Update app.py

app.py

@@ -1,1379 +1,115 @@
-# --- Combined Imports ------------------------------------
-import io
+# app.py (streamlined and modularized for clarity and maintainability)
+import streamlit as st
 import os
-import re
-import base64
 import glob
-import logging
-import random
-import shutil
-import time
-import zipfile
-import json
-import asyncio
-import aiofiles
-
-from datetime import datetime
-from collections import Counter
-from dataclasses import dataclass, field
-from io import BytesIO
-from typing import Optional, List, Dict, Any
-
+import base64
 import pandas as pd
-import pytz
-import streamlit as st
-from PIL import Image, ImageDraw, UnidentifiedImageError # Added ImageDraw and UnidentifiedImageError
+import fitz
+from PIL import Image
+from io import BytesIO
+from datetime import datetime
 from reportlab.pdfgen import canvas
 from reportlab.lib.utils import ImageReader
-from reportlab.lib.pagesizes import letter # Default page size
-from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Image as PlatypusImage, PageBreak, Preformatted
-from reportlab.lib.styles import getSampleStyleSheet
-from reportlab.lib.units import inch
-from reportlab.lib.enums import TA_CENTER, TA_LEFT # For text alignment
-import fitz # PyMuPDF
-
-# --- Hugging Face Imports ---
-from huggingface_hub import InferenceClient, HfApi, list_models
-from huggingface_hub.utils import RepositoryNotFoundError, GatedRepoError # Import specific exceptions
+from markdown2 import markdown
 
-# --- App Configuration -----------------------------------
+# --- Config ---
 st.set_page_config(
-    page_title="Vision & Layout Titans (HF) 🚀🖼️",
+    page_title="Vision & Layout Titans 🚀",
     page_icon="🤖",
-    layout="wide",
-    initial_sidebar_state="expanded",
-    menu_items={
-        'Get Help': 'https://huggingface.co/docs',
-        'Report a Bug': None, # Replace with your bug report link if desired
-        'About': "Combined App: PDF Layout Generator + Hugging Face Powered AI Tools 🌌"
-    }
+    layout="wide"
 )
 
-
-# Conditional imports for optional/heavy libraries
-try:
-    import torch
-    from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor, AutoModelForVision2Seq, AutoModelForImageToWaveform, pipeline
-    # Add more AutoModel classes as needed for different tasks (Vision, OCR, etc.)
-    _transformers_available = True
-except ImportError:
-    _transformers_available = False
-    # Place warning inside main app area if sidebar isn't ready
-    # st.sidebar.warning("AI/ML libraries (torch, transformers) not found. Local model features disabled.")
-
-try:
-    from diffusers import StableDiffusionPipeline
-    _diffusers_available = True
-except ImportError:
-    _diffusers_available = False
-    # Don't show warning if transformers also missing, handled above
-    # if _transformers_available:
-        # st.sidebar.warning("Diffusers library not found. Diffusion model features disabled.")
-
-
-import requests # Keep requests import
-
-# --- Logging Setup ---------------------------------------
-logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
-logger = logging.getLogger(__name__)
-log_records = []
-class LogCaptureHandler(logging.Handler):
-    def emit(self, record):
-        # Limit stored logs to avoid memory issues
-        if len(log_records) > 200:
-             log_records.pop(0)
-        log_records.append(record)
-logger.addHandler(LogCaptureHandler())
-
-# --- Environment Variables & Constants -------------------
-HF_TOKEN = os.getenv("HF_TOKEN")
-DEFAULT_PROVIDER = "hf-inference"
-# Model List (curated, similar to Gradio example) - can be updated
-FEATURED_MODELS_LIST = [
-    "meta-llama/Meta-Llama-3.1-8B-Instruct", # Updated Llama model
-    "mistralai/Mistral-7B-Instruct-v0.3",
-    "google/gemma-2-9b-it", # Added Gemma 2
-    "Qwen/Qwen2-7B-Instruct", # Added Qwen2
-    "microsoft/Phi-3-mini-4k-instruct",
-    "HuggingFaceH4/zephyr-7b-beta",
-    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", # Larger Mixture of Experts
-    # Add a smaller option
-    "HuggingFaceTB/SmolLM-1.7B-Instruct"
-]
-# Add common vision models if planning local loading
-VISION_MODELS_LIST = [
-    "Salesforce/blip-image-captioning-large",
-    "microsoft/trocr-large-handwritten", # OCR model
-    "llava-hf/llava-1.5-7b-hf", # Vision Language Model
-    "google/vit-base-patch16-224", # Basic Vision Transformer
-]
-DIFFUSION_MODELS_LIST = [
-    "stabilityai/stable-diffusion-xl-base-1.0", # Common SDXL
-    "runwayml/stable-diffusion-v1-5", # Classic SD 1.5
-    "OFA-Sys/small-stable-diffusion-v0", # Tiny diffusion
-]
-
-
-# --- Session State Initialization (Combined & Updated) ---
-# Combined PDF Generator specific (replaces layout specific)
-st.session_state.setdefault('combined_pdf_sources', []) # List of dicts {'filepath': path, 'type': type}
-
-# General App State
-st.session_state.setdefault('history', [])
-st.session_state.setdefault('processing', {})
-st.session_state.setdefault('asset_checkboxes', {})
-st.session_state.setdefault('downloaded_pdfs', {})
-st.session_state.setdefault('unique_counter', 0)
-st.session_state.setdefault('cam0_file', None)
-st.session_state.setdefault('cam1_file', None)
-st.session_state.setdefault('characters', [])
-st.session_state.setdefault('char_form_reset_key', 0) # For character form reset
-# Removed gallery_size state - no longer used
-# st.session_state.setdefault('gallery_size', 10)
-
-# --- Hugging Face & Local Model State ---
-st.session_state.setdefault('hf_inference_client', None) # Store initialized client
-st.session_state.setdefault('hf_provider', DEFAULT_PROVIDER)
-st.session_state.setdefault('hf_custom_key', "")
-st.session_state.setdefault('hf_selected_api_model', FEATURED_MODELS_LIST[0]) # Default API model
-st.session_state.setdefault('hf_custom_api_model', "") # User override for API model
-
-# Local Model Management
-st.session_state.setdefault('local_models', {}) # Dict to store loaded models: {'path': {'model': obj, 'tokenizer/proc': obj, 'type': 'causal/vision/etc'}}
-st.session_state.setdefault('selected_local_model_path', None) # Path of the currently active local model
-
-# Inference Parameters (shared for API and local where applicable)
-st.session_state.setdefault('gen_max_tokens', 512)
-st.session_state.setdefault('gen_temperature', 0.7)
-st.session_state.setdefault('gen_top_p', 0.95)
-st.session_state.setdefault('gen_frequency_penalty', 0.0) # Corresponds to repetition_penalty=1.0
-st.session_state.setdefault('gen_seed', -1) # -1 for random
-
-# Removed asset_gallery_container - render directly in sidebar
-# if 'asset_gallery_container' not in st.session_state:
-#     st.session_state['asset_gallery_container'] = st.sidebar.empty()
-
-# --- Dataclasses (Refined for Local Models) -------------
-@dataclass
-class LocalModelConfig:
-    name: str                   # User-defined local name
-    hf_id: str                  # Hugging Face model ID used for download
-    model_type: str             # 'causal', 'vision', 'diffusion', 'ocr', etc.
-    size_category: str = "unknown" # e.g., 'small', 'medium', 'large'
-    domain: Optional[str] = None
-    local_path: str = field(init=False) # Path where it's saved
-
-    def __post_init__(self):
-        # Define local path based on type and name
-        type_folder = f"{self.model_type}_models"
-        safe_name = re.sub(r'[^\w\-]+', '_', self.name) # Sanitize name for path
-        self.local_path = os.path.join(type_folder, safe_name)
-
-    def get_full_path(self):
-        return os.path.abspath(self.local_path)
-
-# (Keep DiffusionConfig if still using diffusers library separately)
-@dataclass
-class DiffusionConfig: # Kept for clarity in diffusion tab if needed
-    name: str
-    base_model: str
-    size: str
-    domain: Optional[str] = None
-    @property
-    def model_path(self):
-        # Ensure diffusion models are saved in their own distinct top-level folder
-        return f"diffusion_models/{re.sub(r'[^w-]+', '_', self.name)}"
-
-
-# --- Helper Functions (Combined and refined) -------------
-def generate_filename(sequence, ext="png"):
-    timestamp = time.strftime('%Y%m%d_%H%M%S')
-    safe_sequence = re.sub(r'[^\w\-]+', '_', str(sequence))
-    return f"{safe_sequence}_{timestamp}.{ext}"
-
-def pdf_url_to_filename(url):
-    name = re.sub(r'^https?://', '', url)
-    name = re.sub(r'[<>:"/\\|?*]', '_', name)
-    return name[:100] + ".pdf" # Limit length
-
-def get_download_link(file_path, mime_type="application/octet-stream", label="Download"):
-    if not os.path.exists(file_path): return f"{label} (File not found)"
-    try:
-        with open(file_path, "rb") as f: file_bytes = f.read()
-        b64 = base64.b64encode(file_bytes).decode()
-        return f'<a href="data:{mime_type};base64,{b64}" download="{os.path.basename(file_path)}">{label}</a>'
-    except Exception as e:
-        logger.error(f"Error creating download link for {file_path}: {e}")
-        return f"{label} (Error)"
-
-def zip_directory(directory_path, zip_path):
-    with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
-        for root, _, files in os.walk(directory_path):
-            for file in files:
-                file_path = os.path.join(root, file)
-                zipf.write(file_path, os.path.relpath(file_path, os.path.dirname(directory_path)))
-
-def get_local_model_paths(model_type="causal"):
-    """Gets paths of locally saved models of a specific type."""
-    pattern = f"{model_type}_models/*"
-    dirs = [d for d in glob.glob(pattern) if os.path.isdir(d)]
-    return dirs
-
-def get_gallery_files(file_types=("png", "pdf", "jpg", "jpeg", "md", "txt")):
-    """Gets all files with specified extensions in the current directory."""
-    all_files = set()
-    for ext in file_types:
-        # Ensure the glob pattern correctly targets files in the script's directory
-        all_files.update(glob.glob(f"./*.{ext.lower()}")) # Use ./* for current dir
-        all_files.update(glob.glob(f"./*.{ext.upper()}"))
-    # Convert to list and remove potential './' prefix for cleaner display
-    return sorted([os.path.normpath(f) for f in all_files])
-
-def get_pdf_files():
-    # Use get_gallery_files to find PDFs
-    return get_gallery_files(['pdf'])
-
-def download_pdf(url, output_path):
-    try:
-        headers = {'User-Agent': 'Mozilla/5.0'}
-        response = requests.get(url, stream=True, timeout=20, headers=headers)
-        response.raise_for_status()
-        with open(output_path, "wb") as f:
-            for chunk in response.iter_content(chunk_size=8192): f.write(chunk)
-        logger.info(f"Successfully downloaded {url} to {output_path}")
-        return True
-    except requests.exceptions.RequestException as e:
-        logger.error(f"Failed to download {url}: {e}")
-        if os.path.exists(output_path):
-            try:
-                os.remove(output_path)
-                logger.info(f"Removed partially downloaded file: {output_path}")
-            except OSError as remove_error:
-                logger.error(f"Error removing partial file {output_path}: {remove_error}")
-            except Exception as general_remove_error:
-                logger.error(f"General error removing partial file {output_path}: {general_remove_error}")
-        return False
-    except Exception as e:
-        logger.error(f"An unexpected error occurred during download of {url}: {e}")
-        if os.path.exists(output_path):
-             try:
-                  os.remove(output_path)
-                  logger.info(f"Removed file after unexpected error: {output_path}")
-             except OSError as remove_error:
-                  logger.error(f"Error removing file after unexpected error {output_path}: {remove_error}")
-             except Exception as general_remove_error:
-                  logger.error(f"General error removing file after unexpected error {output_path}: {general_remove_error}")
-        return False
-
-async def process_pdf_snapshot(pdf_path, mode="single", resolution_factor=2.0):
-    start_time = time.time()
-    # Use a placeholder within the main app area for status during async operations
-    status_placeholder = st.empty()
-    status_placeholder.text(f"Processing PDF Snapshot ({mode}, Res: {resolution_factor}x)... (0s)")
-    output_files = []
-    try:
-        doc = fitz.open(pdf_path)
-        matrix = fitz.Matrix(resolution_factor, resolution_factor)
-        num_pages_to_process = 0
-        if mode == "single": num_pages_to_process = min(1, len(doc))
-        elif mode == "twopage": num_pages_to_process = min(2, len(doc))
-        elif mode == "allpages": num_pages_to_process = len(doc)
-
-        for i in range(num_pages_to_process):
-            page_start_time = time.time()
-            page = doc.load_page(i) # Use load_page for efficiency
-            pix = page.get_pixmap(matrix=matrix)
-            base_name = os.path.splitext(os.path.basename(pdf_path))[0]
-            output_file = generate_filename(f"{base_name}_pg{i+1}_{mode}", "png")
-
-            # Ensure output path is valid before saving
-            output_dir = os.path.dirname(output_file) or "."
