Release v2.3.81

README.md

@@ -278,6 +278,12 @@ npm install praisonai
 | ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
 | ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
 | ↳ CLI Compare | [Example](examples/compare/cli_compare_basic.py) | [📖](https://docs.praison.ai/docs/cli/compare) |
+| ↳ Profile/Benchmark | [Example](#profile-benchmark) | [📖](https://docs.praison.ai/docs/cli/profile) |
+| ↳ Auto Mode | [Example](#auto-mode) | [📖](https://docs.praison.ai/docs/cli/auto) |
+| ↳ Init | [Example](#init) | [📖](https://docs.praison.ai/docs/cli/init) |
+| ↳ File Input | [Example](#file-input) | [📖](https://docs.praison.ai/docs/cli/file-input) |
+| ↳ Final Agent | [Example](#final-agent) | [📖](https://docs.praison.ai/docs/cli/final-agent) |
+| ↳ Max Tokens | [Example](#max-tokens) | [📖](https://docs.praison.ai/docs/cli/max-tokens) |
 | **🧪 Evaluation** | | |
 | ↳ Accuracy Evaluation | [Example](examples/eval/accuracy_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
 | ↳ Performance Evaluation | [Example](examples/eval/performance_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.3.76" \
+    "praisonai>=2.3.81" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.3.76" \
+    "praisonai>=2.3.81" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.3.76" \
+    "praisonai>=2.3.81" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

src/praisonai/README.md

@@ -278,6 +278,12 @@ npm install praisonai
 | ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
 | ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
 | ↳ CLI Compare | [Example](examples/compare/cli_compare_basic.py) | [📖](https://docs.praison.ai/docs/cli/compare) |
+| ↳ Profile/Benchmark | [Example](#profile-benchmark) | [📖](https://docs.praison.ai/docs/cli/profile) |
+| ↳ Auto Mode | [Example](#auto-mode) | [📖](https://docs.praison.ai/docs/cli/auto) |
+| ↳ Init | [Example](#init) | [📖](https://docs.praison.ai/docs/cli/init) |
+| ↳ File Input | [Example](#file-input) | [📖](https://docs.praison.ai/docs/cli/file-input) |
+| ↳ Final Agent | [Example](#final-agent) | [📖](https://docs.praison.ai/docs/cli/final-agent) |
+| ↳ Max Tokens | [Example](#max-tokens) | [📖](https://docs.praison.ai/docs/cli/max-tokens) |
 | **🧪 Evaluation** | | |
 | ↳ Accuracy Evaluation | [Example](examples/eval/accuracy_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |
 | ↳ Performance Evaluation | [Example](examples/eval/performance_example.py) | [📖](https://docs.praison.ai/docs/cli/eval) |

src/praisonai/praisonai.rb

@@ -3,8 +3,8 @@ class Praisonai < Formula
   
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.76.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.76.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.81.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.81.tar.gz | shasum -a 256`.split.first
     license "MIT"
   
     depends_on "[email protected]"

src/praisonai/praisonai/cli/features/at_mentions.py

@@ -105,6 +105,7 @@ class FileSearchService:
     - Fuzzy match file paths
     - Cache results with TTL
     - Respect .gitignore (basic)
+    - Support absolute paths (@/Users/...) and home paths (@~/...)
     """
     
     def __init__(
@@ -125,9 +126,10 @@ class FileSearchService:
         # Cache: query -> (results, timestamp)
         self._cache: Dict[str, Tuple[List[FileSuggestion], float]] = {}
         
-        # File list cache
+        # File list cache per directory
         self._file_list: Optional[List[str]] = None
         self._file_list_time: float = 0
+        self._file_list_dir: Optional[str] = None
     
     def _should_ignore(self, name: str) -> bool:
         """Check if file/dir should be ignored."""
@@ -136,20 +138,23 @@ class FileSearchService:
                 return True
         return False
     
-    def _get_file_list(self) -> List[str]:
+    def _get_file_list(self, search_dir: str = None) -> List[str]:
         """Get list of all files (cached)."""
         now = time.time()
+        target_dir = search_dir or self._root
         
-        # Return cached if fresh
-        if self._file_list is not None and (now - self._file_list_time) < self._cache_ttl:
+        # Return cached if fresh and same directory
+        if (self._file_list is not None and 
+            self._file_list_dir == target_dir and
+            (now - self._file_list_time) < self._cache_ttl):
             return self._file_list
         
         files = []
         
         try:
-            for root, dirs, filenames in os.walk(self._root):
+            for root, dirs, filenames in os.walk(target_dir):
                 # Calculate depth
-                rel_root = os.path.relpath(root, self._root)
+                rel_root = os.path.relpath(root, target_dir)
                 depth = 0 if rel_root == '.' else rel_root.count(os.sep) + 1
                 
                 if depth > self._max_depth:
@@ -161,19 +166,20 @@ class FileSearchService:
                 
                 # Add directories
                 for d in dirs:
-                    rel_path = os.path.relpath(os.path.join(root, d), self._root)
+                    rel_path = os.path.relpath(os.path.join(root, d), target_dir)
                     files.append(rel_path + os.sep)
                 
                 # Add files
                 for f in filenames:
                     if not self._should_ignore(f):
-                        rel_path = os.path.relpath(os.path.join(root, f), self._root)
+                        rel_path = os.path.relpath(os.path.join(root, f), target_dir)
                         files.append(rel_path)
         except OSError:
             pass
         
         self._file_list = files
         self._file_list_time = now
+        self._file_list_dir = target_dir
         return files
     
     def _fuzzy_match(self, text: str, query: str) -> int:
@@ -221,6 +227,11 @@ class FileSearchService:
         """
         Search for files matching query.
         
+        Supports:
+        - Relative paths: @file.txt, @src/main.py
+        - Home paths: @~/Documents, @~/.config
+        - Absolute paths: @/Users/name/file.txt, @/etc/hosts
+        
         Args:
             query: Search query (fuzzy matched)
             max_results: Maximum results to return
@@ -228,8 +239,51 @@ class FileSearchService:
         Returns:
             List of FileSuggestion sorted by score
         """
+        # Determine search directory based on query
+        search_dir = self._root
+        search_query = query
+        prefix = ""
+        
+        # Handle home directory paths (@~/)
+        if query.startswith('~'):
+            expanded = os.path.expanduser(query)
+            # Find the directory part and filename part
+            if os.path.isdir(expanded):
+                search_dir = expanded
+                search_query = ""
+                prefix = query.rstrip('/') + '/'
+            else:
+                parent = os.path.dirname(expanded)
+                if os.path.isdir(parent):
+                    search_dir = parent
+                    search_query = os.path.basename(expanded)
+                    prefix = os.path.dirname(query).rstrip('/') + '/'
+                else:
+                    # Just expand ~ and search from home
+                    search_dir = os.path.expanduser('~')
+                    search_query = query[2:] if query.startswith('~/') else query[1:]
+                    prefix = "~/"
+        
+        # Handle absolute paths (@/Users/..., @/etc/...)
+        elif query.startswith('/'):
+            if os.path.isdir(query):
+                search_dir = query
+                search_query = ""
+                prefix = query.rstrip('/') + '/'
+            else:
+                parent = os.path.dirname(query)
+                if os.path.isdir(parent):
+                    search_dir = parent
+                    search_query = os.path.basename(query)
+                    prefix = parent.rstrip('/') + '/'
+                else:
+                    # Search from root with the query
+                    search_dir = '/'
+                    search_query = query[1:]
+                    prefix = "/"
+        
         # Check cache
-        cache_key = f"{query}:{max_results}"
+        cache_key = f"{search_dir}:{search_query}:{max_results}"
         now = time.time()
         
         if cache_key in self._cache:
@@ -237,25 +291,26 @@ class FileSearchService:
             if (now - cached_time) < self._cache_ttl:
                 return results
         
-        # Get all files
-        all_files = self._get_file_list()
+        # Get all files from the appropriate directory
+        all_files = self._get_file_list(search_dir)
         
         # Score and filter
         scored: List[Tuple[int, str]] = []
         for path in all_files:
-            score = self._fuzzy_match(path, query)
+            score = self._fuzzy_match(path, search_query)
             if score > 0:
                 scored.append((score, path))
         
         # Sort by score descending
         scored.sort(key=lambda x: (-x[0], x[1]))
         
-        # Build results
+        # Build results with proper prefix
         results = []
         for score, path in scored[:max_results]:
             file_type = "directory" if path.endswith(os.sep) else "file"
+            display_path = prefix + path if prefix else path
             results.append(FileSuggestion(
-                path=path,
+                path=display_path,
                 file_type=file_type,
                 score=score
             ))

src/praisonai/praisonai/cli/features/compare.py

@@ -16,7 +16,7 @@ logger = logging.getLogger(__name__)
 
 COMPARE_MODES = {
     "basic": {},
-    "tools": {"tools": "internet_search"},
+    "tools": {"tools": "calculator,internet_search"},
     "research": {"research": True},
     "planning": {"planning": True},
     "memory": {"memory": True},
@@ -177,12 +177,13 @@ def save_compare_result(result: CompareResult, path: str) -> bool:
         return False
 
 
-def format_comparison_table(result: CompareResult) -> str:
+def format_comparison_table(result: CompareResult, show_responses: bool = True) -> str:
     """
-    Format comparison result as a table string.
+    Format comparison result as a table string with optional response display.
     
