Files
bookapp/story/bible_tracker.py
Mike Wichers ff5093a5f9 fix: Pipeline hardening — error handling, token efficiency, and robustness
core/utils.py:
- estimate_tokens: improved heuristic 4 chars/token → 3.5 chars/token (more accurate)
- truncate_to_tokens: added keep_head=True mode for head+tail truncation (better
  context retention for story summaries that need both opening and recent content)
- load_json: explicit exception handling (json.JSONDecodeError, OSError) with log
  instead of silent returns; added utf-8 encoding with error replacement
- log_image_attempt: replaced bare except with (json.JSONDecodeError, OSError);
  added utf-8 encoding to output write
- log_usage: replaced bare except with AttributeError for token count extraction

story/bible_tracker.py:
- merge_selected_changes: wrapped all int() key casts (char idx, book num, beat idx)
  in try/except with meaningful log warning instead of crashing on malformed keys
- harvest_metadata: replaced bare except:pass with except Exception as e + log message

cli/engine.py:
- Persona validation: added warning when all 3 attempts fail and substandard persona
  is accepted — flags elevated voice-drift risk for the run
- Lore index updates: throttled from every chapter to every 3 chapters; lore is
  stable after the first few chapters (~10% token saving per book)
- Mid-gen consistency check: now samples first 2 + last 8 chapters instead of passing
  full manuscript — caps token cost regardless of book length

story/writer.py:
- Two-pass polish: added local filter-word density check (no API call); skips the
  Pro polish if density < 1 per 83 words — saves ~8K tokens on already-clean drafts
- Polish prompt: added prev_context_block for continuity — polished chapter now
  maintains seamless flow from the previous chapter's ending

marketing/fonts.py:
- Separated requests.exceptions.Timeout with specific log message vs generic failure
- Added explicit log message when Roboto fallback also fails (returns None)

marketing/blurb.py:
- Added word count trim: blurbs > 220 words trimmed to last sentence within 220 words
- Changed bare except to except Exception as e with log message
- Added utf-8 encoding to file writes; logs final word count