-            if not os.path.exists(output_dir): os.makedirs(output_dir)
-
-            await asyncio.to_thread(pix.save, output_file)
-            output_files.append(output_file)
-            elapsed_page = int(time.time() - page_start_time)
-            status_placeholder.text(f"Processing PDF Snapshot ({mode}, Res: {resolution_factor}x)... Page {i+1}/{num_pages_to_process} done ({elapsed_page}s)")
-            await asyncio.sleep(0.01)
-
-        doc.close()
-        elapsed = int(time.time() - start_time)
-        status_placeholder.success(f"PDF Snapshot ({mode}, {len(output_files)} files) completed in {elapsed}s!")
-        return output_files
-    except Exception as e:
-        logger.error(f"Failed to process PDF snapshot for {pdf_path}: {e}", exc_info=True) # Add traceback
-        status_placeholder.error(f"Failed to process PDF {os.path.basename(pdf_path)}: {e}")
-        # Clean up any files created before the error
-        for f in output_files:
-            if os.path.exists(f):
-                try: os.remove(f)
-                except: pass
-        return []
-
-
-# --- HF Inference Client Management ---
-def get_hf_client() -> Optional[InferenceClient]:
-    """Gets or initializes the Hugging Face Inference Client based on session state."""
-    provider = st.session_state.hf_provider
-    custom_key = st.session_state.hf_custom_key.strip()
-    token_to_use = custom_key if custom_key else HF_TOKEN
-
-    if not token_to_use and provider != "hf-inference":
-        # Don't show error here, let caller handle it if client is needed
-        # st.error(f"Provider '{provider}' requires a Hugging Face API token...")
-        return None
-    if provider == "hf-inference" and not token_to_use:
-         logger.warning("Using hf-inference provider without a token. Rate limits may apply.")
-         token_to_use = None # Explicitly set to None for public inference API
-
-    # Check if client needs re-initialization
-    current_client = st.session_state.get('hf_inference_client')
-    needs_reinit = True
-    if current_client:
-         # Compare provider and token status more carefully
-         current_token = getattr(current_client, '_token', None) # Access internal token if exists
-         current_provider = getattr(current_client, 'provider', None) # Access provider if exists
-
-         token_matches = (token_to_use == current_token)
-         provider_matches = (provider == current_provider)
-
-         if token_matches and provider_matches:
-              needs_reinit = False
-
-    if needs_reinit:
-        try:
-            logger.info(f"Initializing InferenceClient for provider: {provider}. Token source: {'Custom Key' if custom_key else ('HF_TOKEN' if HF_TOKEN else 'None')}")
-            st.session_state.hf_inference_client = InferenceClient(model=None, token=token_to_use, provider=provider) # Init without model initially
-            # Store provider on client instance if possible (check InferenceClient structure or assume it's handled internally)
-            setattr(st.session_state.hf_inference_client, 'provider', provider) # Explicitly store provider for re-init check
-            setattr(st.session_state.hf_inference_client, '_token', token_to_use) # Explicitly store token for re-init check
-            logger.info("InferenceClient initialized successfully.")
-        except Exception as e:
-            st.error(f"Failed to initialize Hugging Face client for provider {provider}: {e}")
-            logger.error(f"InferenceClient initialization failed: {e}")
-            st.session_state.hf_inference_client = None
-
-    return st.session_state.hf_inference_client
-
-# --- HF/Local Model Processing Functions ---
-def process_text_hf(text: str, prompt: str, use_api: bool) -> str:
-    """Processes text using either HF Inference API or a loaded local model."""
-    status_placeholder = st.empty()
-    start_time = time.time()
-    result_text = ""
-
-    params = {
-        "max_new_tokens": st.session_state.gen_max_tokens,
-        "temperature": st.session_state.gen_temperature,
-        "top_p": st.session_state.gen_top_p,
-        "repetition_penalty": st.session_state.gen_frequency_penalty, # Keep user value, adjust name below if needed
-    }
-    seed = st.session_state.gen_seed
-    if seed != -1: params["seed"] = seed
-
-    system_prompt = "You are a helpful assistant. Process the following text based on the user's request."
-    full_prompt = f"{prompt}\n\n---\n\n{text}"
-    messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": full_prompt}]
-
-    if use_api:
-        status_placeholder.info("Processing text using Hugging Face API...")
-        client = get_hf_client()
-        if not client: return "Error: Hugging Face client not configured/available."
-        model_id = st.session_state.hf_custom_api_model.strip() or st.session_state.hf_selected_api_model
-        if not model_id: return "Error: No Hugging Face API model specified."
-        status_placeholder.info(f"Using API Model: {model_id}")
-        try:
-            # Ensure repetition_penalty is passed correctly if supported
-            api_params = {
-                "max_tokens": params['max_new_tokens'],
-                "temperature": params['temperature'],
-                "top_p": params['top_p'],
-                "repetition_penalty": params.get('repetition_penalty') # Check if API uses this name
-            }
-            if 'seed' in params: api_params['seed'] = params['seed']
-
-            response = client.chat_completion(model=model_id, messages=messages, **api_params)
-            result_text = response.choices[0].message.content or ""
-            logger.info(f"HF API text processing successful for model {model_id}.")
-        except Exception as e:
-            logger.error(f"HF API text processing failed for model {model_id}: {e}", exc_info=True)
-            result_text = f"Error during Hugging Face API inference: {str(e)}"
-    else:
-        status_placeholder.info("Processing text using local model...")
-        if not _transformers_available: return "Error: Transformers library not available."
-        model_path = st.session_state.get('selected_local_model_path')
-        if not model_path or model_path not in st.session_state.get('local_models', {}): return "Error: No suitable local model selected/loaded."
-        local_model_data = st.session_state['local_models'][model_path]
-        if local_model_data.get('type') != 'causal': return f"Error: Loaded model '{os.path.basename(model_path)}' is not a Causal LM."
-        status_placeholder.info(f"Using Local Model: {os.path.basename(model_path)}")
-        model = local_model_data.get('model')
-        tokenizer = local_model_data.get('tokenizer')
-        if not model or not tokenizer: return f"Error: Model/tokenizer not found for {os.path.basename(model_path)}."
-        try:
-            try: prompt_for_model = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-            except: logger.warning(f"Chat template failed for {model_path}. Using basic format."); prompt_for_model = f"System: {system_prompt}\nUser: {full_prompt}\nAssistant:"
-            inputs = tokenizer(prompt_for_model, return_tensors="pt", padding=True, truncation=True, max_length=2048).to(model.device) # Increased context slightly
-            generate_params = {
-                "max_new_tokens": params['max_new_tokens'],
-                "temperature": params['temperature'],
-                "top_p": params['top_p'],
-                "repetition_penalty": params.get('repetition_penalty', 1.0),
-                "do_sample": True if params['temperature'] > 0.01 else False, # Sample if temp > 0.01
-                "pad_token_id": tokenizer.eos_token_id
-            }
-            with torch.no_grad(): outputs = model.generate(**inputs, **generate_params)
-            input_length = inputs['input_ids'].shape[1]; generated_ids = outputs[0][input_length:]
-            result_text = tokenizer.decode(generated_ids, skip_special_tokens=True)
-            logger.info(f"Local text processing successful for model {model_path}.")
-        except Exception as e:
-            logger.error(f"Local text processing failed for model {model_path}: {e}", exc_info=True)
-            result_text = f"Error during local model inference: {str(e)}"
-
-    elapsed = int(time.time() - start_time)
-    status_placeholder.success(f"Text processing completed in {elapsed}s.")
-    return result_text
-
-def process_image_hf(image: Image.Image, prompt: str, use_api: bool) -> str:
-    """Processes an image using either HF Inference API or a local model."""
-    status_placeholder = st.empty()
-    start_time = time.time()
-    result_text = "[Image processing requires specific Vision model implementation]"
-
-    if use_api:
-        status_placeholder.info("Processing image using Hugging Face API (Image-to-Text)...")
-        client = get_hf_client()
-        if not client: return "Error: HF client not configured."
-        buffered = BytesIO(); image.save(buffered, format="PNG"); img_bytes = buffered.getvalue()
-        try:
-            captioning_model_id = "Salesforce/blip-image-captioning-large" # Default captioner
-            vqa_model_id = "llava-hf/llava-1.5-7b-hf" # Default VQA - MAY REQUIRE DIFFERENT CLIENT CALL
-            # Decide whether to use captioning or VQA based on prompt? Simple approach: captioning.
-            status_placeholder.info(f"Using API Image-to-Text Model: {captioning_model_id}")
-            response_list = client.image_to_text(data=img_bytes, model=captioning_model_id)
-            if response_list and 'generated_text' in response_list[0]:
-                result_text = f"API Caption: {response_list[0]['generated_text']}\n(Prompt '{prompt}' likely ignored by this API endpoint)"
-                logger.info(f"HF API image captioning successful for model {captioning_model_id}.")
-            else: result_text = "Error: Unexpected response format from image-to-text API."; logger.warning(f"Unexpected API response: {response_list}")
-        except Exception as e: logger.error(f"HF API image processing failed: {e}"); result_text = f"Error during HF API image inference: {str(e)}"
-    else:
-        status_placeholder.info("Processing image using local model...")
-        if not _transformers_available: return "Error: Transformers library needed."
-        model_path = st.session_state.get('selected_local_model_path')
-        if not model_path or model_path not in st.session_state.get('local_models', {}): return "Error: No suitable local model selected/loaded."
-        local_model_data = st.session_state['local_models'][model_path]
-        model_type = local_model_data.get('type')
-        if model_type not in ['vision', 'ocr']: return f"Error: Loaded model '{os.path.basename(model_path)}' is not a Vision/OCR type."
-        status_placeholder.warning(f"Local {model_type} Model ({os.path.basename(model_path)}): Processing logic depends on specific model. Placeholder active.")
-        # --- ADD SPECIFIC LOCAL VISION/OCR MODEL LOGIC HERE ---
-        # This section needs code tailored to the loaded model's processor/generate methods
-        # Example placeholder:
-        processor = local_model_data.get('processor')
-        model = local_model_data.get('model')
-        if processor and model:
-             result_text = f"[Local {model_type} model processing needs implementation for {os.path.basename(model_path)}. Prompt: '{prompt}']"
-        else:
-             result_text = f"Error: Missing model or processor for local {model_type} model {os.path.basename(model_path)}."
-        # --- END OF PLACEHOLDER ---
-
-    elapsed = int(time.time() - start_time)
-    status_placeholder.success(f"Image processing attempt completed in {elapsed}s.")
