diff --git a/.gitignore b/.gitignore
index c1f0f04..107b564 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,3 +33,4 @@ build*
 compiled/
 images/oai-iOS-Default-1024x1024@1x.png
 images/oai.icon/
+b0.sh
\ No newline at end of file
diff --git a/oai.py b/oai.py
index 0f75fd4..9bf2cc4 100644
--- a/oai.py
+++ b/oai.py
@@ -20,11 +20,17 @@ import re
 import sqlite3
 import json
 import datetime
-import logging  # Added missing import for logging
+import logging
+from logging.handlers import RotatingFileHandler  # Added for log rotation
 from prompt_toolkit import PromptSession
 from prompt_toolkit.history import FileHistory
 from rich.logging import RichHandler
 from prompt_toolkit.auto_suggest import AutoSuggestFromHistory
+from packaging import version as pkg_version
+import io  # Added for custom handler
+
+# App version. Changes by author with new releases.
+version = '1.9.5'
 
 app = typer.Typer()
 
@@ -71,27 +77,9 @@ LOW_CREDIT_RATIO = 0.1  # Warn if credits left < 10% of total
 LOW_CREDIT_AMOUNT = 1.0  # Warn if credits left < $1 in absolute terms
 HIGH_COST_WARNING = "cost_warning_threshold"  # Configurable key for cost threshold, default $0.01
 
-# Setup Rich-powered logging to file as per [rich.readthedocs.io](https://rich.readthedocs.io/en/latest/logging.html)
-log_console = Console(file=open(log_file, 'a'), width=120)  # Append to log file, wider for tracebacks
-handler = RichHandler(
-    console=log_console,
-    level=logging.INFO,
-    rich_tracebacks=True,
-    tracebacks_suppress=['requests', 'openrouter', 'urllib3', 'httpx', 'openai']  # Suppress irrelevant tracebacks for cleaner logs
-)
-logging.basicConfig(
-    level=logging.NOTSET,  # Let handler control what gets written
-    format="%(message)s",  # Rich formats it
-    datefmt="[%X]",
-    handlers=[handler]
-)
-app_logger = logging.getLogger("oai_app")
-app_logger.setLevel(logging.INFO)
-
 # DB configuration
 database = config_dir / 'oai_config.db'
 DB_FILE = str(database)
-version = '1.9'
 
 def create_table_if_not_exists():
     """Ensure the config and conversation_sessions tables exist."""
@@ -122,6 +110,124 @@ def set_config(key: str, value: str):
         conn.execute('INSERT OR REPLACE INTO config (key, value) VALUES (?, ?)', (key, value))
         conn.commit()
 
+# ============================================================================
+# ROTATING RICH HANDLER - Combines RotatingFileHandler with Rich formatting
+# ============================================================================
+class RotatingRichHandler(RotatingFileHandler):
+    """Custom handler that combines RotatingFileHandler with Rich formatting."""
+    
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        # Create a Rich console that writes to a string buffer
+        self.rich_console = Console(file=io.StringIO(), width=120, force_terminal=False)
+        self.rich_handler = RichHandler(
+            console=self.rich_console,
+            show_time=True,
+            show_path=True,
+            rich_tracebacks=True,
+            tracebacks_suppress=['requests', 'openrouter', 'urllib3', 'httpx', 'openai']
+        )
+    
+    def emit(self, record):
+        try:
+            # Let RichHandler format the record
+            self.rich_handler.emit(record)
+            
+            # Get the formatted output from the string buffer
+            output = self.rich_console.file.getvalue()
+            
+            # Clear the buffer for next use
+            self.rich_console.file.seek(0)
+            self.rich_console.file.truncate(0)
+            
+            # Write the Rich-formatted output to our rotating file
+            if output:
+                self.stream.write(output)
+                self.flush()
+                
+        except Exception:
+            self.handleError(record)
+
+# Get log configuration from DB
+LOG_MAX_SIZE_MB = int(get_config('log_max_size_mb') or "10")
+LOG_BACKUP_COUNT = int(get_config('log_backup_count') or "2")
+
+# Create the custom rotating handler
+app_handler = RotatingRichHandler(
+    filename=str(log_file),
+    maxBytes=LOG_MAX_SIZE_MB * 1024 * 1024,  # Convert MB to bytes
+    backupCount=LOG_BACKUP_COUNT,
+    encoding='utf-8'
+)
+
+logging.basicConfig(
+    level=logging.NOTSET,
+    format="%(message)s",  # Rich formats it
+    datefmt="[%X]",
+    handlers=[app_handler]
+)
+
+app_logger = logging.getLogger("oai_app")
+app_logger.setLevel(logging.INFO)
+
+# ============================================================================
+# END OF LOGGING SETUP
+# ============================================================================
+
+logger = logging.getLogger(__name__)
+
+def check_for_updates(current_version: str) -> str:
+    """
+    Check if a new version is available using semantic versioning.
+    
+    Returns:
+        Formatted status string for display
+    """
+    try:
+        response = requests.get(
+            'https://gitlab.pm/api/v1/repos/rune/oai/releases/latest',
+            headers={"Content-Type": "application/json"},
+            timeout=1.0,
+            allow_redirects=True
+        )
+        response.raise_for_status()
+        
+        data = response.json()
+        version_online = data.get('tag_name', '').lstrip('v')
+        
+        if not version_online:
+            logger.warning("No version found in API response")
+            return f"[bold green]oAI version {current_version}[/]"
+        
+        current = pkg_version.parse(current_version)
+        latest = pkg_version.parse(version_online)
+        
+        if latest > current:
+            logger.info(f"Update available: {current_version} → {version_online}")
+            return f"[bold green]oAI version {current_version} [/][bold red](Update available: {current_version} → {version_online})[/]"
+        else:
+            logger.debug(f"Already up to date: {current_version}")
+            return f"[bold green]oAI version {current_version} (up to date)[/]"
+            
+    except requests.exceptions.HTTPError as e:
+        logger.warning(f"HTTP error checking for updates: {e.response.status_code}")
+        return f"[bold green]oAI version {current_version}[/]"
+    except requests.exceptions.ConnectionError:
+        logger.warning("Network error checking for updates (offline?)")
+        return f"[bold green]oAI version {current_version}[/]"
+    except requests.exceptions.Timeout:
+        logger.warning("Timeout checking for updates")
+        return f"[bold green]oAI version {current_version}[/]"
+    except requests.exceptions.RequestException as e:
+        logger.warning(f"Request error checking for updates: {type(e).__name__}")
+        return f"[bold green]oAI version {current_version}[/]"
+    except (KeyError, ValueError) as e:
+        logger.warning(f"Invalid API response checking for updates: {e}")
+        return f"[bold green]oAI version {current_version}[/]"
+    except Exception as e:
+        logger.error(f"Unexpected error checking for updates: {e}")
+        return f"[bold green]oAI version {current_version}[/]"
+
 def save_conversation(name: str, data: List[Dict[str, str]]):
     """Save conversation history to DB."""
     timestamp = datetime.datetime.now().isoformat()
@@ -309,6 +415,7 @@ STREAM_ENABLED = get_config('stream_enabled') or "on"
 DEFAULT_MODEL_ID = get_config('default_model')
 MAX_TOKEN = int(get_config('max_token') or "100000")
 COST_WARNING_THRESHOLD = float(get_config(HIGH_COST_WARNING) or "0.01")  # Configurable cost threshold for alerts
+DEFAULT_ONLINE_MODE = get_config('default_online_mode') or "off"  # New: Default online mode setting
 
