Release v2.3.45

docs: Add examples README with quick links to docs
docs: Update README with Model Router info and fix links
2026-11-09 03:39:37 -10:00 · 2025-12-19 12:16:12 +00:00 · 2025-12-19 11:14:24 +00:00 · 2025-12-19 11:13:48 +00:00 · 2025-12-19 11:07:25 +00:00 · 2025-12-19 11:01:24 +00:00
69 changed files with 15288 additions and 142 deletions
@@ -77,4 +77,7 @@ agents/praisonaiagents/praisonaiagents.egg-info
 .qodo
 CopilotKit*
 .gemini
-issue_details.json
+issue_details.json
+
+# MCP Registry tokens
+.mcpregistry_*
@@ -6,10 +6,13 @@
  </picture>
 </p>

+<!-- mcp-name: io.github.MervinPraison/praisonai -->
+
 <p align="center">
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://static.pepy.tech/badge/PraisonAI" alt="Total Downloads" /></a>
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://img.shields.io/github/v/release/MervinPraison/PraisonAI" alt="Latest Stable Version" /></a>
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License" /></a>
+<a href="https://registry.modelcontextprotocol.io/servers/io.github.MervinPraison/praisonai"><img src="https://img.shields.io/badge/MCP-Registry-blue" alt="MCP Registry" /></a>
 </p>

 <div align="center">
@@ -188,8 +191,14 @@ npm install praisonai
 | 📚 Add Custom Knowledge | [Example](examples/python/concepts/knowledge-agents.py) | [📖](https://docs.praison.ai/features/knowledge) |
 | 🧠 Memory (Short & Long Term) | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
 | 📄 Chat with PDF Agents | [Example](examples/python/concepts/chat-with-pdf.py) | [📖](https://docs.praison.ai/features/chat-with-pdf) |
-| 💻 Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
-| ✏️ AI Code Editing Tools | [Example](#ai-code-editing) | [📖](https://docs.praison.ai/features/code) |
+| **💻 Code** | | |
+| ↳ Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
+| ↳ AI Code Editing Tools | [Example](examples/python/code/code_editing_example.py) | [📖](https://docs.praison.ai/code/editing) |
+| ↳ External Agents (All) | [Example](examples/python/code/external_agents_example.py) | [📖](https://docs.praison.ai/code/external-agents) |
+| ↳ Claude Code CLI | [Example](examples/python/code/claude_code_example.py) | [📖](https://docs.praison.ai/code/claude-code) |
+| ↳ Gemini CLI | [Example](examples/python/code/gemini_cli_example.py) | [📖](https://docs.praison.ai/code/gemini-cli) |
+| ↳ Codex CLI | [Example](examples/python/code/codex_cli_example.py) | [📖](https://docs.praison.ai/code/codex-cli) |
+| ↳ Cursor CLI | [Example](examples/python/code/cursor_cli_example.py) | [📖](https://docs.praison.ai/code/cursor-cli) |
 | 📚 RAG Agents | [Example](examples/python/concepts/rag-agents.py) | [📖](https://docs.praison.ai/features/rag) |
 | 🤔 Async & Parallel Processing | [Example](examples/python/general/async_example.py) | [📖](https://docs.praison.ai/features/async) |
 | 🔢 Math Agents | [Example](examples/python/agents/math-agent.py) | [📖](https://docs.praison.ai/features/mathagent) |
@@ -207,6 +216,7 @@ npm install praisonai
 | 🧠 Claude Memory Tool | [Example](#claude-memory-tool-cli) | [📖](https://docs.praison.ai/features/claude-memory-tool) |
 | 💾 File-Based Memory | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
 | 🔍 Built-in Search Tools | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/tools/tavily) |
+| 🔎 Unified Web Search | [Example](src/praisonai-agents/examples/web_search_example.py) | [📖](https://docs.praison.ai/tools/web-search) |
 | 📋 Planning Mode | [Example](examples/python/agents/planning-agent.py) | [📖](https://docs.praison.ai/features/planning-mode) |
 | 🔧 Planning Tools | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
 | 🧠 Planning Reasoning | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
@@ -226,7 +236,7 @@ npm install praisonai
 | 💻 Programming Agent | [Example](examples/python/agents/programming-agent.py) | [📖](https://docs.praison.ai/agents/programming) |
 | 📝 Markdown Agent | [Example](examples/python/agents/markdown-agent.py) | [📖](https://docs.praison.ai/agents/markdown) |
 | 📝 Prompt Expander Agent | [Example](#prompt-expansion) | [📖](https://docs.praison.ai/agents/prompt-expander) |
-| 🔀 Router Agent | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/routing) |
+| 🔀 Model Router | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/model-router) |
 | ⛓️ Prompt Chaining | [Example](examples/python/general/prompt_chaining.py) | [📖](https://docs.praison.ai/features/promptchaining) |
 | 🔍 Evaluator Optimiser | [Example](examples/python/general/evaluator-optimiser.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
 | 👷 Orchestrator Workers | [Example](examples/python/general/orchestrator-workers.py) | [📖](https://docs.praison.ai/features/orchestrator-worker) |
@@ -248,6 +258,14 @@ npm install praisonai
 | @ @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/cli/mentions) |
 | 💾 Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/cli/session) |
 | 📜 History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/cli/session) |
+| **🖥️ CLI Features** | | |
+| ↳ Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/cli/slash-commands) |
+| ↳ Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/cli/autonomy-modes) |
+| ↳ Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/cli/cost-tracking) |
+| ↳ Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/cli/repo-map) |
+| ↳ Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/cli/interactive-tui) |
+| ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/cli/git-integration) |
+| ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/cli/sandbox-execution) |

 ---

@@ -1120,6 +1138,15 @@ praisonai workflow auto "Research AI trends" --pattern parallel
 # Generate routing workflow (classifier routes to specialists)
 praisonai workflow auto "Build a chatbot" --pattern routing

+# Generate orchestrator-workers workflow (central orchestrator delegates)
+praisonai workflow auto "Comprehensive market analysis" --pattern orchestrator-workers
+
+# Generate evaluator-optimizer workflow (iterative refinement)
+praisonai workflow auto "Write and refine article" --pattern evaluator-optimizer
+
+# Specify output file
+praisonai workflow auto "Build a chatbot" --pattern routing
+
 # Specify output file
 praisonai workflow auto "Research AI" --pattern sequential --output my_workflow.yaml
 ```
@@ -1129,7 +1156,7 @@ praisonai workflow auto "Research AI" --pattern sequential --output my_workflow.
 |------|-------------|
 | `--workflow-var key=value` | Set workflow variable (can be repeated) |
 | `--var key=value` | Set variable for YAML workflows |
-| `--pattern <pattern>` | Pattern for auto-generation (sequential, parallel, routing, loop) |
+| `--pattern <pattern>` | Pattern for auto-generation (sequential, parallel, routing, loop, orchestrator-workers, evaluator-optimizer) |
 | `--output <file>` | Output file for auto-generation |
 | `--llm <model>` | LLM model (e.g., openai/gpt-4o-mini) |
 | `--tools <tools>` | Tools (comma-separated, e.g., tavily) |
@@ -1361,8 +1388,13 @@ praisonai "Complex analysis" --router --router-provider anthropic
 # Router automatically selects:
 # - Simple tasks → gpt-4o-mini, claude-3-haiku
 # - Complex tasks → gpt-4-turbo, claude-3-opus
+
+# Create workflow with model routing template
+praisonai workflow create --template model-routing --output my_workflow.yaml
 ```

+Custom models can be configured in `agents.yaml`. See [Model Router Docs](https://docs.praison.ai/features/model-router) for details.
+
 ### Flow Display CLI:
 ```bash
 # Enable visual workflow tracking
@@ -1451,6 +1483,55 @@ export N8N_API_KEY="your-api-key"
 praisonai agents.yaml --n8n
 ```

+### External Agents CLI:
+
+Use external AI coding CLI tools (Claude Code, Gemini CLI, Codex CLI, Cursor CLI) as agent tools:
+
+```bash
+# Use Claude Code for coding tasks
+praisonai "Refactor the auth module" --external-agent claude
+
+# Use Gemini CLI for code analysis
+praisonai "Analyze codebase architecture" --external-agent gemini
+
+# Use OpenAI Codex CLI
+praisonai "Fix all bugs in src/" --external-agent codex
+
+# Use Cursor CLI
+praisonai "Add comprehensive tests" --external-agent cursor
+```
+
+**Python API:**
+```python
+from praisonai.integrations import (
+    ClaudeCodeIntegration,
+    GeminiCLIIntegration,
+    CodexCLIIntegration,
+    CursorCLIIntegration
+)
+
+# Create integration
+claude = ClaudeCodeIntegration(workspace="/project")
+
+# Execute a coding task
+result = await claude.execute("Refactor the auth module")
+
+# Use as agent tool
+from praisonai import Agent
+tool = claude.as_tool()
+agent = Agent(tools=[tool])
+```
+
+**Environment Variables:**
+```bash
+export ANTHROPIC_API_KEY=your-key  # Claude Code
+export GEMINI_API_KEY=your-key     # Gemini CLI
+export OPENAI_API_KEY=your-key     # Codex CLI
+export CURSOR_API_KEY=your-key     # Cursor CLI
+```
+
+See [External Agents Documentation](https://docs.praison.ai/code/external-agents) for more details.
+
 ### @Mentions in Prompts:
 ```bash
 # Include file content in prompt
@@ -2253,7 +2334,7 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 - 📖 **Wikipedia Agent** - Search and extract Wikipedia information
 - 💻 **Programming Agent** - Code development and analysis
 - 📝 **Markdown Agent** - Generate and format Markdown content
- 🔀 **Router Agent** - Dynamic task routing with cost optimisation
+- 🔀 **Model Router** - Smart model selection based on task complexity

 ### MCP Protocol

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.3.40" \
+    "praisonai>=2.3.45" \
    "praisonai[chat]" \
    "embedchain[github,youtube]"

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.3.40" \
+    "praisonai>=2.3.45" \
    "praisonai[ui]" \
    "praisonai[chat]" \
    "praisonai[realtime]" \
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.3.40" \
+    "praisonai>=2.3.45" \
    "praisonai[ui]" \
    "praisonai[crewai]"

@@ -0,0 +1,49 @@
+# PraisonAI Examples
+
+This folder contains examples for PraisonAI. For detailed documentation, visit [docs.praison.ai](https://docs.praison.ai).
+
+## Structure
+
+```
+examples/
+├── python/           # Python examples
+│   ├── agents/       # Agent examples (single, multi, router, etc.)
+│   ├── workflows/    # Workflow patterns (routing, parallel, loop)
+│   ├── tools/        # Custom tools examples
+│   ├── mcp/          # MCP protocol examples
+│   ├── memory/       # Memory and sessions
+│   ├── code/         # Code editing and external CLI tools
+│   └── ...
+├── yaml/             # YAML workflow examples
+└── cookbooks/        # Complete use-case examples
+```
+
+## Quick Links
+
+| Category | Examples | Docs |
+|----------|----------|------|
+| **Agents** | [python/agents/](python/agents/) | [📖](https://docs.praison.ai/concepts/agents) |
+| **Workflows** | [python/workflows/](python/workflows/) | [📖](https://docs.praison.ai/features/workflows) |
+| **Model Router** | [python/agents/router-agent-cost-optimization.py](python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/model-router) |
+| **MCP** | [python/mcp/](python/mcp/) | [📖](https://docs.praison.ai/mcp) |
+| **Memory** | [python/memory/](python/memory/) | [📖](https://docs.praison.ai/concepts/memory) |
+| **Tools** | [python/tools/](python/tools/) | [📖](https://docs.praison.ai/tools) |
+| **Code** | [python/code/](python/code/) | [📖](https://docs.praison.ai/code) |
+| **YAML** | [yaml/](yaml/) | [📖](https://docs.praison.ai/features/yaml-workflows) |
+
+## Running Examples
+
+```bash
+# Install PraisonAI
+pip install praisonai
+
+# Set API key
+export OPENAI_API_KEY=your_key_here
+
+# Run an example
+python examples/python/agents/single-agent.py
+```
+
+## CLI Commands
+
+See the main [README.md](../README.md#-cli--no-code-interface) for all CLI commands.
@@ -0,0 +1,132 @@
+"""
+AutoAgents Workflow Patterns Example
+
+This example demonstrates the new workflow auto-generation features:
+- Dynamic agent count based on task complexity
+- Multiple workflow patterns (sequential, parallel, routing, orchestrator-workers, evaluator-optimizer)
+- Pattern recommendation based on task keywords
+
+Documentation: https://docs.praison.ai/features/autoagents
+CLI Reference: https://docs.praison.ai/nocode/auto
+"""
+
+from praisonai.auto import AutoGenerator, WorkflowAutoGenerator
+import os
+import tempfile
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+print("=" * 60)
+print("AutoAgents Workflow Patterns Demo")
+print("=" * 60)
+
+# =============================================================================
+# Example 1: Dynamic Agent Count (Simple vs Complex Tasks)
+# =============================================================================
+print("\n📊 Example 1: Dynamic Agent Count")
+print("-" * 40)
+
+# Simple task - should create 1-2 agents
+with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+    simple_file = f.name
+
+simple_generator = AutoGenerator(
+    topic="Write a haiku about spring",
+    agent_file=simple_file,
+    framework="praisonai"
+)
+
+print("Simple task: 'Write a haiku about spring'")
+result = simple_generator.generate()
+print(f"Generated: {result}")
+
+# Complex task - should create 3-4 agents
+with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+    complex_file = f.name
+
+complex_generator = AutoGenerator(
+    topic="Research AI trends, analyze market data, write a comprehensive report with executive summary",
+    agent_file=complex_file,
+    framework="praisonai"
+)
+
+print("\nComplex task: 'Research AI trends, analyze market data...'")
+result = complex_generator.generate()
+print(f"Generated: {result}")
+
+# =============================================================================
+# Example 2: Pattern Recommendation
+# =============================================================================
+print("\n🎯 Example 2: Pattern Recommendation")
+print("-" * 40)
+
+test_tasks = [
+    ("Write a blog post", "sequential"),
+    ("Research from multiple sources simultaneously", "parallel"),
+    ("Classify and route customer requests", "routing"),
+    ("Comprehensive analysis and break down the problem", "orchestrator-workers"),
+    ("Refine and improve content quality", "evaluator-optimizer"),
+]
+
+for task, expected in test_tasks:
+    generator = WorkflowAutoGenerator(topic=task)
+    recommended = generator.recommend_pattern()
+    status = "✅" if recommended == expected else "⚠️"
+    print(f"{status} Task: '{task[:40]}...'")
+    print(f"   Recommended: {recommended}")
+
+# =============================================================================
+# Example 3: Generate Workflow with Specific Pattern
+# =============================================================================
+print("\n🔄 Example 3: Generate Workflows with Patterns")
+print("-" * 40)
+
+patterns = ["sequential", "parallel", "orchestrator-workers", "evaluator-optimizer"]
+
+for pattern in patterns:
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+        workflow_file = f.name
+    
+    generator = WorkflowAutoGenerator(
+        topic="Create a market analysis report",
+        workflow_file=workflow_file
+    )
+    
+    print(f"\n📋 Pattern: {pattern}")
+    result = generator.generate(pattern=pattern)
+    print(f"   Generated: {result}")
+    
+    # Read and show structure
+    import yaml
+    with open(result, 'r') as f:
+        data = yaml.safe_load(f)
+    print(f"   Agents: {list(data.get('agents', {}).keys())}")
+    print(f"   Steps: {len(data.get('steps', []))}")
+
+# =============================================================================
+# Example 4: CLI Usage (for reference)
+# =============================================================================
+print("\n💻 Example 4: CLI Commands (for reference)")
+print("-" * 40)
+print("""
+# Auto-generate agents (dynamic count)
+praisonai --auto "Write a haiku about spring"
+
+# Auto-generate workflow with pattern
+praisonai workflow auto "Research and write a report" --pattern sequential
+praisonai workflow auto "Research from multiple sources" --pattern parallel
+praisonai workflow auto "Comprehensive market analysis" --pattern orchestrator-workers
+praisonai workflow auto "Refine content quality" --pattern evaluator-optimizer
+
+# With output file
+praisonai workflow auto "Customer support routing" --pattern routing --output support.yaml
+""")
+
+print("\n" + "=" * 60)
+print("✅ AutoAgents Workflow Patterns Demo Complete!")
+print("=" * 60)
+print("\nDocumentation: https://docs.praison.ai/features/autoagents")
+print("CLI Reference: https://docs.praison.ai/nocode/auto")
@@ -0,0 +1,38 @@
+"""
+Autonomy Modes Example for PraisonAI CLI.
+
+Control AI autonomy: suggest, auto_edit, full_auto.
+Docs: https://docs.praison.ai/cli/autonomy-modes
+"""
+
+from praisonai.cli.features import AutonomyModeHandler
+from praisonai.cli.features.autonomy_mode import ActionRequest, ActionType
+
+# Initialize with suggest mode (safest)
+handler = AutonomyModeHandler()
+manager = handler.initialize(mode="suggest")
+
+print(f"Current mode: {handler.get_mode()}")
+print("Available modes: suggest, auto_edit, full_auto")
+
+# Create an action request
+action = ActionRequest(
+    action_type=ActionType.FILE_WRITE,
+    description="Edit src/main.py to add logging",
+    details={"file": "src/main.py"}
+)
+
+# In suggest mode, this would require approval
+# For demo, we'll just show the action
+print(f"\nAction: {action.description}")
+print(f"Type: {action.action_type.value}")
+print("Would require approval in 'suggest' mode")
+
+# Change to auto_edit mode
+handler.set_mode("auto_edit")
+print(f"\nChanged to: {handler.get_mode()}")
+print("File edits now auto-approved, shell commands still require approval")
+
+# Get statistics
+stats = handler.get_stats()
+print(f"\nStats: {stats}")
@@ -0,0 +1,34 @@
+"""
+Cost Tracking Example for PraisonAI CLI.
+
+Real-time token usage and cost monitoring.
+Docs: https://docs.praison.ai/cli/cost-tracking
+"""
+
+from praisonai.cli.features import CostTrackerHandler
+
+# Initialize tracker
+handler = CostTrackerHandler()
+tracker = handler.initialize(session_id="demo-session")
+
+# Track some requests
+handler.track_request("gpt-4o", input_tokens=1000, output_tokens=500)
+handler.track_request("gpt-4o-mini", input_tokens=2000, output_tokens=800)
+handler.track_request("claude-3-5-sonnet", input_tokens=1500, output_tokens=600)
+
+# Get totals
+print(f"Total tokens: {handler.get_tokens():,}")
+print(f"Total cost: ${handler.get_cost():.4f}")
+
+# Get detailed summary
+summary = handler.get_summary()
+print("\n=== Session Summary ===")
+print(f"Session ID: {summary['session_id']}")
+print(f"Total requests: {summary['total_requests']}")
+print(f"Input tokens: {summary['total_input_tokens']:,}")
+print(f"Output tokens: {summary['total_output_tokens']:,}")
+print(f"Total cost: ${summary['total_cost']:.4f}")
+print(f"Avg cost/request: ${summary['avg_cost_per_request']:.4f}")
+
+# Display formatted (uses Rich if available)
+handler.display_summary()
@@ -0,0 +1,45 @@
+"""
+Git Integration Example for PraisonAI CLI.
+
+Auto-commit with AI messages, diff viewing, undo.
+Docs: https://docs.praison.ai/cli/git-integration
+"""
+
+from praisonai.cli.features import GitIntegrationHandler
+
+# Initialize
+handler = GitIntegrationHandler(verbose=True)
+git = handler.initialize(repo_path=".")
+
+# Check if it's a git repo
+if not git.is_repo:
+    print("Not a git repository!")
+    exit(1)
+
+# Show status
+print("=== Git Status ===")
+status = handler.show_status()
+print(f"Branch: {status.branch}")
+print(f"Staged: {len(status.staged_files)}")
+print(f"Modified: {len(status.modified_files)}")
+print(f"Untracked: {len(status.untracked_files)}")
+
+# Show diff (if any changes)
+if status.has_changes:
+    print("\n=== Diff ===")
+    diff = handler.show_diff()
+    if diff:
+        print(diff[:300] + "..." if len(diff) > 300 else diff)
+
+# Show recent commits
+print("\n=== Recent Commits ===")
+commits = handler.show_log(count=5)
+for c in commits:
+    print(f"  {c.short_hash} {c.message[:50]}")
+
+# To commit with AI message:
+# commit = handler.commit()  # Auto-generates message
+# commit = handler.commit(message="Custom message")
+
+# To undo last commit:
+# handler.undo(soft=True)  # Keeps changes staged
@@ -0,0 +1,49 @@
+"""
+Interactive TUI Example for PraisonAI CLI.
+
+Rich terminal interface with completions and history.
+Docs: https://docs.praison.ai/cli/interactive-tui
+"""
+
+from praisonai.cli.features import InteractiveTUIHandler
+from praisonai.cli.features.interactive_tui import InteractiveConfig
+
+# Custom configuration
+config = InteractiveConfig(
+    prompt="ai> ",
+    multiline=True,
+    enable_completions=True,
+    show_status_bar=True
+)
+
+# Define callbacks
+def on_input(text):
+    """Handle regular input."""
+    return f"You said: {text}"
+
+def on_command(cmd):
+    """Handle slash commands."""
+    if cmd == "/exit":
+        return {"type": "exit"}
+    return {"type": "command", "message": f"Executed: {cmd}"}
+
+# Initialize
+handler = InteractiveTUIHandler()
+session = handler.initialize(
+    config=config,
+    on_input=on_input,
+    on_command=on_command
+)
+
+# Add commands for completion
+session.add_commands(["help", "exit", "cost", "model", "plan"])
+
+# Add symbols from codebase
+session.add_symbols(["MyClass", "my_function"])
+
+print("Interactive TUI initialized!")
+print("Commands available: /help, /exit, /cost, /model, /plan")
+print("Run handler.run() to start interactive session")
+
+# Uncomment to run interactive session:
+# handler.run()
@@ -0,0 +1,24 @@
+"""
+Repository Map Example for PraisonAI CLI.
+
+Intelligent codebase mapping with symbol extraction.
+Docs: https://docs.praison.ai/cli/repo-map
+"""
+
+from praisonai.cli.features import RepoMapHandler
+
+# Initialize with current directory
+handler = RepoMapHandler(verbose=True)
+repo_map = handler.initialize(root=".")
+
+# Get the repository map
+print("=== Repository Map ===")
+map_str = handler.get_map()
+print(map_str[:500] if len(map_str) > 500 else map_str)
+print("..." if len(map_str) > 500 else "")
+
+# Refresh after file changes
+handler.refresh()
+
+# Get symbols for a specific file (if exists)
+# symbols = handler.get_context("MyClass")
@@ -0,0 +1,42 @@
+"""
+Sandbox Execution Example for PraisonAI CLI.
+
+Secure isolated command execution (--sandbox flag).
+Docs: https://docs.praison.ai/cli/sandbox-execution
+"""
+
+from praisonai.cli.features import SandboxExecutorHandler
+from praisonai.cli.features.sandbox_executor import SandboxMode
+
+# Initialize with basic sandbox
+handler = SandboxExecutorHandler(verbose=True)
+sandbox = handler.initialize(mode="basic")
+
+print(f"Sandbox mode: {handler.get_mode()}")
+print(f"Sandbox enabled: {handler.is_enabled}")
+
+# Execute a safe command
+print("\n=== Safe Command ===")
+result = handler.execute("echo 'Hello from sandbox!'")
+print(f"Success: {result.success}")
+print(f"Output: {result.stdout.strip()}")
+print(f"Sandboxed: {result.was_sandboxed}")
+
+# Try a blocked command
+print("\n=== Blocked Command ===")
+result = handler.execute("rm -rf /")
+print(f"Success: {result.success}")
+print(f"Violations: {result.policy_violations}")
+
+# Validate command before execution
+print("\n=== Command Validation ===")
+violations = handler.validate_command("sudo apt install something")
+if violations:
+    print(f"Command blocked: {violations}")
+else:
+    print("Command allowed")
+
+# Available modes
+print("\n=== Available Modes ===")
+for mode in SandboxMode:
+    print(f"  {mode.value}")
@@ -0,0 +1,51 @@
+"""
+Slash Commands Example for PraisonAI CLI.
+
+Demonstrates interactive slash commands like /help, /cost, /model.
+Docs: https://docs.praison.ai/cli/slash-commands
+"""
+
+from praisonai.cli.features import SlashCommandHandler
+from praisonai.cli.features.slash_commands import SlashCommand, CommandKind
+
+# Create handler
+handler = SlashCommandHandler()
+
+# Execute commands
+print("=== /help ===")
+result = handler.execute("/help")
+print(result.get("message", ""))
+
+print("\n=== /cost ===")
+result = handler.execute("/cost")
+print(result.get("message", ""))
+
+print("\n=== /model ===")
+result = handler.execute("/model")
+print(result.get("message", ""))
+
+# Check if input is a command
+print("\n=== Command Detection ===")
+print(f"/help is command: {handler.is_command('/help')}")
+print(f"hello is command: {handler.is_command('hello')}")
+
+# Get completions for auto-complete
+print("\n=== Completions for '/he' ===")
+completions = handler.get_completions("/he")
+print(completions)
+
+# Register custom command
+def my_custom_handler(args, context):
+    return {"type": "custom", "message": f"Custom command with args: {args}"}
+
+custom_cmd = SlashCommand(
+    name="mycommand",
+    description="My custom command",
+    handler=my_custom_handler,
+    kind=CommandKind.ACTION,
+    aliases=["mc"]
+)
+
+handler.register(custom_cmd)
+result = handler.execute("/mycommand arg1 arg2")
+print(f"\n=== Custom Command ===\n{result.get('message', '')}")
@@ -0,0 +1,34 @@
+"""
+Claude Code CLI Integration Example
+
+Demonstrates how to use Claude Code CLI as an agent tool in PraisonAI.
+"""
+
+import asyncio
+from praisonai.integrations import ClaudeCodeIntegration
+
+async def main():
+    # Create Claude Code integration
+    claude = ClaudeCodeIntegration(
+        workspace=".",
+        output_format="json",
+        skip_permissions=True,
+        system_prompt="Be concise and follow best practices",
+        allowed_tools=["Read", "Write", "Bash"]
+    )
+    
+    # Check availability
+    print(f"Claude CLI available: {claude.is_available}")
+    print(f"Claude SDK available: {claude.sdk_available}")
+    
+    # Execute a coding task
+    result = await claude.execute("List all Python files in the current directory")
+    print(f"Result: {result}")
+    
+    # Stream output
+    print("\nStreaming output:")
+    async for event in claude.stream("Explain the project structure"):
+        print(event)
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,60 @@
+"""
+Code Editing Tools Example
+
+Demonstrates how to use PraisonAI's code editing tools with SEARCH/REPLACE diffs.
+"""
+
+from praisonai.code import (
+    set_workspace,
+    code_read_file,
+    code_write_file,
+    code_apply_diff,
+    code_list_files,
+    code_execute_command,
+    CODE_TOOLS
+)
+
+# Set workspace
+set_workspace(".")
+
+# List files
+print("Files in current directory:")
+files = code_list_files(".", recursive=False)
+for f in files:
+    print(f"  {f}")
+
+# Read a file
+print("\nReading example file:")
+try:
+    content = code_read_file("README.md", start_line=1, end_line=10)
+    print(content)
+except Exception as e:
+    print(f"  File not found: {e}")
+
+# Write a file
+print("\nWriting test file:")
+code_write_file("test_output.txt", "Hello from PraisonAI Code Tools!")
+print("  Created test_output.txt")
+
+# Apply a diff
+print("\nApplying diff:")
+diff = """
+<<<<<<< SEARCH
+Hello from PraisonAI Code Tools!
+=======
+Hello from PraisonAI Code Tools!
+This line was added by a diff.
+>>>>>>> REPLACE
+"""
+result = code_apply_diff("test_output.txt", diff)
+print(f"  {result}")
+
+# Execute command
+print("\nExecuting command:")
+output = code_execute_command("cat test_output.txt")
+print(f"  {output}")
+
+# Cleanup
+import os
+os.remove("test_output.txt")
+print("\nCleanup complete.")
@@ -0,0 +1,36 @@
+"""
+Codex CLI Integration Example
+
+Demonstrates how to use OpenAI Codex CLI as an agent tool in PraisonAI.
+"""
+
+import asyncio
+from praisonai.integrations import CodexCLIIntegration
+
+async def main():
+    # Create Codex CLI integration
+    codex = CodexCLIIntegration(
+        workspace=".",
+        full_auto=True,
+        sandbox="danger-full-access",
+        json_output=True
+    )
+    
+    # Check availability
+    print(f"Codex CLI available: {codex.is_available}")
+    print(f"Full Auto: {codex.full_auto}")
+    print(f"Sandbox: {codex.sandbox}")
+    
+    # Execute a coding task
+    result = await codex.execute("List files in the current directory")
+    print(f"Result: {result}")
+    
+    # Stream JSON events
+    print("\nStreaming events:")
+    async for event in codex.stream("Explain the project"):
+        event_type = event.get("type", "")
+        if event_type == "item.completed":
+            print(f"  {event}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,37 @@
+"""
+Cursor CLI Integration Example
+
+Demonstrates how to use Cursor CLI as an agent tool in PraisonAI.
+"""
+
+import asyncio
+from praisonai.integrations import CursorCLIIntegration
+
+async def main():
+    # Create Cursor CLI integration
+    cursor = CursorCLIIntegration(
+        workspace=".",
+        output_format="json",
+        force=True,
+        model="gpt-5",
+        stream_partial=True
+    )
+    
+    # Check availability
+    print(f"Cursor CLI available: {cursor.is_available}")
+    print(f"Force mode: {cursor.force}")
+    print(f"Model: {cursor.model}")
+    
+    # Execute a coding task
+    result = await cursor.execute("List files in the current directory")
+    print(f"Result: {result}")
+    
+    # Stream output
+    print("\nStreaming output:")
+    async for event in cursor.stream("Explain the project"):
+        content = event.get("content", "")
+        if content:
+            print(content, end="", flush=True)
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,58 @@
+"""
+External Agents Integration Example
+
+Demonstrates how to use all external CLI integrations as agent tools.
+"""
+
+import asyncio
+from praisonai.integrations import (
+    ClaudeCodeIntegration,
+    GeminiCLIIntegration,
+    CodexCLIIntegration,
+    CursorCLIIntegration,
+    get_available_integrations
+)
+
+async def main():
+    # Check availability of all integrations
+    print("=== External CLI Integrations ===\n")
+    
+    availability = get_available_integrations()
+    print("Availability:")
+    for name, avail in availability.items():
+        status = "✅" if avail else "❌"
+        print(f"  {status} {name}")
+    
+    # Create integrations
+    print("\n--- Claude Code ---")
+    claude = ClaudeCodeIntegration(workspace=".", skip_permissions=True)
+    print(f"CLI: {claude.cli_command}")
+    print(f"Available: {claude.is_available}")
+    tool = claude.as_tool()
+    print(f"Tool: {tool.__name__}")
+    
+    print("\n--- Gemini CLI ---")
+    gemini = GeminiCLIIntegration(workspace=".", model="gemini-2.5-flash")
+    print(f"CLI: {gemini.cli_command}")
+    print(f"Available: {gemini.is_available}")
+    tool = gemini.as_tool()
+    print(f"Tool: {tool.__name__}")
+    
+    print("\n--- Codex CLI ---")
+    codex = CodexCLIIntegration(workspace=".", full_auto=True)
+    print(f"CLI: {codex.cli_command}")
+    print(f"Available: {codex.is_available}")
+    tool = codex.as_tool()
+    print(f"Tool: {tool.__name__}")
+    
+    print("\n--- Cursor CLI ---")
+    cursor = CursorCLIIntegration(workspace=".", force=True)
+    print(f"CLI: {cursor.cli_command}")
+    print(f"Available: {cursor.is_available}")
+    tool = cursor.as_tool()
+    print(f"Tool: {tool.__name__}")
+    
+    print("\n=== All integrations ready ===")
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,33 @@
+"""
+Gemini CLI Integration Example
+
+Demonstrates how to use Gemini CLI as an agent tool in PraisonAI.
+"""
+
+import asyncio
+from praisonai.integrations import GeminiCLIIntegration
+
+async def main():
+    # Create Gemini CLI integration
+    gemini = GeminiCLIIntegration(
+        workspace=".",
+        model="gemini-2.5-flash",
+        output_format="json",
+        include_directories=["../lib", "../docs"]
+    )
+    
+    # Check availability
+    print(f"Gemini CLI available: {gemini.is_available}")
+    print(f"Model: {gemini.model}")
+    
+    # Execute a coding task
+    result = await gemini.execute("Analyze the code structure")
+    print(f"Result: {result}")
+    
+    # Execute with stats
+    result, stats = await gemini.execute_with_stats("Explain main.py")
+    print(f"Result: {result}")
+    print(f"Stats: {stats}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -1,11 +1,48 @@
+"""
+AutoAgents Example
+
+AutoAgents automatically creates and manages AI agents based on high-level instructions.
+It features dynamic agent count based on task complexity.
+
+Documentation: https://docs.praison.ai/features/autoagents
+CLI Reference: https://docs.praison.ai/nocode/auto
+
+New Features:
+- Dynamic agent count (1-4 based on task complexity)
+- Workflow patterns: sequential, parallel, routing, orchestrator-workers, evaluator-optimizer
+- Pattern recommendation based on task keywords
+- Tool preservation from LLM suggestions
+"""
+
 from praisonaiagents import AutoAgents
 from praisonaiagents.tools import duckduckgo

+# Basic usage - AutoAgents analyzes complexity and creates optimal agents
 agents = AutoAgents(
    instructions="Search for information about AI Agents",
    tools=[duckduckgo],
-    process="sequential",
-    verbose=True
+    process="sequential",  # or "hierarchical"
+    verbose=True,
+    max_agents=3  # Maximum number of agents to create
 )

-agents.start()
+result = agents.start()
+print(result)
+
+# =============================================================================
+# CLI Usage Examples (for reference)
+# =============================================================================
+# 
+# # Auto-generate agents (dynamic count based on complexity)
+# praisonai --auto "Write a haiku about spring"
+# praisonai --auto "Research AI trends, analyze data, write report"
+#
+# # Auto-generate workflow with specific pattern
+# praisonai workflow auto "Research and write" --pattern sequential
+# praisonai workflow auto "Research from multiple sources" --pattern parallel
+# praisonai workflow auto "Comprehensive analysis" --pattern orchestrator-workers
+# praisonai workflow auto "Refine content quality" --pattern evaluator-optimizer
+#
+# # With framework selection
+# praisonai --framework crewai --auto "Create a movie script"
+# praisonai --framework autogen --auto "Create a movie script"
@@ -0,0 +1,90 @@
+"""
+Unified Web Search Example
+
+This example demonstrates the search_web tool that automatically tries
+multiple search providers with fallback support.
+
+Search Provider Priority:
+1. Tavily (requires TAVILY_API_KEY + tavily-python)
+2. Exa (requires EXA_API_KEY + exa_py)
+3. You.com (requires YDC_API_KEY + youdotcom)
+4. DuckDuckGo (requires duckduckgo_search package, no API key)
+5. SearxNG (requires requests + running SearxNG instance)
+
+Installation:
+    pip install praisonaiagents duckduckgo_search
+
+Usage:
+    python web_search_example.py
+"""
+
+from praisonaiagents import Agent
+from praisonaiagents.tools import search_web, get_available_providers
+
+
+def main():
+    print("=" * 60)
+    print("Unified Web Search - Provider Status")
+    print("=" * 60)
+    
+    # Check which providers are available
+    providers = get_available_providers()
+    for p in providers:
+        status = "✓ Available" if p["available"] else f"✗ {p['reason']}"
+        print(f"  {p['name']:12} {status}")
+    
+    print("\n" + "=" * 60)
+    print("Example 1: Basic Search")
+    print("=" * 60)
+    
+    # Simple search - automatically uses best available provider
+    results = search_web("Python programming best practices", max_results=3)
+    
+    if results and "error" not in results[0]:
+        print(f"\nFound {len(results)} results using {results[0].get('provider', 'unknown')}:\n")
+        for r in results:
+            print(f"  Title: {r.get('title', 'N/A')[:60]}...")
+            print(f"  URL: {r.get('url', 'N/A')}")
+            print()
+    else:
+        print(f"\nSearch failed: {results}")
+    
+    print("=" * 60)
+    print("Example 2: Specify Providers")
+    print("=" * 60)
+    
+    # Only try specific providers
+    results = search_web(
+        "machine learning tutorials",
+        max_results=3,
+        providers=["duckduckgo", "tavily"]  # Try these in order
+    )
+    
+    if results and "error" not in results[0]:
+        print(f"\nFound {len(results)} results using {results[0].get('provider', 'unknown')}:\n")
+        for r in results:
+            print(f"  Title: {r.get('title', 'N/A')[:60]}...")
+            print(f"  URL: {r.get('url', 'N/A')}")
+            print()
+    else:
+        print(f"\nSearch failed: {results}")
+    
+    print("=" * 60)
+    print("Example 3: With PraisonAI Agent")
+    print("=" * 60)
+    
+    # Use search_web as an agent tool
+    agent = Agent(
+        name="SearchAgent",
+        role="Web Researcher",
+        goal="Find and summarize information from the web",
+        instructions="Search the web and provide concise summaries of findings.",
+        tools=[search_web]
+    )
+    
+    result = agent.start("What are the top 3 AI trends in 2025?")
+    print(f"\nAgent Response:\n{result}")
+
+
+if __name__ == "__main__":
+    main()
@@ -218,6 +218,10 @@ TOOL_MAPPINGS = {
    'crawl4ai_extract_sync': ('.crawl4ai_tools', None),
    'Crawl4AITools': ('.crawl4ai_tools', 'Crawl4AITools'),
    'crawl4ai_tools': ('.crawl4ai_tools', None),
+    
+    # Unified Web Search (auto-fallback across providers)
+    'search_web': ('.web_search', None),
+    'get_available_providers': ('.web_search', None),
 }

 _instances = {}  # Cache for class instances
@@ -254,7 +258,8 @@ def __getattr__(name: str) -> Any:
            'exa', 'exa_search', 'exa_search_contents', 'exa_find_similar', 'exa_answer',
            'exa_search_async', 'exa_search_contents_async', 'exa_answer_async',
            'crawl4ai', 'crawl4ai_many', 'crawl4ai_extract', 'crawl4ai_llm_extract',
-            'crawl4ai_sync', 'crawl4ai_extract_sync'
+            'crawl4ai_sync', 'crawl4ai_extract_sync',
+            'search_web', 'get_available_providers'
        ]:
            return getattr(module, name)
        if name in ['file_tools', 'pandas_tools', 'wikipedia_tools',
@@ -0,0 +1,329 @@
+"""Unified web search tool with automatic fallback across multiple providers.
+
+This module provides a single `search_web` function that automatically tries
+multiple search providers in order, falling back to the next if one fails.
+
+Search Provider Priority:
+1. Tavily (requires TAVILY_API_KEY + tavily-python)
+2. Exa (requires EXA_API_KEY + exa_py)
+3. You.com (requires YDC_API_KEY + youdotcom)
+4. DuckDuckGo (requires duckduckgo_search package, no API key)
+5. SearxNG (requires requests + running SearxNG instance)
+
+Usage:
+    from praisonaiagents.tools import search_web
+    
+    # Simple search - automatically uses best available provider
+    results = search_web("AI news 2024")
+    
+    # With max results
+    results = search_web("Python tutorials", max_results=10)
+"""
+
+from typing import List, Dict, Any, Optional
+import logging
+import os
+from importlib import util
+
+logger = logging.getLogger(__name__)
+
+
+def _check_tavily() -> tuple[bool, Optional[str]]:
+    """Check if Tavily is available."""
+    if util.find_spec("tavily") is None:
+        return False, "tavily-python package not installed"
+    if not os.environ.get("TAVILY_API_KEY"):
+        return False, "TAVILY_API_KEY not set"
+    return True, None
+
+
+def _check_exa() -> tuple[bool, Optional[str]]:
+    """Check if Exa is available."""
+    if util.find_spec("exa_py") is None:
+        return False, "exa_py package not installed"
+    if not os.environ.get("EXA_API_KEY"):
+        return False, "EXA_API_KEY not set"
+    return True, None
+
+
+def _check_youdotcom() -> tuple[bool, Optional[str]]:
+    """Check if You.com is available."""
+    if util.find_spec("youdotcom") is None:
+        return False, "youdotcom package not installed"
+    if not os.environ.get("YDC_API_KEY"):
+        return False, "YDC_API_KEY not set"
+    return True, None
+
+
+def _check_duckduckgo() -> tuple[bool, Optional[str]]:
+    """Check if DuckDuckGo is available."""
+    if util.find_spec("duckduckgo_search") is None:
+        return False, "duckduckgo_search package not installed"
+    return True, None
+
+
+def _check_searxng() -> tuple[bool, Optional[str]]:
+    """Check if SearxNG is available."""
+    if util.find_spec("requests") is None:
+        return False, "requests package not installed"
+    return True, None
+
+
+def _search_tavily(query: str, max_results: int = 5) -> List[Dict[str, Any]]:
+    """Search using Tavily."""
+    from tavily import TavilyClient
+    
+    client = TavilyClient(api_key=os.environ.get("TAVILY_API_KEY"))
+    response = client.search(query=query, max_results=max_results)
+    
+    results = []
+    for r in response.get("results", []):
+        results.append({
+            "title": r.get("title", ""),
+            "url": r.get("url", ""),
+            "snippet": r.get("content", ""),
+            "provider": "tavily"
+        })
+    return results
+
+
+def _search_exa(query: str, max_results: int = 5) -> List[Dict[str, Any]]:
+    """Search using Exa."""
+    from exa_py import Exa
+    
+    client = Exa(os.environ.get("EXA_API_KEY"))
+    response = client.search(query=query, num_results=max_results)
+    
+    results = []
+    for r in response.results:
+        results.append({
+            "title": getattr(r, "title", "") or "",
+            "url": r.url,
+            "snippet": getattr(r, "text", "") or "",
+            "provider": "exa"
+        })
+    return results
+
+
+def _search_youdotcom(query: str, max_results: int = 5) -> List[Dict[str, Any]]:
+    """Search using You.com."""
+    from youdotcom import You
+    
+    client = You(api_key_auth=os.environ.get("YDC_API_KEY"))
+    response = client.search.unified(query=query, count=max_results)
+    
+    results = []
+    # Handle response object
+    if hasattr(response, 'results'):
+        web_results = getattr(response.results, 'web', []) or []
+        for r in web_results[:max_results]:
+            results.append({
+                "title": getattr(r, "title", "") or "",
+                "url": getattr(r, "url", "") or "",
+                "snippet": getattr(r, "description", "") or "",
+                "provider": "youdotcom"
+            })
+    elif isinstance(response, dict):
+        web_results = response.get("results", {}).get("web", [])
+        for r in web_results[:max_results]:
+            results.append({
+                "title": r.get("title", ""),
+                "url": r.get("url", ""),
+                "snippet": r.get("description", ""),
+                "provider": "youdotcom"
+            })
+    return results
+
+
+def _search_duckduckgo(query: str, max_results: int = 5) -> List[Dict[str, Any]]:
+    """Search using DuckDuckGo."""
+    from duckduckgo_search import DDGS
+    
+    results = []
+    ddgs = DDGS()
+    for result in ddgs.text(keywords=query, max_results=max_results):
+        results.append({
+            "title": result.get("title", ""),
+            "url": result.get("href", ""),
+            "snippet": result.get("body", ""),
+            "provider": "duckduckgo"
+        })
+    return results
+
+
+def _search_searxng(query: str, max_results: int = 5, searxng_url: Optional[str] = None) -> List[Dict[str, Any]]:
+    """Search using SearxNG."""
+    import requests
+    
+    url = searxng_url or os.environ.get("SEARXNG_URL", "http://localhost:32768/search")
+    
+    params = {
+        'q': query,
+        'format': 'json',
+        'engines': 'google,bing,duckduckgo',
+        'safesearch': '1'
+    }
+    
+    response = requests.get(url, params=params, timeout=10)
+    response.raise_for_status()
+    
+    raw_results = response.json().get('results', [])
+    
+    results = []
+    for result in raw_results[:max_results]:
+        results.append({
+            "title": result.get("title", ""),
+            "url": result.get("url", ""),
+            "snippet": result.get("content", ""),
+            "provider": "searxng"
+        })
+    return results
+
+
+# Provider configuration: (name, check_func, search_func)
+SEARCH_PROVIDERS = [
+    ("tavily", _check_tavily, _search_tavily),
+    ("exa", _check_exa, _search_exa),
+    ("youdotcom", _check_youdotcom, _search_youdotcom),
+    ("duckduckgo", _check_duckduckgo, _search_duckduckgo),
+    ("searxng", _check_searxng, _search_searxng),
+]
+
+
+def search_web(
+    query: str,
+    max_results: int = 5,
+    providers: Optional[List[str]] = None,
+    searxng_url: Optional[str] = None,
+) -> List[Dict[str, Any]]:
+    """Search the web using multiple providers with automatic fallback.
+    
+    Tries each search provider in order until one succeeds. For each provider,
+    it first checks if the API key is set (if required) and if the package is
+    installed, then attempts the search. If the search fails, it moves to the
+    next provider.
+    
+    Args:
+        query: The search query string
+        max_results: Maximum number of results to return (default: 5)
+        providers: Optional list of provider names to try, in order.
+                  If not specified, uses default order:
+                  ["tavily", "exa", "youdotcom", "duckduckgo", "searxng"]
+        searxng_url: Optional custom SearxNG instance URL
+        
+    Returns:
+        List of search results, each containing:
+        - title: Result title
+        - url: Result URL
+        - snippet: Result description/snippet
+        - provider: Name of the provider that returned the result
+        
+        If all providers fail, returns a list with a single error dict.
+        
+    Example:
+        # Use default provider order
+        results = search_web("AI news 2024")
+        
+        # Specify providers to try
+        results = search_web("Python tutorials", providers=["duckduckgo", "tavily"])
+        
+        # With custom SearxNG URL
+        results = search_web("tech news", searxng_url="http://my-searxng:8080/search")
+    """
+    errors = []
+    
+    # Determine which providers to try
+    if providers:
+        # Filter to only valid provider names
+        provider_order = []
+        for name in providers:
+            for pname, check_fn, search_fn in SEARCH_PROVIDERS:
+                if pname == name.lower():
+                    provider_order.append((pname, check_fn, search_fn))
+                    break
+    else:
+        provider_order = SEARCH_PROVIDERS
+    
+    for provider_name, check_func, search_func in provider_order:
+        # Step 1: Check if provider is available (API key + package)
+        is_available, check_error = check_func()
+        if not is_available:
+            logger.debug(f"Skipping {provider_name}: {check_error}")
+            errors.append(f"{provider_name}: {check_error}")
+            continue
+        
+        # Step 2: Try to search
+        try:
+            logger.debug(f"Trying {provider_name} for query: {query}")
+            
+            if provider_name == "searxng":
+                results = search_func(query, max_results, searxng_url)
+            else:
+                results = search_func(query, max_results)
+            
+            if results:
+                logger.info(f"search_web: Successfully used {provider_name}")
+                return results
+            else:
+                errors.append(f"{provider_name}: No results returned")
+                
+        except Exception as e:
+            error_msg = f"{provider_name}: {str(e)}"
+            logger.debug(f"Search failed with {provider_name}: {e}")
+            errors.append(error_msg)
+            continue
+    
+    # All providers failed
+    error_summary = "; ".join(errors) if errors else "No search providers available"
+    logger.error(f"search_web: All providers failed - {error_summary}")
+    return [{"error": f"All search providers failed: {error_summary}"}]
+
+
+def get_available_providers() -> List[Dict[str, Any]]:
+    """Get list of available search providers and their status.
+    
+    Returns:
+        List of dicts with provider info:
+        - name: Provider name
+        - available: Whether the provider is ready to use
+        - reason: Reason if not available
+        
+    Example:
+        providers = get_available_providers()
+        for p in providers:
+            print(f"{p['name']}: {'✓' if p['available'] else '✗'} {p.get('reason', '')}")
+    """
+    result = []
+    for name, check_func, _ in SEARCH_PROVIDERS:
+        is_available, error = check_func()
+        result.append({
+            "name": name,
+            "available": is_available,
+            "reason": error if not is_available else None
+        })
+    return result
+
+
+if __name__ == "__main__":
+    # Example usage and provider status check
+    print("=" * 60)
+    print("Web Search Tool - Provider Status")
+    print("=" * 60)
+    
+    providers = get_available_providers()
+    for p in providers:
+        status = "✓ Available" if p["available"] else f"✗ {p['reason']}"
+        print(f"  {p['name']:12} {status}")
+    
+    print("\n" + "=" * 60)
+    print("Testing search_web...")
+    print("=" * 60)
+    
+    results = search_web("Python programming", max_results=3)
+    if results and "error" not in results[0]:
+        print(f"\nFound {len(results)} results using {results[0].get('provider', 'unknown')}:")
+        for r in results:
+            print(f"\n  Title: {r.get('title', 'N/A')[:50]}...")
+            print(f"  URL: {r.get('url', 'N/A')}")
+    else:
+        print(f"\nSearch failed: {results}")
@@ -6,10 +6,13 @@
  </picture>
 </p>

+<!-- mcp-name: io.github.MervinPraison/praisonai -->
+
 <p align="center">
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://static.pepy.tech/badge/PraisonAI" alt="Total Downloads" /></a>
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://img.shields.io/github/v/release/MervinPraison/PraisonAI" alt="Latest Stable Version" /></a>
 <a href="https://github.com/MervinPraison/PraisonAI"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License" /></a>
+<a href="https://registry.modelcontextprotocol.io/servers/io.github.MervinPraison/praisonai"><img src="https://img.shields.io/badge/MCP-Registry-blue" alt="MCP Registry" /></a>
 </p>

 <div align="center">
@@ -188,8 +191,14 @@ npm install praisonai
 | 📚 Add Custom Knowledge | [Example](examples/python/concepts/knowledge-agents.py) | [📖](https://docs.praison.ai/features/knowledge) |
 | 🧠 Memory (Short & Long Term) | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
 | 📄 Chat with PDF Agents | [Example](examples/python/concepts/chat-with-pdf.py) | [📖](https://docs.praison.ai/features/chat-with-pdf) |
-| 💻 Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
-| ✏️ AI Code Editing Tools | [Example](#ai-code-editing) | [📖](https://docs.praison.ai/features/code) |
+| **💻 Code** | | |
+| ↳ Code Interpreter Agents | [Example](examples/python/agents/code-agent.py) | [📖](https://docs.praison.ai/features/codeagent) |
+| ↳ AI Code Editing Tools | [Example](examples/python/code/code_editing_example.py) | [📖](https://docs.praison.ai/code/editing) |
+| ↳ External Agents (All) | [Example](examples/python/code/external_agents_example.py) | [📖](https://docs.praison.ai/code/external-agents) |
+| ↳ Claude Code CLI | [Example](examples/python/code/claude_code_example.py) | [📖](https://docs.praison.ai/code/claude-code) |
+| ↳ Gemini CLI | [Example](examples/python/code/gemini_cli_example.py) | [📖](https://docs.praison.ai/code/gemini-cli) |
+| ↳ Codex CLI | [Example](examples/python/code/codex_cli_example.py) | [📖](https://docs.praison.ai/code/codex-cli) |
+| ↳ Cursor CLI | [Example](examples/python/code/cursor_cli_example.py) | [📖](https://docs.praison.ai/code/cursor-cli) |
 | 📚 RAG Agents | [Example](examples/python/concepts/rag-agents.py) | [📖](https://docs.praison.ai/features/rag) |
 | 🤔 Async & Parallel Processing | [Example](examples/python/general/async_example.py) | [📖](https://docs.praison.ai/features/async) |
 | 🔢 Math Agents | [Example](examples/python/agents/math-agent.py) | [📖](https://docs.praison.ai/features/mathagent) |
@@ -207,6 +216,7 @@ npm install praisonai
 | 🧠 Claude Memory Tool | [Example](#claude-memory-tool-cli) | [📖](https://docs.praison.ai/features/claude-memory-tool) |
 | 💾 File-Based Memory | [Example](examples/python/general/memory_example.py) | [📖](https://docs.praison.ai/concepts/memory) |
 | 🔍 Built-in Search Tools | [Example](examples/python/agents/websearch-agent.py) | [📖](https://docs.praison.ai/tools/tavily) |
+| 🔎 Unified Web Search | [Example](src/praisonai-agents/examples/web_search_example.py) | [📖](https://docs.praison.ai/tools/web-search) |
 | 📋 Planning Mode | [Example](examples/python/agents/planning-agent.py) | [📖](https://docs.praison.ai/features/planning-mode) |
 | 🔧 Planning Tools | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
 | 🧠 Planning Reasoning | [Example](#3-agent-with-planning-mode) | [📖](https://docs.praison.ai/features/planning-mode) |
@@ -226,7 +236,7 @@ npm install praisonai
 | 💻 Programming Agent | [Example](examples/python/agents/programming-agent.py) | [📖](https://docs.praison.ai/agents/programming) |
 | 📝 Markdown Agent | [Example](examples/python/agents/markdown-agent.py) | [📖](https://docs.praison.ai/agents/markdown) |
 | 📝 Prompt Expander Agent | [Example](#prompt-expansion) | [📖](https://docs.praison.ai/agents/prompt-expander) |
-| 🔀 Router Agent | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/routing) |
+| 🔀 Model Router | [Example](examples/python/agents/router-agent-cost-optimization.py) | [📖](https://docs.praison.ai/features/model-router) |
 | ⛓️ Prompt Chaining | [Example](examples/python/general/prompt_chaining.py) | [📖](https://docs.praison.ai/features/promptchaining) |
 | 🔍 Evaluator Optimiser | [Example](examples/python/general/evaluator-optimiser.py) | [📖](https://docs.praison.ai/features/evaluator-optimiser) |
 | 👷 Orchestrator Workers | [Example](examples/python/general/orchestrator-workers.py) | [📖](https://docs.praison.ai/features/orchestrator-worker) |
@@ -248,6 +258,14 @@ npm install praisonai
 | @ @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/cli/mentions) |
 | 💾 Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/cli/session) |
 | 📜 History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/cli/session) |
+| **🖥️ CLI Features** | | |
+| ↳ Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/cli/slash-commands) |
+| ↳ Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/cli/autonomy-modes) |
+| ↳ Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/cli/cost-tracking) |
+| ↳ Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/cli/repo-map) |
+| ↳ Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/cli/interactive-tui) |
+| ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/cli/git-integration) |
+| ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/cli/sandbox-execution) |

 ---

@@ -1120,6 +1138,15 @@ praisonai workflow auto "Research AI trends" --pattern parallel
 # Generate routing workflow (classifier routes to specialists)
 praisonai workflow auto "Build a chatbot" --pattern routing

+# Generate orchestrator-workers workflow (central orchestrator delegates)
+praisonai workflow auto "Comprehensive market analysis" --pattern orchestrator-workers
+
+# Generate evaluator-optimizer workflow (iterative refinement)
+praisonai workflow auto "Write and refine article" --pattern evaluator-optimizer
+
+# Specify output file
+praisonai workflow auto "Build a chatbot" --pattern routing
+
 # Specify output file
 praisonai workflow auto "Research AI" --pattern sequential --output my_workflow.yaml
 ```
@@ -1129,7 +1156,7 @@ praisonai workflow auto "Research AI" --pattern sequential --output my_workflow.
 |------|-------------|
 | `--workflow-var key=value` | Set workflow variable (can be repeated) |
 | `--var key=value` | Set variable for YAML workflows |
-| `--pattern <pattern>` | Pattern for auto-generation (sequential, parallel, routing, loop) |
+| `--pattern <pattern>` | Pattern for auto-generation (sequential, parallel, routing, loop, orchestrator-workers, evaluator-optimizer) |
 | `--output <file>` | Output file for auto-generation |
 | `--llm <model>` | LLM model (e.g., openai/gpt-4o-mini) |
 | `--tools <tools>` | Tools (comma-separated, e.g., tavily) |
@@ -1361,8 +1388,13 @@ praisonai "Complex analysis" --router --router-provider anthropic
 # Router automatically selects:
 # - Simple tasks → gpt-4o-mini, claude-3-haiku
 # - Complex tasks → gpt-4-turbo, claude-3-opus
+
+# Create workflow with model routing template
+praisonai workflow create --template model-routing --output my_workflow.yaml
 ```

+Custom models can be configured in `agents.yaml`. See [Model Router Docs](https://docs.praison.ai/features/model-router) for details.
+
 ### Flow Display CLI:
 ```bash
 # Enable visual workflow tracking
@@ -1451,6 +1483,55 @@ export N8N_API_KEY="your-api-key"
 praisonai agents.yaml --n8n
 ```

+### External Agents CLI:
+
+Use external AI coding CLI tools (Claude Code, Gemini CLI, Codex CLI, Cursor CLI) as agent tools:
+
+```bash
+# Use Claude Code for coding tasks
+praisonai "Refactor the auth module" --external-agent claude
+
+# Use Gemini CLI for code analysis
+praisonai "Analyze codebase architecture" --external-agent gemini
+
+# Use OpenAI Codex CLI
+praisonai "Fix all bugs in src/" --external-agent codex
+
+# Use Cursor CLI
+praisonai "Add comprehensive tests" --external-agent cursor
+```
+
+**Python API:**
+```python
+from praisonai.integrations import (
+    ClaudeCodeIntegration,
+    GeminiCLIIntegration,
+    CodexCLIIntegration,
+    CursorCLIIntegration
+)
+
+# Create integration
+claude = ClaudeCodeIntegration(workspace="/project")
+
+# Execute a coding task
+result = await claude.execute("Refactor the auth module")
+
+# Use as agent tool
+from praisonai import Agent
+tool = claude.as_tool()
+agent = Agent(tools=[tool])
+```
+
+**Environment Variables:**
+```bash
+export ANTHROPIC_API_KEY=your-key  # Claude Code
+export GEMINI_API_KEY=your-key     # Gemini CLI
+export OPENAI_API_KEY=your-key     # Codex CLI
+export CURSOR_API_KEY=your-key     # Cursor CLI
+```
+
+See [External Agents Documentation](https://docs.praison.ai/code/external-agents) for more details.
+
 ### @Mentions in Prompts:
 ```bash
 # Include file content in prompt
@@ -2253,7 +2334,7 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 - 📖 **Wikipedia Agent** - Search and extract Wikipedia information
 - 💻 **Programming Agent** - Code development and analysis
 - 📝 **Markdown Agent** - Generate and format Markdown content
- 🔀 **Router Agent** - Dynamic task routing with cost optimisation
+- 🔀 **Model Router** - Smart model selection based on task complexity

