Enhancement Suite: Anti-loop protection, Kokoro TTS integration, ComfyUI status monitoring, and auto-open image functionality

build/lib/ollama_cli/core/config.py

@@ -0,0 +1,57 @@
+import os
+import json
+
+CONFIG_FILE = os.path.expanduser("~/.ollama-cli-config.json")
+
+DEFAULT_CONFIG = {
+    "excluded_models": [],
+    "git": {
+        "remote_url": "",
+        "username": "",
+        "password": ""
+    },
+    "gitea": {
+        "url": "",
+        "token": ""
+    },
+    "auto_save_sessions": True,
+    "mcp_servers": {},
+    "ollama_url": "http://localhost:11434",
+    "comfy_url": "http://localhost:9000",
+    "piper": {
+        "path": "~/.ollama-cli/piper/piper",
+        "model": "~/.ollama-cli/piper/voice.onnx"
+    },
+    "ntfy": {
+        "enabled": False,
+        "topic": "",
+        "server": "https://ntfy.sh"
+    },
+    "default_model": "llama3.2"
+}
+
+def load_config():
+    """Load config file"""
+    if os.path.exists(CONFIG_FILE):
+        try:
+            with open(CONFIG_FILE, 'r') as f:
+                config = json.load(f)
+                # Merge with defaults to ensure all keys exist
+                for k, v in DEFAULT_CONFIG.items():
+                    if k not in config:
+                        config[k] = v
+                return config
+        except Exception:
+            pass
+    return DEFAULT_CONFIG.copy()
+
+def save_config(config):
+    """Save config file"""
+    with open(CONFIG_FILE, 'w') as f:
+        json.dump(config, f, indent=2)
+
+def update_config(key, value):
+    """Update a specific config key"""
+    config = load_config()
+    config[key] = value
+    save_config(config)

build/lib/ollama_cli/core/ollama.py

@@ -0,0 +1,87 @@
+import json
+import requests
+import subprocess
+import sys
+from typing import List, Dict, Optional, Generator
+
+class OllamaClient:
+    def __init__(self, base_url: str = "http://localhost:11434"):
+        # Strip trailing slashes and common API paths if user provided them in config
+        self.base_url = base_url.rstrip("/")
+        if self.base_url.endswith("/api/chat"):
+            self.base_url = self.base_url[:-9]
+        elif self.base_url.endswith("/api"):
+            self.base_url = self.base_url[:-4]
+            
+        self.chat_url = f"{self.base_url}/api/chat"
+        self.list_url = f"{self.base_url}/api/tags"
+
+    def get_available_models(self) -> List[str]:
+        """Get list of models available in Ollama"""
+        try:
+            # Try API first
+            response = requests.get(self.list_url, timeout=5)
+            if response.status_code == 200:
+                data = response.json()
+                return [m['name'] for m in data.get('models', [])]
+            
+            # Fallback to CLI
+            result = subprocess.run("ollama list", shell=True, capture_output=True, text=True, timeout=5)
+            models = []
+            for line in result.stdout.split('\n')[1:]:  # Skip header
+                if line.strip():
+                    models.append(line.split()[0])
+            return models
+        except Exception:
+            return []
+
+    def chat(self, messages: List[Dict], model: str, stream: bool = True) -> Generator[str, None, str]:
+        """Call Ollama API with streaming"""
+        try:
+            response = requests.post(self.chat_url, json={
+                "model": model,
+                "messages": messages,
+                "stream": stream
+            }, stream=stream, timeout=60)
+            response.raise_for_status()
+            
+            full_response = ""
+            if stream:
+                for line in response.iter_lines():
+                    if line:
+                        chunk = json.loads(line)
+                        if "message" in chunk and "content" in chunk["message"]:
+                            content = chunk["message"]["content"]
+                            full_response += content
+                            yield content
+                return full_response
+            else:
+                data = response.json()
+                return data.get("message", {}).get("content", "")
+                
+        except requests.exceptions.ConnectionError:
+            raise ConnectionError(f"Cannot connect to Ollama at {self.base_url}. Make sure it's running.")
+        except Exception as e:
+            raise Exception(f"Error calling Ollama: {str(e)}")
+
+    def select_best_model(self, user_input: str, available_models: List[str], default_model: str) -> str:
+        """Select best model based on task type"""
+        if not available_models:
+            return default_model
+            
+        # Model preferences
+        code_models = ["qwen2.5-coder", "mistral-nemo", "codellama", "deepseek-coder"]
+        general_models = ["llama3.2", "llama3.1", "mistral"]
+        
+        # Simple heuristic
+        code_keywords = ['code', 'script', 'program', 'function', 'debug', 'python', 'javascript']
+        is_code_task = any(k in user_input.lower() for k in code_keywords)
+        
+        target_list = code_models if is_code_task else general_models
+        
+        for target in target_list:
+            for available in available_models:
+                if target in available.lower():
+                    return available
+                    
+        return available_models[0] if available_models else default_model

build/lib/ollama_cli/core/sessions.py

@@ -0,0 +1,53 @@
+import os
+import json
+from datetime import datetime
+from typing import List, Dict, Optional
+
+SESSION_DIR = os.path.expanduser("~/.ollama-cli-sessions")
+
+def save_session(messages: List[Dict], session_name: Optional[str] = None) -> str:
+    """Save conversation session"""
+    os.makedirs(SESSION_DIR, exist_ok=True)
+    if not session_name:
+        session_name = datetime.now().strftime("%Y%m%d_%H%M%S")
+    
+    # Ensure filename is safe
+    safe_name = "".join([c for c in session_name if c.isalnum() or c in (' ', '.', '_', '-')]).strip()
+    session_file = os.path.join(SESSION_DIR, f"{safe_name}.json")
+    
+    with open(session_file, 'w') as f:
+        json.dump({
+            "messages": messages, 
+            "timestamp": datetime.now().isoformat(),
+            "name": session_name
+        }, f, indent=2)
+    return session_file
+
+def load_session(session_name: str) -> Optional[List[Dict]]:
+    """Load conversation session"""
+    session_file = os.path.join(SESSION_DIR, f"{session_name}.json")
+    if not os.path.exists(session_file):
+        # Try without extension if name doesn't have it
+        if not session_name.endswith('.json'):
+            session_file = os.path.join(SESSION_DIR, f"{session_name}.json")
+            
+    if os.path.exists(session_file):
+        with open(session_file, 'r') as f:
+            data = json.load(f)
+            return data.get("messages", [])
+    return None
+
+def list_sessions() -> List[str]:
+    """List available sessions"""
+    if not os.path.exists(SESSION_DIR):
+        return []
+    sessions = [f.replace('.json', '') for f in os.listdir(SESSION_DIR) if f.endswith('.json')]
+    return sorted(sessions, reverse=True)
+
+def delete_session(session_name: str) -> bool:
+    """Delete a session"""
+    session_file = os.path.join(SESSION_DIR, f"{session_name}.json")
+    if os.path.exists(session_file):
+        os.remove(session_file)
+        return True
+    return False

build/lib/ollama_cli/integrations/lsp.py

@@ -0,0 +1,75 @@
+import subprocess
+import os
+import json
+from typing import Dict, Any, Optional
+
+LSP_SERVERS = {}
+
+def start_lsp_server(language: str, root_path: str = ".") -> str:
+    """Start a language server"""
+    lsp_commands = {
+        "python": ["pyright-langserver", "--stdio"],
+        "javascript": ["typescript-language-server", "--stdio"],
+        "typescript": ["typescript-language-server", "--stdio"],
+        "rust": ["rust-analyzer"],
+        "go": ["gopls"],
+    }
+    
+    if language not in lsp_commands:
+        return f"No LSP server configured for {language}"
+    
+    try:
+        process = subprocess.Popen(
+            lsp_commands[language],
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True,
+            cwd=os.path.expanduser(root_path)
+        )
+        
+        # Initialize
+        init_request = {
+            "jsonrpc": "2.0",
+            "id": 1,
+            "method": "initialize",
+            "params": {
+                "processId": os.getpid(),
+                "rootUri": f"file://{os.path.abspath(os.path.expanduser(root_path))}",
+                "capabilities": {}
+            }
+        }
+        
+        msg = json.dumps(init_request)
+        process.stdin.write(f"Content-Length: {len(msg)}\r\n\r\n{msg}")
+        process.stdin.flush()
+        
+        LSP_SERVERS[language] = process
+        return f"Started LSP server for {language}"
+    except Exception as e:
+        return f"Error starting LSP: {str(e)}"
+
+def lsp_goto_definition(language: str, file_path: str, line: int, character: int) -> str:
+    """Get definition location"""
+    if language not in LSP_SERVERS:
+        return "LSP server not started"
+    
+    try:
+        process = LSP_SERVERS[language]
+        request = {
+            "jsonrpc": "2.0",
+            "id": 2,
+            "method": "textDocument/definition",
+            "params": {
+                "textDocument": {"uri": f"file://{os.path.abspath(file_path)}"},
+                "position": {"line": line, "character": character}
+            }
+        }
+        
+        msg = json.dumps(request)
+        process.stdin.write(f"Content-Length: {len(msg)}\r\n\r\n{msg}")
+        process.stdin.flush()
+        
+        return "Definition lookup sent (response parsing not implemented)"
+    except Exception as e:
+        return f"LSP error: {str(e)}"