 # Fetch models with app identification headers
 models_data = []
@@ -416,16 +523,15 @@ def display_paginated_table(table: Table, title: str):
         return
     
     # Separate header from data rows
-    # Typically the first 3 lines are: top border, header row, separator
     header_lines = []
     data_lines = []
     
-    # Find where the header ends (usually after the first horizontal line after header text)
+    # Find where the header ends
     header_end_index = 0
     found_header_text = False
     
     for i, line_segments in enumerate(all_lines):
-        # Check if this line contains header-style text (bold/magenta usually)
+        # Check if this line contains header-style text
         has_header_style = any(
             seg.style and ('bold' in str(seg.style) or 'magenta' in str(seg.style))
             for seg in line_segments
@@ -437,21 +543,20 @@ def display_paginated_table(table: Table, title: str):
         # After finding header text, the next line with box-drawing chars is the separator
         if found_header_text and i > 0:
             line_text = ''.join(seg.text for seg in line_segments)
-            # Check for horizontal line characters (─ ━ ╌ etc.)
             if any(char in line_text for char in ['─', '━', '┼', '╪', '┤', '├']):
                 header_end_index = i
                 break
     
     # If we found a header separator, split there
     if header_end_index > 0:
-        header_lines = all_lines[:header_end_index + 1]  # Include the separator
+        header_lines = all_lines[:header_end_index + 1]
         data_lines = all_lines[header_end_index + 1:]
     else:
         # Fallback: assume first 3 lines are header
         header_lines = all_lines[:min(3, len(all_lines))]
         data_lines = all_lines[min(3, len(all_lines)):]
     
-    # Calculate how many data lines fit per page (accounting for header)
+    # Calculate how many data lines fit per page
     lines_per_page = terminal_height - len(header_lines)
     
     # Display with pagination
@@ -469,7 +574,7 @@ def display_paginated_table(table: Table, title: str):
         for line_segments in header_lines:
             for segment in line_segments:
                 console.print(segment.text, style=segment.style, end="")
-            console.print()  # New line after each row
+            console.print()
         
         # Calculate how many data lines to show on this page
         end_line = min(current_line + lines_per_page, len(data_lines))
@@ -478,7 +583,7 @@ def display_paginated_table(table: Table, title: str):
         for line_segments in data_lines[current_line:end_line]:
             for segment in line_segments:
                 console.print(segment.text, style=segment.style, end="")
-            console.print()  # New line after each row
+            console.print()
         
         # Update position
         current_line = end_line
@@ -492,20 +597,16 @@ def display_paginated_table(table: Table, title: str):
                 import tty
                 import termios
                 
-                # Save terminal settings
                 fd = sys.stdin.fileno()
                 old_settings = termios.tcgetattr(fd)
                 
                 try:
-                    # Set terminal to raw mode to read single character
                     tty.setraw(fd)
                     char = sys.stdin.read(1)
                     
-                    # If not space, break pagination
                     if char != ' ':
                         break
                 finally:
-                    # Restore terminal settings
                     termios.tcsetattr(fd, termios.TCSADRAIN, old_settings)
             except:
                 # Fallback for Windows or if termios not available
@@ -513,12 +614,11 @@ def display_paginated_table(table: Table, title: str):
                 if input_char != '':
                     break
         else:
-            # No more content
             break
 