-    return result_text
-
-async def process_hf_ocr(image: Image.Image, output_file: str, use_api: bool) -> str:
-    """ Performs OCR using the process_image_hf function framework. """
-    # Simple prompt for OCR task
-    ocr_prompt = "Extract text content from this image."
-    result = process_image_hf(image, ocr_prompt, use_api=use_api) # Pass use_api flag
-
-    # Save the result if it looks like text (basic check)
-    if result and not result.startswith("Error") and not result.startswith("["):
-        try:
-            async with aiofiles.open(output_file, "w", encoding='utf-8') as f:
-                await f.write(result)
-            logger.info(f"HF OCR result saved to {output_file}")
-        except IOError as e:
-             logger.error(f"Failed to save HF OCR output to {output_file}: {e}")
-             result += f"\n[Error saving file: {e}]" # Append error to result if save fails
-
-    # --- CORRECTED BLOCK ---
-    elif os.path.exists(output_file):
-        # Remove file if processing failed or was just a placeholder message
-        try:
-            os.remove(output_file)
-        except OSError:
-            # Log error or just ignore if removal fails
-            logger.warning(f"Could not remove potentially empty/failed OCR file: {output_file}")
-            pass # Ignore removal error
-        except Exception as e_rem: # Catch any other error during removal
-             logger.warning(f"Error removing OCR file {output_file}: {e_rem}")
-             pass
-    # --- END CORRECTION ---
-
-    return result
-
-# --- Character Functions (Keep from previous) -----------
-def randomize_character_content():
-    intro_templates = ["{char} is a valiant knight...", "{char} is a mischievous thief...", "{char} is a wise scholar...", "{char} is a fiery warrior...", "{char} is a gentle healer..."]
-    greeting_templates = ["'I am from the knight's guild...'", "'I heard you needed help—name’s {char}...", "'Oh, hello! I’m {char}, didn’t see you there...'", "'I’m {char}, and I’m here to fight...'", "'I’m {char}, here to heal...'"]
-    name = f"Character_{random.randint(1000, 9999)}"; gender = random.choice(["Male", "Female"]); intro = random.choice(intro_templates).format(char=name); greeting = random.choice(greeting_templates).format(char=name)
-    return name, gender, intro, greeting
-
-def save_character(character_data):
-    characters = st.session_state.get('characters', []);
-    if any(c['name'] == character_data['name'] for c in characters): st.error(f"Character name '{character_data['name']}' already exists."); return False
-    characters.append(character_data); st.session_state['characters'] = characters
-    try:
-        with open("characters.json", "w", encoding='utf-8') as f: json.dump(characters, f, indent=2); logger.info(f"Saved character: {character_data['name']}"); return True
-    except IOError as e: logger.error(f"Failed to save characters.json: {e}"); st.error(f"Failed to save character file: {e}"); return False
-
-def load_characters():
-    if not os.path.exists("characters.json"): st.session_state['characters'] = []; return
-    try:
-        with open("characters.json", "r", encoding='utf-8') as f: characters = json.load(f)
-        if isinstance(characters, list): st.session_state['characters'] = characters; logger.info(f"Loaded {len(characters)} characters.")
-        else: st.session_state['characters'] = []; logger.warning("characters.json is not a list, resetting."); os.remove("characters.json")
-    except (json.JSONDecodeError, IOError) as e:
-        logger.error(f"Failed to load or decode characters.json: {e}"); st.error(f"Error loading character file: {e}. Starting fresh."); st.session_state['characters'] = []
-        try: corrupt_filename = f"characters_corrupt_{int(time.time())}.json"; shutil.copy("characters.json", corrupt_filename); logger.info(f"Backed up corrupted character file to {corrupt_filename}"); os.remove("characters.json")
-        except Exception as backup_e: logger.error(f"Could not backup corrupted character file: {backup_e}")
-
-# --- Utility: Clean stems (Keep from previous) ----------
-def clean_stem(fn: str) -> str:
-    name = os.path.splitext(os.path.basename(fn))[0]; name = name.replace('-', ' ').replace('_', ' ')
-    return name.strip().title()
-
-# --- PDF Creation Functions ---
-# Original image-only PDF function (might be removed or kept as an option)
-def make_image_sized_pdf(sources):
-    # ... (kept same as previous version for now) ...
-    if not sources: st.warning("No image sources provided for PDF generation."); return None
-    buf = io.BytesIO(); c = canvas.Canvas(buf, pagesize=letter)
-    try:
-        for idx, src in enumerate(sources, start=1):
-            status_placeholder = st.empty(); status_placeholder.info(f"Adding page {idx}/{len(sources)}: {os.path.basename(str(src))}...")
-            try:
-                filename = f'page_{idx}'
-                if isinstance(src, str):
-                    if not os.path.exists(src): logger.warning(f"Image file not found: {src}. Skipping."); status_placeholder.warning(f"Skipping missing file: {os.path.basename(src)}"); continue
-                    img_obj = Image.open(src); filename = os.path.basename(src)
-                elif hasattr(src, 'name'): # Handle uploaded file object
-                    src.seek(0); img_obj = Image.open(src); filename = getattr(src, 'name', f'uploaded_image_{idx}'); src.seek(0)
-                else: continue # Skip unknown source type
-                with img_obj:
-                    iw, ih = img_obj.size
-                    if iw <= 0 or ih <= 0: logger.warning(f"Invalid image dimensions ({iw}x{ih}) for {filename}. Skipping."); status_placeholder.warning(f"Skipping invalid image: {filename}"); continue
-                    cap_h = 30; pw, ph = iw, ih + cap_h; c.setPageSize((pw, ph)); img_reader = ImageReader(img_obj)
-                    c.drawImage(img_reader, 0, cap_h, width=iw, height=ih, preserveAspectRatio=True, anchor='c', mask='auto')
-                    caption = clean_stem(filename); c.setFont('Helvetica', 12); c.setFillColorRGB(0, 0, 0); c.drawCentredString(pw / 2, cap_h / 2 + 3, caption)
-                    c.setFont('Helvetica', 8); c.setFillColorRGB(0.5, 0.5, 0.5); c.drawRightString(pw - 10, 8, f"Page {idx}")
-                    c.showPage(); status_placeholder.success(f"Added page {idx}/{len(sources)}: {filename}")
-            except (IOError, OSError, UnidentifiedImageError) as img_err: logger.error(f"Error processing image {src}: {img_err}"); status_placeholder.error(f"Error adding page {idx}: {img_err}")
-            except Exception as e: logger.error(f"Unexpected error adding page {idx} ({src}): {e}"); status_placeholder.error(f"Unexpected error on page {idx}: {e}")
-        c.save(); buf.seek(0)
-        if buf.getbuffer().nbytes < 100: st.error("PDF generation resulted in an empty file."); return None
-        return buf.getvalue()
-    except Exception as e: logger.error(f"Fatal error during PDF generation: {e}"); st.error(f"PDF Generation Failed: {e}"); return None
-
-# --- NEW Combined PDF Generation Function ---
-def make_combined_pdf(ordered_sources_info: List[Dict]) -> Optional[bytes]:
-    if not ordered_sources_info:
-        st.warning("No items selected for combined PDF generation.")
-        return None
-
-    buf = io.BytesIO()
-    c = canvas.Canvas(buf, pagesize=letter)
-    styles = getSampleStyleSheet()
-    total_pages_generated = 0
-
-    # Add page number function
-    def draw_page_number(canvas, page_num, page_width, page_height):
-        canvas.saveState()
-        canvas.setFont('Helvetica', 8)
-        canvas.setFillColorRGB(0.5, 0.5, 0.5)
-        canvas.drawRightString(page_width - inch/2, inch/2, f"Page {page_num}")
-        canvas.restoreState()
-
-    for idx, item_info in enumerate(ordered_sources_info):
-        filepath = item_info.get('filepath')
-        file_type = item_info.get('type')
-        filename = item_info.get('filename', f"item_{idx+1}")
-        item_caption = clean_stem(filename)
-
-        if not filepath: logger.warning(f"Skipping item {idx+1} due to missing filepath."); continue
-        is_file_object = not isinstance(filepath, str)
-        status_placeholder = st.empty()
-        status_placeholder.info(f"Processing item {idx+1}/{len(ordered_sources_info)}: {filename} ({file_type})...")
-
-        try:
-            # --- IMAGE Processing ---
-            if file_type == 'Image':
-                if is_file_object: filepath.seek(0)
-                try:
-                    img_obj = Image.open(filepath)
-                    with img_obj:
-                        iw, ih = img_obj.size
-                        if iw <= 0 or ih <= 0: raise ValueError("Invalid image dimensions")
-                        cap_h = 30; pw, ph = iw, ih + cap_h
-                        c.setPageSize((pw, ph)); img_reader = ImageReader(img_obj)
-                        c.drawImage(img_reader, 0, cap_h, width=iw, height=ih, preserveAspectRatio=True, anchor='c', mask='auto')
-                        c.setFont('Helvetica', 12); c.setFillColorRGB(0, 0, 0); c.drawCentredString(pw / 2, cap_h / 2 + 3, item_caption)
-                        total_pages_generated += 1; draw_page_number(c, total_pages_generated, pw, ph)
-                        c.showPage()
-                finally:
-                    if is_file_object: filepath.seek(0)
-
-            # --- PDF Processing ---
-            elif file_type == 'PDF':
-                src_doc = None
-                try:
-                    if is_file_object: filepath.seek(0); pdf_bytes = filepath.read(); src_doc = fitz.open("pdf", pdf_bytes)
-                    else: src_doc = fitz.open(filepath)
-                    if len(src_doc) == 0: st.warning(f"Skipping empty PDF: {filename}"); continue
-                    for i, page in enumerate(src_doc):
-                        page_rect = page.rect; pw, ph = page_rect.width, page_rect.height
-                        if pw <= 0 or ph <= 0: continue
-                        c.setPageSize((pw, ph))
-                        pix = page.get_pixmap(dpi=150) # Render as image
-                        if pix.width > 0 and pix.height > 0:
-                             img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples); img_reader = ImageReader(img)
-                             c.drawImage(img_reader, 0, 0, width=pw, height=ph)
-                        else: c.setFont('Helvetica', 10); c.setFillColorRGB(1,0,0); c.drawCentredString(pw/2, ph/2, f"Failed to render page {i+1} preview")
-                        overlay_text = f"{item_caption} (p{i+1})"; c.setFont('Helvetica', 8); c.setFillColorRGB(0, 0, 0, alpha=0.6); c.drawString(10, 10, overlay_text)
-                        total_pages_generated += 1; draw_page_number(c, total_pages_generated, pw, ph)
-                        c.showPage()
-                finally:
-                     if src_doc: src_doc.close()
-                     if is_file_object: filepath.seek(0)
-
-            # --- TEXT/MARKDOWN Processing ---
-            elif file_type == 'Text':
-                if is_file_object:
-                    filepath.seek(0)
-                    try: text_content = filepath.read().decode('utf-8')
-                    except: text_content = filepath.read().decode('latin-1', errors='replace')
-                else:
-                    with open(filepath, 'r', encoding='utf-8', errors='ignore') as f: text_content = f.read()
-
-                temp_buf = io.BytesIO()
-                temp_doc = SimpleDocTemplate(temp_buf, pagesize=letter, leftMargin=inch, rightMargin=inch, topMargin=inch, bottomMargin=inch)
-                story = [Paragraph(f"Content from: {item_caption}", styles['h2']), Spacer(1, 0.2*inch)]
-                # Use Preformatted for simple text dump
-                story.append(Preformatted(text_content, styles['Code']))
-                temp_doc.build(story)
-                temp_buf.seek(0)
-
-                text_pdf = fitz.open("pdf", temp_buf.read())
-                for i, page in enumerate(text_pdf):
-                     page_rect = page.rect; pw, ph = page_rect.width, page_rect.height
-                     c.setPageSize((pw, ph)); pix = page.get_pixmap(dpi=150)
-                     if pix.width > 0 and pix.height > 0:
-                          img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples); img_reader = ImageReader(img)
-                          c.drawImage(img_reader, 0, 0, width=pw, height=ph)
-                     else: c.setFont('Helvetica', 10); c.setFillColorRGB(1,0,0); c.drawCentredString(pw/2, ph/2, f"Failed to render text page {i+1}")
-                     total_pages_generated += 1; draw_page_number(c, total_pages_generated, pw, ph)
-                     c.showPage()
-                text_pdf.close()
-
-            else: # Unknown type
-                logger.warning(f"Unsupported file type for PDF combination: {filename} ({file_type})")
-                c.setPageSize(letter); c.setFont('Helvetica-Bold', 14); c.setFillColorRGB(0.7, 0.7, 0); c.drawCentredString(letter[0] / 2, letter[1] / 2 + 20, f"Unsupported File: {filename}")
-                c.setFont('Helvetica', 10); c.drawCentredString(letter[0] / 2, letter[1] / 2 - 20, f"Type: {file_type}. Cannot include.")
