PraisonAI 3.0.0__py3-none-any.whl

praisonai/scheduler/daemon_manager.py

@@ -0,0 +1,225 @@
+"""
+Daemon process manager for running schedulers in background.
+"""
+import os
+import sys
+import signal
+import subprocess
+from pathlib import Path
+from typing import Optional, Dict, List
+from datetime import datetime
+
+
+class DaemonManager:
+    """Manages daemon processes for schedulers."""
+    
+    def __init__(self, log_dir: Optional[Path] = None, max_log_size_mb: float = 10.0):
+        """
+        Initialize daemon manager.
+        
+        Args:
+            log_dir: Directory for log files. Defaults to ~/.praisonai/logs
+            max_log_size_mb: Maximum log file size in MB before rotation
+        """
+        if log_dir is None:
+            home = Path.home()
+            log_dir = home / ".praisonai" / "logs"
+        
+        self.log_dir = Path(log_dir)
+        self.log_dir.mkdir(parents=True, exist_ok=True)
+        self.max_log_size_bytes = int(max_log_size_mb * 1024 * 1024)
+    
+    def start_daemon(
+        self,
+        name: str,
+        task: str,
+        interval: str,
+        command: List[str]
+    ) -> int:
+        """
+        Start a daemon process.
+        
+        Args:
+            name: Daemon name
+            task: Task description
+            interval: Schedule interval
+            command: Command to run as list
+            
+        Returns:
+            Process ID
+        """
+        log_file = self.log_dir / f"{name}.log"
+        
+        # Open log file - use original working approach
+        with open(log_file, 'a') as log:
+            log.flush()
+            
+            # Start process as daemon
+            proc = subprocess.Popen(
+                command,
+                stdout=log,
+                stderr=subprocess.STDOUT,
+                stdin=subprocess.DEVNULL,
+                start_new_session=True,  # Detach from terminal
+                cwd=os.getcwd()
+            )
+        
+        return proc.pid
+    
+    def start_scheduler_daemon(
+        self,
+        name: str,
+        task: Optional[str] = None,
+        recipe_name: Optional[str] = None,
+        interval: str = "hourly",
+        max_cost: Optional[float] = None,
+        timeout: Optional[int] = None,
+        max_retries: int = 3
+    ) -> int:
+        """
+        Start a PraisonAI scheduler as daemon.
+        
+        Args:
+            name: Scheduler name
+            task: Task to schedule (mutually exclusive with recipe_name)
+            recipe_name: Recipe name to schedule (mutually exclusive with task)
+            interval: Schedule interval
+            max_cost: Maximum cost budget
+            timeout: Timeout per execution
+            max_retries: Maximum retry attempts
+            
+        Returns:
+            Process ID
+        """
+        # Build command - use CLI without --daemon flag (original working approach)
+        command = [
+            sys.executable,
+            "-m",
+            "praisonai.cli.main",
+            "schedule",
+        ]
+        
+        # Add task or recipe
+        if recipe_name:
+            command.append(recipe_name)  # Recipe name will be auto-detected
+        elif task:
+            command.append(task)
+        else:
+            raise ValueError("Either task or recipe_name must be provided")
+        
+        command.extend(["--interval", interval, "--max-retries", str(max_retries)])
+        
+        if timeout:
+            command.extend(["--timeout", str(timeout)])
+        
+        if max_cost:
+            command.extend(["--max-cost", str(max_cost)])
+        
+        display_task = recipe_name or task
+        return self.start_daemon(name, display_task, interval, command)
+    
+    def stop_daemon(self, pid: int, timeout: int = 10) -> bool:
+        """
+        Stop a daemon process gracefully.