     Args:
         result: CompareResult to format
+        show_responses: Whether to show actual responses from each mode
         
     Returns:
         Formatted table string
@@ -190,10 +191,12 @@ def format_comparison_table(result: CompareResult) -> str:
     try:
         from rich.console import Console
         from rich.table import Table
+        from rich.panel import Panel
         from io import StringIO
         
         console = Console(file=StringIO(), force_terminal=True)
         
+        # Main comparison table
         table = Table(title=f"Comparison: {result.query[:50]}...")
         table.add_column("Mode", style="cyan")
         table.add_column("Time (ms)", style="green")
@@ -224,6 +227,26 @@ def format_comparison_table(result: CompareResult) -> str:
             )
         
         console.print(table)
+        
+        # Show responses if enabled
+        if show_responses:
+            console.print("\n[bold cyan]📝 Responses:[/bold cyan]")
+            for c in result.comparisons:
+                if c.error is None:
+                    # Truncate long responses
+                    response_preview = c.output[:500] + "..." if len(c.output) > 500 else c.output
+                    console.print(Panel(
+                        response_preview,
+                        title=f"[bold]{c.mode}[/bold] ({c.execution_time_ms:.0f}ms)",
+                        border_style="cyan"
+                    ))
+                else:
+                    console.print(Panel(
+                        f"[red]Error: {c.error}[/red]",
+                        title=f"[bold]{c.mode}[/bold]",
+                        border_style="red"
+                    ))
+        
         return console.file.getvalue()
     except ImportError:
         lines = [f"Comparison: {result.query}"]
@@ -231,6 +254,8 @@ def format_comparison_table(result: CompareResult) -> str:
         for c in result.comparisons:
             status = "OK" if c.error is None else f"ERROR: {c.error}"
             lines.append(f"{c.mode}: {c.execution_time_ms:.1f}ms - {status}")
+            if show_responses and c.error is None:
+                lines.append(f"  Response: {c.output[:200]}...")
         return "\n".join(lines)
 
 
@@ -407,13 +432,7 @@ class CompareHandler:
                     from praisonaiagents.tools import internet_search
                     tools.append(internet_search)
                 elif name == "calculator":
-                    def calculator(expression: str) -> str:
-                        """Evaluate a mathematical expression."""
-                        try:
-                            return str(eval(expression))
-                        except Exception as e:
-                            return f"Error: {e}"
-                    tools.append(calculator)
+                    tools.append(_calculator_tool)
             except ImportError:
                 logger.warning(f"Could not load tool: {name}")
         
@@ -466,3 +485,50 @@ class CompareHandler:
                 print(f"[red]Failed to save results to: {output_path}[/red]")
         
         return result
+
+
+def _calculator_tool(expression: str) -> str:
+    """
+    Evaluate a mathematical expression safely.
+    
+    Args:
+        expression: Mathematical expression to evaluate (e.g., "2+2", "15*3", "100/4")
+        
+    Returns:
+        The result of the calculation as a string
+    """
+    import ast
+    import operator
+    
+    # Safe operators
+    operators = {
+        ast.Add: operator.add,
+        ast.Sub: operator.sub,
+        ast.Mult: operator.mul,
+        ast.Div: operator.truediv,
+        ast.Pow: operator.pow,
+        ast.USub: operator.neg,
+        ast.UAdd: operator.pos,
+        ast.Mod: operator.mod,
+        ast.FloorDiv: operator.floordiv,
+    }
+    
+    def _eval(node):
+        if isinstance(node, ast.Constant):
+            return node.value
+        elif isinstance(node, ast.BinOp):
+            left = _eval(node.left)
+            right = _eval(node.right)
+            return operators[type(node.op)](left, right)
+        elif isinstance(node, ast.UnaryOp):
+            operand = _eval(node.operand)
+            return operators[type(node.op)](operand)
+        else:
+            raise ValueError(f"Unsupported operation: {type(node)}")
+    
+    try:
+        tree = ast.parse(expression, mode='eval')
+        result = _eval(tree.body)
+        return str(result)
+    except Exception as e:
+        return f"Error evaluating '{expression}': {e}"

src/praisonai/praisonai/cli/features/eval.py

@@ -26,42 +26,68 @@ class EvalHandler:
     
     def run_accuracy(
         self,
-        agent_file: str,
-        input_text: str,
-        expected_output: str,
+        agent_file: Optional[str] = None,
+        input_text: str = "",
+        expected_output: str = "",
         iterations: int = 1,
         model: Optional[str] = None,
-        output_file: Optional[str] = None
+        output_file: Optional[str] = None,
+        prompt: Optional[str] = None,
+        llm: Optional[str] = None
     ) -> Dict[str, Any]:
         """
         Run accuracy evaluation on an agent.
         
         Args:
-            agent_file: Path to agents.yaml file
+            agent_file: Path to agents.yaml file (optional if prompt is provided)
             input_text: Input to provide to the agent
             expected_output: Expected output to compare against
             iterations: Number of evaluation iterations
             model: LLM model for judging
             output_file: Path to save results
+            prompt: Direct prompt (alternative to agent_file)
+            llm: LLM model for the agent (when using prompt)
             
         Returns:
             Evaluation result dictionary
         """
         try:
             from praisonaiagents.eval import AccuracyEvaluator
-            from praisonai.agents_generator import AgentsGenerator
+            from praisonaiagents import Agent
         except ImportError as e:
             logger.error(f"Failed to import evaluation modules: {e}")
             return {"error": str(e)}
         
         try:
-            generator = AgentsGenerator(agent_file)
-            agents = generator.generate_agents()
-            
-            if not agents:
-                return {"error": "No agents found in configuration"}
-            
-            agent = agents[0] if isinstance(agents, list) else agents
+            # Create agent either from file or from prompt
+            if prompt:
+                # Direct prompt mode - create agent on the fly
+                agent = Agent(
+                    name="EvalAgent",
+                    role="Assistant",
+                    goal="Complete the given task",
+                    backstory="You are a helpful assistant.",
+                    llm=llm or model or "gpt-4o-mini",
+                    verbose=False
+                )
+                # Use prompt as input if input_text not provided
+                if not input_text:
+                    input_text = prompt
+            elif agent_file:
+                # Load from agents.yaml
+                try:
+                    from praisonai.agents_generator import AgentsGenerator
+                    generator = AgentsGenerator(agent_file)
+                    agents = generator.generate_agents()
+                    
+                    if not agents:
+                        return {"error": "No agents found in configuration"}
+                    
+                    agent = agents[0] if isinstance(agents, list) else agents
+                except Exception as e:
+                    return {"error": f"Failed to load agents from {agent_file}: {e}"}
+            else:
+                return {"error": "Either --agent or --prompt must be provided"}
             
             evaluator = AccuracyEvaluator(
                 agent=agent,
@@ -321,18 +347,49 @@ class EvalHandler:
         return batch_result
 
 
-def handle_eval_command(args) -> None:
+def handle_eval_command(args) -> int:
     """
     Handle the eval CLI command.
     
     Args:
-        args: Parsed command line arguments
+        args: Command line arguments (list or parsed namespace)
+        
+    Returns:
+        Exit code
     """
+    import argparse
+    
+    # If args is a list, parse it first
+    if isinstance(args, list):
+        parser = argparse.ArgumentParser(prog="praisonai eval")
+        subparsers = parser.add_subparsers(dest='eval_type')
+        add_eval_parser_subcommands(subparsers)
+        
+        try:
+            args = parser.parse_args(args)
+        except SystemExit:
+            return 1
+        
+        if not args.eval_type:
+            parser.print_help()
+            print("\n[bold]Examples:[/bold]")
+            print("  praisonai eval accuracy --prompt \"What is 2+2?\" --expected \"4\"")
+            print("  praisonai eval performance --agent agents.yaml --input \"Hello\"")
+            return 0
+    
     handler = EvalHandler(verbose=getattr(args, 'verbose', False))
     
     eval_type = getattr(args, 'eval_type', 'accuracy')
-    agent_file = getattr(args, 'agent', 'agents.yaml')
+    agent_file = getattr(args, 'agent', None)
     output_file = getattr(args, 'output', None)
+    prompt = getattr(args, 'prompt', None)
+    llm = getattr(args, 'llm', None)
+    
+    # If no agent file and no prompt, check if agents.yaml exists
+    if not agent_file and not prompt:
+        import os
+        if os.path.exists('agents.yaml'):
+            agent_file = 'agents.yaml'
     