 @app.command()
 def chat():
-    global API_KEY, OPENROUTER_BASE_URL, STREAM_ENABLED, MAX_TOKEN, COST_WARNING_THRESHOLD
+    global API_KEY, OPENROUTER_BASE_URL, STREAM_ENABLED, MAX_TOKEN, COST_WARNING_THRESHOLD, DEFAULT_ONLINE_MODE, LOG_MAX_SIZE_MB, LOG_BACKUP_COUNT
     session_max_token = 0
     session_system_prompt = ""
     session_history = []
@@ -531,9 +631,9 @@ def chat():
     conversation_memory_enabled = True  # Memory ON by default
     memory_start_index = 0  # Track when memory was last enabled
     saved_conversations_cache = []  # Cache for /list results to use with /load by number
-    online_mode_enabled = False  # Online mode (web search) disabled by default
+    online_mode_enabled = DEFAULT_ONLINE_MODE == "on"  # Initialize from config
 
-    app_logger.info("Starting new chat session with memory enabled")  # Log session start
+    app_logger.info("Starting new chat session with memory enabled")
 
     if not API_KEY:
         console.print("[bold red]API key not found. Use '/config api'.[/]")
@@ -567,7 +667,8 @@ def chat():
     client = OpenRouter(api_key=API_KEY)
     
     if selected_model:
-        console.print(f"[bold blue]Welcome to oAI![/] [bold red]Active model: {selected_model['name']}[/]")
+        online_status = "enabled" if online_mode_enabled else "disabled"
+        console.print(f"[bold blue]Welcome to oAI![/] [bold red]Active model: {selected_model['name']}[/] [dim cyan](Online mode: {online_status})[/]")
     else:
         console.print("[bold blue]Welcome to oAI![/] [italic blue]Select a model with '/model'.[/]")
 
@@ -584,14 +685,11 @@ def chat():
             # Handle // escape sequence - convert to single / and treat as regular text
             if user_input.startswith("//"):
                 user_input = user_input[1:]  # Remove first slash, keep the rest
-                # Don't process as command, jump to message processing
                 
-            # Check for unknown commands (starts with / but not a valid command)
+            # Check for unknown commands
             elif user_input.startswith("/") and user_input.lower() not in ["exit", "quit", "bye"]:
-                # Extract command (first word after /)
                 command_word = user_input.split()[0].lower() if user_input.split() else user_input.lower()
                 
-                # Check if it's a valid command or partial match
                 if not any(command_word.startswith(cmd) for cmd in VALID_COMMANDS):
                     console.print(f"[bold red]Unknown command: {command_word}[/]")
                     console.print("[bold yellow]Type /help to see all available commands.[/]")
@@ -600,7 +698,7 @@ def chat():
             
             if user_input.lower() in ["exit", "quit", "bye"]:
                 total_tokens = total_input_tokens + total_output_tokens
-                app_logger.info(f"Session ended. Total messages: {message_count}, Total tokens: {total_tokens}, Total cost: ${total_cost:.4f}")  # Log session summary
+                app_logger.info(f"Session ended. Total messages: {message_count}, Total tokens: {total_tokens}, Total cost: ${total_cost:.4f}")
                 console.print("[bold yellow]Goodbye![/]")
                 return
 
@@ -618,7 +716,9 @@ def chat():
                 args = user_input[8:].strip()
                 if not args:
                     status = "enabled" if online_mode_enabled else "disabled"
+                    default_status = "enabled" if DEFAULT_ONLINE_MODE == "on" else "disabled"
                     console.print(f"[bold blue]Online mode (web search) {status}.[/]")
+                    console.print(f"[dim blue]Default setting: {default_status} (use '/config online on|off' to change)[/]")
                     if selected_model:
                         if supports_online_mode(selected_model):
                             console.print(f"[dim green]Current model '{selected_model['name']}' supports online mode.[/]")
@@ -635,12 +735,12 @@ def chat():
                         app_logger.warning(f"Online mode activation failed - model {selected_model['id']} doesn't support it")
                         continue
                     online_mode_enabled = True
-                    console.print("[bold green]Online mode enabled. Model will use web search capabilities.[/]")
+                    console.print("[bold green]Online mode enabled for this session. Model will use web search capabilities.[/]")
                     console.print(f"[dim blue]Effective model ID: {get_effective_model_id(selected_model['id'], True)}[/]")
                     app_logger.info(f"Online mode enabled for model {selected_model['id']}")
                 elif args.lower() == "off":
                     online_mode_enabled = False
-                    console.print("[bold green]Online mode disabled. Model will not use web search.[/]")
+                    console.print("[bold green]Online mode disabled for this session. Model will not use web search.[/]")
                     if selected_model:
                         console.print(f"[dim blue]Effective model ID: {selected_model['id']}[/]")
                     app_logger.info("Online mode disabled")
@@ -660,7 +760,7 @@ def chat():
                     continue
                 if args.lower() == "on":
                     conversation_memory_enabled = True
-                    memory_start_index = len(session_history)  # Remember where we started
+                    memory_start_index = len(session_history)
                     console.print("[bold green]Conversation memory enabled. Will remember conversations from this point forward.[/]")
                     console.print(f"[dim blue]Memory will track messages starting from index {memory_start_index}.[/]")
                     app_logger.info(f"Conversation memory enabled at index {memory_start_index}")
@@ -673,7 +773,6 @@ def chat():
                     console.print("[bold yellow]Usage: /memory on|off (or /memory to view status)[/]")
                 continue
             elif user_input.lower().startswith("/paste"):
-                # Get optional prompt after /paste
                 optional_prompt = user_input[7:].strip()
                 
                 try:
@@ -688,13 +787,10 @@ def chat():
                     app_logger.warning("Paste attempted with empty clipboard")
                     continue
                 
