bookapp/story/style_persona.py

import json
import os
import time
from core import config, utils
from ai import models as ai_models


def get_style_guidelines():
    defaults = {
        "ai_isms": [
            'testament to', 'tapestry', 'shiver down spine', 'unspoken agreement',
            'palpable tension', 'a sense of', 'suddenly', 'in that moment',
            'symphony of', 'dance of', 'azure', 'cerulean'
        ],
        "filter_words": [
            'felt', 'saw', 'heard', 'realized', 'decided', 'noticed', 'knew', 'thought'
        ]
    }
    path = os.path.join(config.DATA_DIR, "style_guidelines.json")
    if os.path.exists(path):
        try:
            user_data = utils.load_json(path)
            if user_data:
                if 'ai_isms' in user_data: defaults['ai_isms'] = user_data['ai_isms']
                if 'filter_words' in user_data: defaults['filter_words'] = user_data['filter_words']
        except: pass
    else:
        try:
            with open(path, 'w') as f: json.dump(defaults, f, indent=2)
        except: pass
    return defaults


def refresh_style_guidelines(model, folder=None):
    utils.log("SYSTEM", "Refreshing Style Guidelines via AI...")
    current = get_style_guidelines()

    prompt = f"""
    ROLE: Literary Editor
    TASK: Update 'Banned Words' lists for AI writing.

    INPUT_DATA:
    - CURRENT_AI_ISMS: {json.dumps(current.get('ai_isms', []))}
    - CURRENT_FILTER_WORDS: {json.dumps(current.get('filter_words', []))}

    INSTRUCTIONS:
    1. Review lists. Remove false positives.
    2. Add new common AI tropes (e.g. 'neon-lit', 'bustling', 'a sense of', 'mined', 'delved').
    3. Ensure robustness.

    OUTPUT_FORMAT (JSON): {{ "ai_isms": [strings], "filter_words": [strings] }}
    """
    try:
        response = model.generate_content(prompt)
        model_name = getattr(model, 'name', ai_models.logic_model_name)
        if folder: utils.log_usage(folder, model_name, response.usage_metadata)
        new_data = json.loads(utils.clean_json(response.text))

        if 'ai_isms' in new_data and 'filter_words' in new_data:
            path = os.path.join(config.DATA_DIR, "style_guidelines.json")
            with open(path, 'w') as f: json.dump(new_data, f, indent=2)
            utils.log("SYSTEM", "Style Guidelines updated.")
            return new_data
    except Exception as e:
        utils.log("SYSTEM", f"Failed to refresh guidelines: {e}")
    return current


def create_initial_persona(bp, folder):
    utils.log("SYSTEM", "Generating initial Author Persona based on genre/tone...")
    meta = bp.get('book_metadata', {})
    style = meta.get('style', {})

    prompt = f"""
    ROLE: Creative Director
    TASK: Create a fictional 'Author Persona'.

    METADATA:
    - TITLE: {meta.get('title')}
    - GENRE: {meta.get('genre')}
    - TONE: {style.get('tone')}
    - AUDIENCE: {meta.get('target_audience')}

    OUTPUT_FORMAT (JSON): {{ "name": "Pen Name", "bio": "Description of writing style (voice, sentence structure, vocabulary)...", "age": "...", "gender": "..." }}
    """
    try:
        response = ai_models.model_logic.generate_content(prompt)
        utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
        return json.loads(utils.clean_json(response.text))
    except Exception as e:
        utils.log("SYSTEM", f"Persona generation failed: {e}")
        return {"name": "AI Author", "bio": "Standard, balanced writing style."}


def refine_persona(bp, text, folder):
    utils.log("SYSTEM", "Refining Author Persona based on recent chapters...")
    ad = bp.get('book_metadata', {}).get('author_details', {})
    current_bio = ad.get('bio', 'Standard style.')

    prompt = f"""
    ROLE: Literary Stylist
    TASK: Refine Author Bio based on text sample.

    INPUT_DATA:
    - TEXT_SAMPLE: {text[:3000]}
    - CURRENT_BIO: {current_bio}

    GOAL: Ensure future chapters sound exactly like the sample. Highlight quirks, patterns, vocabulary.

    OUTPUT_FORMAT (JSON): {{ "bio": "Updated bio..." }}
    """
    try:
        response = ai_models.model_logic.generate_content(prompt)
        utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
        new_bio = json.loads(utils.clean_json(response.text)).get('bio')
        if new_bio:
            ad['bio'] = new_bio
            utils.log("SYSTEM", "  -> Persona bio updated.")
            return ad
    except: pass
    return ad


def update_persona_sample(bp, folder):
    utils.log("SYSTEM", "Extracting author persona from manuscript...")

    ms_path = os.path.join(folder, "manuscript.json")
    if not os.path.exists(ms_path): return
    ms = utils.load_json(ms_path)
    if not ms: return

    full_text = "\n".join([c.get('content', '') for c in ms])
    if len(full_text) < 500: return

    if not os.path.exists(config.PERSONAS_DIR): os.makedirs(config.PERSONAS_DIR)

    meta = bp.get('book_metadata', {})
    safe_title = utils.sanitize_filename(meta.get('title', 'book'))[:20]
    timestamp = int(time.time())
    filename = f"sample_{safe_title}_{timestamp}.txt"
    filepath = os.path.join(config.PERSONAS_DIR, filename)

    sample_text = full_text[:3000]
    with open(filepath, 'w', encoding='utf-8') as f: f.write(sample_text)

    author_name = meta.get('author', 'Unknown Author')

    personas = {}
    if os.path.exists(config.PERSONAS_FILE):
        try:
            with open(config.PERSONAS_FILE, 'r') as f: personas = json.load(f)
        except: pass

    if author_name not in personas:
        utils.log("SYSTEM", f"Generating new persona profile for '{author_name}'...")
        prompt = f"""
        ROLE: Literary Analyst
        TASK: Analyze writing style (Tone, Voice, Vocabulary).
        TEXT: {sample_text[:1000]}
        OUTPUT: 1-sentence author bio.
        """
        try:
            response = ai_models.model_logic.generate_content(prompt)
            utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
            bio = response.text.strip()
        except: bio = "Style analysis unavailable."

        personas[author_name] = {
            "name": author_name,
            "bio": bio,
            "sample_files": [filename],
            "sample_text": sample_text[:500]
        }
    else:
        utils.log("SYSTEM", f"Updating persona '{author_name}' with new sample.")
        if 'sample_files' not in personas[author_name]: personas[author_name]['sample_files'] = []
        if filename not in personas[author_name]['sample_files']:
            personas[author_name]['sample_files'].append(filename)

    with open(config.PERSONAS_FILE, 'w') as f: json.dump(personas, f, indent=2)