build/lib/ollama_cli/integrations/mcp.py

@@ -0,0 +1,103 @@
+import subprocess
+import json
+import os
+from typing import Dict, Any, Optional, List
+
+MCP_SERVERS = {}
+MCP_TOOLS = {}
+
+def connect_mcp_server(name: str, command: str, args: Optional[List[str]] = None) -> str:
+    """Connect to an MCP server via stdio"""
+    try:
+        cmd = [command] + (args or [])
+        process = subprocess.Popen(
+            cmd,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True,
+            bufsize=1
+        )
+        
+        # Send initialize request
+        init_request = {
+            "jsonrpc": "2.0",
+            "id": 1,
+            "method": "initialize",
+            "params": {
+                "protocolVersion": "2024-11-05",
+                "capabilities": {},
+                "clientInfo": {"name": "ollama-cli", "version": "3.0"}
+            }
+        }
+        
+        process.stdin.write(json.dumps(init_request) + "\n")
+        process.stdin.flush()
+        
+        # Read response
+        response = process.stdout.readline()
+        if response:
+            data = json.loads(response)
+            if "result" in data:
+                MCP_SERVERS[name] = process
+                
+                # List tools
+                tools_request = {
+                    "jsonrpc": "2.0",
+                    "id": 2,
+                    "method": "tools/list"
+                }
+                process.stdin.write(json.dumps(tools_request) + "\n")
+                process.stdin.flush()
+                
+                tools_response = process.stdout.readline()
+                if tools_response:
+                    tools_data = json.loads(tools_response)
+                    if "result" in tools_data and "tools" in tools_data["result"]:
+                        for tool in tools_data["result"]["tools"]:
+                            tool_name = f"mcp_{name}_{tool['name']}"
+                            MCP_TOOLS[tool_name] = {
+                                "server": name,
+                                "name": tool["name"],
+                                "description": tool.get("description", ""),
+                                "schema": tool.get("inputSchema", {})
+                            }
+                
+                return f"Connected to MCP server '{name}' with {len([t for t in MCP_TOOLS if t.startswith(f'mcp_{name}_')])} tools"
+        
+        return f"Failed to initialize MCP server '{name}'"
+    except Exception as e:
+        return f"Error connecting to MCP server: {str(e)}"
+
+def call_mcp_tool(server_name: str, tool_name: str, arguments: Dict[str, Any]) -> str:
+    """Call a tool on an MCP server"""
+    try:
+        if server_name not in MCP_SERVERS:
+            return f"Error: MCP server '{server_name}' not connected"
+        
+        process = MCP_SERVERS[server_name]
+        
+        request = {
+            "jsonrpc": "2.0",
+            "id": 3,
+            "method": "tools/call",
+            "params": {
+                "name": tool_name,
+                "arguments": arguments
+            }
+        }
+        
+        process.stdin.write(json.dumps(request) + "\n")
+        process.stdin.flush()
+        
+        response = process.stdout.readline()
+        if response:
+            data = json.loads(response)
+            if "result" in data:
+                return json.dumps(data["result"], indent=2)
+            elif "error" in data:
+                return f"MCP Error: {data['error']}"
+        
+        return "No response from MCP server"
+    except Exception as e:
+        return f"Error calling MCP tool: {str(e)}"

build/lib/ollama_cli/integrations/notify.py

@@ -0,0 +1,64 @@
+import requests
+import json
+import threading
+from typing import Callable, List, Dict
+
+def send_notification(config: Dict, title: str, message: str, priority: str = "default"):
+    """Send notification via ntfy.sh"""
+    ntfy_config = config.get("ntfy", {})
+    
+    if not ntfy_config.get("enabled") or not ntfy_config.get("topic"):
+        return
+    
+    try:
+        server = ntfy_config.get("server", "https://ntfy.sh")
+        topic = ntfy_config["topic"]
+        url = f"{server}/{topic}"
+        
+        requests.post(url, 
+            data=message.encode('utf-8'),
+            headers={
+                "Title": title,
+                "Priority": priority
+            },
+            timeout=5
+        )
+    except:
+        pass
+
+def ntfy_listener(config: Dict, on_message: Callable[[str], str]):
+    """Listen for ntfy notifications and process them"""
+    ntfy_config = config.get("ntfy", {})
+    
+    if not ntfy_config.get("enabled") or not ntfy_config.get("topic"):
+        return
+    
+    server = ntfy_config.get("server", "https://ntfy.sh")
+    topic = ntfy_config["topic"]
+    url = f"{server}/{topic}/json"
+    
+    try:
+        response = requests.get(url, stream=True, timeout=None)
+        for line in response.iter_lines():
+            if line:
+                data = json.loads(line)
+                if data.get("event") == "message":
+                    title = data.get("title", "")
+                    message = data.get("message", "")
+                    
+                    # Skip messages sent by this script
+                    if title in ["Response", "Ollama CLI", "File Created", "Command Complete"]:
+                        continue
+                    
+                    # Process message
+                    response_text = on_message(message)
+                    
+                    # Send response back
+                    send_notification(config, "Response", response_text[:1000])
+    except:
+        pass
+
+def start_notify_thread(config: Dict, on_message: Callable[[str], str]):
+    thread = threading.Thread(target=ntfy_listener, args=(config, on_message), daemon=True)
+    thread.start()
+    return thread