-                # Validate it's text (check if it's valid UTF-8 and printable)
                 try:
-                    # Try to encode/decode to ensure it's valid text
                     clipboard_content.encode('utf-8')
                     
-                    # Show preview of pasted content
-                    preview_lines = clipboard_content.split('\n')[:10]  # First 10 lines
+                    preview_lines = clipboard_content.split('\n')[:10]
                     preview_text = '\n'.join(preview_lines)
                     if len(clipboard_content.split('\n')) > 10:
                         preview_text += "\n... (content truncated for preview)"
@@ -709,7 +805,6 @@ def chat():
                         border_style="cyan"
                     ))
                     
-                    # Build the final prompt
                     if optional_prompt:
                         final_prompt = f"{optional_prompt}\n\n```\n{clipboard_content}\n```"
                         console.print(f"[dim blue]Sending with prompt: '{optional_prompt}'[/]")
@@ -717,7 +812,6 @@ def chat():
                         final_prompt = clipboard_content
                         console.print("[dim blue]Sending clipboard content without additional prompt[/]")
                     
-                    # Set user_input to the pasted content so it gets processed normally
                     user_input = final_prompt
                     app_logger.info(f"Pasted content from clipboard: {char_count} chars, {line_count} lines, with prompt: {bool(optional_prompt)}")
                     
@@ -745,13 +839,11 @@ def chat():
                     console.print("[bold red]No conversation history to export.[/]")
                     continue
                 
-                # Validate format
                 if export_format not in ['md', 'json', 'html']:
                     console.print("[bold red]Invalid format. Use: md, json, or html[/]")
                     continue
                 
                 try:
-                    # Generate export content
                     if export_format == 'md':
                         content = export_as_markdown(session_history, session_system_prompt)
                     elif export_format == 'json':
@@ -759,7 +851,6 @@ def chat():
                     elif export_format == 'html':
                         content = export_as_html(session_history, session_system_prompt)
                     
-                    # Write to file
                     export_path = Path(filename).expanduser()
                     with open(export_path, 'w', encoding='utf-8') as f:
                         f.write(content)
@@ -790,7 +881,6 @@ def chat():
                     console.print("[bold yellow]Tip: Use /list to see numbered conversations[/]")
                     continue
                 
-                # Check if input is a number
                 conversation_name = None
                 if args.isdigit():
                     conv_number = int(args)
@@ -811,9 +901,8 @@ def chat():
                     continue
                 session_history = loaded_data
                 current_index = len(session_history) - 1
-                # When loading, reset memory tracking if memory is enabled
                 if conversation_memory_enabled:
-                    memory_start_index = 0  # Include all loaded messages in memory
+                    memory_start_index = 0
                 total_input_tokens = 0
                 total_output_tokens = 0
                 total_cost = 0.0
@@ -828,7 +917,6 @@ def chat():
                     console.print("[bold yellow]Tip: Use /list to see numbered conversations[/]")
                     continue
                 
-                # Check if input is a number
                 conversation_name = None
                 if args.isdigit():
                     conv_number = int(args)
@@ -842,7 +930,6 @@ def chat():
                 else:
                     conversation_name = args
                 
-                # Confirm deletion
                 try:
                     confirm = typer.confirm(f"Delete conversation '{conversation_name}'? This cannot be undone.", default=False)
                     if not confirm:
@@ -856,7 +943,6 @@ def chat():
                 if deleted_count > 0:
                     console.print(f"[bold green]Conversation '{conversation_name}' deleted ({deleted_count} version(s) removed).[/]")
                     app_logger.info(f"Conversation '{conversation_name}' deleted - {deleted_count} version(s)")
-                    # Refresh cache if deleted conversation was in it
                     if saved_conversations_cache:
                         saved_conversations_cache = [c for c in saved_conversations_cache if c['name'] != conversation_name]
                 else:
@@ -871,12 +957,10 @@ def chat():
                     saved_conversations_cache = []
                     continue
                 
-                # Update cache for /load command
                 saved_conversations_cache = conversations
                 
                 table = Table("No.", "Name", "Messages", "Last Saved", show_header=True, header_style="bold magenta")
                 for idx, conv in enumerate(conversations, 1):
-                    # Parse ISO timestamp and format it nicely
                     try:
                         dt = datetime.datetime.fromisoformat(conv['timestamp'])
                         formatted_time = dt.strftime('%Y-%m-%d %H:%M:%S')
@@ -899,7 +983,6 @@ def chat():
                     continue
                 current_index -= 1
                 prev_response = session_history[current_index]['response']
-                # Render as markdown with proper formatting
                 md = Markdown(prev_response)
                 console.print(Panel(md, title=f"[bold green]Previous Response ({current_index + 1}/{len(session_history)})[/]", title_align="left"))
                 app_logger.debug(f"Viewed previous response at index {current_index}")
@@ -910,7 +993,6 @@ def chat():
                     continue
                 current_index += 1
                 next_response = session_history[current_index]['response']
-                # Render as markdown with proper formatting
                 md = Markdown(next_response)
                 console.print(Panel(md, title=f"[bold green]Next Response ({current_index + 1}/{len(session_history)})[/]", title_align="left"))
                 app_logger.debug(f"Viewed next response at index {current_index}")
@@ -925,7 +1007,6 @@ def chat():
                 console.print(Panel(table, title="[bold green]Session Cost Summary[/]", title_align="left"))
                 app_logger.info(f"User viewed stats: {stats}")
 
