Release v2.3.2

- Save output to output/prompts/ folder with timestamped filename
- Works with all flags: --web-search, --expand-prompt, etc.

Usage:
  praisonai 'latest AI trends' --web-search --save
  praisonai 'write a poem' --expand-prompt --save

.github/workflows/test-comprehensive.yml

@@ -27,6 +27,9 @@ jobs:
   comprehensive-test:
     runs-on: ubuntu-latest
     timeout-minutes: 15
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      OPENAI_MODEL_NAME: gpt-4o-mini
     strategy:
       matrix:
         python-version: ["3.11"]
@@ -55,11 +58,13 @@ jobs:
         # Install knowledge dependencies from praisonai-agents
         uv pip install --system "praisonaiagents[knowledge]"
 
-    - name: Set environment variables
+    - name: Verify environment variables
       run: |
-        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY || 'sk-test-key-for-github-actions-testing-only-not-real' }}" >> $GITHUB_ENV
-        echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE || 'https://api.openai.com/v1' }}" >> $GITHUB_ENV
-        echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME || 'gpt-5-nano' }}" >> $GITHUB_ENV
+        if [ -n "$OPENAI_API_KEY" ]; then
+          echo "✅ OPENAI_API_KEY is set (length: ${#OPENAI_API_KEY})"
+        else
+          echo "⚠️ OPENAI_API_KEY is NOT set"
+        fi
 
     - name: Run Comprehensive Test Suite
       run: |

.github/workflows/test-core.yml

@@ -34,7 +34,7 @@ jobs:
         cd src/praisonai
         uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
         uv pip install --system duckduckgo_search
-        uv pip install --system pytest pytest-asyncio pytest-cov
+        uv pip install --system pytest pytest-asyncio pytest-cov pytest-timeout
         # Install knowledge dependencies from praisonai-agents
         uv pip install --system "praisonaiagents[knowledge]"
 
@@ -262,7 +262,7 @@ jobs:
         export OPENAI_API_KEY="$OPENAI_API_KEY"
         export OPENAI_API_BASE="$OPENAI_API_BASE"
         export OPENAI_MODEL_NAME="$OPENAI_MODEL_NAME"
-        cd src/praisonai && python -m pytest tests/test.py -v --tb=short --disable-warnings
+        cd src/praisonai && python -m pytest tests/test.py -v --tb=short --disable-warnings -m "not real" --timeout=60
 
     - name: Upload coverage reports to Codecov
       if: matrix.python-version == '3.11'

.github/workflows/unittest.yml

@@ -27,7 +27,7 @@ jobs:
         cd src/praisonai
         uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
         uv pip install --system duckduckgo_search
-        uv pip install --system pytest pytest-asyncio pytest-cov
+        uv pip install --system pytest pytest-asyncio pytest-cov pytest-timeout
         # Install knowledge dependencies from praisonai-agents
         uv pip install --system "praisonaiagents[knowledge]"
 
@@ -489,7 +489,7 @@ jobs:
 
     - name: Run Legacy Example Tests
       run: |
-        cd src/praisonai && python -m pytest tests/test.py -v --tb=short --disable-warnings
+        cd src/praisonai && python -m pytest tests/test.py -v --tb=short --disable-warnings -m "not real" --timeout=60
       continue-on-error: true
 
     - name: Upload coverage reports to Codecov

README.md

@@ -55,6 +55,9 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 - 💯 100+ LLM Support
 - 🔬 **Deep Research Agents** (OpenAI & Gemini)
 - 🔄 **Query Rewriter Agent** (HyDE, Step-back, Multi-query)
+- 🌐 **Native Web Search** (OpenAI, Gemini, Anthropic, xAI, Perplexity)
+- 📥 **Web Fetch** (Retrieve full content from URLs - Anthropic)
+- 💾 **Prompt Caching** (Reduce costs & latency - OpenAI, Anthropic, Bedrock, Deepseek)
 
 ## Using Python Code
 
@@ -718,6 +721,97 @@ agent = Agent(tools=["my_tool"])  # Works automatically!
 ```
 
 
+## Prompt Expansion
+
+Expand short prompts into detailed, actionable prompts:
+
+### CLI Usage
+
+```bash
+# Expand a short prompt into detailed prompt
+praisonai "write a movie script in 3 lines" --expand-prompt
+
+# With verbose output
+praisonai "blog about AI" --expand-prompt -v
+
+# With tools for context gathering
+praisonai "latest AI trends" --expand-prompt --expand-tools tools.py
+
+# Combine with query rewrite
+praisonai "AI news" --query-rewrite --expand-prompt
+```
+
+### Programmatic Usage
+
+```python
+from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+
+# Basic usage
+agent = PromptExpanderAgent()
+result = agent.expand("write a movie script in 3 lines")
+print(result.expanded_prompt)
+
+# With specific strategy
+result = agent.expand("blog about AI", strategy=ExpandStrategy.DETAILED)
+
+# Available strategies: BASIC, DETAILED, STRUCTURED, CREATIVE, AUTO
+```
+
+**Key Difference:**
+- `--query-rewrite`: Optimizes queries for **search/retrieval** (RAG)
+- `--expand-prompt`: Expands prompts for **detailed task execution**
+
+
+## Web Search, Web Fetch & Prompt Caching
+
+### CLI Usage
+
+```bash
+# Web Search - Get real-time information
+praisonai "What are the latest AI news today?" --web-search --llm openai/gpt-4o-search-preview
+
+# Web Fetch - Retrieve and analyze URL content (Anthropic only)
+praisonai "Summarize https://docs.praison.ai" --web-fetch --llm anthropic/claude-sonnet-4-20250514
+
+# Prompt Caching - Reduce costs for repeated prompts
+praisonai "Analyze this document..." --prompt-caching --llm anthropic/claude-sonnet-4-20250514
+```
+
+### Programmatic Usage
+
+```python
+from praisonaiagents import Agent
+
+# Web Search
+agent = Agent(
+    instructions="You are a research assistant",
+    llm="openai/gpt-4o-search-preview",
+    web_search=True
+)
+
+# Web Fetch (Anthropic only)
+agent = Agent(
+    instructions="You are a content analyzer",
+    llm="anthropic/claude-sonnet-4-20250514",
+    web_fetch=True
+)
+
+# Prompt Caching
+agent = Agent(
+    instructions="You are an AI assistant..." * 50,  # Long system prompt
+    llm="anthropic/claude-sonnet-4-20250514",
+    prompt_caching=True
+)
+```
+
+**Supported Providers:**
+| Feature | Providers |
+|---------|-----------|
+| Web Search | OpenAI, Gemini, Anthropic, xAI, Perplexity |
+| Web Fetch | Anthropic |
+| Prompt Caching | OpenAI (auto), Anthropic, Bedrock, Deepseek |
+
+
 ## Development:
 
 Below is used for development only.
@@ -735,21 +829,14 @@ uv pip install -r pyproject.toml --extra code
 uv pip install -r pyproject.toml --extra "crewai,autogen"
 ```
 
