v2.0.0: Modularize project into single-responsibility packages

Replaced monolithic modules/ package with a clean architecture:

- core/       config.py, utils.py
- ai/         models.py (ResilientModel), setup.py (init_models)
- story/      planner.py, writer.py, editor.py, style_persona.py, bible_tracker.py
- marketing/  cover.py, blurb.py, fonts.py, assets.py
- export/     exporter.py
- web/        app.py (Flask factory), db.py, helpers.py, tasks.py, routes/{auth,project,run,persona,admin}.py
- cli/        engine.py (run_generation), wizard.py (BookWizard)

Flask routes split into 5 Blueprints; all templates updated with blueprint-
prefixed url_for() calls. Dockerfile and docker-compose updated to use
web.app entry point and new package paths.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ai/models.py

@@ -0,0 +1,71 @@
+import os
+import json
+import time
+import warnings
+import google.generativeai as genai
+from core import utils
+
+# Suppress Vertex AI warnings
+warnings.filterwarnings("ignore", category=UserWarning, module="vertexai")
+
+try:
+    import vertexai
+    from vertexai.preview.vision_models import ImageGenerationModel as VertexImageModel
+    HAS_VERTEX = True
+except ImportError:
+    HAS_VERTEX = False
+
+try:
+    from google.auth.transport.requests import Request
+    from google.oauth2.credentials import Credentials
+    from google_auth_oauthlib.flow import InstalledAppFlow
+    HAS_OAUTH = True
+except ImportError:
+    HAS_OAUTH = False
+
+model_logic = None
+model_writer = None
+model_artist = None
+model_image = None
+logic_model_name = "models/gemini-1.5-pro"
+writer_model_name = "models/gemini-1.5-flash"
+artist_model_name = "models/gemini-1.5-flash"
+image_model_name = None
+image_model_source = "None"
+
+
+class ResilientModel:
+    def __init__(self, name, safety_settings, role):
+        self.name = name
+        self.safety_settings = safety_settings
+        self.role = role
+        self.model = genai.GenerativeModel(name, safety_settings=safety_settings)
+
+    def update(self, name):
+        self.name = name
+        self.model = genai.GenerativeModel(name, safety_settings=self.safety_settings)
+
+    def generate_content(self, *args, **kwargs):
+        retries = 0
+        max_retries = 3
+        base_delay = 5
+
+        while True:
+            try:
+                return self.model.generate_content(*args, **kwargs)
+            except Exception as e:
+                err_str = str(e).lower()
+                is_retryable = "429" in err_str or "quota" in err_str or "500" in err_str or "503" in err_str or "504" in err_str or "deadline" in err_str or "internal error" in err_str
+                if is_retryable and retries < max_retries:
+                    delay = base_delay * (2 ** retries)
+                    utils.log("SYSTEM", f"⚠️ Quota error on {self.role} ({self.name}). Retrying in {delay}s...")
+                    time.sleep(delay)
+
+                    if retries == 0:
+                        utils.log("SYSTEM", "Attempting to re-optimize models to find alternative...")
+                        from ai import setup as _setup
+                        _setup.init_models(force=True)
+
+                    retries += 1
+                    continue
+                raise e