-                # Cost warnings in /stats
                 warnings = check_credit_alerts(credits)
                 if warnings:
                     warning_text = '|'.join(warnings)
@@ -954,7 +1035,7 @@ def chat():
                 session_history = []
                 current_index = -1
                 session_system_prompt = ""
-                memory_start_index = 0  # Reset memory tracking
+                memory_start_index = 0
                 total_input_tokens = 0
                 total_output_tokens = 0
                 total_cost = 0.0
@@ -976,7 +1057,6 @@ def chat():
                         console.print(f"[bold red]Model '{args}' not found.[/]")
                         continue
                 
-                # Display model info
                 pricing = model_to_show.get("pricing", {})
                 architecture = model_to_show.get("architecture", {})
                 supported_params = ", ".join(model_to_show.get("supported_parameters", [])) or "None"
@@ -1002,7 +1082,6 @@ def chat():
                 console.print(Panel(table, title=f"[bold green]Model Info: {model_to_show['name']}[/]", title_align="left"))
                 continue
 
-            # Model selection with Image and Online columns
             elif user_input.startswith("/model"):
                 app_logger.info("User initiated model selection")
                 args = user_input[7:].strip()
@@ -1014,14 +1093,12 @@ def chat():
                     console.print(f"[bold red]No models match '{search_term}'. Try '/model'.[/]")
                     continue
                 
-                # Create table with Image and Online columns
                 table = Table("No.", "Name", "ID", "Image", "Online", show_header=True, header_style="bold magenta")
                 for i, model in enumerate(filtered_models, 1):
                     image_support = "[green]✓[/green]" if has_image_capability(model) else "[red]✗[/red]"
                     online_support = "[green]✓[/green]" if supports_online_mode(model) else "[red]✗[/red]"
                     table.add_row(str(i), model["name"], model["id"], image_support, online_support)
                 
-                # Use pagination for the table
                 title = f"[bold green]Available Models ({'All' if not search_term else f'Search: {search_term}'})[/]"
                 display_paginated_table(table, title)
                 
@@ -1032,14 +1109,19 @@ def chat():
                             break
                         if 1 <= choice <= len(filtered_models):
                             selected_model = filtered_models[choice - 1]
-                            # Disable online mode when switching models (user must re-enable)
-                            if online_mode_enabled:
+                            
+                            # Apply default online mode if model supports it
+                            if supports_online_mode(selected_model) and DEFAULT_ONLINE_MODE == "on":
+                                online_mode_enabled = True
+                                console.print(f"[bold cyan]Selected: {selected_model['name']} ({selected_model['id']})[/]")
+                                console.print("[dim cyan]✓ Online mode auto-enabled (default setting). Use '/online off' to disable for this session.[/]")
+                            else:
                                 online_mode_enabled = False
-                                console.print("[dim yellow]Note: Online mode auto-disabled when changing models.[/]")
-                            console.print(f"[bold cyan]Selected: {selected_model['name']} ({selected_model['id']})[/]")
-                            if supports_online_mode(selected_model):
-                                console.print("[dim green]✓ This model supports online mode. Use '/online on' to enable web search.[/]")
-                            app_logger.info(f"Model selected: {selected_model['name']} ({selected_model['id']})")
+                                console.print(f"[bold cyan]Selected: {selected_model['name']} ({selected_model['id']})[/]")
+                                if supports_online_mode(selected_model):
+                                    console.print("[dim green]✓ This model supports online mode. Use '/online on' to enable web search.[/]")
+                            
+                            app_logger.info(f"Model selected: {selected_model['name']} ({selected_model['id']}), Online: {online_mode_enabled}")
                             break
                         console.print("[bold red]Invalid choice. Try again.[/]")
                     except ValueError:
@@ -1047,7 +1129,6 @@ def chat():
                 continue
 
             elif user_input.startswith("/maxtoken"):
-                # (unchanged)
                 args = user_input[10:].strip()
                 if not args:
                     console.print(f"[bold blue]Current session max tokens: {session_max_token}[/]")
@@ -1067,7 +1148,6 @@ def chat():
                 continue
 
             elif user_input.startswith("/system"):
-                # (unchanged but added to history view)
                 args = user_input[8:].strip()
                 if not args:
                     if session_system_prompt:
@@ -1085,13 +1165,14 @@ def chat():
 