 ### MCP Protocol

@@ -3,8 +3,8 @@ class Praisonai < Formula
  
    desc "AI tools for various AI applications"
    homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.40.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.40.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.45.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.45.tar.gz | shasum -a 256`.split.first
    license "MIT"
  
    depends_on "[email protected]"
@@ -1,3 +1,7 @@
+# Suppress crewai.cli.config logger BEFORE any imports to prevent INFO log
+import logging
+logging.getLogger('crewai.cli.config').setLevel(logging.ERROR)
+
 # Disable OpenTelemetry SDK
 import os
 os.environ["OTEL_SDK_DISABLED"] = "true"
@@ -51,14 +51,140 @@ try:
 except ImportError:
    PRAISONAI_TOOLS_AVAILABLE = False

+# LiteLLM availability check for multi-provider support
+LITELLM_AVAILABLE = False
+try:
+    import litellm  # noqa: F401 - imported for availability check
+    LITELLM_AVAILABLE = True
+except ImportError:
+    pass
+
 logging.basicConfig(level=os.environ.get('LOGLEVEL', 'INFO').upper(), format='%(asctime)s - %(levelname)s - %(message)s')

-# Define Pydantic models outside of the generate method
+# =============================================================================
+# Available Tools List (shared between generators)
+# =============================================================================
+AVAILABLE_TOOLS = [
+    "CodeDocsSearchTool", "CSVSearchTool", "DirectorySearchTool", "DOCXSearchTool",
+    "DirectoryReadTool", "FileReadTool", "TXTSearchTool", "JSONSearchTool",
+    "MDXSearchTool", "PDFSearchTool", "RagTool", "ScrapeElementFromWebsiteTool",
+    "ScrapeWebsiteTool", "WebsiteSearchTool", "XMLSearchTool",
+    "YoutubeChannelSearchTool", "YoutubeVideoSearchTool"
+]
+
+# =============================================================================
+# Base Generator Class (DRY - shared functionality)
+# =============================================================================
+class BaseAutoGenerator:
+    """
+    Base class for auto-generators with shared functionality.
+    
+    Provides:
+    - Lazy-loaded instructor client (LiteLLM or OpenAI fallback)
+    - Environment variable handling for model/API configuration
+    - Config list management
+    """
+    
+    def __init__(self, config_list: Optional[List[Dict]] = None):
+        """
+        Initialize base generator with LLM configuration.
+        
+        Args:
+            config_list: Optional LLM configuration list
+        """
+        # Support multiple environment variable patterns for better compatibility
+        model_name = os.environ.get("MODEL_NAME") or os.environ.get("OPENAI_MODEL_NAME", "gpt-4o-mini")
+        base_url = (
+            os.environ.get("OPENAI_BASE_URL") or 
+            os.environ.get("OPENAI_API_BASE") or
+            os.environ.get("OLLAMA_API_BASE", "https://api.openai.com/v1")
+        )
+        
+        self.config_list = config_list or [
+            {
+                'model': model_name,
+                'base_url': base_url,
+                'api_key': os.environ.get("OPENAI_API_KEY")
+            }
+        ]
+        self._client = None  # Lazy loading for performance
+    
+    @property
+    def client(self):
+        """Lazy load the instructor client to avoid performance impact.
+        
+        Uses LiteLLM via instructor.from_provider if available for multi-provider support,
+        otherwise falls back to direct OpenAI SDK.
+        """
+        if self._client is None:
+            if LITELLM_AVAILABLE:
+                # Use LiteLLM for multi-provider support (100+ LLMs)
+                model_name = self.config_list[0]['model']
+                self._client = instructor.from_provider(
+                    f"litellm/{model_name}",
+                    mode=instructor.Mode.JSON
+                )
+            else:
+                # Fallback to direct OpenAI SDK
+                self._client = instructor.patch(
+                    OpenAI(
+                        base_url=self.config_list[0]['base_url'],
+                        api_key=self.config_list[0]['api_key'],
+                    ),
+                    mode=instructor.Mode.JSON,
+                )
+        return self._client
+    
+    @staticmethod
+    def get_available_tools() -> List[str]:
+        """Return list of available tools for agent assignment."""
+        return AVAILABLE_TOOLS.copy()
+    
+    @staticmethod
+    def analyze_complexity(topic: str) -> str:
+        """
+        Analyze task complexity based on keywords.
+        
+        Args:
+            topic: The task description
+            
+        Returns:
+            str: Complexity level - 'simple', 'moderate', or 'complex'
+        """
+        topic_lower = topic.lower()
+        
+        # Complex task indicators
+        complex_keywords = [
+            'comprehensive', 'multi-step', 'analyze and', 'research and write',
+            'multiple', 'coordinate', 'complex', 'detailed analysis',
+            'full report', 'in-depth', 'thorough'
+        ]
+        
+        # Simple task indicators
+        simple_keywords = [
+            'write a', 'create a', 'simple', 'quick', 'brief',
+            'haiku', 'poem', 'summary', 'list', 'single'
+        ]
+        
+        if any(kw in topic_lower for kw in complex_keywords):
+            return 'complex'
+        elif any(kw in topic_lower for kw in simple_keywords):
+            return 'simple'
+        else:
+            return 'moderate'
+
+
+# =============================================================================
+# Pydantic Models for Structured Output
+# =============================================================================
+
 class TaskDetails(BaseModel):
+    """Details for a single task."""
    description: str
    expected_output: str

 class RoleDetails(BaseModel):
+    """Details for a single role/agent."""
    role: str
    goal: str
    backstory: str
@@ -66,14 +192,62 @@ class RoleDetails(BaseModel):
    tools: List[str]

 class TeamStructure(BaseModel):
+    """Structure for multi-agent team."""
    roles: Dict[str, RoleDetails]

-class AutoGenerator:
-    def __init__(self, topic="Movie Story writing about AI", agent_file="test.yaml", framework="crewai", config_list: Optional[List[Dict]] = None):
+class SingleAgentStructure(BaseModel):
+    """Structure for single-agent generation (Anthropic's 'start simple' principle)."""
+    name: str
+    role: str
+    goal: str
+    backstory: str
+    instructions: str
+    tools: List[str] = []
+    task_description: str
+    expected_output: str
+
+class PatternRecommendation(BaseModel):
+    """LLM-based pattern recommendation with reasoning."""
+    pattern: str  # sequential, parallel, routing, orchestrator-workers, evaluator-optimizer
+    reasoning: str  # Why this pattern was chosen
+    confidence: float  # 0.0 to 1.0 confidence score
+
+class ValidationGate(BaseModel):
+    """Validation gate for prompt chaining workflows."""
+    criteria: str  # What to validate
+    pass_action: str  # Action if validation passes (e.g., "continue", "next_step")
+    fail_action: str  # Action if validation fails (e.g., "retry", "escalate", "abort")
+
+class AutoGenerator(BaseAutoGenerator):
+    """
+    Auto-generates agents.yaml files from a topic description.
+    
+    Inherits from BaseAutoGenerator for shared LLM client functionality.
+    
+    Usage:
+        generator = AutoGenerator(framework="crewai", topic="Create a movie script")
+        path = generator.generate()
+    """
+    
+    def __init__(self, topic="Movie Story writing about AI", agent_file="test.yaml", 
+                 framework="crewai", config_list: Optional[List[Dict]] = None,
+                 pattern: str = "sequential", single_agent: bool = False):
        """
        Initialize the AutoGenerator class with the specified topic, agent file, and framework.
+        
+        Args:
+            topic: The task/topic for agent generation
+            agent_file: Output YAML file name
+            framework: Framework to use (crewai, autogen, praisonai)
+            config_list: Optional LLM configuration
+            pattern: Workflow pattern (sequential, parallel, routing, orchestrator-workers, evaluator-optimizer)
+            single_agent: If True, generate a single agent instead of a team
+        
        Note: autogen framework is different from this AutoGenerator class.
        """
+        # Initialize base class first (handles config_list and client)
+        super().__init__(config_list=config_list)
+        
        # Validate framework availability and show framework-specific messages
        if framework == "crewai" and not CREWAI_AVAILABLE:
            raise ImportError("""
@@ -106,35 +280,42 @@ Tools are not available for {framework}. To use tools, install:
    pip install "praisonai[{framework}]"
 """)

-        # Support multiple environment variable patterns for better compatibility
-        # Priority order: MODEL_NAME > OPENAI_MODEL_NAME for model selection
-        model_name = os.environ.get("MODEL_NAME") or os.environ.get("OPENAI_MODEL_NAME", "gpt-5-nano")
-        
-        # Priority order for base_url: OPENAI_BASE_URL > OPENAI_API_BASE > OLLAMA_API_BASE
-        # OPENAI_BASE_URL is the standard OpenAI SDK environment variable
-        base_url = (
-            os.environ.get("OPENAI_BASE_URL") or 
-            os.environ.get("OPENAI_API_BASE") or
-            os.environ.get("OLLAMA_API_BASE", "https://api.openai.com/v1")
-        )
-        
-        self.config_list = config_list or [
-            {
-                'model': model_name,
-                'base_url': base_url,
-                'api_key': os.environ.get("OPENAI_API_KEY")
-            }
-        ]
        self.topic = topic
        self.agent_file = agent_file
        self.framework = framework or "praisonai"
-        self.client = instructor.patch(
-            OpenAI(
-                base_url=self.config_list[0]['base_url'],
-                api_key=self.config_list[0]['api_key'],
-            ),
-            mode=instructor.Mode.JSON,
-        )
+        self.pattern = pattern
+        self.single_agent = single_agent
+    
+    def recommend_pattern(self, topic: str = None) -> str:
+        """
+        Recommend the best workflow pattern based on task characteristics.
+        
+        Args:
+            topic: The task description (uses self.topic if not provided)
+            
+        Returns:
+            str: Recommended pattern name
+        """
+        task = topic or self.topic
+        task_lower = task.lower()
+        
+        # Keywords that suggest specific patterns
+        parallel_keywords = ['multiple', 'concurrent', 'parallel', 'simultaneously', 'different sources', 'compare', 'various']
+        routing_keywords = ['classify', 'categorize', 'route', 'different types', 'depending on', 'if...then']
+        orchestrator_keywords = ['complex', 'comprehensive', 'multi-step', 'coordinate', 'delegate', 'break down', 'analyze and']
+        evaluator_keywords = ['refine', 'improve', 'iterate', 'quality', 'review', 'feedback', 'polish', 'optimize']
+        
+        # Check for pattern indicators
+        if any(kw in task_lower for kw in evaluator_keywords):
+            return "evaluator-optimizer"
+        elif any(kw in task_lower for kw in orchestrator_keywords):
+            return "orchestrator-workers"
+        elif any(kw in task_lower for kw in routing_keywords):
+            return "routing"
+        elif any(kw in task_lower for kw in parallel_keywords):
+            return "parallel"
+        else:
+            return "sequential"

    def generate(self, merge=False):
        """
@@ -157,7 +338,8 @@ Tools are not available for {framework}. To use tools, install:
        response = self.client.chat.completions.create(
            model=self.config_list[0]['model'],
            response_model=TeamStructure,
-            max_retries=10,
+            max_retries=5,
+            timeout=120.0,  # 2 minute timeout for complex generations
            messages=[
                {"role": "system", "content": "You are a helpful assistant designed to output complex team structures."},
                {"role": "user", "content": self.get_user_content()}
@@ -194,8 +376,7 @@ Tools are not available for {framework}. To use tools, install:
                    "goal": role_details['goal'],
                    "role": role_details['role'],
                    "tasks": {},
-                    # "tools": role_details.get('tools', []),
-                    "tools": ['']
+                    "tools": role_details.get('tools', [])
                }

                for task_id, task_details in role_details['tasks'].items():
@@ -265,7 +446,7 @@ Tools are not available for {framework}. To use tools, install:
                "goal": role_details['goal'],
                "role": role_details['role'],
                "tasks": {},
-                "tools": ['']
+                "tools": role_details.get('tools', [])
            }
            
            # Add tasks for this role
@@ -292,45 +473,77 @@ Tools are not available for {framework}. To use tools, install:
            prompt = generator.get_user_content()
            print(prompt)
        """
-        user_content = """Generate a team structure for  \"""" + self.topic + """\" task. 
-No Input data will be provided to the team.
-The team will work in sequence. First role will pass the output to the next role, and so on.
-The last role will generate the final output.
-Think step by step.
-With maximum 3 roles, each with 1 task. Include role goals, backstories, task descriptions, and expected outputs.
-List of Available Tools: CodeDocsSearchTool, CSVSearchTool, DirectorySearchTool, DOCXSearchTool, DirectoryReadTool, FileReadTool, TXTSearchTool, JSONSearchTool, MDXSearchTool, PDFSearchTool, RagTool, ScrapeElementFromWebsiteTool, ScrapeWebsiteTool, WebsiteSearchTool, XMLSearchTool, YoutubeChannelSearchTool, YoutubeVideoSearchTool.
-Only use Available Tools. Do Not use any other tools. 
-Example Below: 
-Use below example to understand the structure of the output. 
-The final role you create should satisfy the provided task: """ + self.topic + """.
-{
-"roles": {
-"narrative_designer": {
-"role": "Narrative Designer",
-"goal": "Create AI storylines",
-"backstory": "Skilled in narrative development for AI, with a focus on story resonance.",
-"tools": ["ScrapeWebsiteTool"],
-"tasks": {
-"story_concept_development": {
-"description": "Craft a unique AI story concept with depth and engagement using concept from this page the content https://www.asthebirdfliesblog.com/posts/how-to-write-book-story-development .",
-"expected_output": "Document with narrative arcs, character bios, and settings."
-}
-}
-},
-"scriptwriter": {
-"role": "Scriptwriter",
-"goal": "Write scripts from AI concepts",
-"backstory": "Expert in dialogue and script structure, translating concepts into scripts.",
-"tasks": {
-"scriptwriting_task": {
-"description": "Turn narrative concepts into scripts, including dialogue and scenes.",
-"expected_output": "Production-ready script with dialogue and scene details."
-}
-}
-}
-}
-}
-        """
+        # Pattern-specific guidance
+        pattern_guidance = {
+            "sequential": "The team will work in sequence. Each role passes output to the next.",
+            "parallel": "The team will work in parallel on independent subtasks, then combine results.",
+            "routing": "A classifier agent will route requests to specialized agents based on input type.",
+            "orchestrator-workers": "A central orchestrator will dynamically delegate tasks to specialized workers.",
+            "evaluator-optimizer": "One agent generates content, another evaluates it in a loop until quality criteria are met."
+        }
+        
+        workflow_guidance = pattern_guidance.get(self.pattern, pattern_guidance["sequential"])
+        
+        user_content = f"""Analyze and generate a team structure for: "{self.topic}"
+
+STEP 1: TASK COMPLEXITY ANALYSIS
+First, analyze the task complexity:
+- Is this a simple task that 1-2 agents could handle?
+- Does it require multiple specialized perspectives?
+- Are there clear sequential dependencies between steps?
+
+STEP 2: DETERMINE OPTIMAL TEAM SIZE
+Based on your analysis, create the minimum number of agents needed:
+- Simple tasks: 1-2 agents
+- Moderate tasks: 2-3 agents  
+- Complex tasks: 3-4 agents (maximum)
+
+IMPORTANT: Only create agents that provide meaningful specialization. Avoid unnecessary complexity.
+
+STEP 3: DESIGN THE TEAM (Pattern: {self.pattern})
+{workflow_guidance}
+Each agent should have:
+- A clear, distinct role
+- A specific goal
+- Relevant backstory
+- 1 focused task with clear description and expected output
+- Appropriate tools (only if needed)
+
+Available Tools: CodeDocsSearchTool, CSVSearchTool, DirectorySearchTool, DOCXSearchTool, DirectoryReadTool, FileReadTool, TXTSearchTool, JSONSearchTool, MDXSearchTool, PDFSearchTool, RagTool, ScrapeElementFromWebsiteTool, ScrapeWebsiteTool, WebsiteSearchTool, XMLSearchTool, YoutubeChannelSearchTool, YoutubeVideoSearchTool.
+Only use these tools if the task requires them. Use empty list [] if no tools needed.
+
+Example structure (2 agents for a writing task):
+{{
+  "roles": {{
+    "researcher": {{
+      "role": "Research Analyst",
+      "goal": "Gather comprehensive information on the topic",
+      "backstory": "Expert researcher skilled at finding and synthesizing information.",
+      "tools": ["WebsiteSearchTool"],
+      "tasks": {{
+        "research_task": {{
+          "description": "Research key information about the topic and compile findings.",
+          "expected_output": "Comprehensive research notes with key facts and insights."
+        }}
+      }}
+    }},
+    "writer": {{
+      "role": "Content Writer",
+      "goal": "Create polished final content",
+      "backstory": "Skilled writer who transforms research into engaging content.",
+      "tools": [],
+      "tasks": {{
+        "writing_task": {{
+          "description": "Write the final content based on research findings.",
+          "expected_output": "Polished, well-structured final document."
+        }}
+      }}
+    }}
+  }}
+}}
+
+Now generate the optimal team structure for: {self.topic}
+"""
        return user_content

    
@@ -372,13 +585,14 @@ class WorkflowStructure(BaseModel):
    description: str
    agents: Dict[str, WorkflowAgentDetails]
    steps: List[Dict]  # Can be agent steps, route, parallel, etc.
+    gates: Optional[List[ValidationGate]] = None  # Optional validation gates


-class WorkflowAutoGenerator:
+class WorkflowAutoGenerator(BaseAutoGenerator):
    """
    Auto-generates workflow.yaml files from a topic description.
    
-    Uses lazy loading to avoid performance impact when not used.
+    Inherits from BaseAutoGenerator for shared LLM client functionality.
    
    Usage:
        generator = WorkflowAutoGenerator(topic="Research AI trends and write a report")
@@ -387,7 +601,9 @@ class WorkflowAutoGenerator:
    
    def __init__(self, topic: str = "Research and write about AI", 
                 workflow_file: str = "workflow.yaml",
-                 config_list: Optional[List[Dict]] = None):
+                 config_list: Optional[List[Dict]] = None,
+                 framework: str = "praisonai",
+                 single_agent: bool = False):
        """
        Initialize the WorkflowAutoGenerator.
        
@@ -395,45 +611,105 @@ class WorkflowAutoGenerator:
            topic: The task/topic for the workflow
            workflow_file: Output file name
            config_list: Optional LLM configuration
+            framework: Framework to use (praisonai, crewai, autogen)
+            single_agent: If True, generate a single agent workflow
        """
-        # Support multiple environment variable patterns
-        model_name = os.environ.get("MODEL_NAME") or os.environ.get("OPENAI_MODEL_NAME", "gpt-4o-mini")
-        base_url = (
-            os.environ.get("OPENAI_BASE_URL") or 
-            os.environ.get("OPENAI_API_BASE") or
-            os.environ.get("OLLAMA_API_BASE", "https://api.openai.com/v1")
-        )
+        # Initialize base class (handles config_list and client)
+        super().__init__(config_list=config_list)
        
-        self.config_list = config_list or [
-            {
-                'model': model_name,
-                'base_url': base_url,
-                'api_key': os.environ.get("OPENAI_API_KEY")
-            }
-        ]
        self.topic = topic
        self.workflow_file = workflow_file
-        self._client = None  # Lazy loading
+        self.framework = framework
+        self.single_agent = single_agent
    
-    @property
-    def client(self):
-        """Lazy load the OpenAI client to avoid performance impact."""
-        if self._client is None:
-            self._client = instructor.patch(
-                OpenAI(
-                    base_url=self.config_list[0]['base_url'],
-                    api_key=self.config_list[0]['api_key'],
-                ),
-                mode=instructor.Mode.JSON,
-            )
-        return self._client
+    def recommend_pattern(self, topic: str = None) -> str:
+        """
+        Recommend the best workflow pattern based on task characteristics.
+        
+        Args:
+            topic: The task description (uses self.topic if not provided)
+            
+        Returns:
+            str: Recommended pattern name
+            
+        Pattern recommendations based on Anthropic's best practices:
+        - sequential: Clear step-by-step dependencies
+        - parallel: Independent subtasks that can run concurrently
+        - routing: Different input types need different handling
+        - orchestrator-workers: Complex tasks needing dynamic decomposition
+        - evaluator-optimizer: Tasks requiring iterative refinement
+        """
+        task = topic or self.topic
+        task_lower = task.lower()
+        
+        # Keywords that suggest specific patterns
+        parallel_keywords = ['multiple', 'concurrent', 'parallel', 'simultaneously', 'different sources', 'compare', 'various']
+        routing_keywords = ['classify', 'categorize', 'route', 'different types', 'depending on', 'if...then']
+        orchestrator_keywords = ['complex', 'comprehensive', 'multi-step', 'coordinate', 'delegate', 'break down', 'analyze and']
+        evaluator_keywords = ['refine', 'improve', 'iterate', 'quality', 'review', 'feedback', 'polish', 'optimize']
+        
+        # Check for pattern indicators
+        if any(kw in task_lower for kw in evaluator_keywords):
+            return "evaluator-optimizer"
+        elif any(kw in task_lower for kw in orchestrator_keywords):
+            return "orchestrator-workers"
+        elif any(kw in task_lower for kw in routing_keywords):
+            return "routing"
+        elif any(kw in task_lower for kw in parallel_keywords):
+            return "parallel"
+        else:
+            return "sequential"
    
-    def generate(self, pattern: str = "sequential") -> str:
+    def recommend_pattern_llm(self, topic: str = None) -> PatternRecommendation:
+        """
+        Use LLM to recommend the best workflow pattern with reasoning.
+        
+        Args:
+            topic: The task description (uses self.topic if not provided)
+            
+        Returns:
+            PatternRecommendation: Pattern with reasoning and confidence score
+        """
+        task = topic or self.topic
+        
+        prompt = f"""Analyze this task and recommend the best workflow pattern:
+
+Task: "{task}"
+
+Available patterns:
+1. sequential - Agents work one after another, passing output to the next
+2. parallel - Multiple agents work concurrently on independent subtasks
+3. routing - A classifier routes requests to specialized agents based on input type
+4. orchestrator-workers - Central orchestrator dynamically delegates to specialized workers
+5. evaluator-optimizer - Generator creates content, evaluator reviews in a loop until quality met
+
+Respond with:
+- pattern: The recommended pattern name
+- reasoning: Why this pattern is best for this task
+- confidence: Your confidence score (0.0 to 1.0)
+"""
+        
+        response = self.client.chat.completions.create(
+            model=self.config_list[0]['model'],
+            response_model=PatternRecommendation,
+            max_retries=3,
+            timeout=60.0,
+            messages=[
+                {"role": "system", "content": "You are an expert at designing AI agent workflows."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+        
+        return response
+    
+    def generate(self, pattern: str = "sequential", merge: bool = False) -> str:
        """
        Generate a workflow YAML file.
        
        Args:
-            pattern: Workflow pattern - "sequential", "routing", "parallel", "loop"
+            pattern: Workflow pattern - "sequential", "routing", "parallel", "loop",
+                     "orchestrator-workers", "evaluator-optimizer"
+            merge: If True, merge with existing workflow file instead of overwriting
            
        Returns:
            Path to the generated workflow file
@@ -442,6 +718,7 @@ class WorkflowAutoGenerator:
            model=self.config_list[0]['model'],
            response_model=WorkflowStructure,
            max_retries=5,
+            timeout=120.0,  # 2 minute timeout for complex generations
            messages=[
                {"role": "system", "content": "You are a helpful assistant that designs workflow structures."},
                {"role": "user", "content": self._get_prompt(pattern)}
@@ -449,16 +726,86 @@ class WorkflowAutoGenerator:
        )
        
        json_data = json.loads(response.model_dump_json())
+        
+        if merge and os.path.exists(self.workflow_file):
+            return self._save_workflow(self.merge_with_existing_workflow(json_data), pattern)
        return self._save_workflow(json_data, pattern)
    
+    def merge_with_existing_workflow(self, new_data: Dict) -> Dict:
+        """
+        Merge new workflow data with existing workflow file.
+        
+        Args:
+            new_data: The new workflow data to merge
+            
+        Returns:
+            Dict: Merged workflow data
+        """
+        try:
+            with open(self.workflow_file, 'r') as f:
+                existing_data = yaml.safe_load(f)
+            
+            if not existing_data:
+                return new_data
+        except (yaml.YAMLError, FileNotFoundError) as e:
+            logging.warning(f"Could not load existing workflow file {self.workflow_file}: {e}")
+            return new_data
+        
+        # Merge agents (avoid duplicates)
+        merged_agents = existing_data.get('agents', {}).copy()
+        for agent_id, agent_data in new_data.get('agents', {}).items():
+            # Rename if conflict
+            final_id = agent_id
+            counter = 1
+            while final_id in merged_agents:
+                final_id = f"{agent_id}_auto_{counter}"
+                counter += 1
+            merged_agents[final_id] = agent_data
+        
+        # Merge steps (append new steps)
+        merged_steps = existing_data.get('steps', []) + new_data.get('steps', [])
+        
+        # Create merged structure
+        merged = {
+            'name': existing_data.get('name', new_data.get('name', 'Merged Workflow')),
+            'description': f"{existing_data.get('description', '')} + {new_data.get('description', '')}",
+            'agents': merged_agents,
+            'steps': merged_steps
+        }
+        
+        return merged
+    
    def _get_prompt(self, pattern: str) -> str:
        """Generate the prompt based on the workflow pattern."""
+        # Analyze complexity to determine agent count
+        complexity = self.analyze_complexity(self.topic)
+        if complexity == 'simple':
+            agent_guidance = "Create 1-2 agents (simple task detected)."
+        elif complexity == 'complex':
+            agent_guidance = "Create 3-4 agents (complex task detected)."
+        else:
+            agent_guidance = "Create 2-3 agents (moderate task detected)."
+        
+        # Get available tools
+        tools_list = ", ".join(self.get_available_tools())
+        
        base_prompt = f"""Generate a workflow structure for: "{self.topic}"

+STEP 1: ANALYZE TASK COMPLEXITY
+- Is this a simple task (1-2 agents)?
+- Does it require multiple specialists (2-3 agents)?
+- Is it complex with many dependencies (3-4 agents)?
+
+STEP 2: DESIGN WORKFLOW
 The workflow should use the "{pattern}" pattern.
-Create 2-4 agents with clear roles and instructions.
+{agent_guidance}
+Each agent should have clear roles and instructions.
 Each step should have a clear action.