-                total_pages_generated += 1; draw_page_number(c, total_pages_generated, letter[0], letter[1])
-                c.showPage()
-
-        except Exception as item_err:
-            logger.error(f"Error processing item {filename} for PDF: {item_err}", exc_info=True)
-            try: # Add error page
-                 c.setPageSize(letter); c.setFont('Helvetica-Bold', 14); c.setFillColorRGB(1, 0, 0); c.drawCentredString(letter[0] / 2, letter[1] / 2 + 20, f"Error processing: {filename}")
-                 c.setFont('Helvetica', 10); c.drawCentredString(letter[0] / 2, letter[1] / 2 - 20, f"{str(item_err)[:100]}"); total_pages_generated += 1; draw_page_number(c, total_pages_generated, letter[0], letter[1]); c.showPage()
-            except: logger.error(f"Failed to add error page for {filename}")
-        finally:
-             status_placeholder.empty()
-
-    if total_pages_generated == 0: st.error("No pages were successfully added."); return None
-    try:
-         c.save(); buf.seek(0)
-         if buf.getbuffer().nbytes < 100: st.error("Combined PDF generation resulted empty."); return None
-         return buf.getvalue()
-    except Exception as e: logger.error(f"Fatal error during final PDF save: {e}"); st.error(f"PDF Save Failed: {e}"); return None
-
-
-# --- Sidebar Gallery Update Function (MODIFIED for Sort, PDF Preview Fix, Delete Fix) ---
-def get_sort_key(filename):
-    ext = os.path.splitext(filename)[1].lower()
-    if ext in ['.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff']: priority = 1
-    elif ext in ['.md', '.txt']: priority = 2
-    elif ext == '.pdf': priority = 3
-    else: priority = 4
-    return (priority, filename.lower())
-
-def update_gallery():
-    st.sidebar.markdown("### Asset Gallery 📸📖")
-    all_files_unsorted = get_gallery_files()
-    all_files = sorted(all_files_unsorted, key=get_sort_key) # Apply sorting
-
-    if not all_files: st.sidebar.info("No assets found."); return
-    st.sidebar.caption(f"Found {len(all_files)} assets:")
-
-    for idx, file in enumerate(all_files):
-        st.session_state['unique_counter'] += 1
-        unique_id = st.session_state['unique_counter']
-        item_key_base = f"gallery_item_{os.path.basename(file)}_{unique_id}"
-        basename = os.path.basename(file)
-        st.sidebar.markdown(f"**{basename}**")
-
-        try:
-            file_ext = os.path.splitext(file)[1].lower()
-            preview_failed = False
-            # Previews with better error handling
-            if file_ext in ['.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff']:
-                 try:
-                     with st.sidebar.expander("Preview", expanded=False): st.image(Image.open(file), use_container_width=True)
-                 except Exception as img_err: st.sidebar.warning(f"Img preview failed: {img_err}"); preview_failed = True
-            elif file_ext == '.pdf':
-                 try:
-                     with st.sidebar.expander("Preview (Page 1)", expanded=False):
-                          doc = fitz.open(file)
-                          if len(doc) > 0:
-                              pix = doc[0].get_pixmap(matrix=fitz.Matrix(0.5, 0.5))
-                              if pix.width > 0 and pix.height > 0: img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples); st.image(img, use_container_width=True)
-                              else: st.warning("Failed to render PDF page."); preview_failed = True
-                          else: st.warning("Empty PDF")
-                          doc.close()
-                 except Exception as pdf_err: st.sidebar.warning(f"PDF preview failed: {pdf_err}"); logger.warning(f"PDF preview error {file}: {pdf_err}"); preview_failed = True
-            elif file_ext in ['.md', '.txt']:
-                 try:
-                     with st.sidebar.expander("Preview (Start)", expanded=False):
-                          with open(file, 'r', encoding='utf-8', errors='ignore') as f: content_preview = f.read(200)
-                          st.code(content_preview + "...", language='markdown' if file_ext == '.md' else 'text')
-                 except Exception as txt_err: st.sidebar.warning(f"Text preview failed: {txt_err}"); preview_failed = True
-
-            # Actions
-            action_cols = st.sidebar.columns(3)
-            with action_cols[0]:
-                 checkbox_key = f"cb_{item_key_base}"
-                 st.session_state.setdefault('asset_checkboxes', {})
-                 st.session_state['asset_checkboxes'][file] = st.checkbox("Select", value=st.session_state['asset_checkboxes'].get(file, False), key=checkbox_key)
-            with action_cols[1]:
-                 mime_map = {'.png': 'image/png', '.jpg': 'image/jpeg', '.jpeg': 'image/jpeg', '.pdf': 'application/pdf', '.txt': 'text/plain', '.md': 'text/markdown'}
-                 mime_type = mime_map.get(file_ext, "application/octet-stream"); dl_key = f"dl_{item_key_base}"
-                 try:
-                     with open(file, "rb") as fp: st.download_button(label="📥", data=fp, file_name=basename, mime=mime_type, key=dl_key, help="Download")
-                 except Exception as dl_e: st.error(f"DL Err: {dl_e}")
-            with action_cols[2]:
-                delete_key = f"del_{item_key_base}"
-                if st.button("🗑️", key=delete_key, help=f"Delete {basename}"):
-                    delete_success = False
-                    try:
-                        os.remove(file)
-                        st.session_state['asset_checkboxes'].pop(file, None)
-                        if file in st.session_state.get('layout_snapshots', []): st.session_state['layout_snapshots'].remove(file) # Remove if also in old list
-                        logger.info(f"Deleted asset: {file}")
-                        st.toast(f"Deleted {basename}!", icon="✅")
-                        delete_success = True
-                    except OSError as e: logger.error(f"Error deleting file {file}: {e}"); st.error(f"Could not delete {basename}: {e}")
-                    except Exception as e: logger.error(f"Unexpected error deleting file {file}: {e}"); st.error(f"Could not delete {basename}: {e}")
-                    # Rerun to refresh the gallery list after attempting delete
-                    st.rerun()
-
-        except FileNotFoundError: st.sidebar.error(f"File vanished: {basename}"); st.session_state['asset_checkboxes'].pop(file, None)
-        except Exception as e: st.sidebar.error(f"Display Error: {basename}"); logger.error(f"Error displaying asset {file}: {e}")
-        st.sidebar.markdown("---")
-
-# --- UI Elements -----------------------------------------
-# Sidebar Structure
-st.sidebar.subheader("🤖 Hugging Face Settings")
-# ... (HF API, Local Model, Params Expanders - code unchanged) ...
-with st.sidebar.expander("API Inference Settings", expanded=False):
-    st.session_state.hf_custom_key = st.text_input("Custom HF Token (BYOK)", value=st.session_state.get('hf_custom_key', ""), type="password", key="hf_custom_key_input", help="Enter your Hugging Face API token. Overrides HF_TOKEN env var.")
-    token_status = "Custom Key Set" if st.session_state.hf_custom_key else ("Default HF_TOKEN Set" if HF_TOKEN else "No Token Set"); st.caption(f"Token Status: {token_status}")
-    providers_list = ["hf-inference", "cerebras", "together", "sambanova", "novita", "cohere", "fireworks-ai", "hyperbolic", "nebius"]
-    st.session_state.hf_provider = st.selectbox("Inference Provider", options=providers_list, index=providers_list.index(st.session_state.get('hf_provider', DEFAULT_PROVIDER)), key="hf_provider_select", help="Select the backend provider. Some require specific API keys.")
-    if not st.session_state.hf_custom_key and not HF_TOKEN and st.session_state.hf_provider != "hf-inference": st.warning(f"Provider '{st.session_state.hf_provider}' may require a token.")
-    st.session_state.hf_custom_api_model = st.text_input("Custom API Model ID", value=st.session_state.get('hf_custom_api_model', ""), key="hf_custom_model_input", placeholder="e.g., google/gemma-2-9b-it", help="Overrides the featured model selection below if provided.")
-    effective_api_model = st.session_state.hf_custom_api_model.strip() or st.session_state.hf_selected_api_model
-    st.session_state.hf_selected_api_model = st.selectbox("Featured API Model", options=FEATURED_MODELS_LIST, index=FEATURED_MODELS_LIST.index(st.session_state.get('hf_selected_api_model', FEATURED_MODELS_LIST[0])), key="hf_featured_model_select", help="Select a common model. Ignored if Custom API Model ID is set.")
-    st.caption(f"Effective API Model: {effective_api_model}")
-with st.sidebar.expander("Local Model Selection", expanded=True):
-    if not _transformers_available: st.warning("Transformers library not found.")
-    else:
-        local_model_options = ["None"] + list(st.session_state.get('local_models', {}).keys())
-        current_selection = st.session_state.get('selected_local_model_path'); current_selection = current_selection if current_selection in local_model_options else "None"
-        selected_path = st.selectbox("Active Local Model", options=local_model_options, index=local_model_options.index(current_selection), format_func=lambda x: os.path.basename(x) if x != "None" else "None", key="local_model_selector", help="Select a loaded local model.")
-        st.session_state.selected_local_model_path = selected_path if selected_path != "None" else None
-        if st.session_state.selected_local_model_path:
-             model_info = st.session_state.local_models[st.session_state.selected_local_model_path]
-             st.caption(f"Type: {model_info.get('type', '?')} | Device: {model_info.get('model').device if model_info.get('model') else 'N/A'}")
-        else: st.caption("No local model selected.")
-with st.sidebar.expander("Generation Parameters", expanded=False):
-    st.session_state.gen_max_tokens = st.slider("Max New Tokens", 1, 4096, st.session_state.get('gen_max_tokens', 512), step=1, key="param_max_tokens")
-    st.session_state.gen_temperature = st.slider("Temperature", 0.01, 2.0, st.session_state.get('gen_temperature', 0.7), step=0.01, key="param_temp")
-    st.session_state.gen_top_p = st.slider("Top-P", 0.01, 1.0, st.session_state.get('gen_top_p', 0.95), step=0.01, key="param_top_p")
-    st.session_state.gen_frequency_penalty = st.slider("Repetition Penalty", 1.0, 2.0, st.session_state.get('gen_frequency_penalty', 0.0)+1.0, step=0.05, key="param_repetition", help="1.0 means no penalty.")
-    st.session_state.gen_seed = st.slider("Seed", -1, 65535, st.session_state.get('gen_seed', -1), step=1, key="param_seed", help="-1 for random.")
-
-st.sidebar.markdown("---")
-# Gallery is rendered later by calling update_gallery()
-
-# --- App Title & Main Area ---
-st.title("Vision & Layout Titans (HF) 🚀🖼️📄")
-st.markdown("Combined App: PDF Layout Generator + Hugging Face Powered AI Tools")
-
-# Warning for missing libraries in main area if sidebar not ready
-if not _transformers_available:
-     st.warning("AI/ML libraries (torch, transformers) not found. Local model features disabled.")
-elif not _diffusers_available:
-     st.warning("Diffusers library not found. Diffusion model features disabled.")
