v1.4.0: Organic writing, speed, and log improvements

Organic book quality:
- write_chapter: strip key_events spoilers from character context so the writer
  doesn't know planned future events when writing early chapters
- write_chapter: added next_chapter_hint — seeds anticipation for the next scene
  in the final paragraphs of each chapter for natural story flow
- write_chapter: added DIALOGUE VOICE instruction referencing CHARACTER TRACKING
  speech styles so every character sounds distinctly different
- Lowered SCORE_AUTO_ACCEPT 9→8 to stop over-refining already-professional drafts

Speed improvements:
- check_pacing: reduced from every chapter to every other chapter (~50% fewer calls)
- refine_persona: reduced from every 3 to every 5 chapters (~40% fewer calls)
- Resume summary rebuild: uses first + last-4 chapters instead of all chapters
  to avoid massive prompts when resuming mid-book
- Summary context sent to writer capped at 8000 chars (most-recent events)
- update_tracking text cap lowered 500000→20000 (covers any realistic chapter)

Logging and progress bars:
- Progress bar updates at chapter START, not just after completion
- Chapter banner logged before each write so the log shows which chapter is active
- Word count logged after first draft (e.g. "Draft: 2,341 words (target: ~2200)")
- Word count added to chapter completion TIMING line
- Pacing check now logs "Pacing OK" with reason when no intervention needed
- utils: added log_banner() helper for phase separator lines

UI:
- run_details.html: log lines are now phase-coloured (WRITER=cyan, ARCHITECT=green,
  TIMING=gray, SYSTEM=yellow, TRACKER=purple, RESUME=orange, etc.)
- Status bar shows current active phase (e.g. "Status: Running — WRITER")

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

Dockerfile

@@ -3,11 +3,13 @@ FROM python:3.11-slim
 # Set working directory
 WORKDIR /app
 
-# Install system dependencies required for Pillow (image processing)
+# Install system dependencies required for Pillow (image processing) and fonts
 RUN apt-get update && apt-get install -y \
     build-essential \
     libjpeg-dev \
     zlib1g-dev \
+    libpng-dev \
+    libfreetype6-dev \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements files
@@ -24,4 +26,6 @@ COPY . .
 # Set Python path and run
 ENV PYTHONPATH=/app
 EXPOSE 5000
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:5000/login')" || exit 1
 CMD ["python", "-m", "modules.web_app"]

config.py

@@ -14,6 +14,7 @@ GCP_LOCATION = get_clean_env("GCP_LOCATION", "us-central1")
 MODEL_LOGIC_HINT = get_clean_env("MODEL_LOGIC", "AUTO")
 MODEL_WRITER_HINT = get_clean_env("MODEL_WRITER", "AUTO")
 MODEL_ARTIST_HINT = get_clean_env("MODEL_ARTIST", "AUTO")
+MODEL_IMAGE_HINT = get_clean_env("MODEL_IMAGE", "AUTO")
 DEFAULT_BLUEPRINT = "book_def.json"
 
 # --- SECURITY & ADMIN ---
@@ -64,4 +65,4 @@ LENGTH_DEFINITIONS = {
 }
 
 # --- SYSTEM ---
-VERSION = "1.1.0"
+VERSION = "1.4.0"

docker-compose.yml

@@ -37,3 +37,4 @@ services:
       - MODEL_LOGIC=${MODEL_LOGIC:-AUTO}
       - MODEL_WRITER=${MODEL_WRITER:-AUTO}
       - MODEL_ARTIST=${MODEL_ARTIST:-AUTO}
+      - MODEL_IMAGE=${MODEL_IMAGE:-AUTO}

main.py

@@ -97,10 +97,11 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
         
         summary = "The story begins."
         if ms:
-            # Generate summary from ALL written chapters to maintain continuity
-            utils.log("RESUME", "Rebuilding 'Story So Far' from existing manuscript...")
+            # Efficient rebuild: first chapter (setup) + last 4 (recent events) avoids huge prompts
+            utils.log("RESUME", f"Rebuilding story context from {len(ms)} existing chapters...")
             try:
-                combined_text = "\n".join([f"Chapter {c['num']}: {c['content']}" for c in ms])
+                selected = ms[:1] + ms[-4:] if len(ms) > 5 else ms
+                combined_text = "\n".join([f"Chapter {c['num']}: {c['content'][:3000]}" for c in selected])
                 resp_sum = ai.model_writer.generate_content(f"""
                 ROLE: Series Historian
                 TASK: Create a cumulative 'Story So Far' summary.
@@ -134,12 +135,19 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
                 i += 1
                 continue
 
+            # Progress Banner — update bar and log chapter header before writing begins
+            utils.update_progress(15 + int((i / len(chapters)) * 75))
+            utils.log_banner("WRITER", f"Chapter {ch['chapter_number']}/{len(chapters)}: {ch['title']}")
+
             # Pass previous chapter content for continuity if available
             prev_content = ms[-1]['content'] if ms else None
             
             while True:
                 try:
-                    txt = story.write_chapter(ch, bp, folder, summary, tracking, prev_content)
+                    # Cap summary to most-recent 8000 chars; pass next chapter title as hook hint
+                    summary_ctx = summary[-8000:] if len(summary) > 8000 else summary
+                    next_hint = chapters[i+1]['title'] if i + 1 < len(chapters) else ""
+                    txt = story.write_chapter(ch, bp, folder, summary_ctx, tracking, prev_content, next_chapter_hint=next_hint)
                 except Exception as e:
                     utils.log("SYSTEM", f"Chapter generation failed: {e}")
                     if interactive:
@@ -156,8 +164,8 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
                 else:
                     break
             
-            # Refine Persona to match the actual output (Consistency Loop)
-            if (i == 0 or i % 3 == 0) and txt:
+            # Refine Persona to match the actual output (every 5 chapters to save API calls)
+            if (i == 0 or i % 5 == 0) and txt:
                 bp['book_metadata']['author_details'] = story.refine_persona(bp, txt, folder)
                 with open(bp_path, "w") as f: json.dump(bp, f, indent=2)
 
@@ -207,18 +215,23 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
             with open(chars_track_path, "w") as f: json.dump(tracking['characters'], f, indent=2)
             with open(warn_track_path, "w") as f: json.dump(tracking.get('content_warnings', []), f, indent=2)
             