             elif user_input.startswith("/config"):
                 args = user_input[8:].strip().lower()
+                update = check_for_updates(version)
+                
                 if args == "api":
                     try:
                         new_api_key = typer.prompt("Enter new API key")
                         if new_api_key.strip():
                             set_config('api_key', new_api_key.strip())
                             API_KEY = new_api_key.strip()
-                            # Reinitialize client with new API key
                             client = OpenRouter(api_key=API_KEY)
                             console.print("[bold green]API key updated![/]")
                         else:
@@ -1110,7 +1191,7 @@ def chat():
                     except Exception as e:
                         console.print(f"[bold red]Error updating URL: {e}[/]")
                 elif args.startswith("costwarning"):
-                    sub_args = args[11:].strip()  # Extract everything after "costwarning"
+                    sub_args = args[11:].strip()
                     if not sub_args:
                         console.print(f"[bold blue]Stored cost warning threshold: ${COST_WARNING_THRESHOLD:.4f}[/]")
                         continue
@@ -1132,6 +1213,43 @@ def chat():
                         console.print(f"[bold green]Streaming {'enabled' if sub_args == 'on' else 'disabled'}.[/]")
                     else:
                         console.print("[bold yellow]Usage: /config stream on|off[/]")
+                elif args.startswith("log"):
+                    sub_args = args[4:].strip()
+                    if not sub_args:
+                        console.print(f"[bold blue]Current log file size limit: {LOG_MAX_SIZE_MB} MB[/]")
+                        console.print(f"[bold blue]Log backup count: {LOG_BACKUP_COUNT} files[/]")
+                        console.print(f"[dim yellow]Total max disk usage: ~{LOG_MAX_SIZE_MB * (LOG_BACKUP_COUNT + 1)} MB[/]")
+                        continue
+                    try:
+                        new_size_mb = int(sub_args)
+                        if new_size_mb < 1:
+                            console.print("[bold red]Log size must be at least 1 MB.[/]")
+                            continue
+                        if new_size_mb > 100:
+                            console.print("[bold yellow]Warning: Log size > 100MB. Capping at 100MB.[/]")
+                            new_size_mb = 100
+                        set_config('log_max_size_mb', str(new_size_mb))
+                        LOG_MAX_SIZE_MB = new_size_mb
+                        console.print(f"[bold green]Log size limit set to {new_size_mb} MB.[/]")
+                        console.print("[bold yellow]⚠️  Restart the application for this change to take effect.[/]")
+                        app_logger.info(f"Log size limit updated to {new_size_mb} MB (requires restart)")
+                    except ValueError:
+                        console.print("[bold red]Invalid size. Provide a number in MB.[/]")
+                elif args.startswith("online"):
+                    sub_args = args[7:].strip()
+                    if not sub_args:
+                        current_default = "enabled" if DEFAULT_ONLINE_MODE == "on" else "disabled"
+                        console.print(f"[bold blue]Default online mode: {current_default}[/]")
+                        console.print("[dim yellow]This sets the default for new models. Use '/online on|off' to override in current session.[/]")
+                        continue
+                    if sub_args in ["on", "off"]:
+                        set_config('default_online_mode', sub_args)
+                        DEFAULT_ONLINE_MODE = sub_args
+                        console.print(f"[bold green]Default online mode {'enabled' if sub_args == 'on' else 'disabled'}.[/]")
+                        console.print("[dim blue]Note: This affects new model selections. Current session unchanged.[/]")
+                        app_logger.info(f"Default online mode set to {sub_args}")
+                    else:
+                        console.print("[bold yellow]Usage: /config online on|off[/]")
                 elif args.startswith("maxtoken"):
                     sub_args = args[9:].strip()
                     if not sub_args:
@@ -1163,14 +1281,12 @@ def chat():
                         console.print(f"[bold red]No models match '{search_term}'. Try without search.[/]")
                         continue
                     
-                    # Create table with Image and Online columns
                     table = Table("No.", "Name", "ID", "Image", "Online", show_header=True, header_style="bold magenta")
                     for i, model in enumerate(filtered_models, 1):
                         image_support = "[green]✓[/green]" if has_image_capability(model) else "[red]✗[/red]"
                         online_support = "[green]✓[/green]" if supports_online_mode(model) else "[red]✗[/red]"
                         table.add_row(str(i), model["name"], model["id"], image_support, online_support)
                     
-                    # Use pagination for the table
                     title = f"[bold green]Available Models for Default ({'All' if not search_term else f'Search: {search_term}'})[/]"
                     display_paginated_table(table, title)
                     
@@ -1197,10 +1313,13 @@ def chat():
                     table.add_row("Base URL", OPENROUTER_BASE_URL or "[Not set]")
                     table.add_row("DB Path", str(database) or "[Not set]")
                     table.add_row("Logfile", str(log_file) or "[Not set]")
+                    table.add_row("Log Size Limit", f"{LOG_MAX_SIZE_MB} MB")
+                    table.add_row("Log Backups", str(LOG_BACKUP_COUNT))
                     table.add_row("Streaming", "Enabled" if STREAM_ENABLED == "on" else "Disabled")
                     table.add_row("Default Model", DEFAULT_MODEL_ID or "[Not set]")
                     table.add_row("Current Model", "[Not set]" if selected_model is None else str(selected_model["name"]))
-                    table.add_row("Online Mode", "Enabled" if online_mode_enabled else "Disabled")
+                    table.add_row("Default Online Mode", "Enabled" if DEFAULT_ONLINE_MODE == "on" else "Disabled")
+                    table.add_row("Session Online Mode", "Enabled" if online_mode_enabled else "Disabled")
                     table.add_row("Max Token", str(MAX_TOKEN))
                     table.add_row("Session Token", "[Not set]" if session_max_token == 0 else str(session_max_token))
                     table.add_row("Session System Prompt", session_system_prompt or "[Not set]")
@@ -1222,7 +1341,7 @@ def chat():
                         table.add_row("Used Credits", "[Unavailable - Check API key]")
                         table.add_row("Credits Left", "[Unavailable - Check API key]")
 