+STEP 3: ASSIGN TOOLS (if needed)
+Available Tools: {tools_list}
+Only assign tools if the task requires them. Use empty list or null if no tools needed.
+
 """
        
        if pattern == "routing":
@@ -501,6 +848,59 @@ Example structure:
    {"agent": "aggregator", "action": "Combine all findings"}
  ]
 }
+"""
+        elif pattern == "orchestrator-workers":
+            base_prompt += """
+Create an orchestrator-workers workflow where a central orchestrator dynamically delegates tasks to specialized workers.
+The orchestrator analyzes the input, decides which workers are needed, and synthesizes results.
+
+Example structure:
+{
+  "name": "Orchestrator-Workers Workflow",
+  "description": "Central orchestrator delegates to specialized workers",
+  "agents": {
+    "orchestrator": {"name": "Orchestrator", "role": "Task Coordinator", "goal": "Analyze tasks and delegate to appropriate workers", "instructions": "Break down the task, identify required specialists, and coordinate their work. Output a JSON with 'subtasks' array listing which workers to invoke."},
+    "researcher": {"name": "Researcher", "role": "Research Specialist", "goal": "Gather information", "instructions": "Research and provide factual information"},
+    "analyst": {"name": "Analyst", "role": "Data Analyst", "goal": "Analyze data and patterns", "instructions": "Analyze information and identify insights"},
+    "writer": {"name": "Writer", "role": "Content Writer", "goal": "Create written content", "instructions": "Write clear, engaging content"},
+    "synthesizer": {"name": "Synthesizer", "role": "Results Synthesizer", "goal": "Combine all worker outputs", "instructions": "Synthesize all worker outputs into a coherent final result"}
+  },
+  "steps": [
+    {"agent": "orchestrator", "action": "Analyze task and determine required workers: {{input}}"},
+    {"name": "worker_dispatch", "parallel": [
+      {"agent": "researcher", "action": "Research: {{input}}"},
+      {"agent": "analyst", "action": "Analyze: {{input}}"},
+      {"agent": "writer", "action": "Draft content for: {{input}}"}
+    ]},
+    {"agent": "synthesizer", "action": "Combine all worker outputs into final result"}
+  ]
+}
+"""
+        elif pattern == "evaluator-optimizer":
+            base_prompt += """
+Create an evaluator-optimizer workflow where one agent generates content and another evaluates it in a loop.
+The generator improves based on evaluator feedback until quality criteria are met.
+
+Example structure:
+{
+  "name": "Evaluator-Optimizer Workflow",
+  "description": "Iterative refinement through generation and evaluation",
+  "agents": {
+    "generator": {"name": "Generator", "role": "Content Generator", "goal": "Generate high-quality content", "instructions": "Create content based on the input. If feedback is provided, improve the content accordingly."},
+    "evaluator": {"name": "Evaluator", "role": "Quality Evaluator", "goal": "Evaluate content quality", "instructions": "Evaluate the content on: clarity, accuracy, completeness, and relevance. Score 1-10 for each. If average score < 7, provide specific improvement feedback. If score >= 7, respond with 'APPROVED'."}
+  },
+  "steps": [
+    {"agent": "generator", "action": "Generate initial content for: {{input}}"},
+    {"name": "evaluation_loop", "loop": {
+      "agent": "evaluator",
+      "action": "Evaluate the generated content",
+      "condition": "output does not contain 'APPROVED'",
+      "max_iterations": 3,
+      "feedback_to": "generator"
+    }},
+    {"agent": "generator", "action": "Finalize content based on all feedback"}
+  ]
+}
 """
        else:  # sequential
            base_prompt += """
@@ -21,6 +21,10 @@ Features:
 - flow_display: Visual workflow tracking
 - workflow: YAML workflow management
 - n8n: Export workflows to n8n visual editor
+- external_agents: External AI CLI tool integrations (Claude, Gemini, Codex, Cursor)
+- slash_commands: Interactive slash commands (/help, /cost, /plan, etc.)
+- autonomy_mode: Autonomy levels (suggest, auto-edit, full-auto)
+- cost_tracker: Real-time cost and token tracking
 """

 # Type hints available for IDE support
@@ -43,6 +47,15 @@ __all__ = [
    'FlowDisplayHandler',
    'WorkflowHandler',
    'N8nHandler',
+    'ExternalAgentsHandler',
+    # New CLI enhancement features
+    'SlashCommandHandler',
+    'AutonomyModeHandler',
+    'CostTrackerHandler',
+    'RepoMapHandler',
+    'InteractiveTUIHandler',
+    'GitIntegrationHandler',
+    'SandboxExecutorHandler',
 ]