-            # --- DYNAMIC PACING CHECK ---
+            # --- DYNAMIC PACING CHECK (every other chapter to halve API overhead) ---
             remaining = chapters[i+1:]
-            if remaining:
+            if remaining and len(remaining) >= 2 and i % 2 == 1:
                 pacing = story.check_pacing(bp, summary, txt, ch, remaining, folder)
                 if pacing and pacing.get('status') == 'add_bridge':
                     new_data = pacing.get('new_chapter', {})
+                    # Estimate bridge chapter length from current plan average (not hardcoded)
+                    if chapters:
+                        avg_words = int(sum(c.get('estimated_words', 1500) for c in chapters) / len(chapters))
+                    else:
+                        avg_words = 1500
                     new_ch = {
                         "chapter_number": ch['chapter_number'] + 1,
                         "title": new_data.get('title', 'Bridge Chapter'),
                         "pov_character": new_data.get('pov_character', ch.get('pov_character')),
                         "pacing": "Slow",
-                        "estimated_words": 1500,
+                        "estimated_words": avg_words,
                         "beats": new_data.get('beats', [])
                     }
                     chapters.insert(i+1, new_ch)
@@ -235,6 +248,8 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
 
                     with open(chapters_path, "w") as f: json.dump(chapters, f, indent=2)
                     utils.log("ARCHITECT", f"  -> ⚠️ Pacing Intervention: Removed redundant chapter '{removed['title']}'.")
+                elif pacing:
+                    utils.log("ARCHITECT", f"  -> Pacing OK. {pacing.get('reason', '')[:100]}")
 
             # Increment loop
             i += 1
@@ -249,7 +264,8 @@ def process_book(bp, folder, context="", resume=False, interactive=False):
             prog = 15 + int((i / len(chapters)) * 75)
             utils.update_progress(prog)
             
-            utils.log("TIMING", f"  -> Chapter {ch['chapter_number']} finished in {duration:.1f}s | Avg: {avg_time:.1f}s | ETA: {int(eta//60)}m {int(eta%60)}s")
+            word_count = len(txt.split()) if txt else 0
+            utils.log("TIMING", f"  -> Ch {ch['chapter_number']} done in {duration:.1f}s | {word_count:,} words | Avg: {avg_time:.1f}s | ETA: {int(eta//60)}m {int(eta%60)}s")
             
         utils.log("TIMING", f"Writing Phase: {time.time() - t_step:.1f}s")
 

modules/ai.py

@@ -31,6 +31,8 @@ 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):
@@ -75,10 +77,15 @@ def get_optimal_model(base_type="pro"):
         candidates = [m.name for m in models if base_type in m.name]
         if not candidates: return f"models/gemini-1.5-{base_type}"
         def score(n):
-            # Prioritize stable models (higher quotas) over experimental/beta ones
-            if "exp" in n or "beta" in n or "preview" in n: return 0
-            if "latest" in n: return 50
-            return 100
+            # Prefer newer generations: 2.5 > 2.0 > 1.5
+            gen_bonus = 0
+            if "2.5" in n: gen_bonus = 300
+            elif "2.0" in n: gen_bonus = 200
+            elif "2." in n: gen_bonus = 150
+            # Within a generation, prefer stable over experimental
+            if "exp" in n or "beta" in n or "preview" in n: return gen_bonus + 0
+            if "latest" in n: return gen_bonus + 50
+            return gen_bonus + 100
         return sorted(candidates, key=score, reverse=True)[0]
     except Exception as e:
         utils.log("SYSTEM", f"⚠️ Error finding optimal model: {e}")
@@ -86,9 +93,9 @@ def get_optimal_model(base_type="pro"):
 
 def get_default_models():
     return {
-        "logic": {"model": "models/gemini-1.5-pro", "reason": "Fallback: Default Pro model selected.", "estimated_cost": "$3.50/1M"},
-        "writer": {"model": "models/gemini-1.5-flash", "reason": "Fallback: Default Flash model selected.", "estimated_cost": "$0.075/1M"},
-        "artist": {"model": "models/gemini-1.5-flash", "reason": "Fallback: Default Flash model selected.", "estimated_cost": "$0.075/1M"},
+        "logic": {"model": "models/gemini-2.0-pro-exp", "reason": "Fallback: Gemini 2.0 Pro for complex reasoning and JSON adherence.", "estimated_cost": "$0.00/1M (Experimental)"},
+        "writer": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for fast, high-quality creative writing.", "estimated_cost": "$0.10/1M"},
+        "artist": {"model": "models/gemini-2.0-flash", "reason": "Fallback: Gemini 2.0 Flash for visual prompt design.", "estimated_cost": "$0.10/1M"},
         "ranking": []
     }
 
@@ -131,29 +138,37 @@ def select_best_models(force_refresh=False):
         model = genai.GenerativeModel(bootstrapper)
         prompt = f"""
         ROLE: AI Model Architect
-        TASK: Select the optimal Gemini models for specific application roles.
+        TASK: Select the optimal Gemini models for a book-writing application. Prefer newer Gemini 2.x models when available.
 
         AVAILABLE_MODELS:
         {json.dumps(models)}
 
-        PRICING_CONTEXT (USD per 1M tokens):
-        - Flash Models (e.g. gemini-1.5-flash): ~$0.075 Input / $0.30 Output. (Very Cheap)
-        - Pro Models (e.g. gemini-1.5-pro): ~$3.50 Input / $10.50 Output. (Expensive)
+        PRICING_CONTEXT (USD per 1M tokens, approximate):
+        - Gemini 2.5 Pro/Flash: Best quality/speed; check current pricing.
+        - Gemini 2.0 Flash: ~$0.10 Input / $0.40 Output. (Fast, cost-effective, excellent quality).
+        - Gemini 2.0 Pro Exp: Free experimental tier with strong reasoning.
+        - Gemini 1.5 Flash: ~$0.075 Input / $0.30 Output. (Legacy, still reliable).
+        - Gemini 1.5 Pro: ~$1.25 Input / $5.00 Output. (Legacy, expensive).
 
         CRITERIA:
-        - LOGIC: Needs complex reasoning, JSON adherence, and instruction following. (Prefer Pro/1.5).
-        - WRITER: Needs creativity, prose quality, and speed. (Prefer Flash/1.5 for speed, or Pro for quality).
-        - ARTIST: Needs visual prompt understanding.
+        - LOGIC: Needs complex reasoning, strict JSON adherence, plot consistency, and instruction following.
+          -> Prefer: Gemini 2.5 Pro > 2.0 Pro > 2.0 Flash > 1.5 Pro
+        - WRITER: Needs creativity, prose quality, long-form text generation, and speed.
+          -> Prefer: Gemini 2.5 Flash/Pro > 2.0 Flash > 1.5 Flash (balance quality/cost)
+        - ARTIST: Needs rich visual description, prompt understanding for cover art design.
+          -> Prefer: Gemini 2.0 Flash > 1.5 Flash (speed and visual understanding)
 
         CONSTRAINTS:
-        - Avoid 'experimental' or 'preview' unless no stable version exists.
-        - Prioritize 'latest' or stable versions.
+        - Strongly prefer Gemini 2.x over 1.5 where available.
+        - Avoid 'experimental' or 'preview' only if a stable 2.x version exists; otherwise experimental 2.x is fine.
+        - 'thinking' models are too slow/expensive for Writer/Artist roles.
+        - Provide a ranking of ALL available models from best to worst overall.
 