build/lib/ollama_cli/main.py

@@ -0,0 +1,433 @@
+"""
+Ollama CLI v3.0
+License: MIT
+Author: Gemini CLI
+"""
+
+import sys
+import os
+import json
+import re
+import logging
+from typing import List, Dict, Optional, Tuple
+
+# Setup logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler(os.path.expanduser("~/.ollama-cli.log")),
+    ]
+)
+logger = logging.getLogger("ollama-cli")
+
+# Add current directory to path
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from ollama_cli.core.config import load_config, save_config, update_config
+from ollama_cli.core.ollama import OllamaClient
+from ollama_cli.core.sessions import save_session, load_session, list_sessions
+from ollama_cli.ui.formatter import console, print_markdown, print_error, print_status, StreamingDisplay
+from ollama_cli.ui.repl import REPL
+from ollama_cli.tools.base import registry
+import ollama_cli.tools.filesystem
+import ollama_cli.tools.system
+import ollama_cli.tools.web
+import ollama_cli.tools.git
+import ollama_cli.tools.code
+import ollama_cli.tools.knowledge
+import ollama_cli.tools.memory
+import ollama_cli.tools.execution
+import ollama_cli.tools.media
+from ollama_cli.integrations.mcp import connect_mcp_server, call_mcp_tool, MCP_TOOLS
+from ollama_cli.integrations.lsp import start_lsp_server, lsp_goto_definition
+from ollama_cli.integrations.notify import start_notify_thread, send_notification
+
+VERSION = "3.0.0"
+
+class OllamaCLI:
+    def __init__(self):
+        self.config = load_config()
+        self.client = OllamaClient(self.config.get("ollama_url"))
+        self.repl = REPL()
+        self.messages = []
+        self.available_models = []
+        self.current_model = self.config.get("default_model", "llama3.2")
+        self.system_prompt = self._build_system_prompt()
+        self.max_tool_iterations = 5
+
+    def _build_system_prompt(self) -> str:
+        base_prompt = """You are a highly capable AI assistant powered by Ollama. 
+You have access to a variety of tools to help you complete tasks.
+
+CRITICAL RULES:
+1. When you need to use a tool, you MUST use the EXACT format below.
+2. Output ONLY the tool call. DO NOT explain what you are doing.
+3. DO NOT repeat a tool call if you have already received a result for it.
+4. If you have the answer, just give it. Do not use tools unless necessary.
+
+<tool_call>
+<tool_name>name_of_tool</tool_name>
+<parameters>{"param": "value"}</parameters>
+</tool_call>
+
+You can call multiple tools in one response by repeating the block above."""
+        
+        tool_desc = registry.generate_system_prompt_snippet()
+        
+        # Add MCP tools if any
+        if MCP_TOOLS:
+            tool_desc += "\nMCP Tools:\n"
+            for name, info in MCP_TOOLS.items():
+                tool_desc += f"- {name}: {info['description']}\n"
+        
+        return f"{base_prompt}\n\n{tool_desc}"
+
+    def reset_messages(self):
+        self.messages = [{"role": "system", "content": self.system_prompt}]
+
+    def handle_command(self, user_input: str) -> bool:
+        """Handle slash commands."""
+        if not user_input.startswith('/'):
+            return False
+            
+        parts = user_input.split()
+        cmd = parts[0].lower()
+        
+        try:
+            if cmd == '/help':
+                help_text = """
+[bold cyan]Ollama CLI v3.0 Help[/bold cyan]
+
+[bold]General Commands:[/bold]
+  /help           - Show this help message
+  /quit           - Exit the CLI
+  /clear          - Clear conversation history
+
+[bold]Model & Sessions:[/bold]
+  /models         - List available models
+  /model <name>   - Switch current model
+  /sessions       - List saved sessions
+  /save [name]    - Save current session
+  /load <name>    - Load a saved session
+
+[bold]Core Agent Tools:[/bold]
+  [blue]Filesystem:[/blue] read_file, write_file, list_directory, grep_search, get_tree
+  [blue]Code & Python:[/blue] run_python, replace_text, code_analyze_file, run_linter
+  [blue]Web:[/blue] web_search, read_url
+  [blue]Media:[/blue] generate_image, speak_text
+  [blue]Knowledge:[/blue] kb_add, kb_search, remember_fact, recall_facts, clear_memory
+
+[bold]Integrations:[/bold]
+  /mcp connect <name> <cmd> [args] - Connect MCP server
+  /lsp start <lang> [path]         - Start LSP server
+  /notify setup <topic>            - Setup ntfy.sh remote control
+
+[bold]Configuration:[/bold]
+  /config ollama <url> - Set Ollama server URL (default: http://localhost:11434)
+  /config comfy <url>  - Set ComfyUI server URL (default: http://127.0.0.1:8188)
+  /config piper_path <path>  - Set path to Piper binary
+  /config piper_model <path> - Set path to Piper voice model
+"""
+                console.print(help_text)
+            elif cmd == '/config':
+                if len(parts) == 1:
+                    cfg = load_config()
+                    config_display = f"""
+[bold cyan]Current Configuration:[/bold cyan]
+  [blue]Ollama URL:[/blue]  {cfg.get('ollama_url')}
+  [blue]ComfyUI URL:[/blue] {cfg.get('comfy_url')}
+  [blue]Image Model:[/blue] {cfg.get('image_model')}
+  [blue]Piper Path:[/blue]  {cfg.get('piper', {}).get('path')}
+  [blue]Piper Model:[/blue] {cfg.get('piper', {}).get('model')}
+  [blue]Default Model:[/blue] {cfg.get('default_model')}
+"""
+                    console.print(config_display)
+                elif len(parts) > 2:
+                    subcmd = parts[1].lower()
+                    val = parts[2]
+                    if subcmd == 'ollama':
+                        update_config("ollama_url", val)
+                        print_status(f"Ollama URL updated to: {val}")
+                        self.client = OllamaClient(val)
+                    elif subcmd == 'comfy':
+                        update_config("comfy_url", val)
+                        print_status(f"ComfyUI URL updated to: {val}")
+                    elif subcmd == 'piper_path':
+                        cfg = load_config()
+                        cfg["piper"]["path"] = val
+                        save_config(cfg)
+                        print_status(f"Piper binary path updated to: {val}")
+                    elif subcmd == 'piper_model':
+                        cfg = load_config()
+                        cfg["piper"]["model"] = val
+                        save_config(cfg)
+                        print_status(f"Piper model path updated to: {val}")
+                    else:
+                        print_error("Usage: /config <ollama|comfy|piper_path|piper_model> <value>")
+                else:
+                    print_error("Usage: /config <ollama|comfy|piper_path|piper_model> <value>")
+            elif cmd == '/quit':
+                print_status("Goodbye!")
+                sys.exit(0)
+            elif cmd == '/clear':
+                self.reset_messages()
+                print_status("History cleared.")
+            elif cmd == '/models':
+                self.available_models = self.client.get_available_models()
+                print_status(f"Available models: {', '.join(self.available_models)}")
+            elif cmd == '/model':
+                if len(parts) > 1:
+                    self.current_model = parts[1]
+                    update_config("default_model", self.current_model)
+                    print_status(f"Switched to model: {self.current_model}")
+                else:
+                    print_status(f"Current model: {self.current_model}")
+            elif cmd == '/sessions':
+                sessions = list_sessions()
+                print_status(f"Recent sessions: {', '.join(sessions[:10])}")
+            elif cmd == '/save':
+                name = parts[1] if len(parts) > 1 else None
+                path = save_session(self.messages, name)
+                print_status(f"Session saved to {path}")
+            elif cmd == '/load':
+                if len(parts) > 1:
+                    messages = load_session(parts[1])
+                    if messages:
+                        self.messages = messages
+                        print_status(f"Session '{parts[1]}' loaded.")
+                    else:
+                        print_error(f"Session '{parts[1]}' not found.")
+                else:
+                    print_error("Usage: /load <session_name>")
+            elif cmd == '/mcp':
+                if len(parts) > 3 and parts[1] == 'connect':
+                    name = parts[2]
+                    command = parts[3]
+                    args = parts[4:] if len(parts) > 4 else None
+                    result = connect_mcp_server(name, command, args)
+                    print_status(result)
+                    # Refresh system prompt with new tools
+                    self.system_prompt = self._build_system_prompt()
+                    self.reset_messages()
+                else:
+                    print_error("Usage: /mcp connect <name> <command> [args...]")
+            elif cmd == '/lsp':
+                if len(parts) > 2 and parts[1] == 'start':
+                    lang = parts[2]
+                    path = parts[3] if len(parts) > 3 else "."
+                    result = start_lsp_server(lang, path)
+                    print_status(result)
+                else:
+                    print_error("Usage: /lsp start <language> [path]")
+            elif cmd == '/notify':
+                if len(parts) > 2 and parts[1] == 'setup':
+                    topic = parts[2]
+                    self.config["ntfy"]["enabled"] = True
+                    self.config["ntfy"]["topic"] = topic
+                    save_config(self.config)
+                    start_notify_thread(self.config, self.process_remote_message)
+                    print_status(f"Notifications enabled for topic: {topic}")
+                else:
+                    print_error("Usage: /notify setup <topic>")
+            else:
+                print_error(f"Unknown command: {cmd}")
+        except Exception as e:
+            print_error(f"Command error: {e}")
+            
+        return True
+
+    def process_remote_message(self, message: str) -> str:
+        """Handle messages coming from ntfy.sh"""
+        temp_messages = self.messages + [{"role": "user", "content": message}]
+        try:
+            response = ""
+            for chunk in self.client.chat(temp_messages, self.current_model, stream=False):
+                response += chunk
+            return response
+        except Exception as e:
+            return f"Error: {e}"
+
+    def run(self):
+        console.print(f"[bold cyan]Ollama CLI v{VERSION}[/bold cyan]")
+        
+        # Initial model detection
+        try:
+            self.available_models = self.client.get_available_models()
+            if not self.available_models:
+                print_error("No models found. Make sure Ollama is running.")
+            else:
+                if self.current_model not in self.available_models:
+                    self.current_model = self.available_models[0]
+                print_status(f"Using model: [bold green]{self.current_model}[/bold green]")
+        except Exception as e:
+            print_error(f"Could not connect to Ollama: {e}")
+
+        self.reset_messages()
+        
+        # Start notification listener if enabled
+        if self.config.get("ntfy", {}).get("enabled"):
+            start_notify_thread(self.config, self.process_remote_message)
+            print_status(f"Notification listener active on topic: {self.config['ntfy']['topic']}")
+
+        while True:
+            user_input = self.repl.get_input()
+            
+            if not user_input:
+                continue
+                
+            if self.handle_command(user_input):
+                continue
+                
+            self.messages.append({"role": "user", "content": user_input})
+            self.process_chat_cycle()
+
+    def process_chat_cycle(self):
+        """The main loop for chat and tool execution."""
+        executed_tool_calls = set()
+        for iteration in range(self.max_tool_iterations):
+            full_response = ""
+            try:
+                print_status(f"Thinking ([dim]{self.current_model}[/dim])...")
+                with StreamingDisplay() as display:
+                    for chunk in self.client.chat(self.messages, self.current_model):
+                        display.update(chunk)
+                        full_response += chunk
+                
+                self.messages.append({"role": "assistant", "content": full_response})
+                
+                # Check for tool calls
+                tool_calls = self.parse_tool_calls(full_response)
+                if not tool_calls:
+                    break
+                
+                # Execute tool calls
+                results = []
+                for name, params in tool_calls:
+                    # Prevent identical tool call loops across the entire cycle
+                    call_key = f"{name}:{json.dumps(params, sort_keys=True)}"
+                    if call_key in executed_tool_calls:
+                        print_status(f"Skipping duplicate tool call: [dim]{name}[/dim]")
+                        continue
+                    executed_tool_calls.add(call_key)
+                    
+                    result = self.execute_tool(name, params)
+                    # Show result to user
+                    print_status(f"Result: [dim]{result}[/dim]")
+                    results.append(f"Tool Result ({name}):\n{result}")
+                
+                if not results:
+                    # If we had tool calls but they were all duplicates, we must stop
+                    break
+                    
+                # Add all results to conversation
+                self.messages.append({"role": "user", "content": "\n\n".join(results) + "\n\nTool execution complete. If the task is finished, provide a final response to the user. Do not repeat the tool call."})
+                
+                # If we made it here, loop again to let the model process results
+                
+            except Exception as e:
+                print_error(str(e))
+                logger.exception("Chat cycle error")
+                break
+
+    def parse_tool_calls(self, text: str) -> List[tuple]:
+        calls = []
+        
+        # 1. Try to find <tool_call> blocks (handles unclosed tags)
+        tc_blocks = re.findall(r'<tool_call>(.*?)(?:</tool_call>|$)', text, re.DOTALL)
+        if tc_blocks:
+            for block in tc_blocks:
+                if not block.strip(): continue
+                # Try to find tool_name tag (handles unclosed)
+                name_match = re.search(r'<tool_name>(.*?)(?:</tool_name>|$)', block, re.DOTALL)
+                name = name_match.group(1).strip() if name_match else None
+                
+                # Try to find parameters tag (handles unclosed)
+                params_match = re.search(r'<parameters>(.*?)(?:</parameters>|$)', block, re.DOTALL)
+                if name and params_match:
+                    try:
+                        params_str = params_match.group(1).strip()
+                        # Auto-fix unclosed JSON if needed
+                        if params_str.startswith('{') and not params_str.endswith('}'):
+                            params_str += '}'
+                        calls.append((name, json.loads(params_str)))
+                    except:
+                        # Last ditch: search for any JSON-like object in the parameters string
+                        json_match = re.search(r'(\{.*\})', params_str, re.DOTALL)
+                        if json_match:
+                            try: calls.append((name, json.loads(json_match.group(1))))
+                            except: pass
+        
+        # 2. If no <tool_call> blocks, try searching for tool-specific tags
+        if not calls:
+            for tool_name in registry.tools.keys():
+                # Handle <tool_name ... /> or <tool_name ... >
+                attr_pattern = fr'<{tool_name}\s+(.*?)[\s/]*>'
+                attr_matches = re.findall(attr_pattern, text, re.DOTALL)
+                for attr_str in attr_matches:
+                    attrs = {}
+                    kv_pairs = re.findall(r'(\w+)\s*=\s*["\'](.*?)["\']', attr_str)
+                    for k, v in kv_pairs:
+                        attrs[k] = v
+                    if attrs:
+                        calls.append((tool_name, attrs))
+                
+                # Handle <tool_name> {json} </tool_name>
+                block_pattern = fr'<{tool_name}>(.*?)(?:</{tool_name}>|$)'
+                block_matches = re.findall(block_pattern, text, re.DOTALL)
+                for b in block_matches:
+                    json_match = re.search(r'(\{.*\})', b, re.DOTALL)
+                    if json_match:
+                        try: calls.append((tool_name, json.loads(json_match.group(1))))
+                        except: pass
+        
+        # 3. Final fallback: look for tool_name followed by JSON { ... }
+        if not calls:
+            for tool_name in registry.tools.keys():
+                json_pattern = fr'{tool_name}\s*({{.*?}})'
+                json_matches = re.findall(json_pattern, text, re.DOTALL)
+                for json_str in json_matches:
+                    try:
+                        calls.append((tool_name, json.loads(json_str.strip())))
+                    except:
+                        pass
+
+        return calls
+
+    def execute_tool(self, name: str, params: Dict) -> str:
+        """Execute a tool (standard or MCP)."""
+        # Try MCP tools first
+        if name in MCP_TOOLS:
+            mcp_tool = MCP_TOOLS[name]
+            print_status(f"Executing MCP tool [bold blue]{mcp_tool['name']}[/bold blue]...")
+            return call_mcp_tool(mcp_tool["server"], mcp_tool["name"], params)
+        
+        # Try standard tools
+        tool = registry.get_tool(name)
+        if tool:
+            print_status(f"Executing [bold blue]{name}[/bold blue]...")
+            try:
+                result = tool.execute(**params)
+                # Notification for successful file/system ops
+                if name == "write_file" and "Successfully" in str(result):
+                    send_notification(self.config, "File Created", f"Path: {params.get('path')}")
+                return result
+            except Exception as e:
+                return f"Error executing tool: {e}"
+        
+        return f"Unknown tool: {name}"
+
+def main():
+    try:
+        cli = OllamaCLI()
+        cli.run()
+    except KeyboardInterrupt:
+        print_status("Interrupted by user. Exiting.")
+        sys.exit(0)
+    except Exception as e:
+        print_error(f"Fatal error: {e}")
+        logger.exception("Fatal error")
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main()