 def __getattr__(name):
@@ -95,4 +108,29 @@ def __getattr__(name):
    elif name == 'N8nHandler':
        from .n8n import N8nHandler
        return N8nHandler
+    elif name == 'ExternalAgentsHandler':
+        from .external_agents import ExternalAgentsHandler
+        return ExternalAgentsHandler
+    # New CLI enhancement features
+    elif name == 'SlashCommandHandler':
+        from .slash_commands import SlashCommandHandler
+        return SlashCommandHandler
+    elif name == 'AutonomyModeHandler':
+        from .autonomy_mode import AutonomyModeHandler
+        return AutonomyModeHandler
+    elif name == 'CostTrackerHandler':
+        from .cost_tracker import CostTrackerHandler
+        return CostTrackerHandler
+    elif name == 'RepoMapHandler':
+        from .repo_map import RepoMapHandler
+        return RepoMapHandler
+    elif name == 'InteractiveTUIHandler':
+        from .interactive_tui import InteractiveTUIHandler
+        return InteractiveTUIHandler
+    elif name == 'GitIntegrationHandler':
+        from .git_integration import GitIntegrationHandler
+        return GitIntegrationHandler
+    elif name == 'SandboxExecutorHandler':
+        from .sandbox_executor import SandboxExecutorHandler
+        return SandboxExecutorHandler
    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -0,0 +1,490 @@
+"""
+Autonomy Modes for PraisonAI CLI.
+
+Inspired by Codex CLI's approval modes and Gemini CLI's approval settings.
+Provides configurable autonomy levels: suggest, auto-edit, full-auto.
+
+Architecture:
+- AutonomyMode: Enum for different autonomy levels
+- AutonomyPolicy: Policy configuration for each mode
+- AutonomyManager: Manages mode transitions and approvals
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Callable, Dict, Optional, Set
+from enum import Enum
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class AutonomyMode(Enum):
+    """
+    Autonomy levels for agent execution.
+    
+    Inspired by Codex CLI's approval modes:
+    - SUGGEST: Read-only, requires approval for all changes
+    - AUTO_EDIT: Auto-approve file edits, require approval for commands
+    - FULL_AUTO: Auto-approve everything (YOLO mode)
+    """
+    SUGGEST = "suggest"          # Default: ask for approval on everything
+    AUTO_EDIT = "auto_edit"      # Auto-approve file edits only
+    FULL_AUTO = "full_auto"      # Auto-approve everything (dangerous)
+    
+    @classmethod
+    def from_string(cls, value: str) -> "AutonomyMode":
+        """Parse mode from string."""
+        value = value.lower().strip().replace("-", "_")
+        for mode in cls:
+            if mode.value == value:
+                return mode
+        raise ValueError(f"Unknown autonomy mode: {value}")
+
+
+class ActionType(Enum):
+    """Types of actions that require approval."""
+    FILE_READ = "file_read"
+    FILE_WRITE = "file_write"
+    FILE_DELETE = "file_delete"
+    SHELL_COMMAND = "shell_command"
+    NETWORK_REQUEST = "network_request"
+    CODE_EXECUTION = "code_execution"
+    GIT_OPERATION = "git_operation"
+    TOOL_CALL = "tool_call"
+
+
+@dataclass
+class ActionRequest:
+    """
+    Request for an action that may require approval.
+    
+    Attributes:
+        action_type: Type of action
+        description: Human-readable description
+        details: Additional details (file path, command, etc.)
+        risk_level: Estimated risk (low, medium, high)
+        reversible: Whether the action can be undone
+    """
+    action_type: ActionType
+    description: str
+    details: Dict[str, Any] = field(default_factory=dict)
+    risk_level: str = "medium"
+    reversible: bool = True
+    
+    def __str__(self) -> str:
+        return f"{self.action_type.value}: {self.description}"
+
+
+@dataclass
+class ApprovalResult:
+    """Result of an approval request."""
+    approved: bool
+    reason: Optional[str] = None
+    modified_action: Optional[ActionRequest] = None
+    remember_choice: bool = False
+
+
+@dataclass
+class AutonomyPolicy:
+    """
+    Policy configuration for autonomy mode.
+    
+    Defines which actions are auto-approved, require approval,
+    or are blocked entirely.
+    """
+    mode: AutonomyMode
+    
+    # Actions that are auto-approved
+    auto_approve: Set[ActionType] = field(default_factory=set)
+    
+    # Actions that always require approval
+    require_approval: Set[ActionType] = field(default_factory=set)
+    
+    # Actions that are blocked entirely
+    blocked: Set[ActionType] = field(default_factory=set)
+    
+    # Trusted paths for file operations
+    trusted_paths: Set[str] = field(default_factory=set)
+    
+    # Trusted commands (patterns)
+    trusted_commands: Set[str] = field(default_factory=set)
+    
+    # Maximum auto-approved actions before requiring confirmation
+    max_auto_actions: int = 10
+    
+    # Whether to show what would be done in suggest mode
+    show_preview: bool = True
+    
+    @classmethod
+    def for_mode(cls, mode: AutonomyMode) -> "AutonomyPolicy":
+        """Create default policy for a given mode."""
+        if mode == AutonomyMode.SUGGEST:
+            return cls(
+                mode=mode,
+                auto_approve={ActionType.FILE_READ},
+                require_approval={
+                    ActionType.FILE_WRITE,
+                    ActionType.FILE_DELETE,
+                    ActionType.SHELL_COMMAND,
+                    ActionType.CODE_EXECUTION,
+                    ActionType.GIT_OPERATION,
+                    ActionType.NETWORK_REQUEST,
+                    ActionType.TOOL_CALL,
+                },
+                blocked=set(),
+                show_preview=True
+            )
+        elif mode == AutonomyMode.AUTO_EDIT:
+            return cls(
+                mode=mode,
+                auto_approve={
+                    ActionType.FILE_READ,
+                    ActionType.FILE_WRITE,
+                    ActionType.TOOL_CALL,
+                },
+                require_approval={
+                    ActionType.FILE_DELETE,
+                    ActionType.SHELL_COMMAND,
+                    ActionType.CODE_EXECUTION,
+                    ActionType.GIT_OPERATION,
+                    ActionType.NETWORK_REQUEST,
+                },
+                blocked=set(),
+                show_preview=True
+            )
+        elif mode == AutonomyMode.FULL_AUTO:
+            return cls(
+                mode=mode,
+                auto_approve={
+                    ActionType.FILE_READ,
+                    ActionType.FILE_WRITE,
+                    ActionType.FILE_DELETE,
+                    ActionType.SHELL_COMMAND,
+                    ActionType.CODE_EXECUTION,
+                    ActionType.GIT_OPERATION,
+                    ActionType.NETWORK_REQUEST,
+                    ActionType.TOOL_CALL,
+                },
+                require_approval=set(),
+                blocked=set(),
+                show_preview=False,
+                max_auto_actions=100
+            )
+        else:
+            raise ValueError(f"Unknown mode: {mode}")
+
+
+class AutonomyManager:
+    """
+    Manages autonomy mode and approval flow.
+    
+    Handles:
+    - Mode transitions
+    - Approval requests
+    - Action tracking
+    - Policy enforcement
+    """
+    
+    def __init__(
+        self,
+        mode: AutonomyMode = AutonomyMode.SUGGEST,
+        policy: Optional[AutonomyPolicy] = None,
+        approval_callback: Optional[Callable[[ActionRequest], ApprovalResult]] = None,
+        verbose: bool = False
+    ):
+        self.mode = mode
+        self.policy = policy or AutonomyPolicy.for_mode(mode)
+        self.approval_callback = approval_callback or self._default_approval
+        self.verbose = verbose
+        
+        # Tracking
+        self._action_count = 0
+        self._auto_approved_count = 0
+        self._denied_count = 0
+        self._remembered_approvals: Dict[str, bool] = {}
+    
+    def set_mode(self, mode: AutonomyMode) -> None:
+        """Change the autonomy mode."""
+        old_mode = self.mode
+        self.mode = mode
+        self.policy = AutonomyPolicy.for_mode(mode)
+        
+        if self.verbose:
+            logger.info(f"Autonomy mode changed: {old_mode.value} -> {mode.value}")
+    
+    def request_approval(self, action: ActionRequest) -> ApprovalResult:
+        """
+        Request approval for an action.
+        
+        Returns:
+            ApprovalResult with approval decision
+        """
+        self._action_count += 1
+        
+        # Check if blocked
+        if action.action_type in self.policy.blocked:
+            self._denied_count += 1
+            return ApprovalResult(
+                approved=False,
+                reason=f"Action type '{action.action_type.value}' is blocked by policy"
+            )
+        
+        # Check remembered approvals
+        action_key = self._get_action_key(action)
+        if action_key in self._remembered_approvals:
+            approved = self._remembered_approvals[action_key]
+            if approved:
+                self._auto_approved_count += 1
+            else:
+                self._denied_count += 1
+            return ApprovalResult(approved=approved, reason="Remembered choice")
+        
+        # Check if auto-approved
+        if action.action_type in self.policy.auto_approve:
+            # Check max auto actions
+            if self._auto_approved_count >= self.policy.max_auto_actions:
+                # Force approval after max auto actions
+                return self._request_user_approval(action)
+            
+            self._auto_approved_count += 1
+            return ApprovalResult(approved=True, reason="Auto-approved by policy")
+        
+        # Check if requires approval
+        if action.action_type in self.policy.require_approval:
+            return self._request_user_approval(action)
+        
+        # Default: require approval for unknown action types
+        return self._request_user_approval(action)
+    
+    def _request_user_approval(self, action: ActionRequest) -> ApprovalResult:
+        """Request approval from user via callback."""
+        result = self.approval_callback(action)
+        
+        if result.remember_choice:
+            action_key = self._get_action_key(action)
+            self._remembered_approvals[action_key] = result.approved
+        
+        if result.approved:
+            self._auto_approved_count += 1
+        else:
+            self._denied_count += 1
+        
+        return result
+    
+    def _get_action_key(self, action: ActionRequest) -> str:
+        """Generate a key for remembering approval decisions."""
+        # Use action type and relevant details
+        key_parts = [action.action_type.value]
+        
+        if "path" in action.details:
+            key_parts.append(action.details["path"])
+        if "command" in action.details:
+            key_parts.append(action.details["command"])
+        
+        return ":".join(key_parts)
+    
+    def _default_approval(self, action: ActionRequest) -> ApprovalResult:
+        """Default approval callback using console input."""
+        from rich.console import Console
+        from rich.panel import Panel
+        from rich.prompt import Confirm
+        
+        console = Console()
+        
+        # Build action description
+        risk_color = {
+            "low": "green",
+            "medium": "yellow",
+            "high": "red"
+        }.get(action.risk_level, "white")
+        
+        details_str = "\n".join(
+            f"  {k}: {v}" for k, v in action.details.items()
+        ) if action.details else "  (no details)"
+        
+        panel_content = f"""
+[bold]{action.description}[/bold]
+
+Type: {action.action_type.value}
+Risk: [{risk_color}]{action.risk_level}[/{risk_color}]
+Reversible: {"Yes" if action.reversible else "No"}
+
+Details:
+{details_str}
+"""
+        
+        console.print(Panel(
+            panel_content,
+            title="🔒 Approval Required",
+            border_style="yellow"
+        ))
+        
+        approved = Confirm.ask("Approve this action?", default=False)
+        remember = False
+        
+        if approved:
+            remember = Confirm.ask("Remember this choice for similar actions?", default=False)
+        
+        return ApprovalResult(
+            approved=approved,
+            remember_choice=remember
+        )
+    
+    def get_stats(self) -> Dict[str, int]:
+        """Get approval statistics."""
+        return {
+            "total_actions": self._action_count,
+            "auto_approved": self._auto_approved_count,
+            "denied": self._denied_count,
+            "remembered": len(self._remembered_approvals)
+        }
+    
+    def reset_stats(self) -> None:
+        """Reset approval statistics."""
+        self._action_count = 0
+        self._auto_approved_count = 0
+        self._denied_count = 0
+    
+    def clear_remembered(self) -> None:
+        """Clear remembered approval decisions."""
+        self._remembered_approvals.clear()
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class AutonomyModeHandler:
+    """
+    Handler for integrating autonomy modes with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._manager: Optional[AutonomyManager] = None
+    
+    @property
+    def feature_name(self) -> str:
+        return "autonomy_mode"
+    
+    def initialize(
+        self,
+        mode: str = "suggest",
+        approval_callback: Optional[Callable[[ActionRequest], ApprovalResult]] = None
+    ) -> AutonomyManager:
+        """
+        Initialize the autonomy manager.
+        
+        Args:
+            mode: Autonomy mode string (suggest, auto_edit, full_auto)
+            approval_callback: Optional custom approval callback
+            
+        Returns:
+            Configured AutonomyManager
+        """
+        try:
+            autonomy_mode = AutonomyMode.from_string(mode)
+        except ValueError:
+            logger.warning(f"Unknown mode '{mode}', defaulting to 'suggest'")
+            autonomy_mode = AutonomyMode.SUGGEST
+        
+        self._manager = AutonomyManager(
+            mode=autonomy_mode,
+            approval_callback=approval_callback,
+            verbose=self.verbose
+        )
+        
+        if self.verbose:
+            from rich import print as rprint
+            rprint(f"[cyan]Autonomy mode: {autonomy_mode.value}[/cyan]")
+        
+        return self._manager
+    
+    def get_manager(self) -> Optional[AutonomyManager]:
+        """Get the current autonomy manager."""
+        return self._manager
+    
+    def request_approval(self, action: ActionRequest) -> ApprovalResult:
+        """Request approval for an action."""
+        if not self._manager:
+            self._manager = self.initialize()
+        
+        return self._manager.request_approval(action)
+    
+    def set_mode(self, mode: str) -> None:
+        """Change the autonomy mode."""
+        if not self._manager:
+            self.initialize(mode)
+        else:
+            try:
+                autonomy_mode = AutonomyMode.from_string(mode)
+                self._manager.set_mode(autonomy_mode)
+            except ValueError as e:
+                logger.error(f"Failed to set mode: {e}")
+    
+    def get_mode(self) -> str:
+        """Get the current autonomy mode."""
+        if self._manager:
+            return self._manager.mode.value
+        return AutonomyMode.SUGGEST.value
+
+
+# ============================================================================
+# Convenience Functions
+# ============================================================================
+
+def create_file_write_action(path: str, content_preview: str = "") -> ActionRequest:
+    """Create an action request for file write."""
+    return ActionRequest(
+        action_type=ActionType.FILE_WRITE,
+        description=f"Write to file: {path}",
+        details={
+            "path": path,
+            "preview": content_preview[:200] if content_preview else "(no preview)"
+        },
+        risk_level="medium",
+        reversible=True
+    )
+
+
+def create_shell_command_action(command: str, cwd: str = ".") -> ActionRequest:
+    """Create an action request for shell command."""
+    # Assess risk based on command
+    dangerous_patterns = ["rm ", "sudo ", "chmod ", "chown ", "> /", "| sh", "curl |"]
+    risk = "high" if any(p in command for p in dangerous_patterns) else "medium"
+    
+    return ActionRequest(
+        action_type=ActionType.SHELL_COMMAND,
+        description=f"Execute command: {command}",
+        details={
+            "command": command,
+            "cwd": cwd
+        },
+        risk_level=risk,
+        reversible=False
+    )
+
+
+def create_git_action(operation: str, details: Dict[str, Any] = None) -> ActionRequest:
+    """Create an action request for git operation."""
+    return ActionRequest(
+        action_type=ActionType.GIT_OPERATION,
+        description=f"Git {operation}",
+        details=details or {},
+        risk_level="low" if operation in ["status", "log", "diff"] else "medium",
+        reversible=operation not in ["push", "force-push"]
+    )
+
+
+def create_tool_call_action(tool_name: str, args: Dict[str, Any] = None) -> ActionRequest:
+    """Create an action request for tool call."""
+    return ActionRequest(
+        action_type=ActionType.TOOL_CALL,
+        description=f"Call tool: {tool_name}",
+        details={
+            "tool": tool_name,
+            "args": args or {}
+        },
+        risk_level="low",
+        reversible=True
+    )
@@ -0,0 +1,514 @@
+"""
+Cost Tracking System for PraisonAI CLI.
+
+Inspired by Aider's cost tracking and Gemini CLI's stats command.
+Provides real-time cost and token usage tracking.
+
+Architecture:
+- CostTracker: Tracks tokens and costs per session
+- ModelPricing: Pricing data for different models
+- UsageStats: Aggregated usage statistics
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+from datetime import datetime
+import logging
+import json
+
+logger = logging.getLogger(__name__)
+
+
+# ============================================================================
+# Model Pricing Data
+# ============================================================================
+
+@dataclass
+class ModelPricing:
+    """
+    Pricing information for a model.
+    
+    Prices are per 1M tokens (as commonly quoted).
+    """
+    model_name: str
+    input_price_per_1m: float  # Price per 1M input tokens
+    output_price_per_1m: float  # Price per 1M output tokens
+    context_window: int = 128000
+    
+    def calculate_cost(self, input_tokens: int, output_tokens: int) -> float:
+        """Calculate cost for given token counts."""
+        input_cost = (input_tokens / 1_000_000) * self.input_price_per_1m
+        output_cost = (output_tokens / 1_000_000) * self.output_price_per_1m
+        return input_cost + output_cost
+
+
+# Default pricing for common models (as of late 2024)
+DEFAULT_PRICING: Dict[str, ModelPricing] = {
+    # OpenAI models
+    "gpt-4o": ModelPricing("gpt-4o", 2.50, 10.00, 128000),
+    "gpt-4o-mini": ModelPricing("gpt-4o-mini", 0.15, 0.60, 128000),
+    "gpt-4-turbo": ModelPricing("gpt-4-turbo", 10.00, 30.00, 128000),
+    "gpt-4": ModelPricing("gpt-4", 30.00, 60.00, 8192),
+    "gpt-3.5-turbo": ModelPricing("gpt-3.5-turbo", 0.50, 1.50, 16385),
+    "o1": ModelPricing("o1", 15.00, 60.00, 200000),
+    "o1-mini": ModelPricing("o1-mini", 3.00, 12.00, 128000),
+    "o1-preview": ModelPricing("o1-preview", 15.00, 60.00, 128000),
+    "o3-mini": ModelPricing("o3-mini", 1.10, 4.40, 200000),
+    
+    # Anthropic models
+    "claude-3-5-sonnet-20241022": ModelPricing("claude-3-5-sonnet", 3.00, 15.00, 200000),
+    "claude-3-5-sonnet": ModelPricing("claude-3-5-sonnet", 3.00, 15.00, 200000),
+    "claude-3-opus": ModelPricing("claude-3-opus", 15.00, 75.00, 200000),
+    "claude-3-sonnet": ModelPricing("claude-3-sonnet", 3.00, 15.00, 200000),
+    "claude-3-haiku": ModelPricing("claude-3-haiku", 0.25, 1.25, 200000),
+    
+    # Google models
+    "gemini-2.0-flash": ModelPricing("gemini-2.0-flash", 0.10, 0.40, 1000000),
+    "gemini-1.5-pro": ModelPricing("gemini-1.5-pro", 1.25, 5.00, 2000000),
+    "gemini-1.5-flash": ModelPricing("gemini-1.5-flash", 0.075, 0.30, 1000000),
+    
+    # Default fallback
+    "default": ModelPricing("default", 1.00, 3.00, 128000),
+}
+
+
+def get_pricing(model_name: str) -> ModelPricing:
+    """Get pricing for a model, with fallback to default."""
+    # Try exact match
+    if model_name in DEFAULT_PRICING:
+        return DEFAULT_PRICING[model_name]
+    
+    # Try partial match
+    model_lower = model_name.lower()
+    for key, pricing in DEFAULT_PRICING.items():
+        if key in model_lower or model_lower in key:
+            return pricing
+    
+    # Return default
+    logger.debug(f"No pricing found for model '{model_name}', using default")
+    return DEFAULT_PRICING["default"]
+
+
+# ============================================================================
+# Usage Statistics
+# ============================================================================
+
+@dataclass
+class TokenUsage:
+    """Token usage for a single request."""
+    input_tokens: int = 0
+    output_tokens: int = 0
+    total_tokens: int = 0
+    cached_tokens: int = 0
+    
+    def __post_init__(self):
+        if self.total_tokens == 0:
+            self.total_tokens = self.input_tokens + self.output_tokens
+
+
+@dataclass
+class RequestStats:
+    """Statistics for a single request."""
+    timestamp: datetime
+    model: str
+    usage: TokenUsage
+    cost: float
+    duration_ms: float = 0.0
+    prompt_preview: str = ""
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary for serialization."""
+        return {
+            "timestamp": self.timestamp.isoformat(),
+            "model": self.model,
+            "input_tokens": self.usage.input_tokens,
+            "output_tokens": self.usage.output_tokens,
+            "total_tokens": self.usage.total_tokens,
+            "cached_tokens": self.usage.cached_tokens,
+            "cost": self.cost,
+            "duration_ms": self.duration_ms,
+        }
+
+
+@dataclass
+class SessionStats:
+    """Aggregated statistics for a session."""
+    session_id: str
+    start_time: datetime
+    end_time: Optional[datetime] = None
+    
+    total_requests: int = 0
+    total_input_tokens: int = 0
+    total_output_tokens: int = 0
+    total_tokens: int = 0
+    total_cached_tokens: int = 0
+    total_cost: float = 0.0
+    total_duration_ms: float = 0.0
+    
+    models_used: Dict[str, int] = field(default_factory=dict)
+    
+    def add_request(self, stats: RequestStats) -> None:
+        """Add request statistics to session totals."""
+        self.total_requests += 1
+        self.total_input_tokens += stats.usage.input_tokens
+        self.total_output_tokens += stats.usage.output_tokens
+        self.total_tokens += stats.usage.total_tokens
+        self.total_cached_tokens += stats.usage.cached_tokens
+        self.total_cost += stats.cost
+        self.total_duration_ms += stats.duration_ms
+        
+        # Track model usage
+        if stats.model not in self.models_used:
+            self.models_used[stats.model] = 0
+        self.models_used[stats.model] += 1
+    
+    @property
+    def duration_seconds(self) -> float:
+        """Get session duration in seconds."""
+        end = self.end_time or datetime.now()
+        return (end - self.start_time).total_seconds()
+    
+    @property
+    def avg_tokens_per_request(self) -> float:
+        """Get average tokens per request."""
+        if self.total_requests == 0:
+            return 0.0
+        return self.total_tokens / self.total_requests
+    
+    @property
+    def avg_cost_per_request(self) -> float:
+        """Get average cost per request."""
+        if self.total_requests == 0:
+            return 0.0
+        return self.total_cost / self.total_requests
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary for serialization."""
+        return {
+            "session_id": self.session_id,
+            "start_time": self.start_time.isoformat(),
+            "end_time": self.end_time.isoformat() if self.end_time else None,
+            "duration_seconds": self.duration_seconds,
+            "total_requests": self.total_requests,
+            "total_input_tokens": self.total_input_tokens,
+            "total_output_tokens": self.total_output_tokens,
+            "total_tokens": self.total_tokens,
+            "total_cached_tokens": self.total_cached_tokens,
+            "total_cost": self.total_cost,
+            "avg_tokens_per_request": self.avg_tokens_per_request,
+            "avg_cost_per_request": self.avg_cost_per_request,
+            "models_used": self.models_used,
+        }
+
+
+# ============================================================================
+# Cost Tracker
+# ============================================================================
+
+class CostTracker:
+    """
+    Tracks costs and token usage for a session.
+    
+    Features:
+    - Real-time cost tracking
+    - Per-model statistics
+    - Session history
+    - Export to JSON
+    """
+    
+    def __init__(
+        self,
+        session_id: Optional[str] = None,
+        pricing: Optional[Dict[str, ModelPricing]] = None,
+        verbose: bool = False
+    ):
+        self.session_id = session_id or self._generate_session_id()
+        self.pricing = pricing or DEFAULT_PRICING
+        self.verbose = verbose
+        
+        self.session_stats = SessionStats(
+            session_id=self.session_id,
+            start_time=datetime.now()
+        )
+        self.request_history: List[RequestStats] = []
+    
+    def _generate_session_id(self) -> str:
+        """Generate a unique session ID."""
+        import uuid
+        return str(uuid.uuid4())[:8]
+    
+    def track_request(
+        self,
+        model: str,
+        input_tokens: int,
+        output_tokens: int,
+        cached_tokens: int = 0,
+        duration_ms: float = 0.0,
+        prompt_preview: str = ""
+    ) -> RequestStats:
+        """
+        Track a single request.
+        
+        Returns:
+            RequestStats for the tracked request
+        """
+        usage = TokenUsage(
+            input_tokens=input_tokens,
+            output_tokens=output_tokens,
+            cached_tokens=cached_tokens
+        )
+        
+        # Calculate cost
+        pricing = get_pricing(model)
+        cost = pricing.calculate_cost(input_tokens, output_tokens)
+        
+        # Create request stats
+        stats = RequestStats(
+            timestamp=datetime.now(),
+            model=model,
+            usage=usage,
+            cost=cost,
+            duration_ms=duration_ms,
+            prompt_preview=prompt_preview[:100] if prompt_preview else ""
+        )
+        
+        # Update session stats
+        self.session_stats.add_request(stats)
+        self.request_history.append(stats)
+        
+        if self.verbose:
+            logger.info(
+                f"Request tracked: {model} - "
+                f"{usage.total_tokens} tokens, ${cost:.4f}"
+            )
+        
+        return stats
+    
+    def track_from_response(
+        self,
+        model: str,
+        response: Any,
+        duration_ms: float = 0.0
+    ) -> Optional[RequestStats]:
+        """
+        Track request from LLM response object.
+        
+        Handles various response formats from different providers.
+        """
+        try:
+            # Try to extract usage from response
+            usage = None
+            
+            # OpenAI format
+            if hasattr(response, 'usage'):
+                usage = response.usage
+                input_tokens = getattr(usage, 'prompt_tokens', 0)
+                output_tokens = getattr(usage, 'completion_tokens', 0)
+                cached_tokens = getattr(usage, 'cached_tokens', 0)
+            # Dict format
+            elif isinstance(response, dict) and 'usage' in response:
+                usage = response['usage']
+                input_tokens = usage.get('prompt_tokens', 0)
+                output_tokens = usage.get('completion_tokens', 0)
+                cached_tokens = usage.get('cached_tokens', 0)
+            else:
+                logger.debug("Could not extract usage from response")
+                return None
+            
+            return self.track_request(
+                model=model,
+                input_tokens=input_tokens,
+                output_tokens=output_tokens,
+                cached_tokens=cached_tokens,
+                duration_ms=duration_ms
+            )
+        except Exception as e:
+            logger.error(f"Error tracking response: {e}")
+            return None
+    
+    def get_current_stats(self) -> SessionStats:
+        """Get current session statistics."""
+        return self.session_stats
+    
+    def get_total_cost(self) -> float:
+        """Get total cost for the session."""
+        return self.session_stats.total_cost
+    
+    def get_total_tokens(self) -> int:
+        """Get total tokens for the session."""
+        return self.session_stats.total_tokens
+    
+    def get_request_count(self) -> int:
+        """Get total request count."""
+        return self.session_stats.total_requests
+    
+    def format_summary(self) -> str:
+        """Format a summary of the session statistics."""
+        stats = self.session_stats
+        
+        lines = [
+            f"Session: {stats.session_id}",
+            f"Duration: {stats.duration_seconds:.1f}s",
+            f"Requests: {stats.total_requests}",
+            "",
+            "Tokens:",
+            f"  Input:  {stats.total_input_tokens:,}",
+            f"  Output: {stats.total_output_tokens:,}",
+            f"  Total:  {stats.total_tokens:,}",
+            f"  Cached: {stats.total_cached_tokens:,}",
+            "",
+            f"Cost: ${stats.total_cost:.4f}",
+            f"Avg per request: ${stats.avg_cost_per_request:.4f}",
+        ]
+        
+        if stats.models_used:
+            lines.append("")
+            lines.append("Models used:")
+            for model, count in stats.models_used.items():
+                lines.append(f"  {model}: {count} requests")
+        
+        return "\n".join(lines)
+    
+    def print_summary(self) -> None:
+        """Print a formatted summary to console."""
+        from rich.console import Console
+        from rich.panel import Panel
+        from rich.table import Table
+        
+        console = Console()
+        stats = self.session_stats
+        
+        # Create summary table
+        table = Table(show_header=True, header_style="bold cyan")
+        table.add_column("Metric")
+        table.add_column("Value", justify="right")
+        
+        table.add_row("Session ID", stats.session_id)
+        table.add_row("Duration", f"{stats.duration_seconds:.1f}s")
+        table.add_row("Requests", str(stats.total_requests))
+        table.add_row("", "")
+        table.add_row("Input Tokens", f"{stats.total_input_tokens:,}")
+        table.add_row("Output Tokens", f"{stats.total_output_tokens:,}")
+        table.add_row("Total Tokens", f"{stats.total_tokens:,}")
+        table.add_row("Cached Tokens", f"{stats.total_cached_tokens:,}")
+        table.add_row("", "")
+        table.add_row("Total Cost", f"${stats.total_cost:.4f}")
+        table.add_row("Avg Cost/Request", f"${stats.avg_cost_per_request:.4f}")
+        
+        console.print(Panel(table, title="💰 Session Statistics", border_style="green"))
+        
+        # Print model breakdown if multiple models used
+        if len(stats.models_used) > 1:
+            model_table = Table(show_header=True, header_style="bold cyan")
+            model_table.add_column("Model")
+            model_table.add_column("Requests", justify="right")
+            
+            for model, count in stats.models_used.items():
+                model_table.add_row(model, str(count))
+            
+            console.print(Panel(model_table, title="Models Used", border_style="blue"))
+    
+    def export_json(self, filepath: Optional[str] = None) -> str:
+        """
+        Export session data to JSON.
+        
+        Args:
+            filepath: Optional file path to write to
+            
+        Returns:
+            JSON string
+        """
+        data = {
+            "session": self.session_stats.to_dict(),
+            "requests": [r.to_dict() for r in self.request_history]
+        }
+        
+        json_str = json.dumps(data, indent=2)
+        
+        if filepath:
+            with open(filepath, 'w') as f:
+                f.write(json_str)
+            logger.info(f"Exported session data to {filepath}")
+        
+        return json_str
+    
+    def end_session(self) -> SessionStats:
+        """Mark the session as ended."""
+        self.session_stats.end_time = datetime.now()
+        return self.session_stats
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class CostTrackerHandler:
+    """
+    Handler for integrating cost tracking with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._tracker: Optional[CostTracker] = None
+    
+    @property
+    def feature_name(self) -> str:
+        return "cost_tracker"
+    
+    def initialize(self, session_id: Optional[str] = None) -> CostTracker:
+        """Initialize the cost tracker."""
+        self._tracker = CostTracker(
+            session_id=session_id,
+            verbose=self.verbose
+        )
+        
+        if self.verbose:
+            from rich import print as rprint
+            rprint(f"[cyan]Cost tracking enabled for session: {self._tracker.session_id}[/cyan]")
+        
+        return self._tracker
+    
+    def get_tracker(self) -> Optional[CostTracker]:
+        """Get the current cost tracker."""
+        return self._tracker
+    
+    def track_request(
+        self,
+        model: str,
+        input_tokens: int,
+        output_tokens: int,
+        **kwargs
+    ) -> Optional[RequestStats]:
+        """Track a request."""
+        if not self._tracker:
+            self._tracker = self.initialize()
+        
+        return self._tracker.track_request(
+            model=model,
+            input_tokens=input_tokens,
+            output_tokens=output_tokens,
+            **kwargs
+        )
+    
+    def get_summary(self) -> Dict[str, Any]:
+        """Get session summary as dict."""
+        if not self._tracker:
+            return {}
+        return self._tracker.session_stats.to_dict()
+    
+    def print_summary(self) -> None:
+        """Print session summary."""
+        if self._tracker:
+            self._tracker.print_summary()
+    
+    def get_cost(self) -> float:
+        """Get total cost."""
+        if self._tracker:
+            return self._tracker.get_total_cost()
+        return 0.0
+    
+    def get_tokens(self) -> int:
+        """Get total tokens."""
+        if self._tracker:
+            return self._tracker.get_total_tokens()
+        return 0
@@ -0,0 +1,231 @@
+"""
+External Agents Handler for CLI.
+
+Provides integration with external AI coding CLI tools:
+- Claude Code CLI
+- Gemini CLI
+- OpenAI Codex CLI
+- Cursor CLI
+
+Usage:
+    praisonai "Refactor the code" --external-agent claude
+    praisonai "Analyze codebase" --external-agent gemini
+    praisonai "Fix bugs" --external-agent codex
+    praisonai "Add tests" --external-agent cursor
+"""
+
+from typing import Dict, Any, List, Optional, Tuple
+
+from .base import FlagHandler
+
+
+class ExternalAgentsHandler(FlagHandler):
+    """
+    Handler for --external-agent flag.
+    
+    Integrates external AI coding CLI tools as agent tools.
+    
+    Example:
+        praisonai "Refactor the auth module" --external-agent claude
+        praisonai "Analyze this codebase" --external-agent gemini
+    """
+    
+    # Mapping of integration names to their module paths
+    INTEGRATIONS = {
+        "claude": "claude_code.ClaudeCodeIntegration",
+        "gemini": "gemini_cli.GeminiCLIIntegration",
+        "codex": "codex_cli.CodexCLIIntegration",
+        "cursor": "cursor_cli.CursorCLIIntegration",
+    }
+    
+    def __init__(self, verbose: bool = False):
+        """Initialize the handler."""
+        super().__init__(verbose)
+        self._integration_cache: Dict[str, Any] = {}
+    
+    @property
+    def feature_name(self) -> str:
+        """Return the feature name."""
+        return "external_agents"
+    
+    @property
+    def flag_name(self) -> str:
+        """Return the flag name."""
+        return "external-agent"
+    
+    @property
+    def flag_help(self) -> str:
+        """Return the flag help text."""
+        return "External AI CLI tool to use (claude, gemini, codex, cursor)"
+    
+    def check_dependencies(self) -> Tuple[bool, str]:
+        """Check if integrations module is available."""
+        try:
+            import importlib.util
+            if importlib.util.find_spec("praisonai.integrations") is not None:
+                return True, ""
+            return False, "Integrations module not available"
+        except ImportError:
+            return False, "Integrations module not available"
+    
+    def get_integration(self, name: str, **options):
+        """
+        Get an integration instance by name.
+        
+        Args:
+            name: Integration name (claude, gemini, codex, cursor)
+            **options: Options to pass to the integration
+            
+        Returns:
+            Integration instance
+            
+        Raises:
+            ValueError: If integration name is invalid
+        """
+        if name not in self.INTEGRATIONS:
+            raise ValueError(f"Unknown integration: {name}. Available: {list(self.INTEGRATIONS.keys())}")
+        
+        # Check cache first
+        cache_key = f"{name}_{hash(frozenset(options.items()))}"
+        if cache_key in self._integration_cache:
+            return self._integration_cache[cache_key]
+        
+        # Lazy import the integration
+        module_path = self.INTEGRATIONS[name]
+        module_name, class_name = module_path.rsplit(".", 1)
+        
+        import importlib
+        module = importlib.import_module(f"praisonai.integrations.{module_name}")
+        integration_class = getattr(module, class_name)
+        
+        # Create instance with options
+        integration = integration_class(**options)
+        
+        # Cache it
+        self._integration_cache[cache_key] = integration
+        
+        return integration
+    
+    def list_integrations(self) -> List[str]:
+        """
+        List all available integration names.
+        
+        Returns:
+            List of integration names
+        """
+        return list(self.INTEGRATIONS.keys())
+    
+    def check_availability(self) -> Dict[str, bool]:
+        """
+        Check availability of all integrations.
+        
+        Returns:
+            Dict mapping integration name to availability
+        """
+        availability = {}
+        for name in self.INTEGRATIONS:
+            try:
+                integration = self.get_integration(name)
+                availability[name] = integration.is_available
+            except Exception:
+                availability[name] = False
+        return availability
+    
+    def apply_to_agent_config(self, config: Dict[str, Any], flag_value: Any) -> Dict[str, Any]:
+        """
+        Apply external agent configuration to agent config.
+        
+        Args:
+            config: Agent configuration dictionary
+            flag_value: Integration name or dict with name and options
+            
+        Returns:
+            Modified configuration with external agent tool
+        """
+        if not flag_value:
+            return config
+        
+        # Handle both string and dict formats
+        if isinstance(flag_value, str):
+            name = flag_value
+            options = {}
+        elif isinstance(flag_value, dict):
+            name = flag_value.get("name", "")
+            options = {k: v for k, v in flag_value.items() if k != "name"}
+        else:
+            return config
+        
+        try:
+            integration = self.get_integration(name, **options)
+            
+            if integration.is_available:
+                # Add tool to existing tools
+                existing_tools = config.get("tools", [])
+                if isinstance(existing_tools, list):
+                    existing_tools.append(integration.as_tool())
+                else:
+                    existing_tools = [integration.as_tool()]
+                config["tools"] = existing_tools
+                
+                self.print_status(f"🔌 External agent connected: {name}", "success")
+            else:
+                self.print_status(f"⚠️ External agent not available: {name}", "warning")
+                
+        except ValueError as e:
+            self.print_status(str(e), "error")
+        except Exception as e:
+            self.print_status(f"Failed to connect external agent: {e}", "error")
+        
+        return config
+    
+    def execute(
+        self, 
+        integration_name: str = None, 
+        **options
+    ) -> Optional[Any]:
+        """
+        Execute external agent setup.
+        
+        Args:
+            integration_name: Name of the integration
+            **options: Options for the integration
+            
+        Returns:
+            Integration instance or None
+        """
+        if not integration_name:
+            # List available integrations
+            self.print_status("\n🔧 Available External Agents:", "info")
+            self.print_status("-" * 40, "info")
+            
+            availability = self.check_availability()
+            for name, available in availability.items():
+                status = "✅ Available" if available else "❌ Not installed"
+                self.print_status(f"  {name}: {status}", "info")
+            
+            return None
+        
+        try:
+            integration = self.get_integration(integration_name, **options)
+            
+            if integration.is_available:
+                self.print_status(f"🔌 External agent ready: {integration_name}", "success")
+                return integration
+            else:
+                self.print_status(f"⚠️ External agent not installed: {integration_name}", "warning")
+                self.print_status(f"   Install with: {self._get_install_instructions(integration_name)}", "info")
+                return None
+                
+        except ValueError as e:
+            self.print_status(str(e), "error")
+            return None
+    
+    def _get_install_instructions(self, name: str) -> str:
+        """Get installation instructions for an integration."""
+        instructions = {
+            "claude": "npm install -g @anthropic-ai/claude-code",
+            "gemini": "npm install -g @anthropic-ai/gemini-cli",
+            "codex": "npm install -g @openai/codex",
+            "cursor": "Download from cursor.com",
+        }
+        return instructions.get(name, "See documentation")
@@ -0,0 +1,651 @@
+"""
+Git Integration System for PraisonAI CLI.
+
+Inspired by Aider's Git integration for auto-commits and change tracking.
+Provides seamless Git operations with AI-generated commit messages.
+
+Architecture:
+- GitManager: Core Git operations using subprocess
+- CommitGenerator: AI-powered commit message generation
+- DiffViewer: Rich diff display
+"""
+
+from dataclasses import dataclass, field
+from typing import List, Optional
+from pathlib import Path
+import subprocess
+import logging
+import re
+
+logger = logging.getLogger(__name__)
+
+
+# ============================================================================
+# Data Classes
+# ============================================================================
+
+@dataclass
+class GitStatus:
+    """Git repository status."""
+    branch: str = ""
+    is_clean: bool = True
+    staged_files: List[str] = field(default_factory=list)
+    modified_files: List[str] = field(default_factory=list)
+    untracked_files: List[str] = field(default_factory=list)
+    ahead: int = 0
+    behind: int = 0
+    
+    @property
+    def has_changes(self) -> bool:
+        """Check if there are any changes."""
+        return bool(self.staged_files or self.modified_files or self.untracked_files)
+
+
+@dataclass
+class GitCommit:
+    """Git commit information."""
+    hash: str
+    short_hash: str
+    message: str
+    author: str
+    date: str
+    files_changed: int = 0
+    insertions: int = 0
+    deletions: int = 0
+
+
+@dataclass
+class GitDiff:
+    """Git diff information."""
+    file_path: str
+    additions: int = 0
+    deletions: int = 0
+    content: str = ""
+    is_new: bool = False
+    is_deleted: bool = False
+
+
+# ============================================================================
+# Git Manager
+# ============================================================================
+
+class GitManager:
+    """
+    Manages Git operations using subprocess.
+    
+    Uses subprocess instead of GitPython for lighter dependencies.
+    """
+    
+    def __init__(self, repo_path: Optional[str] = None, verbose: bool = False):
+        self.repo_path = Path(repo_path) if repo_path else Path.cwd()
+        self.verbose = verbose
+        self._git_available = self._check_git()
+    
+    def _check_git(self) -> bool:
+        """Check if git is available."""
+        try:
+            result = subprocess.run(
+                ["git", "--version"],
+                capture_output=True,
+                text=True,
+                cwd=self.repo_path
+            )
+            return result.returncode == 0
+        except FileNotFoundError:
+            return False
+    
+    def _run_git(self, *args: str, check: bool = True) -> subprocess.CompletedProcess:
+        """Run a git command."""
+        cmd = ["git"] + list(args)
+        if self.verbose:
+            logger.debug(f"Running: {' '.join(cmd)}")
+        
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            cwd=self.repo_path
+        )
+        
+        if check and result.returncode != 0:
+            logger.debug(f"Git error: {result.stderr}")
+        
+        return result
+    
+    @property
+    def is_repo(self) -> bool:
+        """Check if current directory is a git repository."""
+        if not self._git_available:
+            return False
+        result = self._run_git("rev-parse", "--git-dir", check=False)
+        return result.returncode == 0
+    
+    def get_status(self) -> GitStatus:
+        """Get repository status."""
+        status = GitStatus()
+        
+        if not self.is_repo:
+            return status
+        
+        # Get branch
+        result = self._run_git("branch", "--show-current", check=False)
+        if result.returncode == 0:
+            status.branch = result.stdout.strip()
+        
+        # Get status
+        result = self._run_git("status", "--porcelain", check=False)
+        if result.returncode == 0:
+            for line in result.stdout.strip().split("\n"):
+                if not line:
+                    continue
+                
+                status_code = line[:2]
+                file_path = line[3:]
+                
+                if status_code[0] in "MADRCU":
+                    status.staged_files.append(file_path)
+                if status_code[1] in "MD":
+                    status.modified_files.append(file_path)
+                if status_code == "??":
+                    status.untracked_files.append(file_path)
+        
+        status.is_clean = not status.has_changes
+        
+        # Get ahead/behind
+        result = self._run_git("rev-list", "--left-right", "--count", "HEAD...@{u}", check=False)
+        if result.returncode == 0:
+            parts = result.stdout.strip().split()
+            if len(parts) == 2:
+                status.ahead = int(parts[0])
+                status.behind = int(parts[1])
+        
+        return status
+    
+    def get_diff(self, staged: bool = False, file_path: Optional[str] = None) -> List[GitDiff]:
+        """Get diff information."""
+        diffs = []
+        
+        if not self.is_repo:
+            return diffs
+        
+        args = ["diff"]
+        if staged:
+            args.append("--staged")
+        args.append("--numstat")
+        
+        if file_path:
+            args.append("--")
+            args.append(file_path)
+        
+        result = self._run_git(*args, check=False)
+        if result.returncode != 0:
+            return diffs
+        
+        for line in result.stdout.strip().split("\n"):
+            if not line:
+                continue
+            
+            parts = line.split("\t")
+            if len(parts) >= 3:
+                additions = int(parts[0]) if parts[0] != "-" else 0
+                deletions = int(parts[1]) if parts[1] != "-" else 0
+                path = parts[2]
+                
+                diffs.append(GitDiff(
+                    file_path=path,
+                    additions=additions,
+                    deletions=deletions
+                ))
+        
+        return diffs
+    
+    def get_diff_content(self, staged: bool = False, file_path: Optional[str] = None) -> str:
+        """Get full diff content."""
+        if not self.is_repo:
+            return ""
+        
+        args = ["diff"]
+        if staged:
+            args.append("--staged")
+        
+        if file_path:
+            args.append("--")
+            args.append(file_path)
+        
+        result = self._run_git(*args, check=False)
+        return result.stdout if result.returncode == 0 else ""
+    
+    def stage_files(self, files: Optional[List[str]] = None) -> bool:
+        """Stage files for commit."""
+        if not self.is_repo:
+            return False
+        
+        if files:
+            result = self._run_git("add", *files, check=False)
+        else:
+            result = self._run_git("add", "-A", check=False)
+        
+        return result.returncode == 0
+    
+    def commit(self, message: str, allow_empty: bool = False) -> Optional[GitCommit]:
+        """Create a commit."""
+        if not self.is_repo:
+            return None
+        
+        args = ["commit", "-m", message]
+        if allow_empty:
+            args.append("--allow-empty")
+        
+        result = self._run_git(*args, check=False)
+        
+        if result.returncode != 0:
+            logger.debug(f"Commit failed: {result.stderr}")
+            return None
+        
+        # Get commit info
+        return self.get_last_commit()
+    
+    def get_last_commit(self) -> Optional[GitCommit]:
+        """Get the last commit."""
+        if not self.is_repo:
+            return None
+        
+        result = self._run_git(
+            "log", "-1",
+            "--format=%H|%h|%s|%an|%ai",
+            check=False
+        )
+        
+        if result.returncode != 0:
+            return None
+        
+        parts = result.stdout.strip().split("|")
+        if len(parts) >= 5:
+            return GitCommit(
+                hash=parts[0],
+                short_hash=parts[1],
+                message=parts[2],
+                author=parts[3],
+                date=parts[4]
+            )
+        
+        return None
+    
+    def get_log(self, count: int = 10) -> List[GitCommit]:
+        """Get commit log."""
+        commits = []
+        
+        if not self.is_repo:
+            return commits
+        
+        result = self._run_git(
+            "log", f"-{count}",
+            "--format=%H|%h|%s|%an|%ai",
+            check=False
+        )
+        
+        if result.returncode != 0:
+            return commits
+        
+        for line in result.stdout.strip().split("\n"):
+            if not line:
+                continue
+            
+            parts = line.split("|")
+            if len(parts) >= 5:
+                commits.append(GitCommit(
+                    hash=parts[0],
+                    short_hash=parts[1],
+                    message=parts[2],
+                    author=parts[3],
+                    date=parts[4]
+                ))
+        
+        return commits
+    
+    def undo_last_commit(self, soft: bool = True) -> bool:
+        """Undo the last commit."""
+        if not self.is_repo:
+            return False
+        
+        reset_type = "--soft" if soft else "--hard"
+        result = self._run_git("reset", reset_type, "HEAD~1", check=False)
+        
+        return result.returncode == 0
+    
+    def create_branch(self, name: str, checkout: bool = True) -> bool:
+        """Create a new branch."""
+        if not self.is_repo:
+            return False
+        
+        if checkout:
+            result = self._run_git("checkout", "-b", name, check=False)
+        else:
+            result = self._run_git("branch", name, check=False)
+        
+        return result.returncode == 0
+    
+    def checkout_branch(self, name: str) -> bool:
+        """Checkout a branch."""
+        if not self.is_repo:
+            return False
+        
+        result = self._run_git("checkout", name, check=False)
+        return result.returncode == 0
+    
+    def get_branches(self) -> List[str]:
+        """Get list of branches."""
+        if not self.is_repo:
+            return []
+        
+        result = self._run_git("branch", "--list", check=False)
+        if result.returncode != 0:
+            return []
+        
+        branches = []
+        for line in result.stdout.strip().split("\n"):
+            if line:
+                # Remove * and whitespace
+                branch = line.strip().lstrip("* ")
+                branches.append(branch)
+        
+        return branches
+    
+    def stash(self, message: Optional[str] = None) -> bool:
+        """Stash changes."""
+        if not self.is_repo:
+            return False
+        
+        args = ["stash", "push"]
+        if message:
+            args.extend(["-m", message])
+        
+        result = self._run_git(*args, check=False)
+        return result.returncode == 0
+    
+    def stash_pop(self) -> bool:
+        """Pop stashed changes."""
+        if not self.is_repo:
+            return False
+        
+        result = self._run_git("stash", "pop", check=False)
+        return result.returncode == 0
+
+
+# ============================================================================
+# Commit Message Generator
+# ============================================================================
+
+class CommitMessageGenerator:
+    """
+    Generates commit messages using AI or templates.
+    """
+    
+    def __init__(self, use_ai: bool = True):
+        self.use_ai = use_ai
+    
+    def generate(
+        self,
+        diff_content: str,
+        context: Optional[str] = None,
+        style: str = "conventional"
+    ) -> str:
+        """
+        Generate a commit message.
+        
+        Args:
+            diff_content: The diff to describe
+            context: Optional context about the changes
+            style: Message style (conventional, simple, detailed)
+            
+        Returns:
+            Generated commit message
+        """
+        if not diff_content:
+            return "Empty commit"
+        
+        if self.use_ai:
+            return self._generate_with_ai(diff_content, context, style)
+        else:
+            return self._generate_from_diff(diff_content, style)
+    
+    def _generate_with_ai(
+        self,
+        diff_content: str,
+        context: Optional[str],
+        style: str
+    ) -> str:
+        """Generate commit message using AI."""
+        # This would integrate with the agent system
+        # For now, return a template-based message
+        return self._generate_from_diff(diff_content, style)
+    
+    def _generate_from_diff(self, diff_content: str, style: str) -> str:
+        """Generate commit message from diff analysis."""
+        # Analyze diff
+        files_changed = set()
+        additions = 0
+        deletions = 0
+        
+        for line in diff_content.split("\n"):
+            if line.startswith("diff --git"):
+                match = re.search(r"b/(.+)$", line)
+                if match:
+                    files_changed.add(match.group(1))
+            elif line.startswith("+") and not line.startswith("+++"):
+                additions += 1
+            elif line.startswith("-") and not line.startswith("---"):
+                deletions += 1
+        
+        # Determine change type
+        if additions > deletions * 2:
+            change_type = "feat"
+            action = "Add"
+        elif deletions > additions * 2:
+            change_type = "refactor"
+            action = "Remove"
+        else:
+            change_type = "fix"
+            action = "Update"
+        
+        # Build message
+        if len(files_changed) == 1:
+            file_name = list(files_changed)[0]
+            scope = Path(file_name).stem
+            message = f"{change_type}({scope}): {action} {file_name}"
+        elif len(files_changed) <= 3:
+            files_str = ", ".join(sorted(files_changed))
+            message = f"{change_type}: {action} {files_str}"
+        else:
+            message = f"{change_type}: {action} {len(files_changed)} files"
+        
+        if style == "detailed":
+            message += f"\n\n+{additions} -{deletions} lines"
+        
+        return message
+
+
+# ============================================================================
+# Diff Viewer
+# ============================================================================
+
+class DiffViewer:
+    """
+    Rich-based diff viewer.
+    """
+    
+    def __init__(self):
+        self._console = None
+    
+    @property
+    def console(self):
+        """Lazy load Rich console."""
+        if self._console is None:
+            try:
+                from rich.console import Console
+                self._console = Console()
+            except ImportError:
+                self._console = None
+        return self._console
+    
+    def display_diff(self, diff_content: str, title: str = "Changes") -> None:
+        """Display diff with syntax highlighting."""
+        if not self.console:
+            print(diff_content)
+            return
+        
+        from rich.panel import Panel
+        from rich.syntax import Syntax
+        
+        syntax = Syntax(diff_content, "diff", theme="monokai", line_numbers=True)
+        self.console.print(Panel(syntax, title=title, border_style="blue"))
+    
+    def display_status(self, status: GitStatus) -> None:
+        """Display git status."""
+        if not self.console:
+            print(f"Branch: {status.branch}")
+            print(f"Staged: {len(status.staged_files)}")
+            print(f"Modified: {len(status.modified_files)}")
+            print(f"Untracked: {len(status.untracked_files)}")
+            return
+        
+        from rich.panel import Panel
+        from rich.table import Table
+        
+        table = Table(show_header=True, header_style="bold cyan")
+        table.add_column("Category")
+        table.add_column("Files", justify="right")
+        
+        table.add_row("Branch", status.branch or "detached")
+        table.add_row("Staged", str(len(status.staged_files)))
+        table.add_row("Modified", str(len(status.modified_files)))
+        table.add_row("Untracked", str(len(status.untracked_files)))
+        
+        if status.ahead or status.behind:
+            table.add_row("Ahead/Behind", f"+{status.ahead} / -{status.behind}")
+        
+        self.console.print(Panel(table, title="📊 Git Status", border_style="green"))
+    
+    def display_log(self, commits: List[GitCommit]) -> None:
+        """Display commit log."""
+        if not self.console:
+            for commit in commits:
+                print(f"{commit.short_hash} {commit.message}")
+            return
+        
+        from rich.table import Table
+        
+        table = Table(show_header=True, header_style="bold cyan")
+        table.add_column("Hash")
+        table.add_column("Message")
+        table.add_column("Author")
+        table.add_column("Date")
+        
+        for commit in commits:
+            table.add_row(
+                commit.short_hash,
+                commit.message[:50] + "..." if len(commit.message) > 50 else commit.message,
+                commit.author,
+                commit.date[:10]
+            )
+        
+        self.console.print(table)
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class GitIntegrationHandler:
+    """
+    Handler for integrating Git with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._git: Optional[GitManager] = None
+        self._viewer: Optional[DiffViewer] = None
+        self._generator: Optional[CommitMessageGenerator] = None
+    
+    @property
+    def feature_name(self) -> str:
+        return "git_integration"
+    
+    def initialize(self, repo_path: Optional[str] = None) -> GitManager:
+        """Initialize Git manager."""
+        self._git = GitManager(repo_path=repo_path, verbose=self.verbose)
+        self._viewer = DiffViewer()
+        self._generator = CommitMessageGenerator()
+        
+        if self.verbose and self._git.is_repo:
+            from rich import print as rprint
+            status = self._git.get_status()
+            rprint(f"[cyan]Git initialized on branch: {status.branch}[/cyan]")
+        
+        return self._git
+    
+    def get_git(self) -> Optional[GitManager]:
+        """Get the Git manager."""
+        return self._git
+    
+    def show_status(self) -> GitStatus:
+        """Show git status."""
+        if not self._git:
+            self._git = self.initialize()
+        
+        status = self._git.get_status()
+        if self._viewer:
+            self._viewer.display_status(status)
+        
+        return status
+    
+    def show_diff(self, staged: bool = False) -> str:
+        """Show diff."""
+        if not self._git:
+            self._git = self.initialize()
+        
+        diff_content = self._git.get_diff_content(staged=staged)
+        if self._viewer and diff_content:
+            self._viewer.display_diff(diff_content)
+        
+        return diff_content
+    
+    def commit(
+        self,
+        message: Optional[str] = None,
+        auto_stage: bool = True
+    ) -> Optional[GitCommit]:
+        """Create a commit."""
+        if not self._git:
+            self._git = self.initialize()
+        
+        if auto_stage:
+            self._git.stage_files()
+        
+        if not message:
+            # Generate message from diff
+            diff_content = self._git.get_diff_content(staged=True)
+            if self._generator:
+                message = self._generator.generate(diff_content)
+            else:
+                message = "Update files"
+        
+        return self._git.commit(message)
+    
+    def undo(self, soft: bool = True) -> bool:
+        """Undo last commit."""
+        if not self._git:
+            self._git = self.initialize()
+        
+        return self._git.undo_last_commit(soft=soft)
+    
+    def show_log(self, count: int = 10) -> List[GitCommit]:
+        """Show commit log."""
+        if not self._git:
+            self._git = self.initialize()
+        
+        commits = self._git.get_log(count=count)
+        if self._viewer:
+            self._viewer.display_log(commits)
+        
+        return commits
@@ -0,0 +1,603 @@
+"""
+Interactive TUI System for PraisonAI CLI.
+
+Inspired by Aider's interactive mode and prompt_toolkit usage.
+Provides rich interactive terminal experience with completions and history.
+
+Architecture:
+- InteractiveSession: Main interactive session manager
+- CommandCompleter: Auto-completion for commands and files
+- HistoryManager: Persistent command history
+- StatusDisplay: Rich-based status bar and output
+"""
+
+from dataclasses import dataclass
+from typing import Any, Callable, Dict, List, Optional
+from pathlib import Path
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+# ============================================================================
+# Configuration
+# ============================================================================
+
+@dataclass
+class InteractiveConfig:
+    """Configuration for interactive session."""
+    prompt: str = ">>> "
+    multiline: bool = True
+    history_file: Optional[str] = None
+    max_history: int = 1000
+    enable_completions: bool = True
+    enable_syntax_highlighting: bool = True
+    vi_mode: bool = False
+    auto_suggest: bool = True
+    show_status_bar: bool = True
+    color_scheme: str = "monokai"
+
+
+# ============================================================================
+# Command Completer
+# ============================================================================
+
+class CommandCompleter:
+    """
+    Provides auto-completion for commands, files, and symbols.
+    """
+    
+    def __init__(
+        self,
+        commands: Optional[List[str]] = None,
+        file_patterns: Optional[List[str]] = None
+    ):
+        self.commands = commands or []
+        self.file_patterns = file_patterns or ["*.py", "*.js", "*.ts"]
+        self._file_cache: List[str] = []
+        self._symbol_cache: List[str] = []
+    
+    def add_commands(self, commands: List[str]) -> None:
+        """Add commands to completion list."""
+        self.commands.extend(commands)
+    
+    def add_symbols(self, symbols: List[str]) -> None:
+        """Add symbols to completion list."""
+        self._symbol_cache.extend(symbols)
+    
+    def refresh_files(self, root: Optional[Path] = None) -> None:
+        """Refresh file cache."""
+        root = root or Path.cwd()
+        self._file_cache = []
+        
+        for pattern in self.file_patterns:
+            for file_path in root.rglob(pattern):
+                try:
+                    rel_path = str(file_path.relative_to(root))
+                    if not any(excl in rel_path for excl in ["__pycache__", "node_modules", ".git"]):
+                        self._file_cache.append(rel_path)
+                except ValueError:
+                    pass
+    
+    def get_completions(self, text: str, cursor_pos: int) -> List[str]:
+        """
+        Get completions for the current input.
+        
+        Args:
+            text: Current input text
+            cursor_pos: Cursor position
+            
+        Returns:
+            List of completion suggestions
+        """
+        # Get word before cursor
+        before_cursor = text[:cursor_pos]
+        words = before_cursor.split()
+        current_word = words[-1] if words else ""
+        
+        completions = []
+        
+        # Slash commands
+        if current_word.startswith("/"):
+            cmd_part = current_word[1:].lower()
+            for cmd in self.commands:
+                if cmd.lower().startswith(cmd_part):
+                    completions.append(f"/{cmd}")
+        
+        # @ mentions for files
+        elif current_word.startswith("@"):
+            file_part = current_word[1:].lower()
+            for file_path in self._file_cache:
+                if file_part in file_path.lower():
+                    completions.append(f"@{file_path}")
+        
+        # General completions
+        else:
+            word_lower = current_word.lower()
+            
+            # Check symbols
+            for symbol in self._symbol_cache:
+                if symbol.lower().startswith(word_lower):
+                    completions.append(symbol)
+            
+            # Check files
+            for file_path in self._file_cache:
+                if word_lower in file_path.lower():
+                    completions.append(file_path)
+        
+        return completions[:20]  # Limit results
+    
+    def create_prompt_toolkit_completer(self) -> Any:
+        """Create a prompt_toolkit completer."""
+        try:
+            from prompt_toolkit.completion import Completer, Completion
+            
+            outer_self = self
+            
+            class PTCompleter(Completer):
+                def get_completions(self, document, complete_event):
+                    text = document.text
+                    cursor_pos = document.cursor_position
+                    
+                    for completion in outer_self.get_completions(text, cursor_pos):
+                        # Calculate start position
+                        words = text[:cursor_pos].split()
+                        current_word = words[-1] if words else ""
+                        start_pos = -len(current_word)
+                        
+                        yield Completion(completion, start_position=start_pos)
+            
+            return PTCompleter()
+        except ImportError:
+            return None
+
+
+# ============================================================================
+# History Manager
+# ============================================================================
+
+class HistoryManager:
+    """
+    Manages command history with persistence.
+    """
+    
+    def __init__(
+        self,
+        history_file: Optional[str] = None,
+        max_entries: int = 1000
+    ):
+        self.history_file = Path(history_file) if history_file else None
+        self.max_entries = max_entries
+        self._history: List[str] = []
+        self._position: int = 0
+        
+        if self.history_file:
+            self._load_history()
+    
+    def _load_history(self) -> None:
+        """Load history from file."""
+        if self.history_file and self.history_file.exists():
+            try:
+                with open(self.history_file, 'r', encoding='utf-8') as f:
+                    self._history = [
+                        line.strip() for line in f.readlines()
+                        if line.strip()
+                    ][-self.max_entries:]
+            except Exception as e:
+                logger.debug(f"Could not load history: {e}")
+    
+    def _save_history(self) -> None:
+        """Save history to file."""
+        if self.history_file:
+            try:
+                self.history_file.parent.mkdir(parents=True, exist_ok=True)
+                with open(self.history_file, 'w', encoding='utf-8') as f:
+                    for entry in self._history[-self.max_entries:]:
+                        f.write(entry + "\n")
+            except Exception as e:
+                logger.debug(f"Could not save history: {e}")
+    
+    def add(self, entry: str) -> None:
+        """Add an entry to history."""
+        entry = entry.strip()
+        if entry and (not self._history or self._history[-1] != entry):
+            self._history.append(entry)
+            self._position = len(self._history)
+            self._save_history()
+    
+    def get_previous(self) -> Optional[str]:
+        """Get previous history entry."""
+        if self._position > 0:
+            self._position -= 1
+            return self._history[self._position]
+        return None
+    
+    def get_next(self) -> Optional[str]:
+        """Get next history entry."""
+        if self._position < len(self._history) - 1:
+            self._position += 1
+            return self._history[self._position]
+        elif self._position == len(self._history) - 1:
+            self._position = len(self._history)
+            return ""
+        return None
+    
+    def search(self, prefix: str) -> List[str]:
+        """Search history for entries starting with prefix."""
+        return [
+            entry for entry in self._history
+            if entry.lower().startswith(prefix.lower())
+        ]
+    
+    def get_all(self) -> List[str]:
+        """Get all history entries."""
+        return self._history.copy()
+    
+    def clear(self) -> None:
+        """Clear history."""
+        self._history.clear()
+        self._position = 0
+        if self.history_file and self.history_file.exists():
+            self.history_file.unlink()
+    
+    def create_prompt_toolkit_history(self) -> Any:
+        """Create a prompt_toolkit history object."""
+        try:
+            from prompt_toolkit.history import FileHistory, InMemoryHistory
+            
+            if self.history_file:
+                return FileHistory(str(self.history_file))
+            return InMemoryHistory()
+        except ImportError:
+            return None
+
+
+# ============================================================================
+# Status Display
+# ============================================================================
+
+class StatusDisplay:
+    """
+    Rich-based status display for interactive session.
+    """
+    
+    def __init__(self, show_status_bar: bool = True):
+        self.show_status_bar = show_status_bar
+        self._console = None
+        self._status_items: Dict[str, str] = {}
+    
+    @property
+    def console(self):
+        """Lazy load Rich console."""
+        if self._console is None:
+            try:
+                from rich.console import Console
+                self._console = Console()
+            except ImportError:
+                self._console = None
+        return self._console
+    
+    def set_status(self, key: str, value: str) -> None:
+        """Set a status item."""
+        self._status_items[key] = value
+    
+    def clear_status(self, key: str) -> None:
+        """Clear a status item."""
+        self._status_items.pop(key, None)
+    
+    def print_status_bar(self) -> None:
+        """Print the status bar."""
+        if not self.show_status_bar or not self.console:
+            return
+        
+        from rich.columns import Columns
+        from rich.text import Text
+        
+        items = []
+        for key, value in self._status_items.items():
+            items.append(Text(f"{key}: {value}", style="dim"))
+        
+        if items:
+            self.console.print(Columns(items, equal=True, expand=True))
+    
+    def print_welcome(self, version: str = "1.0.0") -> None:
+        """Print welcome message."""
+        if not self.console:
+            print(f"PraisonAI CLI v{version}")
+            return
+        
+        from rich.panel import Panel
+        from rich.text import Text
+        
+        welcome = Text()
+        welcome.append("PraisonAI CLI", style="bold cyan")
+        welcome.append(f" v{version}\n", style="dim")
+        welcome.append("Type ", style="dim")
+        welcome.append("/help", style="bold green")
+        welcome.append(" for commands, ", style="dim")
+        welcome.append("/exit", style="bold yellow")
+        welcome.append(" to quit", style="dim")
+        
+        self.console.print(Panel(welcome, border_style="blue"))
+    
+    def print_response(self, response: str, title: str = "Response") -> None:
+        """Print a response with formatting."""
+        if not self.console:
+            print(response)
+            return
+        
+        from rich.panel import Panel
+        from rich.markdown import Markdown
+        
+        try:
+            md = Markdown(response)
+            self.console.print(Panel(md, title=title, border_style="green"))
+        except Exception:
+            self.console.print(Panel(response, title=title, border_style="green"))
+    
+    def print_error(self, error: str) -> None:
+        """Print an error message."""
+        if not self.console:
+            print(f"Error: {error}")
+            return
+        
+        from rich.panel import Panel
+        self.console.print(Panel(error, title="Error", border_style="red"))
+    
+    def print_info(self, message: str) -> None:
+        """Print an info message."""
+        if not self.console:
+            print(message)
+            return
+        
+        self.console.print(f"[cyan]ℹ[/cyan] {message}")
+    
+    def print_success(self, message: str) -> None:
+        """Print a success message."""
+        if not self.console:
+            print(message)
+            return
+        
+        self.console.print(f"[green]✓[/green] {message}")
+
+
+# ============================================================================
+# Interactive Session
+# ============================================================================
+
+class InteractiveSession:
+    """
+    Main interactive session manager.
+    
+    Provides a rich interactive terminal experience with:
+    - Command completion
+    - History
+    - Syntax highlighting
+    - Status bar
+    - Keyboard shortcuts
+    """
+    
+    def __init__(
+        self,
+        config: Optional[InteractiveConfig] = None,
+        on_input: Optional[Callable[[str], Optional[str]]] = None,
+        on_command: Optional[Callable[[str], Optional[Dict[str, Any]]]] = None
+    ):
+        self.config = config or InteractiveConfig()
+        self.on_input = on_input
+        self.on_command = on_command
+        
+        self.completer = CommandCompleter()
+        self.history = HistoryManager(
+            history_file=self.config.history_file,
+            max_entries=self.config.max_history
+        )
+        self.display = StatusDisplay(show_status_bar=self.config.show_status_bar)
+        
+        self._running = False
+        self._prompt_session = None
+    
+    def _create_prompt_session(self) -> Any:
+        """Create a prompt_toolkit session."""
+        try:
+            from prompt_toolkit import PromptSession
+            from prompt_toolkit.lexers import PygmentsLexer
+            from prompt_toolkit.auto_suggest import AutoSuggestFromHistory
+            from pygments.lexers import MarkdownLexer
+            
+            session_kwargs = {
+                "message": self.config.prompt,
+                "multiline": self.config.multiline,
+            }
+            
+            # Add completer
+            if self.config.enable_completions:
+                completer = self.completer.create_prompt_toolkit_completer()
+                if completer:
+                    session_kwargs["completer"] = completer
+            
+            # Add history
+            history = self.history.create_prompt_toolkit_history()
+            if history:
+                session_kwargs["history"] = history
+            
+            # Add syntax highlighting
+            if self.config.enable_syntax_highlighting:
+                session_kwargs["lexer"] = PygmentsLexer(MarkdownLexer)
+            
+            # Add auto-suggest
+            if self.config.auto_suggest:
+                session_kwargs["auto_suggest"] = AutoSuggestFromHistory()
+            
+            # VI mode
+            if self.config.vi_mode:
+                from prompt_toolkit.enums import EditingMode
+                session_kwargs["editing_mode"] = EditingMode.VI
+            
+            return PromptSession(**session_kwargs)
+        
+        except ImportError as e:
+            logger.debug(f"prompt_toolkit not available: {e}")
+            return None
+    
+    def _get_input_fallback(self) -> str:
+        """Fallback input method without prompt_toolkit."""
+        try:
+            if self.config.multiline:
+                print(f"{self.config.prompt}(Enter empty line to submit)")
+                lines = []
+                while True:
+                    line = input()
+                    if not line:
+                        break
+                    lines.append(line)
+                return "\n".join(lines)
+            else:
+                return input(self.config.prompt)
+        except EOFError:
+            return "/exit"
+        except KeyboardInterrupt:
+            print()
+            return ""
+    
+    def get_input(self) -> str:
+        """Get input from user."""
+        if self._prompt_session:
+            try:
+                return self._prompt_session.prompt()
+            except KeyboardInterrupt:
+                return ""
+            except EOFError:
+                return "/exit"
+        else:
+            return self._get_input_fallback()
+    
+    def process_input(self, user_input: str) -> Optional[str]:
+        """
+        Process user input.
+        
+        Args:
+            user_input: Raw user input
+            
+        Returns:
+            Response string or None
+        """
+        user_input = user_input.strip()
+        
+        if not user_input:
+            return None
+        
+        # Add to history
+        self.history.add(user_input)
+        
+        # Check for slash commands
+        if user_input.startswith("/"):
+            if self.on_command:
+                result = self.on_command(user_input)
+                if result:
+                    if result.get("type") == "exit":
+                        self._running = False
+                        return None
+                    return result.get("message")
+            return None
+        
+        # Regular input
+        if self.on_input:
+            return self.on_input(user_input)
+        
+        return None
+    
+    def run(self) -> None:
+        """Run the interactive session."""
+        self._running = True
+        self._prompt_session = self._create_prompt_session()
+        
+        # Print welcome
+        self.display.print_welcome()
+        
+        while self._running:
+            try:
+                # Get input
+                user_input = self.get_input()
+                
+                # Process
+                response = self.process_input(user_input)
+                
+                # Display response
+                if response:
+                    self.display.print_response(response)
+                
+            except KeyboardInterrupt:
+                self.display.print_info("Use /exit to quit")
+            except Exception as e:
+                self.display.print_error(str(e))
+                logger.exception("Error in interactive session")
+    
+    def stop(self) -> None:
+        """Stop the interactive session."""
+        self._running = False
+    
+    def add_commands(self, commands: List[str]) -> None:
+        """Add commands for completion."""
+        self.completer.add_commands(commands)
+    
+    def add_symbols(self, symbols: List[str]) -> None:
+        """Add symbols for completion."""
+        self.completer.add_symbols(symbols)
+    
+    def refresh_files(self, root: Optional[Path] = None) -> None:
+        """Refresh file completions."""
+        self.completer.refresh_files(root)
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class InteractiveTUIHandler:
+    """
+    Handler for integrating Interactive TUI with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._session: Optional[InteractiveSession] = None
+    
+    @property
+    def feature_name(self) -> str:
+        return "interactive_tui"
+    
+    def initialize(
+        self,
+        config: Optional[InteractiveConfig] = None,
+        on_input: Optional[Callable[[str], Optional[str]]] = None,
+        on_command: Optional[Callable[[str], Optional[Dict[str, Any]]]] = None
+    ) -> InteractiveSession:
+        """Initialize the interactive session."""
+        self._session = InteractiveSession(
+            config=config,
+            on_input=on_input,
+            on_command=on_command
+        )
+        
+        if self.verbose:
+            from rich import print as rprint
+            rprint("[cyan]Interactive TUI initialized[/cyan]")
+        
+        return self._session
+    
+    def get_session(self) -> Optional[InteractiveSession]:
+        """Get the current session."""
+        return self._session
+    
+    def run(self) -> None:
+        """Run the interactive session."""
+        if not self._session:
+            self._session = self.initialize()
+        
+        self._session.run()
+    
+    def stop(self) -> None:
+        """Stop the interactive session."""
+        if self._session:
+            self._session.stop()
@@ -0,0 +1,860 @@
+"""
+Repository Map System for PraisonAI CLI.
+
+Inspired by Aider's RepoMap using tree-sitter for code parsing.
+Provides intelligent codebase context for LLM interactions.
+
+Architecture:
+- RepoMap: Main class for building repository maps
+- SymbolExtractor: Extracts symbols using tree-sitter or regex fallback
+- SymbolRanker: Ranks symbols by importance using graph analysis
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Set
+from pathlib import Path
+from collections import defaultdict
+import logging
+import re
+
+logger = logging.getLogger(__name__)
+
+
+# ============================================================================
+# Data Classes
+# ============================================================================
+
+@dataclass
+class Symbol:
+    """
+    Represents a code symbol (class, function, method, variable).
+    """
+    name: str
+    kind: str  # class, function, method, variable, import
+    file_path: str
+    line_number: int
+    signature: str = ""  # Full signature for functions/methods
+    parent: Optional[str] = None  # Parent class for methods
+    references: int = 0  # Number of references in codebase
+    
+    @property
+    def qualified_name(self) -> str:
+        """Get fully qualified name."""
+        if self.parent:
+            return f"{self.parent}.{self.name}"
+        return self.name
+    
+    def __hash__(self):
+        return hash((self.name, self.kind, self.file_path, self.line_number))
+
+
+@dataclass
+class FileMap:
+    """
+    Map of symbols in a single file.
+    """
+    file_path: str
+    symbols: List[Symbol] = field(default_factory=list)
+    imports: List[str] = field(default_factory=list)
+    
+    def add_symbol(self, symbol: Symbol) -> None:
+        """Add a symbol to the file map."""
+        self.symbols.append(symbol)
+    
+    def get_summary(self, max_symbols: int = 10) -> str:
+        """Get a summary of the file's symbols."""
+        lines = [f"{self.file_path}:"]
+        
+        # Sort by importance (references) and take top symbols
+        sorted_symbols = sorted(
+            self.symbols,
+            key=lambda s: (s.references, s.kind == "class"),
+            reverse=True
+        )[:max_symbols]
+        
+        for symbol in sorted_symbols:
+            if symbol.signature:
+                lines.append(f"  {symbol.signature}")
+            else:
+                lines.append(f"  {symbol.kind} {symbol.name}")
+        
+        return "\n".join(lines)
+
+
+@dataclass
+class RepoMapConfig:
+    """Configuration for repository mapping."""
+    max_tokens: int = 1024
+    max_files: int = 50
+    max_symbols_per_file: int = 20
+    include_imports: bool = True
+    include_docstrings: bool = False
+    file_extensions: Set[str] = field(default_factory=lambda: {
+        ".py", ".js", ".ts", ".jsx", ".tsx", ".java", ".go", ".rs",
+        ".cpp", ".c", ".h", ".hpp", ".rb", ".php", ".swift", ".kt"
+    })
+    exclude_patterns: Set[str] = field(default_factory=lambda: {
+        "__pycache__", "node_modules", ".git", ".venv", "venv",
+        "build", "dist", ".egg-info", "__init__.py"
+    })
+
+
+# ============================================================================
+# Symbol Extraction
+# ============================================================================
+
+class SymbolExtractor:
+    """
+    Extracts symbols from source code.
+    
+    Uses tree-sitter when available, falls back to regex patterns.
+    """
+    
+    def __init__(self, use_tree_sitter: bool = True):
+        self.use_tree_sitter = use_tree_sitter
+        self._tree_sitter_available = False
+        self._parsers: Dict[str, Any] = {}
+        
+        if use_tree_sitter:
+            self._init_tree_sitter()
+    
+    def _init_tree_sitter(self) -> None:
+        """Initialize tree-sitter if available."""
+        try:
+            # Try to import tree-sitter-languages (pip installable)
+            import tree_sitter_languages
+            self._tree_sitter_available = True
+            self._ts_languages = tree_sitter_languages
+            logger.debug("tree-sitter-languages available")
+        except ImportError:
+            try:
+                # Fallback to tree-sitter with manual language setup
+                import tree_sitter
+                self._tree_sitter_available = True
+                self._tree_sitter = tree_sitter
+                logger.debug("tree-sitter available (manual setup required)")
+            except ImportError:
+                logger.debug("tree-sitter not available, using regex fallback")
+                self._tree_sitter_available = False
+    
+    def extract_symbols(self, file_path: str, content: str) -> List[Symbol]:
+        """
+        Extract symbols from file content.
+        
+        Args:
+            file_path: Path to the file
+            content: File content
+            
+        Returns:
+            List of extracted symbols
+        """
+        ext = Path(file_path).suffix.lower()
+        
+        if self._tree_sitter_available:
+            try:
+                return self._extract_with_tree_sitter(file_path, content, ext)
+            except Exception as e:
+                logger.debug(f"tree-sitter extraction failed: {e}")
+        
+        # Fallback to regex
+        return self._extract_with_regex(file_path, content, ext)
+    
+    def _extract_with_tree_sitter(
+        self, file_path: str, content: str, ext: str
+    ) -> List[Symbol]:
+        """Extract symbols using tree-sitter."""
+        symbols = []
+        
+        # Map extension to language
+        lang_map = {
+            ".py": "python",
+            ".js": "javascript",
+            ".ts": "typescript",
+            ".jsx": "javascript",
+            ".tsx": "typescript",
+            ".java": "java",
+            ".go": "go",
+            ".rs": "rust",
+            ".rb": "ruby",
+            ".cpp": "cpp",
+            ".c": "c",
+            ".h": "c",
+        }
+        
+        lang = lang_map.get(ext)
+        if not lang:
+            return self._extract_with_regex(file_path, content, ext)
+        
+        try:
+            parser = self._ts_languages.get_parser(lang)
+            tree = parser.parse(content.encode())
+            
+            # Extract based on language
+            if lang == "python":
+                symbols = self._extract_python_symbols(file_path, tree, content)
+            else:
+                # Generic extraction for other languages
+                symbols = self._extract_generic_symbols(file_path, tree, content, lang)
+        except Exception as e:
+            logger.debug(f"tree-sitter parsing failed for {lang}: {e}")
+            return self._extract_with_regex(file_path, content, ext)
+        
+        return symbols
+    
+    def _extract_python_symbols(
+        self, file_path: str, tree: Any, content: str
+    ) -> List[Symbol]:
+        """Extract Python symbols from tree-sitter AST."""
+        symbols = []
+        lines = content.split("\n")
+        
+        def visit_node(node, parent_class=None):
+            if node.type == "class_definition":
+                name_node = node.child_by_field_name("name")
+                if name_node:
+                    class_name = content[name_node.start_byte:name_node.end_byte]
+                    line_num = node.start_point[0] + 1
+                    
+                    # Get class signature
+                    sig_end = node.children[0].end_byte if node.children else node.start_byte + 50
+                    signature = content[node.start_byte:sig_end].split("\n")[0]
+                    
+                    symbols.append(Symbol(
+                        name=class_name,
+                        kind="class",
+                        file_path=file_path,
+                        line_number=line_num,
+                        signature=signature.strip()
+                    ))
+                    
+                    # Visit children with class context
+                    for child in node.children:
+                        visit_node(child, class_name)
+                    return
+            
+            elif node.type == "function_definition":
+                name_node = node.child_by_field_name("name")
+                if name_node:
+                    func_name = content[name_node.start_byte:name_node.end_byte]
+                    line_num = node.start_point[0] + 1
+                    
+                    # Get function signature
+                    sig_line = lines[line_num - 1] if line_num <= len(lines) else ""
+                    
+                    kind = "method" if parent_class else "function"
+                    symbols.append(Symbol(
+                        name=func_name,
+                        kind=kind,
+                        file_path=file_path,
+                        line_number=line_num,
+                        signature=sig_line.strip(),
+                        parent=parent_class
+                    ))
+            
+            # Visit children
+            for child in node.children:
+                visit_node(child, parent_class)
+        
+        visit_node(tree.root_node)
+        return symbols
+    
+    def _extract_generic_symbols(
+        self, file_path: str, tree: Any, content: str, lang: str
+    ) -> List[Symbol]:
+        """Generic symbol extraction for other languages."""
+        symbols = []
+        
+        # Node types for different languages
+        class_types = {"class_definition", "class_declaration", "struct_definition"}
+        func_types = {"function_definition", "function_declaration", "method_definition"}
+        
+        def visit_node(node, parent=None):
+            if node.type in class_types:
+                name = self._get_node_name(node, content)
+                if name:
+                    symbols.append(Symbol(
+                        name=name,
+                        kind="class",
+                        file_path=file_path,
+                        line_number=node.start_point[0] + 1
+                    ))
+                    for child in node.children:
+                        visit_node(child, name)
+                    return
+            
+            elif node.type in func_types:
+                name = self._get_node_name(node, content)
+                if name:
+                    symbols.append(Symbol(
+                        name=name,
+                        kind="method" if parent else "function",
+                        file_path=file_path,
+                        line_number=node.start_point[0] + 1,
+                        parent=parent
+                    ))
+            
+            for child in node.children:
+                visit_node(child, parent)
+        
+        visit_node(tree.root_node)
+        return symbols
+    
+    def _get_node_name(self, node: Any, content: str) -> Optional[str]:
+        """Get name from a tree-sitter node."""
+        name_node = node.child_by_field_name("name")
+        if name_node:
+            return content[name_node.start_byte:name_node.end_byte]
+        return None
+    
+    def _extract_with_regex(
+        self, file_path: str, content: str, ext: str
+    ) -> List[Symbol]:
+        """Extract symbols using regex patterns (fallback)."""
+        symbols = []
+        lines = content.split("\n")
+        
+        if ext == ".py":
+            symbols = self._extract_python_regex(file_path, lines)
+        elif ext in {".js", ".ts", ".jsx", ".tsx"}:
+            symbols = self._extract_js_regex(file_path, lines)
+        elif ext in {".java", ".kt"}:
+            symbols = self._extract_java_regex(file_path, lines)
+        elif ext == ".go":
+            symbols = self._extract_go_regex(file_path, lines)
+        elif ext == ".rs":
+            symbols = self._extract_rust_regex(file_path, lines)
+        else:
+            # Generic extraction
+            symbols = self._extract_generic_regex(file_path, lines)
+        
+        return symbols
+    
+    def _extract_python_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Extract Python symbols using regex."""
+        symbols = []
+        current_class = None
+        
+        class_pattern = re.compile(r'^class\s+(\w+)')
+        func_pattern = re.compile(r'^(\s*)def\s+(\w+)\s*\(([^)]*)\)')
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            # Check for class
+            class_match = class_pattern.match(line)
+            if class_match:
+                current_class = class_match.group(1)
+                symbols.append(Symbol(
+                    name=current_class,
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num,
+                    signature=line.strip()
+                ))
+                continue
+            
+            # Check for function/method
+            func_match = func_pattern.match(line)
+            if func_match:
+                indent = len(func_match.group(1))
+                func_name = func_match.group(2)
+                
+                # If indented, it's a method
+                if indent > 0 and current_class:
+                    symbols.append(Symbol(
+                        name=func_name,
+                        kind="method",
+                        file_path=file_path,
+                        line_number=line_num,
+                        signature=line.strip(),
+                        parent=current_class
+                    ))
+                else:
+                    current_class = None  # Reset class context
+                    symbols.append(Symbol(
+                        name=func_name,
+                        kind="function",
+                        file_path=file_path,
+                        line_number=line_num,
+                        signature=line.strip()
+                    ))
+        
+        return symbols
+    
+    def _extract_js_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Extract JavaScript/TypeScript symbols using regex."""
+        symbols = []
+        
+        class_pattern = re.compile(r'(?:export\s+)?class\s+(\w+)')
+        func_pattern = re.compile(
+            r'(?:export\s+)?(?:async\s+)?function\s+(\w+)|'
+            r'(?:const|let|var)\s+(\w+)\s*=\s*(?:async\s+)?\([^)]*\)\s*=>'
+        )
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            class_match = class_pattern.search(line)
+            if class_match:
+                symbols.append(Symbol(
+                    name=class_match.group(1),
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num,
+                    signature=line.strip()[:80]
+                ))
+            
+            func_match = func_pattern.search(line)
+            if func_match:
+                name = func_match.group(1) or func_match.group(2)
+                if name:
+                    symbols.append(Symbol(
+                        name=name,
+                        kind="function",
+                        file_path=file_path,
+                        line_number=line_num,
+                        signature=line.strip()[:80]
+                    ))
+        
+        return symbols
+    
+    def _extract_java_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Extract Java/Kotlin symbols using regex."""
+        symbols = []
+        
+        class_pattern = re.compile(
+            r'(?:public|private|protected)?\s*(?:static\s+)?'
+            r'(?:class|interface|enum)\s+(\w+)'
+        )
+        method_pattern = re.compile(
+            r'(?:public|private|protected)?\s*(?:static\s+)?'
+            r'(?:\w+(?:<[^>]+>)?)\s+(\w+)\s*\('
+        )
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            class_match = class_pattern.search(line)
+            if class_match:
+                symbols.append(Symbol(
+                    name=class_match.group(1),
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+            
+            method_match = method_pattern.search(line)
+            if method_match and not class_match:
+                symbols.append(Symbol(
+                    name=method_match.group(1),
+                    kind="method",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+        
+        return symbols
+    
+    def _extract_go_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Extract Go symbols using regex."""
+        symbols = []
+        
+        func_pattern = re.compile(r'^func\s+(?:\([^)]+\)\s+)?(\w+)')
+        type_pattern = re.compile(r'^type\s+(\w+)\s+(?:struct|interface)')
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            type_match = type_pattern.match(line)
+            if type_match:
+                symbols.append(Symbol(
+                    name=type_match.group(1),
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+            
+            func_match = func_pattern.match(line)
+            if func_match:
+                symbols.append(Symbol(
+                    name=func_match.group(1),
+                    kind="function",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+        
+        return symbols
+    
+    def _extract_rust_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Extract Rust symbols using regex."""
+        symbols = []
+        
+        fn_pattern = re.compile(r'(?:pub\s+)?(?:async\s+)?fn\s+(\w+)')
+        struct_pattern = re.compile(r'(?:pub\s+)?struct\s+(\w+)')
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            struct_match = struct_pattern.match(line)
+            if struct_match:
+                symbols.append(Symbol(
+                    name=struct_match.group(1),
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+            
+            fn_match = fn_pattern.search(line)
+            if fn_match:
+                symbols.append(Symbol(
+                    name=fn_match.group(1),
+                    kind="function",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+        
+        return symbols
+    
+    def _extract_generic_regex(self, file_path: str, lines: List[str]) -> List[Symbol]:
+        """Generic symbol extraction for unknown languages."""
+        symbols = []
+        
+        # Very basic patterns
+        class_pattern = re.compile(r'(?:class|struct|interface)\s+(\w+)')
+        func_pattern = re.compile(r'(?:function|def|fn|func)\s+(\w+)')
+        
+        for i, line in enumerate(lines):
+            line_num = i + 1
+            
+            class_match = class_pattern.search(line)
+            if class_match:
+                symbols.append(Symbol(
+                    name=class_match.group(1),
+                    kind="class",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+            
+            func_match = func_pattern.search(line)
+            if func_match:
+                symbols.append(Symbol(
+                    name=func_match.group(1),
+                    kind="function",
+                    file_path=file_path,
+                    line_number=line_num
+                ))
+        
+        return symbols
+
+
+# ============================================================================
+# Symbol Ranking
+# ============================================================================
+
+class SymbolRanker:
+    """
+    Ranks symbols by importance using reference counting and graph analysis.
+    """
+    
+    def __init__(self):
+        self.symbol_refs: Dict[str, int] = defaultdict(int)
+        self.file_refs: Dict[str, Set[str]] = defaultdict(set)
+    
+    def analyze_references(
+        self, file_maps: Dict[str, FileMap], all_content: Dict[str, str]
+    ) -> None:
+        """
+        Analyze references between symbols across files.
+        
+        Args:
+            file_maps: Map of file path to FileMap
+            all_content: Map of file path to content
+        """
+        # Build symbol name set
+        all_symbols = set()
+        for file_map in file_maps.values():
+            for symbol in file_map.symbols:
+                all_symbols.add(symbol.name)
+        
+        # Count references
+        for file_path, content in all_content.items():
+            for symbol_name in all_symbols:
+                # Simple word boundary match
+                pattern = rf'\b{re.escape(symbol_name)}\b'
+                matches = len(re.findall(pattern, content))
+                if matches > 0:
+                    self.symbol_refs[symbol_name] += matches
+                    self.file_refs[file_path].add(symbol_name)
+        
+        # Update symbol reference counts
+        for file_map in file_maps.values():
+            for symbol in file_map.symbols:
+                symbol.references = self.symbol_refs.get(symbol.name, 0)
+    
+    def get_top_symbols(
+        self, file_maps: Dict[str, FileMap], max_symbols: int = 50
+    ) -> List[Symbol]:
+        """Get the most important symbols across the codebase."""
+        all_symbols = []
+        for file_map in file_maps.values():
+            all_symbols.extend(file_map.symbols)
+        
+        # Sort by references and kind priority
+        kind_priority = {"class": 3, "function": 2, "method": 1, "variable": 0}
+        
+        sorted_symbols = sorted(
+            all_symbols,
+            key=lambda s: (s.references, kind_priority.get(s.kind, 0)),
+            reverse=True
+        )
+        
+        return sorted_symbols[:max_symbols]
+
+
+# ============================================================================
+# Repository Map
+# ============================================================================
+
+class RepoMap:
+    """
+    Main class for building repository maps.
+    
+    Provides intelligent codebase context for LLM interactions.
+    """
+    
+    def __init__(
+        self,
+        root: Optional[str] = None,
+        config: Optional[RepoMapConfig] = None,
+        verbose: bool = False
+    ):
+        self.root = Path(root) if root else Path.cwd()
+        self.config = config or RepoMapConfig()
+        self.verbose = verbose
+        
+        self.extractor = SymbolExtractor()
+        self.ranker = SymbolRanker()
+        
+        self._file_maps: Dict[str, FileMap] = {}
+        self._all_content: Dict[str, str] = {}
+        self._last_map: Optional[str] = None
+    
+    def scan(self, paths: Optional[List[str]] = None) -> None:
+        """
+        Scan the repository for symbols.
+        
+        Args:
+            paths: Optional list of specific paths to scan
+        """
+        if paths:
+            files_to_scan = [Path(p) for p in paths]
+        else:
+            files_to_scan = self._find_files()
+        
+        for file_path in files_to_scan:
+            try:
+                self._scan_file(file_path)
+            except Exception as e:
+                logger.debug(f"Error scanning {file_path}: {e}")
+        
+        # Analyze references
+        self.ranker.analyze_references(self._file_maps, self._all_content)
+        
+        if self.verbose:
+            logger.info(f"Scanned {len(self._file_maps)} files")
+    
+    def _find_files(self) -> List[Path]:
+        """Find all relevant source files in the repository."""
+        files = []
+        
+        for ext in self.config.file_extensions:
+            for file_path in self.root.rglob(f"*{ext}"):
+                # Check exclusions
+                if any(excl in str(file_path) for excl in self.config.exclude_patterns):
+                    continue
+                files.append(file_path)
+        
+        return files[:self.config.max_files]
+    
+    def _scan_file(self, file_path: Path) -> None:
+        """Scan a single file for symbols."""
+        try:
+            content = file_path.read_text(encoding="utf-8", errors="ignore")
+        except Exception as e:
+            logger.debug(f"Could not read {file_path}: {e}")
+            return
+        
+        rel_path = str(file_path.relative_to(self.root))
+        self._all_content[rel_path] = content
+        
+        symbols = self.extractor.extract_symbols(rel_path, content)
+        
+        file_map = FileMap(file_path=rel_path)
+        for symbol in symbols[:self.config.max_symbols_per_file]:
+            file_map.add_symbol(symbol)
+        
+        self._file_maps[rel_path] = file_map
+    
+    def get_map(
+        self,
+        focus_files: Optional[List[str]] = None,
+        max_tokens: Optional[int] = None
+    ) -> str:
+        """
+        Get the repository map as a string.
+        
+        Args:
+            focus_files: Files to prioritize in the map
+            max_tokens: Maximum tokens for the map
+            
+        Returns:
+            Formatted repository map string
+        """
+        if not self._file_maps:
+            self.scan()
+        
+        max_tokens = max_tokens or self.config.max_tokens
+        
+        # Get top symbols
+        top_symbols = self.ranker.get_top_symbols(self._file_maps)
+        
+        # Group by file
+        file_symbols: Dict[str, List[Symbol]] = defaultdict(list)
+        for symbol in top_symbols:
+            file_symbols[symbol.file_path].append(symbol)
+        
+        # Prioritize focus files
+        if focus_files:
+            focus_set = set(focus_files)
+            sorted_files = sorted(
+                file_symbols.keys(),
+                key=lambda f: (f not in focus_set, f)
+            )
+        else:
+            sorted_files = sorted(file_symbols.keys())
+        
+        # Build map
+        lines = []
+        estimated_tokens = 0
+        
+        for file_path in sorted_files:
+            symbols = file_symbols[file_path]
+            
+            file_lines = [f"{file_path}:"]
+            for symbol in symbols:
+                if symbol.signature:
+                    file_lines.append(f"  │{symbol.signature}")
+                else:
+                    file_lines.append(f"  │{symbol.kind} {symbol.name}")
+            file_lines.append("  ⋮...")
+            
+            file_text = "\n".join(file_lines)
+            file_tokens = len(file_text) // 4  # Rough token estimate
+            
+            if estimated_tokens + file_tokens > max_tokens:
+                break
+            
+            lines.extend(file_lines)
+            estimated_tokens += file_tokens
+        
+        self._last_map = "\n".join(lines)
+        return self._last_map
+    
+    def get_file_symbols(self, file_path: str) -> List[Symbol]:
+        """Get symbols for a specific file."""
+        if file_path in self._file_maps:
+            return self._file_maps[file_path].symbols
+        return []
+    
+    def get_symbol_context(self, symbol_name: str) -> Optional[str]:
+        """Get context around a specific symbol."""
+        for file_path, file_map in self._file_maps.items():
+            for symbol in file_map.symbols:
+                if symbol.name == symbol_name:
+                    content = self._all_content.get(file_path, "")
+                    lines = content.split("\n")
+                    
+                    # Get lines around the symbol
+                    start = max(0, symbol.line_number - 3)
+                    end = min(len(lines), symbol.line_number + 10)
+                    
+                    context_lines = lines[start:end]
+                    return f"{file_path}:{symbol.line_number}\n" + "\n".join(context_lines)
+        
+        return None
+    
+    def refresh(self) -> None:
+        """Refresh the repository map."""
+        self._file_maps.clear()
+        self._all_content.clear()
+        self.ranker = SymbolRanker()
+        self.scan()
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class RepoMapHandler:
+    """
+    Handler for integrating RepoMap with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._repo_map: Optional[RepoMap] = None
+    
+    @property
+    def feature_name(self) -> str:
+        return "repo_map"
+    
+    def initialize(
+        self,
+        root: Optional[str] = None,
+        config: Optional[RepoMapConfig] = None
+    ) -> RepoMap:
+        """Initialize the repository map."""
+        self._repo_map = RepoMap(
+            root=root,
+            config=config,
+            verbose=self.verbose
+        )
+        
+        if self.verbose:
+            from rich import print as rprint
+            rprint(f"[cyan]RepoMap initialized for: {self._repo_map.root}[/cyan]")
+        
+        return self._repo_map
+    
+    def get_map(self, focus_files: Optional[List[str]] = None) -> str:
+        """Get the repository map."""
+        if not self._repo_map:
+            self._repo_map = self.initialize()
+        
+        return self._repo_map.get_map(focus_files=focus_files)
+    
+    def get_context(self, symbol_name: str) -> Optional[str]:
+        """Get context for a symbol."""
+        if not self._repo_map:
+            self._repo_map = self.initialize()
+        
+        return self._repo_map.get_symbol_context(symbol_name)
+    
+    def refresh(self) -> None:
+        """Refresh the map."""
+        if self._repo_map:
+            self._repo_map.refresh()
+    
+    def print_map(self) -> None:
+        """Print the repository map."""
+        from rich.console import Console
+        from rich.panel import Panel
+        from rich.syntax import Syntax
+        
+        console = Console()
+        map_str = self.get_map()
+        
+        console.print(Panel(
+            Syntax(map_str, "text", theme="monokai"),
+            title="📁 Repository Map",
+            border_style="blue"
+        ))
@@ -3,12 +3,45 @@ Router Handler for CLI.