-                    console.print(Panel(table, title="[bold green]Current Configurations[/]", title_align="left", subtitle="[bold green]oAI Version %s" % version, subtitle_align="right"))
+                    console.print(Panel(table, title="[bold green]Current Configurations[/]", title_align="left", subtitle="%s" %(update), subtitle_align="right"))
                 continue
 
             if user_input.lower() == "/credits":
@@ -1250,7 +1369,7 @@ def chat():
             if user_input.lower() == "/help":
                 help_table = Table("Command", "Description", "Example", show_header=True, header_style="bold cyan", width=console.width - 10)
                 
-                # ===== SESSION COMMANDS =====
+                # SESSION COMMANDS
                 help_table.add_row(
                     "[bold yellow]━━━ SESSION COMMANDS ━━━[/]",
                     "",
@@ -1278,7 +1397,7 @@ def chat():
                 )
                 help_table.add_row(
                     "/online [on|off]",
-                    "Enable/disable online mode (web search) for current model. Only works with models that support tools.",
+                    "Enable/disable online mode (web search) for current session. Overrides default setting.",
                     "/online on\n/online off"
                 )
                 help_table.add_row(
@@ -1302,7 +1421,7 @@ def chat():
                     "/retry"
                 )
                 
-                # ===== MODEL COMMANDS =====
+                # MODEL COMMANDS
                 help_table.add_row(
                     "[bold yellow]━━━ MODEL COMMANDS ━━━[/]",
                     "",
@@ -1319,7 +1438,7 @@ def chat():
                     "/model\n/model gpt"
                 )
                 
-                # ===== CONFIGURATION COMMANDS (ALPHABETICAL) =====
+                # CONFIGURATION COMMANDS
                 help_table.add_row(
                     "[bold yellow]━━━ CONFIGURATION ━━━[/]",
                     "",
@@ -1340,6 +1459,11 @@ def chat():
                     "Set the cost warning threshold. Alerts when response exceeds this cost (in USD).",
                     "/config costwarning 0.05"
                 )
+                help_table.add_row(
+                    "/config log [size_mb]",
+                    "Set log file size limit in MB. Older logs are rotated automatically. Requires restart.",
+                    "/config log 20"
+                )
                 help_table.add_row(
                     "/config maxtoken [value]",
                     "Set stored max token limit (persisted in DB). View current if no value provided.",
@@ -1350,6 +1474,11 @@ def chat():
                     "Set default model that loads on startup. Shows image and online capabilities. Doesn't change current session model.",
                     "/config model gpt"
                 )
+                help_table.add_row(
+                    "/config online [on|off]",
+                    "Set default online mode for new model selections. Use '/online on|off' to override current session.",
+                    "/config online on"
+                )
                 help_table.add_row(
                     "/config stream [on|off]",
                     "Enable or disable response streaming.",
@@ -1361,7 +1490,7 @@ def chat():
                     "/config url"
                 )
                 
-                # ===== TOKEN & SYSTEM COMMANDS =====
+                # TOKEN & SYSTEM COMMANDS
                 help_table.add_row(
                     "[bold yellow]━━━ TOKEN & SYSTEM ━━━[/]",
                     "",
@@ -1383,7 +1512,7 @@ def chat():
                     "/system You are a Python expert"
                 )
                 
-                # ===== CONVERSATION MANAGEMENT =====
+                # CONVERSATION MANAGEMENT
                 help_table.add_row(
                     "[bold yellow]━━━ CONVERSATION MGMT ━━━[/]",
                     "",
@@ -1415,7 +1544,7 @@ def chat():
                     "/save my_chat"
                 )
                 
-                # ===== MONITORING & STATS =====
+                # MONITORING & STATS
                 help_table.add_row(
                     "[bold yellow]━━━ MONITORING & STATS ━━━[/]",
                     "",
@@ -1432,7 +1561,7 @@ def chat():
                     "/stats"
                 )
                 
-                # ===== FILE ATTACHMENTS =====
+                # INPUT METHODS
                 help_table.add_row(
                     "[bold yellow]━━━ INPUT METHODS ━━━[/]",
                     "",
@@ -1454,7 +1583,7 @@ def chat():
                     "//help sends '/help' as text"
                 )
                 
-                # ===== EXIT =====
+                # EXIT
                 help_table.add_row(
                     "[bold yellow]━━━ EXIT ━━━[/]",
                     "",
@@ -1514,7 +1643,6 @@ def chat():
                     # Handle PDFs
                     elif mime_type == 'application/pdf' or file_ext == '.pdf':
                         modalities = selected_model.get("architecture", {}).get("input_modalities", [])
-                        # Check for various possible modality indicators for PDFs
                         supports_pdf = any(mod in modalities for mod in ["document", "pdf", "file"])
                         if not supports_pdf:
                             console.print("[bold red]Selected model does not support PDF attachments.[/]")
@@ -1560,13 +1688,10 @@ def chat():
             # Build API messages with conversation history if memory is enabled
             api_messages = []
             
-            # Add system prompt if set
             if session_system_prompt:
                 api_messages.append({"role": "system", "content": session_system_prompt})
             
-            # Add conversation history only if memory is enabled (from memory start point onwards)
             if conversation_memory_enabled:
-                # Only include history from when memory was last enabled
                 for i in range(memory_start_index, len(session_history)):
                     history_entry = session_history[i]
                     api_messages.append({
@@ -1578,13 +1703,12 @@ def chat():
                         "content": history_entry['response']
                     })
             