build/lib/ollama_cli/tools/base.py

@@ -0,0 +1,55 @@
+from typing import Dict, Any, Callable, List, Optional
+import json
+import inspect
+
+class BaseTool:
+    def __init__(self, name: str, description: str, parameters: Dict[str, Any]):
+        self.name = name
+        self.description = description
+        self.parameters = parameters
+
+    def execute(self, **kwargs) -> Any:
+        raise NotImplementedError
+
+class ToolRegistry:
+    def __init__(self):
+        self.tools: Dict[str, BaseTool] = {}
+
+    def register(self, tool: BaseTool):
+        self.tools[tool.name] = tool
+
+    def get_tool(self, name: str) -> Optional[BaseTool]:
+        return self.tools.get(name)
+
+    def list_tools(self) -> List[Dict[str, Any]]:
+        return [
+            {
+                "name": t.name,
+                "description": t.description,
+                "parameters": t.parameters
+            }
+            for t in self.tools.values()
+        ]
+
+    def generate_system_prompt_snippet(self) -> str:
+        snippet = "Available tools:\n"
+        for t in self.tools.values():
+            snippet += f"- {t.name}: {t.description}\n"
+            snippet += f"  Parameters: {json.dumps(t.parameters)}\n"
+        return snippet
+
+# Singleton registry
+registry = ToolRegistry()
+
+def tool(name: str, description: str, parameters: Dict[str, Any]):
+    """Decorator to register a function as a tool"""
+    def decorator(func: Callable):
+        class DecoratedTool(BaseTool):
+            def __init__(self):
+                super().__init__(name, description, parameters)
+            def execute(self, **kwargs):
+                return func(**kwargs)
+        
+        registry.register(DecoratedTool())
+        return func
+    return decorator

build/lib/ollama_cli/tools/code.py

@@ -0,0 +1,96 @@
+import os
+import subprocess
+from .base import tool
+
+@tool(
+    name="code_analyze_file",
+    description="Analyze code structure and suggest improvements",
+    parameters={
+        "file_path": {"type": "string", "description": "Path to the file to analyze"}
+    }
+)
+def code_analyze_file(file_path: str) -> str:
+    try:
+        with open(os.path.expanduser(file_path), 'r') as f:
+            content = f.read()
+        
+        lines = content.split('\n')
+        functions = [l for l in lines if 'def ' in l]
+        classes = [l for l in lines if 'class ' in l]
+        
+        issues = []
+        if len(lines) > 500:
+            issues.append(f"Large file ({len(lines)} lines) - consider splitting")
+        if len(functions) > 30:
+            issues.append(f"Many functions ({len(functions)}) - consider refactoring")
+        
+        return f"""File: {file_path}
+Lines: {len(lines)} | Functions: {len(functions)} | Classes: {len(classes)}
+
+Issues:
+{chr(10).join(f'- {i}' for i in issues) if issues else '- None detected'}"""
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool(
+    name="generate_readme",
+    description="Generate a README.md for the current project",
+    parameters={
+        "path": {"type": "string", "description": "Project root path", "default": "."}
+    }
+)
+def generate_readme(path: str = ".") -> str:
+    try:
+        project_name = os.path.basename(os.path.abspath(path))
+        readme_content = f"# {project_name}\n\nGenerated by Ollama CLI."
+        readme_path = os.path.join(path, "README.md")
+        with open(readme_path, 'w') as f:
+            f.write(readme_content)
+        return f"Generated README.md at {readme_path}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool(
+    name="replace_text",
+    description="Surgically replace text in a file",
+    parameters={
+        "path": {"type": "string", "description": "Path to the file"},
+        "old_text": {"type": "string", "description": "The exact text to find"},
+        "new_text": {"type": "string", "description": "The text to replace it with"}
+    }
+)
+def replace_text(path: str, old_text: str, new_text: str) -> str:
+    try:
+        expanded_path = os.path.expanduser(path)
+        with open(expanded_path, 'r') as f:
+            content = f.read()
+        
+        if old_text not in content:
+            return f"Error: The text to replace was not found in {path}"
+            
+        new_content = content.replace(old_text, new_text, 1) # Replace first occurrence
+        with open(expanded_path, 'w') as f:
+            f.write(new_content)
+        return f"Successfully updated {path}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool(
+    name="run_linter",
+    description="Run a linter on a file",
+    parameters={
+        "file_path": {"type": "string", "description": "Path to the file"},
+        "linter": {"type": "string", "description": "Linter to use (pylint|eslint|auto)", "default": "auto"}
+    }
+)
+def run_linter(file_path: str, linter: str = "auto") -> str:
+    try:
+        file_path = os.path.expanduser(file_path)
+        if linter == "auto":
+            ext = os.path.splitext(file_path)[1]
+            linter = "pylint" if ext == ".py" else "eslint"
+        
+        result = subprocess.run(f"{linter} {file_path}", shell=True, capture_output=True, text=True)
+        return result.stdout + result.stderr
+    except Exception as e:
+        return f"Error: {str(e)}"

build/lib/ollama_cli/tools/execution.py

@@ -0,0 +1,36 @@
+import subprocess
+import os
+import sys
+from .base import tool
+
+@tool(
+    name="run_python",
+    description="Execute a Python script or snippet",
+    parameters={
+        "code": {"type": "string", "description": "Python code to execute"},
+        "args": {"type": "string", "description": "Optional arguments", "default": ""}
+    }
+)
+def run_python(code: str, args: str = "") -> str:
+    try:
+        # Create a temp file
+        temp_file = ".ollama-cli-exec.py"
+        with open(temp_file, "w") as f:
+            f.write(code)
+        
+        cmd = f"{sys.executable} {temp_file} {args}"
+        result = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=30)
+        
+        output = result.stdout + result.stderr
+        
+        # Cleanup
+        if os.path.exists(temp_file):
+            os.remove(temp_file)
+            
+        if result.returncode == 0:
+            return f"Success:\n{output}" if output else "Success (no output)"
+        else:
+            return f"Error (Exit {result.returncode}):\n{output}"
+            
+    except Exception as e:
+        return f"Execution Error: {str(e)}"

build/lib/ollama_cli/tools/filesystem.py

@@ -0,0 +1,83 @@
+import os
+import subprocess
+from .base import tool
+
+@tool(
+    name="read_file",
+    description="Read the contents of a file",
+    parameters={
+        "path": {"type": "string", "description": "Path to the file"}
+    }
+)
+def read_file(path: str) -> str:
+    try:
+        with open(os.path.expanduser(path), 'r') as f:
+            return f.read()
+    except Exception as e:
+        return f"Error reading file: {str(e)}"
+
+@tool(
+    name="write_file",
+    description="Write content to a file",
+    parameters={
+        "path": {"type": "string", "description": "Path to the file"},
+        "content": {"type": "string", "description": "Content to write"}
+    }
+)
+def write_file(path: str, content: str) -> str:
+    try:
+        expanded_path = os.path.expanduser(path)
+        os.makedirs(os.path.dirname(expanded_path), exist_ok=True)
+        with open(expanded_path, 'w') as f:
+            f.write(content)
+        return f"Successfully written to {path}"
+    except Exception as e:
+        return f"Error writing file: {str(e)}"
+
+@tool(
+    name="list_directory",
+    description="List contents of a directory",
+    parameters={
+        "path": {"type": "string", "description": "Path to the directory", "default": "."}
+    }
+)
+def list_directory(path: str = ".") -> str:
+    try:
+        expanded = os.path.expanduser(path)
+        files = os.listdir(expanded)
+        return "\n".join(files) if files else "Directory is empty"
+    except Exception as e:
+        return f"Error listing directory: {str(e)}"
+
+@tool(
+    name="grep_search",
+    description="Search for a regular expression pattern in file contents",
+    parameters={
+        "pattern": {"type": "string", "description": "The regex pattern to search for"},
+        "path": {"type": "string", "description": "Directory to search in", "default": "."},
+        "include": {"type": "string", "description": "Glob pattern for files to include", "default": "*"}
+    }
+)
+def grep_search(pattern: str, path: str = ".", include: str = "*") -> str:
+    try:
+        cmd = f'grep -rE --include="{include}" "{pattern}" {path}'
+        result = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=20)
+        return result.stdout if result.stdout else "No matches found."
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool(
+    name="get_tree",
+    description="Show the directory structure as a tree",
+    parameters={
+        "path": {"type": "string", "description": "Root path", "default": "."},
+        "depth": {"type": "integer", "description": "Max depth", "default": 2}
+    }
+)
+def get_tree(path: str = ".", depth: int = 2) -> str:
+    try:
+        cmd = f"find {path} -maxdepth {depth} -not -path '*/.*'"
+        result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+        return result.stdout
+    except Exception as e:
+        return f"Error: {str(e)}"