-
-
-# --- Main Application Tabs ---
-tabs_to_create = [
-    "Combined PDF Generator 📄", # Renamed Tab 0
-    "Camera Snap 📷",
-    "Download PDFs 📥",
-    "Build Titan (Local Models) 🌱",
-    "PDF Page Process (HF) 📄", # Clarified name
-    "Image Process (HF) 🖼️",
-    "Text Process (HF) 📝",
-    "Test OCR (HF) 🔍",
-    "Test Image Gen (Diffusers) 🎨",
-    "Character Editor 🧑‍🎨",
-    "Character Gallery 🖼️",
-]
-tabs = st.tabs(tabs_to_create)
-
-# --- Tab Implementations ---
-
-# --- Tab 1: Combined PDF Generator (OVERHAULED) ---
-with tabs[0]:
-    st.header("Combined PDF Generator 📄➕🖼️➕...")
-    st.markdown("Select assets (Images, PDFs, Text/MD) from the sidebar gallery, reorder them, and generate a combined PDF.")
-
-    # --- Get Selected Files ---
-    selected_files_paths = [
-        f for f, selected in st.session_state.get('asset_checkboxes', {}).items()
-        if selected and os.path.exists(f) # Ensure file still exists
-    ]
-
-    if not selected_files_paths:
-        st.info("👈 Select one or more assets from the sidebar gallery using the checkboxes.")
-    else:
-        st.info(f"{len(selected_files_paths)} assets selected from gallery.")
-
-        # --- Populate DataFrame for Reordering ---
-        combined_records = []
-        for idx, filepath in enumerate(selected_files_paths):
-            filename = os.path.basename(filepath)
-            ext = os.path.splitext(filename)[1].lower()
-            file_type = "Unknown"
-            if ext in ['.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff']: file_type = "Image"
-            elif ext == '.pdf': file_type = "PDF"
-            elif ext in ['.md', '.txt']: file_type = "Text"
-
-            combined_records.append({
-                "filename": filename,
-                "filepath": filepath, # Keep the path
-                "type": file_type,
-                "order": idx, # Initial order based on selection
-            })
-
-        combined_df_initial = pd.DataFrame(combined_records)
-
-        st.markdown("#### Reorder Selected Assets for PDF")
-        st.caption("Edit the 'Order' column or drag rows to set the sequence for the combined PDF.")
-
-        edited_combined_df = st.data_editor(
-             combined_df_initial,
-             column_config={
-                  "filename": st.column_config.TextColumn("Filename", disabled=True),
-                  "filepath": None, # Hide filepath column
-                  "type": st.column_config.TextColumn("Type", disabled=True),
-                  "order": st.column_config.NumberColumn(
-                       "Order",
-                       min_value=0,
-                       # max_value=len(combined_df_initial)-1, # Max can cause issues if rows added/removed by user selection change
-                       step=1,
-                       required=True,
-                  ),
-             },
-             hide_index=True,
-             use_container_width=True,
-             num_rows="dynamic", # Allow drag-and-drop reordering
-             key="combined_pdf_editor"
-        )
-
-        # Sort by the edited 'order' column
-        ordered_combined_df = edited_combined_df.sort_values('order').reset_index(drop=True)
-
-        # Prepare list of dicts for the PDF generation function
-        ordered_sources_info_for_pdf = ordered_combined_df[['filepath', 'type', 'filename']].to_dict('records')
-
-        # --- Generate & Download ---
-        st.subheader("Generate Combined PDF")
-        if st.button("🖋️ Generate Combined PDF", key="generate_combined_pdf_btn"):
-            if not ordered_sources_info_for_pdf:
-                st.warning("No items available after reordering.")
-            else:
-                with st.spinner("Generating combined PDF... This might take a while."):
-                    combined_pdf_bytes = make_combined_pdf(ordered_sources_info_for_pdf)
-
-                if combined_pdf_bytes:
-                    # Create filename
-                    now = datetime.now(pytz.timezone("US/Central"))
-                    prefix = now.strftime("%Y%m%d-%H%M%p")
-                    first_item_name = clean_stem(ordered_sources_info_for_pdf[0].get('filename','combined'))
-                    combined_pdf_fname = f"{prefix}_Combined_{first_item_name}.pdf"
-                    combined_pdf_fname = re.sub(r'[^\w\-\.\_]', '_', combined_pdf_fname) # Sanitize
-
-                    st.success(f"✅ Combined PDF ready: **{combined_pdf_fname}**")
-                    st.download_button(
-                        "⬇️ Download Combined PDF",
-                        data=combined_pdf_bytes,
-                        file_name=combined_pdf_fname,
-                        mime="application/pdf",
-                        key="download_combined_pdf_btn"
-                    )
-                    # Add preview (optional, might be slow for large combined PDFs)
-                    # ... (preview logic similar to other tabs if desired) ...
-                else:
-                    st.error("Combined PDF generation failed. Check logs or input files.")
-
-
-# --- Tab 2: Camera Snap ---
-with tabs[1]:
-    st.header("Camera Snap 📷")
-    st.subheader("Single Capture (Adds to General Gallery)")
-    cols = st.columns(2)
-    with cols[0]:
-        cam0_img = st.camera_input("Take a picture - Cam 0", key="main_cam0")
-        if cam0_img:
-            filename = generate_filename("cam0_snap");
-            if st.session_state.get('cam0_file') and os.path.exists(st.session_state['cam0_file']): 
-                try: 
-                    os.remove(st.session_state['cam0_file']) 
-                except OSError: 
-                    pass
-            try:
-                with open(filename, "wb") as f: f.write(cam0_img.getvalue())
-                st.session_state['cam0_file'] = filename; st.session_state['history'].append(f"Snapshot from Cam 0: {filename}"); st.image(Image.open(filename), caption="Camera 0 Snap", use_container_width=True); logger.info(f"Saved snapshot from Camera 0: {filename}"); st.success(f"Saved {filename}")
-                update_gallery(); # Refresh sidebar without rerun
-            except Exception as e: st.error(f"Failed to save Cam 0 snap: {e}"); logger.error(f"Failed to save Cam 0 snap {filename}: {e}")
-    with cols[1]:
-        cam1_img = st.camera_input("Take a picture - Cam 1", key="main_cam1")
-        if cam1_img:
-            filename = generate_filename("cam1_snap")
-            if st.session_state.get('cam1_file') and os.path.exists(st.session_state['cam1_file']): 
-                try: 
-                    os.remove(st.session_state['cam1_file']) 
-                except OSError: 
-                    pass
-            try:
-                with open(filename, "wb") as f: f.write(cam1_img.getvalue())
-                st.session_state['cam1_file'] = filename; st.session_state['history'].append(f"Snapshot from Cam 1: {filename}"); st.image(Image.open(filename), caption="Camera 1 Snap", use_container_width=True); logger.info(f"Saved snapshot from Camera 1: {filename}"); st.success(f"Saved {filename}")
-                update_gallery(); # Refresh sidebar without rerun
-            except Exception as e: st.error(f"Failed to save Cam 1 snap: {e}"); logger.error(f"Failed to save Cam 1 snap {filename}: {e}")
-
-
-# --- Tab 3: Download PDFs ---
-with tabs[2]:
-    st.header("Download PDFs 📥")
-    st.markdown("Download PDFs from URLs and optionally create image snapshots.")
-    if st.button("Load Example arXiv URLs 📚", key="load_examples"):
-        example_urls = ["https://arxiv.org/pdf/2308.03892", "https://arxiv.org/pdf/1706.03762", "https://arxiv.org/pdf/2402.17764", "https://www.clickdimensions.com/links/ACCERL/"]
-        st.session_state['pdf_urls_input'] = "\n".join(example_urls)
-    url_input = st.text_area("Enter PDF URLs (one per line)", value=st.session_state.get('pdf_urls_input', ""), height=150, key="pdf_urls_textarea")
-    if st.button("Robo-Download PDFs 🤖", key="download_pdfs_button"):
-        urls = [url.strip() for url in url_input.strip().split("\n") if url.strip()]
-        if not urls: st.warning("Please enter at least one URL.")
-        else:
-            progress_bar = st.progress(0); status_text = st.empty(); total_urls = len(urls); download_count = 0; existing_pdfs = get_pdf_files()
-            for idx, url in enumerate(urls):
-                output_path = pdf_url_to_filename(url); status_text.text(f"Processing {idx + 1}/{total_urls}: {os.path.basename(output_path)}..."); progress_bar.progress((idx + 1) / total_urls)
-                if os.path.exists(output_path): # Check existence properly
-                    st.info(f"Already exists: {os.path.basename(output_path)}")
-                    st.session_state['downloaded_pdfs'][url] = output_path
-                    # Ensure checkbox state is preserved or reset if needed
-                    st.session_state['asset_checkboxes'][output_path] = st.session_state['asset_checkboxes'].get(output_path, False)
-                else:
-                    if download_pdf(url, output_path):
-                         st.session_state['downloaded_pdfs'][url] = output_path; logger.info(f"Downloaded PDF from {url} to {output_path}"); st.session_state['history'].append(f"Downloaded PDF: {output_path}"); st.session_state['asset_checkboxes'][output_path] = False; download_count += 1; existing_pdfs.append(output_path)
-                    else: st.error(f"Failed to download: {url}")
-            status_text.success(f"Download process complete! Successfully downloaded {download_count} new PDFs.")
-            if download_count > 0: update_gallery(); # Refresh sidebar without rerun
-
-    st.subheader("Create Snapshots from Gallery PDFs")
-    snapshot_mode = st.selectbox("Snapshot Mode", ["First Page (High-Res)", "First Two Pages (High-Res)", "All Pages (High-Res)", "First Page (Low-Res Preview)"], key="pdf_snapshot_mode")
-    resolution_map = {"First Page (High-Res)": 2.0, "First Two Pages (High-Res)": 2.0, "All Pages (High-Res)": 2.0, "First Page (Low-Res Preview)": 1.0}
-    mode_key_map = {"First Page (High-Res)": "single", "First Two Pages (High-Res)": "twopage", "All Pages (High-Res)": "allpages", "First Page (Low-Res Preview)": "single"}
-    resolution = resolution_map[snapshot_mode]; mode_key = mode_key_map[snapshot_mode]
-    if st.button("Snapshot Selected PDFs 📸", key="snapshot_selected_pdfs"):
-        selected_pdfs = [path for path in get_gallery_files(['pdf']) if st.session_state['asset_checkboxes'].get(path, False)]
-        if not selected_pdfs: st.warning("No PDFs selected in the sidebar gallery!")
-        else:
-            st.info(f"Starting snapshot process for {len(selected_pdfs)} selected PDF(s)..."); snapshot_count = 0; total_snapshots_generated = 0
-            for pdf_path in selected_pdfs:
-                if not os.path.exists(pdf_path): st.warning(f"File not found: {pdf_path}. Skipping."); continue
-                new_snapshots = asyncio.run(process_pdf_snapshot(pdf_path, mode_key, resolution))
-                if new_snapshots:
-                    snapshot_count += 1; total_snapshots_generated += len(new_snapshots)
-                    st.write(f"Snapshots for {os.path.basename(pdf_path)}:"); cols = st.columns(3)
-                    for i, snap_path in enumerate(new_snapshots):
-                         with cols[i % 3]:
-                              try: st.image(Image.open(snap_path), caption=os.path.basename(snap_path), use_container_width=True)
-                              except Exception as snap_img_err: st.warning(f"Cannot display snap {os.path.basename(snap_path)}: {snap_img_err}")
-                         st.session_state['asset_checkboxes'][snap_path] = False # Add to gallery
-            if total_snapshots_generated > 0: st.success(f"Generated {total_snapshots_generated} snapshots from {snapshot_count} PDFs."); update_gallery(); # Refresh sidebar without rerun
-            else: st.warning("No snapshots were generated. Check logs or PDF files.")