-            # Add current user message
             api_messages.append({"role": "user", "content": message_content})
 
             # Get effective model ID with :online suffix if enabled
             effective_model_id = get_effective_model_id(selected_model["id"], online_mode_enabled)
 
-            # Build API params with app identification headers (using http_headers)
+            # Build API params
             api_params = {
                 "model": effective_model_id,
                 "messages": api_messages, 
@@ -1606,17 +1730,17 @@ def chat():
             online_status = "ON" if online_mode_enabled else "OFF"
             app_logger.info(f"API Request: Model '{effective_model_id}' (Online: {online_status}), Prompt length: {len(text_part)} chars, {file_count} file(s) attached, Memory: {memory_status}, History sent: {history_messages_count} messages, Transforms: middle-out {'enabled' if middle_out_enabled else 'disabled'}, App: {APP_NAME} ({APP_URL}).")
 
-            # Send and handle response with metrics and timing
+            # Send and handle response
             is_streaming = STREAM_ENABLED == "on"
             if is_streaming:
                 console.print("[bold green]Streaming response...[/] [dim](Press Ctrl+C to cancel)[/]")
                 if online_mode_enabled:
                     console.print("[dim cyan]🌐 Online mode active - model has web search access[/]")
-                console.print("")  # Add spacing before response
+                console.print("")
             else:
                 console.print("[bold green]Thinking...[/]", end="\r")
 
-            start_time = time.time()  # Start timing request
+            start_time = time.time()
             try:
                 response = client.chat.send(**api_params)
                 app_logger.info(f"API call successful for model '{effective_model_id}'")
@@ -1625,12 +1749,11 @@ def chat():
                 app_logger.error(f"API Error: {type(e).__name__}: {e}")
                 continue
 
-            response_time = time.time() - start_time  # Calculate response time
+            response_time = time.time() - start_time
 
             full_response = ""
             if is_streaming:
                 try:
-                    # Use Live display for smooth streaming with proper wrapping
                     with Live("", console=console, refresh_per_second=10, auto_refresh=True) as live:
                         for chunk in response:
                             if hasattr(chunk, 'error') and chunk.error:
@@ -1640,11 +1763,9 @@ def chat():
                             if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content:
                                 content_chunk = chunk.choices[0].delta.content
                                 full_response += content_chunk
-                                # Update live display with markdown rendering
                                 md = Markdown(full_response)
                                 live.update(md)
                     
-                    # Add newline after streaming completes
                     console.print("")
                     
                 except KeyboardInterrupt:
@@ -1656,15 +1777,14 @@ def chat():
                 console.print(f"\r{' ' * 20}\r", end="")
 
             if full_response:
-                # Render response with proper markdown formatting
-                if not is_streaming:  # Only show panel for non-streaming (streaming already displayed)
+                if not is_streaming:
                     md = Markdown(full_response)
                     console.print(Panel(md, title="[bold green]AI Response[/]", title_align="left", border_style="green"))
                 
                 session_history.append({'prompt': user_input, 'response': full_response})
                 current_index = len(session_history) - 1
 
-                # Process metrics for per-message display and session tracking
+                # Process metrics
                 usage = getattr(response, 'usage', None)
                 input_tokens = usage.input_tokens if usage and hasattr(usage, 'input_tokens') else 0
                 output_tokens = usage.output_tokens if usage and hasattr(usage, 'output_tokens') else 0
@@ -1675,10 +1795,9 @@ def chat():
                 total_cost += msg_cost
                 message_count += 1
 
-                # Log response metrics
                 app_logger.info(f"Response: Tokens - I:{input_tokens} O:{output_tokens} T:{input_tokens + output_tokens}, Cost: ${msg_cost:.4f}, Time: {response_time:.2f}s, Online: {online_mode_enabled}")
 
-                # Per-message metrics display with context info
+                # Per-message metrics display
                 if conversation_memory_enabled:
                     context_count = len(session_history) - memory_start_index
                     context_info = f", Context: {context_count} msg(s)" if context_count > 1 else ""
@@ -1701,7 +1820,6 @@ def chat():
                     console.print(f"[bold red]⚠️  {warning_text}[/]")
                     app_logger.warning(f"Warnings triggered: {warning_text}")
 
-                # Add spacing before copy prompt
                 console.print("")
                 try:
                     copy_choice = input("💾 Type 'c' to copy response, or press Enter to continue: ").strip().lower()
@@ -1711,7 +1829,6 @@ def chat():
                 except (EOFError, KeyboardInterrupt):
                     pass
                 
-                # Add spacing after interaction
                 console.print("")
             else:
                 console.print("[bold red]No response received.[/]")
diff --git a/requirements.txt b/requirements.txt
index 1ae029d..8a0a132 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -14,8 +14,9 @@ markdown2==2.5.4
 mdurl==0.1.2
 natsort==8.4.0
 openrouter==0.0.19
+packaging==25.0
 pipreqs==0.4.13
-prompt_toolkit==3.0.52
+prompt-toolkit==3.0.52
 Pygments==2.19.2
 pyperclip==1.11.0
 python-dateutil==2.9.0.post0
@@ -30,7 +31,7 @@ soupsieve==2.8
 svgwrite==1.4.3
 tqdm==4.67.1
 typer==0.20.0
-typing_extensions==4.15.0
+typing-extensions==4.15.0
 urllib3==2.5.0
 wavedrom==2.0.3.post3
 wcwidth==0.2.14