     if eval_type == 'accuracy':
         result = handler.run_accuracy(
@@ -341,7 +398,9 @@ def handle_eval_command(args) -> None:
             expected_output=getattr(args, 'expected', ''),
             iterations=getattr(args, 'iterations', 1),
             model=getattr(args, 'model', None),
-            output_file=output_file
+            output_file=output_file,
+            prompt=prompt,
+            llm=llm
         )
     elif eval_type == 'performance':
         result = handler.run_performance(
@@ -384,12 +443,40 @@ def handle_eval_command(args) -> None:
         )
     else:
         print(f"Unknown evaluation type: {eval_type}")
-        return
+        return 1
     
     if 'error' in result:
         print(f"Error: {result['error']}")
+        return 1
     elif not getattr(args, 'quiet', False):
         print(json.dumps(result, indent=2))
+    
+    return 0
+
+
+def add_eval_parser_subcommands(subparsers) -> None:
+    """Add eval subcommand parsers to an existing subparsers object."""
+    accuracy_parser = subparsers.add_parser('accuracy', help='Run accuracy evaluation')
+    accuracy_parser.add_argument('--agent', '-a', help='Agent config file (optional if --prompt used)')
+    accuracy_parser.add_argument('--prompt', '-p', type=str, help='Direct prompt (alternative to --agent)')
+    accuracy_parser.add_argument('--llm', help='LLM model for agent (when using --prompt)')
+    accuracy_parser.add_argument('--input', '-i', help='Input text (defaults to --prompt if not provided)')
+    accuracy_parser.add_argument('--expected', '-e', required=True, help='Expected output')
+    accuracy_parser.add_argument('--iterations', '-n', type=int, default=1, help='Number of iterations')
+    accuracy_parser.add_argument('--model', '-m', help='Judge model')
+    accuracy_parser.add_argument('--output', '-o', help='Output file')
+    accuracy_parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
+    accuracy_parser.add_argument('--quiet', '-q', action='store_true', help='Suppress JSON output')
+    
+    perf_parser = subparsers.add_parser('performance', help='Run performance evaluation')
+    perf_parser.add_argument('--agent', '-a', default='agents.yaml', help='Agent config file')
+    perf_parser.add_argument('--input', '-i', default='Hello', help='Input text')
+    perf_parser.add_argument('--iterations', '-n', type=int, default=10, help='Number of iterations')
+    perf_parser.add_argument('--warmup', '-w', type=int, default=2, help='Warmup runs')
+    perf_parser.add_argument('--memory', action='store_true', default=True, help='Track memory')
+    perf_parser.add_argument('--output', '-o', help='Output file')
+    perf_parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
+    perf_parser.add_argument('--quiet', '-q', action='store_true', help='Suppress JSON output')
 
 
 def add_eval_parser(subparsers) -> None:
@@ -410,8 +497,10 @@ def add_eval_parser(subparsers) -> None:
         'accuracy',
         help='Run accuracy evaluation'
     )
-    accuracy_parser.add_argument('--agent', '-a', default='agents.yaml', help='Agent config file')
-    accuracy_parser.add_argument('--input', '-i', required=True, help='Input text')
+    accuracy_parser.add_argument('--agent', '-a', help='Agent config file (optional if --prompt used)')
+    accuracy_parser.add_argument('--prompt', '-p', help='Direct prompt (alternative to --agent)')
+    accuracy_parser.add_argument('--llm', help='LLM model for agent (when using --prompt)')
+    accuracy_parser.add_argument('--input', '-i', help='Input text (defaults to --prompt if not provided)')
     accuracy_parser.add_argument('--expected', '-e', required=True, help='Expected output')
     accuracy_parser.add_argument('--iterations', '-n', type=int, default=1, help='Number of iterations')
     accuracy_parser.add_argument('--model', '-m', help='Judge model')

src/praisonai/praisonai/cli/features/fast_context.py

@@ -3,12 +3,21 @@ Fast Context Handler for CLI.
 
 Provides codebase search capability using FastContext.
 Usage: praisonai "Find authentication code" --fast-context ./src
+
+Fast Context Strategy:
+1. Extract search keywords from natural language query using LLM
+2. Provide folder tree context to help understand codebase structure
+3. Use both file name search AND content search (ripgrep-style)
+4. Return relevant code snippets for context
 """
 
 import os
+import logging
 from typing import Any, Dict, Tuple, List
 from .base import FlagHandler
 
+logger = logging.getLogger(__name__)
+
 
 class FastContextHandler(FlagHandler):
     """
@@ -61,14 +70,208 @@ class FastContextHandler(FlagHandler):
         
         return True, ""
     
+    def _count_files_quick(self, path: str, max_count: int = 1000) -> int:
+        """Quickly count files in directory, stopping at max_count."""
+        count = 0
+        ignore_dirs = {'.git', '__pycache__', 'node_modules', '.venv', 'venv', '.cache', 'dist', 'build'}
+        
+        for root, dirs, files in os.walk(path):
+            dirs[:] = [d for d in dirs if d not in ignore_dirs and not d.startswith('.')]
+            count += len(files)
+            if count >= max_count:
+                return count
+        return count
+    
+    def _get_folder_tree(self, path: str, max_depth: int = 2) -> str:
+        """
+        Get a compact folder tree structure for context.
+        
+        Optimized for large directories:
+        - Limits depth to max_depth (default 2)
+        - Shows max 10 files per directory
+        - Truncates total output to 50 lines
+        - Skips common non-code directories
+        """
+        # Quick check for very large directories
+        file_count = self._count_files_quick(path, 500)
+        if file_count >= 500:
+            # For large directories, reduce depth and show summary
+            max_depth = 1
+            logger.debug(f"Large directory detected ({file_count}+ files), reducing tree depth")
+        
+        tree_lines = []
+        ignore_dirs = {'.git', '__pycache__', 'node_modules', '.venv', 'venv', '.cache', 'dist', 'build', 'coverage', '.pytest_cache', '.mypy_cache', 'eggs', '*.egg-info'}
+        ignore_exts = {'.pyc', '.pyo', '.so', '.o', '.a', '.dylib', '.class', '.jar'}
+        total_files = 0
+        max_total_files = 100  # Stop after seeing this many files
+        
+        def walk_tree(current_path, prefix="", depth=0):
+            nonlocal total_files
+            if depth > max_depth or total_files >= max_total_files:
+                return
+            
+            try:
+                entries = sorted(os.listdir(current_path))
+            except PermissionError:
+                return
+            
+            dirs = []
+            files = []
+            for entry in entries:
+                full_path = os.path.join(current_path, entry)
+                if os.path.isdir(full_path):
+                    if entry not in ignore_dirs and not entry.startswith('.'):
+                        dirs.append(entry)
+                else:
+                    ext = os.path.splitext(entry)[1]
+                    if ext not in ignore_exts and not entry.startswith('.'):
+                        files.append(entry)
+            
+            # Limit directories shown at each level
+            dirs_to_show = dirs[:15]
+            for i, d in enumerate(dirs_to_show):
+                is_last = (i == len(dirs_to_show) - 1) and not files
+                tree_lines.append(f"{prefix}{'└── ' if is_last else '├── '}{d}/")
+                walk_tree(os.path.join(current_path, d), 
+                         prefix + ('    ' if is_last else '│   '), depth + 1)
+            if len(dirs) > 15:
+                tree_lines.append(f"{prefix}    ... and {len(dirs) - 15} more directories")
+            
+            # Limit files shown
+            files_to_show = files[:10]
+            total_files += len(files)
+            for i, f in enumerate(files_to_show):
+                is_last = i == len(files_to_show) - 1
+                tree_lines.append(f"{prefix}{'└── ' if is_last else '├── '}{f}")
+            if len(files) > 10:
+                tree_lines.append(f"{prefix}    ... and {len(files) - 10} more files")
+        
+        tree_lines.append(os.path.basename(path) + "/")
+        walk_tree(path)
+        return "\n".join(tree_lines[:50])  # Limit total lines
+    
+    def _extract_keywords(self, query: str, folder_tree: str) -> List[str]:
+        """Extract search keywords from natural language query using LLM."""
+        try:
+            from praisonaiagents import Agent
+            
+            extractor = Agent(
+                name="KeywordExtractor",
+                role="Search Query Analyzer",
+                goal="Extract file search keywords from natural language",
+                backstory="Expert at understanding code search queries",
+                llm="gpt-4o-mini",
+                verbose=False
+            )
+            
+            prompt = f"""Given this folder structure:
+{folder_tree}
+
+And this search query: "{query}"
+
+Extract 1-5 specific keywords/patterns to search for in file names and content.
+Return ONLY the keywords, one per line, no explanations.
+Focus on: file names, function names, class names, variable names that might match.
+If the query mentions a folder name that exists, include files from that folder."""
+
+            response = extractor.chat(prompt, stream=False)
+            keywords = [k.strip() for k in str(response).strip().split('\n') if k.strip()]
+            logger.debug(f"Extracted keywords: {keywords}")
+            return keywords[:5]  # Limit to 5 keywords
+        except Exception as e:
+            logger.debug(f"Keyword extraction failed: {e}")
+            # Fallback: extract words from query
+            return [w for w in query.split() if len(w) > 2][:3]
+    
+    def _search_files_by_name(self, path: str, keywords: List[str]) -> List[Dict[str, Any]]:
+        """Search for files matching keywords in their names."""
+        matches = []
+        path = os.path.abspath(path)
+        
+        ignore_dirs = {'.git', '__pycache__', 'node_modules', '.venv', 'venv'}
+        
+        for root, dirs, files in os.walk(path):
+            dirs[:] = [d for d in dirs if d not in ignore_dirs]
+            
+            for filename in files:
+                filepath = os.path.join(root, filename)
+                rel_path = os.path.relpath(filepath, path)
+                
+                # Check if any keyword matches filename or path
+                for kw in keywords:
+                    kw_lower = kw.lower()
+                    if kw_lower in filename.lower() or kw_lower in rel_path.lower():
+                        matches.append({
+                            'file': rel_path,
+                            'lines': [(1, 50)],  # First 50 lines
+                            'relevance': 1.0,
+                            'match_type': 'filename'
+                        })
+                        break
+        
+        return matches[:20]  # Limit results
+    
+    def _search_files_by_content(self, path: str, keywords: List[str]) -> List[Dict[str, Any]]:
+        """Search for files containing keywords in content."""
+        matches = []
+        path = os.path.abspath(path)
+        
+        ignore_dirs = {'.git', '__pycache__', 'node_modules', '.venv', 'venv'}
+        code_exts = {'.py', '.js', '.ts', '.jsx', '.tsx', '.java', '.go', '.rs', '.rb', '.sh', '.yaml', '.yml', '.json', '.md', '.txt'}
+        
+        for root, dirs, files in os.walk(path):
+            dirs[:] = [d for d in dirs if d not in ignore_dirs]
+            
+            for filename in files:
+                ext = os.path.splitext(filename)[1]
+                if ext not in code_exts:
+                    continue
+                    
+                filepath = os.path.join(root, filename)
+                rel_path = os.path.relpath(filepath, path)
+                
+                try:
+                    with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        content = f.read(50000)  # Read first 50KB
+                    
+                    content_lower = content.lower()
+                    for kw in keywords:
+                        if kw.lower() in content_lower:
+                            # Find line numbers with matches
+                            lines = content.split('\n')
+                            match_lines = []
+                            for i, line in enumerate(lines[:200], 1):  # Check first 200 lines
+                                if kw.lower() in line.lower():
+                                    match_lines.append((max(1, i-2), min(len(lines), i+2)))
+                            
+                            if match_lines:
+                                matches.append({
+                                    'file': rel_path,
+                                    'lines': match_lines[:5],  # Limit line ranges
+                                    'relevance': 0.8,
+                                    'match_type': 'content'
+                                })
+                            break
+                except Exception:
+                    continue
+        
+        return matches[:15]  # Limit results
+    
     def search_context(self, query: str, path: str, **kwargs) -> List[Dict[str, Any]]:
         """
         Search for relevant context in the codebase.
         