-
-
-# --- Tab 4: Build Titan (Local Models) ---
-with tabs[3]:
-    st.header("Build Titan (Local Models) 🌱")
-    st.markdown("Download and save models from Hugging Face Hub for local use.")
-    if not _transformers_available:
-        st.error("Transformers library not available. Cannot download or load local models.")
-    else:
-        build_model_type = st.selectbox("Select Model Type", ["Causal LM", "Vision/Multimodal", "OCR", "Diffusion"], key="build_type_local")
-        st.subheader(f"Download {build_model_type} Model")
-        hf_model_id = st.text_input("Hugging Face Model ID", placeholder=f"e.g., {'google/gemma-2-9b-it' if build_model_type == 'Causal LM' else 'llava-hf/llava-1.5-7b-hf' if build_model_type == 'Vision/Multimodal' else 'microsoft/trocr-base-handwritten' if build_model_type == 'OCR' else 'stabilityai/stable-diffusion-xl-base-1.0'}", key="build_hf_model_id")
-        local_model_name = st.text_input("Local Name for this Model", value=f"{build_model_type.split('/')[0].lower()}_{os.path.basename(hf_model_id).replace('.','') if hf_model_id else 'model'}", key="build_local_name", help="A unique name to identify this model locally.")
-        st.info("Private or gated models require a valid Hugging Face token (set via HF_TOKEN env var or the Custom Key in sidebar API settings).")
-
-        if st.button(f"Download & Save '{hf_model_id}' Locally", key="build_download_button", disabled=not hf_model_id or not local_model_name):
-            local_name_check = re.sub(r'[^\w\-]+', '_', local_model_name) # Sanitize proposed name for path check
-            potential_path_base = os.path.join(f"{build_model_type.split('/')[0].lower()}_models", local_name_check)
-
-            if any(os.path.basename(p) == local_name_check for p in get_local_model_paths(build_model_type.split('/')[0].lower())):
-                 st.error(f"A local model folder named '{local_name_check}' already exists. Choose a different local name.")
-            else:
-                model_type_map = {"Causal LM": "causal", "Vision/Multimodal": "vision", "OCR": "ocr", "Diffusion": "diffusion"}
-                model_type_short = model_type_map.get(build_model_type, "unknown")
-                config = LocalModelConfig(name=local_model_name, hf_id=hf_model_id, model_type=model_type_short)
-                save_path = config.get_full_path()
-                os.makedirs(os.path.dirname(save_path), exist_ok=True)
-                st.info(f"Attempting to download '{hf_model_id}' to '{save_path}'..."); progress_bar_build = st.progress(0); status_text_build = st.empty()
-                token_build = st.session_state.hf_custom_key or HF_TOKEN or None
-                try:
-                    if build_model_type == "Diffusion":
-                         if not _diffusers_available: raise ImportError("Diffusers library required.")
-                         status_text_build.text("Downloading diffusion pipeline..."); pipeline_obj = StableDiffusionPipeline.from_pretrained(hf_model_id, token=token_build); status_text_build.text("Saving diffusion model pipeline..."); pipeline_obj.save_pretrained(save_path)
-                         st.session_state.local_models[save_path] = {'type': 'diffusion', 'hf_id': hf_model_id, 'model':None, 'processor':None} # Mark as downloaded
-                         st.success(f"Diffusion model '{hf_model_id}' downloaded and saved to {save_path}")
-                         del pipeline_obj # Free memory
-                    else:
-                         status_text_build.text("Downloading model components...")
-                         if model_type_short == 'causal': model_class, proc_tok_class = AutoModelForCausalLM, AutoTokenizer; proc_name="tokenizer"
-                         elif model_type_short == 'vision': model_class, proc_tok_class = AutoModelForVision2Seq, AutoProcessor; proc_name="processor"
-                         elif model_type_short == 'ocr': model_class, proc_tok_class = AutoModelForVision2Seq, AutoProcessor; proc_name="processor"
-                         else: raise ValueError(f"Unknown model type: {model_type_short}")
-
-                         model_obj = model_class.from_pretrained(hf_model_id, token=token_build); model_obj.save_pretrained(save_path)
-                         status_text_build.text(f"Model saved. Downloading {proc_name}..."); proc_tok_obj = proc_tok_class.from_pretrained(hf_model_id, token=token_build); proc_tok_obj.save_pretrained(save_path)
-                         status_text_build.text(f"Components saved. Loading '{local_model_name}' into memory...")
-                         device = "cuda" if torch.cuda.is_available() else "cpu"
-                         # Use trust_remote_code cautiously if needed for specific models
-                         reloaded_model = model_class.from_pretrained(save_path).to(device)
-                         reloaded_proc_tok = proc_tok_class.from_pretrained(save_path)
-                         st.session_state.local_models[save_path] = {'type': model_type_short, 'hf_id': hf_model_id, 'model': reloaded_model, proc_name: reloaded_proc_tok}
-                         # Add tokenizer specifically if it's nested in processor
-                         if proc_name == "processor" and hasattr(reloaded_proc_tok, 'tokenizer'):
-                             st.session_state.local_models[save_path]['tokenizer'] = reloaded_proc_tok.tokenizer
-                         st.success(f"{build_model_type} model '{hf_model_id}' downloaded to {save_path} and loaded ({device})."); st.session_state.selected_local_model_path = save_path
-                         del model_obj, proc_tok_obj # Free memory from download cache if possible
-                except (RepositoryNotFoundError, GatedRepoError) as e: st.error(f"Download failed: Repo not found or requires access/token. Error: {e}"); logger.error(f"Download failed for {hf_model_id}: {e}"); #if os.path.exists(save_path): shutil.rmtree(save_path)
-                except ImportError as e: st.error(f"Download failed: Library missing. {e}"); logger.error(f"ImportError for {hf_model_id}: {e}")
-                except Exception as e: st.error(f"Download error: {e}"); logger.error(f"Download failed for {hf_model_id}: {e}", exc_info=True); #if os.path.exists(save_path): shutil.rmtree(save_path)
-                finally: progress_bar_build.progress(1.0); status_text_build.empty(); #st.rerun() # Rerun removed
-
-        st.subheader("Manage Local Models")
-        # Refresh list for display
-        loaded_model_paths = list(st.session_state.get('local_models', {}).keys())
-        if not loaded_model_paths: st.info("No models downloaded yet.")
-        else:
-            models_df_data = []
-            for path in loaded_model_paths:
-                 data = st.session_state.local_models.get(path, {}) # Safely get data
-                 models_df_data.append({
-                      "Local Name": os.path.basename(path), "Type": data.get('type', '?'),
-                      "HF ID": data.get('hf_id', '?'), "Loaded": "Yes" if data.get('model') else "No", "Path": path })
-            models_df = pd.DataFrame(models_df_data); st.dataframe(models_df, use_container_width=True, hide_index=True, column_order=["Local Name", "Type", "HF ID", "Loaded"])
-            model_to_delete = st.selectbox("Select model to delete", [""] + [os.path.basename(p) for p in loaded_model_paths], key="delete_model_select")
-            if model_to_delete and st.button(f"Delete Local Model '{model_to_delete}'", type="primary"):
-                path_to_delete = next((p for p in loaded_model_paths if os.path.basename(p) == model_to_delete), None)
-                if path_to_delete:
-                    try:
-                        # Explicitly delete model objects from memory first if they exist
-                        if path_to_delete in st.session_state.local_models:
-                             model_data_to_del = st.session_state.local_models[path_to_delete]
-                             if model_data_to_del.get('model'): del model_data_to_del['model']
-                             if model_data_to_del.get('tokenizer'): del model_data_to_del['tokenizer']
-                             if model_data_to_del.get('processor'): del model_data_to_del['processor']
-                             if _transformers_available and torch.cuda.is_available(): torch.cuda.empty_cache() # Try to clear VRAM
-
-                        # Remove from session state
-                        st.session_state.local_models.pop(path_to_delete, None)
-                        if st.session_state.selected_local_model_path == path_to_delete: st.session_state.selected_local_model_path = None
-                        # Delete from disk
-                        if os.path.exists(path_to_delete): shutil.rmtree(path_to_delete)
-                        st.success(f"Deleted model '{model_to_delete}'."); logger.info(f"Deleted local model: {path_to_delete}"); st.rerun()
-                    except Exception as e: st.error(f"Failed to delete model '{model_to_delete}': {e}"); logger.error(f"Failed to delete model {path_to_delete}: {e}")
-
-
-# --- Tab 5: PDF Process (HF) ---
-with tabs[4]:
-    st.header("PDF Page Process with HF Models 📄")
-    st.markdown("Upload PDFs, view pages, and extract text/info using selected HF models (API or Local Vision/OCR).")
-    pdf_use_api = st.radio("Choose Processing Method", ["Hugging Face API", "Loaded Local Model"], key="pdf_process_source", horizontal=True, help="API uses settings from sidebar. Local uses the selected local model (if suitable for vision/OCR).")
-    if pdf_use_api == "Hugging Face API": st.info(f"Using API Model: {st.session_state.hf_custom_api_model.strip() or st.session_state.hf_selected_api_model} (likely image-to-text)")
-    else:
-        if st.session_state.selected_local_model_path: st.info(f"Using Local Model: {os.path.basename(st.session_state.selected_local_model_path)}")
-        else: st.warning("No local model selected.")
-
-    uploaded_pdfs_process_hf = st.file_uploader("Upload PDF files to process", type=["pdf"], accept_multiple_files=True, key="pdf_process_uploader_hf")
-    if uploaded_pdfs_process_hf:
-        process_all_pages_pdf = st.checkbox("Process All Pages (can be slow/expensive)", value=False, key="pdf_process_all_hf")
-        pdf_prompt = st.text_area("Prompt for PDF Page Processing", "Extract the text content from this page.", key="pdf_process_prompt_hf")
-        if st.button("Process Uploaded PDFs with HF", key="process_uploaded_pdfs_hf"):
-            if pdf_use_api == "Loaded Local Model" and not st.session_state.selected_local_model_path: st.error("Cannot process locally: No local model selected.")
-            else:
-                combined_text_output_hf = f"# HF PDF Processing Results ({'API' if pdf_use_api else 'Local'})\n\n"; total_pages_processed_hf = 0; output_placeholder_hf = st.container()
-                for pdf_file in uploaded_pdfs_process_hf:
-                    output_placeholder_hf.markdown(f"--- \n### Processing: {pdf_file.name}")
-                    try:
-                        pdf_bytes = pdf_file.read(); doc = fitz.open("pdf", pdf_bytes); num_pages = len(doc)
-                        pages_to_process = range(num_pages) if process_all_pages_pdf else range(min(1, num_pages))
-                        output_placeholder_hf.info(f"Processing {len(pages_to_process)} of {num_pages} pages..."); doc_text = f"## File: {pdf_file.name}\n\n"
-                        for i in pages_to_process:
-                            page_placeholder = output_placeholder_hf.empty(); page_placeholder.info(f"Processing Page {i + 1}/{num_pages}...")
-                            page = doc.load_page(i); pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0)); img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
-                            cols_pdf = output_placeholder_hf.columns(2); cols_pdf[0].image(img, caption=f"Page {i+1}", use_container_width=True)
-                            with cols_pdf[1], st.spinner("Processing page with HF model..."): hf_text = process_image_hf(img, pdf_prompt, use_api=pdf_use_api)
-                            st.text_area(f"Result (Page {i+1})", hf_text, height=250, key=f"pdf_hf_out_{pdf_file.name}_{i}")
-                            doc_text += f"### Page {i + 1}\n\n{hf_text}\n\n---\n\n"; total_pages_processed_hf += 1; page_placeholder.empty()
-                        combined_text_output_hf += doc_text; doc.close()
-                    except Exception as e: output_placeholder_hf.error(f"Error processing {pdf_file.name}: {str(e)}")
-                if total_pages_processed_hf > 0:
-                    st.markdown("--- \n### Combined Processing Results"); st.text_area("Full Output", combined_text_output_hf, height=400, key="combined_pdf_hf_output")
-                    output_filename_pdf_hf = generate_filename("hf_processed_pdfs", "md")
-                    try:
-                        with open(output_filename_pdf_hf, "w", encoding="utf-8") as f: f.write(combined_text_output_hf)
-                        st.success(f"Combined output saved to {output_filename_pdf_hf}")
-                        st.markdown(get_download_link(output_filename_pdf_hf, "text/markdown", "Download Combined MD"), unsafe_allow_html=True)
-                        st.session_state['asset_checkboxes'][output_filename_pdf_hf] = False; update_gallery() # Refresh sidebar
-                    except IOError as e: st.error(f"Failed to save combined output file: {e}")
-
-# --- Tab 6: Image Process (HF) ---
-with tabs[5]:
-    st.header("Image Process with HF Models 🖼️")
-    st.markdown("Upload images and process them using selected HF models (API or Local).")