 Provides smart model selection based on task complexity.
 Usage: praisonai "Complex task" --router
+
+Supports custom model configuration from agents.yaml/workflow.yaml:
+
+models:
+  gpt-4o-mini:
+    provider: openai
+    complexity: [simple, moderate]
+    cost_per_1k: 0.00075
+    capabilities: [text, function-calling]
 """

-from typing import Any, Dict, Tuple
+from typing import Any, Dict, List, Optional, Tuple
+from dataclasses import dataclass
+from enum import IntEnum
 from .base import FlagHandler


+class TaskComplexity(IntEnum):
+    """Enum for task complexity levels."""
+    SIMPLE = 1
+    MODERATE = 2
+    COMPLEX = 3
+    VERY_COMPLEX = 4
+
+
+@dataclass
+class ModelProfile:
+    """Profile for an LLM model with its characteristics."""
+    name: str
+    provider: str
+    complexity_range: Tuple[TaskComplexity, TaskComplexity]
+    cost_per_1k_tokens: float
+    capabilities: List[str]
+    context_window: int = 128000
+    supports_tools: bool = True
+    supports_streaming: bool = True
+    strengths: Optional[List[str]] = None
+
+
 class RouterHandler(FlagHandler):
    """
    Handler for --router flag.
@@ -20,13 +53,82 @@ class RouterHandler(FlagHandler):
        praisonai "Complex analysis" --router
    """
    
-    # Model tiers for routing
-    MODEL_TIERS = {
-        'simple': ['gpt-4o-mini', 'claude-3-haiku', 'gemini-1.5-flash'],
-        'medium': ['gpt-4o', 'claude-3-sonnet', 'gemini-1.5-pro'],
-        'complex': ['gpt-4-turbo', 'claude-3-opus', 'o1-preview'],
+    # Default model tiers for routing (used when no custom models configured)
+    # Note: Use full model names for API compatibility
+    DEFAULT_MODEL_TIERS = {
+        'simple': ['gpt-4o-mini', 'anthropic/claude-3-haiku-20240307', 'gemini/gemini-1.5-flash'],
+        'medium': ['gpt-4o', 'anthropic/claude-3-5-sonnet-20241022', 'gemini/gemini-1.5-pro'],
+        'complex': ['gpt-4-turbo', 'anthropic/claude-3-opus-20240229', 'o1-preview'],
    }
    
+    # Default model profiles
+    DEFAULT_MODELS: List[ModelProfile] = [
+        ModelProfile(
+            name="gpt-4o-mini",
+            provider="openai",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.00075,
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="gpt-4o",
+            provider="openai",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.COMPLEX),
+            cost_per_1k_tokens=0.0075,
+            capabilities=["text", "vision", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="anthropic/claude-3-haiku-20240307",
+            provider="anthropic",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.0008,
+            capabilities=["text", "function-calling"],
+            context_window=200000
+        ),
+        ModelProfile(
+            name="anthropic/claude-3-5-sonnet-20241022",
+            provider="anthropic",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.009,
+            capabilities=["text", "vision", "function-calling"],
+            context_window=200000,
+            strengths=["reasoning", "code-generation", "analysis"]
+        ),
+        ModelProfile(
+            name="gemini/gemini-1.5-flash",
+            provider="google",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+            cost_per_1k_tokens=0.000125,
+            capabilities=["text", "vision", "function-calling"],
+            context_window=1048576
+        ),
+        ModelProfile(
+            name="gemini/gemini-1.5-pro",
+            provider="google",
+            complexity_range=(TaskComplexity.COMPLEX, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.00625,
+            capabilities=["text", "vision", "function-calling"],
+            context_window=2097152
+        ),
+    ]
+    
+    def __init__(self, verbose: bool = False):
+        """Initialize RouterHandler with model routing support."""
+        super().__init__(verbose=verbose)
+        self._model_router: Optional[List[ModelProfile]] = None
+        self._custom_models: Dict[str, ModelProfile] = {}
+        self._cost_threshold: Optional[float] = None
+        self._model_tiers = self.DEFAULT_MODEL_TIERS.copy()
+    
+    @property
+    def model_router(self) -> List[ModelProfile]:
+        """Get the list of available model profiles."""
+        if self._model_router is None:
+            return self.DEFAULT_MODELS.copy()
+        return self._model_router
+    
    @property
    def feature_name(self) -> str:
        return "router"
@@ -94,17 +196,29 @@ class RouterHandler(FlagHandler):
            Selected model name
        """
        complexity = self.analyze_complexity(prompt)
-        models = self.MODEL_TIERS.get(complexity, self.MODEL_TIERS['medium'])
+        
+        # If custom models are loaded, use ModelProfile-based selection
+        if self._custom_models:
+            return self._select_from_profiles(prompt, complexity, preferred_provider)
+        
+        # Otherwise use tier-based selection
+        models = self._model_tiers.get(complexity, self._model_tiers['medium'])
        
        # Filter by provider if specified
        if preferred_provider:
            provider_prefixes = {
                'openai': ['gpt-', 'o1-'],
-                'anthropic': ['claude-'],
-                'google': ['gemini-']
+                'anthropic': ['anthropic/', 'claude-'],
+                'google': ['gemini/', 'gemini-']
            }
            prefixes = provider_prefixes.get(preferred_provider.lower(), [])
-            filtered = [m for m in models if any(m.startswith(p) for p in prefixes)]
+            filtered = [m for m in models if any(p in m for p in prefixes)]
+            if filtered:
+                models = filtered
+        
+        # Apply cost threshold if set
+        if self._cost_threshold:
+            filtered = [m for m in models if self.get_model_cost(m) <= self._cost_threshold]
            if filtered:
                models = filtered
        
@@ -115,6 +229,48 @@ class RouterHandler(FlagHandler):
        
        return selected
    
+    def _select_from_profiles(
+        self, 
+        prompt: str, 
+        complexity: str, 
+        preferred_provider: str = None
+    ) -> str:
+        """Select model from custom ModelProfile objects."""
+        # Map string complexity to TaskComplexity enum
+        complexity_map = {
+            'simple': TaskComplexity.SIMPLE,
+            'medium': TaskComplexity.MODERATE,
+            'complex': TaskComplexity.COMPLEX,
+        }
+        task_complexity = complexity_map.get(complexity, TaskComplexity.MODERATE)
+        
+        # Get all models that support this complexity level
+        candidates = []
+        for name, profile in self._custom_models.items():
+            min_c, max_c = profile.complexity_range
+            if min_c.value <= task_complexity.value <= max_c.value:
+                candidates.append(profile)
+        
+        if not candidates:
+            return 'gpt-4o-mini'
+        
+        # Filter by provider if specified
+        if preferred_provider:
+            filtered = [m for m in candidates if m.provider == preferred_provider]
+            if filtered:
+                candidates = filtered
+        
+        # Filter by cost threshold if set
+        if self._cost_threshold:
+            filtered = [m for m in candidates if m.cost_per_1k_tokens <= self._cost_threshold]
+            if filtered:
+                candidates = filtered
+        
+        # Sort by cost (cheapest first)
+        candidates.sort(key=lambda m: m.cost_per_1k_tokens)
+        
+        return candidates[0].name if candidates else 'gpt-4o-mini'
+    
    def apply_to_agent_config(self, config: Dict[str, Any], flag_value: Any) -> Dict[str, Any]:
        """
        Apply router configuration.
@@ -158,3 +314,153 @@ class RouterHandler(FlagHandler):
            return 'gpt-4o-mini'  # Default
        