-        OUTPUT_FORMAT (JSON):
+        OUTPUT_FORMAT (JSON only, no markdown):
         {{
-            "logic": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX Input / $X.XX Output" }},
-            "writer": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX Input / $X.XX Output" }},
-            "artist": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX Input / $X.XX Output" }},
+            "logic": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }},
+            "writer": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }},
+            "artist": {{ "model": "string", "reason": "string", "estimated_cost": "$X.XX/1M" }},
             "ranking": [ {{ "model": "string", "reason": "string", "estimated_cost": "string" }} ]
         }}
         """
@@ -195,7 +210,7 @@ def select_best_models(force_refresh=False):
         return fallback
 
 def init_models(force=False):
-    global model_logic, model_writer, model_artist, model_image, logic_model_name, writer_model_name, artist_model_name
+    global model_logic, model_writer, model_artist, model_image, logic_model_name, writer_model_name, artist_model_name, image_model_name, image_model_source
     if model_logic and not force: return
     genai.configure(api_key=config.API_KEY)
     
@@ -264,13 +279,28 @@ def init_models(force=False):
         model_writer.update(writer_name)
         model_artist.update(artist_name)
     
-    # Initialize Image Model (Default to None)
+    # Initialize Image Model
     model_image = None
-    if hasattr(genai, 'ImageGenerationModel'):
-        try: model_image = genai.ImageGenerationModel("imagen-3.0-generate-001")
-        except: pass
+    image_model_name = None
+    image_model_source = "None"
 
-    img_source = "Gemini API" if model_image else "None"
+    hint = config.MODEL_IMAGE_HINT if hasattr(config, 'MODEL_IMAGE_HINT') else "AUTO"
+
+    if hasattr(genai, 'ImageGenerationModel'):
+        # Candidate image models in preference order
+        if hint and hint != "AUTO":
+            candidates = [hint]
+        else:
+            candidates = ["imagen-3.0-generate-001", "imagen-3.0-fast-generate-001"]
+        for candidate in candidates:
+            try:
+                model_image = genai.ImageGenerationModel(candidate)
+                image_model_name = candidate
+                image_model_source = "Gemini API"
+                utils.log("SYSTEM", f"✅ Image model: {candidate} (Gemini API)")
+                break
+            except Exception:
+                continue
 
     # Auto-detect GCP Project from credentials if not set (Fix for Image Model)
     if HAS_VERTEX and not config.GCP_PROJECT and config.GOOGLE_CREDS and os.path.exists(config.GOOGLE_CREDS):
@@ -326,9 +356,17 @@ def init_models(force=False):
         utils.log("SYSTEM", f"✅ Vertex AI initialized (Project: {config.GCP_PROJECT})")
         
         # Override with Vertex Image Model if available
-        try:
-            model_image = VertexImageModel.from_pretrained("imagen-3.0-generate-001")
-            img_source = "Vertex AI"
-        except: pass
+        vertex_candidates = ["imagen-3.0-generate-001", "imagen-3.0-fast-generate-001"]
+        if hint and hint != "AUTO":
+            vertex_candidates = [hint]
+        for candidate in vertex_candidates:
+            try:
+                model_image = VertexImageModel.from_pretrained(candidate)
+                image_model_name = candidate
+                image_model_source = "Vertex AI"
+                utils.log("SYSTEM", f"✅ Image model: {candidate} (Vertex AI)")
+                break
+            except Exception:
+                continue
 
-    utils.log("SYSTEM", f"Image Generation Provider: {img_source}")
+    utils.log("SYSTEM", f"Image Generation Provider: {image_model_source} ({image_model_name or 'unavailable'})")

modules/marketing.py

@@ -1,10 +1,10 @@
 import os
+import sys
 import json
 import shutil
 import textwrap
 import subprocess
 import requests
-import google.generativeai as genai
 from . import utils
 import config
 from modules import ai
@@ -90,18 +90,40 @@ def generate_blurb(bp, folder):
     utils.log("MARKETING", "Generating blurb...")
     meta = bp.get('book_metadata', {})
 
+    # Format beats as a readable list, not raw JSON
+    beats = bp.get('plot_beats', [])
+    beats_text = "\n".join(f"  - {b}" for b in beats[:6]) if beats else "  - (no beats provided)"
+
+    # Format protagonist for the blurb
+    chars = bp.get('characters', [])
+    protagonist = next((c for c in chars if 'protagonist' in c.get('role', '').lower()), None)
+    protagonist_desc = f"{protagonist['name']} — {protagonist.get('description', '')}" if protagonist else "the protagonist"
+
     prompt = f"""
     ROLE: Marketing Copywriter
-    TASK: Write a back-cover blurb (150-200 words).
+    TASK: Write a compelling back-cover blurb for a {meta.get('genre', 'fiction')} novel.
 
-    INPUT_DATA:
+    BOOK DETAILS:
     - TITLE: {meta.get('title')}
     - GENRE: {meta.get('genre')}
-    - LOGLINE: {bp.get('manual_instruction')}
-    - PLOT: {json.dumps(bp.get('plot_beats', []))}
-    - CHARACTERS: {json.dumps(bp.get('characters', []))}
+    - AUDIENCE: {meta.get('target_audience', 'General')}
+    - PROTAGONIST: {protagonist_desc}
+    - LOGLINE: {bp.get('manual_instruction', '(none)')}
+    - KEY PLOT BEATS:
+{beats_text}
 
-    OUTPUT: Text only.
+    BLURB STRUCTURE:
+    1. HOOK (1-2 sentences): Open with the protagonist's world and the inciting disruption. Make it urgent.
+    2. STAKES (2-3 sentences): Raise the central conflict. What does the protagonist stand to lose?
+    3. TENSION (1-2 sentences): Hint at the impossible choice or escalating danger without revealing the resolution.
+    4. HOOK CLOSE (1 sentence): End with a tantalising question or statement that demands the reader open the book.
+
+    RULES:
+    - 150-200 words total.
+    - DO NOT reveal the ending or resolution.
+    - Match the genre's marketing tone ({meta.get('genre', 'fiction')}: e.g. thriller = urgent/terse, romance = emotionally charged, fantasy = epic/wondrous, horror = dread-laden).
+    - Use present tense for the blurb voice.
+    - No "Blurb:", no title prefix, no labels — marketing copy only.
     """
     try:
         response = ai.model_writer.generate_content(prompt)
@@ -167,30 +189,51 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
         except:
             utils.log("MARKETING", "Feedback analysis failed. Defaulting to full regeneration.")
 
+    genre = meta.get('genre', 'Fiction')
+    tone = meta.get('style', {}).get('tone', 'Balanced')
+    # Map genre to visual style suggestion
+    genre_style_map = {
+        'thriller': 'dark, cinematic, high-contrast photography style',
+        'mystery': 'moody, atmospheric, noir-inspired painting',
+        'romance': 'warm, painterly, soft-focus illustration',
+        'fantasy': 'epic digital painting, rich colours, mythic scale',
+        'science fiction': 'sharp digital art, cool palette, futuristic',
+        'horror': 'unsettling, dark atmospheric painting, desaturated',
+        'historical fiction': 'classical oil painting style, period-accurate',
+        'young adult': 'vibrant illustrated style, bold colours',
+    }
+    suggested_style = genre_style_map.get(genre.lower(), 'professional digital illustration or photography')
+
     design_prompt = f"""
     ROLE: Art Director
-    TASK: Design a book cover.
+    TASK: Design a professional book cover for an AI image generator.
 