-### Version Bump
+### Bump and Release
 
 ```bash
-# From project root
-python src/praisonai/scripts/bump_version.py 2.2.96
+# From project root - bumps version and releases in one command
+python src/praisonai/scripts/bump_and_release.py 2.2.99
 
 # With praisonaiagents dependency
-python src/praisonai/scripts/bump_version.py 2.2.96 --agents 0.0.167
-```
-
-### Release
-
-```bash
-# From project root (runs uv lock, build, git tag, gh release)
-python src/praisonai/scripts/release.py
+python src/praisonai/scripts/bump_and_release.py 2.2.99 --agents 0.0.169
 
 # Then publish
 cd src/praisonai && uv publish

docker/Dockerfile

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     flask \
-    "praisonai>=2.2.99" \
+    "praisonai>=2.3.2" \
     "praisonai[api]" \
     gunicorn \
     markdown

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>=2.2.99" \
+    "praisonai>=2.3.2" \
     "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>=2.2.99" \
+    "praisonai>=2.3.2" \
     "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>=2.2.99" \
+    "praisonai>=2.3.2" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

src/praisonai-agents/README.md

@@ -347,6 +347,92 @@ agent = Agent(
 
 ---
 
+## Native Web Search
+
+Enable real-time web search capabilities using LiteLLM's native web search.
+
+```python
+from praisonaiagents import Agent
+
+# Enable web search with a supported model
+agent = Agent(
+    name="Researcher",
+    instructions="You are a helpful research assistant.",
+    llm="openai/gpt-4o-search-preview",
+    web_search=True
+)
+
+result = agent.start("What are the latest developments in AI today?")
+```
+
+**Supported Providers:**
+- **OpenAI**: `gpt-4o-search-preview`, `gpt-4o-mini-search-preview`
+- **Anthropic**: `claude-3-5-sonnet-latest`, `claude-sonnet-4`
+- **Google/Gemini**: `gemini-2.0-flash`, `gemini-2.5-pro`
+- **xAI**: `grok-3`
+- **Perplexity**: All models
+
+---
+
+## Web Fetch
+
+Retrieve full content from specific URLs (Anthropic models only).
+
+```python
+from praisonaiagents import Agent
+
+# Enable web fetch with an Anthropic model
+agent = Agent(
+    name="Content Analyzer",
+    instructions="You can fetch and analyze web content.",
+    llm="anthropic/claude-sonnet-4-20250514",
+    web_fetch=True
+)
+
+result = agent.start("Fetch and summarize https://example.com")
+```
+
+**Web Fetch Options:**
+```python
+agent = Agent(
+    llm="anthropic/claude-sonnet-4-20250514",
+    web_fetch={
+        "max_uses": 10,
+        "allowed_domains": ["example.com"],
+        "citations": {"enabled": True}
+    }
+)
+```
+
+---
+
+## Prompt Caching
+
+Reduce costs and latency by caching parts of prompts.
+
+```python
+from praisonaiagents import Agent
+
+# Enable prompt caching for Anthropic models
+agent = Agent(
+    name="Legal Analyst",
+    instructions="You are an AI assistant analyzing legal documents." * 50,  # Long prompt
+    llm="anthropic/claude-3-5-sonnet-latest",
+    prompt_caching=True
+)
+
+# First call creates cache, subsequent calls use cached tokens
+result = agent.start("Summarize the key terms")
+```
+
+**Supported Providers:**
+- **OpenAI** (`openai/`) - Automatic caching for prompts ≥1024 tokens
+- **Anthropic** (`anthropic/`) - Manual caching with `cache_control`
+- **Bedrock** (`bedrock/`) - All models supporting prompt caching
+- **Deepseek** (`deepseek/`) - Works like OpenAI
+
+---
+
 ## Guardrails
 
 Add safety checks and validation to agent responses.

src/praisonai-agents/praisonaiagents/__init__.py

@@ -31,6 +31,11 @@ from .agent.query_rewriter_agent import (
     RewriteStrategy,
     RewriteResult
 )
+from .agent.prompt_expander_agent import (
+    PromptExpanderAgent,
+    ExpandStrategy,
+    ExpandResult
+)
 from .agents.agents import PraisonAIAgents
 from .task.task import Task
 from .tools.tools import Tools
@@ -228,7 +233,10 @@ __all__ = [
     'Provider',
     'QueryRewriterAgent',
     'RewriteStrategy',
-    'RewriteResult'
+    'RewriteResult',
+    'PromptExpanderAgent',
+    'ExpandStrategy',
+    'ExpandResult'
 ]
 
 # Add MCP to __all__ if available

src/praisonai-agents/praisonaiagents/agent/__init__.py

@@ -20,6 +20,11 @@ from .query_rewriter_agent import (
     RewriteStrategy,
     RewriteResult
 )
+from .prompt_expander_agent import (
+    PromptExpanderAgent,
+    ExpandStrategy,
+    ExpandResult
+)
 
 __all__ = [
     'Agent',
@@ -43,5 +48,8 @@ __all__ = [
     'Provider',
     'QueryRewriterAgent',
     'RewriteStrategy',
-    'RewriteResult'
+    'RewriteResult',
+    'PromptExpanderAgent',
+    'ExpandStrategy',
+    'ExpandResult'
 ]

src/praisonai-agents/praisonaiagents/agent/agent.py

@@ -234,7 +234,10 @@ class Agent:
         max_guardrail_retries: int = 3,
         handoffs: Optional[List[Union['Agent', 'Handoff']]] = None,
         base_url: Optional[str] = None,
-        api_key: Optional[str] = None
+        api_key: Optional[str] = None,
+        web_search: Optional[Union[bool, Dict[str, Any]]] = None,
+        web_fetch: Optional[Union[bool, Dict[str, Any]]] = None,
+        prompt_caching: Optional[bool] = None
     ):
         """Initialize an Agent instance.
 
@@ -400,7 +403,10 @@ class Agent:
                         model=model_name,
                         base_url=base_url,
                         api_key=api_key,
-                        metrics=metrics
+                        metrics=metrics,
+                        web_search=web_search,
+                        web_fetch=web_fetch,
+                        prompt_caching=prompt_caching
                     )
                 self._using_custom_llm = True
             except ImportError as e:
@@ -435,6 +441,9 @@ class Agent:
                 if api_key:
                     llm_params['api_key'] = api_key
                 llm_params['metrics'] = metrics
+                llm_params['web_search'] = web_search
+                llm_params['web_fetch'] = web_fetch
+                llm_params['prompt_caching'] = prompt_caching
                 self.llm_instance = LLM(**llm_params)
                 self._using_custom_llm = True
                 
@@ -511,6 +520,22 @@ Your Goal: {self.goal}
         # Store user_id
         self.user_id = user_id or "praison"
         self.reasoning_steps = reasoning_steps
+        self.web_search = web_search
+        self.web_fetch = web_fetch
+        self.prompt_caching = prompt_caching
+        
+        # Handle web_search fallback: inject DuckDuckGo tool for unsupported models
+        if web_search and not self._model_supports_web_search():
+            from ..tools.duckduckgo_tools import internet_search
+            # Check if internet_search is not already in tools
+            tool_names = [getattr(t, '__name__', str(t)) for t in self.tools]
+            if 'internet_search' not in tool_names and 'duckduckgo' not in tool_names:
+                self.tools.append(internet_search)
+                logging.info("Model does not support native web search. Added DuckDuckGo fallback tool.")
+        
+        # Log warning if web_fetch is enabled but model doesn't support it
+        if web_fetch and not self._model_supports_web_fetch():
+            logging.warning(f"Model '{self.llm}' does not support native web fetch. Web fetch will be ignored.")
         
         # Initialize guardrail settings
         self.guardrail = guardrail
@@ -576,6 +601,69 @@ Your Goal: {self.goal}
             self._agent_id = str(uuid.uuid4())
         return self._agent_id
     
+    def _model_supports_web_search(self) -> bool:
+        """
+        Check if the agent's model supports native web search via LiteLLM.
+        
+        Returns:
+            bool: True if the model supports native web search, False otherwise
+        """
+        from ..llm.model_capabilities import supports_web_search
+        
+        # Get the model name
+        if hasattr(self, 'llm_instance') and self.llm_instance:
+            model_name = self.llm_instance.model
+        elif hasattr(self, 'llm') and self.llm:
+            model_name = self.llm
+        else:
+            model_name = "gpt-5-nano"
+        
+        return supports_web_search(model_name)
+    
+    def _model_supports_web_fetch(self) -> bool:
+        """
+        Check if the agent's model supports web fetch via LiteLLM.
+        
+        Web fetch allows the model to retrieve full content from specific URLs.
+        Currently only supported by Anthropic Claude models.
+        
+        Returns:
+            bool: True if the model supports web fetch, False otherwise
+        """
+        from ..llm.model_capabilities import supports_web_fetch
+        
+        # Get the model name
+        if hasattr(self, 'llm_instance') and self.llm_instance:
+            model_name = self.llm_instance.model
+        elif hasattr(self, 'llm') and self.llm:
+            model_name = self.llm
+        else:
+            model_name = "gpt-5-nano"
+        
+        return supports_web_fetch(model_name)
+    
+    def _model_supports_prompt_caching(self) -> bool:
+        """
+        Check if the agent's model supports prompt caching via LiteLLM.
+        
+        Prompt caching allows caching parts of prompts to reduce costs and latency.
+        Supported by OpenAI, Anthropic, Bedrock, and Deepseek.
+        
+        Returns:
+            bool: True if the model supports prompt caching, False otherwise
+        """
+        from ..llm.model_capabilities import supports_prompt_caching
+        
+        # Get the model name
+        if hasattr(self, 'llm_instance') and self.llm_instance:
+            model_name = self.llm_instance.model
+        elif hasattr(self, 'llm') and self.llm:
+            model_name = self.llm
+        else:
+            model_name = "gpt-4o-mini"
+        
+        return supports_prompt_caching(model_name)
+    
     @property
     def llm_model(self):
         """Unified property to get the LLM model regardless of configuration type.

src/praisonai-agents/praisonaiagents/agent/prompt_expander_agent.py

@@ -0,0 +1,367 @@
+"""
+Prompt Expander Agent Module
+
+This module provides the PromptExpanderAgent class for expanding short prompts
+into detailed, comprehensive prompts for better task execution.
+
+Unlike QueryRewriterAgent (which optimizes queries for search/retrieval),
+PromptExpanderAgent focuses on enriching prompts for task execution.
+
+Supported Expansion Strategies:
+- **BASIC**: Simple expansion with clarity improvements
+- **DETAILED**: Rich expansion with context, constraints, and examples
+- **STRUCTURED**: Expansion with clear structure (task, format, requirements)
+- **CREATIVE**: Expansion with creative flair and vivid language
+- **AUTO**: Automatically selects the best strategy based on prompt analysis
+
+Example:
+    from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+    
+    agent = PromptExpanderAgent(verbose=True)
+    
+    # Basic expansion
+    result = agent.expand("write a movie script in 3 lines")
+    print(result.expanded_prompt)
+    
+    # Detailed expansion
+    result = agent.expand("blog about AI", strategy=ExpandStrategy.DETAILED)
+    print(result.expanded_prompt)
+    
+    # With tools for context gathering
+    from praisonaiagents.tools import internet_search
+    agent = PromptExpanderAgent(tools=[internet_search], verbose=True)
+    result = agent.expand("latest AI developments")
+"""
+
+import logging
+from typing import List, Optional, Any, Dict
+from dataclasses import dataclass, field
+from enum import Enum
+from datetime import datetime
+
+class ExpandStrategy(Enum):
+    """Enumeration of available prompt expansion strategies."""
+    BASIC = "basic"
+    DETAILED = "detailed"
+    STRUCTURED = "structured"
+    CREATIVE = "creative"
+    AUTO = "auto"
+
+
+@dataclass
+class ExpandResult:
+    """Result of a prompt expansion operation."""
+    original_prompt: str
+    expanded_prompt: str
+    strategy_used: ExpandStrategy
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    
+    def __repr__(self):
+        return f"ExpandResult(strategy={self.strategy_used.value}, original_len={len(self.original_prompt)}, expanded_len={len(self.expanded_prompt)})"
+
+
+class PromptExpanderAgent:
+    """
+    Agent for expanding short prompts into detailed, comprehensive prompts.
+    
+    This agent transforms brief task descriptions into rich, detailed prompts
+    that provide better context and guidance for task execution.
+    
+    Key difference from QueryRewriterAgent:
+    - QueryRewriterAgent: Optimizes queries for search/retrieval (RAG)
+    - PromptExpanderAgent: Expands prompts for detailed task execution
+    
+    Attributes:
+        name: Name of the agent
+        model: LLM model to use for expansion
+        verbose: Whether to print detailed logs
+        temperature: Temperature for LLM generation (higher = more creative)
+        tools: Optional tools for context gathering
+        
+    Example:
+        agent = PromptExpanderAgent(model="gpt-4o-mini", verbose=True)
+        result = agent.expand("write a poem", strategy=ExpandStrategy.CREATIVE)
+        print(result.expanded_prompt)
+    """
+    
+    # Default prompts for each strategy
+    PROMPTS = {
+        "basic": """You are an expert at improving task prompts.
+
+Current date: {current_date}
+
+Given the following task prompt, expand it to be clearer and more actionable while preserving the original intent.
+
+Guidelines:
+- Keep it as a TASK/COMMAND (do NOT convert to a question)
+- Add clarity without changing the core request
+- Fix any ambiguity
+- Keep it concise but complete
+- Use the current date for any time-sensitive context
+
+Original prompt: {prompt}
+
+Expanded prompt:""",
+
+        "detailed": """You are an expert at creating comprehensive task prompts.
+
+Current date: {current_date}
+
+Given the following brief task prompt, expand it into a detailed, actionable prompt that provides rich context and clear guidance.
+
+Guidelines:
+- Keep it as a TASK/COMMAND (do NOT convert to a question)
+- Add specific details about what to include
+- Specify quality expectations
+- Add relevant constraints or requirements
+- Include format guidance if applicable
+- Mention style or tone if relevant
+- Use the current date for any time-sensitive context
+
+Original prompt: {prompt}
+
+Detailed expanded prompt:""",
+
+        "structured": """You are an expert at creating well-structured task prompts.
+
+Current date: {current_date}
+
+Given the following task prompt, expand it into a structured format with clear sections.
+
+Guidelines:
+- Keep it as a TASK/COMMAND (do NOT convert to a question)
+- Use a clear structure:
+  * Task: What to do
+  * Format: Expected output format
+  * Requirements: Specific requirements
+  * Style: Tone or style guidance
+  * Constraints: Any limitations
+- Be specific and actionable
+- Use the current date for any time-sensitive context
+
+Original prompt: {prompt}
+
+Structured expanded prompt:""",
+
+        "creative": """You are an expert at crafting inspiring, creative task prompts.
+
+Current date: {current_date}
+
+Given the following task prompt, expand it with vivid language and creative direction while keeping it actionable.
+
+Guidelines:
+- Keep it as a TASK/COMMAND (do NOT convert to a question)
+- Use evocative, inspiring language
+- Paint a picture of the desired outcome
+- Add creative direction and artistic guidance
+- Make it exciting and engaging
+- Preserve the core task intent
+- Use the current date for any time-sensitive context
+
+Original prompt: {prompt}
+
+Creative expanded prompt:""",
+
+        "auto": """You are an expert at analyzing and expanding task prompts.
+
+Current date: {current_date}
+
+Analyze the following prompt and expand it appropriately based on its nature.
+
+For short/vague prompts: Add significant detail and context
+For task prompts: Preserve the action-oriented nature
+For creative tasks: Add artistic direction
+For technical tasks: Add precision and requirements
+
+IMPORTANT: Keep it as a TASK/COMMAND. Never convert to a question.
+Use the current date for any time-sensitive context.
+
+Original prompt: {prompt}
+{context}
+
+Expanded prompt:"""
+    }
+    
+    def __init__(
+        self,
+        name: str = "PromptExpanderAgent",
+        model: str = "gpt-4o-mini",
+        instructions: Optional[str] = None,
+        verbose: bool = False,
+        temperature: float = 0.7,  # Higher for creativity
+        max_tokens: int = 1000,
+        tools: Optional[List[Any]] = None
+    ):
+        """
+        Initialize the PromptExpanderAgent.
+        
+        Args:
+            name: Name of the agent
+            model: LLM model to use (default: gpt-4o-mini)
+            instructions: Custom instructions for the agent
+            verbose: Whether to print detailed logs
+            temperature: Temperature for LLM generation (default: 0.7 for creativity)
+            max_tokens: Maximum tokens for LLM response
+            tools: Optional list of tools for context gathering
+        """
+        self.name = name
+        self.model = model
+        self.instructions = instructions
+        self.verbose = verbose
+        self.temperature = temperature
+        self.max_tokens = max_tokens
+        self.tools = tools or []
+        self._agent = None  # Lazy initialized
+        
+        # Setup logging
+        self.logger = logging.getLogger(__name__)
+        if self.verbose:
+            self.logger.setLevel(logging.DEBUG)
+    
+    @property
+    def agent(self):
+        """Lazy initialization of internal Agent."""
+        if self._agent is None:
+            from .agent import Agent
+            self._agent = Agent(
+                name=self.name,
+                role="Prompt Expansion Specialist",
+                goal="Expand brief prompts into detailed, actionable prompts for better task execution. Use available tools when needed to gather context.",
+                backstory="You are an expert at understanding user intent and transforming brief requests into comprehensive, detailed prompts.",
+                tools=self.tools,
+                llm=self.model,
+                verbose=self.verbose,
+                markdown=False
+            )
+        return self._agent
+    
+    def _call_agent(self, prompt: str) -> str:
+        """Call the internal Agent with the given prompt."""
+        try:
+            response = self.agent.chat(prompt)
+            return response if response else ""
+        except Exception as e:
+            self.logger.error(f"Agent call failed: {e}")
+            raise
+    
+    def _is_short_prompt(self, prompt: str, threshold: int = 10) -> bool:
+        """Check if prompt is considered short."""
+        return len(prompt.split()) < threshold
+    
+    def _is_task_prompt(self, prompt: str) -> bool:
+        """Check if prompt is a task/command (vs a question)."""
+        task_verbs = [
+            "write", "create", "generate", "build", "make", "design",
+            "develop", "implement", "compose", "draft", "produce",
+            "craft", "construct", "prepare", "draw", "paint", "code"
+        ]
+        prompt_lower = prompt.lower().strip()
+        return any(prompt_lower.startswith(verb) for verb in task_verbs)
+    
+    def _is_creative_task(self, prompt: str) -> bool:
+        """Check if prompt is a creative task."""
+        creative_indicators = [
+            "poem", "story", "script", "song", "art", "creative",
+            "fiction", "novel", "essay", "blog", "article", "write"
+        ]
+        prompt_lower = prompt.lower()
+        return any(ind in prompt_lower for ind in creative_indicators)
+    
+    def _detect_strategy(self, prompt: str) -> ExpandStrategy:
+        """Auto-detect the best expansion strategy for a prompt."""
+        # Very short prompts need detailed expansion
+        if self._is_short_prompt(prompt, threshold=5):
+            return ExpandStrategy.DETAILED
+        
+        # Creative tasks benefit from creative expansion
+        if self._is_creative_task(prompt):
+            return ExpandStrategy.CREATIVE
+        
+        # Task prompts get structured expansion
+        if self._is_task_prompt(prompt):
+            return ExpandStrategy.STRUCTURED
+        
+        # Default to basic
+        return ExpandStrategy.BASIC
+    
+    def expand(
+        self,
+        prompt: str,
+        strategy: ExpandStrategy = ExpandStrategy.AUTO,
+        context: Optional[str] = None
+    ) -> ExpandResult:
+        """
+        Expand a prompt using the specified strategy.
+        
+        All operations go through an internal Agent which automatically handles
+        tool calling when tools are provided. The agent decides when to use tools
+        based on the prompt context.
+        
+        Args:
+            prompt: The original user prompt
+            strategy: Expansion strategy to use
+            context: Additional context to help with expansion
+            
+        Returns:
+            ExpandResult containing the expanded prompt
+        """
+        if self.verbose:
+            self.logger.debug(f"Expanding prompt: '{prompt}' with strategy: {strategy.value}")
+            if self.tools:
+                print(f"[cyan]Agent has {len(self.tools)} tools available (will use if needed)...[/cyan]")
+        
+        # Auto-detect strategy if needed
+        if strategy == ExpandStrategy.AUTO:
+            strategy = self._detect_strategy(prompt)
+            if self.verbose:
+                self.logger.debug(f"Auto-detected strategy: {strategy.value}")
+        
+        # Build the expansion prompt
+        if strategy == ExpandStrategy.AUTO:
+            # Fallback if auto-detect returns AUTO
+            strategy = ExpandStrategy.DETAILED
+        
+        # Get current date for time-sensitive context