+        Uses a smart multi-step approach:
+        1. Get folder tree structure
+        2. Use LLM to extract search keywords from query
+        3. Search by filename AND content
+        4. Return combined results
+        
         Args:
-            query: Search query
+            query: Natural language search query
             path: Path to search
             **kwargs: Additional search options
+                - use_llm_keywords: Use LLM to extract keywords (default: True)
             
         Returns:
             List of matching results
@@ -84,32 +287,50 @@ class FastContextHandler(FlagHandler):
             return []
         
         try:
-            from praisonaiagents import FastContext
+            use_llm_keywords = kwargs.get('use_llm_keywords', True)
             
-            fc = FastContext(
-                path=path,
-                model=kwargs.get('model', 'gpt-4o-mini'),
-                max_turns=kwargs.get('max_turns', 4),
-                parallelism=kwargs.get('parallelism', 8),
-                timeout=kwargs.get('timeout', 30.0)
-            )
+            # Step 1: Get folder tree for context
+            logger.debug(f"Getting folder tree for: {path}")
+            folder_tree = self._get_folder_tree(path)
+            logger.debug(f"Folder tree:\n{folder_tree}")
             
-            result = fc.search(query)
+            # Step 2: Extract keywords
+            if use_llm_keywords:
+                logger.debug(f"Extracting keywords from query: {query}")
+                keywords = self._extract_keywords(query, folder_tree)
+            else:
+                keywords = [w for w in query.split() if len(w) > 2][:3]
             
-            # Convert to list of dicts
+            logger.debug(f"Search keywords: {keywords}")
+            
+            if not keywords:
+                self.print_status("Could not extract search keywords", "warning")
+                return []
+            
+            # Step 3: Search by filename
+            logger.debug("Searching by filename...")
+            filename_matches = self._search_files_by_name(path, keywords)
+            logger.debug(f"Found {len(filename_matches)} filename matches")
+            
+            # Step 4: Search by content
+            logger.debug("Searching by content...")
+            content_matches = self._search_files_by_content(path, keywords)
+            logger.debug(f"Found {len(content_matches)} content matches")
+            
+            # Combine and deduplicate
+            seen_files = set()
             matches = []
-            if hasattr(result, 'files'):
-                for file_match in result.files:
-                    matches.append({
-                        'file': file_match.path,
-                        'lines': [(lr.start, lr.end) for lr in file_match.line_ranges],
-                        'relevance': getattr(file_match, 'relevance', 1.0)
-                    })
+            
+            for m in filename_matches + content_matches:
+                if m['file'] not in seen_files:
+                    seen_files.add(m['file'])
+                    matches.append(m)
             
             self.print_status(f"🔍 Found {len(matches)} relevant files", "success")
             return matches
             
         except Exception as e:
+            logger.error(f"FastContext search error: {e}")
             self.log(f"FastContext search error: {e}", "error")
             return []
     

src/praisonai/praisonai/cli/features/guardrail.py

@@ -75,7 +75,7 @@ class GuardrailHandler(FlagHandler):
         
         Args:
             description: Natural language description of validation criteria
-            llm: Optional LLM instance for validation
+            llm: Optional LLM instance for validation (defaults to gpt-4o-mini)
             
         Returns:
             LLMGuardrail instance or None if unavailable
@@ -87,6 +87,12 @@ class GuardrailHandler(FlagHandler):
             )
             return None
         
+        # Provide default LLM if none specified
+        if llm is None:
+            import os
+            # Try to get from environment or use default
+            llm = os.environ.get('OPENAI_MODEL_NAME', 'gpt-4o-mini')
+        
         return LLMGuardrail(description=description, llm=llm)
     
     def validate_output(self, output: str, description: str, llm: Any = None) -> Tuple[bool, str]:

src/praisonai/praisonai/cli/features/handoff.py

@@ -72,11 +72,11 @@ class HandoffHandler(FlagHandler):
             self.print_status(msg, "error")
             return []
         
-        from praisonaiagents import Agent, Handoff
+        from praisonaiagents import Agent, handoff
         
         agents = []
         
-        # Create agents for each role
+        # First pass: Create all agents without handoffs
         for i, name in enumerate(agent_names):
             agent_config = {
                 "name": name.title().replace("_", " "),
@@ -91,26 +91,45 @@ class HandoffHandler(FlagHandler):
             agent = Agent(**agent_config)
             agents.append(agent)
         
-        # Set up handoffs between agents
-        for i, agent in enumerate(agents[:-1]):
-            next_agent = agents[i + 1]
-            handoff = Handoff(
-                target=next_agent,
-                name=f"handoff_to_{agent_names[i + 1]}",
-                description=f"Hand off task to {agent_names[i + 1]} for further processing"
-            )
+        # Second pass: Set up handoffs by recreating agents with handoff config
+        final_agents = []
+        for i, name in enumerate(agent_names):
+            agent_config = {
+                "name": name.title().replace("_", " "),
+                "role": name.title().replace("_", " "),
+                "goal": f"Complete tasks as {name}",
+                "backstory": f"Expert {name} with specialized skills"
+            }
             
-            # Add handoff to agent
-            if not hasattr(agent, 'handoffs') or agent.handoffs is None:
-                agent.handoffs = []
-            agent.handoffs.append(handoff)
+            if llm:
+                agent_config["llm"] = llm
+            
+            # Add handoff to next agent if not the last agent
+            if i < len(agent_names) - 1:
+                next_agent = agents[i + 1]
+                next_agent_name = agent_names[i + 1]
+                
+                # Pass handoffs via constructor - this properly registers them as tools
+                agent_config["handoffs"] = [
+                    handoff(
+                        agent=next_agent,
+                        tool_name_override=f"handoff_to_{next_agent_name}",
+                        tool_description_override=f"Hand off the task to {next_agent_name}. Call this after completing your part."
+                    )
+                ]
+                
+                # Add instructions to use handoff
+                agent_config["instructions"] = f"After completing your task, you MUST use the handoff_to_{next_agent_name} tool to pass your work to the next agent."
+            
+            final_agent = Agent(**agent_config)
+            final_agents.append(final_agent)
         
-        self.print_status(f"🤝 Created {len(agents)} agents with handoff chain", "success")
+        self.print_status(f"🤝 Created {len(final_agents)} agents with handoff chain", "success")
         for i, name in enumerate(agent_names):
             arrow = " → " if i < len(agent_names) - 1 else ""
             self.print_status(f"  {name}{arrow}", "info")
         
-        return agents
+        return final_agents
     
     def apply_to_agent_config(self, config: Dict[str, Any], flag_value: Any) -> Dict[str, Any]:
         """

src/praisonai/praisonai/cli/features/image.py

@@ -1,32 +1,52 @@
 """
 Image Handler for CLI.
 