build/lib/ollama_cli/tools/git.py

@@ -0,0 +1,52 @@
+import subprocess
+import requests
+from typing import Optional
+from .base import tool
+from ..core.config import load_config
+
+@tool(
+    name="git_operation",
+    description="Perform git operations (status, diff, commit, push, pull, list)",
+    parameters={
+        "operation": {"type": "string", "description": "Operation to perform (status|diff|commit|push|pull|list)"},
+        "message": {"type": "string", "description": "Commit message", "default": "Auto commit"}
+    }
+)
+def git_operation(operation: str, message: str = "Auto commit") -> str:
+    config = load_config()
+    git_config = config.get("git", {})
+    gitea_config = config.get("gitea", {})
+    
+    try:
+        if operation == "status":
+            result = subprocess.run("git status", shell=True, capture_output=True, text=True)
+        elif operation == "diff":
+            result = subprocess.run("git diff", shell=True, capture_output=True, text=True)
+        elif operation == "commit":
+            result = subprocess.run(f'git add -A && git commit -m "{message}"', 
+                                  shell=True, capture_output=True, text=True)
+        elif operation == "push":
+            result = subprocess.run("git push", shell=True, capture_output=True, text=True)
+        elif operation == "pull":
+            result = subprocess.run("git pull", shell=True, capture_output=True, text=True)
+        elif operation == "list":
+            if gitea_config.get("url") and gitea_config.get("token"):
+                gitea_url = gitea_config["url"].rstrip("/")
+                token = gitea_config["token"]
+                response = requests.get(
+                    f"{gitea_url}/api/v1/user/repos",
+                    headers={"Authorization": f"token {token}"},
+                    timeout=10
+                )
+                if response.status_code == 200:
+                    repos = response.json()
+                    return "\n".join([f"- {r['full_name']} ({r['clone_url']})" for r in repos])
+                return f"Gitea API error: {response.status_code}"
+            result = subprocess.run("find . -maxdepth 2 -name '.git' -type d | sed 's|/.git||'", 
+                                  shell=True, capture_output=True, text=True)
+        else:
+            return f"Unknown git operation: {operation}"
+        
+        return result.stdout + result.stderr
+    except Exception as e:
+        return f"Git error: {str(e)}"

build/lib/ollama_cli/tools/knowledge.py

@@ -0,0 +1,41 @@
+import json
+import os
+from .base import tool
+
+KB_FILE = os.path.expanduser("~/.ollama-cli-kb.json")
+
+def load_kb():
+    if os.path.exists(KB_FILE):
+        with open(KB_FILE, 'r') as f:
+            return json.load(f)
+    return {}
+
+def save_kb(kb):
+    with open(KB_FILE, 'w') as f:
+        json.dump(kb, f, indent=2)
+
+@tool(
+    name="kb_add",
+    description="Add content to the knowledge base",
+    parameters={
+        "key": {"type": "string", "description": "Search key"},
+        "content": {"type": "string", "description": "Information content"}
+    }
+)
+def kb_add(key: str, content: str) -> str:
+    kb = load_kb()
+    kb[key] = content
+    save_kb(kb)
+    return f"Added '{key}' to knowledge base"
+
+@tool(
+    name="kb_search",
+    description="Search the knowledge base",
+    parameters={
+        "query": {"type": "string", "description": "Search query"}
+    }
+)
+def kb_search(query: str) -> str:
+    kb = load_kb()
+    results = [f"{k}: {v[:100]}..." for k, v in kb.items() if query.lower() in k.lower() or query.lower() in v.lower()]
+    return "\n".join(results) if results else "No matches found"

build/lib/ollama_cli/tools/media.py

@@ -0,0 +1,183 @@
+import subprocess
+import os
+import sys
+import requests
+import json
+import random
+from .base import tool
+from ..core.config import load_config
+
+@tool(
+    name="generate_image",
+    description="Generate an image using the local Stable Diffusion workflow (ComfyUI)",
+    parameters={
+        "prompt": {"type": "string", "description": "The image description"}
+    }
+)
+def generate_image(prompt: str) -> str:
+    """Invokes the ComfyUI API directly with a predefined workflow"""
+    config = load_config()
+    comfy_url = config.get("comfy_url", "http://127.0.0.1:8188").rstrip("/")
+    image_model = config.get("image_model", "dreamshaper_8_pruned.safetensors")
+    
+    # Determine dimensions (SDXL prefers 1024x1024)
+    width, height = (512, 512)
+    if "xl" in image_model.lower():
+        width, height = (1024, 1024)
+
+    try:
+        # Check if ComfyUI is running
+        try:
+            requests.get(comfy_url, timeout=2)
+        except:
+            return f"Error: ComfyUI server ({comfy_url}) appears to be down. Please start it first or configure the URL with '/config comfy <url>'."
+
+        # Define the workflow directly
+        workflow = {
+            "1": {
+                "inputs": {"ckpt_name": image_model},
+                "class_type": "CheckpointLoaderSimple"
+            },
+            "2": {
+                "inputs": {
+                    "text": f"masterpiece, best quality, highly detailed, {prompt}",
+                    "clip": ["1", 1]
+                },
+                "class_type": "CLIPTextEncode"
+            },
+            "3": {
+                "inputs": {
+                    "text": "blurry, low quality, distorted, watermark, nsfw",
+                    "clip": ["1", 1]
+                },
+                "class_type": "CLIPTextEncode"
+            },
+            "4": {
+                "inputs": {"width": width, "height": height, "batch_size": 1},
+                "class_type": "EmptyLatentImage"
+            },
+            "5": {
+                "inputs": {
+                    "seed": random.randint(1, 1000000000), "steps": 20, "cfg": 7.0,
+                    "sampler_name": "dpmpp_2m", "scheduler": "karras",
+                    "denoise": 1.0, "model": ["1", 0],
+                    "positive": ["2", 0], "negative": ["3", 0],
+                    "latent_image": ["4", 0]
+                },
+                "class_type": "KSampler"
+            },
+            "6": {
+                "inputs": {"samples": ["5", 0], "vae": ["1", 2]},
+                "class_type": "VAEDecode"
+            },
+            "7": {
+                "inputs": {
+                    "filename_prefix": "ollama_cli_",
+                    "images": ["6", 0]
+                },
+                "class_type": "SaveImage"
+            }
+        }
+        
+        payload = {"prompt": workflow}
+        response = requests.post(f"{comfy_url}/prompt", json=payload, timeout=10)
+        
+        if response.status_code == 200:
+            data = response.json()
+            prompt_id = data.get('prompt_id', 'unknown')
+            return f"Image generation queued successfully on {comfy_url}.\nPrompt ID: {prompt_id}\nCheck your ComfyUI output folder for 'ollama_cli_' prefixed files."
+        else:
+            return f"Error form ComfyUI: {response.status_code} - {response.text}"
+            
+    except Exception as e:
+        return f"Error generating image: {str(e)}"
+
+@tool(
+    name="speak_text",
+    description="Convert text to speech using Piper TTS (high quality)",
+    parameters={
+        "text": {"type": "string", "description": "Text to speak"},
+        "output_file": {"type": "string", "description": "Output filename", "default": "output.wav"}
+    }
+)
+def speak_text(text: str, output_file: str = "output.wav") -> str:
+    """Uses the best available TTS engine (Kokoro > Piper > System)"""
+    config = load_config()
+    
+    # 1. Try Kokoro (Ultra-Realistic)
+    kokoro_python = os.path.expanduser(config.get("kokoro_path", "~/.ollama-cli/kokoro/venv/bin/python"))
+    if os.path.exists(kokoro_python):
+        try:
+            # Inline script to run in Kokoro venv
+            kokoro_script = f"""
+import sys
+import soundfile as sf
+import os
+try:
+    from kokoro import KPipeline
+    import torch
+except ImportError:
+    print("Dependencies missing")
+    sys.exit(1)
+
+text = sys.argv[1]
+output_file = sys.argv[2]
+
+# Initialize pipeline
+pipeline = KPipeline(lang_code='a') 
+generator = pipeline(text, voice='af_bella', speed=1)
+
+all_audio = []
+for gs, ps, audio in generator:
+    if audio is not None:
+        all_audio.append(audio)
+
+if all_audio:
+    import numpy as np
+    full_audio = np.concatenate(all_audio)
+    sf.write(output_file, full_audio, 24000)
+    print("Success")
+else:
+    print("No audio generated")
+    sys.exit(1)
+"""
+            # Run in venv
+            subprocess.run([kokoro_python, "-c", kokoro_script, text, output_file], 
+                           check=True, capture_output=True)
+            
+            if sys.platform == "darwin":
+                subprocess.run(["afplay", output_file])
+            return f"Audio saved to {output_file} and played (using Ultra-Realistic Kokoro TTS)"
+        except Exception as e:
+            # Continue to fallback
+            pass
+
+    # 2. Try Piper (High-Quality)
+    piper_config = config.get("piper", {})
+    piper_bin = os.path.expanduser(piper_config.get("path", "~/.ollama-cli/piper/piper"))
+    model_path = os.path.expanduser(piper_config.get("model", "~/.ollama-cli/piper/voice.onnx"))
+    
+    if os.path.exists(piper_bin) and os.path.exists(model_path):
+        try:
+            # Piper reads from stdin and writes to file
+            cmd = f'echo "{text}" | {piper_bin} --model {model_path} --output_file {output_file}'
+            subprocess.run(cmd, shell=True, check=True, capture_output=True)
+            
+            # Auto-play on macOS
+            if sys.platform == "darwin":
+                subprocess.run(["afplay", output_file])
+                
+            return f"Audio saved to {output_file} and played (using high-quality Piper TTS)"
+        except Exception as e:
+            pass
+    
+    # 3. Fallback to system 'say' command on macOS
+    if sys.platform == "darwin":
+        try:
+            subprocess.run(["say", "-o", output_file, text], check=True)
+            subprocess.run(["afplay", output_file])
+            return f"Audio saved to {output_file} and played (using system 'say' fallback)"
+        except Exception as e:
+            return f"Error using 'say': {e}"
+            
+    return "No compatible TTS engine found. Please run the installer."