+        
+        Args:
+            pid: Process ID
+            timeout: Timeout in seconds
+            
+        Returns:
+            True if stopped successfully
+        """
+        try:
+            # Try graceful shutdown first (SIGTERM)
+            os.kill(pid, signal.SIGTERM)
+            
+            # Wait for process to terminate
+            import time
+            for _ in range(timeout * 10):
+                try:
+                    os.kill(pid, 0)  # Check if still alive
+                    time.sleep(0.1)
+                except (OSError, ProcessLookupError):
+                    return True  # Process terminated
+            
+            # Force kill if still alive
+            try:
+                os.kill(pid, signal.SIGKILL)
+                time.sleep(0.2)  # Give it time to die
+            except (OSError, ProcessLookupError):
+                pass
+            
+            return True
+            
+        except (OSError, ProcessLookupError):
+            return False
+    
+    def get_status(self, pid: int) -> Optional[Dict]:
+        """
+        Get daemon process status.
+        
+        Args:
+            pid: Process ID
+            
+        Returns:
+            Status dictionary or None if not found
+        """
+        try:
+            os.kill(pid, 0)  # Check if process exists
+            
+            return {
+                "pid": pid,
+                "is_alive": True
+            }
+        except (OSError, ProcessLookupError):
+            return {
+                "pid": pid,
+                "is_alive": False
+            }
+    
+    def read_logs(self, name: str, lines: int = 50) -> Optional[str]:
+        """
+        Read daemon logs.
+        
+        Args:
+            name: Daemon name
+            lines: Number of lines to read from end
+            
+        Returns:
+            Log content or None if not found
+        """
+        log_file = self.log_dir / f"{name}.log"
+        
+        if not log_file.exists():
+            return None
+        
+        try:
+            with open(log_file) as f:
+                all_lines = f.readlines()
+                return ''.join(all_lines[-lines:])
+        except IOError:
+            return None
+    
+    def rotate_log(self, name: str) -> bool:
+        """
+        Rotate log file if it exceeds max size.
+        
+        Args:
+            name: Daemon name
+            
+        Returns:
+            True if rotated
+        """
+        log_file = self.log_dir / f"{name}.log"
+        
+        if not log_file.exists():
+            return False
+        
+        if log_file.stat().st_size > self.max_log_size_bytes:
+            # Rotate: rename to .log.1, .log.2, etc.
+            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+            rotated_file = self.log_dir / f"{name}.log.{timestamp}"
+            log_file.rename(rotated_file)
+            return True
+        
+        return False

praisonai/scheduler/state_manager.py

@@ -0,0 +1,155 @@
+"""
+Scheduler state manager for persistent storage of scheduler processes.
+"""
+import json
+import os
+import signal
+from pathlib import Path
+from typing import Dict, List, Optional
+from datetime import datetime
+
+
+class SchedulerStateManager:
+    """Manages persistent state for scheduler processes."""
+    
+    def __init__(self, state_dir: Optional[Path] = None):
+        """
+        Initialize state manager.
+        
+        Args:
+            state_dir: Directory to store state files. Defaults to ~/.praisonai/schedulers
+        """
+        if state_dir is None:
+            home = Path.home()
+            state_dir = home / ".praisonai" / "schedulers"
+        
+        self.state_dir = Path(state_dir)
+        self.state_dir.mkdir(parents=True, exist_ok=True)
+    
+    def save_state(self, name: str, state: Dict) -> None:
+        """
+        Save scheduler state to JSON file.
+        
+        Args:
+            name: Scheduler name
+            state: State dictionary to save
+        """
+        state_file = self.state_dir / f"{name}.json"
+        
+        with open(state_file, 'w') as f:
+            json.dump(state, f, indent=2)
+    
+    def load_state(self, name: str) -> Optional[Dict]:
+        """
+        Load scheduler state from JSON file.
+        
+        Args:
+            name: Scheduler name
+            
+        Returns:
+            State dictionary or None if not found
+        """
+        state_file = self.state_dir / f"{name}.json"
+        
+        if not state_file.exists():
+            return None
+        
+        try:
+            with open(state_file) as f:
+                return json.load(f)
+        except (json.JSONDecodeError, IOError):
+            return None
+    
+    def delete_state(self, name: str) -> bool:
+        """
+        Delete scheduler state file.