        return self.select_model(prompt, provider)
+    
+    # =========================================================================
+    # Custom Model Configuration Methods
+    # =========================================================================
+    
+    def yaml_to_model_profile(self, name: str, config: Dict[str, Any]) -> ModelProfile:
+        """
+        Convert YAML model configuration to ModelProfile object.
+        
+        Args:
+            name: Model name
+            config: Model configuration from YAML
+            
+        Returns:
+            ModelProfile object
+        """
+        # Parse complexity strings to TaskComplexity enum
+        complexity_list = config.get('complexity', ['moderate'])
+        complexity_map = {
+            'simple': TaskComplexity.SIMPLE,
+            'moderate': TaskComplexity.MODERATE,
+            'complex': TaskComplexity.COMPLEX,
+            'very_complex': TaskComplexity.VERY_COMPLEX,
+        }
+        
+        complexities = [complexity_map.get(c.lower(), TaskComplexity.MODERATE) for c in complexity_list]
+        min_complexity = min(complexities, key=lambda x: x.value)
+        max_complexity = max(complexities, key=lambda x: x.value)
+        
+        return ModelProfile(
+            name=name,
+            provider=config.get('provider', 'unknown'),
+            complexity_range=(min_complexity, max_complexity),
+            cost_per_1k_tokens=config.get('cost_per_1k', 0.001),
+            capabilities=config.get('capabilities', ['text']),
+            context_window=config.get('context_window', 128000),
+            supports_tools=config.get('supports_tools', True),
+            supports_streaming=config.get('supports_streaming', True),
+            strengths=config.get('strengths', None)
+        )
+    
+    def load_models_from_config(
+        self, 
+        models_config: Dict[str, Dict[str, Any]], 
+        merge_with_defaults: bool = False
+    ) -> None:
+        """
+        Load custom models from YAML configuration.
+        
+        Args:
+            models_config: Dictionary of model configurations from YAML
+            merge_with_defaults: If True, merge with default models
+        """
+        # Start with defaults if merging
+        if merge_with_defaults:
+            for profile in self.DEFAULT_MODELS:
+                self._custom_models[profile.name] = profile
+        
+        # Add custom models
+        for name, config in models_config.items():
+            profile = self.yaml_to_model_profile(name, config)
+            self._custom_models[name] = profile
+        
+        # Rebuild model tiers from profiles
+        self._rebuild_model_tiers()
+    
+    def _rebuild_model_tiers(self) -> None:
+        """Rebuild MODEL_TIERS from custom model profiles."""
+        self._model_tiers = {
+            'simple': [],
+            'medium': [],
+            'complex': [],
+        }
+        
+        for name, profile in self._custom_models.items():
+            min_c, max_c = profile.complexity_range
+            
+            if min_c.value <= TaskComplexity.SIMPLE.value <= max_c.value:
+                self._model_tiers['simple'].append(name)
+            if min_c.value <= TaskComplexity.MODERATE.value <= max_c.value:
+                self._model_tiers['medium'].append(name)
+            if min_c.value <= TaskComplexity.COMPLEX.value <= max_c.value:
+                self._model_tiers['complex'].append(name)
+        
+        # Sort by cost (cheapest first)
+        for tier in self._model_tiers:
+            self._model_tiers[tier].sort(
+                key=lambda n: self._custom_models[n].cost_per_1k_tokens
+            )
+    
+    def get_available_models(self) -> List[str]:
+        """
+        Get list of available model names.
+        
+        Returns:
+            List of model names
+        """
+        if self._custom_models:
+            return list(self._custom_models.keys())
+        return [p.name for p in self.DEFAULT_MODELS]
+    
+    def get_model_cost(self, model_name: str) -> float:
+        """
+        Get cost per 1k tokens for a model.
+        
+        Args:
+            model_name: Name of the model
+            
+        Returns:
+            Cost per 1k tokens
+        """
+        # Check custom models first
+        if model_name in self._custom_models:
+            return self._custom_models[model_name].cost_per_1k_tokens
+        
+        # Check default models
+        for profile in self.DEFAULT_MODELS:
+            if profile.name == model_name:
+                return profile.cost_per_1k_tokens
+        
+        # Default cost for unknown models
+        return 0.01
+    
+    def set_cost_threshold(self, threshold: float) -> None:
+        """
+        Set maximum cost per 1k tokens for model selection.
+        
+        Args:
+            threshold: Maximum cost per 1k tokens
+        """
+        self._cost_threshold = threshold
+    
+    def get_model_profile(self, model_name: str) -> Optional[ModelProfile]:
+        """
+        Get ModelProfile for a model.
+        
+        Args:
+            model_name: Name of the model
+            
+        Returns:
+            ModelProfile or None if not found
+        """
+        if model_name in self._custom_models:
+            return self._custom_models[model_name]
+        
+        for profile in self.DEFAULT_MODELS:
+            if profile.name == model_name:
+                return profile
+        
+        return None
@@ -0,0 +1,515 @@
+"""
+Sandboxed Execution System for PraisonAI CLI.
+
+Inspired by Codex CLI's sandbox modes for secure command execution.
+Provides isolated execution environment when enabled via --sandbox flag.
+
+Architecture:
+- SandboxExecutor: Base class for sandboxed execution
+- SubprocessSandbox: Subprocess-based isolation with resource limits
+- SandboxPolicy: Configurable security policies
+
+Note: Sandbox is ONLY activated when explicitly requested via CLI flag.
+"""
+
+from dataclasses import dataclass, field
+from typing import Dict, List, Optional, Set
+from pathlib import Path
+from enum import Enum
+import subprocess
+import logging
+import tempfile
+import shutil
+import time
+
+logger = logging.getLogger(__name__)
+
+
+# ============================================================================
+# Sandbox Modes
+# ============================================================================
+
+class SandboxMode(Enum):
+    """
+    Sandbox execution modes.
+    
+    - DISABLED: No sandboxing (default)
+    - BASIC: Basic isolation with resource limits
+    - STRICT: Strict isolation with filesystem restrictions
+    - NETWORK_ISOLATED: No network access
+    """
+    DISABLED = "disabled"
+    BASIC = "basic"
+    STRICT = "strict"
+    NETWORK_ISOLATED = "network_isolated"
+    
+    @classmethod
+    def from_string(cls, value: str) -> "SandboxMode":
+        """Parse mode from string."""
+        value = value.lower().strip().replace("-", "_")
+        for mode in cls:
+            if mode.value == value:
+                return mode
+        raise ValueError(f"Unknown sandbox mode: {value}")
+
+
+# ============================================================================
+# Data Classes
+# ============================================================================
+
+@dataclass
+class SandboxPolicy:
+    """
+    Security policy for sandbox execution.
+    """
+    mode: SandboxMode = SandboxMode.DISABLED
+    
+    # Resource limits
+    max_memory_mb: int = 512
+    max_cpu_seconds: int = 30
+    max_file_size_mb: int = 10
+    max_processes: int = 10
+    
+    # Filesystem restrictions
+    allowed_paths: Set[str] = field(default_factory=set)
+    blocked_paths: Set[str] = field(default_factory=lambda: {
+        "/etc", "/var", "/usr", "/bin", "/sbin",
+        "/root", "/home", "/sys", "/proc"
+    })
+    temp_dir: Optional[str] = None
+    
+    # Network restrictions
+    allow_network: bool = True
+    allowed_hosts: Set[str] = field(default_factory=set)
+    
+    # Command restrictions
+    blocked_commands: Set[str] = field(default_factory=lambda: {
+        "rm", "rmdir", "mv", "dd", "mkfs", "fdisk",
+        "sudo", "su", "chmod", "chown", "kill", "pkill"
+    })
+    
+    @classmethod
+    def for_mode(cls, mode: SandboxMode) -> "SandboxPolicy":
+        """Create policy for a given mode."""
+        if mode == SandboxMode.DISABLED:
+            return cls(mode=mode)
+        
+        elif mode == SandboxMode.BASIC:
+            return cls(
+                mode=mode,
+                max_memory_mb=512,
+                max_cpu_seconds=60,
+                allow_network=True
+            )
+        
+        elif mode == SandboxMode.STRICT:
+            return cls(
+                mode=mode,
+                max_memory_mb=256,
+                max_cpu_seconds=30,
+                max_processes=5,
+                allow_network=True,
+                blocked_commands={
+                    "rm", "rmdir", "mv", "dd", "mkfs", "fdisk",
+                    "sudo", "su", "chmod", "chown", "kill", "pkill",
+                    "curl", "wget", "nc", "netcat", "ssh", "scp"
+                }
+            )
+        
+        elif mode == SandboxMode.NETWORK_ISOLATED:
+            return cls(
+                mode=mode,
+                max_memory_mb=512,
+                max_cpu_seconds=60,
+                allow_network=False
+            )
+        
+        return cls(mode=mode)
+
+
+@dataclass
+class ExecutionResult:
+    """Result of sandboxed execution."""
+    success: bool
+    exit_code: int
+    stdout: str
+    stderr: str
+    duration_ms: float
+    was_sandboxed: bool
+    policy_violations: List[str] = field(default_factory=list)
+    
+    @property
+    def output(self) -> str:
+        """Get combined output."""
+        return self.stdout + self.stderr
+
+
+# ============================================================================
+# Command Validator
+# ============================================================================
+
+class CommandValidator:
+    """
+    Validates commands against sandbox policy.
+    """
+    
+    def __init__(self, policy: SandboxPolicy):
+        self.policy = policy
+    
+    def validate(self, command: str) -> List[str]:
+        """
+        Validate a command against the policy.
+        
+        Returns:
+            List of policy violations (empty if valid)
+        """
+        violations = []
+        
+        if self.policy.mode == SandboxMode.DISABLED:
+            return violations
+        
+        # Parse command
+        parts = command.split()
+        if not parts:
+            return violations
+        
+        cmd_name = Path(parts[0]).name
+        
+        # Check blocked commands
+        if cmd_name in self.policy.blocked_commands:
+            violations.append(f"Command '{cmd_name}' is blocked by sandbox policy")
+        
+        # Check for dangerous patterns
+        dangerous_patterns = [
+            ("rm -rf", "Recursive force delete is blocked"),
+            ("> /dev/", "Writing to device files is blocked"),
+            ("| sh", "Piping to shell is blocked"),
+            ("| bash", "Piping to bash is blocked"),
+            ("$(", "Command substitution is blocked"),
+            ("`", "Backtick command substitution is blocked"),
+        ]
+        
+        for pattern, message in dangerous_patterns:
+            if pattern in command:
+                violations.append(message)
+        
+        # Check path access
+        for part in parts:
+            if part.startswith("/"):
+                for blocked in self.policy.blocked_paths:
+                    if part.startswith(blocked):
+                        violations.append(f"Access to '{blocked}' is blocked")
+                        break
+        
+        return violations
+    
+    def is_allowed(self, command: str) -> bool:
+        """Check if command is allowed."""
+        return len(self.validate(command)) == 0
+
+
+# ============================================================================
+# Subprocess Sandbox
+# ============================================================================
+
+class SubprocessSandbox:
+    """
+    Subprocess-based sandbox execution.
+    
+    Provides basic isolation through:
+    - Resource limits (timeout, memory via ulimit)
+    - Working directory isolation
+    - Environment variable control
+    - Command validation
+    """
+    
+    def __init__(
+        self,
+        policy: Optional[SandboxPolicy] = None,
+        working_dir: Optional[str] = None,
+        verbose: bool = False
+    ):
+        self.policy = policy or SandboxPolicy()
+        self.working_dir = Path(working_dir) if working_dir else Path.cwd()
+        self.verbose = verbose
+        self.validator = CommandValidator(self.policy)
+        
+        self._temp_dir: Optional[Path] = None
+    
+    def _setup_temp_dir(self) -> Path:
+        """Set up temporary directory for isolated execution."""
+        if self._temp_dir is None:
+            self._temp_dir = Path(tempfile.mkdtemp(prefix="praisonai_sandbox_"))
+        return self._temp_dir
+    
+    def _cleanup_temp_dir(self) -> None:
+        """Clean up temporary directory."""
+        if self._temp_dir and self._temp_dir.exists():
+            try:
+                shutil.rmtree(self._temp_dir)
+            except Exception as e:
+                logger.debug(f"Failed to cleanup temp dir: {e}")
+            self._temp_dir = None
+    
+    def _build_environment(self) -> Dict[str, str]:
+        """Build restricted environment variables."""
+        import os
+        
+        # Start with minimal environment
+        env = {
+            "PATH": "/usr/local/bin:/usr/bin:/bin",
+            "HOME": str(self._temp_dir or self.working_dir),
+            "TERM": "xterm",
+            "LANG": "en_US.UTF-8",
+        }
+        
+        # Add some safe variables from current environment
+        safe_vars = ["USER", "SHELL", "PYTHONPATH"]
+        for var in safe_vars:
+            if var in os.environ:
+                env[var] = os.environ[var]
+        
+        return env
+    
+    def execute(
+        self,
+        command: str,
+        timeout: Optional[float] = None,
+        capture_output: bool = True
+    ) -> ExecutionResult:
+        """
+        Execute a command in the sandbox.
+        
+        Args:
+            command: Command to execute
+            timeout: Timeout in seconds (overrides policy)
+            capture_output: Whether to capture stdout/stderr
+            
+        Returns:
+            ExecutionResult with execution details
+        """
+        start_time = time.time()
+        
+        # Check if sandbox is enabled
+        if self.policy.mode == SandboxMode.DISABLED:
+            return self._execute_unsandboxed(command, timeout, capture_output)
+        
+        # Validate command
+        violations = self.validator.validate(command)
+        if violations:
+            return ExecutionResult(
+                success=False,
+                exit_code=-1,
+                stdout="",
+                stderr="Command blocked by sandbox policy:\n" + "\n".join(violations),
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=True,
+                policy_violations=violations
+            )
+        
+        # Set up sandbox
+        if self.policy.mode == SandboxMode.STRICT:
+            self._setup_temp_dir()
+            cwd = self._temp_dir
+        else:
+            cwd = self.working_dir
+        
+        # Build environment
+        env = self._build_environment()
+        
+        # Set timeout
+        if timeout is None:
+            timeout = float(self.policy.max_cpu_seconds)
+        
+        # Execute
+        try:
+            result = subprocess.run(
+                command,
+                shell=True,
+                cwd=cwd,
+                env=env,
+                capture_output=capture_output,
+                text=True,
+                timeout=timeout
+            )
+            
+            return ExecutionResult(
+                success=result.returncode == 0,
+                exit_code=result.returncode,
+                stdout=result.stdout if capture_output else "",
+                stderr=result.stderr if capture_output else "",
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=True
+            )
+        
+        except subprocess.TimeoutExpired:
+            return ExecutionResult(
+                success=False,
+                exit_code=-1,
+                stdout="",
+                stderr=f"Command timed out after {timeout}s",
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=True,
+                policy_violations=["Timeout exceeded"]
+            )
+        
+        except Exception as e:
+            return ExecutionResult(
+                success=False,
+                exit_code=-1,
+                stdout="",
+                stderr=str(e),
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=True,
+                policy_violations=[str(e)]
+            )
+        
+        finally:
+            if self.policy.mode == SandboxMode.STRICT:
+                self._cleanup_temp_dir()
+    
+    def _execute_unsandboxed(
+        self,
+        command: str,
+        timeout: Optional[float],
+        capture_output: bool
+    ) -> ExecutionResult:
+        """Execute without sandbox (when disabled)."""
+        start_time = time.time()
+        
+        try:
+            result = subprocess.run(
+                command,
+                shell=True,
+                cwd=self.working_dir,
+                capture_output=capture_output,
+                text=True,
+                timeout=timeout
+            )
+            
+            return ExecutionResult(
+                success=result.returncode == 0,
+                exit_code=result.returncode,
+                stdout=result.stdout if capture_output else "",
+                stderr=result.stderr if capture_output else "",
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=False
+            )
+        
+        except subprocess.TimeoutExpired:
+            return ExecutionResult(
+                success=False,
+                exit_code=-1,
+                stdout="",
+                stderr=f"Command timed out after {timeout}s",
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=False
+            )
+        
+        except Exception as e:
+            return ExecutionResult(
+                success=False,
+                exit_code=-1,
+                stdout="",
+                stderr=str(e),
+                duration_ms=(time.time() - start_time) * 1000,
+                was_sandboxed=False
+            )
+
+
+# ============================================================================
+# CLI Integration Handler
+# ============================================================================
+
+class SandboxExecutorHandler:
+    """
+    Handler for integrating Sandbox Execution with PraisonAI CLI.
+    
+    Note: Sandbox is ONLY activated when --sandbox flag is passed.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self._sandbox: Optional[SubprocessSandbox] = None
+        self._enabled: bool = False
+    
+    @property
+    def feature_name(self) -> str:
+        return "sandbox_executor"
+    
+    @property
+    def is_enabled(self) -> bool:
+        """Check if sandbox is enabled."""
+        return self._enabled
+    
+    def initialize(
+        self,
+        mode: str = "disabled",
+        working_dir: Optional[str] = None,
+        policy: Optional[SandboxPolicy] = None
+    ) -> SubprocessSandbox:
+        """
+        Initialize the sandbox.
+        
+        Args:
+            mode: Sandbox mode (disabled, basic, strict, network_isolated)
+            working_dir: Working directory for execution
+            policy: Optional custom policy
+            
+        Returns:
+            Configured SubprocessSandbox
+        """
+        try:
+            sandbox_mode = SandboxMode.from_string(mode)
+        except ValueError:
+            logger.warning(f"Unknown sandbox mode '{mode}', defaulting to 'disabled'")
+            sandbox_mode = SandboxMode.DISABLED
+        
+        if policy is None:
+            policy = SandboxPolicy.for_mode(sandbox_mode)
+        
+        self._sandbox = SubprocessSandbox(
+            policy=policy,
+            working_dir=working_dir,
+            verbose=self.verbose
+        )
+        
+        self._enabled = sandbox_mode != SandboxMode.DISABLED
+        
+        if self.verbose and self._enabled:
+            from rich import print as rprint
+            rprint(f"[yellow]⚠ Sandbox enabled: {sandbox_mode.value}[/yellow]")
+        
+        return self._sandbox
+    
+    def get_sandbox(self) -> Optional[SubprocessSandbox]:
+        """Get the sandbox executor."""
+        return self._sandbox
+    
+    def execute(
+        self,
+        command: str,
+        timeout: Optional[float] = None
+    ) -> ExecutionResult:
+        """
+        Execute a command.
+        
+        If sandbox is not initialized, runs without sandboxing.
+        """
+        if not self._sandbox:
+            self._sandbox = self.initialize()
+        
+        return self._sandbox.execute(command, timeout=timeout)
+    
+    def validate_command(self, command: str) -> List[str]:
+        """Validate a command against sandbox policy."""
+        if not self._sandbox:
+            return []
+        
+        return self._sandbox.validator.validate(command)
+    
+    def get_mode(self) -> str:
+        """Get current sandbox mode."""
+        if self._sandbox:
+            return self._sandbox.policy.mode.value
+        return SandboxMode.DISABLED.value
@@ -0,0 +1,650 @@
+"""
+Slash Commands System for PraisonAI CLI.
+
+Inspired by Aider's command system and Gemini CLI's slash commands.
+Provides interactive commands like /help, /cost, /plan, /model, /clear, etc.
+
+Architecture:
+- SlashCommand: Base class for all commands
+- SlashCommandRegistry: Manages command registration and lookup
+- SlashCommandParser: Parses user input for slash commands
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Callable, Dict, List, Optional
+from enum import Enum
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class CommandKind(Enum):
+    """Type of slash command."""
+    BUILT_IN = "built_in"
+    CUSTOM = "custom"
+    MCP = "mcp"
+
+
+@dataclass
+class SlashCommand:
+    """
+    Represents a slash command.
+    
+    Attributes:
+        name: Primary command name (e.g., "help", "cost")
+        description: Short description for help text
+        action: Callable that executes the command
+        alt_names: Alternative names/aliases
+        sub_commands: Nested sub-commands
+        kind: Type of command (built-in, custom, MCP)
+        auto_execute: Whether to execute without confirmation
+    """
+    name: str
+    description: str
+    action: Optional[Callable[["CommandContext", str], Any]] = None
+    alt_names: List[str] = field(default_factory=list)
+    sub_commands: List["SlashCommand"] = field(default_factory=list)
+    kind: CommandKind = CommandKind.BUILT_IN
+    auto_execute: bool = True
+    
+    def __post_init__(self):
+        """Validate command after initialization."""
+        if not self.name:
+            raise ValueError("Command name cannot be empty")
+        if not self.name.isalnum() and "_" not in self.name and "-" not in self.name:
+            raise ValueError(f"Invalid command name: {self.name}")
+
+
+@dataclass
+class CommandContext:
+    """
+    Context passed to command actions.
+    
+    Contains all services and state needed by commands.
+    """
+    # Core services
+    agent: Any = None  # PraisonAI Agent instance
+    config: Dict[str, Any] = field(default_factory=dict)
+    
+    # Session state
+    session_id: Optional[str] = None
+    session_start_time: Optional[float] = None
+    
+    # Metrics
+    total_tokens: int = 0
+    total_cost: float = 0.0
+    prompt_count: int = 0
+    
+    # UI callbacks
+    print_fn: Callable[[str], None] = print
+    input_fn: Callable[[str], str] = input
+    
+    # Command invocation info
+    raw_input: str = ""
+    command_name: str = ""
+    args: str = ""
+
+
+@dataclass
+class ParsedSlashCommand:
+    """Result of parsing a slash command."""
+    command: Optional[SlashCommand] = None
+    args: str = ""
+    canonical_path: List[str] = field(default_factory=list)
+    error: Optional[str] = None
+
+
+class SlashCommandRegistry:
+    """
+    Registry for slash commands.
+    
+    Manages command registration, lookup, and help generation.
+    """
+    
+    def __init__(self):
+        self._commands: Dict[str, SlashCommand] = {}
+        self._aliases: Dict[str, str] = {}  # alias -> primary name
+    
+    def register(self, command: SlashCommand) -> None:
+        """Register a slash command."""
+        if command.name in self._commands:
+            logger.warning(f"Overwriting existing command: {command.name}")
+        
+        self._commands[command.name] = command
+        
+        # Register aliases
+        for alias in command.alt_names:
+            if alias in self._aliases:
+                logger.warning(f"Alias '{alias}' already registered")
+            self._aliases[alias] = command.name
+    
+    def unregister(self, name: str) -> bool:
+        """Unregister a command by name."""
+        if name in self._commands:
+            cmd = self._commands.pop(name)
+            # Remove aliases
+            for alias in cmd.alt_names:
+                self._aliases.pop(alias, None)
+            return True
+        return False
+    
+    def get(self, name: str) -> Optional[SlashCommand]:
+        """Get a command by name or alias."""
+        # Check primary name first
+        if name in self._commands:
+            return self._commands[name]
+        # Check aliases
+        if name in self._aliases:
+            return self._commands.get(self._aliases[name])
+        return None
+    
+    def get_all(self) -> List[SlashCommand]:
+        """Get all registered commands."""
+        return list(self._commands.values())
+    
+    def get_names(self) -> List[str]:
+        """Get all command names (including aliases)."""
+        names = list(self._commands.keys())
+        names.extend(self._aliases.keys())
+        return sorted(set(names))
+
+
+class SlashCommandParser:
+    """
+    Parser for slash commands.
+    
+    Handles parsing of user input into command and arguments.
+    """
+    
+    def __init__(self, registry: SlashCommandRegistry):
+        self.registry = registry
+    
+    def is_slash_command(self, query: str) -> bool:
+        """Check if input is a slash command."""
+        query = query.strip()
+        if not query.startswith('/'):
+            return False
+        # Exclude code comments
+        if query.startswith('//') or query.startswith('/*'):
+            return False
+        return True
+    
+    def parse(self, query: str) -> ParsedSlashCommand:
+        """
+        Parse a slash command string.
+        
+        Args:
+            query: Raw input string (e.g., "/help model" or "/cost")
+            
+        Returns:
+            ParsedSlashCommand with resolved command and arguments
+        """
+        if not self.is_slash_command(query):
+            return ParsedSlashCommand(error="Not a slash command")
+        
+        trimmed = query.strip()
+        parts = trimmed[1:].strip().split()  # Remove leading /
+        
+        if not parts:
+            return ParsedSlashCommand(error="Empty command")
+        
+        command_path = parts
+        canonical_path: List[str] = []
+        current_commands = self.registry.get_all()
+        command_to_execute: Optional[SlashCommand] = None
+        path_index = 0
+        
+        for part in command_path:
+            # First pass: exact match on primary name
+            found_command = None
+            for cmd in current_commands:
+                if cmd.name == part:
+                    found_command = cmd
+                    break
+            
+            # Second pass: check aliases
+            if not found_command:
+                for cmd in current_commands:
+                    if part in cmd.alt_names:
+                        found_command = cmd
+                        break
+            
+            if found_command:
+                command_to_execute = found_command
+                canonical_path.append(found_command.name)
+                path_index += 1
+                if found_command.sub_commands:
+                    current_commands = found_command.sub_commands
+                else:
+                    break
+            else:
+                break
+        
+        args = ' '.join(parts[path_index:])
+        
+        return ParsedSlashCommand(
+            command=command_to_execute,
+            args=args,
+            canonical_path=canonical_path
+        )
+
+
+# ============================================================================
+# Built-in Commands
+# ============================================================================
+
+def cmd_help(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show help for commands."""
+    from rich.console import Console
+    from rich.table import Table
+    
+    console = Console()
+    
+    if args:
+        # Help for specific command
+        registry = context.config.get("command_registry")
+        if registry:
+            cmd = registry.get(args)
+            if cmd:
+                console.print(f"\n[bold cyan]/{cmd.name}[/bold cyan]")
+                console.print(f"  {cmd.description}")
+                if cmd.alt_names:
+                    console.print(f"  Aliases: {', '.join(cmd.alt_names)}")
+                if cmd.sub_commands:
+                    console.print("\n  Sub-commands:")
+                    for sub in cmd.sub_commands:
+                        console.print(f"    /{cmd.name} {sub.name} - {sub.description}")
+                return {"type": "help", "command": cmd.name}
+            else:
+                console.print(f"[red]Unknown command: {args}[/red]")
+                return {"type": "error", "message": f"Unknown command: {args}"}
+    
+    # General help
+    table = Table(title="Available Commands", show_header=True)
+    table.add_column("Command", style="cyan")
+    table.add_column("Description")
+    
+    registry = context.config.get("command_registry")
+    if registry:
+        for cmd in registry.get_all():
+            aliases = f" ({', '.join(cmd.alt_names)})" if cmd.alt_names else ""
+            table.add_row(f"/{cmd.name}{aliases}", cmd.description)
+    
+    console.print(table)
+    return {"type": "help"}
+
+
+def cmd_cost(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show session cost and token usage."""
+    from rich.console import Console
+    from rich.panel import Panel
+    
+    console = Console()
+    
+    cost_info = f"""
+[bold]Session Statistics[/bold]
+
+Total Tokens: {context.total_tokens:,}
+Total Cost: ${context.total_cost:.4f}
+Prompts: {context.prompt_count}
+"""
+    
+    if context.session_start_time:
+        import time
+        duration = time.time() - context.session_start_time
+        minutes = int(duration // 60)
+        seconds = int(duration % 60)
+        cost_info += f"Duration: {minutes}m {seconds}s\n"
+    
+    console.print(Panel(cost_info, title="💰 Cost Tracker", border_style="green"))
+    
+    return {
+        "type": "stats",
+        "tokens": context.total_tokens,
+        "cost": context.total_cost,
+        "prompts": context.prompt_count
+    }
+
+
+def cmd_clear(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Clear the conversation history."""
+    from rich.console import Console
+    console = Console()
+    
+    # Reset agent conversation if available
+    if context.agent and hasattr(context.agent, 'clear_history'):
+        context.agent.clear_history()
+    
+    console.print("[green]✓ Conversation cleared[/green]")
+    return {"type": "clear"}
+
+
+def cmd_model(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show or change the current model."""
+    from rich.console import Console
+    console = Console()
+    
+    if args:
+        # Change model
+        if context.agent and hasattr(context.agent, 'set_model'):
+            context.agent.set_model(args)
+            console.print(f"[green]✓ Model changed to: {args}[/green]")
+            return {"type": "model_change", "model": args}
+        else:
+            console.print(f"[yellow]Model change requested: {args}[/yellow]")
+            return {"type": "model_change", "model": args}
+    else:
+        # Show current model
+        current_model = "unknown"
+        if context.agent and hasattr(context.agent, 'llm'):
+            current_model = getattr(context.agent.llm, 'model', 'unknown')
+        console.print(f"[cyan]Current model: {current_model}[/cyan]")
+        return {"type": "model_info", "model": current_model}
+
+
+def cmd_tokens(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show token usage breakdown."""
+    from rich.console import Console
+    from rich.table import Table
+    
+    console = Console()
+    
+    table = Table(title="Token Usage", show_header=True)
+    table.add_column("Metric", style="cyan")
+    table.add_column("Value", justify="right")
+    
+    table.add_row("Total Tokens", f"{context.total_tokens:,}")
+    table.add_row("Prompts Sent", str(context.prompt_count))
+    if context.prompt_count > 0:
+        avg = context.total_tokens / context.prompt_count
+        table.add_row("Avg Tokens/Prompt", f"{avg:.0f}")
+    
+    console.print(table)
+    return {"type": "tokens", "total": context.total_tokens}
+
+
+def cmd_plan(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show or create an execution plan."""
+    from rich.console import Console
+    console = Console()
+    
+    if args:
+        console.print(f"[cyan]Creating plan for: {args}[/cyan]")
+        # Trigger planning mode
+        return {"type": "submit_prompt", "content": f"Create a detailed plan for: {args}"}
+    else:
+        console.print("[yellow]Usage: /plan <task description>[/yellow]")
+        return {"type": "help", "command": "plan"}
+
+
+def cmd_undo(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Undo the last change."""
+    from rich.console import Console
+    console = Console()
+    
+    # Check for git integration
+    try:
+        import subprocess
+        result = subprocess.run(
+            ["git", "diff", "--stat", "HEAD~1"],
+            capture_output=True,
+            text=True,
+            cwd="."
+        )
+        if result.returncode == 0:
+            console.print("[yellow]Last commit changes:[/yellow]")
+            console.print(result.stdout)
+            console.print("\n[cyan]Run 'git reset --soft HEAD~1' to undo[/cyan]")
+        else:
+            console.print("[red]No git history available[/red]")
+    except Exception as e:
+        console.print(f"[red]Error: {e}[/red]")
+    
+    return {"type": "undo"}
+
+
+def cmd_diff(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show git diff of changes."""
+    from rich.console import Console
+    from rich.syntax import Syntax
+    
+    console = Console()
+    
+    try:
+        import subprocess
+        result = subprocess.run(
+            ["git", "diff"],
+            capture_output=True,
+            text=True,
+            cwd="."
+        )
+        if result.stdout:
+            syntax = Syntax(result.stdout, "diff", theme="monokai")
+            console.print(syntax)
+        else:
+            console.print("[green]No uncommitted changes[/green]")
+    except Exception as e:
+        console.print(f"[red]Error: {e}[/red]")
+    
+    return {"type": "diff"}
+
+
+def cmd_commit(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Commit changes with AI-generated message."""
+    from rich.console import Console
+    console = Console()
+    
+    console.print("[cyan]Generating commit message...[/cyan]")
+    
+    # This will trigger the commit command handler
+    return {"type": "commit", "message": args if args else None}
+
+
+def cmd_exit(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Exit the CLI."""
+    from rich.console import Console
+    console = Console()
+    
+    console.print("[yellow]Goodbye![/yellow]")
+    return {"type": "exit"}
+
+
+def cmd_settings(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show current settings."""
+    from rich.console import Console
+    from rich.table import Table
+    
+    console = Console()
+    
+    table = Table(title="Current Settings", show_header=True)
+    table.add_column("Setting", style="cyan")
+    table.add_column("Value")
+    
+    for key, value in context.config.items():
+        if key != "command_registry":  # Skip internal objects
+            table.add_row(key, str(value))
+    
+    console.print(table)
+    return {"type": "settings"}
+
+
+def cmd_map(context: CommandContext, args: str) -> Dict[str, Any]:
+    """Show repository map."""
+    from rich.console import Console
+    console = Console()
+    
+    console.print("[cyan]Generating repository map...[/cyan]")
+    # This will be implemented with RepoMap feature
+    return {"type": "map"}
+
+
+# ============================================================================
+# Registry Setup
+# ============================================================================
+
+def create_default_registry() -> SlashCommandRegistry:
+    """Create registry with default built-in commands."""
+    registry = SlashCommandRegistry()
+    
+    # Core commands
+    registry.register(SlashCommand(
+        name="help",
+        description="Show help for commands",
+        action=cmd_help,
+        alt_names=["h", "?"]
+    ))
+    
+    registry.register(SlashCommand(
+        name="cost",
+        description="Show session cost and token usage",
+        action=cmd_cost,
+        alt_names=["usage", "stats"]
+    ))
+    
+    registry.register(SlashCommand(
+        name="clear",
+        description="Clear conversation history",
+        action=cmd_clear,
+        alt_names=["reset"]
+    ))
+    
+    registry.register(SlashCommand(
+        name="model",
+        description="Show or change the current model",
+        action=cmd_model,
+        alt_names=["m"]
+    ))
+    
+    registry.register(SlashCommand(
+        name="tokens",
+        description="Show token usage breakdown",
+        action=cmd_tokens
+    ))
+    
+    registry.register(SlashCommand(
+        name="plan",
+        description="Create an execution plan for a task",
+        action=cmd_plan
+    ))
+    
+    registry.register(SlashCommand(
+        name="undo",
+        description="Undo the last change",
+        action=cmd_undo
+    ))
+    
+    registry.register(SlashCommand(
+        name="diff",
+        description="Show git diff of changes",
+        action=cmd_diff
+    ))
+    
+    registry.register(SlashCommand(
+        name="commit",
+        description="Commit changes with AI-generated message",
+        action=cmd_commit
+    ))
+    
+    registry.register(SlashCommand(
+        name="exit",
+        description="Exit the CLI",
+        action=cmd_exit,
+        alt_names=["quit", "q"]
+    ))
+    
+    registry.register(SlashCommand(
+        name="settings",
+        description="Show current settings",
+        action=cmd_settings
+    ))
+    
+    registry.register(SlashCommand(
+        name="map",
+        description="Show repository map",
+        action=cmd_map,
+        alt_names=["repo"]
+    ))
+    
+    return registry
+
+
+# ============================================================================
+# Handler for CLI Integration
+# ============================================================================
+
+class SlashCommandHandler:
+    """
+    Handler for integrating slash commands with PraisonAI CLI.
+    """
+    
+    def __init__(self, verbose: bool = False):
+        self.verbose = verbose
+        self.registry = create_default_registry()
+        self.parser = SlashCommandParser(self.registry)
+        self._context: Optional[CommandContext] = None
+    
+    def set_context(self, context: CommandContext) -> None:
+        """Set the command context."""
+        self._context = context
+        context.config["command_registry"] = self.registry
+    
+    def is_command(self, query: str) -> bool:
+        """Check if input is a slash command."""
+        return self.parser.is_slash_command(query)
+    
+    def execute(self, query: str) -> Optional[Dict[str, Any]]:
+        """
+        Execute a slash command.
+        
+        Returns:
+            Command result dict or None if not a command
+        """
+        if not self.is_command(query):
+            return None
+        
+        parsed = self.parser.parse(query)
+        
+        if parsed.error:
+            if self.verbose:
+                print(f"[red]Error: {parsed.error}[/red]")
+            return {"type": "error", "message": parsed.error}
+        
+        if not parsed.command:
+            return {"type": "error", "message": "Unknown command"}
+        
+        if not parsed.command.action:
+            return {"type": "error", "message": f"Command '{parsed.command.name}' has no action"}
+        
+        # Create context if not set
+        if not self._context:
+            self._context = CommandContext()
+            self._context.config["command_registry"] = self.registry
+        
+        self._context.raw_input = query
+        self._context.command_name = parsed.command.name
+        self._context.args = parsed.args
+        
+        try:
+            result = parsed.command.action(self._context, parsed.args)
+            return result
+        except Exception as e:
+            logger.error(f"Error executing command: {e}")
+            return {"type": "error", "message": str(e)}
+    
+    def register_command(self, command: SlashCommand) -> None:
+        """Register a custom command."""
+        self.registry.register(command)
+    
+    def get_completions(self, partial: str) -> List[str]:
+        """Get command completions for partial input."""
+        if not partial.startswith('/'):
+            return []
+        
+        partial_cmd = partial[1:].lower()
+        completions = []
+        
+        for name in self.registry.get_names():
+            if name.lower().startswith(partial_cmd):
+                completions.append(f"/{name}")
+        
+        return sorted(completions)
@@ -199,6 +199,73 @@ steps:
    repeat:
      until: "approved"
      max_iterations: 3
+""",
+        "model-routing": """# Model Routing Workflow
+name: Cost-Optimized Model Routing Workflow
+description: Uses custom models with automatic routing based on task complexity
+
+# Custom models configuration - define your own models with costs and capabilities
+models:
+  cheap-fast:
+    provider: openai
+    complexity: [simple]
+    cost_per_1k: 0.0001
+    capabilities: [text]
+    context_window: 16000
+  
+  balanced:
+    provider: openai
+    complexity: [moderate]
+    cost_per_1k: 0.001
+    capabilities: [text, function-calling]
+    context_window: 128000
+  
+  premium:
+    provider: anthropic
+    complexity: [complex, very_complex]
+    cost_per_1k: 0.015
+    capabilities: [text, vision, function-calling]
+    context_window: 200000
+    strengths: [reasoning, analysis, code-generation]
+
+workflow:
+  verbose: true
+  router: true  # Enable model routing
+  routing_strategy: cost-optimized  # Options: auto, cost-optimized, performance-optimized
+
+agents:
+  classifier:
+    name: Classifier
+    role: Request Classifier
+    goal: Classify incoming requests by complexity
+    instructions: "Classify the request as 'simple', 'moderate', or 'complex'."
+    llm: cheap-fast  # Always use cheap model for classification
+
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics thoroughly
+    instructions: "Research the topic and provide detailed findings."
+    llm_routing: auto  # Auto-select based on task complexity
+    llm_models: [balanced, premium]  # Models to choose from
+
+  writer:
+    name: Writer
+    role: Content Writer
+    goal: Write high-quality content
+    instructions: "Write clear, engaging content based on research."
+    llm: premium  # Always use premium for quality writing
+
+steps:
+  - agent: classifier
+    action: "Classify complexity of: {{input}}"
+    
+  - name: routing
+    route:
+      simple: [researcher]
+      moderate: [researcher]
+      complex: [researcher, writer]
+      default: [researcher]
 """
    }
    
@@ -224,7 +291,7 @@ Workflow Commands:
  praisonai workflow create --template <name>  - Create from template
  praisonai workflow auto "topic" --pattern <pattern>  - Auto-generate workflow
  
-Templates: simple, routing, parallel, loop, evaluator-optimizer
+Templates: simple, routing, parallel, loop, evaluator-optimizer, model-routing
 Patterns: sequential, routing, parallel

 Example:
@@ -610,7 +677,7 @@ Example:
            return None
        
        # Validate pattern
-        valid_patterns = ["sequential", "routing", "parallel", "loop"]
+        valid_patterns = ["sequential", "routing", "parallel", "loop", "orchestrator-workers", "evaluator-optimizer"]
        if pattern not in valid_patterns:
            self.print_status(f"Unknown pattern: {pattern}", "error")
            self.print_status(f"Valid patterns: {', '.join(valid_patterns)}", "info")
@@ -2002,7 +2002,7 @@ class PraisonAI:
            return
        
        # Validate pattern
-        valid_patterns = ["sequential", "routing", "parallel", "loop"]
+        valid_patterns = ["sequential", "routing", "parallel", "loop", "orchestrator-workers", "evaluator-optimizer"]
        if pattern not in valid_patterns:
            print(f"[red]Unknown pattern: {pattern}[/red]")
            print(f"[cyan]Valid patterns: {', '.join(valid_patterns)}[/cyan]")
@@ -57,7 +57,7 @@ class CloudDeployer:
            file.write("FROM python:3.11-slim\n")
            file.write("WORKDIR /app\n")
            file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.3.40 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.3.45 gunicorn markdown\n")
            file.write("EXPOSE 8080\n")
            file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
            