-    img_use_api = st.radio("Choose Processing Method", ["Hugging Face API", "Loaded Local Model"], key="img_process_source_hf", horizontal=True)
-    if img_use_api == "Hugging Face API": st.info(f"Using API Model: {st.session_state.hf_custom_api_model.strip() or st.session_state.hf_selected_api_model} (likely image-to-text)")
-    else:
-        if st.session_state.selected_local_model_path: st.info(f"Using Local Model: {os.path.basename(st.session_state.selected_local_model_path)}")
-        else: st.warning("No local model selected.")
-    img_prompt_hf = st.text_area("Prompt for Image Processing", "Describe this image in detail.", key="img_process_prompt_hf")
-    uploaded_images_process_hf = st.file_uploader("Upload image files", type=["png", "jpg", "jpeg"], accept_multiple_files=True, key="image_process_uploader_hf")
-    if uploaded_images_process_hf:
-        if st.button("Process Uploaded Images with HF", key="process_images_hf"):
-             if img_use_api == "Loaded Local Model" and not st.session_state.selected_local_model_path: st.error("Cannot process locally: No local model selected.")
-             else:
-                combined_img_text_hf = f"# HF Image Processing Results ({'API' if img_use_api else 'Local'})\n\n**Prompt:** {img_prompt_hf}\n\n---\n\n"; images_processed_hf = 0; output_img_placeholder_hf = st.container()
-                for img_file in uploaded_images_process_hf:
-                    output_img_placeholder_hf.markdown(f"### Processing: {img_file.name}")
-                    try:
-                        img = Image.open(img_file); cols_img_hf = output_img_placeholder_hf.columns(2); cols_img_hf[0].image(img, caption=f"Input: {img_file.name}", use_container_width=True)
-                        with cols_img_hf[1], st.spinner("Processing image with HF model..."): hf_img_text = process_image_hf(img, img_prompt_hf, use_api=img_use_api)
-                        st.text_area(f"Result", hf_img_text, height=300, key=f"img_hf_out_{img_file.name}")
-                        combined_img_text_hf += f"## Image: {img_file.name}\n\n{hf_img_text}\n\n---\n\n"; images_processed_hf += 1
-                    except UnidentifiedImageError: output_img_placeholder_hf.error(f"Invalid Image: {img_file.name}. Skipping.")
-                    except Exception as e: output_img_placeholder_hf.error(f"Error processing {img_file.name}: {str(e)}")
-                if images_processed_hf > 0:
-                    st.markdown("--- \n### Combined Processing Results"); st.text_area("Full Output", combined_img_text_hf, height=400, key="combined_img_hf_output")
-                    output_filename_img_hf = generate_filename("hf_processed_images", "md")
-                    try:
-                        with open(output_filename_img_hf, "w", encoding="utf-8") as f: f.write(combined_img_text_hf)
-                        st.success(f"Combined output saved to {output_filename_img_hf}"); st.markdown(get_download_link(output_filename_img_hf, "text/markdown", "Download Combined MD"), unsafe_allow_html=True)
-                        st.session_state['asset_checkboxes'][output_filename_img_hf] = False; update_gallery() # Refresh sidebar
-                    except IOError as e: st.error(f"Failed to save combined output file: {e}")
-
-# --- Tab 7: Text Process (HF) ---
-with tabs[6]:
-    st.header("Text Process with HF Models 📝")
-    st.markdown("Process Markdown (.md) or Text (.txt) files using selected HF models (API or Local).")
-    text_use_api = st.radio("Choose Processing Method", ["Hugging Face API", "Loaded Local Model"], key="text_process_source_hf", horizontal=True)
-    if text_use_api == "Hugging Face API": st.info(f"Using API Model: {st.session_state.hf_custom_api_model.strip() or st.session_state.hf_selected_api_model}")
-    else:
-        if st.session_state.selected_local_model_path: st.info(f"Using Local Model: {os.path.basename(st.session_state.selected_local_model_path)}")
-        else: st.warning("No local model selected.")
-    text_files_hf = get_gallery_files(['md', 'txt'])
-    if not text_files_hf: st.warning("No .md or .txt files in gallery to process.")
-    else:
-        selected_text_file_hf = st.selectbox("Select Text/MD File to Process", options=[""] + text_files_hf, format_func=lambda x: os.path.basename(x) if x else "Select a file...", key="text_process_select_hf")
-        if selected_text_file_hf:
-             st.write(f"Selected: {os.path.basename(selected_text_file_hf)}")
-             try:
-                 with open(selected_text_file_hf, "r", encoding="utf-8", errors='ignore') as f: content_text_hf = f.read()
-                 st.text_area("File Content Preview", content_text_hf[:1000] + ("..." if len(content_text_hf) > 1000 else ""), height=200, key="text_content_preview_hf")
-                 prompt_text_hf = st.text_area("Enter Prompt for this File", "Summarize the key points of this text.", key="text_individual_prompt_hf")
-                 if st.button(f"Process '{os.path.basename(selected_text_file_hf)}' with HF", key=f"process_text_hf_btn"):
-                     if text_use_api == "Loaded Local Model" and not st.session_state.selected_local_model_path: st.error("Cannot process locally: No local model selected.")
-                     else:
-                        with st.spinner("Processing text with HF model..."): result_text_processed = process_text_hf(content_text_hf, prompt_text_hf, use_api=text_use_api)
-                        st.markdown("### Processing Result"); st.markdown(result_text_processed)
-                        output_filename_text_hf = generate_filename(f"hf_processed_{os.path.splitext(os.path.basename(selected_text_file_hf))[0]}", "md")
-                        try:
-                            with open(output_filename_text_hf, "w", encoding="utf-8") as f: f.write(result_text_processed)
-                            st.success(f"Result saved to {output_filename_text_hf}"); st.markdown(get_download_link(output_filename_text_hf, "text/markdown", "Download Result MD"), unsafe_allow_html=True)
-                            st.session_state['asset_checkboxes'][output_filename_text_hf] = False; update_gallery() # Refresh sidebar
-                        except IOError as e: st.error(f"Failed to save result file: {e}")
-             except FileNotFoundError: st.error("Selected file not found.")
-             except Exception as e: st.error(f"Error reading file: {e}")
-
-# --- Tab 8: Test OCR (HF) ---
-with tabs[7]:
-    st.header("Test OCR with HF Models 🔍")
-    st.markdown("Select an image/PDF and run OCR using HF models (API or Local - requires suitable local model).")
-    ocr_use_api = st.radio("Choose OCR Method", ["Hugging Face API (Basic Captioning/OCR)", "Loaded Local OCR Model"], key="ocr_source_hf", horizontal=True, help="API uses basic image-to-text. Local requires a dedicated OCR model (e.g., TrOCR) to be loaded.")
-    if ocr_use_api == "Loaded Local OCR Model":
-         if st.session_state.selected_local_model_path:
-              model_info = st.session_state.local_models.get(st.session_state.selected_local_model_path,{})
-              model_type = model_info.get('type'); model_name = os.path.basename(st.session_state.selected_local_model_path)
-              if model_type != 'ocr': st.warning(f"Selected model ({model_name}) is type '{model_type}', not 'ocr'. Results may be poor.")
-              else: st.info(f"Using Local OCR Model: {model_name}")
-         else: st.warning("No local model selected.")
-
-    gallery_files_ocr_hf = get_gallery_files(['png', 'jpg', 'jpeg', 'pdf'])
-    if not gallery_files_ocr_hf: st.warning("No images or PDFs in gallery.")
-    else:
-        selected_file_ocr_hf = st.selectbox("Select Image or PDF from Gallery for OCR", options=[""] + gallery_files_ocr_hf, format_func=lambda x: os.path.basename(x) if x else "Select a file...", key="ocr_select_file_hf")
-        if selected_file_ocr_hf:
-            st.write(f"Selected: {os.path.basename(selected_file_ocr_hf)}"); file_ext_ocr_hf = os.path.splitext(selected_file_ocr_hf)[1].lower(); image_to_ocr_hf = None; page_info_hf = ""
-            try:
-                if file_ext_ocr_hf in ['.png', '.jpg', '.jpeg']: image_to_ocr_hf = Image.open(selected_file_ocr_hf)
-                elif file_ext_ocr_hf == '.pdf':
-                    doc = fitz.open(selected_file_ocr_hf)
-                    if len(doc) > 0: pix = doc[0].get_pixmap(matrix=fitz.Matrix(2.0, 2.0)); image_to_ocr_hf = Image.frombytes("RGB", [pix.width, pix.height], pix.samples); page_info_hf = " (Page 1)"
-                    else: st.warning("Selected PDF is empty.")
-                    doc.close()
-                if image_to_ocr_hf:
-                    st.image(image_to_ocr_hf, caption=f"Image for OCR{page_info_hf}", use_container_width=True)
-                    if st.button("Run HF OCR on this Image 🚀", key="ocr_run_button_hf"):
-                        if ocr_use_api == "Loaded Local OCR Model" and not st.session_state.selected_local_model_path: st.error("Cannot run locally: No local model selected.")
-                        else:
-                            output_ocr_file_hf = generate_filename(f"hf_ocr_{os.path.splitext(os.path.basename(selected_file_ocr_hf))[0]}", "txt"); st.session_state['processing']['ocr'] = True
-                            with st.spinner("Performing OCR with HF model..."): ocr_result_hf = asyncio.run(process_hf_ocr(image_to_ocr_hf, output_ocr_file_hf, use_api=ocr_use_api))
-                            st.session_state['processing']['ocr'] = False; st.text_area("OCR Result", ocr_result_hf, height=300, key="ocr_result_display_hf")
-                            if ocr_result_hf and not ocr_result_hf.startswith("Error") and not ocr_result_hf.startswith("["):
-                                entry = f"HF OCR: {selected_file_ocr_hf}{page_info_hf} -> {output_ocr_file_hf}"
-                                st.session_state['history'].append(entry)
-                                if len(ocr_result_hf) > 5: st.success(f"OCR output saved to {output_ocr_file_hf}"); st.markdown(get_download_link(output_ocr_file_hf, "text/plain", "Download OCR Text"), unsafe_allow_html=True); st.session_state['asset_checkboxes'][output_ocr_file_hf] = False; update_gallery() # Refresh sidebar
-                                else: st.warning("OCR output seems short/empty.")
-                            else: st.error(f"OCR failed. {ocr_result_hf}")
-            except Exception as e: st.error(f"Error loading file for OCR: {e}")
-
-# --- Tab 9: Test Image Gen (Diffusers) ---
-with tabs[8]:
-    st.header("Test Image Generation (Diffusers) 🎨")
-    st.markdown("Generate images using Stable Diffusion models loaded locally via the Diffusers library.")
-    if not _diffusers_available: st.error("Diffusers library is required.")