-    METADATA:
+    BOOK:
     - TITLE: {meta.get('title')}
-    - GENRE: {meta.get('genre')}
-    - TONE: {meta.get('style', {}).get('tone', 'Balanced')}
+    - GENRE: {genre}
+    - TONE: {tone}
+    - SUGGESTED_VISUAL_STYLE: {suggested_style}
 
-    VISUAL_CONTEXT:
-    {visual_context}
+    VISUAL_CONTEXT (characters and key themes from the story):
+    {visual_context if visual_context else "Use genre conventions."}
 
-    USER_FEEDBACK:
-    {f"{feedback}" if feedback else "None"}
+    USER_FEEDBACK: {feedback if feedback else "None"}
+    DESIGN_INSTRUCTION: {design_instruction if design_instruction else "Create a compelling, genre-appropriate cover."}
 
-    INSTRUCTION:
-    {f"{design_instruction}" if design_instruction else "Create a compelling, genre-appropriate cover."}
+    COVER_ART_RULES:
+    - The art_prompt must produce an image with NO text, no letters, no numbers, no watermarks, no UI elements, no logos.
+    - Describe a clear FOCAL POINT (e.g. the protagonist, a dramatic scene, a symbolic object).
+    - Use RULE OF THIRDS composition — leave visual space at top and/or bottom for the title and author text to be overlaid.
+    - Describe LIGHTING that reinforces the tone (e.g. "harsh neon backlight" for thriller, "golden hour" for romance).
+    - Describe the COLOUR PALETTE explicitly (e.g. "deep crimson and shadow-black", "soft rose gold and cream").
+    - Characters must match their descriptions from VISUAL_CONTEXT if present.
 
-    OUTPUT_FORMAT (JSON):
+    OUTPUT_FORMAT (JSON only, no markdown):
     {{
-        "font_name": "Name of a popular Google Font (e.g. Roboto, Cinzel, Oswald, Playfair Display)",
-        "primary_color": "#HexCode (Background)",
-        "text_color": "#HexCode (Contrast)",
-        "art_prompt": "A detailed description of the cover art for an image generator. Explicitly describe characters based on the visual context."
+        "font_name": "Name of a Google Font suited to the genre (e.g. Cinzel for fantasy, Oswald for thriller, Playfair Display for romance)",
+        "primary_color": "#HexCode (dominant background/cover colour)",
+        "text_color": "#HexCode (high contrast against primary_color)",
+        "art_prompt": "Detailed {suggested_style} image generation prompt. Begin with the style. Describe composition, focal point, lighting, colour palette, and any characters. End with: No text, no letters, no watermarks, photorealistic/painted quality, 8k detail."
     }}
     """
     try:
@@ -212,9 +255,10 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
         best_img_score = 0
         best_img_path = None
         
+        MAX_IMG_ATTEMPTS = 3
         if regenerate_image:
-            for i in range(1, 4):
-                utils.log("MARKETING", f"Generating cover art (Attempt {i}/5)...")
+            for i in range(1, MAX_IMG_ATTEMPTS + 1):
+                utils.log("MARKETING", f"Generating cover art (Attempt {i}/{MAX_IMG_ATTEMPTS})...")
                 try:
                     if not ai.model_image: raise ImportError("No Image Generation Model available.")
 
@@ -222,25 +266,44 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
                     try:
                         result = ai.model_image.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
                     except Exception as e:
-                        if "resource" in str(e).lower() and ai.HAS_VERTEX:
-                            utils.log("MARKETING", "⚠️ Imagen 3 failed. Trying Imagen 2...")
-                            fb_model = ai.VertexImageModel.from_pretrained("imagegeneration@006")
-                            result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
-                            status = "success_fallback"
-                        else: raise e
+                        err_lower = str(e).lower()
+                        # Try fast imagen variant before falling back to legacy
+                        if ai.HAS_VERTEX and ("resource" in err_lower or "quota" in err_lower):
+                            try:
+                                utils.log("MARKETING", "⚠️ Imagen 3 failed. Trying Imagen 3 Fast...")
+                                fb_model = ai.VertexImageModel.from_pretrained("imagen-3.0-fast-generate-001")
+                                result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
+                                status = "success_fast"
+                            except Exception:
+                                utils.log("MARKETING", "⚠️ Imagen 3 Fast failed. Trying Imagen 2...")
+                                fb_model = ai.VertexImageModel.from_pretrained("imagegeneration@006")
+                                result = fb_model.generate_images(prompt=art_prompt, number_of_images=1, aspect_ratio=ar)
+                                status = "success_fallback"
+                        else:
+                            raise e
 
                     attempt_path = os.path.join(folder, f"cover_art_attempt_{i}.png")
                     result.images[0].save(attempt_path)
                     utils.log_usage(folder, "imagen", image_count=1)
 
-                    score, critique = evaluate_image_quality(attempt_path, art_prompt, ai.model_writer, folder)
+                    cover_eval_criteria = (
+                        f"Book cover art for a {genre} novel titled '{meta.get('title')}'.\n\n"
+                        f"Evaluate STRICTLY as a professional book cover on these criteria:\n"
+                        f"1. VISUAL IMPACT: Is the image immediately arresting and compelling?\n"
+                        f"2. GENRE FIT: Does the visual style, mood, and palette match {genre}?\n"
+                        f"3. COMPOSITION: Is there a clear focal point? Are top/bottom areas usable for title/author text?\n"
+                        f"4. QUALITY: Is the image sharp, detailed, and free of deformities or blurring?\n"
+                        f"5. CLEAN IMAGE: Are there absolutely NO text, watermarks, letters, or UI artifacts?\n"
+                        f"Score 1-10. Deduct 3 points if any text/watermarks are visible. "
+                        f"Deduct 2 if the image is blurry or has deformed anatomy."
+                    )
+                    score, critique = evaluate_image_quality(attempt_path, cover_eval_criteria, ai.model_writer, folder)
                     if score is None: score = 0
 
                     utils.log("MARKETING", f"  -> Image Score: {score}/10. Critique: {critique}")
                     utils.log_image_attempt(folder, "cover", art_prompt, f"cover_art_{i}.png", status, score=score, critique=critique)
 
                     if interactive:
-                        # Open image for review
                         try:
                             if os.name == 'nt': os.startfile(attempt_path)
                             elif sys.platform == 'darwin': subprocess.call(('open', attempt_path))
@@ -254,16 +317,30 @@ def generate_cover(bp, folder, tracking=None, feedback=None, interactive=False):
                             utils.log("MARKETING", "User rejected cover. Retrying...")
                             continue
 
-                    if score > best_img_score:
+                    # Only keep as best if score meets minimum quality bar
+                    if score >= 5 and score > best_img_score:
+                        best_img_score = score
+                        best_img_path = attempt_path
+                    elif best_img_path is None and score > 0:
+                        # Accept even low-quality image if we have nothing else
                         best_img_score = score
                         best_img_path = attempt_path
 