@@ -0,0 +1,56 @@
+"""
+PraisonAI Integrations - External CLI tool integrations.
+
+This module provides integrations with external AI coding CLI tools:
+- Claude Code CLI
+- Gemini CLI
+- OpenAI Codex CLI
+- Cursor CLI
+
+All integrations use lazy loading to avoid performance impact.
+
+Usage:
+    from praisonai.integrations import ClaudeCodeIntegration, GeminiCLIIntegration
+    
+    # Create integration
+    claude = ClaudeCodeIntegration(workspace="/path/to/project")
+    
+    # Use as agent tool
+    tool = claude.as_tool()
+    
+    # Or execute directly
+    result = await claude.execute("Refactor this code")
+"""
+
+# Lazy imports to avoid performance impact
+__all__ = [
+    'BaseCLIIntegration',
+    'ClaudeCodeIntegration',
+    'GeminiCLIIntegration',
+    'CodexCLIIntegration',
+    'CursorCLIIntegration',
+    'get_available_integrations',
+]
+
+
+def __getattr__(name):
+    """Lazy load integrations to minimize import overhead."""
+    if name == 'BaseCLIIntegration':
+        from .base import BaseCLIIntegration
+        return BaseCLIIntegration
+    elif name == 'ClaudeCodeIntegration':
+        from .claude_code import ClaudeCodeIntegration
+        return ClaudeCodeIntegration
+    elif name == 'GeminiCLIIntegration':
+        from .gemini_cli import GeminiCLIIntegration
+        return GeminiCLIIntegration
+    elif name == 'CodexCLIIntegration':
+        from .codex_cli import CodexCLIIntegration
+        return CodexCLIIntegration
+    elif name == 'CursorCLIIntegration':
+        from .cursor_cli import CursorCLIIntegration
+        return CursorCLIIntegration
+    elif name == 'get_available_integrations':
+        from .base import get_available_integrations
+        return get_available_integrations
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -0,0 +1,300 @@
+"""
+Base class for external CLI tool integrations.
+
+Provides a consistent interface for integrating with AI coding CLI tools
+like Claude Code, Gemini CLI, Codex CLI, and Cursor CLI.
+
+Features:
+- Lazy availability checking with caching
+- Async subprocess execution
+- Tool wrapper for agent integration
+- Timeout handling
+"""
+
+from abc import ABC, abstractmethod
+from typing import AsyncIterator, Optional, Dict, Any, Tuple, List
+import asyncio
+import shutil
+import os
+
+
+class BaseCLIIntegration(ABC):
+    """
+    Abstract base class for external CLI tool integrations.
+    
+    Provides:
+    - Lazy availability checking with class-level caching
+    - Async subprocess execution with timeout handling
+    - Tool wrapper for PraisonAI agent integration
+    
+    Subclasses must implement:
+    - cli_command property: The CLI command name
+    - execute method: Execute the CLI and return result
+    - stream method: Stream output from the CLI
+    
+    Example:
+        class MyIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "my-cli"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return await self.execute_async(["my-cli", "-p", prompt])
+            
+            async def stream(self, prompt: str, **options):
+                async for line in self.stream_async(["my-cli", "-p", prompt]):
+                    yield line
+    """
+    
+    # Class-level cache for availability checks (shared across instances)
+    _availability_cache: Dict[str, bool] = {}
+    
+    def __init__(self, workspace: str = ".", timeout: int = 300):
+        """
+        Initialize the CLI integration.
+        
+        Args:
+            workspace: Working directory for CLI execution (default: current dir)
+            timeout: Default timeout in seconds for CLI execution (default: 300)
+        """
+        self.workspace = workspace
+        self.timeout = timeout
+    
+    @property
+    @abstractmethod
+    def cli_command(self) -> str:
+        """
+        Return the CLI command name.
+        
+        This is used for availability checking and tool naming.
+        
+        Returns:
+            str: The CLI command (e.g., "claude", "gemini", "codex", "cursor-agent")
+        """
+        pass
+    
+    @property
+    def is_available(self) -> bool:
+        """
+        Check if the CLI tool is installed and available.
+        
+        Uses class-level caching to avoid repeated filesystem checks.
+        
+        Returns:
+            bool: True if the CLI is available, False otherwise
+        """
+        if self.cli_command not in self._availability_cache:
+            self._availability_cache[self.cli_command] = shutil.which(self.cli_command) is not None
+        return self._availability_cache[self.cli_command]
+    
+    @abstractmethod
+    async def execute(self, prompt: str, **options) -> str:
+        """
+        Execute the CLI tool and return the result.
+        
+        Args:
+            prompt: The prompt/query to send to the CLI
+            **options: Additional options for the CLI
+            
+        Returns:
+            str: The CLI output
+        """
+        pass
+    
+    @abstractmethod
+    async def stream(self, prompt: str, **options) -> AsyncIterator[Dict[str, Any]]:
+        """
+        Stream output from the CLI tool.
+        
+        Args:
+            prompt: The prompt/query to send to the CLI
+            **options: Additional options for the CLI
+            
+        Yields:
+            dict: Parsed output events from the CLI
+        """
+        pass
+    
+    async def execute_async(self, cmd: List[str], timeout: Optional[int] = None) -> str:
+        """
+        Execute a command asynchronously and return stdout.
+        
+        Args:
+            cmd: Command and arguments as a list
+            timeout: Timeout in seconds (uses self.timeout if not specified)
+            
+        Returns:
+            str: The command's stdout
+            
+        Raises:
+            TimeoutError: If the command times out
+        """
+        timeout = timeout or self.timeout
+        
+        proc = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
+            cwd=self.workspace
+        )
+        
+        try:
+            stdout, stderr = await asyncio.wait_for(
+                proc.communicate(),
+                timeout=timeout
+            )
+            return stdout.decode()
+        except asyncio.TimeoutError:
+            proc.kill()
+            await proc.wait()
+            raise TimeoutError(f"Command timed out after {timeout}s: {' '.join(cmd)}")
+    
+    async def execute_async_with_stderr(
+        self, 
+        cmd: List[str], 
+        timeout: Optional[int] = None
+    ) -> Tuple[str, str]:
+        """
+        Execute a command asynchronously and return both stdout and stderr.
+        
+        Args:
+            cmd: Command and arguments as a list
+            timeout: Timeout in seconds (uses self.timeout if not specified)
+            
+        Returns:
+            Tuple[str, str]: (stdout, stderr)
+            
+        Raises:
+            TimeoutError: If the command times out
+        """
+        timeout = timeout or self.timeout
+        
+        proc = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
+            cwd=self.workspace
+        )
+        
+        try:
+            stdout, stderr = await asyncio.wait_for(
+                proc.communicate(),
+                timeout=timeout
+            )
+            return stdout.decode(), stderr.decode()
+        except asyncio.TimeoutError:
+            proc.kill()
+            await proc.wait()
+            raise TimeoutError(f"Command timed out after {timeout}s: {' '.join(cmd)}")
+    
+    async def stream_async(
+        self, 
+        cmd: List[str], 
+        timeout: Optional[int] = None
+    ) -> AsyncIterator[str]:
+        """
+        Stream stdout lines from a command asynchronously.
+        
+        Args:
+            cmd: Command and arguments as a list
+            timeout: Timeout in seconds for the entire operation
+            
+        Yields:
+            str: Each line of output
+        """
+        timeout = timeout or self.timeout
+        
+        proc = await asyncio.create_subprocess_exec(
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.PIPE,
+            cwd=self.workspace
+        )
+        
+        try:
+            async def read_lines():
+                while True:
+                    line = await proc.stdout.readline()
+                    if not line:
+                        break
+                    yield line.decode().rstrip('\n')
+            
+            async for line in read_lines():
+                yield line
+                
+        except asyncio.TimeoutError:
+            proc.kill()
+            await proc.wait()
+            raise TimeoutError(f"Stream timed out after {timeout}s")
+        finally:
+            if proc.returncode is None:
+                proc.kill()
+                await proc.wait()
+    
+    def as_tool(self) -> callable:
+        """
+        Return a callable suitable for use as a PraisonAI agent tool.
+        
+        The returned function is synchronous and wraps the async execute method.
+        Uses asyncio.run() for proper event loop handling (Python 3.7+).
+        
+        Returns:
+            callable: A function that can be used as an agent tool
+        """
+        # Capture self for closure
+        integration = self
+        
+        def tool_func(query: str) -> str:
+            """Execute the CLI tool with the given query."""
+            # Use asyncio.run() for clean event loop management
+            # This creates a new event loop, runs the coroutine, and closes it
+            try:
+                # Check if we're already in an async context
+                asyncio.get_running_loop()
+                # If we're in an async context, use ThreadPoolExecutor to avoid nested loop
+                import concurrent.futures
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    future = executor.submit(asyncio.run, integration.execute(query))
+                    return future.result()
+            except RuntimeError:
+                # No running loop, safe to use asyncio.run()
+                return asyncio.run(integration.execute(query))
+        
+        # Set function metadata for agent tool registration
+        tool_func.__name__ = f"{self.cli_command}_tool"
+        tool_func.__doc__ = f"Execute {self.cli_command} for coding tasks."
+        
+        return tool_func
+    
+    def get_env(self) -> Dict[str, str]:
+        """
+        Get environment variables for CLI execution.
+        
+        Subclasses can override this to add tool-specific environment variables.
+        
+        Returns:
+            dict: Environment variables to pass to the CLI
+        """
+        return dict(os.environ)
+
+
+def get_available_integrations() -> Dict[str, bool]:
+    """
+    Get a dictionary of all integrations and their availability status.
+    
+    Returns:
+        dict: Mapping of integration name to availability (True/False)
+    """
+    from .claude_code import ClaudeCodeIntegration
+    from .gemini_cli import GeminiCLIIntegration
+    from .codex_cli import CodexCLIIntegration
+    from .cursor_cli import CursorCLIIntegration
+    
+    integrations = {
+        'claude': ClaudeCodeIntegration(),
+        'gemini': GeminiCLIIntegration(),
+        'codex': CodexCLIIntegration(),
+        'cursor': CursorCLIIntegration(),
+    }
+    
+    return {name: integration.is_available for name, integration in integrations.items()}
@@ -0,0 +1,270 @@
+"""
+Claude Code CLI Integration.
+
+Provides integration with Claude Code CLI for AI-powered coding tasks.
+
+Features:
+- Headless mode execution with JSON output
+- Session continuation support
+- System prompt customization
+- Tool restrictions
+- Optional SDK integration (when claude-agent-sdk is installed)
+
+Usage:
+    from praisonai.integrations import ClaudeCodeIntegration
+    
+    # Create integration
+    claude = ClaudeCodeIntegration(workspace="/path/to/project")
+    
+    # Execute a coding task
+    result = await claude.execute("Refactor the auth module")
+    
+    # Stream output
+    async for event in claude.stream("Add error handling"):
+        print(event)
+    
+    # Use as agent tool
+    tool = claude.as_tool()
+"""
+
+import json
+import os
+from typing import AsyncIterator, Dict, Any, Optional, List
+
+from .base import BaseCLIIntegration
+
+
+# Check if Claude Code SDK is available
+CLAUDE_SDK_AVAILABLE = False
+try:
+    from claude_agent_sdk import query as claude_query, ClaudeAgentOptions
+    CLAUDE_SDK_AVAILABLE = True
+except ImportError:
+    pass
+
+
+class ClaudeCodeIntegration(BaseCLIIntegration):
+    """
+    Integration with Claude Code CLI.
+    
+    Supports both subprocess-based execution and SDK-based execution
+    (when claude-agent-sdk is installed).
+    
+    Attributes:
+        output_format: Output format ("json", "text", "stream-json")
+        skip_permissions: Whether to skip permission prompts
+        system_prompt: Custom system prompt to append
+        allowed_tools: List of allowed tools (e.g., ["Read", "Write", "Bash"])
+        disallowed_tools: List of disallowed tools
+        use_sdk: Whether to use the SDK instead of subprocess
+    """
+    
+    def __init__(
+        self,
+        workspace: str = ".",
+        timeout: int = 300,
+        output_format: str = "json",
+        skip_permissions: bool = True,
+        system_prompt: Optional[str] = None,
+        allowed_tools: Optional[List[str]] = None,
+        disallowed_tools: Optional[List[str]] = None,
+        use_sdk: bool = False,
+        model: Optional[str] = None,
+    ):
+        """
+        Initialize Claude Code integration.
+        
+        Args:
+            workspace: Working directory for CLI execution
+            timeout: Timeout in seconds for CLI execution
+            output_format: Output format ("json", "text", "stream-json")
+            skip_permissions: Whether to skip permission prompts (--dangerously-skip-permissions)
+            system_prompt: Custom system prompt to append
+            allowed_tools: List of allowed tools
+            disallowed_tools: List of disallowed tools
+            use_sdk: Whether to use the SDK instead of subprocess
+            model: Model to use (e.g., "sonnet", "opus")
+        """
+        super().__init__(workspace=workspace, timeout=timeout)
+        
+        self.output_format = output_format
+        self.skip_permissions = skip_permissions
+        self.system_prompt = system_prompt
+        self.allowed_tools = allowed_tools
+        self.disallowed_tools = disallowed_tools
+        self.use_sdk = use_sdk and CLAUDE_SDK_AVAILABLE
+        self.model = model
+        
+        # Session management
+        self._session_active = False
+    
+    @property
+    def cli_command(self) -> str:
+        """Return the CLI command name."""
+        return "claude"
+    
+    @property
+    def sdk_available(self) -> bool:
+        """Check if the Claude Code SDK is available."""
+        return CLAUDE_SDK_AVAILABLE
+    
+    def _build_command(
+        self, 
+        prompt: str, 
+        continue_session: bool = False,
+        **options
+    ) -> List[str]:
+        """
+        Build the Claude CLI command.
+        
+        Args:
+            prompt: The prompt to send
+            continue_session: Whether to continue a previous session
+            **options: Additional options
+            
+        Returns:
+            List of command arguments
+        """
+        cmd = ["claude"]
+        
+        # Add continue flag if needed
+        if continue_session or self._session_active:
+            cmd.append("--continue")
+        
+        # Add skip permissions flag
+        if self.skip_permissions:
+            cmd.append("--dangerously-skip-permissions")
+        
+        # Add print mode flag
+        cmd.append("-p")
+        
+        # Add prompt
+        cmd.append(prompt)
+        
+        # Add output format
+        cmd.extend(["--output-format", self.output_format])
+        
+        # Add model if specified
+        if self.model:
+            cmd.extend(["--model", self.model])
+        
+        # Add system prompt if specified
+        if self.system_prompt:
+            cmd.extend(["--append-system-prompt", self.system_prompt])
+        
+        # Add allowed tools if specified
+        if self.allowed_tools:
+            cmd.extend(["--allowedTools", ",".join(self.allowed_tools)])
+        
+        # Add disallowed tools if specified
+        if self.disallowed_tools:
+            cmd.extend(["--disallowedTools", ",".join(self.disallowed_tools)])
+        
+        return cmd
+    
+    async def execute(self, prompt: str, **options) -> str:
+        """
+        Execute Claude Code CLI and return the result.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options (continue_session, etc.)
+            
+        Returns:
+            str: The CLI output (parsed from JSON if output_format is "json")
+        """
+        if self.use_sdk:
+            return await self._execute_sdk(prompt, **options)
+        
+        return await self._execute_subprocess(prompt, **options)
+    
+    async def _execute_subprocess(self, prompt: str, **options) -> str:
+        """Execute using subprocess."""
+        cmd = self._build_command(prompt, **options)
+        
+        output = await self.execute_async(cmd)
+        
+        # Mark session as active for continuation
+        self._session_active = True
+        
+        # Parse JSON output if applicable
+        if self.output_format == "json":
+            try:
+                data = json.loads(output)
+                # Extract the main result
+                if isinstance(data, dict):
+                    return data.get("result", data.get("content", str(data)))
+                return str(data)
+            except json.JSONDecodeError:
+                return output
+        
+        return output
+    
+    async def _execute_sdk(self, prompt: str, **options) -> str:
+        """Execute using the Claude Code SDK."""
+        if not CLAUDE_SDK_AVAILABLE:
+            raise RuntimeError("Claude Code SDK not available. Install with: pip install claude-agent-sdk")
+        
+        sdk_options = ClaudeAgentOptions(
+            cwd=self.workspace,
+            system_prompt=self.system_prompt,
+        )
+        
+        if self.allowed_tools:
+            sdk_options.allowed_tools = self.allowed_tools
+        
+        if self.skip_permissions:
+            sdk_options.permission_mode = 'acceptEdits'
+        
+        result_parts = []
+        async for message in claude_query(prompt=prompt, options=sdk_options):
+            if hasattr(message, 'content'):
+                for block in message.content:
+                    if hasattr(block, 'text'):
+                        result_parts.append(block.text)
+        
+        return '\n'.join(result_parts)
+    
+    async def stream(self, prompt: str, **options) -> AsyncIterator[Dict[str, Any]]:
+        """
+        Stream output from Claude Code CLI.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Yields:
+            dict: Parsed JSON events from the CLI
+        """
+        # Use stream-json format for streaming
+        original_format = self.output_format
+        self.output_format = "stream-json"
+        
+        try:
+            cmd = self._build_command(prompt, **options)
+            
+            async for line in self.stream_async(cmd):
+                if line.strip():
+                    try:
+                        event = json.loads(line)
+                        yield event
+                    except json.JSONDecodeError:
+                        yield {"type": "text", "content": line}
+        finally:
+            self.output_format = original_format
+    
+    def reset_session(self):
+        """Reset the session state."""
+        self._session_active = False
+    
+    def get_env(self) -> Dict[str, str]:
+        """Get environment variables for CLI execution."""
+        env = super().get_env()
+        
+        # Add Anthropic API key if available
+        if "ANTHROPIC_API_KEY" in os.environ:
+            env["ANTHROPIC_API_KEY"] = os.environ["ANTHROPIC_API_KEY"]
+        elif "CLAUDE_API_KEY" in os.environ:
+            env["ANTHROPIC_API_KEY"] = os.environ["CLAUDE_API_KEY"]
+        
+        return env
@@ -0,0 +1,252 @@
+"""
+OpenAI Codex CLI Integration.
+
+Provides integration with OpenAI's Codex CLI for AI-powered coding tasks.
+
+Features:
+- Non-interactive execution with `codex exec`
+- Full auto mode for file modifications
+- Sandbox modes for security
+- JSON streaming output
+- Structured output with schemas
+
+Usage:
+    from praisonai.integrations import CodexCLIIntegration
+    
+    # Create integration
+    codex = CodexCLIIntegration(workspace="/path/to/project")
+    
+    # Execute a coding task
+    result = await codex.execute("Fix the authentication bug")
+    
+    # Execute with full auto (allows file modifications)
+    codex_auto = CodexCLIIntegration(full_auto=True)
+    result = await codex_auto.execute("Refactor the module")
+    
+    # Use as agent tool
+    tool = codex.as_tool()
+"""
+
+import json
+import os
+from typing import AsyncIterator, Dict, Any, Optional, List
+
+from .base import BaseCLIIntegration
+
+
+class CodexCLIIntegration(BaseCLIIntegration):
+    """
+    Integration with OpenAI's Codex CLI.
+    
+    Attributes:
+        full_auto: Whether to allow file modifications
+        sandbox: Sandbox mode ("default", "danger-full-access")
+        json_output: Whether to use JSON streaming output
+        output_schema: Path to JSON schema for structured output
+    """
+    
+    def __init__(
+        self,
+        workspace: str = ".",
+        timeout: int = 300,
+        full_auto: bool = False,
+        sandbox: str = "default",
+        json_output: bool = False,
+        output_schema: Optional[str] = None,
+        output_file: Optional[str] = None,
+    ):
+        """
+        Initialize Codex CLI integration.
+        
+        Args:
+            workspace: Working directory for CLI execution
+            timeout: Timeout in seconds for CLI execution
+            full_auto: Whether to allow file modifications (--full-auto)
+            sandbox: Sandbox mode ("default", "danger-full-access")
+            json_output: Whether to use JSON streaming output (--json)
+            output_schema: Path to JSON schema for structured output
+            output_file: Path to save the final output (-o)
+        """
+        super().__init__(workspace=workspace, timeout=timeout)
+        
+        self.full_auto = full_auto
+        self.sandbox = sandbox
+        self.json_output = json_output
+        self.output_schema = output_schema
+        self.output_file = output_file
+    
+    @property
+    def cli_command(self) -> str:
+        """Return the CLI command name."""
+        return "codex"
+    
+    def _build_command(self, task: str, **options) -> List[str]:
+        """
+        Build the Codex CLI command.
+        
+        Args:
+            task: The task to execute
+            **options: Additional options
+            
+        Returns:
+            List of command arguments
+        """
+        cmd = ["codex", "exec"]
+        
+        # Add task
+        cmd.append(task)
+        
+        # Add full auto flag if enabled
+        if self.full_auto:
+            cmd.append("--full-auto")
+        
+        # Add sandbox mode if not default
+        if self.sandbox and self.sandbox != "default":
+            cmd.extend(["--sandbox", self.sandbox])
+        
+        # Add JSON output flag if enabled
+        if self.json_output:
+            cmd.append("--json")
+        
+        # Add output schema if specified
+        if self.output_schema:
+            cmd.extend(["--output-schema", self.output_schema])
+        
+        # Add output file if specified
+        if self.output_file:
+            cmd.extend(["-o", self.output_file])
+        
+        return cmd
+    
+    async def execute(self, prompt: str, **options) -> str:
+        """
+        Execute Codex CLI and return the result.
+        
+        Args:
+            prompt: The task/prompt to execute
+            **options: Additional options
+            
+        Returns:
+            str: The CLI output
+        """
+        cmd = self._build_command(prompt, **options)
+        
+        output = await self.execute_async(cmd)
+        
+        # Parse JSON Lines output if json_output is enabled
+        if self.json_output:
+            return self._parse_json_events(output)
+        
+        return output
+    
+    def _parse_json_events(self, output: str) -> str:
+        """
+        Parse JSON Lines output and extract the final result.
+        
+        Args:
+            output: Raw JSON Lines output
+            
+        Returns:
+            str: The extracted result
+        """
+        result_parts = []
+        
+        for line in output.strip().split('\n'):
+            if not line.strip():
+                continue
+            
+            try:
+                event = json.loads(line)
+                event_type = event.get("type", "")
+                
+                # Extract agent messages
+                if event_type == "item.completed":
+                    item = event.get("item", {})
+                    if item.get("type") == "agent_message":
+                        text = item.get("text", "")
+                        if text:
+                            result_parts.append(text)
+                
+            except json.JSONDecodeError:
+                continue
+        
+        return '\n'.join(result_parts) if result_parts else output
+    
+    async def stream(self, prompt: str, **options) -> AsyncIterator[Dict[str, Any]]:
+        """
+        Stream output from Codex CLI.
+        
+        Args:
+            prompt: The task/prompt to execute
+            **options: Additional options
+            
+        Yields:
+            dict: Parsed JSON events from the CLI
+        """
+        # Ensure JSON output is enabled for streaming
+        original_json = self.json_output
+        self.json_output = True
+        
+        try:
+            cmd = self._build_command(prompt, **options)
+            
+            async for line in self.stream_async(cmd):
+                if line.strip():
+                    try:
+                        event = json.loads(line)
+                        yield event
+                    except json.JSONDecodeError:
+                        yield {"type": "text", "content": line}
+        finally:
+            self.json_output = original_json
+    
+    async def execute_with_schema(
+        self, 
+        prompt: str, 
+        schema_path: str,
+        output_path: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """
+        Execute Codex with structured output schema.
+        
+        Args:
+            prompt: The task/prompt to execute
+            schema_path: Path to the JSON schema file
+            output_path: Optional path to save the output
+            
+        Returns:
+            dict: Parsed structured output
+        """
+        original_schema = self.output_schema
+        original_output = self.output_file
+        
+        self.output_schema = schema_path
+        if output_path:
+            self.output_file = output_path
+        
+        try:
+            cmd = self._build_command(prompt)
+            output = await self.execute_async(cmd)
+            
+            # If output file was specified, read from it
+            if output_path and os.path.exists(output_path):
+                with open(output_path, 'r') as f:
+                    return json.load(f)
+            
+            # Otherwise parse the output
+            try:
+                return json.loads(output)
+            except json.JSONDecodeError:
+                return {"result": output}
+        finally:
+            self.output_schema = original_schema
+            self.output_file = original_output
+    
+    def get_env(self) -> Dict[str, str]:
+        """Get environment variables for CLI execution."""
+        env = super().get_env()
+        
+        # Codex uses ChatGPT authentication or API key
+        # The CLI handles authentication internally
+        
+        return env
@@ -0,0 +1,192 @@
+"""
+Cursor CLI Integration.
+
+Provides integration with Cursor's CLI (cursor-agent) for AI-powered coding tasks.
+
+Features:
+- Headless mode execution with JSON output
+- Force mode for file modifications
+- Model selection
+- Session resume support
+- Streaming output with partial deltas
+
+Usage:
+    from praisonai.integrations import CursorCLIIntegration
+    
+    # Create integration
+    cursor = CursorCLIIntegration(workspace="/path/to/project")
+    
+    # Execute a coding task
+    result = await cursor.execute("Fix the authentication bug")
+    
+    # Execute with force mode (allows file modifications)
+    cursor_force = CursorCLIIntegration(force=True)
+    result = await cursor_force.execute("Refactor the module")
+    
+    # Use as agent tool
+    tool = cursor.as_tool()
+"""
+
+import json
+import os
+from typing import AsyncIterator, Dict, Any, Optional, List
+
+from .base import BaseCLIIntegration
+
+
+class CursorCLIIntegration(BaseCLIIntegration):
+    """
+    Integration with Cursor CLI (cursor-agent).
+    
+    Attributes:
+        output_format: Output format ("json", "text", "stream-json")
+        force: Whether to allow file modifications
+        model: Model to use (e.g., "gpt-5")
+        stream_partial: Whether to stream partial output
+        resume_session: Session ID to resume
+    """
+    
+    def __init__(
+        self,
+        workspace: str = ".",
+        timeout: int = 300,
+        output_format: str = "json",
+        force: bool = False,
+        model: Optional[str] = None,
+        stream_partial: bool = False,
+        resume_session: Optional[str] = None,
+    ):
+        """
+        Initialize Cursor CLI integration.
+        
+        Args:
+            workspace: Working directory for CLI execution
+            timeout: Timeout in seconds for CLI execution
+            output_format: Output format ("json", "text", "stream-json")
+            force: Whether to allow file modifications (--force)
+            model: Model to use (e.g., "gpt-5")
+            stream_partial: Whether to stream partial output (--stream-partial-output)
+            resume_session: Session ID to resume (--resume)
+        """
+        super().__init__(workspace=workspace, timeout=timeout)
+        
+        self.output_format = output_format
+        self.force = force
+        self.model = model
+        self.stream_partial = stream_partial
+        self.resume_session = resume_session
+    
+    @property
+    def cli_command(self) -> str:
+        """Return the CLI command name."""
+        return "cursor-agent"
+    
+    def _build_command(self, prompt: str, **options) -> List[str]:
+        """
+        Build the Cursor CLI command.
+        
+        Args:
+            prompt: The prompt to send
+            **options: Additional options
+            
+        Returns:
+            List of command arguments
+        """
+        cmd = ["cursor-agent"]
+        
+        # Add print mode flag
+        cmd.append("-p")
+        
+        # Add force flag if enabled
+        if self.force:
+            cmd.append("--force")
+        
+        # Add model if specified
+        if self.model:
+            cmd.extend(["-m", self.model])
+        
+        # Add output format
+        cmd.extend(["--output-format", self.output_format])
+        
+        # Add stream partial flag if enabled
+        if self.stream_partial:
+            cmd.append("--stream-partial-output")
+        
+        # Add resume session if specified
+        if self.resume_session:
+            cmd.extend(["--resume", self.resume_session])
+        
+        # Add prompt (must be last)
+        cmd.append(prompt)
+        
+        return cmd
+    
+    async def execute(self, prompt: str, **options) -> str:
+        """
+        Execute Cursor CLI and return the result.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Returns:
+            str: The CLI output (parsed from JSON if output_format is "json")
+        """
+        cmd = self._build_command(prompt, **options)
+        
+        output = await self.execute_async(cmd)
+        
+        # Parse JSON output if applicable
+        if self.output_format == "json":
+            try:
+                data = json.loads(output)
+                # Extract the main result
+                if isinstance(data, dict):
+                    return data.get("result", data.get("content", str(data)))
+                return str(data)
+            except json.JSONDecodeError:
+                return output
+        
+        return output
+    
+    async def stream(self, prompt: str, **options) -> AsyncIterator[Dict[str, Any]]:
+        """
+        Stream output from Cursor CLI.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Yields:
+            dict: Parsed JSON events from the CLI
+        """
+        # Use stream-json format for streaming
+        original_format = self.output_format
+        original_partial = self.stream_partial
+        
+        self.output_format = "stream-json"
+        self.stream_partial = True
+        
+        try:
+            cmd = self._build_command(prompt, **options)
+            
+            async for line in self.stream_async(cmd):
+                if line.strip():
+                    try:
+                        event = json.loads(line)
+                        yield event
+                    except json.JSONDecodeError:
+                        yield {"type": "text", "content": line}
+        finally:
+            self.output_format = original_format
+            self.stream_partial = original_partial
+    
+    def get_env(self) -> Dict[str, str]:
+        """Get environment variables for CLI execution."""
+        env = super().get_env()
+        
+        # Add Cursor API key if available
+        if "CURSOR_API_KEY" in os.environ:
+            env["CURSOR_API_KEY"] = os.environ["CURSOR_API_KEY"]
+        
+        return env
@@ -0,0 +1,222 @@
+"""
+Gemini CLI Integration.
+
+Provides integration with Google's Gemini CLI for AI-powered coding tasks.
+
+Features:
+- Headless mode execution with JSON output
+- Model selection (gemini-2.5-pro, gemini-2.5-flash, etc.)
+- Multi-directory context support
+- Google Search grounding
+- Usage statistics
+
+Usage:
+    from praisonai.integrations import GeminiCLIIntegration
+    
+    # Create integration
+    gemini = GeminiCLIIntegration(workspace="/path/to/project")
+    
+    # Execute a coding task
+    result = await gemini.execute("Analyze this codebase")
+    
+    # Get result with stats
+    result, stats = await gemini.execute_with_stats("Explain the architecture")
+    
+    # Use as agent tool
+    tool = gemini.as_tool()
+"""
+
+import json
+import os
+from typing import AsyncIterator, Dict, Any, Optional, List, Tuple
+
+from .base import BaseCLIIntegration
+
+
+class GeminiCLIIntegration(BaseCLIIntegration):
+    """
+    Integration with Google's Gemini CLI.
+    
+    Attributes:
+        output_format: Output format ("json", "text", "stream-json")
+        model: Gemini model to use
+        include_directories: Additional directories to include in context
+        sandbox: Whether to run in sandbox mode
+    """
+    
+    def __init__(
+        self,
+        workspace: str = ".",
+        timeout: int = 300,
+        output_format: str = "json",
+        model: str = "gemini-2.5-pro",
+        include_directories: Optional[List[str]] = None,
+        sandbox: bool = False,
+    ):
+        """
+        Initialize Gemini CLI integration.
+        
+        Args:
+            workspace: Working directory for CLI execution
+            timeout: Timeout in seconds for CLI execution
+            output_format: Output format ("json", "text", "stream-json")
+            model: Gemini model to use (e.g., "gemini-2.5-pro", "gemini-2.5-flash")
+            include_directories: Additional directories to include in context
+            sandbox: Whether to run in sandbox mode
+        """
+        super().__init__(workspace=workspace, timeout=timeout)
+        
+        self.output_format = output_format
+        self.model = model
+        self.include_directories = include_directories
+        self.sandbox = sandbox
+        
+        # Store last stats for retrieval
+        self._last_stats: Optional[Dict[str, Any]] = None
+    
+    @property
+    def cli_command(self) -> str:
+        """Return the CLI command name."""
+        return "gemini"
+    
+    def _build_command(self, prompt: str, **options) -> List[str]:
+        """
+        Build the Gemini CLI command.
+        
+        Args:
+            prompt: The prompt to send
+            **options: Additional options
+            
+        Returns:
+            List of command arguments
+        """
+        cmd = ["gemini"]
+        
+        # Add print mode flag
+        cmd.append("-p")
+        
+        # Add prompt
+        cmd.append(prompt)
+        
+        # Add model
+        cmd.extend(["-m", self.model])
+        
+        # Add output format
+        cmd.extend(["--output-format", self.output_format])
+        
+        # Add include directories if specified
+        if self.include_directories:
+            cmd.extend(["--include-directories", ",".join(self.include_directories)])
+        
+        # Add sandbox flag if enabled
+        if self.sandbox:
+            cmd.append("--sandbox")
+        
+        return cmd
+    
+    async def execute(self, prompt: str, **options) -> str:
+        """
+        Execute Gemini CLI and return the result.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Returns:
+            str: The CLI output (parsed from JSON if output_format is "json")
+        """
+        cmd = self._build_command(prompt, **options)
+        
+        output = await self.execute_async(cmd)
+        
+        # Parse JSON output if applicable
+        if self.output_format == "json":
+            try:
+                data = json.loads(output)
+                # Store stats for later retrieval
+                self._last_stats = data.get("stats")
+                # Extract the main response
+                return data.get("response", str(data))
+            except json.JSONDecodeError:
+                return output
+        
+        return output
+    
+    async def execute_with_stats(self, prompt: str, **options) -> Tuple[str, Optional[Dict[str, Any]]]:
+        """
+        Execute Gemini CLI and return both result and usage stats.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Returns:
+            Tuple[str, dict]: (result, stats) where stats contains usage information
+        """
+        # Ensure JSON format for stats
+        original_format = self.output_format
+        self.output_format = "json"
+        
+        try:
+            cmd = self._build_command(prompt, **options)
+            output = await self.execute_async(cmd)
+            
+            try:
+                data = json.loads(output)
+                response = data.get("response", str(data))
+                stats = data.get("stats")
+                return response, stats
+            except json.JSONDecodeError:
+                return output, None
+        finally:
+            self.output_format = original_format
+    
+    async def stream(self, prompt: str, **options) -> AsyncIterator[Dict[str, Any]]:
+        """
+        Stream output from Gemini CLI.
+        
+        Args:
+            prompt: The prompt/query to send
+            **options: Additional options
+            
+        Yields:
+            dict: Parsed JSON events from the CLI
+        """
+        # Use stream-json format for streaming
+        original_format = self.output_format
+        self.output_format = "stream-json"
+        
+        try:
+            cmd = self._build_command(prompt, **options)
+            
+            async for line in self.stream_async(cmd):
+                if line.strip():
+                    try:
+                        event = json.loads(line)
+                        yield event
+                    except json.JSONDecodeError:
+                        yield {"type": "text", "content": line}
+        finally:
+            self.output_format = original_format
+    
+    def get_last_stats(self) -> Optional[Dict[str, Any]]:
+        """
+        Get the stats from the last execution.
+        
+        Returns:
+            dict: Usage statistics or None if not available
+        """
+        return self._last_stats
+    
+    def get_env(self) -> Dict[str, str]:
+        """Get environment variables for CLI execution."""
+        env = super().get_env()
+        
+        # Add Google API key if available
+        if "GOOGLE_API_KEY" in os.environ:
+            env["GOOGLE_API_KEY"] = os.environ["GOOGLE_API_KEY"]
+        elif "GEMINI_API_KEY" in os.environ:
+            # Map GEMINI_API_KEY to GOOGLE_API_KEY
+            env["GOOGLE_API_KEY"] = os.environ["GEMINI_API_KEY"]
+        
+        return env
@@ -1 +1 @@
-__version__ = "2.3.40"
+__version__ = "2.3.45"
@@ -7,12 +7,12 @@
    "url": "https://github.com/MervinPraison/PraisonAI",
    "source": "github"
  },
-  "version": "2.3.39",
+  "version": "2.3.42",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "praisonai",
-      "version": "2.3.39",
+      "version": "2.3.42",
      "transport": {
        "type": "stdio"
      }
@@ -0,0 +1,309 @@
+"""
+End-to-End Tests for CLI Features with Real API Keys.
+
+These tests require actual API keys to be set in environment variables:
+- OPENAI_API_KEY
+- ANTHROPIC_API_KEY (optional)
+- GEMINI_API_KEY (optional)
+
+Run with: pytest tests/e2e/test_cli_features_e2e.py -v --tb=short
+"""
+
+import pytest
+import os
+import time
+from unittest.mock import patch
+
+# Skip all tests if no API key is available
+pytestmark = pytest.mark.skipif(
+    not os.environ.get("OPENAI_API_KEY"),
+    reason="OPENAI_API_KEY not set"
+)
+
+
+class TestSlashCommandsE2E:
+    """End-to-end tests for slash commands."""
+    
+    def test_slash_command_handler_initialization(self):
+        """Test that slash command handler initializes correctly."""
+        from praisonai.cli.features import SlashCommandHandler
+        
+        handler = SlashCommandHandler(verbose=True)
+        assert handler.registry is not None
+        assert len(handler.registry.get_all()) > 0
+    
+    def test_help_command_execution(self):
+        """Test /help command execution."""
+        from praisonai.cli.features import SlashCommandHandler
+        
+        handler = SlashCommandHandler()
+        
+        with patch('rich.console.Console.print'):
+            result = handler.execute("/help")
+        
+        assert result is not None
+        assert result["type"] == "help"
+    
+    def test_cost_command_with_context(self):
+        """Test /cost command with session context."""
+        from praisonai.cli.features.slash_commands import (
+            SlashCommandHandler,
+            CommandContext
+        )
+        
+        handler = SlashCommandHandler()
+        ctx = CommandContext(
+            total_tokens=5000,
+            total_cost=0.015,
+            prompt_count=10,
+            session_start_time=time.time() - 300
+        )
+        handler.set_context(ctx)
+        
+        with patch('rich.console.Console.print'):
+            result = handler.execute("/cost")
+        
+        assert result["type"] == "stats"
+        assert result["tokens"] == 5000
+        assert result["cost"] == 0.015
+    
+    def test_command_completions(self):
+        """Test command auto-completion."""
+        from praisonai.cli.features import SlashCommandHandler
+        
+        handler = SlashCommandHandler()
+        
+        completions = handler.get_completions("/he")
+        assert "/help" in completions
+        
+        completions = handler.get_completions("/mo")
+        assert "/model" in completions
+
+
+class TestAutonomyModeE2E:
+    """End-to-end tests for autonomy modes."""
+    
+    def test_autonomy_mode_initialization(self):
+        """Test autonomy mode handler initialization."""
+        from praisonai.cli.features import AutonomyModeHandler
+        
+        handler = AutonomyModeHandler(verbose=True)
+        manager = handler.initialize(mode="suggest")
+        
+        assert manager is not None
+        assert handler.get_mode() == "suggest"
+    
+    def test_mode_transitions(self):
+        """Test transitioning between autonomy modes."""
+        from praisonai.cli.features import AutonomyModeHandler
+        
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="suggest")
+        
+        # Test all mode transitions
+        for mode in ["suggest", "auto_edit", "full_auto"]:
+            handler.set_mode(mode)
+            assert handler.get_mode() == mode
+    
+    def test_approval_flow_suggest_mode(self):
+        """Test approval flow in suggest mode."""
+        from praisonai.cli.features.autonomy_mode import (
+            AutonomyModeHandler,
+            ActionRequest,
+            ActionType,
+            ApprovalResult
+        )
+        
+        # Mock approval callback
+        def mock_approval(action):
+            return ApprovalResult(approved=True)
+        
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="suggest", approval_callback=mock_approval)
+        
+        # File read should be auto-approved
+        read_action = ActionRequest(ActionType.FILE_READ, "Read file")
+        result = handler.request_approval(read_action)
+        assert result.approved is True
+        
+        # File write should require approval (via callback)
+        write_action = ActionRequest(ActionType.FILE_WRITE, "Write file")
+        result = handler.request_approval(write_action)
+        assert result.approved is True
+    
+    def test_full_auto_mode(self):
+        """Test full auto mode approves everything."""
+        from praisonai.cli.features.autonomy_mode import (
+            AutonomyModeHandler,
+            ActionRequest,
+            ActionType
+        )
+        
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="full_auto")
+        
+        # All actions should be auto-approved
+        actions = [
+            ActionRequest(ActionType.FILE_WRITE, "Write"),
+            ActionRequest(ActionType.SHELL_COMMAND, "Command"),
+            ActionRequest(ActionType.FILE_DELETE, "Delete"),
+        ]
+        
+        for action in actions:
+            result = handler.request_approval(action)
+            assert result.approved is True
+
+
+class TestCostTrackerE2E:
+    """End-to-end tests for cost tracking."""
+    
+    def test_cost_tracker_initialization(self):
+        """Test cost tracker initialization."""
+        from praisonai.cli.features import CostTrackerHandler
+        
+        handler = CostTrackerHandler(verbose=True)
+        tracker = handler.initialize(session_id="e2e-test")
+        
+        assert tracker is not None
+        assert tracker.session_id == "e2e-test"
+    
+    def test_track_multiple_requests(self):
+        """Test tracking multiple requests."""
+        from praisonai.cli.features import CostTrackerHandler
+        
+        handler = CostTrackerHandler()
+        handler.initialize()
+        
+        # Track several requests
+        models = ["gpt-4o", "gpt-4o-mini", "gpt-4o"]
+        for i, model in enumerate(models):
+            handler.track_request(
+                model=model,
+                input_tokens=1000 * (i + 1),
+                output_tokens=500 * (i + 1)
+            )
+        
+        assert handler.get_tokens() == 9000  # (1500 + 3000 + 4500)
+        assert handler.get_cost() > 0
+    
+    def test_cost_calculation_accuracy(self):
+        """Test cost calculation is accurate."""
+        from praisonai.cli.features.cost_tracker import CostTracker
+        
+        tracker = CostTracker()
+        
+        # gpt-4o: $2.50/1M input, $10.00/1M output
+        stats = tracker.track_request(
+            model="gpt-4o",
+            input_tokens=100_000,
+            output_tokens=50_000
+        )
+        
+        # Expected: (100K/1M * 2.50) + (50K/1M * 10.00) = 0.25 + 0.50 = 0.75
+        assert abs(stats.cost - 0.75) < 0.01
+    
+    def test_session_export(self):
+        """Test session data export."""
+        from praisonai.cli.features.cost_tracker import CostTracker
+        import json
+        
+        tracker = CostTracker(session_id="export-test")
+        tracker.track_request("gpt-4o", 1000, 500)
+        tracker.track_request("gpt-4o-mini", 2000, 1000)
+        
+        json_str = tracker.export_json()
+        data = json.loads(json_str)
+        
+        assert data["session"]["session_id"] == "export-test"
+        assert len(data["requests"]) == 2
+
+
+class TestIntegratedFeaturesE2E:
+    """End-to-end tests for integrated features."""
+    
+    def test_all_features_together(self):
+        """Test all features working together."""
+        from praisonai.cli.features import (
+            SlashCommandHandler,
+            AutonomyModeHandler,
+            CostTrackerHandler
+        )
+        from praisonai.cli.features.slash_commands import CommandContext
+        from praisonai.cli.features.autonomy_mode import (
+            ActionRequest,
+            ActionType,
+        )
+        
+        # Initialize all handlers
+        slash_handler = SlashCommandHandler()
+        autonomy_handler = AutonomyModeHandler()
+        cost_handler = CostTrackerHandler()
+        
+        # Set up autonomy mode
+        autonomy_handler.initialize(mode="auto_edit")
+        
+        # Initialize cost tracking
+        cost_handler.initialize(session_id="integrated-test")
+        
+        # Track some requests
+        cost_handler.track_request("gpt-4o", 1000, 500)
+        cost_handler.track_request("gpt-4o", 2000, 1000)
+        
+        # Set up slash command context with cost data
+        ctx = CommandContext(
+            total_tokens=cost_handler.get_tokens(),
+            total_cost=cost_handler.get_cost(),
+            prompt_count=2
+        )
+        slash_handler.set_context(ctx)
+        
+        # Execute cost command
+        with patch('rich.console.Console.print'):
+            result = slash_handler.execute("/cost")
+        
+        assert result["tokens"] == 4500
+        assert result["cost"] > 0
+        
+        # Test autonomy mode
+        write_action = ActionRequest(ActionType.FILE_WRITE, "Write file")
+        approval = autonomy_handler.request_approval(write_action)
+        assert approval.approved is True  # Auto-approved in auto_edit mode
+
+
+class TestRealAPIIntegration:
+    """Tests that use real API calls."""
+    
+    @pytest.mark.skipif(
+        not os.environ.get("OPENAI_API_KEY"),
+        reason="OPENAI_API_KEY required for this test"
+    )
+    def test_cost_tracking_with_real_agent(self):
+        """Test cost tracking with a real agent call."""
+        from praisonai.cli.features import CostTrackerHandler
+        
+        handler = CostTrackerHandler()
+        handler.initialize()
+        
+        # Simulate what would happen after an agent call
+        # In real usage, this would be called after agent.start()
+        handler.track_request(
+            model="gpt-4o-mini",
+            input_tokens=150,
+            output_tokens=50,
+            duration_ms=500.0
+        )
+        
+        summary = handler.get_summary()
+        
+        assert summary["total_requests"] == 1
+        assert summary["total_tokens"] == 200
+        assert summary["total_cost"] > 0
+        
+        # Print summary for verification
+        print("\nCost tracking test:")
+        print(f"  Tokens: {summary['total_tokens']}")
+        print(f"  Cost: ${summary['total_cost']:.6f}")
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v", "--tb=short"])
@@ -0,0 +1,182 @@
+"""
+Integration tests for AutoGenerator and WorkflowAutoGenerator.
+
+These tests require a real OpenAI API key and make actual API calls.
+Run with: OPENAI_API_KEY=your-key pytest tests/integration/test_auto_generator_integration.py -v
+"""
+
+import pytest
+import os
+import sys
+import tempfile
+import yaml
+
+# Add the source path for imports
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
+
+# Skip if no API key
+if not os.environ.get('OPENAI_API_KEY'):
+    pytest.skip("OPENAI_API_KEY not set", allow_module_level=True)
+
+try:
+    from praisonai.auto import AutoGenerator, WorkflowAutoGenerator
+except ImportError as e:
+    pytest.skip(f"Could not import required modules: {e}", allow_module_level=True)
+
+
+class TestAutoGeneratorIntegration:
+    """Integration tests for AutoGenerator with real API calls."""
+    
+    @pytest.mark.integration
+    def test_generate_agents_yaml(self):
+        """Test generating agents.yaml with real API call."""
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+            agent_file = f.name
+        
+        try:
+            generator = AutoGenerator(
+                topic="Create a simple greeting bot",
+                agent_file=agent_file,
+                framework="praisonai"
+            )
+            
+            result_path = generator.generate()
+            
+            # Verify file was created
+            assert os.path.exists(result_path)
+            
+            # Verify file content
+            with open(result_path, 'r') as f:
+                data = yaml.safe_load(f)
+            
+            # Check structure
+            assert 'framework' in data
+            assert 'topic' in data
+            assert 'roles' in data
+            assert len(data['roles']) > 0
+            
+            # Check that tools are preserved (not empty list)
+            for role_id, role_data in data['roles'].items():
+                assert 'tools' in role_data
+                # Tools should be a list (may be empty if LLM didn't suggest any)
+                assert isinstance(role_data['tools'], list)
+                
+            print(f"✓ Generated agents.yaml successfully")
+            print(f"  Roles: {list(data['roles'].keys())}")
+            
+        finally:
+            if os.path.exists(agent_file):
+                os.unlink(agent_file)
+    
+    @pytest.mark.integration
+    def test_generate_with_merge(self):
+        """Test generating and merging agents."""
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+            agent_file = f.name
+        
+        try:
+            # First generation
+            generator1 = AutoGenerator(
+                topic="Create a researcher",
+                agent_file=agent_file,
+                framework="praisonai"
+            )
+            generator1.generate()
+            
+            # Second generation with merge
+            generator2 = AutoGenerator(
+                topic="Create a writer",
+                agent_file=agent_file,
+                framework="praisonai"
+            )
+            generator2.generate(merge=True)
+            
+            # Verify merged content
+            with open(agent_file, 'r') as f:
+                data = yaml.safe_load(f)
+            
+            # Should have roles from both generations
+            assert len(data['roles']) >= 2
+            
+            print(f"✓ Merged agents.yaml successfully")
+            print(f"  Total roles: {len(data['roles'])}")
+            
+        finally:
+            if os.path.exists(agent_file):
+                os.unlink(agent_file)
+
+
+class TestWorkflowAutoGeneratorIntegration:
+    """Integration tests for WorkflowAutoGenerator with real API calls."""
+    
+    @pytest.mark.integration
+    def test_generate_sequential_workflow(self):
+        """Test generating sequential workflow."""
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+            workflow_file = f.name
+        
+        try:
+            generator = WorkflowAutoGenerator(
+                topic="Research and summarize AI news",
+                workflow_file=workflow_file
+            )
+            
+            result_path = generator.generate(pattern="sequential")
+            
+            # Verify file was created
+            assert os.path.exists(result_path)
+            
+            # Verify file content
+            with open(result_path, 'r') as f:
+                data = yaml.safe_load(f)
+            
+            # Check structure
+            assert 'name' in data
+            assert 'agents' in data
+            assert 'steps' in data