-Provides image processing capabilities using ImageAgent.
-Usage: praisonai "Describe this image" --image path/to/image.png
+Provides two distinct image capabilities:
+1. Image Description (Vision) - Analyze existing images using vision-capable LLMs
+   Usage: praisonai "Describe this image" --image path/to/image.png
+
+2. Image Generation - Generate new images from text prompts
+   Usage: praisonai "A sunset over mountains" --image-generate
 """
 
 import os
-from typing import Any, Dict, Tuple, List
+import base64
+import logging
+from typing import Any, Dict, Tuple, List, Optional
 from .base import FlagHandler
 
-# Supported image extensions
-SUPPORTED_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.bmp', '.svg'}
+logger = logging.getLogger(__name__)
+
+# Supported image extensions for vision/description
+SUPPORTED_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.bmp', '.svg', '.tiff'}
+
+# Default vision-capable models (gpt-4o has better vision support than gpt-4o-mini)
+DEFAULT_VISION_MODEL = "gpt-4o"
+
+# Default image generation models
+DEFAULT_IMAGE_GEN_MODEL = "dall-e-3"
+SUPPORTED_IMAGE_GEN_MODELS = [
+    'gpt-image-1', 'gpt-image-1-mini', 'gpt-image-1.5', 
+    'chatgpt-image-latest', 'dall-e-2', 'dall-e-3'
+]
 
 
 class ImageHandler(FlagHandler):
     """
-    Handler for --image flag.
+    Handler for --image flag (Image Description/Vision).
     
-    Processes images using ImageAgent for vision-based tasks.
+    Describes/analyzes existing images using vision-capable LLMs like GPT-4o.
+    This is for understanding what's IN an image, not generating new images.
     
     Example:
         praisonai "Describe this image" --image photo.png
         praisonai "What's in this image?" --image /path/to/image.jpg
+        praisonai "Count the objects" --image image1.png,image2.png
     """
     
     @property
     def feature_name(self) -> str:
-        return "image"
+        return "image_describe"
     
     @property
     def flag_name(self) -> str:
@@ -34,17 +54,15 @@ class ImageHandler(FlagHandler):
     
     @property
     def flag_help(self) -> str:
-        return "Path to image file for vision-based tasks"
+        return "Path to image file for vision-based description/analysis"
     
     def check_dependencies(self) -> Tuple[bool, str]:
-        """Check if ImageAgent is available."""
+        """Check if litellm is available for vision."""
         try:
-            import importlib.util
-            if importlib.util.find_spec("praisonaiagents") is not None:
-                return True, ""
-            return False, "praisonaiagents not installed. Install with: pip install praisonaiagents"
+            import litellm
+            return True, ""
         except ImportError:
-            return False, "praisonaiagents not installed. Install with: pip install praisonaiagents"
+            return False, "litellm not installed. Install with: pip install litellm"
     
     def validate_image_path(self, path: str) -> Tuple[bool, str]:
         """
@@ -71,127 +89,154 @@ class ImageHandler(FlagHandler):
         
         return True, ""
     
+    def _encode_image_to_base64(self, image_path: str) -> str:
+        """Encode a local image file to base64."""
+        with open(image_path, 'rb') as f:
+            return base64.b64encode(f.read()).decode('utf-8')
+    
+    def _get_image_mime_type(self, image_path: str) -> str:
+        """Get MIME type based on file extension."""
+        ext = os.path.splitext(image_path)[1].lower()
+        mime_types = {
+            '.png': 'image/png',
+            '.jpg': 'image/jpeg',
+            '.jpeg': 'image/jpeg',
+            '.gif': 'image/gif',
+            '.webp': 'image/webp',
+            '.bmp': 'image/bmp',
+            '.svg': 'image/svg+xml',
+            '.tiff': 'image/tiff',
+        }
+        return mime_types.get(ext, 'image/png')
+    
+    def _build_image_content(self, image_path: str) -> Dict[str, Any]:
+        """Build image content for vision API."""
+        if image_path.startswith(('http://', 'https://')):
+            return {
+                "type": "image_url",
+                "image_url": {"url": image_path}
+            }
+        else:
+            mime_type = self._get_image_mime_type(image_path)
+            base64_data = self._encode_image_to_base64(image_path)
+            return {
+                "type": "image_url",
+                "image_url": {"url": f"data:{mime_type};base64,{base64_data}"}
+            }
+    
     def apply_to_agent_config(self, config: Dict[str, Any], flag_value: Any) -> Dict[str, Any]:
-        """
-        Apply image configuration to agent config.
-        
-        Args:
-            config: Agent configuration dictionary
-            flag_value: Image path or list of paths
-            
-        Returns:
-            Modified configuration with image settings
-        """
+        """Apply image configuration to agent config."""
         if flag_value:
-            # Store image path(s) for use with ImageAgent
             if isinstance(flag_value, str):
                 config["images"] = [flag_value]
             elif isinstance(flag_value, list):
                 config["images"] = flag_value
-            config["use_image_agent"] = True
+            config["use_vision"] = True
         return config
     
-    def create_image_agent(self, llm: str = None, **kwargs) -> Any:
+    def describe_image(self, prompt: str, image_path: str, llm = None) -> str:
         """
-        Create an ImageAgent instance.
-        
-        Args:
-            llm: Optional LLM model name
-            **kwargs: Additional agent configuration
-            
-        Returns:
-            ImageAgent instance or None if unavailable
-        """
-        available, msg = self.check_dependencies()
-        if not available:
-            self.print_status(msg, "error")
-            return None
-        
-        from praisonaiagents import ImageAgent
-        
-        agent_config = {
-            "name": "ImageAnalyzer",
-            "role": "Image Analyst",
-            "goal": "Analyze and describe images accurately",
-            "backstory": "Expert at understanding visual content"
-        }
-        
-        if llm:
-            agent_config["llm"] = llm
-        
-        agent_config.update(kwargs)
-        
-        return ImageAgent(**agent_config)
-    
-    def process_image(self, prompt: str, image_path: str, llm: str = None) -> str:
-        """
-        Process an image with the given prompt.
+        Describe an image using vision-capable LLM.
         
         Args:
             prompt: The prompt/question about the image
             image_path: Path to the image file
-            llm: Optional LLM model name
+            llm: Optional LLM model name (must be vision-capable), can be string or dict
             
         Returns:
-            Agent's response about the image
+            Description of the image
         """
-        # Validate image path
         valid, msg = self.validate_image_path(image_path)
         if not valid:
             return f"Error: {msg}"
         
-        agent = self.create_image_agent(llm=llm)
-        if not agent:
-            return "Error: Could not create ImageAgent"
+        available, dep_msg = self.check_dependencies()
+        if not available:
+            return f"Error: {dep_msg}"
+        
+        import litellm
+        
+        # Handle llm being a dict (from agent_config) or string
+        if isinstance(llm, dict):
+            model = llm.get('model', DEFAULT_VISION_MODEL)
+        else:
+            model = llm or DEFAULT_VISION_MODEL
         
         try:
-            # ImageAgent expects images as a list
-            result = agent.chat(prompt, images=[image_path])
-            return result
+            # Build message with image
+            content = [
+                {"type": "text", "text": prompt},
+                self._build_image_content(image_path)
+            ]
+            
+            response = litellm.completion(
+                model=model,
+                messages=[{"role": "user", "content": content}]
+            )
+            
+            return response.choices[0].message.content
+            
         except Exception as e:
-            self.log(f"Image processing error: {e}", "error")
-            return f"Error processing image: {e}"
+            logger.error(f"Error describing image: {e}")
+            return f"Error describing image: {e}"
     
-    def process_multiple_images(self, prompt: str, image_paths: List[str], llm: str = None) -> str:
+    def describe_multiple_images(self, prompt: str, image_paths: List[str], llm = None) -> str:
         """
-        Process multiple images with the given prompt.
+        Describe multiple images using vision-capable LLM.
         