-                    if score == 10:
-                        utils.log("MARKETING", "  -> Perfect image accepted.")
+                    if score >= 9:
+                        utils.log("MARKETING", "  -> High quality image accepted.")
                         break
 
-                    if "scar" in critique.lower() or "deform" in critique.lower() or "blur" in critique.lower():
-                        art_prompt += " (Ensure high quality, clear skin, no scars, sharp focus)."
+                    # Refine prompt based on critique keywords
+                    prompt_additions = []
+                    critique_lower = critique.lower() if critique else ""
+                    if "scar" in critique_lower or "deform" in critique_lower:
+                        prompt_additions.append("perfect anatomy, no deformities")
+                    if "blur" in critique_lower or "blurry" in critique_lower:
+                        prompt_additions.append("sharp focus, highly detailed")
+                    if "text" in critique_lower or "letter" in critique_lower:
+                        prompt_additions.append("no text, no letters, no watermarks")
+                    if prompt_additions:
+                        art_prompt += f". ({', '.join(prompt_additions)})"
 
                 except Exception as e:
                     utils.log("MARKETING", f"Image generation failed: {e}")

modules/story.py

@@ -223,13 +223,31 @@ def plan_structure(bp, folder):
     if not beats_context:
         beats_context = bp.get('plot_beats', [])
 
+    target_chapters = bp.get('length_settings', {}).get('chapters', 'flexible')
+    target_words = bp.get('length_settings', {}).get('words', 'flexible')
+    chars_summary = [{"name": c.get("name"), "role": c.get("role")} for c in bp.get('characters', [])]
+
     prompt = f"""
     ROLE: Story Architect
-    TASK: Create a structural event outline.
+    TASK: Create a detailed structural event outline for a {target_chapters}-chapter book.
 
-    ARCHETYPE: {structure_type}
-    TITLE: {bp['book_metadata']['title']}
-    EXISTING_BEATS: {json.dumps(beats_context)}
+    BOOK:
+    - TITLE: {bp['book_metadata']['title']}
+    - GENRE: {bp.get('book_metadata', {}).get('genre', 'Fiction')}
+    - TARGET_CHAPTERS: {target_chapters}
+    - TARGET_WORDS: {target_words}
+    - STRUCTURE: {structure_type}
+
+    CHARACTERS: {json.dumps(chars_summary)}
+
+    USER_BEATS (must all be preserved and woven into the outline):
+    {json.dumps(beats_context)}
+
+    REQUIREMENTS:
+    - Produce enough events to fill approximately {target_chapters} chapters.
+    - Each event must serve a narrative purpose (setup, escalation, reversal, climax, resolution).
+    - Distribute events across a beginning, middle, and end — avoid front-loading.
+    - Character arcs must be visible through the events (growth, change, revelation).
 
     OUTPUT_FORMAT (JSON): {{ "events": [{{ "description": "String", "purpose": "String" }}] }}
     """
@@ -243,29 +261,40 @@ def plan_structure(bp, folder):
 def expand(events, pass_num, target_chapters, bp, folder):
     utils.log("ARCHITECT", f"Expansion pass {pass_num} | Current Beats: {len(events)} | Target Chaps: {target_chapters}")
 
-    beats_context = []
+    # If events already well exceed the target, only deepen descriptions — don't add more
+    event_ceiling = int(target_chapters * 1.5)
+    if len(events) >= event_ceiling:
+        task = (
+            f"The outline already has {len(events)} beats for a {target_chapters}-chapter book — do NOT add more events. "
+            f"Instead, enrich each existing beat's description with more specific detail: setting, characters involved, emotional stakes, and how it connects to what follows."
+        )
+    else:
+        task = (
+            f"Expand the outline toward {target_chapters} chapters. "
+            f"Current count: {len(events)} beats. "
+            f"Add intermediate events to fill pacing gaps, deepen subplots, and ensure character arcs are visible. "
+            f"Do not overshoot — aim for {target_chapters} to {event_ceiling} total events."
+        )
 
-    if not beats_context:
-        beats_context = bp.get('plot_beats', [])
+    original_beats = bp.get('plot_beats', [])
 
     prompt = f"""
     ROLE: Story Architect
-    TASK: Expand the outline to fit a {target_chapters}-chapter book.
-    CURRENT_COUNT: {len(events)} beats.
+    TASK: {task}
 
-    INPUT_OUTLINE:
-    {json.dumps(beats_context)}
+    ORIGINAL_USER_BEATS (must all remain present):
+    {json.dumps(original_beats)}
 
     CURRENT_EVENTS:
     {json.dumps(events)}
 
     RULES:
-    1. Detect pacing gaps.
-    2. Insert intermediate events.
-    3. Deepen subplots.
-    4. PRESERVE original beats.
+    1. PRESERVE all original user beats — do not remove or alter them.
+    2. New events must serve a clear narrative purpose (tension, character, world, reversal).
+    3. Avoid repetitive events — each beat must be distinct.
+    4. Distribute additions evenly — do not front-load the outline.
 
-    OUTPUT_FORMAT (JSON): {{ "events": [{{ "description": "String", "purpose": "String" }}] }}
+    OUTPUT_FORMAT (JSON): {{ "events": [{{"description": "String", "purpose": "String"}}] }}
     """
     try:
         response = ai.model_logic.generate_content(prompt)
@@ -304,24 +333,30 @@ def create_chapter_plan(events, bp, folder):
 
     prompt = f"""
     ROLE: Pacing Specialist
-    TASK: Group events into Chapters.
+    TASK: Group the provided events into chapters for a {meta.get('genre', 'Fiction')} {bp['length_settings'].get('label', 'novel')}.
 
-    CONSTRAINTS:
-    - TARGET_CHAPTERS: {target}
-    - TARGET_WORDS: {words}
-    - INSTRUCTIONS:
+    GUIDELINES:
+    - AIM for approximately {target} chapters, but the final count may vary ±15% if the story structure demands it.
+      (e.g. a tightly plotted thriller may need fewer; an epic with many subplots may need more.)
+    - TARGET_WORDS for the whole book: {words}
+    - Assign pacing to each chapter: Very Fast / Fast / Standard / Slow / Very Slow
+      Reflect dramatic rhythm — action scenes run fast, emotional beats run slow.
+    - estimated_words per chapter should reflect its pacing:
+      Very Fast ≈ 60% of average, Fast ≈ 80%, Standard ≈ 100%, Slow ≈ 125%, Very Slow ≈ 150%
+    - Do NOT force equal word counts. Natural variation makes the book feel alive.
     {structure_instructions}
     {pov_instruction}
 