+        current_date = datetime.now().strftime("%B %d, %Y")
+        
+        expansion_prompt = self.PROMPTS[strategy.value].format(
+            prompt=prompt,
+            context=context or "",
+            current_date=current_date
+        )
+        
+        # Call the agent
+        expanded = self._call_agent(expansion_prompt).strip()
+        
+        # If expansion failed, return original
+        if not expanded:
+            expanded = prompt
+        
+        return ExpandResult(
+            original_prompt=prompt,
+            expanded_prompt=expanded,
+            strategy_used=strategy,
+            metadata={
+                "original_length": len(prompt),
+                "expanded_length": len(expanded),
+                "has_context": bool(context),
+                "has_tools": bool(self.tools)
+            }
+        )
+    
+    # Convenience methods for direct strategy access
+    def expand_basic(self, prompt: str, context: Optional[str] = None) -> ExpandResult:
+        """Convenience method for basic expansion."""
+        return self.expand(prompt, strategy=ExpandStrategy.BASIC, context=context)
+    
+    def expand_detailed(self, prompt: str, context: Optional[str] = None) -> ExpandResult:
+        """Convenience method for detailed expansion."""
+        return self.expand(prompt, strategy=ExpandStrategy.DETAILED, context=context)
+    
+    def expand_structured(self, prompt: str, context: Optional[str] = None) -> ExpandResult:
+        """Convenience method for structured expansion."""
+        return self.expand(prompt, strategy=ExpandStrategy.STRUCTURED, context=context)
+    
+    def expand_creative(self, prompt: str, context: Optional[str] = None) -> ExpandResult:
+        """Convenience method for creative expansion."""
+        return self.expand(prompt, strategy=ExpandStrategy.CREATIVE, context=context)

src/praisonai-agents/praisonaiagents/agent/query_rewriter_agent.py

@@ -110,20 +110,23 @@ class QueryRewriterAgent:
     
     # Default prompts for each strategy
     PROMPTS = {
-        "basic": """You are an expert at rewriting search queries for better retrieval.
+        "basic": """You are an expert at improving prompts and queries.
 
-Given the following query, rewrite it to be clearer, more specific, and better suited for searching a knowledge base.
+Given the following input, improve it while preserving its original intent and type.
 
 Guidelines:
+- If it's a TASK (e.g., "write X", "create Y", "generate Z"), keep it as a task - do NOT convert to a question
+- If it's a QUESTION (e.g., "what is X?", "how does Y work?"), keep it as a question
 - Expand abbreviations and acronyms
 - Fix typos and grammatical errors
-- Add relevant context if the query is too short
-- Transform keyword searches into natural questions
-- Keep the original intent intact
+- Add relevant context if too short
+- Keep the original intent and action intact
 
-Query: {query}
+IMPORTANT: If the input is a command/task to DO something, the output must also be a command/task to DO that thing.
 
-Rewritten query:""",
+Input: {query}
+
+Improved version:""",
 
         "hyde": """You are an expert at generating hypothetical documents.
 
@@ -198,21 +201,23 @@ Follow-up query: {query}
 
 Standalone question:""",
 
-        "auto": """You are an expert at analyzing and rewriting queries.
+        "auto": """You are an expert at analyzing and improving prompts and queries.
 
-Analyze the following query and determine the best rewriting strategy, then apply it.
+Analyze the following input and improve it while preserving its original intent and type.
 
-Query types to consider:
-1. Short/keyword queries → Expand into full questions
-2. Ambiguous queries → Clarify with context
-3. Complex multi-part queries → Break into sub-queries
-4. Follow-up queries → Resolve references from context
-5. Well-formed queries → Minor optimization only
+Input types to consider:
+1. TASK/COMMAND (write, create, generate, build) → Keep as a task, make it clearer
+2. QUESTION (what, how, why, when) → Keep as a question, make it more specific
+3. Short/keyword inputs → Expand with context but preserve type
+4. Complex multi-part inputs → Clarify structure
+5. Well-formed inputs → Minor optimization only
 
-Query: {query}
+IMPORTANT: Never convert a task into a question. "Write X" should remain "Write X", not "How to write X?"
+
+Input: {query}
 {context}
 
-Analysis and rewritten query:"""
+Improved version:"""
     }
     
     def __init__(

src/praisonai-agents/praisonaiagents/llm/llm.py

@@ -239,6 +239,9 @@ class LLM:
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         events: List[Any] = [],
+        web_search: Optional[Union[bool, Dict[str, Any]]] = None,
+        web_fetch: Optional[Union[bool, Dict[str, Any]]] = None,
+        prompt_caching: Optional[bool] = None,
         **extra_settings
     ):
         # Configure logging only once at the class level
@@ -273,6 +276,9 @@ class LLM:
         self.base_url = base_url
         self.events = events
         self.extra_settings = extra_settings
+        self.web_search = web_search
+        self.web_fetch = web_fetch
+        self.prompt_caching = prompt_caching
         self._console = None  # Lazy load console when needed
         self.chat_history = []
         self.verbose = extra_settings.get('verbose', True)
@@ -381,6 +387,45 @@ class LLM:
         else:
             return False
 
+    def _supports_web_search(self) -> bool:
+        """
+        Check if the current model supports native web search via LiteLLM.
+        
+        Native web search allows the model to search the web in real-time
+        without requiring external tools like DuckDuckGo.
+        
+        Returns:
+            bool: True if the model supports native web search, False otherwise
+        """
+        from .model_capabilities import supports_web_search
+        return supports_web_search(self.model)
+
+    def _supports_web_fetch(self) -> bool:
+        """
+        Check if the current model supports web fetch via LiteLLM.
+        
+        Web fetch allows the model to retrieve full content from specific URLs
+        (web pages and PDF documents). Currently only supported by Anthropic Claude models.
+        
+        Returns:
+            bool: True if the model supports web fetch, False otherwise
+        """
+        from .model_capabilities import supports_web_fetch
+        return supports_web_fetch(self.model)
+
+    def _supports_prompt_caching(self) -> bool:
+        """
+        Check if the current model supports prompt caching via LiteLLM.
+        
+        Prompt caching allows caching parts of prompts to reduce costs and latency.
+        Supported by OpenAI, Anthropic, Bedrock, and Deepseek.
+        
+        Returns:
+            bool: True if the model supports prompt caching, False otherwise
+        """
+        from .model_capabilities import supports_prompt_caching
+        return supports_prompt_caching(self.model)
+
     def _generate_ollama_tool_summary(self, tool_results: List[Any], response_text: str) -> Optional[str]:
         """
         Generate a summary from tool results for Ollama to prevent infinite loops.
@@ -724,7 +769,21 @@ class LLM:
             
             # Skip system messages for legacy o1 models as they don't support them
             if not self._needs_system_message_skip():
-                messages.append({"role": "system", "content": system_prompt})
+                # Apply prompt caching for Anthropic models if enabled
+                if self.prompt_caching and self._supports_prompt_caching() and self._is_anthropic_model():
+                    # Anthropic requires cache_control in content array format
+                    messages.append({
+                        "role": "system",
+                        "content": [
+                            {
+                                "type": "text",
+                                "text": system_prompt,
+                                "cache_control": {"type": "ephemeral"}
+                            }
+                        ]
+                    })
+                else:
+                    messages.append({"role": "system", "content": system_prompt})
         
         # Add chat history if provided
         if chat_history:
@@ -2295,6 +2354,12 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             return False
         return any(prefix in self.model.lower() for prefix in ['gemini', 'gemini/', 'google/gemini'])
     
+    def _is_anthropic_model(self) -> bool:
+        """Check if the model is an Anthropic Claude model."""
+        if not self.model:
+            return False
+        return any(prefix in self.model.lower() for prefix in ['claude', 'anthropic/', 'anthropic/claude'])
+    
     def _is_streaming_error_recoverable(self, error: Exception) -> bool:
         """Check if a streaming error is recoverable (e.g., malformed chunk vs connection error)."""
         error_msg = str(error).lower()
@@ -3171,6 +3236,57 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                     logging.debug(f"Could not verify function calling support: {e}. Setting tool_choice anyway.")
                     params['tool_choice'] = 'auto'
         
+        # Add web_search_options if web_search is enabled and model supports it
+        if self.web_search and self._supports_web_search():
+            if isinstance(self.web_search, dict):
+                # Use custom web_search_options provided by user
+                params['web_search_options'] = self.web_search
+            else:
+                # Use default web_search_options
+                params['web_search_options'] = {"search_context_size": "medium"}
+            logging.debug(f"Web search enabled with options: {params['web_search_options']}")
+            
+            # Some web search models (like gpt-4o-search-preview) don't support certain parameters
+            # Remove incompatible parameters to avoid BadRequestError
+            incompatible_params = ['temperature', 'top_p', 'presence_penalty', 'frequency_penalty', 'logit_bias']
+            for param in incompatible_params:
+                if param in params:
+                    del params[param]
+                    logging.debug(f"Removed incompatible parameter '{param}' for web search model")
+        
+        # Add web_fetch tool if web_fetch is enabled and model supports it
+        # Web fetch is passed as a tool (unlike web_search which uses web_search_options)
+        if self.web_fetch and self._supports_web_fetch():
+            # Build the web_fetch tool definition
+            web_fetch_tool = {
+                "type": "web_fetch_20250910",
+                "name": "web_fetch",
+            }
+            
+            # Add optional parameters from web_fetch dict if provided
+            if isinstance(self.web_fetch, dict):
+                if 'max_uses' in self.web_fetch:
+                    web_fetch_tool['max_uses'] = self.web_fetch['max_uses']
+                if 'allowed_domains' in self.web_fetch:
+                    web_fetch_tool['allowed_domains'] = self.web_fetch['allowed_domains']
+                if 'blocked_domains' in self.web_fetch:
+                    web_fetch_tool['blocked_domains'] = self.web_fetch['blocked_domains']
+                if 'citations' in self.web_fetch:
+                    web_fetch_tool['citations'] = self.web_fetch['citations']
+                if 'max_content_tokens' in self.web_fetch:
+                    web_fetch_tool['max_content_tokens'] = self.web_fetch['max_content_tokens']
+            else:
+                # Default max_uses if web_fetch=True
+                web_fetch_tool['max_uses'] = 5
+            
+            # Add web_fetch tool to existing tools or create tools list
+            if 'tools' in params and params['tools']:
+                params['tools'].append(web_fetch_tool)
+            else:
+                params['tools'] = [web_fetch_tool]
+            
+            logging.debug(f"Web fetch enabled with tool: {web_fetch_tool}")
+        
         return params
 
     def _prepare_response_logging(self, temperature: float, stream: bool, verbose: bool, markdown: bool, **kwargs) -> Optional[Dict[str, Any]]:

src/praisonai-agents/praisonaiagents/llm/model_capabilities.py

@@ -1,62 +1,30 @@
 """
 Model capabilities configuration for different LLM providers.
-This module defines which models support specific features like structured outputs.
+
+This module uses LiteLLM's helper functions as the primary source for model capability detection.
+LiteLLM is maintained by many contributors and is more accurate and up-to-date.
+
+LiteLLM Helper Functions:
+- litellm.supports_web_search(model=) - Check web search support
+- litellm.supports_function_calling(model=) - Check function calling support
+- litellm.supports_parallel_function_calling(model=) - Check parallel function calling
+- litellm.supports_response_schema(model=) - Check JSON schema/structured outputs support
+- litellm.utils.supports_prompt_caching(model=) - Check prompt caching support
+- litellm.get_supported_openai_params(model=) - Get all supported params
+
+Sources:
+- https://docs.litellm.ai/docs/completion/web_search
+- https://docs.litellm.ai/docs/completion/json_mode
+- https://docs.litellm.ai/docs/completion/function_call
+- https://docs.litellm.ai/docs/completion/prompt_caching
 """
 
-# Models that support OpenAI-style structured outputs (response_format with Pydantic models)
-MODELS_SUPPORTING_STRUCTURED_OUTPUTS = {
-    # OpenAI models
-    "gpt-5-nano",
-    "gpt-5-nano",
-    "gpt-4-turbo",
-    "gpt-4-turbo-preview",
-    "gpt-4-turbo-2024-04-09",
-    "gpt-4-1106-preview",
-    "gpt-4-0125-preview",
-    "gpt-3.5-turbo",
-    "gpt-3.5-turbo-1106",
-    "gpt-3.5-turbo-0125",
-    
-    # New/Future OpenAI models (as mentioned by user)
-    "codex-mini",
-    "o3-pro",
-    "gpt-4.5-preview",
-    "o3-mini",
-    "o1",
-    "o1-preview",
-    "o1-mini",
-    "gpt-4.1",
-    "gpt-4.1-nano",
-    "gpt-4.1-mini",
-    "o4-mini",
-    "o3",
-    
-    # Gemini models that support structured outputs
-    "gemini-2.0-flash",
-    "gemini-2.0-flash-exp",
-    "gemini-1.5-pro",
-    "gemini-1.5-pro-latest",
-    "gemini-1.5-flash",
-    "gemini-1.5-flash-latest",
-    "gemini-1.5-flash-8b",
-    "gemini-1.5-flash-8b-latest",
-}
-
-# Models that explicitly DON'T support structured outputs
-MODELS_NOT_SUPPORTING_STRUCTURED_OUTPUTS = {
-    # Audio preview models
-    "gpt-4o-audio-preview",
-    "gpt-5-nano-audio-preview",
-    
-    # Legacy o1 models (don't support system messages either)
-    "o1-preview-2024-09-12",
-    "o1-mini-2024-09-12",
-}
-
 
 def supports_structured_outputs(model_name: str) -> bool:
     """
-    Check if a model supports OpenAI-style structured outputs.
+    Check if a model supports structured outputs (JSON schema).
+    
+    Uses LiteLLM's supports_response_schema() as the primary check.
     
     Args:
         model_name: The name of the model to check
@@ -67,34 +35,72 @@ def supports_structured_outputs(model_name: str) -> bool:
     if not model_name:
         return False
     
-    # Strip provider prefixes (e.g., 'google/', 'openai/', etc.)
-    model_without_provider = model_name
-    for prefix in ['google/', 'openai/', 'anthropic/', 'gemini/', 'mistral/', 'deepseek/', 'groq/']:
-        if model_name.startswith(prefix):
-            model_without_provider = model_name[len(prefix):]
-            break
+    try:
+        import litellm
+        # Use LiteLLM's built-in check - most accurate and up-to-date
+        if hasattr(litellm, 'supports_response_schema'):
+            return litellm.supports_response_schema(model=model_name)
+    except Exception:
+        pass
     
-    # First check if it's explicitly in the NOT supporting list
-    if model_without_provider in MODELS_NOT_SUPPORTING_STRUCTURED_OUTPUTS:
+    return False
+
+
+def supports_function_calling(model_name: str) -> bool:
+    """
+    Check if a model supports function calling.
+    
+    Uses LiteLLM's supports_function_calling() as the primary check.
+    
+    Args:
+        model_name: The name of the model to check
+        
+    Returns:
+        bool: True if the model supports function calling, False otherwise
+    """
+    if not model_name:
         return False
     
-    # Then check if it's in the supporting list
-    if model_without_provider in MODELS_SUPPORTING_STRUCTURED_OUTPUTS:
-        return True
+    try:
+        import litellm
+        # Use LiteLLM's built-in check - most accurate and up-to-date
+        if hasattr(litellm, 'supports_function_calling'):
+            return litellm.supports_function_calling(model=model_name)
+    except Exception:
+        pass
     
-    # For models with version suffixes, check the base model name
-    base_model = model_without_provider.split('-2024-')[0].split('-2025-')[0]
-    if base_model in MODELS_SUPPORTING_STRUCTURED_OUTPUTS:
-        return True
+    return False
+
+
+def supports_parallel_function_calling(model_name: str) -> bool:
+    """
+    Check if a model supports parallel function calling.
+    
+    Uses LiteLLM's supports_parallel_function_calling() as the primary check.
+    
+    Args:
+        model_name: The name of the model to check
+        
+    Returns:
+        bool: True if the model supports parallel function calling, False otherwise
+    """
+    if not model_name:
+        return False
+    
+    try:
+        import litellm
+        # Use LiteLLM's built-in check - most accurate and up-to-date
+        if hasattr(litellm, 'supports_parallel_function_calling'):
+            return litellm.supports_parallel_function_calling(model=model_name)
+    except Exception:
+        pass
     
-    # Default to False for unknown models
     return False
 
 
 def supports_streaming_with_tools(model_name: str) -> bool:
     """
     Check if a model supports streaming when tools are provided.
-    Most models that support structured outputs also support streaming with tools.
     
     Args:
         model_name: The name of the model to check
@@ -102,15 +108,153 @@ def supports_streaming_with_tools(model_name: str) -> bool:
     Returns:
         bool: True if the model supports streaming with tools, False otherwise
     """
-    # For now, use the same logic as structured outputs
-    # In the future, this could be a separate list if needed
-    return supports_structured_outputs(model_name)
+    # Models that support function calling generally support streaming with tools
+    return supports_function_calling(model_name)
 
 
 # Supported Gemini internal tools
 GEMINI_INTERNAL_TOOLS = {'googleSearch', 'urlContext', 'codeExecution'}
 
 
+def supports_web_search(model_name: str) -> bool:
+    """
+    Check if a model supports native web search via LiteLLM.
+    
+    Uses LiteLLM's supports_web_search() as the primary check.
+    
+    Native web search allows the model to search the web in real-time
+    without requiring external tools like DuckDuckGo.
+    
+    Supported providers:
+    - OpenAI (gpt-4o-search-preview, gpt-4o-mini-search-preview)
+    - xAI (grok-3)
+    - Anthropic (claude-3-5-sonnet-latest, claude-sonnet-4, etc.)
+    - Google/Vertex AI (gemini-2.0-flash, gemini-2.5-*, etc.)
+    - Perplexity (all models)
+    
+    Args:
+        model_name: The name of the model to check (with or without provider prefix)
+        
+    Returns:
+        bool: True if the model supports native web search, False otherwise
+    """
+    if not model_name:
+        return False
+    
+    try:
+        import litellm
+        # Use LiteLLM's built-in check - most accurate and up-to-date
+        if hasattr(litellm, 'supports_web_search'):
+            return litellm.supports_web_search(model=model_name)
+    except Exception:
+        pass
+    
+    return False
+
+
+def supports_prompt_caching(model_name: str) -> bool:
+    """
+    Check if a model supports prompt caching via LiteLLM.
+    
+    Uses LiteLLM's supports_prompt_caching() as the primary check.
+    
+    Prompt caching allows caching parts of prompts to reduce costs and latency
+    on subsequent requests with similar prompts.
+    
+    Supported providers:
+    - OpenAI (openai/) - Automatic caching for prompts ≥1024 tokens
+    - Anthropic (anthropic/) - Manual caching with cache_control
+    - Bedrock (bedrock/) - All models that support prompt caching
+    - Deepseek (deepseek/) - Works like OpenAI
+    
+    Args:
+        model_name: The name of the model to check (with or without provider prefix)
+        
+    Returns:
+        bool: True if the model supports prompt caching, False otherwise
+    """
+    if not model_name:
+        return False
+    
+    try:
+        from litellm.utils import supports_prompt_caching as litellm_supports_prompt_caching
+        return litellm_supports_prompt_caching(model=model_name)
+    except Exception:
+        pass
+    
+    return False
+
+
+# Models that support web fetch via LiteLLM (Anthropic only)
+# Web fetch retrieves full content from specific URLs (web pages and PDFs)
+# Source: https://docs.litellm.ai/docs/completion/web_fetch
+# Note: LiteLLM doesn't have a supports_web_fetch() helper yet, so we maintain a static list
+MODELS_SUPPORTING_WEB_FETCH = {
+    # Anthropic Claude models with web fetch support
+    "claude-opus-4-1-20250805",
+    "claude-opus-4-1",
+    "claude-opus-4-20250514",
+    "claude-opus-4",
+    "claude-sonnet-4-20250514",
+    "claude-sonnet-4",
+    "claude-3-7-sonnet-20250219",
+    "claude-3-7-sonnet-latest",
+    "claude-3-5-sonnet-latest",
+    "claude-3-5-sonnet-20241022",
+    "claude-3-5-haiku-latest",
+    "claude-3-5-haiku-20241022",
+}
+
+
+def supports_web_fetch(model_name: str) -> bool:
+    """
+    Check if a model supports web fetch via LiteLLM.
+    
+    Web fetch allows the model to retrieve full content from specific URLs
+    (web pages and PDF documents). Currently only supported by Anthropic Claude models.
+    
+    Note: LiteLLM doesn't have a supports_web_fetch() helper yet, so we use a static list
+    with auto-detection for Claude 4+ models.
+    
+    Args:
+        model_name: The name of the model to check (with or without provider prefix)
+        
+    Returns:
+        bool: True if the model supports web fetch, False otherwise
+    """
+    if not model_name:
+        return False
+    
+    # Strip provider prefixes
+    model_without_provider = model_name
+    for prefix in ['anthropic/', 'bedrock/', 'vertex_ai/']:
+        if model_name.startswith(prefix):
+            model_without_provider = model_name[len(prefix):]
+            break
+    
+    # Check our static list
+    if model_without_provider in MODELS_SUPPORTING_WEB_FETCH:
+        return True
+    
+    # Check base model name (without version suffix)
+    base_model = model_without_provider.split('-2024-')[0].split('-2025-')[0]
+    if base_model in MODELS_SUPPORTING_WEB_FETCH:
+        return True
+    
+    # Auto-support for Claude 4+ models (Anthropic only)
+    model_lower = model_without_provider.lower()
+    if 'claude' in model_lower:
+        import re
+        # Match patterns like claude-4, claude-5, claude-sonnet-4, claude-opus-4, etc.
+        version_match = re.search(r'claude-(?:sonnet-|opus-|haiku-)?(\d+)', model_lower)
+        if version_match:
+            version = int(version_match.group(1))
+            if version >= 4:  # Claude 4 and later
+                return True
+    
+    return False
+
+
 def is_gemini_internal_tool(tool) -> bool:
     """
     Check if a tool is a Gemini internal tool and should be included in formatted tools.

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.0.169"
+version = "0.0.175"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 requires-python = ">=3.10"
 authors = [

src/praisonai-agents/tests/test_prompt_caching.py

@@ -0,0 +1,239 @@
+"""
+Tests for prompt caching feature.
+
+Prompt caching allows caching parts of prompts to reduce costs and latency.
+Supported by OpenAI, Anthropic, Bedrock, and Deepseek.
+
+Source: https://docs.litellm.ai/docs/completion/prompt_caching
+"""
+
+import pytest
+from unittest.mock import patch, MagicMock
+
+
+class TestSupportsPromptCaching:
+    """Tests for the supports_prompt_caching function in model_capabilities.py"""
+    
+    def test_supports_prompt_caching_anthropic(self):
+        """Test that Anthropic Claude models support prompt caching."""
+        from praisonaiagents.llm.model_capabilities import supports_prompt_caching
+        
+        # Mock litellm.utils.supports_prompt_caching
+        with patch('praisonaiagents.llm.model_capabilities.supports_prompt_caching') as mock_func:
+            # Just test that the function exists and can be called
+            mock_func.return_value = True
+            result = mock_func(model="anthropic/claude-3-5-sonnet-latest")
+            assert result == True
+    
+    def test_supports_prompt_caching_openai(self):
+        """Test that OpenAI models support prompt caching."""
+        from praisonaiagents.llm.model_capabilities import supports_prompt_caching
+        
+        with patch('litellm.utils.supports_prompt_caching', return_value=True):
+            # The function should delegate to litellm
+            result = supports_prompt_caching("openai/gpt-4o")
+            # Result depends on litellm's implementation
+            assert isinstance(result, bool)
+    
+    def test_supports_prompt_caching_empty_model(self):
+        """Test that empty model name returns False."""
+        from praisonaiagents.llm.model_capabilities import supports_prompt_caching
+        
+        assert supports_prompt_caching("") == False
+        assert supports_prompt_caching(None) == False
+
+
+class TestLLMPromptCachingParameter:
+    """Tests for prompt_caching parameter in LLM class."""
+    
+    def test_llm_init_with_prompt_caching_true(self):
+        """Test LLM initialization with prompt_caching=True."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", prompt_caching=True)
+        assert llm.prompt_caching == True
+    
+    def test_llm_init_with_prompt_caching_false(self):
+        """Test LLM initialization with prompt_caching=False."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", prompt_caching=False)
+        assert llm.prompt_caching == False
+    
+    def test_llm_init_without_prompt_caching(self):
+        """Test LLM initialization without prompt_caching parameter."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="gpt-4o-mini")
+        assert llm.prompt_caching is None
+    
+    def test_llm_supports_prompt_caching_method(self):
+        """Test _supports_prompt_caching method exists and works."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest")
+        # Method should exist and return a boolean
+        result = llm._supports_prompt_caching()
+        assert isinstance(result, bool)
+    
+    def test_llm_is_anthropic_model_method(self):
+        """Test _is_anthropic_model method."""
+        from praisonaiagents.llm.llm import LLM
+        
+        # Anthropic model
+        llm_anthropic = LLM(model="anthropic/claude-3-5-sonnet-latest")
+        assert llm_anthropic._is_anthropic_model() == True
+        
+        # OpenAI model
+        llm_openai = LLM(model="gpt-4o-mini")
+        assert llm_openai._is_anthropic_model() == False
+        
+        # Gemini model
+        llm_gemini = LLM(model="gemini/gemini-2.0-flash")
+        assert llm_gemini._is_anthropic_model() == False
+
+
+class TestLLMBuildMessagesWithPromptCaching:
+    """Tests for _build_messages with prompt caching enabled."""
+    
+    def test_build_messages_with_prompt_caching_anthropic(self):
+        """Test that _build_messages adds cache_control for Anthropic models."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", prompt_caching=True)
+        
+        # Mock _supports_prompt_caching to return True
+        with patch.object(llm, '_supports_prompt_caching', return_value=True):
+            messages, _ = llm._build_messages(
+                prompt="Hello",
+                system_prompt="You are a helpful assistant."
+            )
+            
+            # Check that system message has cache_control
+            system_msg = messages[0]
+            assert system_msg["role"] == "system"
+            # For Anthropic with prompt_caching, content should be an array
+            assert isinstance(system_msg["content"], list)
+            assert system_msg["content"][0]["type"] == "text"
+            assert system_msg["content"][0]["cache_control"] == {"type": "ephemeral"}
+    
+    def test_build_messages_without_prompt_caching(self):
+        """Test that _build_messages doesn't add cache_control when disabled."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", prompt_caching=False)
+        
+        messages, _ = llm._build_messages(
+            prompt="Hello",
+            system_prompt="You are a helpful assistant."
+        )
+        
+        # Check that system message is a simple string
+        system_msg = messages[0]
+        assert system_msg["role"] == "system"
+        assert isinstance(system_msg["content"], str)
+    
+    def test_build_messages_prompt_caching_non_anthropic(self):
+        """Test that prompt caching doesn't affect non-Anthropic models."""
+        from praisonaiagents.llm.llm import LLM
+        
+        llm = LLM(model="gpt-4o-mini", prompt_caching=True)
+        
+        messages, _ = llm._build_messages(
+            prompt="Hello",
+            system_prompt="You are a helpful assistant."
+        )
+        
+        # For non-Anthropic models, content should remain a string
+        system_msg = messages[0]
+        assert system_msg["role"] == "system"
+        assert isinstance(system_msg["content"], str)
+
+
+class TestAgentPromptCachingParameter:
+    """Tests for prompt_caching parameter in Agent class."""
+    
+    def test_agent_init_with_prompt_caching_true(self):
+        """Test Agent initialization with prompt_caching=True."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            prompt_caching=True
+        )
+        assert agent.prompt_caching == True
+    
+    def test_agent_init_with_prompt_caching_false(self):
+        """Test Agent initialization with prompt_caching=False."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            prompt_caching=False
+        )
+        assert agent.prompt_caching == False
+    
+    def test_agent_init_without_prompt_caching(self):
+        """Test Agent initialization without prompt_caching parameter."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(name="Test Agent")
+        assert agent.prompt_caching is None
+    
+    def test_agent_model_supports_prompt_caching_method(self):
+        """Test _model_supports_prompt_caching method exists."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest"
+        )
+        # Method should exist and return a boolean
+        result = agent._model_supports_prompt_caching()
+        assert isinstance(result, bool)
+    
+    def test_agent_passes_prompt_caching_to_llm(self):
+        """Test that Agent passes prompt_caching to LLM instance."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            prompt_caching=True
+        )
+        
+        # Check that LLM instance has prompt_caching set
+        if hasattr(agent, 'llm_instance') and agent.llm_instance:
+            assert agent.llm_instance.prompt_caching == True
+
+
+class TestPromptCachingIntegration:
+    """Integration tests for prompt caching (requires API key)."""
+    
+    @pytest.mark.skip(reason="Requires ANTHROPIC_API_KEY environment variable")
+    def test_prompt_caching_with_anthropic(self):
+        """Test prompt caching with actual Anthropic API."""
+        import os
+        from praisonaiagents import Agent
+        
+        # Skip if no API key
+        if not os.getenv("ANTHROPIC_API_KEY"):
+            pytest.skip("ANTHROPIC_API_KEY not set")
+        
+        agent = Agent(
+            name="Caching Test Agent",
+            instructions="You are a helpful assistant." * 100,  # Long system prompt
+            llm="anthropic/claude-3-5-sonnet-latest",
+            prompt_caching=True,
+            verbose=False
+        )
+        
+        # First call - should create cache
+        result1 = agent.start("What is 2+2?")
+        assert result1 is not None
+        
+        # Second call - should use cache
+        result2 = agent.start("What is 3+3?")
+        assert result2 is not None

src/praisonai-agents/tests/test_prompt_expander_agent.py

@@ -0,0 +1,316 @@
+"""
+Tests for PromptExpanderAgent
+
+Run with: python -m pytest tests/test_prompt_expander_agent.py -v
+"""
+
+import pytest
+from unittest.mock import patch, MagicMock
+
+
+class TestPromptExpanderImports:
+    """Test that all imports work correctly."""
+    
+    def test_import_from_package(self):
+        """Test importing from main package."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy, ExpandResult
+        assert PromptExpanderAgent is not None
+        assert ExpandStrategy is not None
+        assert ExpandResult is not None
+    
+    def test_import_from_agent_module(self):
+        """Test importing from agent module."""
+        from praisonaiagents.agent import PromptExpanderAgent, ExpandStrategy, ExpandResult
+        assert PromptExpanderAgent is not None
+        assert ExpandStrategy is not None
+        assert ExpandResult is not None
+
+
+class TestExpandStrategy:
+    """Test ExpandStrategy enum."""
+    
+    def test_strategy_values(self):
+        """Test all strategy values exist."""
+        from praisonaiagents import ExpandStrategy
+        
+        assert ExpandStrategy.BASIC.value == "basic"
+        assert ExpandStrategy.DETAILED.value == "detailed"
+        assert ExpandStrategy.STRUCTURED.value == "structured"
+        assert ExpandStrategy.CREATIVE.value == "creative"
+        assert ExpandStrategy.AUTO.value == "auto"
+
+
+class TestExpandResult:
+    """Test ExpandResult dataclass."""
+    
+    def test_result_creation(self):
+        """Test creating an ExpandResult."""
+        from praisonaiagents import ExpandResult, ExpandStrategy
+        
+        result = ExpandResult(
+            original_prompt="write a movie script",
+            expanded_prompt="Write a compelling movie script...",
+            strategy_used=ExpandStrategy.BASIC
+        )
+        
+        assert result.original_prompt == "write a movie script"
+        assert result.expanded_prompt == "Write a compelling movie script..."
+        assert result.strategy_used == ExpandStrategy.BASIC
+    
+    def test_result_with_metadata(self):
+        """Test ExpandResult with metadata."""
+        from praisonaiagents import ExpandResult, ExpandStrategy
+        
+        result = ExpandResult(
+            original_prompt="test",
+            expanded_prompt="expanded test",
+            strategy_used=ExpandStrategy.DETAILED,
+            metadata={"word_count": 50, "has_context": True}
+        )
+        
+        assert result.metadata["word_count"] == 50
+        assert result.metadata["has_context"] is True
+
+
+class TestPromptExpanderAgentInit:
+    """Test PromptExpanderAgent initialization."""
+    
+    def test_default_initialization(self):
+        """Test agent initializes with defaults."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent()
+        
+        assert agent.name == "PromptExpanderAgent"
+        assert agent.model == "gpt-4o-mini"
+        assert not agent.verbose
+        assert agent.temperature == 0.7  # Higher for creativity
+    
+    def test_custom_initialization(self):
+        """Test agent initializes with custom values."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent(
+            name="CustomExpander",
+            model="gpt-4o",
+            verbose=True,
+            temperature=0.5
+        )
+        
+        assert agent.name == "CustomExpander"
+        assert agent.model == "gpt-4o"
+        assert agent.verbose
+        assert agent.temperature == 0.5
+    
+    def test_initialization_with_tools(self):
+        """Test agent initializes with tools."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        def mock_tool(query: str) -> str:
+            return "mock result"
+        
+        agent = PromptExpanderAgent(tools=[mock_tool])
+        
+        assert len(agent.tools) == 1
+
+
+class TestPromptExpansion:
+    """Test prompt expansion functionality."""
+    
+    def test_expand_preserves_task_intent(self):
+        """Test that expansion preserves task intent (not converting to question)."""
+        from praisonaiagents import PromptExpanderAgent, ExpandResult
+        
+        agent = PromptExpanderAgent()
+        
+        # Mock the internal agent call
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = "Write a compelling three-line movie script that captures a dramatic moment with vivid imagery and emotional depth."
+            
+            result = agent.expand("write a movie script in 3 lines")
+            
+            assert result.original_prompt == "write a movie script in 3 lines"
+            assert "Write" in result.expanded_prompt  # Should start with action verb
+            assert "?" not in result.expanded_prompt  # Should NOT be a question
+    
+    def test_expand_adds_detail(self):
+        """Test that expansion adds meaningful detail."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = "Create a detailed blog post about artificial intelligence trends in 2025, covering key developments in large language models, multimodal AI, and autonomous agents. Include specific examples and expert predictions."
+            
+            result = agent.expand("write about AI")
+            
+            # Expanded should be longer than original
+            assert len(result.expanded_prompt) > len(result.original_prompt)
+
+
+class TestExpandStrategies:
+    """Test different expansion strategies."""
+    
+    def test_basic_strategy(self):
+        """Test BASIC expansion strategy."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = "Write a movie script in three lines."
+            
+            result = agent.expand("movie script 3 lines", strategy=ExpandStrategy.BASIC)
+            
+            assert result.strategy_used == ExpandStrategy.BASIC
+            mock_call.assert_called_once()
+    
+    def test_detailed_strategy(self):
+        """Test DETAILED expansion strategy."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = """Write a compelling three-line movie script that:
+- Opens with a hook that immediately grabs attention
+- Builds tension or emotion in the middle line
+- Delivers a powerful, memorable conclusion
+Include vivid imagery, strong verbs, and emotional resonance."""
+            
+            result = agent.expand("movie script 3 lines", strategy=ExpandStrategy.DETAILED)
+            
+            assert result.strategy_used == ExpandStrategy.DETAILED
+    
+    def test_structured_strategy(self):
+        """Test STRUCTURED expansion strategy."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = """Task: Write a three-line movie script
+Format: Three lines, each serving a narrative purpose
+Requirements:
+- Line 1: Setup/Hook
+- Line 2: Conflict/Development  
+- Line 3: Resolution/Twist
+Style: Cinematic, impactful"""
+            
+            result = agent.expand("movie script 3 lines", strategy=ExpandStrategy.STRUCTURED)
+            
+            assert result.strategy_used == ExpandStrategy.STRUCTURED
+    
+    def test_creative_strategy(self):
+        """Test CREATIVE expansion strategy."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = "Craft an unforgettable three-line movie script that transports the reader into a vivid world. Let each line breathe with cinematic tension - a hook that grabs, a twist that surprises, and a finale that lingers in the mind long after reading."
+            
+            result = agent.expand("movie script 3 lines", strategy=ExpandStrategy.CREATIVE)
+            
+            assert result.strategy_used == ExpandStrategy.CREATIVE
+    
+    def test_auto_strategy_detection(self):
+        """Test AUTO strategy detects appropriate expansion type."""
+        from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+        
+        agent = PromptExpanderAgent()
+        
+        # Short prompts should get DETAILED expansion
+        strategy = agent._detect_strategy("AI")
+        assert strategy in [ExpandStrategy.BASIC, ExpandStrategy.DETAILED]
+        
+        # Task prompts should preserve task nature
+        strategy = agent._detect_strategy("write a poem about love")
+        assert strategy is not None
+
+
+class TestToolsIntegration:
+    """Test tools integration with PromptExpanderAgent."""
+    
+    def test_expand_with_tools(self):
+        """Test expansion with tools for context gathering."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        def search_tool(query: str) -> str:
+            return "Latest AI trends: LLMs, multimodal, agents"
+        
+        agent = PromptExpanderAgent(tools=[search_tool])
+        
+        assert len(agent.tools) == 1
+    
+    def test_tools_passed_to_internal_agent(self):
+        """Test that tools are passed to the internal agent."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        def mock_tool(query: str) -> str:
+            return "result"
+        
+        agent = PromptExpanderAgent(tools=[mock_tool])
+        
+        # Access the lazy-initialized agent
+        internal_agent = agent.agent
+        
+        # The internal agent should have the tools
+        assert internal_agent.tools is not None
+
+
+class TestConvenienceMethods:
+    """Test convenience methods."""
+    
+    def test_convenience_methods_exist(self):
+        """Test all convenience methods exist."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent()
+        
+        assert hasattr(agent, 'expand')
+        assert hasattr(agent, 'expand_basic')
+        assert hasattr(agent, 'expand_detailed')
+        assert hasattr(agent, 'expand_structured')
+        assert hasattr(agent, 'expand_creative')
+
+
+class TestEdgeCases:
+    """Test edge cases."""
+    
+    def test_empty_prompt(self):
+        """Test handling of empty prompt."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent()
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            mock_call.return_value = ""
+            
+            result = agent.expand("")
+            
+            # Should return original if expansion fails
+            assert result.expanded_prompt == "" or result.original_prompt == ""
+    
+    def test_already_detailed_prompt(self):
+        """Test that already detailed prompts are minimally modified."""
+        from praisonaiagents import PromptExpanderAgent
+        
+        agent = PromptExpanderAgent()
+        
+        detailed_prompt = """Write a comprehensive blog post about machine learning, 
+        covering supervised learning, unsupervised learning, and reinforcement learning. 
+        Include code examples in Python and real-world applications."""
+        
+        with patch.object(agent, '_call_agent') as mock_call:
+            # For detailed prompts, minimal expansion expected
+            mock_call.return_value = detailed_prompt + " Ensure clarity and technical accuracy."
+            
+            result = agent.expand(detailed_prompt)
+            
+            # Should not drastically change already detailed prompts