         Args:
             prompt: The prompt/question about the images
             image_paths: List of paths to image files
-            llm: Optional LLM model name
+            llm: Optional LLM model name, can be string or dict
             
         Returns:
-            Agent's response about the images
+            Description of the images
         """
-        # Validate all image paths
         for path in image_paths:
             valid, msg = self.validate_image_path(path)
             if not valid:
                 return f"Error: {msg}"
         
-        agent = self.create_image_agent(llm=llm)
-        if not agent:
-            return "Error: Could not create ImageAgent"
+        available, dep_msg = self.check_dependencies()
+        if not available:
+            return f"Error: {dep_msg}"
+        
+        import litellm
+        
+        # Handle llm being a dict (from agent_config) or string
+        if isinstance(llm, dict):
+            model = llm.get('model', DEFAULT_VISION_MODEL)
+        else:
+            model = llm or DEFAULT_VISION_MODEL
         
         try:
-            result = agent.chat(prompt, images=image_paths)
-            return result
+            # Build message with all images
+            content = [{"type": "text", "text": prompt}]
+            for path in image_paths:
+                content.append(self._build_image_content(path))
+            
+            response = litellm.completion(
+                model=model,
+                messages=[{"role": "user", "content": content}]
+            )
+            
+            return response.choices[0].message.content
+            
         except Exception as e:
-            self.log(f"Image processing error: {e}", "error")
-            return f"Error processing images: {e}"
+            logger.error(f"Error describing images: {e}")
+            return f"Error describing images: {e}"
     
     def execute(self, prompt: str = None, image_path: str = None, llm: str = None, **kwargs) -> str:
         """
-        Execute image processing.
+        Execute image description (vision).
         
         Args:
             prompt: The prompt/question about the image
             image_path: Path to the image file (or comma-separated paths)
-            llm: Optional LLM model name
+            llm: Optional vision-capable LLM model name
             
         Returns:
-            Agent's response
+            Description of the image(s)
         """
         if not prompt:
             return "Error: No prompt provided"
@@ -202,6 +247,138 @@ class ImageHandler(FlagHandler):
         # Handle multiple images (comma-separated)
         if ',' in image_path:
             paths = [p.strip() for p in image_path.split(',')]
-            return self.process_multiple_images(prompt, paths, llm)
+            return self.describe_multiple_images(prompt, paths, llm)
         
-        return self.process_image(prompt, image_path, llm)
+        return self.describe_image(prompt, image_path, llm)
+
+
+class ImageGenerateHandler(FlagHandler):
+    """
+    Handler for --image-generate flag (Image Generation).
+    
+    Generates NEW images from text prompts using DALL-E or similar models.
+    This is for CREATING images, not analyzing existing ones.
+    
+    Example:
+        praisonai "A sunset over mountains" --image-generate
+        praisonai "A cat wearing a hat" --image-generate --llm dall-e-3
+    """
+    
+    @property
+    def feature_name(self) -> str:
+        return "image_generate"
+    
+    @property
+    def flag_name(self) -> str:
+        return "image_generate"
+    
+    @property
+    def flag_help(self) -> str:
+        return "Generate an image from the text prompt"
+    
+    def check_dependencies(self) -> Tuple[bool, str]:
+        """Check if ImageAgent is available."""
+        try:
+            import importlib.util
+            if importlib.util.find_spec("praisonaiagents") is not None:
+                return True, ""
+            return False, "praisonaiagents not installed. Install with: pip install praisonaiagents"
+        except ImportError:
+            return False, "praisonaiagents not installed. Install with: pip install praisonaiagents"
+    
+    def apply_to_agent_config(self, config: Dict[str, Any], flag_value: Any) -> Dict[str, Any]:
+        """Apply image generation configuration."""
+        if flag_value:
+            config["use_image_generation"] = True
+        return config
+    
+    def generate_image(self, prompt: str, llm: str = None, output_path: str = None) -> Dict[str, Any]:
+        """
+        Generate an image from a text prompt.
+        
+        Args:
+            prompt: Text description of the image to generate
+            llm: Image generation model (dall-e-3, dall-e-2, etc.)
+            output_path: Optional path to save the generated image
+            
+        Returns:
+            Dict with image URL or path, or error message
+        """
+        available, msg = self.check_dependencies()
+        if not available:
+            return {"error": msg}
+        
+        from praisonaiagents import ImageAgent
+        
+        # Use provided model or default
+        model = llm or DEFAULT_IMAGE_GEN_MODEL
+        
+        # Validate model is supported for generation
+        if model not in SUPPORTED_IMAGE_GEN_MODELS:
+            return {
+                "error": f"Invalid model: '{model}'. Supported image generation models: {', '.join(SUPPORTED_IMAGE_GEN_MODELS)}"
+            }
+        
+        try:
+            agent = ImageAgent(
+                name="ImageGenerator",
+                role="Image Generation Assistant",
+                goal="Generate high-quality images from text descriptions",
+                llm=model
+            )
+            
+            result = agent.chat(prompt)
+            
+            # Save image if output path provided
+            if output_path and isinstance(result, dict) and 'data' in result:
+                self._save_image(result, output_path)
+                result['saved_to'] = output_path
+            
+            return result
+            
+        except Exception as e:
+            logger.error(f"Error generating image: {e}")
+            return {"error": str(e)}
+    
+    def _save_image(self, result: Dict[str, Any], output_path: str) -> bool:
+        """Save generated image to file."""
+        try:
+            import requests
+            
+            if 'data' in result and len(result['data']) > 0:
+                image_data = result['data'][0]
+                
+                if 'url' in image_data:
+                    # Download from URL
+                    response = requests.get(image_data['url'])
+                    with open(output_path, 'wb') as f:
+                        f.write(response.content)
+                    return True
+                elif 'b64_json' in image_data:
+                    # Decode base64
+                    import base64
+                    img_bytes = base64.b64decode(image_data['b64_json'])
+                    with open(output_path, 'wb') as f:
+                        f.write(img_bytes)
+                    return True
+            return False
+        except Exception as e:
+            logger.error(f"Error saving image: {e}")
+            return False
+    
+    def execute(self, prompt: str = None, llm: str = None, output_path: str = None, **kwargs) -> Dict[str, Any]:
+        """
+        Execute image generation.
+        
+        Args:
+            prompt: Text description of the image to generate
+            llm: Image generation model name
+            output_path: Optional path to save the image
+            
+        Returns:
+            Dict with generated image info or error
+        """
+        if not prompt:
+            return {"error": "No prompt provided for image generation"}
+        
+        return self.generate_image(prompt, llm, output_path)

src/praisonai/praisonai/cli/features/metrics.py

@@ -107,6 +107,14 @@ class MetricsHandler(FlagHandler):
         if hasattr(agent, 'last_token_metrics'):
             metrics.update(agent.last_token_metrics or {})
         
+        # Check llm_model property for model info
+        if hasattr(agent, 'llm_model'):
+            llm_model = agent.llm_model
+            if hasattr(llm_model, 'model'):
+                metrics['model'] = llm_model.model
+            elif isinstance(llm_model, str):
+                metrics['model'] = llm_model
+        
         if hasattr(agent, 'llm') and agent.llm:
             llm = agent.llm
             if hasattr(llm, 'last_token_metrics'):
@@ -117,6 +125,42 @@ class MetricsHandler(FlagHandler):
         if hasattr(agent, 'metrics') and isinstance(agent.metrics, dict):
             metrics.update(agent.metrics or {})
         
+        # Try to get from litellm's success callback data
+        try:
+            import litellm
+            # Check if there's accumulated usage data
+            if hasattr(litellm, '_thread_context') and litellm._thread_context:
+                ctx = litellm._thread_context
+                if hasattr(ctx, 'usage'):
+                    usage = ctx.usage
+                    if hasattr(usage, 'prompt_tokens'):
+                        metrics['prompt_tokens'] = usage.prompt_tokens
+                    if hasattr(usage, 'completion_tokens'):
+                        metrics['completion_tokens'] = usage.completion_tokens
+                    if hasattr(usage, 'total_tokens'):
+                        metrics['total_tokens'] = usage.total_tokens
+        except:
+            pass
+        
+        # Try to get cost from litellm cost tracking
+        try:
+            import litellm
+            from litellm import completion_cost
+            # If we have token counts, estimate cost
+            if 'prompt_tokens' in metrics and 'completion_tokens' in metrics:
+                model = metrics.get('model', 'gpt-4o-mini')
+                try:
+                    cost = completion_cost(
+                        model=model,
+                        prompt_tokens=metrics['prompt_tokens'],
+                        completion_tokens=metrics['completion_tokens']
+                    )
+                    metrics['cost'] = cost
+                except:
+                    pass
+        except:
+            pass
+        
         return metrics
     
     def post_process_result(self, result: Any, flag_value: Any) -> Any:

src/praisonai/praisonai/cli/features/profile.py

@@ -0,0 +1,226 @@
+"""
+Profile Handler for CLI.
+
+Provides performance profiling and benchmarking capabilities.
+Usage: praisonai profile <subcommand> [options]
+"""
+
+import argparse
+import time
+import json
+from typing import Any, Dict, List, Optional
+from dataclasses import dataclass, field
+from datetime import datetime
+
+
+@dataclass
+class ProfileResult:
+    """Result from a profiling run."""
+    prompt: str
+    response: str
+    execution_time_ms: float
+    model: str
+    tokens: Optional[Dict[str, int]] = None
+    timestamp: str = field(default_factory=lambda: datetime.now().isoformat())
+    
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "prompt": self.prompt,
+            "response": self.response[:200] + "..." if len(self.response) > 200 else self.response,
+            "execution_time_ms": self.execution_time_ms,
+            "model": self.model,
+            "tokens": self.tokens,
+            "timestamp": self.timestamp
+        }
+
+
+def run_benchmark(prompt: str, model: str = None, iterations: int = 1, verbose: bool = False) -> List[ProfileResult]:
+    """
+    Run a benchmark on a prompt.
+    
+    Args:
+        prompt: The prompt to benchmark
+        model: Optional model to use
+        iterations: Number of iterations to run
+        verbose: Enable verbose output
+        
+    Returns:
+        List of ProfileResult objects
+    """
+    try:
+        from praisonaiagents import Agent
+    except ImportError:
+        print("[red]ERROR: praisonaiagents not installed. Install with: pip install praisonaiagents[/red]")
+        return []
+    
+    results = []
+    
+    agent_config = {
+        "name": "BenchmarkAgent",
+        "role": "Benchmark Assistant",
+        "goal": "Complete tasks efficiently",
+        "verbose": verbose
+    }
+    
+    if model:
+        agent_config["llm"] = model
+    
+    agent = Agent(**agent_config)
+    
+    for i in range(iterations):
+        if verbose:
+            print(f"[dim]Running iteration {i + 1}/{iterations}...[/dim]")
+        
+        start_time = time.time()
+        response = agent.start(prompt)
+        end_time = time.time()
+        
+        execution_time_ms = (end_time - start_time) * 1000
+        
+        result = ProfileResult(
+            prompt=prompt,
+            response=str(response),
+            execution_time_ms=execution_time_ms,
+            model=model or "default"
+        )
+        results.append(result)
+    
+    return results
+
+
+def display_benchmark_results(results: List[ProfileResult], output_format: str = "table"):
+    """Display benchmark results."""
+    if not results:
+        print("[yellow]No results to display[/yellow]")
+        return
+    
+    try:
+        from rich.console import Console
+        from rich.table import Table
+        console = Console()
+    except ImportError:
+        # Fallback to simple output
+        for r in results:
+            print(f"Time: {r.execution_time_ms:.1f}ms | Model: {r.model}")
+        return
+    
+    if output_format == "json":
+        print(json.dumps([r.to_dict() for r in results], indent=2))
+        return
+    
+    # Calculate statistics
+    times = [r.execution_time_ms for r in results]
+    avg_time = sum(times) / len(times)
+    min_time = min(times)
+    max_time = max(times)
+    
+    table = Table(title="📊 Benchmark Results")
+    table.add_column("Metric", style="cyan")
+    table.add_column("Value", style="green")
+    
+    table.add_row("Iterations", str(len(results)))
+    table.add_row("Average Time", f"{avg_time:.1f}ms")
+    table.add_row("Min Time", f"{min_time:.1f}ms")
+    table.add_row("Max Time", f"{max_time:.1f}ms")
+    table.add_row("Model", results[0].model)
+    
+    console.print(table)
+    
+    # Show response preview
+    if results:
+        console.print("\n[bold]Response Preview:[/bold]")
+        preview = results[0].response[:300] + "..." if len(results[0].response) > 300 else results[0].response
+        console.print(f"[dim]{preview}[/dim]")
+
+
+def handle_profile_command(args: List[str]) -> int:
+    """
+    Handle the profile command.
+    
+    Args:
+        args: Command line arguments
+        
+    Returns:
+        Exit code
+    """
+    parser = argparse.ArgumentParser(prog="praisonai profile", description="Performance profiling and benchmarking")
+    subparsers = parser.add_subparsers(dest='subcommand', help='Profile subcommands')
+    
+    # Benchmark subcommand
+    bench_parser = subparsers.add_parser('benchmark', aliases=['bench', 'run'], help='Run a benchmark')
+    bench_parser.add_argument('prompt', nargs='?', help='Prompt to benchmark')
+    bench_parser.add_argument('--model', '-m', type=str, help='Model to use')
+    bench_parser.add_argument('--iterations', '-n', type=int, default=1, help='Number of iterations')
+    bench_parser.add_argument('--output', '-o', type=str, help='Output file path')
+    bench_parser.add_argument('--format', '-f', type=str, choices=['table', 'json', 'html'], default='table', help='Output format')
+    bench_parser.add_argument('--verbose', '-v', action='store_true', help='Verbose output')
+    
+    # Compare subcommand
+    compare_parser = subparsers.add_parser('compare', help='Compare models')
+    compare_parser.add_argument('prompt', nargs='?', help='Prompt to compare')
+    compare_parser.add_argument('--models', type=str, help='Comma-separated list of models to compare')
+    
+    # Report subcommand
+    report_parser = subparsers.add_parser('report', help='Generate a profiling report')
+    report_parser.add_argument('--input', '-i', type=str, help='Input JSON file with results')
+    report_parser.add_argument('--output', '-o', type=str, help='Output file path')
+    report_parser.add_argument('--format', '-f', type=str, choices=['html', 'json', 'markdown'], default='html', help='Report format')
+    
+    try:
+        parsed_args = parser.parse_args(args)
+    except SystemExit:
+        return 1
+    
+    if not parsed_args.subcommand:
+        parser.print_help()
+        print("\n[bold]Examples:[/bold]")
+        print("  praisonai profile benchmark \"What is 2+2?\"")
+        print("  praisonai profile benchmark \"Write a poem\" --model gpt-4o --iterations 3")
+        print("  praisonai profile compare \"Explain AI\" --models gpt-4o,gpt-4o-mini")
+        return 0
+    
+    if parsed_args.subcommand in ['benchmark', 'bench', 'run']:
+        if not parsed_args.prompt:
+            print("[red]ERROR: Please provide a prompt to benchmark[/red]")
+            print("Usage: praisonai profile benchmark \"Your prompt here\"")
+            return 1
+        
+        print(f"[bold cyan]🔬 Running benchmark...[/bold cyan]")
+        results = run_benchmark(
+            parsed_args.prompt,
+            model=parsed_args.model,
+            iterations=parsed_args.iterations,
+            verbose=parsed_args.verbose
+        )
+        
+        display_benchmark_results(results, parsed_args.format)
+        
+        if parsed_args.output:
+            with open(parsed_args.output, 'w') as f:
+                json.dump([r.to_dict() for r in results], f, indent=2)
+            print(f"[green]Results saved to {parsed_args.output}[/green]")
+        
+        return 0
+    
+    elif parsed_args.subcommand == 'compare':
+        if not parsed_args.prompt:
+            print("[red]ERROR: Please provide a prompt to compare[/red]")
+            return 1
+        
+        models = parsed_args.models.split(',') if parsed_args.models else ['gpt-4o-mini', 'gpt-4o']
+        print(f"[bold cyan]🔬 Comparing models: {', '.join(models)}[/bold cyan]")
+        
+        all_results = []
+        for model in models:
+            print(f"[dim]Testing {model}...[/dim]")
+            results = run_benchmark(parsed_args.prompt, model=model, iterations=1)
+            all_results.extend(results)
+        
+        display_benchmark_results(all_results)
+        return 0
+    
+    elif parsed_args.subcommand == 'report':
+        print("[yellow]Report generation not yet implemented[/yellow]")
+        return 0
+    
+    return 0

src/praisonai/praisonai/cli/main.py

@@ -313,6 +313,18 @@ class PraisonAI:
         elif hasattr(args, 'direct_prompt') and args.direct_prompt:
             # Only handle direct prompt if agent_file wasn't explicitly set in constructor
             if original_agent_file == "agents.yaml":  # Default value, so safe to use direct prompt
+                # Handle --compare flag for CLI mode comparison
+                if hasattr(args, 'compare') and args.compare:
+                    from .features.compare import CompareHandler
+                    handler = CompareHandler(verbose=getattr(args, 'verbose', False))
+                    result = handler.execute(
+                        args.direct_prompt,
+                        args.compare,
+                        model=getattr(args, 'llm', None),
+                        output_path=getattr(args, 'compare_output', None)
+                    )
+                    return result
+                
                 # Combine direct prompt with any available inputs (stdin and/or file)
                 prompt_parts = [args.direct_prompt]
                 if stdin_input:
@@ -649,7 +661,7 @@ class PraisonAI:
             return default_args
         
         # Define special commands
-        special_commands = ['chat', 'code', 'call', 'realtime', 'train', 'ui', 'context', 'research', 'memory', 'rules', 'workflow', 'hooks', 'knowledge', 'session', 'tools', 'todo', 'docs', 'mcp', 'commit', 'serve', 'schedule', 'skills']
+        special_commands = ['chat', 'code', 'call', 'realtime', 'train', 'ui', 'context', 'research', 'memory', 'rules', 'workflow', 'hooks', 'knowledge', 'session', 'tools', 'todo', 'docs', 'mcp', 'commit', 'serve', 'schedule', 'skills', 'profile', 'eval']
         
         parser = argparse.ArgumentParser(prog="praisonai", description="praisonAI command-line interface")
         parser.add_argument("--framework", choices=["crewai", "autogen", "praisonai"], help="Specify the framework")
@@ -721,8 +733,12 @@ class PraisonAI:
         # Metrics - token/cost tracking
         parser.add_argument("--metrics", action="store_true", help="Display token usage and cost metrics")
         