     INPUT_EVENTS: {json.dumps(events)}
 
-    OUTPUT_FORMAT (JSON): [{{ "chapter_number": 1, "title": "String", "pov_character": "String", "pacing": "String", "estimated_words": 2000, "beats": ["String"] }}]
+    OUTPUT_FORMAT (JSON): [{{"chapter_number": 1, "title": "String", "pov_character": "String", "pacing": "String", "estimated_words": 2000, "beats": ["String"]}}]
     """
     try:
         response = ai.model_logic.generate_content(prompt)
         utils.log_usage(folder, ai.model_logic.name, response.usage_metadata)
         plan = json.loads(utils.clean_json(response.text))
 
+        # Parse target word count
         target_str = str(words).lower().replace(',', '').replace('k', '000').replace('+', '').replace(' ', '')
         target_val = 0
         if '-' in target_str:
@@ -334,16 +369,31 @@ def create_chapter_plan(events, bp, folder):
             except: pass
 
         if target_val > 0:
-            variance = random.uniform(0.90, 1.10)
+            variance = random.uniform(0.92, 1.08)
             target_val = int(target_val * variance)
-            utils.log("ARCHITECT", f"Target adjusted with variance ({variance:.2f}x): {target_val} words.")
+            utils.log("ARCHITECT", f"Word target after variance ({variance:.2f}x): {target_val} words.")
 
             current_sum = sum(int(c.get('estimated_words', 0)) for c in plan)
             if current_sum > 0:
-                factor = target_val / current_sum
-                utils.log("ARCHITECT", f"Adjusting chapter lengths by {factor:.2f}x to match target.")
+                base_factor = target_val / current_sum
+                # Pacing multipliers — fast chapters are naturally shorter, slow chapters longer
+                pacing_weight = {
+                    'very fast': 0.60, 'fast': 0.80, 'standard': 1.00,
+                    'slow': 1.25, 'very slow': 1.50
+                }
+                # Two-pass: apply pacing weights then normalise to hit total target
                 for c in plan:
-                    c['estimated_words'] = int(c.get('estimated_words', 0) * factor)
+                    pw = pacing_weight.get(c.get('pacing', 'standard').lower(), 1.0)
+                    c['estimated_words'] = max(300, int(c.get('estimated_words', 0) * base_factor * pw))
+
+                # Normalise to keep total close to target
+                adjusted_sum = sum(c['estimated_words'] for c in plan)
+                if adjusted_sum > 0:
+                    norm = target_val / adjusted_sum
+                    for c in plan:
+                        c['estimated_words'] = max(300, int(c['estimated_words'] * norm))
+
+                utils.log("ARCHITECT", f"Chapter lengths scaled by pacing. Total ≈ {sum(c['estimated_words'] for c in plan)} words across {len(plan)} chapters.")
 
         return plan
     except Exception as e:
@@ -361,7 +411,7 @@ def update_tracking(folder, chapter_num, chapter_text, current_tracking):
     {json.dumps(current_tracking)}
     
     NEW_TEXT:
-    {chapter_text[:500000]} 
+    {chapter_text[:20000]}
     
     OPERATIONS:
     1. EVENTS: Append 1-3 key plot points to 'events'.
@@ -544,7 +594,7 @@ def refine_persona(bp, text, folder):
     except: pass
     return ad
 
-def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
+def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None, next_chapter_hint=""):
     pacing = chap.get('pacing', 'Standard')
     est_words = chap.get('estimated_words', 'Flexible')
     utils.log("WRITER", f"Drafting Ch {chap['chapter_number']} ({pacing} | ~{est_words} words): {chap['title']}")
@@ -612,6 +662,14 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
         trunc_content = prev_content[-3000:] if len(prev_content) > 3000 else prev_content
         prev_context_block = f"\nPREVIOUS CHAPTER TEXT (For Tone & Continuity):\n{trunc_content}\n"
 
+    # Strip future planning notes (key_events) from character context — the writer
+    # should not know what is *planned* to happen; only name, role, and description.
+    chars_for_writer = [
+        {"name": c.get("name"), "role": c.get("role"), "description": c.get("description", "")}
+        for c in bp.get('characters', [])
+    ]
+
+    total_chapters = ls.get('chapters', '?')
     prompt = f"""
     ROLE: Fiction Writer
     TASK: Write Chapter {chap['chapter_number']}: {chap['title']}
@@ -619,10 +677,18 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
     METADATA:
     - GENRE: {genre}
     - FORMAT: {ls.get('label', 'Story')}
-    - PACING: {pacing}
-    - TARGET_WORDS: ~{est_words}
+    - POSITION: Chapter {chap['chapter_number']} of {total_chapters} — calibrate narrative tension accordingly (early = setup/intrigue, middle = escalation, final third = payoff/climax)
+    - PACING: {pacing} — see PACING_GUIDE below
+    - TARGET_WORDS: ~{est_words} (write to this length; do not summarise to save space)
     - POV: {pov_char if pov_char else 'Protagonist'}
 
+    PACING_GUIDE:
+    - 'Very Fast': Pure action/dialogue. Minimal description. Short punchy paragraphs.
+    - 'Fast': Keep momentum. No lingering. Cut to the next beat quickly.
+    - 'Standard': Balanced dialogue and description. Standard paragraph lengths.
+    - 'Slow': Detailed, atmospheric. Linger on emotion and environment.
+    - 'Very Slow': Deep introspection. Heavy sensory immersion. Slow burn tension.
+    
     STYLE_GUIDE:
     {style_block}
     
@@ -646,6 +712,8 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
     - CHARACTER INTERACTIONS: If characters are meeting for the first time in the summary, treat them as strangers.
     - SENTENCE VARIETY: Avoid repetitive sentence structures (e.g. starting multiple sentences with "He" or "She"). Vary sentence length to create rhythm.
     - GENRE CONSISTENCY: Ensure all introductions of characters, places, items, or actions are strictly appropriate for the {genre} genre. Avoid anachronisms or tonal clashes.
+    - DIALOGUE VOICE: Every character speaks with their own distinct voice (see CHARACTER TRACKING for speech styles). No two characters may sound the same. Vary sentence length, vocabulary, and register per character.
+    - CHAPTER HOOK: End this chapter with unresolved tension — a decision pending, a threat imminent, or a question unanswered.{f" Seed subtle anticipation for the next scene: '{next_chapter_hint}'." if next_chapter_hint else " Do not neatly resolve all threads."}
 
     QUALITY_CRITERIA:
     1. ENGAGEMENT & TENSION: Grip the reader. Ensure conflict/tension in every scene.
@@ -662,16 +730,10 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
     12. PROSE DYNAMICS: Vary sentence length. Use strong verbs. Avoid passive voice.
     13. CLARITY: Ensure sentences are clear and readable. Avoid convoluted phrasing.
 
