Mike Wichers
d2c65f010a
1. editor.py — Fix rewrite_chapter_content to use model_writer (was model_logic). Chapter rewrites now use the creative writing model, not the cheaper analysis model. 2. editor.py — evaluate_chapter_quality now uses keep_head=True so the evaluator sees the chapter opening (engagement hook, sensory anchoring) as well as the ending; long chapters no longer scored on tail only. 3. editor.py — Consistency analysis sampling upgraded to head+middle+tail (was head+tail), giving the LLM a complete view of each chapter's events. 4. writer.py — max_attempts is now adaptive: climax/resolution chapters (position >= 0.75) receive 3 refinement attempts; others keep 2. 5. writer.py — Polish-skip threshold tightened from 0.012 to 0.008 (1 filter word per 125 words vs. 1 per 83 words), so more borderline drafts are cleaned. 6. style_persona.py — Persona validation sample increased from 200 to 400 words for more reliable voice quality assessment. Version bumped: 3.0 → 3.1 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
306 lines
12 KiB
Python
306 lines
12 KiB
Python
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',
|
|
'delved', 'mined', 'neon-lit', 'bustling', 'weaved', 'intricately',
|
|
'a reminder that', 'couldn\'t help but', 'it occurred to',
|
|
'the air was thick with', 'etched in', 'a wave of', 'wash of emotion',
|
|
'intertwined', 'navigate', 'realm', 'in the grand scheme',
|
|
'at the end of the day', 'painting a picture', 'a dance between',
|
|
'the weight of', 'visceral reminder', 'stark reminder',
|
|
'a symphony', 'a mosaic', 'rich tapestry', 'whirlwind of',
|
|
'his/her heart raced', 'time seemed to slow', 'the world fell away',
|
|
'needless to say', 'it goes without saying', 'importantly',
|
|
'it is worth noting', 'commendable', 'meticulous', 'pivotal',
|
|
'in conclusion', 'overall', 'in summary', 'to summarize'
|
|
],
|
|
"filter_words": [
|
|
'felt', 'saw', 'heard', 'realized', 'decided', 'noticed', 'knew', 'thought',
|
|
'wondered', 'seemed', 'appeared', 'looked like', 'watched', 'observed', 'sensed'
|
|
]
|
|
}
|
|
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 validate_persona(bp, persona_details, folder):
|
|
"""Validate a newly created persona by generating a 200-word sample and scoring it.
|
|
|
|
Experiment 6 (Iterative Persona Validation): generates a test passage in the
|
|
persona's voice and evaluates voice quality before accepting it. This front-loads
|
|
quality assurance so Phase 3 starts with a well-calibrated author voice.
|
|
|
|
Returns (is_valid: bool, score: int). Threshold: score >= 7 → accepted.
|
|
"""
|
|
meta = bp.get('book_metadata', {})
|
|
genre = meta.get('genre', 'Fiction')
|
|
tone = meta.get('style', {}).get('tone', 'balanced')
|
|
name = persona_details.get('name', 'Unknown Author')
|
|
bio = persona_details.get('bio', 'Standard style.')
|
|
|
|
sample_prompt = f"""
|
|
ROLE: Fiction Writer
|
|
TASK: Write a 400-word opening scene that perfectly demonstrates this author's voice.
|
|
|
|
AUTHOR_PERSONA:
|
|
Name: {name}
|
|
Style/Bio: {bio}
|
|
|
|
GENRE: {genre}
|
|
TONE: {tone}
|
|
|
|
RULES:
|
|
- Exactly ~400 words of prose (no chapter header, no commentary)
|
|
- Must reflect the persona's stated sentence structure, vocabulary, and voice
|
|
- Show, don't tell — no filter words (felt, saw, heard, realized, noticed)
|
|
- Deep POV: immerse the reader in a character's immediate experience
|
|
|
|
OUTPUT: Prose only.
|
|
"""
|
|
try:
|
|
resp = ai_models.model_logic.generate_content(sample_prompt)
|
|
utils.log_usage(folder, ai_models.model_logic.name, resp.usage_metadata)
|
|
sample_text = resp.text
|
|
except Exception as e:
|
|
utils.log("SYSTEM", f" -> Persona validation sample failed: {e}. Accepting persona.")