-    else:
-        local_diffusion_paths = get_local_model_paths("diffusion") # Check diffusion_models folder
-        if not local_diffusion_paths: st.warning("No local diffusion models found. Download one using the 'Build Titan' tab."); selected_diffusion_model_path = None
-        else: selected_diffusion_model_path = st.selectbox("Select Local Diffusion Model", options=[""] + local_diffusion_paths, format_func=lambda x: os.path.basename(x) if x else "Select...", key="imggen_diffusion_model_select")
-        prompt_imggen_diff = st.text_area("Image Generation Prompt", "A photorealistic cat wearing sunglasses, studio lighting", key="imggen_prompt_diff")
-        neg_prompt_imggen_diff = st.text_area("Negative Prompt (Optional)", "ugly, deformed, blurry, low quality", key="imggen_neg_prompt_diff")
-        steps_imggen_diff = st.slider("Inference Steps", 10, 100, 25, key="imggen_steps"); guidance_imggen_diff = st.slider("Guidance Scale", 1.0, 20.0, 7.5, step=0.5, key="imggen_guidance")
-        if st.button("Generate Image 🚀", key="imggen_run_button_diff", disabled=not selected_diffusion_model_path):
-            if not prompt_imggen_diff: st.warning("Please enter a prompt.")
-            else:
-                 status_imggen = st.empty()
-                 try:
-                     status_imggen.info(f"Loading diffusion pipeline: {os.path.basename(selected_diffusion_model_path)}..."); device = "cuda" if _transformers_available and torch.cuda.is_available() else "cpu"; dtype = torch.float16 if device == "cuda" else torch.float32
-                     pipe = StableDiffusionPipeline.from_pretrained(selected_diffusion_model_path, torch_dtype=dtype).to(device); pipe.safety_checker = None # Optional
-                     status_imggen.info(f"Generating image on {device} ({dtype})..."); start_gen_time = time.time()
-                     gen_output = pipe(prompt=prompt_imggen_diff, negative_prompt=neg_prompt_imggen_diff or None, num_inference_steps=steps_imggen_diff, guidance_scale=guidance_imggen_diff)
-                     gen_image = gen_output.images[0]; elapsed_gen = int(time.time() - start_gen_time); status_imggen.success(f"Image generated in {elapsed_gen}s!")
-                     output_imggen_file_diff = generate_filename("diffusion_gen", "png"); gen_image.save(output_imggen_file_diff)
-                     st.image(gen_image, caption=f"Generated: {output_imggen_file_diff}", use_container_width=True)
-                     st.markdown(get_download_link(output_imggen_file_diff, "image/png", "Download Generated Image"), unsafe_allow_html=True)
-                     st.session_state['asset_checkboxes'][output_imggen_file_diff] = False; update_gallery() # Refresh sidebar
-                     st.session_state['history'].append(f"Diffusion Gen: '{prompt_imggen_diff[:30]}...' -> {output_imggen_file_diff}")
-                 except ImportError: st.error("Diffusers or Torch library not found.")
-                 except Exception as e: st.error(f"Image generation failed: {e}"); logger.error(f"Diffusion generation failed for {selected_diffusion_model_path}: {e}", exc_info=True)
-                 finally: 
-                     if 'pipe' in locals(): 
-                         del pipe; torch.cuda.empty_cache() if device == "cuda" else None # Clear VRAM
-
-# --- Tab 10: Character Editor ---
-with tabs[9]:
-    st.header("Character Editor 🧑‍🎨"); st.subheader("Create Your Character")
-    load_characters(); existing_char_names = [c['name'] for c in st.session_state.get('characters', [])]
-    form_key = f"character_form_{st.session_state.get('char_form_reset_key', 0)}"
-    with st.form(key=form_key):
-        st.markdown("**Create New Character**")
-        if st.form_submit_button("Randomize Content 🎲"): st.session_state['char_form_reset_key'] += 1; st.rerun()
-        rand_name, rand_gender, rand_intro, rand_greeting = randomize_character_content()
-        name_char = st.text_input("Name (3-25 chars...)", value=rand_name, max_chars=25, key="char_name_input")
-        gender_char = st.radio("Gender", ["Male", "Female"], index=["Male", "Female"].index(rand_gender), key="char_gender_radio")
-        intro_char = st.text_area("Intro (Public description)", value=rand_intro, max_chars=300, height=100, key="char_intro_area")
-        greeting_char = st.text_area("Greeting (First message)", value=rand_greeting, max_chars=300, height=100, key="char_greeting_area")
-        tags_char = st.text_input("Tags (comma-separated)", "OC, friendly", key="char_tags_input")
-        submitted = st.form_submit_button("Create Character ✨")
-        if submitted:
-            error = False; # Validation checks...
-            if not (3 <= len(name_char) <= 25): st.error("Name must be 3-25 characters."); error = True
-            if not re.match(r'^[a-zA-Z0-9 _-]+$', name_char): st.error("Name contains invalid characters."); error = True
-            if name_char in existing_char_names: st.error(f"Name '{name_char}' already exists!"); error = True
-            if not intro_char or not greeting_char: st.error("Intro/Greeting cannot be empty."); error = True
-            if not error:
-                tag_list = [tag.strip() for tag in tags_char.split(',') if tag.strip()]
-                character_data = {"name": name_char, "gender": gender_char, "intro": intro_char, "greeting": greeting_char, "created_at": datetime.now(pytz.timezone("US/Central")).strftime('%Y-%m-%d %H:%M:%S %Z'), "tags": tag_list}
-                if save_character(character_data): st.success(f"Character '{name_char}' created!"); st.session_state['char_form_reset_key'] += 1; st.rerun()
-
-# --- Tab 11: Character Gallery ---
-with tabs[10]:
-    st.header("Character Gallery 🖼️"); load_characters(); characters_list = st.session_state.get('characters', [])
-    if not characters_list: st.warning("No characters created yet.")
-    else:
-        st.subheader(f"Your Characters ({len(characters_list)})"); search_term = st.text_input("Search Characters by Name", key="char_gallery_search")
-        if search_term: characters_list = [c for c in characters_list if search_term.lower() in c['name'].lower()]
-        cols_char_gallery = st.columns(3); chars_to_delete = []
-        for idx, char in enumerate(characters_list):
-            with cols_char_gallery[idx % 3], st.container(border=True):
-                st.markdown(f"**{char['name']}**"); st.caption(f"Gender: {char.get('gender', 'N/A')}")
-                st.markdown("**Intro:**"); st.markdown(f"> {char.get('intro', '')}")
-                st.markdown("**Greeting:**"); st.markdown(f"> {char.get('greeting', '')}")
-                st.caption(f"Tags: {', '.join(char.get('tags', ['N/A']))}"); st.caption(f"Created: {char.get('created_at', 'N/A')}")
-                delete_key_char = f"delete_char_{char['name']}_{idx}";
-                if st.button(f"Delete", key=delete_key_char, type="primary", help=f"Delete {char['name']}"): chars_to_delete.append(char['name']) # Shorten button label
-        if chars_to_delete:
-             current_characters = st.session_state.get('characters', []); updated_characters = [c for c in current_characters if c['name'] not in chars_to_delete]
-             st.session_state['characters'] = updated_characters
-             try:
-                 with open("characters.json", "w", encoding='utf-8') as f: json.dump(updated_characters, f, indent=2)
-                 logger.info(f"Deleted characters: {', '.join(chars_to_delete)}"); st.success(f"Deleted: {', '.join(chars_to_delete)}"); st.rerun()
-             except IOError as e: logger.error(f"Failed to save characters.json after deletion: {e}"); st.error("Failed to update character file.")
-
-# --- Footer and Persistent Sidebar Elements ------------
-st.sidebar.markdown("---")
-# Update Sidebar Gallery (Call this at the end to reflect all changes)
-update_gallery()
-
-# Action Logs in Sidebar
-st.sidebar.subheader("Action Logs 📜")
-log_expander = st.sidebar.expander("View Logs", expanded=False)
-with log_expander:
-    # Display logs in reverse order (newest first)
-    log_text = "\n".join([f"{record.levelname}: {record.message}" for record in reversed(log_records)])
-    st.code(log_text, language='log')
-
-# History in Sidebar
-st.sidebar.subheader("Session History 📜")
-history_expander = st.sidebar.expander("View History", expanded=False)
-with history_expander:
-     for entry in reversed(st.session_state.get("history", [])):
-         if entry: history_expander.write(f"- {entry}")
-
-st.sidebar.markdown("---")
-st.sidebar.info("Using Hugging Face models for AI tasks.")
-st.sidebar.caption("App Modified by AI Assistant")
+# --- Helper Functions ---
+def get_files(exts):
+    files = []
+    for ext in exts:
+        files.extend(glob.glob(f'*.{ext}'))
+    return sorted([f for f in files if f.lower() != "readme.md"])
+
+def image_to_pdf(images, md_files):
+    buffer = BytesIO()
+    c = canvas.Canvas(buffer)
+    
+    for img_path in images:
+        img = Image.open(img_path)
+        width, height = img.size
+        c.setPageSize((width, height))
+        c.drawImage(ImageReader(img), 0, 0, width, height)
+        c.showPage()
+
+    for md_path in md_files:
+        with open(md_path, 'r', encoding='utf-8') as f:
+            md_content = f.read()
+            html = markdown(md_content)
+        c.setPageSize((595, 842))  # A4 size
+        c.setFont("Helvetica", 10)
+        c.drawString(50, 800, md_content[:1000])  # Simplified render
+        c.showPage()
+
+    c.save()
+    buffer.seek(0)
+    return buffer
+
+def render_pdf_gallery(pdf_files):
+    for pdf_file in pdf_files:
+        doc = fitz.open(pdf_file)
+        page = doc.load_page(0)
+        pix = page.get_pixmap(matrix=fitz.Matrix(0.5, 0.5))
+        img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+        st.image(img, caption=os.path.basename(pdf_file))
+
+# --- Sidebar Management ---
+st.sidebar.header("Content Management")
+
+image_files = get_files(['png', 'jpg', 'jpeg'])
+pdf_files = get_files(['pdf'])
+md_files = get_files(['md'])
+
+selected_images = st.sidebar.multiselect("Select Images", image_files)
+selected_md_files = st.sidebar.multiselect("Select Markdown Files", md_files)
+
+# PDF Gallery
+if st.sidebar.checkbox("Show PDF Gallery"):
+    render_pdf_gallery(pdf_files)
+
+# PDF Generation with rearrangement
+st.sidebar.subheader("Reorder Content for PDF")
+content_df = pd.DataFrame({
+    "Content": selected_images + selected_md_files,
+    "Type": ["Image"] * len(selected_images) + ["Markdown"] * len(selected_md_files),
+    "Order": range(len(selected_images) + len(selected_md_files))
+})
+
+edited_df = st.sidebar.data_editor(content_df, use_container_width=True)
+sorted_contents = edited_df.sort_values('Order')['Content'].tolist()
+
+if st.sidebar.button("Generate PDF"):
+    sorted_images = [item for item in sorted_contents if item in selected_images]
+    sorted_md_files = [item for item in sorted_contents if item in selected_md_files]
+    pdf_buffer = image_to_pdf(sorted_images, sorted_md_files)
+    st.sidebar.download_button("Download PDF", pdf_buffer, "output.pdf")
+
+# Deletion
+st.sidebar.subheader("Delete Files")
+file_to_delete = st.sidebar.selectbox("Select file to delete", image_files + pdf_files + md_files)
+if st.sidebar.button("Delete Selected File"):
+    os.remove(file_to_delete)
+    st.sidebar.success(f"Deleted {file_to_delete}")
+    st.rerun()
+
+# --- Main Page ---
+st.title("Vision & Layout Titans 🚀")
+st.markdown("### Manage, View, and Export Your Files Easily!")
+
+# Display selected images
+st.subheader("Selected Images")
+for img_path in selected_images:
+    img = Image.open(img_path)
+    st.image(img, caption=os.path.basename(img_path))
+
+# Display selected markdown
+st.subheader("Selected Markdown")
+for md_path in selected_md_files:
+    with open(md_path, 'r', encoding='utf-8') as f:
+        md_content = f.read()
+    st.markdown(md_content[:500] + '...')