-    - 'Very Fast': Rapid fire, pure action/dialogue, minimal description.
-    - 'Fast': Punchy, keep it moving.
-    - 'Standard': Balanced dialogue and description.
-    - 'Slow': Detailed, atmospheric, immersive.
-    - 'Very Slow': Deep introspection, heavy sensory detail, slow burn.
-    
     CONTEXT:
     - STORY_SO_FAR: {prev_sum}
     {prev_context_block}
-    - CHARACTERS: {json.dumps(bp['characters'])}
+    - CHARACTERS: {json.dumps(chars_for_writer)}
     {char_visuals}
     - SCENE_BEATS: {json.dumps(chap['beats'])}
     
@@ -682,13 +744,15 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
         resp_draft = ai.model_writer.generate_content(prompt)
         utils.log_usage(folder, ai.model_writer.name, resp_draft.usage_metadata)
         current_text = resp_draft.text
+        draft_words = len(current_text.split()) if current_text else 0
+        utils.log("WRITER", f"  -> Draft: {draft_words:,} words (target: ~{est_words})")
     except Exception as e:
         utils.log("WRITER", f"⚠️ Failed Ch {chap['chapter_number']}: {e}")
         return f"## Chapter {chap['chapter_number']} Failed\n\nError: {e}"
 
     # Refinement Loop
     max_attempts = 5
-    SCORE_AUTO_ACCEPT = 9
+    SCORE_AUTO_ACCEPT = 8   # 8 = professional quality; no marginal gain from extra refinement
     SCORE_PASSING = 7
     SCORE_REWRITE_THRESHOLD = 6
     
@@ -750,43 +814,50 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None):
         guidelines = get_style_guidelines()
         fw_list = '", "'.join(guidelines['filter_words'])
         
-        # Exclude current critique from history to avoid duplication in prompt
-        history_str = "\n".join(past_critiques[:-1]) if len(past_critiques) > 1 else "None"
+        # Cap history to last 2 critiques to avoid token bloat
+        history_str = "\n".join(past_critiques[-3:-1]) if len(past_critiques) > 1 else "None"
 
         refine_prompt = f"""
         ROLE: Automated Editor
-        TASK: Rewrite text to satisfy critique and style rules.
+        TASK: Rewrite the draft chapter to address the critique. Preserve the narrative content and approximate word count.
 
-        CRITIQUE:
+        CURRENT_CRITIQUE:
         {critique}
 
-        HISTORY:
+        PREVIOUS_ATTEMPTS (context only):
         {history_str}
 
-        CONSTRAINTS:
+        HARD_CONSTRAINTS:
+        - TARGET_WORDS: ~{est_words} words (aim for this; ±20% is acceptable if the scene genuinely demands it — but do not condense beats to save space)
+        - BEATS MUST BE COVERED: {json.dumps(chap.get('beats', []))}
+        - SUMMARY CONTEXT: {prev_sum[:1500]}
+
+        AUTHOR_VOICE:
         {persona_info}
+
+        STYLE:
         {style_block}
         {char_visuals}
-        - BEATS: {json.dumps(chap.get('beats', []))}
 
-        OPTIMIZATION_RULES:
-        1. NO_FILTERS: Remove [{fw_list}].
-        2. VARIETY: No consecutive sentence starts.
-        3. SUBTEXT: Indirect dialogue.
-        4. TONE: Match {meta.get('genre', 'Fiction')}.
-        5. INTERACTION: Use environment.
-        6. DRAMA: No summary mode.
-        7. ACTIVE_VERBS: No 'was/were' + ing.
-        8. SHOWING: Physical emotion.
-        9. LOGIC: Continuous staging.
-        10. CLARITY: Simple structures.
+        PROSE_RULES (fix each one found in the draft):
+        1. FILTER_REMOVAL: Remove filter words [{fw_list}] — rewrite to show the sensation directly.
+        2. VARIETY: No two consecutive sentences starting with the same word or pronoun.
+        3. SUBTEXT: Dialogue must imply meaning — not state it outright.
+        4. TONE: Match {meta.get('genre', 'Fiction')} conventions throughout.
+        5. ENVIRONMENT: Characters interact with their physical space.
+        6. NO_SUMMARY_MODE: Dramatise key moments — do not skip or summarise them.
+        7. ACTIVE_VOICE: Replace 'was/were + verb-ing' constructions with active alternatives.
+        8. SHOWING: Render emotion through physical reactions, not labels.
+        9. STAGING: Characters must enter and exit physically — no teleporting.
+        10. CLARITY: Prefer simple sentence structures over convoluted ones.
 
-        INPUT_CONTEXT:
-        - SUMMARY: {prev_sum}
-        - PREVIOUS_TEXT: {prev_context_block}
-        - DRAFT: {current_text}
+        DRAFT_TO_REWRITE:
+        {current_text}
 
-        OUTPUT: Polished Markdown.
+        PREVIOUS_CHAPTER_ENDING (maintain continuity):
+        {prev_context_block}
+
+        OUTPUT: Complete polished chapter in Markdown. Include the chapter header. Same approximate length as the draft.
         """
         try:
             # Use Writer model (Flash) for refinement to save costs (Flash 1.5 is sufficient for editing)
@@ -1159,25 +1230,33 @@ def check_and_propagate(bp, manuscript, changed_chap_num, folder, change_summary
 
         utils.log("WRITER", f"  -> Checking Ch {target_chap['num']} for continuity...")
         
+        chap_word_count = len(target_chap.get('content', '').split())
         prompt = f"""
         ROLE: Continuity Checker
-        TASK: Determine if chapter needs rewrite based on new context.
+        TASK: Determine if a chapter contradicts a story change. If it does, rewrite it to fix the contradiction.
 
-        INPUT_DATA:
-        - CHANGED_CHAPTER: {changed_chap_num}
-        - NEW_CONTEXT: {current_context}
-        - CURRENT_CHAPTER_TEXT: {target_chap['content'][:5000]}...
+        CHANGED_CHAPTER: {changed_chap_num}
+        CHANGE_SUMMARY: {current_context}
+
+        CHAPTER_TO_CHECK (Ch {target_chap['num']}):
+        {target_chap['content'][:12000]}
 
         DECISION_LOGIC:
-        - Compare CURRENT_CHAPTER_TEXT with NEW_CONTEXT.
-        - If the chapter contradicts the new context (e.g. references events that didn't happen, or characters who are now dead/absent), it needs a REWRITE.
-        - If it fits fine, NO_CHANGE.
+        - If the chapter directly contradicts the change (references dead characters, items that no longer exist, events that didn't happen), status = REWRITE.
+        - If the chapter is consistent or only tangentially related, status = NO_CHANGE.
+        - Be conservative — only rewrite if there is a genuine contradiction.
+
+        REWRITE_RULES (apply only if REWRITE):
+        - Fix the specific contradiction. Preserve all other content.
+        - The rewritten chapter MUST be approximately {chap_word_count} words (same length as original).
+        - Include the chapter header formatted as Markdown H1.
+        - Do not add new plot points not in the original.
 
