mix dreams and past contexts into a chaotic dream
    all_sources = [d["sentence"] for d in selected_dreams] + [c["text"] for c in selected_contexts]
    random.shuffle(all_sources)

    mixed_sentence = " ".join(random.sample(all_sources, min(len(all_sources), 3)))

    if mixed_sentence:
        train_on_message(mixed_sentence, source="dream")