+            assert result.original_prompt == detailed_prompt
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

src/praisonai-agents/tests/test_web_fetch.py

@@ -0,0 +1,284 @@
+"""
+Test suite for web_fetch feature.
+
+This module tests the web fetch functionality that allows LLMs to retrieve
+full content from specific URLs (web pages and PDF documents).
+Currently only supported by Anthropic Claude models.
+"""
+
+import pytest
+import os
+
+
+class TestSupportsWebFetch:
+    """Test the supports_web_fetch function in model_capabilities."""
+    
+    def test_anthropic_claude_opus_4_1_supports_web_fetch(self):
+        """Test that Claude Opus 4.1 supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-opus-4-1-20250805")
+        assert supports_web_fetch("claude-opus-4-1")
+    
+    def test_anthropic_claude_opus_4_supports_web_fetch(self):
+        """Test that Claude Opus 4 supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-opus-4-20250514")
+        assert supports_web_fetch("claude-opus-4")
+    
+    def test_anthropic_claude_sonnet_4_supports_web_fetch(self):
+        """Test that Claude Sonnet 4 supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-sonnet-4-20250514")
+        assert supports_web_fetch("claude-sonnet-4")
+    
+    def test_anthropic_claude_3_7_sonnet_supports_web_fetch(self):
+        """Test that Claude 3.7 Sonnet supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-3-7-sonnet-20250219")
+        assert supports_web_fetch("claude-3-7-sonnet-latest")
+    
+    def test_anthropic_claude_3_5_sonnet_supports_web_fetch(self):
+        """Test that Claude 3.5 Sonnet supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-3-5-sonnet-latest")
+        assert supports_web_fetch("claude-3-5-sonnet-20241022")
+    
+    def test_anthropic_claude_3_5_haiku_supports_web_fetch(self):
+        """Test that Claude 3.5 Haiku supports web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("anthropic/claude-3-5-haiku-latest")
+        assert supports_web_fetch("claude-3-5-haiku-20241022")
+    
+    def test_claude_5_auto_supports_web_fetch(self):
+        """Test that Claude 5+ models auto-support web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert supports_web_fetch("claude-5")
+        assert supports_web_fetch("claude-sonnet-5")
+        assert supports_web_fetch("claude-opus-5")
+    
+    def test_openai_models_do_not_support_web_fetch(self):
+        """Test that OpenAI models do not support web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert not supports_web_fetch("openai/gpt-4o")
+        assert not supports_web_fetch("gpt-4o-mini")
+        assert not supports_web_fetch("gpt-4o-search-preview")
+    
+    def test_gemini_models_do_not_support_web_fetch(self):
+        """Test that Gemini models do not support web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert not supports_web_fetch("gemini/gemini-2.0-flash")
+        assert not supports_web_fetch("gemini-2.5-pro")
+    
+    def test_unknown_models_do_not_support_web_fetch(self):
+        """Test that unknown models do not support web fetch."""
+        from praisonaiagents.llm.model_capabilities import supports_web_fetch
+        assert not supports_web_fetch("ollama/llama3")
+        assert not supports_web_fetch("unknown/model")
+
+
+class TestLLMWebFetchParameter:
+    """Test the web_fetch parameter in LLM class."""
+    
+    def test_llm_init_with_web_fetch_true(self):
+        """Test LLM initialization with web_fetch=True."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", web_fetch=True)
+        assert llm.web_fetch is True
+    
+    def test_llm_init_with_web_fetch_dict(self):
+        """Test LLM initialization with web_fetch as dict."""
+        from praisonaiagents.llm.llm import LLM
+        web_fetch_config = {
+            "max_uses": 10,
+            "allowed_domains": ["example.com"],
+            "citations": {"enabled": True}
+        }
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", web_fetch=web_fetch_config)
+        assert llm.web_fetch == web_fetch_config
+    
+    def test_llm_init_without_web_fetch(self):
+        """Test LLM initialization without web_fetch."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini")
+        assert llm.web_fetch is None
+    
+    def test_llm_supports_web_fetch_method(self):
+        """Test LLM._supports_web_fetch() method."""
+        from praisonaiagents.llm.llm import LLM
+        
+        # Claude model should support web fetch
+        llm_claude = LLM(model="anthropic/claude-3-5-sonnet-latest")
+        assert llm_claude._supports_web_fetch()
+        
+        # OpenAI model should not support web fetch
+        llm_openai = LLM(model="gpt-4o-mini")
+        assert not llm_openai._supports_web_fetch()
+
+
+class TestLLMBuildCompletionParamsWebFetch:
+    """Test _build_completion_params with web_fetch."""
+    
+    def test_build_params_with_web_fetch_true(self):
+        """Test that web_fetch=True adds web_fetch tool to params."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", web_fetch=True)
+        params = llm._build_completion_params()
+        
+        assert 'tools' in params
+        # Find the web_fetch tool
+        web_fetch_tool = None
+        for tool in params['tools']:
+            if isinstance(tool, dict) and tool.get('type') == 'web_fetch_20250910':
+                web_fetch_tool = tool
+                break
+        
+        assert web_fetch_tool is not None
+        assert web_fetch_tool['name'] == 'web_fetch'
+        assert web_fetch_tool['max_uses'] == 5  # default
+    
+    def test_build_params_with_web_fetch_dict(self):
+        """Test that web_fetch dict adds customized web_fetch tool."""
+        from praisonaiagents.llm.llm import LLM
+        web_fetch_config = {
+            "max_uses": 10,
+            "allowed_domains": ["example.com", "docs.example.com"],
+            "citations": {"enabled": True},
+            "max_content_tokens": 50000
+        }
+        llm = LLM(model="anthropic/claude-3-5-sonnet-latest", web_fetch=web_fetch_config)
+        params = llm._build_completion_params()
+        
+        assert 'tools' in params
+        # Find the web_fetch tool
+        web_fetch_tool = None
+        for tool in params['tools']:
+            if isinstance(tool, dict) and tool.get('type') == 'web_fetch_20250910':
+                web_fetch_tool = tool
+                break
+        
+        assert web_fetch_tool is not None
+        assert web_fetch_tool['max_uses'] == 10
+        assert web_fetch_tool['allowed_domains'] == ["example.com", "docs.example.com"]
+        assert web_fetch_tool['citations'] == {"enabled": True}
+        assert web_fetch_tool['max_content_tokens'] == 50000
+    
+    def test_build_params_web_fetch_unsupported_model(self):
+        """Test that web_fetch is ignored for unsupported models."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini", web_fetch=True)
+        params = llm._build_completion_params()
+        
+        # Should not have web_fetch tool
+        if 'tools' in params:
+            for tool in params['tools']:
+                if isinstance(tool, dict):
+                    assert tool.get('type') != 'web_fetch_20250910'
+
+
+class TestAgentWebFetchParameter:
+    """Test the web_fetch parameter in Agent class."""
+    
+    def test_agent_init_with_web_fetch_true(self):
+        """Test Agent initialization with web_fetch=True."""
+        from praisonaiagents.agent.agent import Agent
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            web_fetch=True
+        )
+        assert agent.web_fetch is True
+    
+    def test_agent_init_with_web_fetch_dict(self):
+        """Test Agent initialization with web_fetch as dict."""
+        from praisonaiagents.agent.agent import Agent
+        web_fetch_config = {"max_uses": 10, "allowed_domains": ["example.com"]}
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            web_fetch=web_fetch_config
+        )
+        assert agent.web_fetch == web_fetch_config
+    
+    def test_agent_init_without_web_fetch(self):
+        """Test Agent initialization without web_fetch."""
+        from praisonaiagents.agent.agent import Agent
+        agent = Agent(name="Test Agent", llm="gpt-4o-mini")
+        assert agent.web_fetch is None
+    
+    def test_agent_passes_web_fetch_to_llm(self):
+        """Test that Agent passes web_fetch to LLM instance."""
+        from praisonaiagents.agent.agent import Agent
+        agent = Agent(
+            name="Test Agent",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            web_fetch=True
+        )
+        assert agent.llm_instance.web_fetch is True
+    
+    def test_agent_model_supports_web_fetch_method(self):
+        """Test Agent._model_supports_web_fetch() method."""
+        from praisonaiagents.agent.agent import Agent
+        
+        # Claude model should support web fetch
+        agent_claude = Agent(
+            name="Claude Agent",
+            llm="anthropic/claude-3-5-sonnet-latest"
+        )
+        assert agent_claude._model_supports_web_fetch()
+        
+        # OpenAI model should not support web fetch
+        agent_openai = Agent(
+            name="OpenAI Agent",
+            llm="gpt-4o-mini"
+        )
+        assert not agent_openai._model_supports_web_fetch()
+
+
+class TestWebFetchWithWebSearch:
+    """Test that web_fetch and web_search can be used together."""
+    
+    def test_both_web_fetch_and_web_search(self):
+        """Test using both web_fetch and web_search on supported model."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(
+            model="anthropic/claude-3-5-sonnet-latest",
+            web_search=True,
+            web_fetch=True
+        )
+        params = llm._build_completion_params()
+        
+        # Should have web_search_options
+        assert 'web_search_options' in params
+        
+        # Should also have web_fetch tool
+        assert 'tools' in params
+        web_fetch_found = False
+        for tool in params['tools']:
+            if isinstance(tool, dict) and tool.get('type') == 'web_fetch_20250910':
+                web_fetch_found = True
+                break
+        assert web_fetch_found
+
+
+@pytest.mark.skipif(
+    not os.getenv('ANTHROPIC_API_KEY'),
+    reason="ANTHROPIC_API_KEY not set"
+)
+class TestWebFetchIntegration:
+    """Integration tests for web_fetch (requires API key)."""
+    
+    def test_web_fetch_with_anthropic(self):
+        """Test actual web fetch with Anthropic API."""
+        from praisonaiagents.agent.agent import Agent
+        
+        agent = Agent(
+            name="Web Fetch Agent",
+            instructions="You are a helpful assistant that can fetch web content.",
+            llm="anthropic/claude-3-5-sonnet-latest",
+            web_fetch=True
+        )
+        
+        # This would make an actual API call
+        # response = agent.chat("Fetch and summarize https://example.com")
+        # assert response is not None
+        pass  # Skip actual API call in tests

src/praisonai-agents/tests/test_web_search.py

@@ -0,0 +1,255 @@
+"""
+Test file for web_search feature (TDD approach).
+
+Tests the LiteLLM native web search integration with fallback to DuckDuckGo.
+"""
+
+import pytest
+import os
+from unittest.mock import patch
+
+
+class TestWebSearchSupport:
+    """Test web search capability detection."""
+    
+    def test_supports_web_search_openai_search_preview(self):
+        """Test that gpt-4o-search-preview is detected as supporting web search."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("openai/gpt-4o-search-preview") == True
+    
+    def test_supports_web_search_xai_grok(self):
+        """Test that xai/grok-3 is detected as supporting web search."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("xai/grok-3") == True
+    
+    def test_supports_web_search_anthropic_claude(self):
+        """Test that claude-3-5-sonnet-latest is detected as supporting web search."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("anthropic/claude-3-5-sonnet-latest") == True
+    
+    def test_supports_web_search_gemini(self):
+        """Test that gemini-2.0-flash is detected as supporting web search."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("gemini-2.0-flash") == True
+    
+    def test_supports_web_search_ollama_false(self):
+        """Test that ollama models don't support native web search."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("ollama/llama3") == False
+    
+    def test_supports_web_search_unknown_model(self):
+        """Test that unknown models default to False."""
+        from praisonaiagents.llm.model_capabilities import supports_web_search
+        assert supports_web_search("unknown/model") == False
+
+
+class TestLLMWebSearchParameter:
+    """Test LLM class web_search parameter."""
+    
+    def test_llm_init_with_web_search_true(self):
+        """Test LLM initialization with web_search=True."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini", web_search=True)
+        assert llm.web_search == True
+    
+    def test_llm_init_with_web_search_dict(self):
+        """Test LLM initialization with web_search as dict."""
+        from praisonaiagents.llm.llm import LLM
+        web_search_options = {"search_context_size": "high"}
+        llm = LLM(model="gpt-4o-mini", web_search=web_search_options)
+        assert llm.web_search == web_search_options
+    
+    def test_llm_init_with_web_search_false(self):
+        """Test LLM initialization with web_search=False."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini", web_search=False)
+        assert llm.web_search == False
+    
+    def test_llm_init_without_web_search(self):
+        """Test LLM initialization without web_search (default None)."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini")
+        assert llm.web_search is None
+    
+    def test_llm_supports_web_search_method(self):
+        """Test LLM._supports_web_search() method."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="openai/gpt-4o-search-preview")
+        assert llm._supports_web_search() == True
+    
+    def test_llm_supports_web_search_method_ollama(self):
+        """Test LLM._supports_web_search() returns False for Ollama."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="ollama/llama3")
+        assert llm._supports_web_search() == False
+
+
+class TestLLMBuildCompletionParams:
+    """Test _build_completion_params includes web_search_options."""
+    
+    def test_build_params_with_web_search_true(self):
+        """Test that web_search=True adds web_search_options to params."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="openai/gpt-4o-search-preview", web_search=True)
+        
+        with patch.object(llm, '_supports_web_search', return_value=True):
+            params = llm._build_completion_params(messages=[{"role": "user", "content": "test"}])
+            assert "web_search_options" in params
+            assert params["web_search_options"] == {"search_context_size": "medium"}
+    
+    def test_build_params_with_web_search_dict(self):
+        """Test that web_search dict is passed correctly."""
+        from praisonaiagents.llm.llm import LLM
+        web_search_options = {"search_context_size": "high"}
+        llm = LLM(model="openai/gpt-4o-search-preview", web_search=web_search_options)
+        
+        with patch.object(llm, '_supports_web_search', return_value=True):
+            params = llm._build_completion_params(messages=[{"role": "user", "content": "test"}])
+            assert "web_search_options" in params
+            assert params["web_search_options"] == {"search_context_size": "high"}
+    
+    def test_build_params_without_web_search(self):
+        """Test that web_search_options is not added when web_search is None."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="gpt-4o-mini")
+        
+        params = llm._build_completion_params(messages=[{"role": "user", "content": "test"}])
+        assert "web_search_options" not in params
+    
+    def test_build_params_web_search_unsupported_model(self):
+        """Test that web_search_options is not added for unsupported models."""
+        from praisonaiagents.llm.llm import LLM
+        llm = LLM(model="ollama/llama3", web_search=True)
+        
+        with patch.object(llm, '_supports_web_search', return_value=False):
+            params = llm._build_completion_params(messages=[{"role": "user", "content": "test"}])
+            assert "web_search_options" not in params
+
+
+class TestAgentWebSearchParameter:
+    """Test Agent class web_search parameter."""
+    
+    def test_agent_init_with_web_search_true(self):
+        """Test Agent initialization with web_search=True."""
+        from praisonaiagents import Agent
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            web_search=True
+        )
+        assert agent.web_search == True
+    
+    def test_agent_init_with_web_search_dict(self):
+        """Test Agent initialization with web_search as dict."""
+        from praisonaiagents import Agent
+        web_search_options = {"search_context_size": "high"}
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            web_search=web_search_options
+        )
+        assert agent.web_search == web_search_options
+    
+    def test_agent_init_without_web_search(self):
+        """Test Agent initialization without web_search (default None)."""
+        from praisonaiagents import Agent
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test"
+        )
+        assert agent.web_search is None
+    
+    def test_agent_with_custom_llm_passes_web_search(self):
+        """Test that Agent passes web_search to custom LLM instance."""
+        from praisonaiagents import Agent
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            llm="openai/gpt-4o-search-preview",
+            web_search=True
+        )
+        # When using custom LLM (with /), it creates llm_instance
+        assert hasattr(agent, 'llm_instance')
+        assert agent.llm_instance.web_search == True
+
+
+class TestWebSearchFallback:
+    """Test fallback to DuckDuckGo when native web search not supported."""
+    
+    def test_fallback_tool_injection_for_unsupported_model(self):
+        """Test that DuckDuckGo tool is injected for unsupported models."""
+        from praisonaiagents import Agent
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            llm="ollama/llama3",
+            web_search=True
+        )
+        # Check that internet_search tool was added to tools
+        tool_names = [getattr(t, '__name__', str(t)) for t in agent.tools]
+        assert 'internet_search' in tool_names or 'duckduckgo' in tool_names
+    
+    def test_no_fallback_for_supported_model(self):
+        """Test that no fallback tool is added for supported models."""
+        from praisonaiagents import Agent
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            llm="openai/gpt-4o-search-preview",
+            web_search=True,
+            tools=[]  # Explicitly empty tools
+        )
+        # For supported models, tools should remain empty (native web search used)
+        # Only check if no DuckDuckGo tool was auto-added
+        tool_names = [getattr(t, '__name__', str(t)) for t in agent.tools]
+        # internet_search should NOT be auto-added for supported models
+        assert 'internet_search' not in tool_names
+
+
+class TestDuckDuckGoToolPreservation:
+    """Test that DuckDuckGo tools still work as before."""
+    
+    def test_duckduckgo_import(self):
+        """Test that DuckDuckGo tools can still be imported."""
+        from praisonaiagents.tools import internet_search, duckduckgo
+        assert callable(internet_search)
+        assert callable(duckduckgo)
+    
+    def test_explicit_duckduckgo_tool_usage(self):
+        """Test that explicit DuckDuckGo tool usage still works."""
+        from praisonaiagents import Agent
+        from praisonaiagents.tools import internet_search
+        
+        agent = Agent(
+            name="Test Agent",
+            instructions="Test",
+            tools=[internet_search]
+        )
+        assert internet_search in agent.tools
+
+
+class TestWebSearchIntegration:
+    """Integration tests for web search (requires API keys)."""
+    
+    @pytest.mark.skipif(
+        not os.getenv("OPENAI_API_KEY"),
+        reason="OPENAI_API_KEY not set"
+    )
+    def test_web_search_with_openai(self):
+        """Test actual web search with OpenAI (integration test)."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="Researcher",
+            instructions="You are a helpful research assistant.",
+            llm="openai/gpt-4o-search-preview",
+            web_search=True
+        )
+        
+        result = agent.start("What is the current weather in San Francisco?")
+        assert result is not None
+        assert len(result) > 0
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

src/praisonai-agents/uv.lock

@@ -2422,7 +2422,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.169"
+version = "0.0.175"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

src/praisonai/README.md

@@ -55,6 +55,9 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 - 💯 100+ LLM Support
 - 🔬 **Deep Research Agents** (OpenAI & Gemini)
 - 🔄 **Query Rewriter Agent** (HyDE, Step-back, Multi-query)
+- 🌐 **Native Web Search** (OpenAI, Gemini, Anthropic, xAI, Perplexity)
+- 📥 **Web Fetch** (Retrieve full content from URLs - Anthropic)
+- 💾 **Prompt Caching** (Reduce costs & latency - OpenAI, Anthropic, Bedrock, Deepseek)
 
 ## Using Python Code
 
@@ -718,6 +721,97 @@ agent = Agent(tools=["my_tool"])  # Works automatically!
 ```
 