-        # Image - vision processing
-        parser.add_argument("--image", type=str, help="Path to image file for vision-based tasks")
+        # Image Description (Vision) - analyze existing images
+        parser.add_argument("--image", type=str, help="Path to image file for vision-based description/analysis")
+        
+        # Image Generation - create new images from text
+        parser.add_argument("--image-generate", action="store_true", dest="image_generate", 
+                          help="Generate an image from the text prompt (use with --llm for model selection)")
         
         # Telemetry - usage monitoring
         parser.add_argument("--telemetry", action="store_true", help="Enable usage monitoring and analytics")
@@ -1094,6 +1110,18 @@ class PraisonAI:
                 
                 exit_code = handle_skills_command(skills_args)
                 sys.exit(exit_code)
+            
+            elif args.command == 'profile':
+                # Profile command - performance profiling and benchmarking
+                from .features.profile import handle_profile_command
+                exit_code = handle_profile_command(unknown_args)
+                sys.exit(exit_code)
+            
+            elif args.command == 'eval':
+                # Eval command - evaluate model responses against expected outputs
+                from .features.eval import handle_eval_command
+                exit_code = handle_eval_command(unknown_args)
+                sys.exit(exit_code)
 
         # Only check framework availability for agent-related operations
         if not args.command and (args.init or args.auto or args.framework):
@@ -3178,10 +3206,9 @@ Provide ONLY the commit message, no explanations."""
                     selected_model = router.select_model(prompt, provider)
                     agent_config["llm"] = selected_model
                 
-                # Metrics - Token/cost tracking
+                # Metrics - Token/cost tracking (display happens AFTER execution)
                 if getattr(self.args, 'metrics', False):
                     agent_config["metrics"] = True
-                    print("[bold cyan]Metrics enabled - will display token usage and costs[/bold cyan]")
                 
                 # Telemetry - Usage monitoring
                 if getattr(self.args, 'telemetry', False):
@@ -3189,6 +3216,12 @@ Provide ONLY the commit message, no explanations."""
                     telemetry = TelemetryHandler(verbose=getattr(self.args, 'verbose', False))
                     telemetry.enable()
                 
+                # Sandbox - Secure command execution (display only, actual sandboxing is in tool approval)
+                sandbox_mode = getattr(self.args, 'sandbox', None)
+                if sandbox_mode and sandbox_mode != 'off':
+                    print(f"[bold green]🔒 Sandbox Mode: {sandbox_mode.upper()}[/bold green]")
+                    print("[dim]Commands will be validated before execution[/dim]")
+                
                 # Auto Memory - Automatic memory extraction (handled post-processing, not as Agent param)
                 if getattr(self.args, 'auto_memory', False):
                     print("[bold cyan]Auto Memory enabled - will extract and store memories[/bold cyan]")
@@ -3279,7 +3312,7 @@ Provide ONLY the commit message, no explanations."""
                         
                         return result
             
-            # Image processing - Use ImageAgent instead
+            # Image Description (Vision) - analyze existing images
             if hasattr(self, 'args') and getattr(self.args, 'image', None):
                 from .features.image import ImageHandler
                 image_handler = ImageHandler(verbose=getattr(self.args, 'verbose', False))
@@ -3301,6 +3334,27 @@ Provide ONLY the commit message, no explanations."""
                 
                 return result
             
+            # Image Generation - create new images from text
+            if hasattr(self, 'args') and getattr(self.args, 'image_generate', False):
+                from .features.image import ImageGenerateHandler
+                image_gen_handler = ImageGenerateHandler(verbose=getattr(self.args, 'verbose', False))
+                result = image_gen_handler.execute(
+                    prompt=prompt,
+                    llm=agent_config.get('llm')
+                )
+                
+                # Format output for display
+                if isinstance(result, dict):
+                    if 'error' in result:
+                        print(f"[red]Error: {result['error']}[/red]")
+                    elif 'data' in result and len(result['data']) > 0:
+                        image_url = result['data'][0].get('url', result['data'][0].get('b64_json', 'Generated'))
+                        print(f"[green]Image generated successfully![/green]")
+                        if 'url' in result['data'][0]:
+                            print(f"URL: {result['data'][0]['url']}")
+                
+                return result
+            
             # Flow Display - Visual workflow tracking
             if hasattr(self, 'args') and getattr(self.args, 'flow_display', False):
                 from .features.flow_display import FlowDisplayHandler
@@ -3347,6 +3401,12 @@ Provide ONLY the commit message, no explanations."""
                 todo = TodoHandler(verbose=getattr(self.args, 'verbose', False))
                 todo.post_process_result(result, True)
             
+            # Telemetry - Display usage summary after execution
+            if hasattr(self, 'args') and getattr(self.args, 'telemetry', False):
+                from .features.telemetry import TelemetryHandler
+                telemetry = TelemetryHandler(verbose=getattr(self.args, 'verbose', False))
+                telemetry.post_process_result(result, True)
+            
             # Flow Display - End workflow
             if hasattr(self, 'args') and getattr(self.args, 'flow_display', False):
                 from .features.flow_display import FlowDisplayHandler
@@ -4741,16 +4801,14 @@ Provide a concise summary (max 200 words):"""
     
     def _process_interactive_prompt_async(self, prompt, tools_list, console, session_state=None):
         """
-        Process a prompt asynchronously with live status display.
+        Process a prompt asynchronously with non-blocking status display.
         
-        Shows real-time status (tools, commands) while processing in background.
+        Shows status updates without blocking user input.
         Allows user to queue more messages while processing.
         """
         import threading
         import time
-        from rich.live import Live
-        from rich.panel import Panel
-        from rich.text import Text
+        import sys
         from praisonai.cli.features.message_queue import ProcessingState
         
         state_manager = session_state['state_manager']
@@ -4762,8 +4820,11 @@ Provide a concise summary (max 200 words):"""
         live_status.clear()
         live_status.update_status("Thinking...")
         
+        # Print initial status (non-blocking - user can still type)
+        console.print(f"[dim cyan]⏳ {live_status.current_status}[/dim cyan]")
+        
         # Result container for thread communication
-        result_container = {'response': None, 'error': None, 'done': False}
+        result_container = {'response': None, 'error': None, 'done': False, 'last_status': ''}
         
         def process_in_background():
             """Run agent processing in background thread."""
@@ -4809,37 +4870,36 @@ Provide a concise summary (max 200 words):"""
         bg_thread = threading.Thread(target=process_in_background, daemon=True)
         bg_thread.start()
         
-        # Show live status while processing
-        try:
-            with Live(console=console, refresh_per_second=4, transient=True) as live:
-                while not result_container['done']:
-                    # Build status display
-                    status_text = Text()
-                    status_text.append("⏳ ", style="cyan")
-                    status_text.append(live_status.current_status or "Processing...", style="dim")
-                    
-                    # Show queued messages if any
-                    queue_count = message_queue.count
-                    if queue_count > 0:
-                        status_text.append(f"\n📋 Queued: {queue_count}", style="dim yellow")
-                    
-                    live.update(Panel(status_text, border_style="dim"))
-                    time.sleep(0.1)
-        except KeyboardInterrupt:
-            console.print("\n[dim]Processing interrupted[/dim]")
+        # Wait for completion with periodic status updates (non-blocking style)
+        start_time = time.time()
+        last_status_update = ""
+        while not result_container['done']:
+            time.sleep(0.2)
+            current_status = live_status.current_status
+            # Only print status if it changed
+            if current_status != last_status_update:
+                # Use carriage return to update in place
+                elapsed = time.time() - start_time
+                queue_count = message_queue.count
+                queue_info = f" | 📋 Queued: {queue_count}" if queue_count > 0 else ""
+                sys.stdout.write(f"\r[dim cyan]⏳ {current_status} ({elapsed:.1f}s){queue_info}[/dim cyan]")
+                sys.stdout.flush()
+                last_status_update = current_status
+        
+        # Clear the status line
+        sys.stdout.write("\r" + " " * 80 + "\r")
+        sys.stdout.flush()
         
         # Wait for thread to finish
         bg_thread.join(timeout=1.0)
         
         # Handle result
         if result_container['error']:
-            console.print(f"\n[red]Error: {result_container['error']}[/red]")
+            console.print(f"[red]Error: {result_container['error']}[/red]")
         elif result_container['response']:
             # Print response with streaming effect
-            console.print()
             response_str = result_container['response']
             words = response_str.split()
-            import sys
             for i, word in enumerate(words):
                 console.print(word + " ", end="")
                 sys.stdout.flush()

src/praisonai/praisonai/deploy.py

@@ -57,7 +57,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.3.76 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.3.81 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

src/praisonai/praisonai/version.py

@@ -1 +1 @@
-__version__ = "2.3.76"
+__version__ = "2.3.81"