build/lib/ollama_cli/tools/memory.py

@@ -0,0 +1,59 @@
+import json
+import os
+from .base import tool
+
+PROJECT_MEMORY_FILE = ".ollama-cli/memory.json"
+
+def load_project_memory():
+    if os.path.exists(PROJECT_MEMORY_FILE):
+        try:
+            with open(PROJECT_MEMORY_FILE, 'r') as f:
+                return json.load(f)
+        except:
+            pass
+    return {}
+
+def save_project_memory(memory):
+    os.makedirs(os.path.dirname(PROJECT_MEMORY_FILE), exist_ok=True)
+    with open(PROJECT_MEMORY_FILE, 'w') as f:
+        json.dump(memory, f, indent=2)
+
+@tool(
+    name="remember_fact",
+    description="Store a key piece of information about the project",
+    parameters={
+        "fact": {"type": "string", "description": "The fact to remember (e.g., 'API key is in .env', 'Main entry point is src/index.ts')"}
+    }
+)
+def remember_fact(fact: str) -> str:
+    memory = load_project_memory()
+    facts = memory.get("facts", [])
+    if fact not in facts:
+        facts.append(fact)
+        memory["facts"] = facts
+        save_project_memory(memory)
+        return f"Remembered: {fact}"
+    return "Fact already known."
+
+@tool(
+    name="recall_facts",
+    description="Recall all stored facts about the project",
+    parameters={}
+)
+def recall_facts() -> str:
+    memory = load_project_memory()
+    facts = memory.get("facts", [])
+    if not facts:
+        return "No project facts stored."
+    return "Project Facts:\n" + "\n".join(f"- {f}" for f in facts)
+
+@tool(
+    name="clear_memory",
+    description="Clear project memory",
+    parameters={}
+)
+def clear_memory() -> str:
+    if os.path.exists(PROJECT_MEMORY_FILE):
+        os.remove(PROJECT_MEMORY_FILE)
+        return "Project memory cleared."
+    return "Memory was already empty."

build/lib/ollama_cli/tools/system.py

@@ -0,0 +1,46 @@
+import subprocess
+import os
+from .base import tool
+
+@tool(
+    name="execute_bash",
+    description="Execute a bash command and return its output",
+    parameters={
+        "command": {"type": "string", "description": "The command to execute"}
+    }
+)
+def execute_bash(command: str) -> str:
+    # Basic safety check
+    dangerous = ['rm -rf /', 'dd if=', 'mkfs', ':(){:|:&};:']
+    if any(d in command for d in dangerous):
+        return f"⚠️ DANGEROUS COMMAND BLOCKED: {command}"
+    
+    try:
+        result = subprocess.run(
+            command, 
+            shell=True, 
+            capture_output=True, 
+            text=True, 
+            cwd=os.getcwd(), 
+            timeout=60
+        )
+        output = result.stdout + result.stderr
+        return f"Exit code: {result.returncode}\n{output}" if output else f"Exit code: {result.returncode} (no output)"
+    except subprocess.TimeoutExpired:
+        return "Error: Command timed out after 60 seconds"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool(
+    name="get_env_info",
+    description="Get information about the current system environment",
+    parameters={}
+)
+def get_env_info() -> str:
+    import sys
+    import platform
+    return f"""OS: {platform.system()} {platform.release()}
+Python: {sys.version}
+Shell: {os.environ.get('SHELL', 'unknown')}
+User: {os.environ.get('USER', 'unknown')}
+CWD: {os.getcwd()}"""

build/lib/ollama_cli/tools/web.py

@@ -0,0 +1,67 @@
+import requests
+import urllib.parse
+from .base import tool
+
+@tool(
+    name="web_search",
+    description="Search the web for information",
+    parameters={
+        "query": {"type": "string", "description": "The search query"}
+    }
+)
+def web_search(query: str) -> str:
+    """Enhanced web search with DuckDuckGo"""
+    try:
+        encoded = urllib.parse.quote(query)
+        # Use DuckDuckGo Instant Answer API
+        api_url = f"https://api.duckduckgo.com/?q={encoded}&format=json"
+        response = requests.get(api_url, timeout=10)
+        data = response.json()
+        
+        results = []
+        if data.get("AbstractText"):
+            results.append(f"Summary: {data['AbstractText']}")
+        
+        for topic in data.get("RelatedTopics", [])[:5]:
+            if isinstance(topic, dict) and "Text" in topic:
+                results.append(f"- {topic['Text']}")
+        
+        return "\n".join(results) if results else "No direct results found. Try a different query."
+    except Exception as e:
+        return f"Search error: {str(e)}"
+
+@tool(
+    name="read_url",
+    description="Read and extract text content from a URL",
+    parameters={
+        "url": {"type": "string", "description": "The URL to read"}
+    }
+)
+def read_url(url: str) -> str:
+    try:
+        response = requests.get(url, timeout=10)
+        response.raise_for_status()
+        
+        try:
+            from bs4 import BeautifulSoup
+            soup = BeautifulSoup(response.text, 'html.parser')
+            
+            # Remove scripts and styles
+            for script in soup(["script", "style"]):
+                script.decompose()
+                
+            text = soup.get_text()
+            
+            # Clean up whitespace
+            lines = (line.strip() for line in text.splitlines())
+            chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+            text = '\n'.join(chunk for chunk in chunks if chunk)
+            
+            return text[:10000] + ("\n... (truncated)" if len(text) > 10000 else "")
+            
+        except ImportError:
+            # Fallback if bs4 is missing (though we checked)
+            return response.text[:10000]
+            
+    except Exception as e:
+        return f"Error reading URL: {str(e)}"

build/lib/ollama_cli/ui/formatter.py

@@ -0,0 +1,40 @@
+from rich.console import Console
+from rich.markdown import Markdown
+from rich.panel import Panel
+from rich.live import Live
+from rich.text import Text
+from rich.syntax import Syntax
+from typing import Optional
+
+console = Console()
+
+def print_markdown(text: str):
+    console.print(Markdown(text))
+
+def print_panel(text: str, title: Optional[str] = None, style: str = "blue"):
+    console.print(Panel(text, title=title, border_style=style))
+
+def print_error(text: str):
+    console.print(f"[bold red]Error:[/bold red] {text}")
+
+def print_status(text: str):
+    console.print(f"[bold blue]>>>[/bold blue] {text}")
+
+class StreamingDisplay:
+    def __init__(self, title: Optional[str] = None):
+        self.text = ""
+        self.live = Live(Text(self.text), refresh_per_second=10)
+        self.title = title
+
+    def __enter__(self):
+        self.live.start()
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.live.stop()
+
+    def update(self, chunk: str):
+        self.text += chunk
+        # Try to parse markdown if it looks complete-ish, otherwise just show text
+        # For performance, we might just show raw text during streaming
+        self.live.update(Markdown(self.text) if "```" in self.text else Text(self.text))

build/lib/ollama_cli/ui/repl.py

@@ -0,0 +1,25 @@
+from prompt_toolkit import PromptSession
+from prompt_toolkit.history import FileHistory
+from prompt_toolkit.styles import Style
+from prompt_toolkit.formatted_text import HTML
+import os
+
+class REPL:
+    def __init__(self):
+        history_file = os.path.expanduser("~/.ollama-cli-history")
+        self.session = PromptSession(history=FileHistory(history_file))
+        self.style = Style.from_dict({
+            'prompt': 'ansicyan bold',
+            'command': 'ansigreen',
+        })
+
+    def get_input(self) -> str:
+        try:
+            return self.session.prompt(
+                HTML('<prompt><b>&gt; </b></prompt>'),
+                style=self.style
+            ).strip()
+        except KeyboardInterrupt:
+            return ""
+        except EOFError:
+            return "/quit"

install.sh

@@ -82,18 +82,51 @@ if [[ $REPLY =~ ^[Yy]$ ]]; then
 
     # 5. Download Image Generation Model
     echo ""
-    echo "[*] Downloading Image Generation Model (DreamShaper 8)..."
+    echo "-------------------------------------------"
+    echo "Select Image Generation Model:"
+    echo "1) DreamShaper 8 (Good quality, fast, ~2GB)"
+    echo "2) Juggernaut XL (Photo-realistic, high detail, ~6GB)"
+    read -p "Choose option (1 or 2): " MODEL_CHOICE
+    echo ""
+
     MODEL_DIR="$INSTALL_DIR/models/checkpoints"
     mkdir -p "$MODEL_DIR"
-    MODEL_PATH="$MODEL_DIR/dreamshaper_8_pruned.safetensors"
+
+    if [[ "$MODEL_CHOICE" == "2" ]]; then
+        MODEL_NAME="juggernaut_xl.safetensors"
+        MODEL_URL="https://huggingface.co/RunDiffusion/Juggernaut-XL-v9/resolve/main/Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors"
+        echo "[*] Downloading Juggernaut XL..."
+    else
+        MODEL_NAME="dreamshaper_8_pruned.safetensors"
+        MODEL_URL="https://huggingface.co/Lykon/DreamShaper/resolve/main/DreamShaper_8_pruned.safetensors"
+        echo "[*] Downloading DreamShaper 8..."
+    fi
+
+    MODEL_PATH="$MODEL_DIR/$MODEL_NAME"
     if [ ! -f "$MODEL_PATH" ]; then
-        echo "    This may take a few minutes (approx. 2GB)..."
+        echo "    This may take a few minutes..."
-        curl -L "https://huggingface.co/Lykon/DreamShaper/resolve/main/DreamShaper_8_pruned.safetensors" -o "$MODEL_PATH"
+        curl -L "$MODEL_URL" -o "$MODEL_PATH"
         echo "✅ Model downloaded."
     else
         echo "✅ Model already exists."
     fi
 
+    # Update config with the chosen model name
+    python3 -c "
+import json
+import os
+config_path = os.path.expanduser('~/.ollama-cli-config.json')
+if os.path.exists(config_path):
+    with open(config_path, 'r') as f:
+        config = json.load(f)
+else:
+    config = {}
+config['image_model'] = '$MODEL_NAME'
+config['comfy_output_path'] = os.path.expanduser('$INSTALL_DIR/output')
+with open(config_path, 'w') as f:
+    json.dump(config, f, indent=2)
+"
+
     echo ""
     echo "[!] To use Image Generation, you must start ComfyUI:"
     echo "    cd $INSTALL_DIR"

src/ollama_cli.egg-info/SOURCES.txt

@@ -20,9 +20,12 @@ src/ollama_cli/integrations/notify.py
 src/ollama_cli/tools/__init__.py
 src/ollama_cli/tools/base.py
 src/ollama_cli/tools/code.py
+src/ollama_cli/tools/execution.py
 src/ollama_cli/tools/filesystem.py
 src/ollama_cli/tools/git.py
 src/ollama_cli/tools/knowledge.py
+src/ollama_cli/tools/media.py
+src/ollama_cli/tools/memory.py
 src/ollama_cli/tools/system.py
 src/ollama_cli/tools/web.py
 src/ollama_cli/ui/__init__.py

src/ollama_cli/core/config.py

@@ -18,6 +18,12 @@ DEFAULT_CONFIG = {
     "mcp_servers": {},
     "ollama_url": "http://localhost:11434",
     "comfy_url": "http://localhost:9000",
+    "comfy_output_path": "~/ComfyUI/output",
+    "image_model": "dreamshaper_8_pruned.safetensors",
+    "piper": {
+        "path": "~/.ollama-cli/piper/piper",
+        "model": "~/.ollama-cli/piper/voice.onnx"
+    },
     "ntfy": {
         "enabled": False,
         "topic": "",

src/ollama_cli/main.py

@@ -60,13 +60,18 @@ class OllamaCLI:
         base_prompt = """You are a highly capable AI assistant powered by Ollama. 
 You have access to a variety of tools to help you complete tasks.
 