 
+## Prompt Expansion
+
+Expand short prompts into detailed, actionable prompts:
+
+### CLI Usage
+
+```bash
+# Expand a short prompt into detailed prompt
+praisonai "write a movie script in 3 lines" --expand-prompt
+
+# With verbose output
+praisonai "blog about AI" --expand-prompt -v
+
+# With tools for context gathering
+praisonai "latest AI trends" --expand-prompt --expand-tools tools.py
+
+# Combine with query rewrite
+praisonai "AI news" --query-rewrite --expand-prompt
+```
+
+### Programmatic Usage
+
+```python
+from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+
+# Basic usage
+agent = PromptExpanderAgent()
+result = agent.expand("write a movie script in 3 lines")
+print(result.expanded_prompt)
+
+# With specific strategy
+result = agent.expand("blog about AI", strategy=ExpandStrategy.DETAILED)
+
+# Available strategies: BASIC, DETAILED, STRUCTURED, CREATIVE, AUTO
+```
+
+**Key Difference:**
+- `--query-rewrite`: Optimizes queries for **search/retrieval** (RAG)
+- `--expand-prompt`: Expands prompts for **detailed task execution**
+
+
+## Web Search, Web Fetch & Prompt Caching
+
+### CLI Usage
+
+```bash
+# Web Search - Get real-time information
+praisonai "What are the latest AI news today?" --web-search --llm openai/gpt-4o-search-preview
+
+# Web Fetch - Retrieve and analyze URL content (Anthropic only)
+praisonai "Summarize https://docs.praison.ai" --web-fetch --llm anthropic/claude-sonnet-4-20250514
+
+# Prompt Caching - Reduce costs for repeated prompts
+praisonai "Analyze this document..." --prompt-caching --llm anthropic/claude-sonnet-4-20250514
+```
+
+### Programmatic Usage
+
+```python
+from praisonaiagents import Agent
+
+# Web Search
+agent = Agent(
+    instructions="You are a research assistant",
+    llm="openai/gpt-4o-search-preview",
+    web_search=True
+)
+
+# Web Fetch (Anthropic only)
+agent = Agent(
+    instructions="You are a content analyzer",
+    llm="anthropic/claude-sonnet-4-20250514",
+    web_fetch=True
+)
+
+# Prompt Caching
+agent = Agent(
+    instructions="You are an AI assistant..." * 50,  # Long system prompt
+    llm="anthropic/claude-sonnet-4-20250514",
+    prompt_caching=True
+)
+```
+
+**Supported Providers:**
+| Feature | Providers |
+|---------|-----------|
+| Web Search | OpenAI, Gemini, Anthropic, xAI, Perplexity |
+| Web Fetch | Anthropic |
+| Prompt Caching | OpenAI (auto), Anthropic, Bedrock, Deepseek |
+
+
 ## Development:
 