+        
+        Args:
+            name: Scheduler name
+            
+        Returns:
+            True if deleted, False if not found
+        """
+        state_file = self.state_dir / f"{name}.json"
+        
+        if state_file.exists():
+            state_file.unlink()
+            return True
+        
+        return False
+    
+    def list_all(self) -> List[Dict]:
+        """
+        List all scheduler states.
+        
+        Returns:
+            List of state dictionaries
+        """
+        states = []
+        
+        for state_file in self.state_dir.glob("*.json"):
+            try:
+                with open(state_file) as f:
+                    state = json.load(f)
+                    states.append(state)
+            except (json.JSONDecodeError, IOError):
+                continue
+        
+        return states
+    
+    def generate_unique_name(self, base_name: str = "scheduler") -> str:
+        """
+        Generate a unique scheduler name.
+        
+        Args:
+            base_name: Base name for the scheduler
+            
+        Returns:
+            Unique name like "scheduler-0", "scheduler-1", etc.
+        """
+        existing_states = self.list_all()
+        existing_names = {s.get("name", "") for s in existing_states}
+        
+        counter = 0
+        while True:
+            name = f"{base_name}-{counter}"
+            if name not in existing_names:
+                return name
+            counter += 1
+    
+    def is_process_alive(self, pid: int) -> bool:
+        """
+        Check if a process is still alive.
+        
+        Args:
+            pid: Process ID
+            
+        Returns:
+            True if process is alive, False otherwise
+        """
+        try:
+            # Send signal 0 to check if process exists
+            os.kill(pid, 0)
+            return True
+        except (OSError, ProcessLookupError):
+            return False
+    
+    def cleanup_dead_processes(self) -> int:
+        """
+        Clean up state files for dead processes.
+        
+        Returns:
+            Number of dead processes cleaned up
+        """
+        cleaned = 0
+        states = self.list_all()
+        
+        for state in states:
+            pid = state.get("pid")
+            name = state.get("name")
+            
+            if pid and name and not self.is_process_alive(pid):
+                self.delete_state(name)
+                cleaned += 1
+        
+        return cleaned

praisonai/scheduler/yaml_loader.py

@@ -0,0 +1,193 @@
+"""
+YAML loader for agent scheduler configuration.
+
+Loads agent and schedule configuration from agents.yaml files.
+"""
+
+import yaml
+import logging
+from typing import Dict, Any, Tuple
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+
+def load_agent_yaml_with_schedule(yaml_path: str) -> Tuple[Dict[str, Any], Dict[str, Any]]:
+    """
+    Load agents.yaml file and extract agent and schedule configuration.
+    
+    Args:
+        yaml_path: Path to agents.yaml file
+        
+    Returns:
+        Tuple of (agent_config, schedule_config)
+        
+    Raises:
+        FileNotFoundError: If YAML file doesn't exist
+        ValueError: If YAML is invalid or missing required fields
+        
+    Example YAML structure:
+        framework: praisonai
+        
+        agents:
+          - name: "AI News Monitor"
+            role: "News Analyst"
+            goal: "Monitor AI news"
+            instructions: "Search and summarize"
+            tools:
+              - search_tool
+            verbose: true
+        
+        task: "Search for latest AI news"
+        
+        schedule:
+          interval: "hourly"
+          max_retries: 3
+          run_immediately: true
+    """
+    yaml_path = Path(yaml_path)
+    
+    if not yaml_path.exists():
+        raise FileNotFoundError(f"YAML file not found: {yaml_path}")
+    
+    try:
+        with open(yaml_path, 'r') as f:
+            config = yaml.safe_load(f)
+    except yaml.YAMLError as e:
+        raise ValueError(f"Invalid YAML file: {e}")
+    
+    if not config:
+        raise ValueError("Empty YAML file")
+    
+    # Extract agent configuration
+    agent_config = {}
+    
+    # Get agents list (can be single agent or multiple)
+    agents = config.get('agents', [])
+    if not agents:
+        raise ValueError("No agents defined in YAML file")
+    