|
|
return True, 7
|
|
|
|
# Lightweight scoring: focused on voice quality (not full 13-rubric)
|
|
score_prompt = f"""
|
|
ROLE: Literary Editor
|
|
TASK: Score this prose sample for author voice quality.
|
|
|
|
EXPECTED_PERSONA:
|
|
{bio}
|
|
|
|
SAMPLE:
|
|
{sample_text}
|
|
|
|
CRITERIA:
|
|
1. Does the prose reflect the stated author persona? (voice, register, sentence style)
|
|
2. Is the prose free of filter words (felt, saw, heard, noticed, realized)?
|
|
3. Is it deep POV — immediate, immersive, not distant narration?
|
|
4. Is there genuine sentence variety and strong verb choice?
|
|
|
|
SCORING (1-10):
|
|
- 8-10: Voice is distinct, matches persona, clean deep POV
|
|
- 6-7: Reasonable voice, minor filter word issues
|
|
- 1-5: Generic AI prose, heavy filter words, or persona not reflected
|
|
|
|
OUTPUT_FORMAT (JSON): {{"score": int, "reason": "One sentence."}}
|
|
"""
|
|
try:
|
|
resp2 = ai_models.model_logic.generate_content(score_prompt)
|
|
utils.log_usage(folder, ai_models.model_logic.name, resp2.usage_metadata)
|
|
data = json.loads(utils.clean_json(resp2.text))
|
|
score = int(data.get('score', 7))
|
|
reason = data.get('reason', '')
|
|
is_valid = score >= 7
|
|
utils.log("SYSTEM", f" -> Persona validation: {score}/10 {'✅ Accepted' if is_valid else '❌ Rejected'} — {reason}")
|
|
return is_valid, score
|
|
except Exception as e:
|
|
utils.log("SYSTEM", f" -> Persona scoring failed: {e}. Accepting persona.")
|
|
return True, 7
|
|
|
|
|
|
def refine_persona(bp, text, folder, pov_character=None):
|
|
utils.log("SYSTEM", "Refining Author Persona based on recent chapters...")
|
|
ad = bp.get('book_metadata', {}).get('author_details', {})
|
|
|
|
# If a POV character is given and has a voice_profile, refine that instead
|
|
if pov_character:
|
|
for char in bp.get('characters', []):
|
|
if char.get('name') == pov_character and char.get('voice_profile'):
|
|
vp = char['voice_profile']
|
|
current_bio = vp.get('bio', 'Standard style.')
|
|
prompt = f"""
|
|
ROLE: Literary Stylist
|
|
TASK: Refine a POV character's voice profile based on the text sample.
|
|
|
|
INPUT_DATA:
|
|
- TEXT_SAMPLE: {text[:3000]}
|
|
- CHARACTER: {pov_character}
|
|
- CURRENT_VOICE_BIO: {current_bio}
|
|
|
|
GOAL: Ensure future chapters for this POV character sound exactly like the sample. Highlight quirks, patterns, vocabulary specific to this character's perspective.
|
|
|
|
OUTPUT_FORMAT (JSON): {{ "bio": "Updated voice 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:
|
|
char['voice_profile']['bio'] = new_bio
|
|
utils.log("SYSTEM", f" -> Voice profile bio updated for '{pov_character}'.")
|
|
except Exception as e:
|
|
utils.log("SYSTEM", f" -> Voice profile refinement failed for '{pov_character}': {e}")
|
|
return ad # Return author_details unchanged
|
|
|
|
# Default: refine the main author persona bio
|
|
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')
|
|
|
|
# Use a local file mirror for the engine context (runs outside Flask app context)
|
|
_personas_file = os.path.join(config.PERSONAS_DIR, "personas.json")
|
|
personas = {}
|
|
if os.path.exists(_personas_file):
|
|
try:
|
|
with open(_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(_personas_file, 'w') as f: json.dump(personas, f, indent=2)
|