 Below is used for development only.
@@ -735,21 +829,14 @@ uv pip install -r pyproject.toml --extra code
 uv pip install -r pyproject.toml --extra "crewai,autogen"
 ```
 
-### Version Bump
+### Bump and Release
 
 ```bash
-# From project root
-python src/praisonai/scripts/bump_version.py 2.2.96
+# From project root - bumps version and releases in one command
+python src/praisonai/scripts/bump_and_release.py 2.2.99
 
 # With praisonaiagents dependency
-python src/praisonai/scripts/bump_version.py 2.2.96 --agents 0.0.167
-```
-
-### Release
-
-```bash
-# From project root (runs uv lock, build, git tag, gh release)
-python src/praisonai/scripts/release.py
+python src/praisonai/scripts/bump_and_release.py 2.2.99 --agents 0.0.169
 
 # Then publish
 cd src/praisonai && uv publish

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/v2.2.99.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.99.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.2.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.2.tar.gz | shasum -a 256`.split.first
     license "MIT"
   
     depends_on "[email protected]"

src/praisonai/praisonai/cli.py

@@ -579,9 +579,14 @@ class PraisonAI:
         parser.add_argument("--research", action="store_true", help="Run deep research on a topic")
         parser.add_argument("--query-rewrite", action="store_true", help="Rewrite query for better results (works with any command)")
         parser.add_argument("--rewrite-tools", type=str, help="Tools for query rewriter (e.g., 'internet_search' or path to tools.py)")
+        parser.add_argument("--expand-prompt", action="store_true", help="Expand short prompt into detailed prompt (works with any command)")
+        parser.add_argument("--expand-tools", type=str, help="Tools for prompt expander (e.g., 'internet_search' or path to tools.py)")
         parser.add_argument("--tools", "-t", type=str, help="Path to tools.py file for research agent")
         parser.add_argument("--save", "-s", action="store_true", help="Save research output to file (output/research/)")
         parser.add_argument("--verbose", "-v", action="store_true", help="Enable verbose output for research")
+        parser.add_argument("--web-search", action="store_true", help="Enable native web search (OpenAI, Gemini, Anthropic, xAI, Perplexity)")
+        parser.add_argument("--web-fetch", action="store_true", help="Enable web fetch to retrieve URL content (Anthropic only)")
+        parser.add_argument("--prompt-caching", action="store_true", help="Enable prompt caching to reduce costs (OpenAI, Anthropic, Bedrock, Deepseek)")
         
         # If we're in a test environment, parse with empty args to avoid pytest interference
         if in_test_env:
@@ -839,12 +844,135 @@ class PraisonAI:
         verbose = getattr(self.args, 'verbose', False)
         return self._rewrite_query(query, rewrite_tools, verbose)
 
+    def _expand_prompt(self, prompt: str, expand_tools: str = None, verbose: bool = False) -> str:
+        """
+        Expand prompt using PromptExpanderAgent.
+        
+        Args:
+            prompt: The prompt to expand
+            expand_tools: Tool names (comma-separated) or path to tools.py
+            verbose: Enable verbose output
+            
+        Returns:
+            Expanded prompt or original if expansion fails
+        """
+        try:
+            from praisonaiagents import PromptExpanderAgent, ExpandStrategy
+            from rich import print
+            
+            print("[bold cyan]Expanding prompt for detailed execution...[/bold cyan]")
+            
+            # Load expand tools if specified
+            expand_tools_list = []
+            if expand_tools:
+                if os.path.isfile(expand_tools):
+                    # Load from file
+                    try:
+                        import inspect
+                        import importlib.util
+                        spec = importlib.util.spec_from_file_location("expand_tools_module", expand_tools)
+                        if spec and spec.loader:
+                            module = importlib.util.module_from_spec(spec)
+                            spec.loader.exec_module(module)
+                            for name, obj in inspect.getmembers(module):
+                                if inspect.isfunction(obj) and not name.startswith('_'):
+                                    expand_tools_list.append(obj)
+                            if expand_tools_list:
+                                print(f"[cyan]Loaded {len(expand_tools_list)} tools for prompt expander[/cyan]")
+                    except Exception as e:
+                        print(f"[yellow]Warning: Failed to load expand tools: {e}[/yellow]")
+                else:
+                    # Treat as comma-separated tool names
+                    try:
+                        from praisonaiagents.tools import TOOL_MAPPINGS
+                        import praisonaiagents.tools as tools_module
+                        
+                        tool_names = [t.strip() for t in expand_tools.split(',')]
+                        for tool_name in tool_names:
+                            if tool_name in TOOL_MAPPINGS:
+                                try:
+                                    tool = getattr(tools_module, tool_name)
+                                    expand_tools_list.append(tool)
+                                except Exception as e:
+                                    print(f"[yellow]Warning: Failed to load expand tool '{tool_name}': {e}[/yellow]")
+                            else:
+                                print(f"[yellow]Warning: Unknown expand tool '{tool_name}'[/yellow]")
+                        if expand_tools_list:
+                            print(f"[cyan]Using expand tools: {', '.join(tool_names)}[/cyan]")
+                    except ImportError:
+                        print("[yellow]Warning: Could not import tools module[/yellow]")
+            
+            expander = PromptExpanderAgent(
+                model="gpt-4o-mini", 
+                verbose=verbose, 
+                tools=expand_tools_list if expand_tools_list else None
+            )
+            result = expander.expand(prompt, strategy=ExpandStrategy.AUTO)
+            expanded = result.expanded_prompt
+            
+            print(f"[cyan]Original:[/cyan] {prompt}")
+            print(f"[cyan]Expanded:[/cyan] {expanded}")
+            
+            return expanded
+            
+        except ImportError:
+            from rich import print
+            print("[yellow]Warning: PromptExpanderAgent not available, using original prompt[/yellow]")
+            return prompt
+        except Exception as e:
+            from rich import print
+            print(f"[yellow]Warning: Prompt expansion failed ({e}), using original prompt[/yellow]")
+            return prompt
+
+    def _expand_prompt_if_enabled(self, prompt: str) -> str:
+        """
+        Expand prompt using PromptExpanderAgent if --expand-prompt is enabled.
+        Returns the expanded prompt or original if expansion is disabled/fails.
+        """
+        if not hasattr(self, 'args') or not getattr(self.args, 'expand_prompt', False):
+            return prompt
+        
+        expand_tools = getattr(self.args, 'expand_tools', None)
+        verbose = getattr(self.args, 'verbose', False)
+        return self._expand_prompt(prompt, expand_tools, verbose)
+
+    def _save_output(self, prompt: str, result: str):
+        """
+        Save output to output/prompts/ folder.
+        
+        Args:
+            prompt: The original prompt
+            result: The output result to save
+        """
+        from datetime import datetime
+        from rich import print
+        
+        # Create output directory
+        output_dir = os.path.join(os.getcwd(), "output", "prompts")
+        os.makedirs(output_dir, exist_ok=True)
+        
+        # Generate filename with timestamp
+        timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+        # Create a safe filename from prompt (first 30 chars)
+        safe_prompt = "".join(c if c.isalnum() or c in " -_" else "" for c in prompt[:30]).strip().replace(" ", "_")
+        filename = f"{timestamp}_{safe_prompt}.md"
+        filepath = os.path.join(output_dir, filename)
+        
+        # Write output
+        with open(filepath, "w", encoding="utf-8") as f:
+            f.write(f"# Prompt\n\n{prompt}\n\n")
+            f.write(f"# Output\n\n{result}\n")
+        
+        print(f"[green]✅ Output saved to: {filepath}[/green]")
+
     def handle_direct_prompt(self, prompt):
         """
         Handle direct prompt by creating a single agent and running it.
         """
         # Apply query rewriting if enabled
         prompt = self._rewrite_query_if_enabled(prompt)
+        # Apply prompt expansion if enabled
+        prompt = self._expand_prompt_if_enabled(prompt)
         
         if PRAISONAI_AVAILABLE:
             agent_config = {
@@ -858,8 +986,22 @@ class PraisonAI:
             if hasattr(self, 'args') and self.args.llm:
                 agent_config["llm"] = self.args.llm
             