-When you need to use a tool, output a tool call in the following format:
+CRITICAL RULES:
+1. When you need to use a tool, you MUST use the EXACT format below.
+2. Output ONLY the tool call. DO NOT explain what you are doing.
+3. DO NOT repeat a tool call if you have already received a result for it.
+4. If you have the answer, just give it. Do not use tools unless necessary.
+
 <tool_call>
-<tool_name>tool_name</tool_name>
+<tool_name>name_of_tool</tool_name>
 <parameters>{"param": "value"}</parameters>
 </tool_call>
 
-You can call multiple tools in one response. Be precise and helpful."""
+You can call multiple tools in one response by repeating the block above."""
         
         tool_desc = registry.generate_system_prompt_snippet()
         
@@ -110,7 +115,7 @@ You can call multiple tools in one response. Be precise and helpful."""
   [blue]Filesystem:[/blue] read_file, write_file, list_directory, grep_search, get_tree
   [blue]Code & Python:[/blue] run_python, replace_text, code_analyze_file, run_linter
   [blue]Web:[/blue] web_search, read_url
-  [blue]Media:[/blue] generate_image, speak_text
+  [blue]Media:[/blue] generate_image, speak_text, get_comfy_status
   [blue]Knowledge:[/blue] kb_add, kb_search, remember_fact, recall_facts, clear_memory
 
 [bold]Integrations:[/bold]
@@ -119,12 +124,28 @@ You can call multiple tools in one response. Be precise and helpful."""
   /notify setup <topic>            - Setup ntfy.sh remote control
 
 [bold]Configuration:[/bold]
-  /config ollama <url> - Set Ollama server URL (default: http://localhost:11434)
+  /config ollama <url>       - Set Ollama server URL
-  /config comfy <url>  - Set ComfyUI server URL (default: http://127.0.0.1:8188)
+  /config comfy <url>        - Set ComfyUI server URL
+  /config comfy_output <path> - Set ComfyUI output folder path
+  /config piper_path <path>  - Set path to Piper binary
+  /config piper_model <path> - Set path to Piper voice model
 """
                 console.print(help_text)
             elif cmd == '/config':
-                if len(parts) > 2:
+                if len(parts) == 1:
+                    cfg = load_config()
+                    config_display = f"""
+[bold cyan]Current Configuration:[/bold cyan]
+  [blue]Ollama URL:[/blue]  {cfg.get('ollama_url')}
+  [blue]ComfyUI URL:[/blue] {cfg.get('comfy_url')}
+  [blue]Comfy Output:[/blue] {cfg.get('comfy_output_path')}
+  [blue]Image Model:[/blue] {cfg.get('image_model')}
+  [blue]Piper Path:[/blue]  {cfg.get('piper', {}).get('path')}
+  [blue]Piper Model:[/blue] {cfg.get('piper', {}).get('model')}
+  [blue]Default Model:[/blue] {cfg.get('default_model')}
+"""
+                    console.print(config_display)
+                elif len(parts) > 2:
                     subcmd = parts[1].lower()
                     val = parts[2]
                     if subcmd == 'ollama':
@@ -134,10 +155,23 @@ You can call multiple tools in one response. Be precise and helpful."""
                     elif subcmd == 'comfy':
                         update_config("comfy_url", val)
                         print_status(f"ComfyUI URL updated to: {val}")
+                    elif subcmd == 'comfy_output':
+                        update_config("comfy_output_path", val)
+                        print_status(f"ComfyUI output path updated to: {val}")
+                    elif subcmd == 'piper_path':
+                        cfg = load_config()
+                        cfg["piper"]["path"] = val
+                        save_config(cfg)
+                        print_status(f"Piper binary path updated to: {val}")
+                    elif subcmd == 'piper_model':
+                        cfg = load_config()
+                        cfg["piper"]["model"] = val
+                        save_config(cfg)
+                        print_status(f"Piper model path updated to: {val}")
                     else:
-                        print_error("Usage: /config <ollama|comfy> <url>")
+                        print_error("Usage: /config <ollama|comfy|comfy_output|piper_path|piper_model> <value>")
                 else:
-                    print_error("Usage: /config <ollama|comfy> <url>")
+                    print_error("Usage: /config <ollama|comfy|comfy_output|piper_path|piper_model> <value>")
             elif cmd == '/quit':
                 print_status("Goodbye!")
                 sys.exit(0)
@@ -255,6 +289,7 @@ You can call multiple tools in one response. Be precise and helpful."""
 
     def process_chat_cycle(self):
         """The main loop for chat and tool execution."""
+        executed_tool_calls = set()
         for iteration in range(self.max_tool_iterations):
             full_response = ""
             try:
@@ -274,11 +309,24 @@ You can call multiple tools in one response. Be precise and helpful."""
                 # Execute tool calls
                 results = []
                 for name, params in tool_calls:
+                    # Prevent identical tool call loops across the entire cycle
+                    call_key = f"{name}:{json.dumps(params, sort_keys=True)}"
+                    if call_key in executed_tool_calls:
+                        print_status(f"Skipping duplicate tool call: [dim]{name}[/dim]")
+                        continue
+                    executed_tool_calls.add(call_key)
+                    
                     result = self.execute_tool(name, params)
+                    # Show result to user
+                    print_status(f"Result: [dim]{result}[/dim]")
                     results.append(f"Tool Result ({name}):\n{result}")
                 
+                if not results:
+                    # If we had tool calls but they were all duplicates, we must stop
+                    break
+                    
                 # Add all results to conversation
-                self.messages.append({"role": "user", "content": "\n\n".join(results)})
+                self.messages.append({"role": "user", "content": "\n\n".join(results) + "\n\nTool execution complete. If the task is finished, provide a final response to the user. Do not repeat the tool call."})
                 
                 # If we made it here, loop again to let the model process results
                 
@@ -288,17 +336,67 @@ You can call multiple tools in one response. Be precise and helpful."""
                 break
 
     def parse_tool_calls(self, text: str) -> List[tuple]:
-        pattern = r'<tool_call>\s*<tool_name>(.*?)</tool_name>\s*<parameters>(.*?)</parameters>\s*</tool_call>'
-        matches = re.findall(pattern, text, re.DOTALL)
-        
         calls = []
-        for name, params_str in matches:
+        
-            name = name.strip()
+        # 1. Try to find <tool_call> blocks (handles unclosed tags)
-            try:
+        tc_blocks = re.findall(r'<tool_call>(.*?)(?:</tool_call>|$)', text, re.DOTALL)
-                params = json.loads(params_str.strip())
+        if tc_blocks:
-                calls.append((name, params))
+            for block in tc_blocks:
-            except Exception as e:
+                if not block.strip(): continue
-                print_error(f"Failed to parse parameters for {name}: {e}")
+                # Try to find tool_name tag (handles unclosed)
+                name_match = re.search(r'<tool_name>(.*?)(?:</tool_name>|$)', block, re.DOTALL)
+                name = name_match.group(1).strip() if name_match else None
+                
+                # Try to find parameters tag (handles unclosed)
+                params_match = re.search(r'<parameters>(.*?)(?:</parameters>|$)', block, re.DOTALL)
+                if name and params_match:
+                    try:
+                        params_str = params_match.group(1).strip()
+                        # Auto-fix unclosed JSON if needed
+                        if params_str.startswith('{') and not params_str.endswith('}'):
+                            params_str += '}'
+                        calls.append((name, json.loads(params_str)))
+                    except:
+                        # Last ditch: search for any JSON-like object in the parameters string
+                        json_match = re.search(r'(\{.*\})', params_str, re.DOTALL)
+                        if json_match:
+                            try: calls.append((name, json.loads(json_match.group(1))))
+                            except: pass
+        
+        # 2. If no <tool_call> blocks, try searching for tool-specific tags
+        if not calls:
+            for tool_name in registry.tools.keys():
+                # Handle <tool_name ... /> or <tool_name ... >
+                attr_pattern = fr'<{tool_name}\s+(.*?)[\s/]*>'
+                attr_matches = re.findall(attr_pattern, text, re.DOTALL)
+                for attr_str in attr_matches:
+                    attrs = {}
+                    kv_pairs = re.findall(r'(\w+)\s*=\s*["\'](.*?)["\']', attr_str)
+                    for k, v in kv_pairs:
+                        attrs[k] = v
+                    if attrs:
+                        calls.append((tool_name, attrs))
+                
+                # Handle <tool_name> {json} </tool_name>
+                block_pattern = fr'<{tool_name}>(.*?)(?:</{tool_name}>|$)'
+                block_matches = re.findall(block_pattern, text, re.DOTALL)
+                for b in block_matches:
+                    json_match = re.search(r'(\{.*\})', b, re.DOTALL)
+                    if json_match:
+                        try: calls.append((tool_name, json.loads(json_match.group(1))))
+                        except: pass
+        
+        # 3. Final fallback: look for tool_name followed by JSON { ... }
+        if not calls:
+            for tool_name in registry.tools.keys():
+                json_pattern = fr'{tool_name}\s*({{.*?}})'
+                json_matches = re.findall(json_pattern, text, re.DOTALL)
+                for json_str in json_matches:
+                    try:
+                        calls.append((tool_name, json.loads(json_str.strip())))
+                    except:
+                        pass
+
         return calls
 
     def execute_tool(self, name: str, params: Dict) -> str:

src/ollama_cli/tools/media.py

@@ -7,6 +7,56 @@ import random
 from .base import tool
 from ..core.config import load_config
 