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-22 22:31:22 -05:00

212 lines
9.4 KiB
Python

import json
from core import utils
from ai import models as ai_models
def merge_selected_changes(original, draft, selected_keys):
def sort_key(k):
return [int(p) if p.isdigit() else p for p in k.split('.')]
selected_keys.sort(key=sort_key)
for key in selected_keys:
parts = key.split('.')
if parts[0] == 'meta' and len(parts) == 2:
field = parts[1]
if field == 'tone':
original['project_metadata']['style']['tone'] = draft['project_metadata']['style']['tone']
elif field in original['project_metadata']:
original['project_metadata'][field] = draft['project_metadata'][field]
elif parts[0] == 'char' and len(parts) >= 2:
try:
idx = int(parts[1])
except (ValueError, IndexError):
utils.log("SYSTEM", f"⚠️ Skipping malformed bible merge key: '{key}'")
continue
if idx < len(draft['characters']):
if idx < len(original['characters']):
original['characters'][idx] = draft['characters'][idx]
else:
original['characters'].append(draft['characters'][idx])
elif parts[0] == 'book' and len(parts) >= 2:
try:
book_num = int(parts[1])
except (ValueError, IndexError):
utils.log("SYSTEM", f"⚠️ Skipping malformed bible merge key: '{key}'")
continue
orig_book = next((b for b in original['books'] if b['book_number'] == book_num), None)
draft_book = next((b for b in draft['books'] if b['book_number'] == book_num), None)
if draft_book:
if not orig_book:
original['books'].append(draft_book)
original['books'].sort(key=lambda x: x.get('book_number', 999))
continue
if len(parts) == 2:
orig_book['title'] = draft_book['title']
orig_book['manual_instruction'] = draft_book['manual_instruction']
elif len(parts) == 4 and parts[2] == 'beat':
try:
beat_idx = int(parts[3])
except (ValueError, IndexError):
utils.log("SYSTEM", f"⚠️ Skipping malformed beat merge key: '{key}'")
continue
if beat_idx < len(draft_book['plot_beats']):
while len(orig_book['plot_beats']) <= beat_idx:
orig_book['plot_beats'].append("")
orig_book['plot_beats'][beat_idx] = draft_book['plot_beats'][beat_idx]
return original
def filter_characters(chars):
blacklist = ['name', 'character name', 'role', 'protagonist', 'antagonist', 'love interest', 'unknown', 'tbd', 'todo', 'hero', 'villain', 'main character', 'side character']
return [c for c in chars if c.get('name') and c.get('name').lower().strip() not in blacklist]
def update_tracking(folder, chapter_num, chapter_text, current_tracking):
utils.log("TRACKER", f"Updating world state & character visuals for Ch {chapter_num}...")
prompt = f"""
ROLE: Continuity Tracker
TASK: Update the Story Bible based on the new chapter.
INPUT_TRACKING:
{json.dumps(current_tracking)}
NEW_TEXT:
{chapter_text[:20000]}
OPERATIONS:
1. EVENTS: Append 1-3 key plot points to 'events'.
2. CHARACTERS: Update 'descriptors', 'likes_dislikes', 'speech_style', 'last_worn', 'major_events', 'current_location', 'time_of_day', 'held_items'.
- "descriptors": List of strings. Add PERMANENT physical traits (height, hair, eyes), specific items (jewelry, weapons). Avoid duplicates.
- "likes_dislikes": List of strings. Add specific preferences, likes, or dislikes mentioned (e.g., "Hates coffee", "Loves jazz").
- "speech_style": String. Describe how they speak (e.g. "Formal, no contractions", "Uses slang", "Stutters", "Short sentences").
- "last_worn": String. Update if specific clothing is described. IMPORTANT: If a significant time jump occurred (e.g. next day) and no new clothing is described, reset this to "Unknown".
- "major_events": List of strings. Log significant life-altering events occurring in THIS chapter (e.g. "Lost an arm", "Married", "Betrayed by X").
- "current_location": String. The character's physical location at the END of this chapter (e.g., "The King's Throne Room", "Aboard the Nighthawk ship"). Update whenever the character moves.
- "time_of_day": String. The approximate time of day at the END of this chapter (e.g., "Dawn", "Late afternoon", "Midnight"). Reset to "Unknown" if unclear.
- "held_items": List of strings. Items the character is actively carrying or holding at chapter end (e.g., "Iron sword", "Stolen ledger"). Remove items they have dropped or given away.
3. WARNINGS: Append new 'content_warnings'.
OUTPUT_FORMAT (JSON): Return the updated tracking object structure.
"""
try:
response = ai_models.model_logic.generate_content(prompt)
utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
new_data = json.loads(utils.clean_json(response.text))
return new_data
except Exception as e:
utils.log("TRACKER", f"Failed to update tracking: {e}")
return current_tracking
def update_lore_index(folder, chapter_text, current_lore):
"""Extract canonical descriptions of locations and key items from a chapter
and merge them into the lore index dict. Returns the updated lore dict."""
utils.log("TRACKER", "Updating lore index from chapter...")
prompt = f"""
ROLE: Lore Keeper
TASK: Extract canonical descriptions of locations and key items from this chapter.
EXISTING_LORE:
{json.dumps(current_lore)}
CHAPTER_TEXT:
{chapter_text[:15000]}
INSTRUCTIONS:
1. For each LOCATION mentioned: provide a 1-2 sentence canonical description (appearance, atmosphere, notable features).
2. For each KEY ITEM or ARTIFACT mentioned: provide a 1-2 sentence canonical description (appearance, properties, significance).
3. Do NOT add characters — only physical places and objects.
4. If an entry already exists in EXISTING_LORE, update or preserve it — do not duplicate.
5. Use the exact name as the key (e.g., "The Thornwood Inn", "The Sunstone Amulet").
6. Only include entries that have meaningful descriptive detail in the chapter text.
OUTPUT_FORMAT (JSON): {{"LocationOrItemName": "Description.", ...}}
"""
try:
response = ai_models.model_logic.generate_content(prompt)
utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
new_entries = json.loads(utils.clean_json(response.text))
if isinstance(new_entries, dict):
current_lore.update(new_entries)
return current_lore
except Exception as e:
utils.log("TRACKER", f"Lore index update failed: {e}")
return current_lore
def harvest_metadata(bp, folder, full_manuscript):
utils.log("HARVESTER", "Scanning for new characters...")
full_text = "\n".join([c.get('content', '') for c in full_manuscript])[:500000]
prompt = f"""
ROLE: Data Extractor
TASK: Identify NEW significant characters.
INPUT_TEXT:
{full_text}
KNOWN_CHARACTERS: {json.dumps(bp['characters'])}
OUTPUT_FORMAT (JSON): {{ "new_characters": [{{ "name": "String", "role": "String", "description": "String" }}] }}
"""
try:
response = ai_models.model_logic.generate_content(prompt)
utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
new_chars = json.loads(utils.clean_json(response.text)).get('new_characters', [])
if new_chars:
valid_chars = filter_characters(new_chars)
if valid_chars:
utils.log("HARVESTER", f"Found {len(valid_chars)} new chars.")
bp['characters'].extend(valid_chars)
except Exception as e:
utils.log("HARVESTER", f"⚠️ Metadata harvest failed: {e}")
return bp
def get_chapter_neighbours(manuscript, current_num):
"""Return (prev_num, next_num) chapter numbers adjacent to current_num.
manuscript: list of chapter dicts each with a 'num' key.
Returns None for prev/next when at the boundary.
"""
nums = sorted({ch.get('num') for ch in manuscript if ch.get('num') is not None})
if current_num not in nums:
return None, None
idx = nums.index(current_num)
prev_num = nums[idx - 1] if idx > 0 else None
next_num = nums[idx + 1] if idx < len(nums) - 1 else None
return prev_num, next_num
def refine_bible(bible, instruction, folder):
utils.log("SYSTEM", f"Refining Bible with instruction: {instruction}")
prompt = f"""
ROLE: Senior Developmental Editor
TASK: Update the Bible JSON based on instruction.
INPUT_DATA:
- CURRENT_JSON: {json.dumps(bible)}
- INSTRUCTION: {instruction}
CONSTRAINTS:
- Maintain valid JSON structure.
- Ensure consistency.
OUTPUT_FORMAT (JSON): The full updated Bible JSON object.
"""
try:
response = ai_models.model_logic.generate_content(prompt)
utils.log_usage(folder, ai_models.model_logic.name, response.usage_metadata)
new_data = json.loads(utils.clean_json(response.text))
return new_data
except Exception as e:
utils.log("SYSTEM", f"Refinement failed: {e}")
return None