+    # Use first agent for scheduling (can be extended for multi-agent later)
+    if isinstance(agents, list):
+        agent_config = agents[0]
+    else:
+        agent_config = agents
+    
+    # Get task
+    task = config.get('task', '')
+    if not task:
+        # Try to get from agent's tasks
+        if 'tasks' in agent_config and agent_config['tasks']:
+            first_task = list(agent_config['tasks'].values())[0]
+            task = first_task.get('description', '')
+    
+    agent_config['task'] = task
+    
+    # Get framework (default to praisonai)
+    agent_config['framework'] = config.get('framework', 'praisonai')
+    
+    # Extract schedule configuration (optional)
+    schedule_section = config.get('schedule', {})
+    
+    # Set defaults for schedule if not provided
+    schedule_config = {
+        'interval': schedule_section.get('interval', 'hourly'),
+        'max_retries': schedule_section.get('max_retries', 3),
+        'run_immediately': schedule_section.get('run_immediately', False),
+        'timeout': schedule_section.get('timeout'),  # Optional timeout in seconds
+        'max_cost': schedule_section.get('max_cost', 1.00)  # Default $1.00 budget limit for safety
+    }
+    
+    logger.info(f"Loaded agent '{agent_config.get('name', 'Unknown')}' with schedule interval '{schedule_config['interval']}'")
+    
+    return agent_config, schedule_config
+
+
+def create_agent_from_config(agent_config: Dict[str, Any]) -> Any:
+    """
+    Create a PraisonAI Agent instance from configuration.
+    
+    Args:
+        agent_config: Agent configuration dictionary
+        
+    Returns:
+        Agent instance
+        
+    Raises:
+        ImportError: If praisonaiagents is not installed
+    """
+    try:
+        from praisonaiagents import Agent
+    except ImportError:
+        raise ImportError("praisonaiagents package is required. Install with: pip install praisonaiagents")
+    
+    # Extract agent parameters
+    name = agent_config.get('name', 'Scheduled Agent')
+    role = agent_config.get('role', '')
+    goal = agent_config.get('goal', '')
+    instructions = agent_config.get('instructions', agent_config.get('backstory', ''))
+    verbose = agent_config.get('verbose', False)
+    
+    # Handle tools
+    tools = []
+    tool_names = agent_config.get('tools', [])
+    
+    if tool_names:
+        # Try to import tools
+        for tool_name in tool_names:
+            try:
+                # Try common tool imports
+                if tool_name == 'search_tool' or tool_name == 'InternetSearchTool':
+                    try:
+                        from tools import search_tool
+                        tools.append(search_tool)
+                    except ImportError:
+                        logger.warning(f"Could not import {tool_name}, skipping")
+                # Add more tool imports as needed
+            except Exception as e:
+                logger.warning(f"Error loading tool {tool_name}: {e}")
+    
+    # Create agent
+    agent = Agent(
+        name=name,
+        role=role,
+        goal=goal,
+        instructions=instructions,
+        tools=tools,
+        verbose=verbose
+    )
+    
+    return agent
+
+
+def validate_schedule_config(schedule_config: Dict[str, Any]) -> None:
+    """
+    Validate schedule configuration.
+    
+    Args:
+        schedule_config: Schedule configuration dictionary
+        
+    Raises:
+        ValueError: If configuration is invalid
+    """
+    required_fields = ['interval']
+    for field in required_fields:
+        if field not in schedule_config:
+            raise ValueError(f"Missing required schedule field: {field}")
+    
+    # Validate interval format
+    interval = schedule_config['interval']
+    valid_intervals = ['hourly', 'daily']
+    
+    if interval not in valid_intervals:
+        # Check if it's a custom format (*/Nm, */Nh, */Ns, or plain number)
+        if not (interval.startswith('*/') or interval.isdigit()):
+            raise ValueError(
+                f"Invalid interval format: {interval}. "
+                f"Use 'hourly', 'daily', '*/30m', '*/6h', or seconds as number"
+            )
+    
+    # Validate max_retries
+    max_retries = schedule_config.get('max_retries', 3)
+    if not isinstance(max_retries, int) or max_retries < 0:
+        raise ValueError(f"max_retries must be a non-negative integer, got: {max_retries}")