+@tool(
+    name="generate_image",
+    description="Generate an image using the local Stable Diffusion workflow (ComfyUI)",
+    parameters={
+        "prompt": {"type": "string", "description": "The image description"}
+    }
+)
+@tool(
+    name="get_comfy_status",
+    description="Check the status of image generation jobs or the ComfyUI queue",
+    parameters={
+        "prompt_id": {"type": "string", "description": "Optional: Specific prompt ID to check", "default": ""}
+    }
+)
+def get_comfy_status(prompt_id: str = "") -> str:
+    """Queries the ComfyUI API for queue or history status"""
+    config = load_config()
+    comfy_url = config.get("comfy_url", "http://127.0.0.1:8188").rstrip("/")
+    
+    try:
+        if prompt_id:
+            # Check history for specific prompt
+            resp = requests.get(f"{comfy_url}/history/{prompt_id}", timeout=5)
+            if resp.status_code == 200:
+                history = resp.json()
+                if prompt_id in history:
+                    return f"Status for {prompt_id}: Completed. Result saved."
+            
+            # Check queue if not in history
+            resp = requests.get(f"{comfy_url}/queue", timeout=5)
+            if resp.status_code == 200:
+                queue_data = resp.json()
+                for job in queue_data.get("queue_running", []):
+                    if job[1] == prompt_id: return f"Status for {prompt_id}: Currently Running."
+                for job in queue_data.get("queue_pending", []):
+                    if job[1] == prompt_id: return f"Status for {prompt_id}: Pending in Queue."
+            
+            return f"Status for {prompt_id}: ID not found in current queue or history."
+        else:
+            # General queue status
+            resp = requests.get(f"{comfy_url}/queue", timeout=5)
+            if resp.status_code == 200:
+                queue_data = resp.json()
+                running = len(queue_data.get("queue_running", []))
+                pending = len(queue_data.get("queue_pending", []))
+                return f"ComfyUI Queue Status: {running} running, {pending} pending."
+            return f"Error: Could not retrieve queue from {comfy_url}"
+    except Exception as e:
+        return f"Error connecting to ComfyUI: {str(e)}"
+
 @tool(
     name="generate_image",
     description="Generate an image using the local Stable Diffusion workflow (ComfyUI)",
@@ -18,6 +68,12 @@ def generate_image(prompt: str) -> str:
     """Invokes the ComfyUI API directly with a predefined workflow"""
     config = load_config()
     comfy_url = config.get("comfy_url", "http://127.0.0.1:8188").rstrip("/")
+    image_model = config.get("image_model", "dreamshaper_8_pruned.safetensors")
+    
+    # Determine dimensions (SDXL prefers 1024x1024)
+    width, height = (512, 512)
+    if "xl" in image_model.lower():
+        width, height = (1024, 1024)
 
     try:
         # Check if ComfyUI is running
@@ -27,10 +83,9 @@ def generate_image(prompt: str) -> str:
             return f"Error: ComfyUI server ({comfy_url}) appears to be down. Please start it first or configure the URL with '/config comfy <url>'."
 
         # Define the workflow directly
-        # Based on the user's previous generate_image.py, but using the configured URL
         workflow = {
             "1": {
-                "inputs": {"ckpt_name": "dreamshaper_8_pruned.safetensors"},
+                "inputs": {"ckpt_name": image_model},
                 "class_type": "CheckpointLoaderSimple"
             },
             "2": {
@@ -48,7 +103,7 @@ def generate_image(prompt: str) -> str:
                 "class_type": "CLIPTextEncode"
             },
             "4": {
-                "inputs": {"width": 512, "height": 512, "batch_size": 1},
+                "inputs": {"width": width, "height": height, "batch_size": 1},
                 "class_type": "EmptyLatentImage"
             },
             "5": {
@@ -80,7 +135,44 @@ def generate_image(prompt: str) -> str:
         if response.status_code == 200:
             data = response.json()
             prompt_id = data.get('prompt_id', 'unknown')
-            return f"Image generation queued successfully on {comfy_url}.\nPrompt ID: {prompt_id}\nCheck your ComfyUI output folder for 'ollama_cli_' prefixed files."
+            
+            # Start monitoring for the new image
+            output_path = os.path.expanduser(config.get("comfy_output_path", "~/ComfyUI/output"))
+            
+            # Helper to find the newest file with our prefix
+            def find_newest_image():
+                import glob
+                files = glob.glob(os.path.join(output_path, "ollama_cli_*"))
+                if not files: return None
+                return max(files, key=os.path.getctime)
+
+            initial_newest = find_newest_image()
+            
+            # Polling loop (max 60 seconds)
+            import time
+            found_file = None
+            for _ in range(30):
+                # Check status via API
+                status_check = get_comfy_status(prompt_id)
+                if "Completed" in status_check:
+                    # Give filesystem a moment to sync
+                    time.sleep(1)
+                    current_newest = find_newest_image()
+                    if current_newest and current_newest != initial_newest:
+                        found_file = current_newest
+                        break
+                
+                time.sleep(2)
+            
+            if found_file:
+                # Open the image automatically
+                if sys.platform == "darwin":
+                    subprocess.run(["open", found_file])
+                else:
+                    subprocess.run(["xdg-open", found_file])
+                return f"Image generation complete!\nSaved to: {found_file}\nOpening image now..."
+            
+            return f"Image generation queued successfully on {comfy_url}.\nPrompt ID: {prompt_id}\nMonitoring timed out, but the image should appear in {output_path} soon."
         else:
             return f"Error form ComfyUI: {response.status_code} - {response.text}"
             
@@ -96,26 +188,83 @@ def generate_image(prompt: str) -> str:
     }
 )
 def speak_text(text: str, output_file: str = "output.wav") -> str:
-    """Uses the high-quality Piper TTS installed by the installer"""
+    """Uses the best available TTS engine (Kokoro > Piper > System)"""
-    piper_dir = os.path.expanduser("~/.ollama-cli/piper")
+    config = load_config()
-    piper_bin = os.path.join(piper_dir, "piper")
+    
-    model_path = os.path.join(piper_dir, "voice.onnx")
+    # 1. Try Kokoro (Ultra-Realistic)
+    kokoro_python = os.path.expanduser(config.get("kokoro_path", "~/.ollama-cli/kokoro/venv/bin/python"))
+    if os.path.exists(kokoro_python):
+        try:
+            # Inline script to run in Kokoro venv
+            kokoro_script = f"""
+import sys
+import soundfile as sf
+import os
+try:
+    from kokoro import KPipeline
+    import torch
+except ImportError:
+    print("Dependencies missing")
+    sys.exit(1)
+
+text = sys.argv[1]
+output_file = sys.argv[2]
+
+# Initialize pipeline
+pipeline = KPipeline(lang_code='a') 
+generator = pipeline(text, voice='af_bella', speed=1)
+
+all_audio = []
+for gs, ps, audio in generator:
+    if audio is not None:
+        all_audio.append(audio)
+
+if all_audio:
+    import numpy as np
+    full_audio = np.concatenate(all_audio)
+    sf.write(output_file, full_audio, 24000)
+    print("Success")
+else:
+    print("No audio generated")
+    sys.exit(1)
+"""
+            # Run in venv
+            subprocess.run([kokoro_python, "-c", kokoro_script, text, output_file], 
+                           check=True, capture_output=True)
+            
+            if sys.platform == "darwin":
+                subprocess.run(["afplay", output_file])
+            return f"Audio saved to {output_file} and played (using Ultra-Realistic Kokoro TTS)"
+        except Exception as e:
+            # Continue to fallback
+            pass
+
+    # 2. Try Piper (High-Quality)
+    piper_config = config.get("piper", {})
+    piper_bin = os.path.expanduser(piper_config.get("path", "~/.ollama-cli/piper/piper"))
+    model_path = os.path.expanduser(piper_config.get("model", "~/.ollama-cli/piper/voice.onnx"))
     
     if os.path.exists(piper_bin) and os.path.exists(model_path):
         try:
             # Piper reads from stdin and writes to file
             cmd = f'echo "{text}" | {piper_bin} --model {model_path} --output_file {output_file}'
             subprocess.run(cmd, shell=True, check=True, capture_output=True)
-            return f"Audio saved to {output_file} (using high-quality Piper TTS)"
-        except Exception as e:
-            return f"Error using Piper: {e}. Falling back to system TTS..."
             
-    # Fallback to simple 'say' command on macOS
+            # Auto-play on macOS
+            if sys.platform == "darwin":
+                subprocess.run(["afplay", output_file])
+                
+            return f"Audio saved to {output_file} and played (using high-quality Piper TTS)"
+        except Exception as e:
+            pass
+    
+    # 3. Fallback to system 'say' command on macOS
     if sys.platform == "darwin":
         try:
             subprocess.run(["say", "-o", output_file, text], check=True)
-            return f"Audio saved to {output_file} (using system 'say' fallback)"
+            subprocess.run(["afplay", output_file])
+            return f"Audio saved to {output_file} and played (using system 'say' fallback)"
         except Exception as e:
             return f"Error using 'say': {e}"
             
-    return "TTS engine not found. Please run the installer to set up Piper."
+    return "No compatible TTS engine found. Please run the installer."

src/ollama_cli/tools/memory.py

@@ -45,9 +45,7 @@ def recall_facts() -> str:
     facts = memory.get("facts", [])
     if not facts:
         return "No project facts stored."
-    return "Project Facts:
+    return "Project Facts:\n" + "\n".join(f"- {f}" for f in facts)
-" + "
-".join(f"- {f}" for f in facts)
 
 @tool(
     name="clear_memory",