         OUTPUT_FORMAT (JSON):
         {{
             "status": "NO_CHANGE" or "REWRITE",
-            "reason": "Brief explanation",
-            "content": "Full Markdown text of the rewritten chapter (ONLY if status is REWRITE, otherwise null)"
+            "reason": "Brief explanation of the contradiction or why it's consistent",
+            "content": "Full Markdown rewritten chapter (ONLY if status is REWRITE, otherwise null)"
         }}
         """
         

modules/utils.py

@@ -71,6 +71,10 @@ def get_sorted_book_folders(run_dir):
     return sorted(subdirs, key=sort_key)
 
 # --- SHARED UTILS ---
+def log_banner(phase, title):
+    """Log a visually distinct phase separator line."""
+    log(phase, f"{'─' * 18} {title} {'─' * 18}")
+
 def log(phase, msg):
     timestamp = datetime.datetime.now().strftime('%H:%M:%S')
     line = f"[{timestamp}] {phase:<15} | {msg}"

modules/web_app.py

@@ -1303,7 +1303,8 @@ def system_status():
                 models_info = cache_data.get('models', {})
         except: pass
 
-    return render_template('system_status.html', models=models_info, cache=cache_data, datetime=datetime)
+    return render_template('system_status.html', models=models_info, cache=cache_data, datetime=datetime,
+                           image_model=ai.image_model_name, image_source=ai.image_model_source)
 
 @app.route('/personas')
 @login_required

templates/run_details.html

@@ -338,12 +338,61 @@
     const statusBar = document.getElementById('status-bar');
     const costEl = document.getElementById('run-cost');
 
+    let lastLog = '';
+
+    // Phase → colour mapping (matches utils.log phase labels)
+    const PHASE_COLORS = {
+        'WRITER':    '#4fc3f7',
+        'ARCHITECT': '#81c784',
+        'TIMING':    '#78909c',
+        'SYSTEM':    '#fff176',
+        'TRACKER':   '#ce93d8',
+        'RESUME':    '#ffb74d',
+        'SERIES':    '#64b5f6',
+        'ENRICHER':  '#4dd0e1',
+        'HARVESTER': '#ff8a65',
+        'EDITOR':    '#f48fb1',
+    };
+
+    function escapeHtml(str) {
+        return str.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
+    }
+
+    function colorizeLog(logText) {
+        if (!logText) return '';
+        return logText.split('\n').map(line => {
+            const m = line.match(/^(\[[\d:]+\])\s+(\w+)\s+\|(.*)$/);
+            if (!m) return '<span style="color:#666">' + escapeHtml(line) + '</span>';
+            const [, ts, phase, msg] = m;
+            const color = PHASE_COLORS[phase] || '#aaaaaa';
+            return '<span style="color:#555">' + escapeHtml(ts) + '</span> '
+                 + '<span style="color:' + color + ';font-weight:bold">' + phase.padEnd(14) + '</span>'
+                 + '<span style="color:#ccc">|' + escapeHtml(msg) + '</span>';
+        }).join('\n');
+    }
+
+    function getCurrentPhase(logText) {
+        if (!logText) return '';
+        const lines = logText.split('\n').filter(l => l.trim());
+        for (let k = lines.length - 1; k >= 0; k--) {
+            const m = lines[k].match(/\]\s+(\w+)\s+\|/);
+            if (m) return m[1];
+        }
+        return '';
+    }
+
     function updateLog() {
         fetch(`/run/${runId}/status`)
             .then(response => response.json())
             .then(data => {
-                // Update Status Text
-                statusText.innerText = "Status: " + data.status.charAt(0).toUpperCase() + data.status.slice(1);
+                // Update Status Text + current phase
+                const statusLabel = data.status.charAt(0).toUpperCase() + data.status.slice(1);
+                if (data.status === 'running') {
+                    const phase = getCurrentPhase(data.log);
+                    statusText.innerText = 'Status: Running' + (phase ? ' — ' + phase : '');
+                } else {
+                    statusText.innerText = 'Status: ' + statusLabel;
+                }
                 costEl.innerText = '$' + parseFloat(data.cost).toFixed(4);
 
                 // Update Status Bar
@@ -371,10 +420,11 @@
                     statusBar.innerText = "";
                 }
 
-                // Update Log (only if changed to avoid scroll jitter)
-                if (consoleEl.innerText !== data.log) {
+                // Update Log with phase colorization (only if changed to avoid scroll jitter)
+                if (lastLog !== data.log) {
+                    lastLog = data.log;
                     const isScrolledToBottom = consoleEl.scrollHeight - consoleEl.clientHeight <= consoleEl.scrollTop + 50;
-                    consoleEl.innerText = data.log;
+                    consoleEl.innerHTML = colorizeLog(data.log);
                     if (isScrolledToBottom) {
                         consoleEl.scrollTop = consoleEl.scrollHeight;
                     }

templates/system_status.html

@@ -56,6 +56,22 @@
                         </tr>
                         {% endif %}
                         {% endfor %}
+                        <tr>
+                            <td class="fw-bold text-uppercase">Image</td>
+                            <td>
+                                {% if image_model %}
+                                <span class="badge bg-success">{{ image_model }}</span>
+                                {% else %}
+                                <span class="badge bg-danger">Unavailable</span>
+                                {% endif %}
+                            </td>
+                            <td>
+                                <span class="badge bg-light text-dark border">{{ image_source or 'None' }}</span>
+                            </td>
+                            <td class="small text-muted">
+                                {% if image_model %}Imagen model used for book cover generation.{% else %}No image generation model could be initialized. Check GCP credentials or Gemini API key.{% endif %}
+                            </td>
+                        </tr>
                     {% else %}
                         <tr>
                             <td colspan="3" class="text-center py-4 text-muted">
@@ -139,15 +155,32 @@
         <h5 class="mb-0"><i class="fas fa-clock me-2"></i>Cache Status</h5>
     </div>
     <div class="card-body">
-        <p class="mb-0">
+        <p class="mb-1">
             <strong>Last Scan:</strong>
             {% if cache and cache.timestamp %}
-                {{ datetime.fromtimestamp(cache.timestamp).strftime('%Y-%m-%d %H:%M:%S') }}
+                {{ datetime.fromtimestamp(cache.timestamp).strftime('%Y-%m-%d %H:%M:%S') }} UTC
             {% else %}
                 Never
             {% endif %}
         </p>
-        <p class="text-muted small mb-0">Model selection is cached for 24 hours to save API calls.</p>
+        <p class="mb-0">
+            <strong>Next Refresh:</strong>
+            {% if cache and cache.timestamp %}
+                {% set expires = cache.timestamp + 86400 %}
+                {% set now_ts = datetime.utcnow().timestamp() %}
+                {% if expires > now_ts %}
+                    {% set remaining = (expires - now_ts) | int %}
+                    {% set h = remaining // 3600 %}{% set m = (remaining % 3600) // 60 %}
+                    in {{ h }}h {{ m }}m
+                    <span class="badge bg-success ms-1">Cache Valid</span>
+                {% else %}
+                    <span class="badge bg-warning text-dark">Expired — click Refresh &amp; Optimize</span>
+                {% endif %}
+            {% else %}
+                <span class="badge bg-warning text-dark">No cache — click Refresh &amp; Optimize</span>
+            {% endif %}
+        </p>
+        <p class="text-muted small mt-2 mb-0">Model selection is cached for 24 hours to save API calls.</p>
     </div>
 </div>
 {% endblock %}