+            # Add feature flags if enabled
+            if hasattr(self, 'args'):
+                if getattr(self.args, 'web_search', False):
+                    agent_config["web_search"] = True
+                if getattr(self.args, 'web_fetch', False):
+                    agent_config["web_fetch"] = True
+                if getattr(self.args, 'prompt_caching', False):
+                    agent_config["prompt_caching"] = True
+            
             agent = PraisonAgent(**agent_config)
             result = agent.start(prompt)
+            
+            # Save output if --save is enabled
+            if hasattr(self, 'args') and getattr(self.args, 'save', False):
+                self._save_output(prompt, result)
+            
             return result
         elif CREWAI_AVAILABLE:
             from crewai import Agent, Task, Crew

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==2.2.99 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.3.2 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__ = "2.2.99"
+__version__ = "2.3.2"

src/praisonai/pyproject.toml

@@ -12,7 +12,7 @@ dependencies = [
     "rich>=13.7",
     "markdown>=3.5",
     "pyparsing>=3.0.0",
-    "praisonaiagents>=0.0.169",
+    "praisonaiagents>=0.0.175",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",

src/praisonai/scripts/bump_and_release.py

@@ -0,0 +1,222 @@
+#!/usr/bin/env python3
+"""
+Combined bump version and release script for PraisonAI package.
+
+Usage:
+    python src/praisonai/scripts/bump_and_release.py 2.2.99
+    
+Or with optional praisonaiagents version:
+    python src/praisonai/scripts/bump_and_release.py 2.2.99 --agents 0.0.169
+
+This script:
+1. Bumps version in all required files
+2. Copies root README.md to package dir
+3. Runs uv lock & uv build
+4. Commits changes
+5. Creates git tag
+6. Pushes to GitHub
+7. Creates GitHub release (latest)
+"""
+
+import re
+import sys
+import argparse
+import subprocess
+import shutil
+from pathlib import Path
+
+
+def get_project_root() -> Path:
+    """Get the project root directory (praisonai-package)."""
+    return Path(__file__).parent.parent.parent.parent
+
+
+def get_praisonai_dir() -> Path:
+    """Get the praisonai package directory."""
+    return get_project_root() / "src/praisonai"
+
+
+def run(cmd: list[str], cwd: Path | None = None, check: bool = True) -> subprocess.CompletedProcess:
+    """Run a command and print it."""
+    print(f"$ {' '.join(cmd)}")
+    result = subprocess.run(cmd, cwd=cwd, capture_output=True, text=True)
+    if result.stdout:
+        print(result.stdout)
+    if result.stderr:
+        print(result.stderr, file=sys.stderr)
+    if check and result.returncode != 0:
+        print(f"❌ Command failed with exit code {result.returncode}")
+        sys.exit(1)
+    return result
+
+
+def update_file(filepath: Path, patterns: list[tuple[str, str]], root: Path) -> bool:
+    """Update a file with the given regex patterns and replacements."""
+    if not filepath.exists():
+        print(f"  ⚠️  File not found: {filepath}")
+        return False
+    
+    content = filepath.read_text()
+    original = content
+    
+    for pattern, replacement in patterns:
+        content = re.sub(pattern, replacement, content)
+    
+    if content != original:
+        filepath.write_text(content)
+        print(f"  ✅ Updated: {filepath.relative_to(root)}")
+        return True
+    else:
+        print(f"  ⏭️  No changes: {filepath.relative_to(root)}")
+        return False
+
+
+def bump_version(new_version: str, agents_version: str | None = None):
+    """Bump version in all required files."""
+    root = get_project_root()
+    praisonai_dir = get_praisonai_dir()
+    
+    print(f"\n🚀 Bumping PraisonAI version to {new_version}\n")
+    
+    # 1. Update version.py (single source of truth)
+    print("📦 Python Package:")
+    update_file(
+        praisonai_dir / "praisonai/version.py",
+        [(r'__version__ = "[^"]+"', f'__version__ = "{new_version}"')],
+        root
+    )
+    
+    # 2. Update deploy.py (Dockerfile template)
+    print("\n🐳 Deploy Script:")
+    update_file(
+        praisonai_dir / "praisonai/deploy.py",
+        [(r'praisonai==[0-9.]+', f'praisonai=={new_version}')],
+        root
+    )
+    
+    # 3. Update Dockerfiles
+    print("\n🐳 Dockerfiles:")
+    dockerfiles = [
+        "docker/Dockerfile",
+        "docker/Dockerfile.chat",
+        "docker/Dockerfile.dev",
+        "docker/Dockerfile.ui",
+    ]
+    for dockerfile in dockerfiles:
+        update_file(
+            root / dockerfile,
+            [(r'"praisonai>=[0-9.]+"', f'"praisonai>={new_version}"')],
+            root
+        )
+    
+    # 4. Update Homebrew formula
+    print("\n🍺 Homebrew Formula:")
+    update_file(
+        praisonai_dir / "praisonai.rb",
+        [(r'v[0-9]+\.[0-9]+\.[0-9]+', f'v{new_version}')],
+        root
+    )
+    
+    # 5. Update praisonaiagents dependency if specified
+    if agents_version:
+        print(f"\n📦 Updating praisonaiagents dependency to {agents_version}:")
+        update_file(
+            praisonai_dir / "pyproject.toml",
+            [(r'praisonaiagents>=[0-9.]+', f'praisonaiagents>={agents_version}')],
+            root
+        )
+    
+    print("\n✨ Version bump complete!")
+
+
+def release(version: str):
+    """Run the release process."""
+    root = get_project_root()
+    praisonai_dir = get_praisonai_dir()
+    tag = f"v{version}"
+    
+    print(f"\n🚀 Releasing PraisonAI {tag}\n")
+    
+    # 1. Copy root README.md to package dir for PyPI
+    print("📄 Copying README.md...")
+    root_readme = root / "README.md"
+    pkg_readme = praisonai_dir / "README.md"
+    if root_readme.exists():
+        shutil.copy(root_readme, pkg_readme)
+        print(f"  ✅ Copied {root_readme} -> {pkg_readme}")
+    
+    # 2. Clear uv cache and run uv lock
+    print("\n🧹 Clearing uv cache...")
+    run(["uv", "cache", "clean"], cwd=praisonai_dir)
+    
+    print("\n📦 Running uv lock...")
+    run(["uv", "lock"], cwd=praisonai_dir)
+    
+    # 3. uv build
+    print("\n🔨 Running uv build...")
+    run(["uv", "build"], cwd=praisonai_dir)
+    
+    # 4. Git add and commit
+    print("\n📝 Committing changes...")
+    run(["git", "add", "-A"], cwd=root)
+    run(["git", "commit", "-m", f"Release {tag}"], cwd=root, check=False)
+    
+    # 5. Create git tag
+    print(f"\n🏷️  Creating tag {tag}...")
+    run(["git", "tag", "-f", tag], cwd=root)
+    
+    # 6. Push to GitHub
+    print("\n⬆️  Pushing to GitHub...")
+    run(["git", "push"], cwd=root)
+    run(["git", "push", "--tags", "-f"], cwd=root)
+    
+    # 7. Create GitHub release
+    print(f"\n🎉 Creating GitHub release {tag}...")
+    run([
+        "gh", "release", "create", tag,
+        "--title", f"PraisonAI {tag}",
+        "--notes", f"Release {tag}",
+        "--latest"
+    ], cwd=root)
+    
+    print(f"\n✅ Released PraisonAI {tag}")
+    print("\nNext step:")
+    print("  cd src/praisonai && uv publish")
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Bump version and release PraisonAI package"
+    )
+    parser.add_argument(
+        "version",
+        help="New version number (e.g., 2.2.99)"
+    )
+    parser.add_argument(
+        "--agents", "-a",
+        help="Optional: Update praisonaiagents dependency version (e.g., 0.0.169)",
+        default=None
+    )
+    
+    args = parser.parse_args()
+    
+    # Validate version format
+    if not re.match(r'^\d+\.\d+\.\d+$', args.version):
+        print(f"❌ Invalid version format: {args.version}")
+        print("   Expected format: X.Y.Z (e.g., 2.2.99)")
+        sys.exit(1)
+    
+    if args.agents and not re.match(r'^\d+\.\d+\.\d+$', args.agents):
+        print(f"❌ Invalid agents version format: {args.agents}")
+        print("   Expected format: X.Y.Z (e.g., 0.0.169)")
+        sys.exit(1)
+    
+    # Run bump version
+    bump_version(args.version, args.agents)
+    
+    # Run release
+    release(args.version)
+
+
+if __name__ == "__main__":
+    main()

src/praisonai/scripts/release.py

@@ -71,7 +71,10 @@ def main():
         shutil.copy(root_readme, pkg_readme)
         print(f"  ✅ Copied {root_readme} -> {pkg_readme}")
     
-    # 2. uv lock
+    # 2. Clear uv cache and run uv lock
+    print("\n🧹 Clearing uv cache...")
+    run(["uv", "cache", "clean"], cwd=praisonai_dir)
+    
     print("\n📦 Running uv lock...")
     run(["uv", "lock"], cwd=praisonai_dir)
     

src/praisonai/tests/e2e/crewai/test_crewai_real.py

@@ -72,10 +72,10 @@ roles:
         except Exception as e:
             pytest.fail(f"CrewAI real test failed: {e}")
 
+    @pytest.mark.skipif(not os.getenv("OPENAI_API_KEY"), reason="OPENAI_API_KEY not set")
     def test_crewai_environment_check(self):
         """Verify CrewAI environment is properly configured"""
-        # Check API key is available
-        assert os.getenv("OPENAI_API_KEY"), "OPENAI_API_KEY required for real tests"
+        # Check API key is available (already checked by skipif)
         
         # Check CrewAI can be imported
         try:

src/praisonai/tests/test.py

@@ -59,8 +59,11 @@ class TestPraisonAICommandLine(unittest.TestCase):
             # In CI, it should be set by the workflow
             print("Warning: OPENAI_API_KEY not found in CLI test environment. API calls might fail if not mocked.")
             
-        result = subprocess.run(command, shell=True, capture_output=True, text=True, env=env)
-        return result.stdout + result.stderr
+        try:
+            result = subprocess.run(command, shell=True, capture_output=True, text=True, env=env, timeout=120)
+            return result.stdout + result.stderr
+        except subprocess.TimeoutExpired:
+            return "TIMEOUT: Command exceeded 120 seconds"
 
     @pytest.mark.real
     def test_praisonai_command(self):

src/praisonai/uv.lock

@@ -4197,7 +4197,7 @@ requires-dist = [
     { name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.0.22" },
     { name = "praisonai-tools", marker = "extra == 'autogen-v4'", specifier = ">=0.0.22" },
     { name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.0.22" },
-    { name = "praisonaiagents", specifier = ">=0.0.169" },
+    { name = "praisonaiagents", specifier = ">=0.0.175" },
     { name = "pyautogen", marker = "extra == 'autogen'", specifier = "==0.2.29" },
     { name = "pydantic", marker = "extra == 'chat'", specifier = "<=2.10.1" },
     { name = "pydantic", marker = "extra == 'code'", specifier = "<=2.10.1" },
@@ -4252,7 +4252,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.169"
+version = "0.0.175"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
@@ -4261,9 +4261,9 @@ dependencies = [
     { name = "pydantic" },
     { name = "rich" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4e/0c/94820a01306d53ce99f2b8d0f424566e74fe883aaca0e1a5c81f8364dddf/praisonaiagents-0.0.169.tar.gz", hash = "sha256:0774dd1fd8a5066e4ab2d612153d07bf1ac275105c10396730a9b542d4060ff3", size = 319791, upload-time = "2025-12-15T10:09:24.429Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a7/3a/a3f78a53c5ffdab876b59c7f7ea86ed815d641dff45465c70b6fd8ab1a8f/praisonaiagents-0.0.175.tar.gz", hash = "sha256:5f2bdeae4988a34947aa231c7a3de76bf50d60d2dfd43e214769d188886d6362", size = 332558, upload-time = "2025-12-15T12:43:06.491Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d6/f4/9342ee5340a2fdf1e3b9b8c1d10d9f2962c4fc577925c41b81db7b9beea1/praisonaiagents-0.0.169-py3-none-any.whl", hash = "sha256:ea491a2097224544f7ebb19b19daaabfc814c22bf92fb2adeb8e7d3f33d1233c", size = 333017, upload-time = "2025-12-15T10:09:23.016Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/c9/93cf31b2c1011ee205efc75080a4d7ab9ed68e53e033d51a861112545428/praisonaiagents-0.0.175-py3-none-any.whl", hash = "sha256:1bdb672efefd562c47be481008551894e57083e52005227650f97999f88e7ff6", size = 339912, upload-time = "2025-12-15T12:43:05.064Z" },
 ]
 
 [[package]]