+            assert len(data['agents']) > 0
+            assert len(data['steps']) > 0
+            
+            print(f"✓ Generated sequential workflow successfully")
+            print(f"  Agents: {list(data['agents'].keys())}")
+            print(f"  Steps: {len(data['steps'])}")
+            
+        finally:
+            if os.path.exists(workflow_file):
+                os.unlink(workflow_file)
+    
+    @pytest.mark.integration
+    def test_generate_parallel_workflow(self):
+        """Test generating parallel workflow."""
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+            workflow_file = f.name
+        
+        try:
+            generator = WorkflowAutoGenerator(
+                topic="Multi-source research on climate change",
+                workflow_file=workflow_file
+            )
+            
+            result_path = generator.generate(pattern="parallel")
+            
+            # Verify file was created
+            assert os.path.exists(result_path)
+            
+            # Verify file content
+            with open(result_path, 'r') as f:
+                data = yaml.safe_load(f)
+            
+            # Check structure
+            assert 'agents' in data
+            assert 'steps' in data
+            
+            print(f"✓ Generated parallel workflow successfully")
+            print(f"  Agents: {list(data['agents'].keys())}")
+            
+        finally:
+            if os.path.exists(workflow_file):
+                os.unlink(workflow_file)
+
+
+if __name__ == '__main__':
+    pytest.main([__file__, '-v', '-m', 'integration'])
@@ -0,0 +1,271 @@
+"""
+Integration tests for CLI tool integrations.
+
+These tests require the actual CLI tools to be installed and API keys to be set.
+Run with: pytest tests/integration/test_cli_integrations.py -v
+
+Environment variables required:
+- OPENAI_API_KEY: For general testing
+- ANTHROPIC_API_KEY or CLAUDE_API_KEY: For Claude Code
+- GEMINI_API_KEY or GOOGLE_API_KEY: For Gemini CLI
+- CURSOR_API_KEY: For Cursor CLI
+"""
+
+import pytest
+import os
+import asyncio
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
+
+
+# Skip all tests if no API keys are set
+pytestmark = pytest.mark.skipif(
+    not os.environ.get("OPENAI_API_KEY"),
+    reason="OPENAI_API_KEY not set"
+)
+
+
+class TestIntegrationAvailability:
+    """Test that integrations can be imported and checked."""
+    
+    def test_import_all_integrations(self):
+        """Test importing all integrations."""
+        from praisonai.integrations import (
+            BaseCLIIntegration,
+            ClaudeCodeIntegration,
+            GeminiCLIIntegration,
+            CodexCLIIntegration,
+            CursorCLIIntegration,
+        )
+        
+        assert BaseCLIIntegration is not None
+        assert ClaudeCodeIntegration is not None
+        assert GeminiCLIIntegration is not None
+        assert CodexCLIIntegration is not None
+        assert CursorCLIIntegration is not None
+    
+    def test_get_available_integrations(self):
+        """Test getting available integrations."""
+        from praisonai.integrations import get_available_integrations
+        
+        availability = get_available_integrations()
+        
+        assert isinstance(availability, dict)
+        assert "claude" in availability
+        assert "gemini" in availability
+        assert "codex" in availability
+        assert "cursor" in availability
+        
+        print("\n📊 Integration Availability:")
+        for name, available in availability.items():
+            status = "✅" if available else "❌"
+            print(f"  {status} {name}")
+
+
+class TestClaudeCodeIntegrationReal:
+    """Real integration tests for Claude Code CLI."""
+    
+    @pytest.mark.skipif(
+        not os.environ.get("ANTHROPIC_API_KEY") and not os.environ.get("CLAUDE_API_KEY"),
+        reason="ANTHROPIC_API_KEY or CLAUDE_API_KEY not set"
+    )
+    def test_claude_integration_creation(self):
+        """Test creating Claude Code integration."""
+        from praisonai.integrations import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(
+            workspace=".",
+            output_format="json",
+            skip_permissions=True
+        )
+        
+        assert integration.cli_command == "claude"
+        print(f"\n🔧 Claude CLI available: {integration.is_available}")
+    
+    @pytest.mark.skipif(
+        not os.environ.get("ANTHROPIC_API_KEY") and not os.environ.get("CLAUDE_API_KEY"),
+        reason="ANTHROPIC_API_KEY or CLAUDE_API_KEY not set"
+    )
+    def test_claude_as_tool(self):
+        """Test Claude Code as agent tool."""
+        from praisonai.integrations import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        tool = integration.as_tool()
+        
+        assert callable(tool)
+        assert tool.__name__ == "claude_tool"
+        print(f"\n🔧 Claude tool created: {tool.__name__}")
+
+
+class TestGeminiCLIIntegrationReal:
+    """Real integration tests for Gemini CLI."""
+    
+    @pytest.mark.skipif(
+        not os.environ.get("GEMINI_API_KEY") and not os.environ.get("GOOGLE_API_KEY"),
+        reason="GEMINI_API_KEY or GOOGLE_API_KEY not set"
+    )
+    def test_gemini_integration_creation(self):
+        """Test creating Gemini CLI integration."""
+        from praisonai.integrations import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration(
+            workspace=".",
+            model="gemini-2.5-pro",
+            output_format="json"
+        )
+        
+        assert integration.cli_command == "gemini"
+        assert integration.model == "gemini-2.5-pro"
+        print(f"\n🔧 Gemini CLI available: {integration.is_available}")
+    
+    @pytest.mark.skipif(
+        not os.environ.get("GEMINI_API_KEY") and not os.environ.get("GOOGLE_API_KEY"),
+        reason="GEMINI_API_KEY or GOOGLE_API_KEY not set"
+    )
+    def test_gemini_as_tool(self):
+        """Test Gemini CLI as agent tool."""
+        from praisonai.integrations import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        tool = integration.as_tool()
+        
+        assert callable(tool)
+        assert tool.__name__ == "gemini_tool"
+        print(f"\n🔧 Gemini tool created: {tool.__name__}")
+
+
+class TestCursorCLIIntegrationReal:
+    """Real integration tests for Cursor CLI."""
+    
+    @pytest.mark.skipif(
+        not os.environ.get("CURSOR_API_KEY"),
+        reason="CURSOR_API_KEY not set"
+    )
+    def test_cursor_integration_creation(self):
+        """Test creating Cursor CLI integration."""
+        from praisonai.integrations import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(
+            workspace=".",
+            output_format="json",
+            force=False
+        )
+        
+        assert integration.cli_command == "cursor-agent"
+        print(f"\n🔧 Cursor CLI available: {integration.is_available}")
+    
+    @pytest.mark.skipif(
+        not os.environ.get("CURSOR_API_KEY"),
+        reason="CURSOR_API_KEY not set"
+    )
+    def test_cursor_as_tool(self):
+        """Test Cursor CLI as agent tool."""
+        from praisonai.integrations import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        tool = integration.as_tool()
+        
+        assert callable(tool)
+        assert tool.__name__ == "cursor-agent_tool"
+        print(f"\n🔧 Cursor tool created: {tool.__name__}")
+
+
+class TestExternalAgentsHandler:
+    """Test the ExternalAgentsHandler."""
+    
+    def test_handler_creation(self):
+        """Test creating the handler."""
+        from praisonai.cli.features import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler(verbose=True)
+        
+        assert handler.feature_name == "external_agents"
+        assert handler.flag_name == "external-agent"
+    
+    def test_handler_list_integrations(self):
+        """Test listing integrations."""
+        from praisonai.cli.features import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        integrations = handler.list_integrations()
+        
+        assert "claude" in integrations
+        assert "gemini" in integrations
+        assert "codex" in integrations
+        assert "cursor" in integrations
+        
+        print("\n📋 Available integrations:", integrations)
+    
+    def test_handler_check_availability(self):
+        """Test checking availability."""
+        from praisonai.cli.features import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        availability = handler.check_availability()
+        
+        print("\n📊 Handler Availability Check:")
+        for name, available in availability.items():
+            status = "✅" if available else "❌"
+            print(f"  {status} {name}")
+
+
+class TestPerformanceImpact:
+    """Test that integrations don't impact performance."""
+    
+    def test_lazy_loading_integrations(self):
+        """Test that integrations are lazy loaded."""
+        import time
+        
+        # Measure import time
+        start = time.time()
+        from praisonai.integrations import BaseCLIIntegration
+        import_time = time.time() - start
+        
+        print(f"\n⏱️ Import time: {import_time*1000:.2f}ms")
+        
+        # Should be fast (< 100ms)
+        assert import_time < 0.1, f"Import took too long: {import_time}s"
+    
+    def test_lazy_loading_handler(self):
+        """Test that handler is lazy loaded."""
+        import time
+        
+        # Measure import time
+        start = time.time()
+        from praisonai.cli.features import ExternalAgentsHandler
+        import_time = time.time() - start
+        
+        print(f"\n⏱️ Handler import time: {import_time*1000:.2f}ms")
+        
+        # Should be fast (< 100ms)
+        assert import_time < 0.1, f"Import took too long: {import_time}s"
+    
+    def test_availability_caching(self):
+        """Test that availability checks are cached."""
+        import time
+        from praisonai.integrations import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        
+        # First check
+        start = time.time()
+        _ = integration.is_available
+        first_time = time.time() - start
+        
+        # Second check (should be cached)
+        start = time.time()
+        _ = integration.is_available
+        second_time = time.time() - start
+        
+        print(f"\n⏱️ First availability check: {first_time*1000:.4f}ms")
+        print(f"⏱️ Second availability check: {second_time*1000:.4f}ms")
+        
+        # Both should be very fast (< 10ms) due to caching
+        assert first_time < 0.01, f"First check too slow: {first_time}s"
+        assert second_time < 0.01, f"Second check too slow: {second_time}s"
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v", "-s"])
@@ -0,0 +1,324 @@
+"""
+Real integration tests for Model Routing with actual API calls.
+
+Tests the RouterHandler with real LLM providers.
+Requires API keys: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY
+"""
+
+import pytest
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
+
+from praisonai.cli.features.router import RouterHandler
+
+
+class TestRouterHandlerReal:
+    """Real integration tests for RouterHandler."""
+    
+    def test_router_handler_initialization(self):
+        """Test RouterHandler initializes correctly."""
+        handler = RouterHandler(verbose=True)
+        
+        assert handler is not None
+        assert handler.model_router is not None
+        assert len(handler.model_router) > 0
+        print(f"✅ RouterHandler initialized with {len(handler.model_router)} default models")
+    
+    def test_complexity_analysis(self):
+        """Test complexity analysis for different prompts."""
+        handler = RouterHandler()
+        
+        # Simple prompts
+        simple_prompts = [
+            "What is 2+2?",
+            "Define photosynthesis",
+            "List the planets",
+        ]
+        
+        for prompt in simple_prompts:
+            complexity = handler.analyze_complexity(prompt)
+            print(f"  '{prompt[:30]}...' -> {complexity}")
+            assert complexity == 'simple', f"Expected 'simple' for: {prompt}"
+        
+        print("✅ Simple prompts correctly classified")
+        
+        # Complex prompts
+        complex_prompts = [
+            "Analyze and research the comprehensive impact of AI on healthcare systems globally",
+            "Compare and evaluate different machine learning architectures for natural language processing",
+        ]
+        
+        for prompt in complex_prompts:
+            complexity = handler.analyze_complexity(prompt)
+            print(f"  '{prompt[:40]}...' -> {complexity}")
+            assert complexity == 'complex', f"Expected 'complex' for: {prompt}"
+        
+        print("✅ Complex prompts correctly classified")
+    
+    def test_model_selection_by_complexity(self):
+        """Test model selection based on complexity."""
+        handler = RouterHandler(verbose=True)
+        
+        # Simple task - should select cheap model
+        simple_model = handler.select_model("What is the capital of France?")
+        print(f"Simple task model: {simple_model}")
+        assert simple_model in ['gpt-4o-mini', 'claude-3-haiku', 'gemini-1.5-flash']
+        
+        # Complex task - should select powerful model
+        complex_model = handler.select_model(
+            "Analyze and research the comprehensive impact of quantum computing on cybersecurity"
+        )
+        print(f"Complex task model: {complex_model}")
+        assert complex_model in ['gpt-4-turbo', 'claude-3-opus', 'o1-preview']
+        
+        print("✅ Model selection by complexity works correctly")
+    
+    def test_model_selection_with_provider_preference(self):
+        """Test model selection with provider preference."""
+        handler = RouterHandler(verbose=True)
+        
+        # Prefer OpenAI
+        openai_model = handler.select_model(
+            "Write a simple greeting",
+            preferred_provider='openai'
+        )
+        print(f"OpenAI preferred: {openai_model}")
+        assert 'gpt' in openai_model.lower() or 'o1' in openai_model.lower()
+        
+        # Prefer Anthropic
+        anthropic_model = handler.select_model(
+            "Write a simple greeting",
+            preferred_provider='anthropic'
+        )
+        print(f"Anthropic preferred: {anthropic_model}")
+        assert 'claude' in anthropic_model.lower()
+        
+        # Prefer Google
+        google_model = handler.select_model(
+            "Write a simple greeting",
+            preferred_provider='google'
+        )
+        print(f"Google preferred: {google_model}")
+        assert 'gemini' in google_model.lower()
+        
+        print("✅ Provider preference works correctly")
+    
+    def test_custom_models_from_yaml(self):
+        """Test loading custom models from YAML-like config."""
+        handler = RouterHandler(verbose=True)
+        
+        # Define custom models (as would be in YAML)
+        custom_models = {
+            'my-cheap-model': {
+                'provider': 'openai',
+                'complexity': ['simple'],
+                'cost_per_1k': 0.0001,
+                'capabilities': ['text']
+            },
+            'my-balanced-model': {
+                'provider': 'openai',
+                'complexity': ['moderate'],
+                'cost_per_1k': 0.001,
+                'capabilities': ['text', 'function-calling']
+            },
+            'my-premium-model': {
+                'provider': 'anthropic',
+                'complexity': ['complex', 'very_complex'],
+                'cost_per_1k': 0.015,
+                'capabilities': ['text', 'vision', 'function-calling']
+            }
+        }
+        
+        # Load custom models
+        handler.load_models_from_config(custom_models)
+        
+        # Verify models are loaded
+        available = handler.get_available_models()
+        print(f"Available models: {available}")
+        
+        assert 'my-cheap-model' in available
+        assert 'my-balanced-model' in available
+        assert 'my-premium-model' in available
+        
+        # Test selection with custom models
+        simple_model = handler.select_model("What is 2+2?")
+        print(f"Simple task -> {simple_model}")
+        assert simple_model == 'my-cheap-model'
+        
+        complex_model = handler.select_model(
+            "Analyze and research the comprehensive impact of AI"
+        )
+        print(f"Complex task -> {complex_model}")
+        assert complex_model == 'my-premium-model'
+        
+        print("✅ Custom models from YAML config work correctly")
+    
+    def test_cost_threshold(self):
+        """Test cost threshold filtering."""
+        handler = RouterHandler(verbose=True)
+        
+        # Load models with different costs
+        custom_models = {
+            'cheap': {
+                'provider': 'openai',
+                'complexity': ['simple', 'moderate', 'complex'],
+                'cost_per_1k': 0.0001,
+                'capabilities': ['text']
+            },
+            'expensive': {
+                'provider': 'anthropic',
+                'complexity': ['simple', 'moderate', 'complex'],
+                'cost_per_1k': 0.05,
+                'capabilities': ['text']
+            }
+        }
+        
+        handler.load_models_from_config(custom_models)
+        
+        # Set cost threshold
+        handler.set_cost_threshold(0.001)
+        
+        # Should only select cheap model
+        model = handler.select_model("Any task here")
+        print(f"With cost threshold 0.001: {model}")
+        assert model == 'cheap'
+        
+        # Verify cost
+        cost = handler.get_model_cost(model)
+        assert cost <= 0.001
+        
+        print("✅ Cost threshold filtering works correctly")
+    
+    def test_merge_with_defaults(self):
+        """Test merging custom models with defaults."""
+        handler = RouterHandler(verbose=True)
+        
+        custom_models = {
+            'my-custom-model': {
+                'provider': 'custom',
+                'complexity': ['moderate'],
+                'cost_per_1k': 0.002,
+                'capabilities': ['text']
+            }
+        }
+        
+        handler.load_models_from_config(custom_models, merge_with_defaults=True)
+        
+        available = handler.get_available_models()
+        print(f"Available models (merged): {available}")
+        
+        # Should have both custom and default models
+        assert 'my-custom-model' in available
+        assert 'gpt-4o-mini' in available
+        
+        print("✅ Merge with defaults works correctly")
+
+
+class TestRealAPIIntegration:
+    """Tests that make real API calls - requires API keys."""
+    
+    @pytest.mark.skipif(
+        not os.getenv('OPENAI_API_KEY'),
+        reason="OPENAI_API_KEY not set"
+    )
+    def test_real_openai_call(self):
+        """Test real OpenAI API call with routed model."""
+        from praisonaiagents import Agent
+        
+        handler = RouterHandler(verbose=True)
+        
+        # Select model for simple task
+        model = handler.select_model(
+            "What is 2+2?",
+            preferred_provider='openai'
+        )
+        print(f"Selected model: {model}")
+        
+        # Create agent with selected model
+        agent = Agent(
+            name="TestAgent",
+            role="Calculator",
+            goal="Answer simple math questions",
+            llm=model,
+            verbose=True
+        )
+        
+        # Run simple task
+        result = agent.start("What is 2+2? Answer with just the number.")
+        print(f"Result: {result}")
+        
+        assert '4' in str(result)
+        print("✅ Real OpenAI API call successful")
+    
+    @pytest.mark.skipif(
+        not os.getenv('ANTHROPIC_API_KEY'),
+        reason="ANTHROPIC_API_KEY not set"
+    )
+    def test_real_anthropic_call(self):
+        """Test real Anthropic API call with routed model."""
+        from praisonaiagents import Agent
+        
+        handler = RouterHandler(verbose=True)
+        
+        # Select Anthropic model
+        model = handler.select_model(
+            "What is the capital of France?",
+            preferred_provider='anthropic'
+        )
+        print(f"Selected model: {model}")
+        
+        # Create agent with selected model
+        agent = Agent(
+            name="TestAgent",
+            role="Geography Expert",
+            goal="Answer geography questions",
+            llm=model,
+            verbose=True
+        )
+        
+        # Run task
+        result = agent.start("What is the capital of France? Answer with just the city name.")
+        print(f"Result: {result}")
+        
+        assert 'paris' in str(result).lower()
+        print("✅ Real Anthropic API call successful")
+    
+    @pytest.mark.skipif(
+        not os.getenv('GEMINI_API_KEY'),
+        reason="GEMINI_API_KEY not set"
+    )
+    def test_real_gemini_call(self):
+        """Test real Gemini API call with routed model."""
+        from praisonaiagents import Agent
+        
+        handler = RouterHandler(verbose=True)
+        
+        # Select Google model
+        model = handler.select_model(
+            "What is 3 times 7?",
+            preferred_provider='google'
+        )
+        print(f"Selected model: {model}")
+        
+        # Create agent with selected model
+        agent = Agent(
+            name="TestAgent",
+            role="Calculator",
+            goal="Answer math questions",
+            llm=f"gemini/{model}" if not model.startswith("gemini/") else model,
+            verbose=True
+        )
+        
+        # Run task
+        result = agent.start("What is 3 times 7? Answer with just the number.")
+        print(f"Result: {result}")
+        
+        assert '21' in str(result)
+        print("✅ Real Gemini API call successful")
+
+
+if __name__ == '__main__':
+    # Run tests
+    pytest.main([__file__, '-v', '-s'])
@@ -0,0 +1,590 @@
+"""
+Tests for Autonomy Mode System.
+
+Test-Driven Development approach for autonomy/approval modes.
+"""
+
+import pytest
+from unittest.mock import MagicMock
+
+from praisonai.cli.features.autonomy_mode import (
+    AutonomyMode,
+    ActionType,
+    ActionRequest,
+    ApprovalResult,
+    AutonomyPolicy,
+    AutonomyManager,
+    AutonomyModeHandler,
+    create_file_write_action,
+    create_shell_command_action,
+    create_git_action,
+    create_tool_call_action,
+)
+
+
+# ============================================================================
+# AutonomyMode Tests
+# ============================================================================
+
+class TestAutonomyMode:
+    """Tests for AutonomyMode enum."""
+    
+    def test_mode_values(self):
+        """Test mode enum values."""
+        assert AutonomyMode.SUGGEST.value == "suggest"
+        assert AutonomyMode.AUTO_EDIT.value == "auto_edit"
+        assert AutonomyMode.FULL_AUTO.value == "full_auto"
+    
+    def test_from_string_valid(self):
+        """Test parsing valid mode strings."""
+        assert AutonomyMode.from_string("suggest") == AutonomyMode.SUGGEST
+        assert AutonomyMode.from_string("auto_edit") == AutonomyMode.AUTO_EDIT
+        assert AutonomyMode.from_string("full_auto") == AutonomyMode.FULL_AUTO
+    
+    def test_from_string_with_hyphen(self):
+        """Test parsing mode strings with hyphens."""
+        assert AutonomyMode.from_string("auto-edit") == AutonomyMode.AUTO_EDIT
+        assert AutonomyMode.from_string("full-auto") == AutonomyMode.FULL_AUTO
+    
+    def test_from_string_case_insensitive(self):
+        """Test case insensitive parsing."""
+        assert AutonomyMode.from_string("SUGGEST") == AutonomyMode.SUGGEST
+        assert AutonomyMode.from_string("Auto_Edit") == AutonomyMode.AUTO_EDIT
+    
+    def test_from_string_invalid(self):
+        """Test parsing invalid mode string."""
+        with pytest.raises(ValueError, match="Unknown autonomy mode"):
+            AutonomyMode.from_string("invalid_mode")
+
+
+# ============================================================================
+# ActionType Tests
+# ============================================================================
+
+class TestActionType:
+    """Tests for ActionType enum."""
+    
+    def test_action_types_exist(self):
+        """Test all action types exist."""
+        assert ActionType.FILE_READ.value == "file_read"
+        assert ActionType.FILE_WRITE.value == "file_write"
+        assert ActionType.FILE_DELETE.value == "file_delete"
+        assert ActionType.SHELL_COMMAND.value == "shell_command"
+        assert ActionType.NETWORK_REQUEST.value == "network_request"
+        assert ActionType.CODE_EXECUTION.value == "code_execution"
+        assert ActionType.GIT_OPERATION.value == "git_operation"
+        assert ActionType.TOOL_CALL.value == "tool_call"
+
+
+# ============================================================================
+# ActionRequest Tests
+# ============================================================================
+
+class TestActionRequest:
+    """Tests for ActionRequest dataclass."""
+    
+    def test_create_basic_action(self):
+        """Test creating a basic action request."""
+        action = ActionRequest(
+            action_type=ActionType.FILE_WRITE,
+            description="Write to config.py"
+        )
+        assert action.action_type == ActionType.FILE_WRITE
+        assert action.description == "Write to config.py"
+        assert action.details == {}
+        assert action.risk_level == "medium"
+        assert action.reversible is True
+    
+    def test_create_action_with_details(self):
+        """Test creating action with details."""
+        action = ActionRequest(
+            action_type=ActionType.SHELL_COMMAND,
+            description="Run tests",
+            details={"command": "pytest", "cwd": "/project"},
+            risk_level="low",
+            reversible=False
+        )
+        assert action.details["command"] == "pytest"
+        assert action.risk_level == "low"
+        assert action.reversible is False
+    
+    def test_action_str(self):
+        """Test action string representation."""
+        action = ActionRequest(
+            action_type=ActionType.FILE_WRITE,
+            description="Write to file.py"
+        )
+        assert "file_write" in str(action)
+        assert "Write to file.py" in str(action)
+
+
+# ============================================================================
+# ApprovalResult Tests
+# ============================================================================
+
+class TestApprovalResult:
+    """Tests for ApprovalResult dataclass."""
+    
+    def test_approved_result(self):
+        """Test approved result."""
+        result = ApprovalResult(approved=True)
+        assert result.approved is True
+        assert result.reason is None
+        assert result.remember_choice is False
+    
+    def test_denied_result_with_reason(self):
+        """Test denied result with reason."""
+        result = ApprovalResult(
+            approved=False,
+            reason="User denied the action"
+        )
+        assert result.approved is False
+        assert result.reason == "User denied the action"
+    
+    def test_result_with_remember(self):
+        """Test result with remember choice."""
+        result = ApprovalResult(
+            approved=True,
+            remember_choice=True
+        )
+        assert result.remember_choice is True
+
+
+# ============================================================================
+# AutonomyPolicy Tests
+# ============================================================================
+
+class TestAutonomyPolicy:
+    """Tests for AutonomyPolicy."""
+    
+    def test_suggest_mode_policy(self):
+        """Test policy for suggest mode."""
+        policy = AutonomyPolicy.for_mode(AutonomyMode.SUGGEST)
+        
+        assert policy.mode == AutonomyMode.SUGGEST
+        assert ActionType.FILE_READ in policy.auto_approve
+        assert ActionType.FILE_WRITE in policy.require_approval
+        assert ActionType.SHELL_COMMAND in policy.require_approval
+        assert policy.show_preview is True
+    
+    def test_auto_edit_mode_policy(self):
+        """Test policy for auto-edit mode."""
+        policy = AutonomyPolicy.for_mode(AutonomyMode.AUTO_EDIT)
+        
+        assert policy.mode == AutonomyMode.AUTO_EDIT
+        assert ActionType.FILE_READ in policy.auto_approve
+        assert ActionType.FILE_WRITE in policy.auto_approve
+        assert ActionType.SHELL_COMMAND in policy.require_approval
+        assert ActionType.FILE_DELETE in policy.require_approval
+    
+    def test_full_auto_mode_policy(self):
+        """Test policy for full-auto mode."""
+        policy = AutonomyPolicy.for_mode(AutonomyMode.FULL_AUTO)
+        
+        assert policy.mode == AutonomyMode.FULL_AUTO
+        assert ActionType.FILE_WRITE in policy.auto_approve
+        assert ActionType.SHELL_COMMAND in policy.auto_approve
+        assert ActionType.FILE_DELETE in policy.auto_approve
+        assert len(policy.require_approval) == 0
+        assert policy.max_auto_actions == 100
+    
+    def test_custom_policy(self):
+        """Test creating custom policy."""
+        policy = AutonomyPolicy(
+            mode=AutonomyMode.SUGGEST,
+            auto_approve={ActionType.FILE_READ, ActionType.TOOL_CALL},
+            blocked={ActionType.FILE_DELETE},
+            trusted_paths={"/safe/path"}
+        )
+        
+        assert ActionType.TOOL_CALL in policy.auto_approve
+        assert ActionType.FILE_DELETE in policy.blocked
+        assert "/safe/path" in policy.trusted_paths
+
+
+# ============================================================================
+# AutonomyManager Tests
+# ============================================================================
+
+class TestAutonomyManager:
+    """Tests for AutonomyManager."""
+    
+    def test_create_manager_default(self):
+        """Test creating manager with defaults."""
+        manager = AutonomyManager()
+        
+        assert manager.mode == AutonomyMode.SUGGEST
+        assert manager.policy is not None
+    
+    def test_create_manager_with_mode(self):
+        """Test creating manager with specific mode."""
+        manager = AutonomyManager(mode=AutonomyMode.FULL_AUTO)
+        
+        assert manager.mode == AutonomyMode.FULL_AUTO
+    
+    def test_set_mode(self):
+        """Test changing mode."""
+        manager = AutonomyManager(mode=AutonomyMode.SUGGEST)
+        manager.set_mode(AutonomyMode.AUTO_EDIT)
+        
+        assert manager.mode == AutonomyMode.AUTO_EDIT
+    
+    def test_auto_approve_file_read(self):
+        """Test auto-approval of file read in suggest mode."""
+        manager = AutonomyManager(mode=AutonomyMode.SUGGEST)
+        
+        action = ActionRequest(
+            action_type=ActionType.FILE_READ,
+            description="Read config.py"
+        )
+        
+        result = manager.request_approval(action)
+        
+        assert result.approved is True
+        assert "Auto-approved" in result.reason
+    
+    def test_require_approval_file_write_suggest(self):
+        """Test file write requires approval in suggest mode."""
+        # Mock the approval callback
+        mock_callback = MagicMock(return_value=ApprovalResult(approved=True))
+        manager = AutonomyManager(
+            mode=AutonomyMode.SUGGEST,
+            approval_callback=mock_callback
+        )
+        
+        action = ActionRequest(
+            action_type=ActionType.FILE_WRITE,
+            description="Write to config.py"
+        )
+        
+        result = manager.request_approval(action)
+        
+        assert result.approved is True
+        mock_callback.assert_called_once()
+    
+    def test_auto_approve_file_write_auto_edit(self):
+        """Test file write is auto-approved in auto-edit mode."""
+        manager = AutonomyManager(mode=AutonomyMode.AUTO_EDIT)
+        
+        action = ActionRequest(
+            action_type=ActionType.FILE_WRITE,
+            description="Write to config.py"
+        )
+        
+        result = manager.request_approval(action)
+        
+        assert result.approved is True
+        assert "Auto-approved" in result.reason
+    
+    def test_auto_approve_everything_full_auto(self):
+        """Test everything is auto-approved in full-auto mode."""
+        manager = AutonomyManager(mode=AutonomyMode.FULL_AUTO)
+        
+        actions = [
+            ActionRequest(ActionType.FILE_WRITE, "Write file"),
+            ActionRequest(ActionType.SHELL_COMMAND, "Run command"),
+            ActionRequest(ActionType.FILE_DELETE, "Delete file"),
+        ]
+        
+        for action in actions:
+            result = manager.request_approval(action)
+            assert result.approved is True
+    
+    def test_blocked_action(self):
+        """Test blocked action is denied."""
+        policy = AutonomyPolicy(
+            mode=AutonomyMode.SUGGEST,
+            blocked={ActionType.FILE_DELETE}
+        )
+        manager = AutonomyManager(mode=AutonomyMode.SUGGEST, policy=policy)
+        
+        action = ActionRequest(
+            action_type=ActionType.FILE_DELETE,
+            description="Delete important file"
+        )
+        
+        result = manager.request_approval(action)
+        
+        assert result.approved is False
+        assert "blocked" in result.reason.lower()
+    
+    def test_remember_approval(self):
+        """Test remembered approval decisions."""
+        mock_callback = MagicMock(return_value=ApprovalResult(
+            approved=True,
+            remember_choice=True
+        ))
+        manager = AutonomyManager(
+            mode=AutonomyMode.SUGGEST,
+            approval_callback=mock_callback
+        )
+        
+        action = ActionRequest(
+            action_type=ActionType.FILE_WRITE,
+            description="Write to config.py",
+            details={"path": "/project/config.py"}
+        )
+        
+        # First request - should call callback
+        result1 = manager.request_approval(action)
+        assert result1.approved is True
+        assert mock_callback.call_count == 1
+        
+        # Second request - should use remembered choice
+        result2 = manager.request_approval(action)
+        assert result2.approved is True
+        assert mock_callback.call_count == 1  # Not called again
+    
+    def test_max_auto_actions(self):
+        """Test max auto actions limit."""
+        mock_callback = MagicMock(return_value=ApprovalResult(approved=True))
+        policy = AutonomyPolicy(
+            mode=AutonomyMode.SUGGEST,
+            auto_approve={ActionType.FILE_READ},
+            max_auto_actions=3
+        )
+        manager = AutonomyManager(
+            mode=AutonomyMode.SUGGEST,
+            policy=policy,
+            approval_callback=mock_callback
+        )
+        
+        action = ActionRequest(ActionType.FILE_READ, "Read file")
+        
+        # First 3 should be auto-approved
+        for _ in range(3):
+            result = manager.request_approval(action)
+            assert result.approved is True
+        
+        # 4th should require approval (callback called)
+        result = manager.request_approval(action)
+        assert mock_callback.call_count == 1
+    
+    def test_get_stats(self):
+        """Test getting approval statistics."""
+        manager = AutonomyManager(mode=AutonomyMode.FULL_AUTO)
+        
+        # Perform some actions
+        manager.request_approval(ActionRequest(ActionType.FILE_READ, "Read"))
+        manager.request_approval(ActionRequest(ActionType.FILE_WRITE, "Write"))
+        
+        stats = manager.get_stats()
+        
+        assert stats["total_actions"] == 2
+        assert stats["auto_approved"] == 2
+        assert stats["denied"] == 0
+    
+    def test_reset_stats(self):
+        """Test resetting statistics."""
+        manager = AutonomyManager(mode=AutonomyMode.FULL_AUTO)
+        
+        manager.request_approval(ActionRequest(ActionType.FILE_READ, "Read"))
+        manager.reset_stats()
+        
+        stats = manager.get_stats()
+        assert stats["total_actions"] == 0
+    
+    def test_clear_remembered(self):
+        """Test clearing remembered approvals."""
+        mock_callback = MagicMock(return_value=ApprovalResult(
+            approved=True,
+            remember_choice=True
+        ))
+        manager = AutonomyManager(
+            mode=AutonomyMode.SUGGEST,
+            approval_callback=mock_callback
+        )
+        
+        action = ActionRequest(ActionType.FILE_WRITE, "Write", details={"path": "/a"})
+        
+        # Remember approval
+        manager.request_approval(action)
+        assert mock_callback.call_count == 1
+        
+        # Clear remembered
+        manager.clear_remembered()
+        
+        # Should call callback again
+        manager.request_approval(action)
+        assert mock_callback.call_count == 2
+
+
+# ============================================================================
+# AutonomyModeHandler Tests
+# ============================================================================
+
+class TestAutonomyModeHandler:
+    """Tests for AutonomyModeHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = AutonomyModeHandler()
+        assert handler.feature_name == "autonomy_mode"
+    
+    def test_initialize_default(self):
+        """Test initializing with defaults."""
+        handler = AutonomyModeHandler()
+        manager = handler.initialize()
+        
+        assert manager is not None
+        assert manager.mode == AutonomyMode.SUGGEST
+    
+    def test_initialize_with_mode(self):
+        """Test initializing with specific mode."""
+        handler = AutonomyModeHandler()
+        manager = handler.initialize(mode="full_auto")
+        
+        assert manager.mode == AutonomyMode.FULL_AUTO
+    
+    def test_initialize_invalid_mode(self):
+        """Test initializing with invalid mode falls back to suggest."""
+        handler = AutonomyModeHandler()
+        manager = handler.initialize(mode="invalid_mode")
+        
+        assert manager.mode == AutonomyMode.SUGGEST
+    
+    def test_get_manager(self):
+        """Test getting manager."""
+        handler = AutonomyModeHandler()
+        
+        assert handler.get_manager() is None
+        
+        handler.initialize()
+        assert handler.get_manager() is not None
+    
+    def test_request_approval(self):
+        """Test requesting approval through handler."""
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="full_auto")
+        
+        action = ActionRequest(ActionType.FILE_WRITE, "Write file")
+        result = handler.request_approval(action)
+        
+        assert result.approved is True
+    
+    def test_set_mode(self):
+        """Test setting mode through handler."""
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="suggest")
+        
+        handler.set_mode("auto_edit")
+        
+        assert handler.get_mode() == "auto_edit"
+    
+    def test_get_mode(self):
+        """Test getting mode through handler."""
+        handler = AutonomyModeHandler()
+        
+        # Before initialization
+        assert handler.get_mode() == "suggest"
+        
+        handler.initialize(mode="full_auto")
+        assert handler.get_mode() == "full_auto"
+
+
+# ============================================================================
+# Convenience Function Tests
+# ============================================================================
+
+class TestConvenienceFunctions:
+    """Tests for convenience functions."""
+    
+    def test_create_file_write_action(self):
+        """Test creating file write action."""
+        action = create_file_write_action("/path/to/file.py", "content preview")
+        
+        assert action.action_type == ActionType.FILE_WRITE
+        assert "/path/to/file.py" in action.description
+        assert action.details["path"] == "/path/to/file.py"
+        assert action.risk_level == "medium"
+        assert action.reversible is True
+    
+    def test_create_shell_command_action(self):
+        """Test creating shell command action."""
+        action = create_shell_command_action("pytest tests/", "/project")
+        
+        assert action.action_type == ActionType.SHELL_COMMAND
+        assert action.details["command"] == "pytest tests/"
+        assert action.details["cwd"] == "/project"
+        assert action.risk_level == "medium"
+        assert action.reversible is False
+    
+    def test_create_shell_command_dangerous(self):
+        """Test dangerous shell command has high risk."""
+        action = create_shell_command_action("rm -rf /")
+        
+        assert action.risk_level == "high"
+    
+    def test_create_git_action(self):
+        """Test creating git action."""
+        action = create_git_action("commit", {"message": "Fix bug"})
+        
+        assert action.action_type == ActionType.GIT_OPERATION
+        assert "commit" in action.description
+        assert action.details["message"] == "Fix bug"
+    
+    def test_create_git_action_status_low_risk(self):
+        """Test git status has low risk."""
+        action = create_git_action("status")
+        
+        assert action.risk_level == "low"
+    
+    def test_create_tool_call_action(self):
+        """Test creating tool call action."""
+        action = create_tool_call_action("web_search", {"query": "python"})
+        
+        assert action.action_type == ActionType.TOOL_CALL
+        assert action.details["tool"] == "web_search"
+        assert action.details["args"]["query"] == "python"
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestAutonomyModeIntegration:
+    """Integration tests for autonomy mode."""
+    
+    def test_full_workflow_suggest_mode(self):
+        """Test full workflow in suggest mode."""
+        approvals = []
+        
+        def track_approval(action):
+            approvals.append(action)
+            return ApprovalResult(approved=True)
+        
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="suggest", approval_callback=track_approval)
+        
+        # File read should be auto-approved
+        read_action = ActionRequest(ActionType.FILE_READ, "Read file")
+        result = handler.request_approval(read_action)
+        assert result.approved is True
+        assert len(approvals) == 0  # No callback for auto-approved
+        
+        # File write should require approval
+        write_action = ActionRequest(ActionType.FILE_WRITE, "Write file")
+        result = handler.request_approval(write_action)
+        assert result.approved is True
+        assert len(approvals) == 1  # Callback was called
+    
+    def test_mode_transition(self):
+        """Test transitioning between modes."""
+        handler = AutonomyModeHandler()
+        handler.initialize(mode="suggest")
+        
+        # In suggest mode, file write requires approval
+        mock_callback = MagicMock(return_value=ApprovalResult(approved=True))
+        handler._manager.approval_callback = mock_callback
+        
+        write_action = ActionRequest(ActionType.FILE_WRITE, "Write")
+        handler.request_approval(write_action)
+        assert mock_callback.call_count == 1
+        
+        # Switch to auto-edit mode
+        handler.set_mode("auto_edit")
+        mock_callback.reset_mock()
+        
+        # Now file write should be auto-approved
+        handler.request_approval(write_action)
+        assert mock_callback.call_count == 0  # Not called
@@ -0,0 +1,620 @@
+"""
+Tests for Cost Tracking System.
+
+Test-Driven Development approach for cost and token tracking.
+"""
+
+import pytest
+from unittest.mock import MagicMock
+from datetime import datetime, timedelta
+import json
+
+from praisonai.cli.features.cost_tracker import (
+    ModelPricing,
+    TokenUsage,
+    RequestStats,
+    SessionStats,
+    CostTracker,
+    CostTrackerHandler,
+    get_pricing,
+    DEFAULT_PRICING,
+)
+
+
+# ============================================================================
+# ModelPricing Tests
+# ============================================================================
+
+class TestModelPricing:
+    """Tests for ModelPricing dataclass."""
+    
+    def test_create_pricing(self):
+        """Test creating model pricing."""
+        pricing = ModelPricing(
+            model_name="gpt-4o",
+            input_price_per_1m=2.50,
+            output_price_per_1m=10.00
+        )
+        assert pricing.model_name == "gpt-4o"
+        assert pricing.input_price_per_1m == 2.50
+        assert pricing.output_price_per_1m == 10.00
+        assert pricing.context_window == 128000
+    
+    def test_calculate_cost(self):
+        """Test cost calculation."""
+        pricing = ModelPricing(
+            model_name="test",
+            input_price_per_1m=1.00,
+            output_price_per_1m=2.00
+        )
+        
+        # 1000 input tokens, 500 output tokens
+        cost = pricing.calculate_cost(1000, 500)
+        
+        # Expected: (1000/1M * 1.00) + (500/1M * 2.00) = 0.001 + 0.001 = 0.002
+        assert cost == pytest.approx(0.002, rel=1e-6)
+    
+    def test_calculate_cost_large_tokens(self):
+        """Test cost calculation with large token counts."""
+        pricing = ModelPricing(
+            model_name="test",
+            input_price_per_1m=2.50,
+            output_price_per_1m=10.00
+        )
+        
+        # 100K input, 50K output
+        cost = pricing.calculate_cost(100_000, 50_000)
+        
+        # Expected: (100K/1M * 2.50) + (50K/1M * 10.00) = 0.25 + 0.50 = 0.75
+        assert cost == pytest.approx(0.75, rel=1e-6)
+
+
+# ============================================================================
+# get_pricing Tests
+# ============================================================================
+
+class TestGetPricing:
+    """Tests for get_pricing function."""
+    
+    def test_get_exact_match(self):
+        """Test getting pricing with exact model name."""
+        pricing = get_pricing("gpt-4o")
+        assert pricing.model_name == "gpt-4o"
+    
+    def test_get_partial_match(self):
+        """Test getting pricing with partial model name."""
+        pricing = get_pricing("gpt-4o-2024-08-06")
+        assert "gpt-4o" in pricing.model_name.lower() or pricing == DEFAULT_PRICING["default"]
+    
+    def test_get_unknown_model(self):
+        """Test getting pricing for unknown model returns default."""
+        pricing = get_pricing("unknown-model-xyz")
+        assert pricing == DEFAULT_PRICING["default"]
+    
+    def test_default_pricing_exists(self):
+        """Test that default pricing models exist."""
+        assert "gpt-4o" in DEFAULT_PRICING
+        assert "gpt-4o-mini" in DEFAULT_PRICING
+        assert "claude-3-5-sonnet" in DEFAULT_PRICING
+        assert "gemini-2.0-flash" in DEFAULT_PRICING
+        assert "default" in DEFAULT_PRICING
+
+
+# ============================================================================
+# TokenUsage Tests
+# ============================================================================
+
+class TestTokenUsage:
+    """Tests for TokenUsage dataclass."""
+    
+    def test_create_usage(self):
+        """Test creating token usage."""
+        usage = TokenUsage(
+            input_tokens=100,
+            output_tokens=50
+        )
+        assert usage.input_tokens == 100
+        assert usage.output_tokens == 50
+        assert usage.total_tokens == 150
+        assert usage.cached_tokens == 0
+    
+    def test_usage_with_cached(self):
+        """Test usage with cached tokens."""
+        usage = TokenUsage(
+            input_tokens=100,
+            output_tokens=50,
+            cached_tokens=30
+        )
+        assert usage.cached_tokens == 30
+    
+    def test_total_tokens_auto_calculated(self):
+        """Test total tokens is auto-calculated."""
+        usage = TokenUsage(input_tokens=200, output_tokens=100)
+        assert usage.total_tokens == 300
+    
+    def test_total_tokens_explicit(self):
+        """Test explicit total tokens is preserved."""
+        usage = TokenUsage(
+            input_tokens=100,
+            output_tokens=50,
+            total_tokens=200  # Explicit value
+        )
+        assert usage.total_tokens == 200
+
+
+# ============================================================================
+# RequestStats Tests
+# ============================================================================
+
+class TestRequestStats:
+    """Tests for RequestStats dataclass."""
+    
+    def test_create_request_stats(self):
+        """Test creating request stats."""
+        usage = TokenUsage(input_tokens=100, output_tokens=50)
+        stats = RequestStats(
+            timestamp=datetime.now(),
+            model="gpt-4o",
+            usage=usage,
+            cost=0.001
+        )
+        assert stats.model == "gpt-4o"
+        assert stats.usage.total_tokens == 150
+        assert stats.cost == 0.001
+    
+    def test_to_dict(self):
+        """Test converting to dictionary."""
+        usage = TokenUsage(input_tokens=100, output_tokens=50)
+        stats = RequestStats(
+            timestamp=datetime(2024, 1, 1, 12, 0, 0),
+            model="gpt-4o",
+            usage=usage,
+            cost=0.001,
+            duration_ms=500.0
+        )
+        
+        data = stats.to_dict()
+        
+        assert data["model"] == "gpt-4o"
+        assert data["input_tokens"] == 100
+        assert data["output_tokens"] == 50
+        assert data["cost"] == 0.001
+        assert data["duration_ms"] == 500.0
+        assert "timestamp" in data
+
+
+# ============================================================================
+# SessionStats Tests
+# ============================================================================
+
+class TestSessionStats:
+    """Tests for SessionStats dataclass."""
+    
+    def test_create_session_stats(self):
+        """Test creating session stats."""
+        stats = SessionStats(
+            session_id="test-123",
+            start_time=datetime.now()
+        )
+        assert stats.session_id == "test-123"
+        assert stats.total_requests == 0
+        assert stats.total_cost == 0.0
+    
+    def test_add_request(self):
+        """Test adding request to session."""
+        session = SessionStats(
+            session_id="test",
+            start_time=datetime.now()
+        )
+        
+        usage = TokenUsage(input_tokens=100, output_tokens=50)
+        request = RequestStats(
+            timestamp=datetime.now(),
+            model="gpt-4o",
+            usage=usage,
+            cost=0.001
+        )
+        
+        session.add_request(request)
+        
+        assert session.total_requests == 1
+        assert session.total_input_tokens == 100
+        assert session.total_output_tokens == 50
+        assert session.total_tokens == 150
+        assert session.total_cost == 0.001
+        assert "gpt-4o" in session.models_used
+    
+    def test_add_multiple_requests(self):
+        """Test adding multiple requests."""
+        session = SessionStats(
+            session_id="test",
+            start_time=datetime.now()
+        )
+        
+        for i in range(3):
+            usage = TokenUsage(input_tokens=100, output_tokens=50)
+            request = RequestStats(
+                timestamp=datetime.now(),
+                model="gpt-4o",
+                usage=usage,
+                cost=0.001
+            )
+            session.add_request(request)
+        
+        assert session.total_requests == 3
+        assert session.total_tokens == 450
+        assert session.total_cost == pytest.approx(0.003)
+    
+    def test_avg_tokens_per_request(self):
+        """Test average tokens per request."""
+        session = SessionStats(
+            session_id="test",
+            start_time=datetime.now()
+        )
+        
+        for tokens in [100, 200, 300]:
+            usage = TokenUsage(input_tokens=tokens, output_tokens=0)
+            request = RequestStats(
+                timestamp=datetime.now(),
+                model="gpt-4o",
+                usage=usage,
+                cost=0.0
+            )
+            session.add_request(request)
+        
+        assert session.avg_tokens_per_request == 200.0
+    
+    def test_avg_cost_per_request(self):
+        """Test average cost per request."""
+        session = SessionStats(
+            session_id="test",
+            start_time=datetime.now()
+        )
+        
+        for cost in [0.001, 0.002, 0.003]:
+            usage = TokenUsage(input_tokens=100, output_tokens=50)
+            request = RequestStats(
+                timestamp=datetime.now(),
+                model="gpt-4o",
+                usage=usage,
+                cost=cost
+            )
+            session.add_request(request)
+        
+        assert session.avg_cost_per_request == pytest.approx(0.002)
+    
+    def test_duration_seconds(self):
+        """Test session duration calculation."""
+        start = datetime.now() - timedelta(seconds=60)
+        session = SessionStats(
+            session_id="test",
+            start_time=start
+        )
+        
+        assert session.duration_seconds >= 60
+    
+    def test_to_dict(self):
+        """Test converting to dictionary."""
+        session = SessionStats(
+            session_id="test-123",
+            start_time=datetime(2024, 1, 1, 12, 0, 0)
+        )
+        
+        data = session.to_dict()
+        
+        assert data["session_id"] == "test-123"
+        assert data["total_requests"] == 0
+        assert "start_time" in data
+
+
+# ============================================================================
+# CostTracker Tests
+# ============================================================================
+
+class TestCostTracker:
+    """Tests for CostTracker."""
+    
+    def test_create_tracker(self):
+        """Test creating cost tracker."""
+        tracker = CostTracker()
+        
+        assert tracker.session_id is not None
+        assert len(tracker.session_id) == 8
+        assert tracker.session_stats is not None
+    
+    def test_create_tracker_with_session_id(self):
+        """Test creating tracker with custom session ID."""
+        tracker = CostTracker(session_id="custom-id")
+        
+        assert tracker.session_id == "custom-id"
+    
+    def test_track_request(self):
+        """Test tracking a request."""
+        tracker = CostTracker()
+        
+        stats = tracker.track_request(
+            model="gpt-4o",
+            input_tokens=1000,
+            output_tokens=500
+        )
+        
+        assert stats is not None
+        assert stats.model == "gpt-4o"
+        assert stats.usage.input_tokens == 1000
+        assert stats.usage.output_tokens == 500
+        assert stats.cost > 0
+    
+    def test_track_multiple_requests(self):
+        """Test tracking multiple requests."""
+        tracker = CostTracker()
+        
+        tracker.track_request("gpt-4o", 1000, 500)
+        tracker.track_request("gpt-4o-mini", 2000, 1000)
+        tracker.track_request("gpt-4o", 500, 250)
+        
+        assert tracker.get_request_count() == 3
+        assert tracker.get_total_tokens() == 5250
+        assert tracker.get_total_cost() > 0
+    
+    def test_track_with_cached_tokens(self):
+        """Test tracking with cached tokens."""
+        tracker = CostTracker()
+        
+        stats = tracker.track_request(
+            model="gpt-4o",
+            input_tokens=1000,
+            output_tokens=500,
+            cached_tokens=200
+        )
+        
+        assert stats.usage.cached_tokens == 200
+        assert tracker.session_stats.total_cached_tokens == 200
+    
+    def test_track_with_duration(self):
+        """Test tracking with duration."""
+        tracker = CostTracker()
+        
+        stats = tracker.track_request(
+            model="gpt-4o",
+            input_tokens=1000,
+            output_tokens=500,
+            duration_ms=1500.0
+        )
+        
+        assert stats.duration_ms == 1500.0
+    
+    def test_get_current_stats(self):
+        """Test getting current stats."""
+        tracker = CostTracker()
+        tracker.track_request("gpt-4o", 1000, 500)
+        
+        stats = tracker.get_current_stats()
+        
+        assert stats.total_requests == 1
+        assert stats.total_tokens == 1500
+    
+    def test_format_summary(self):
+        """Test formatting summary."""
+        tracker = CostTracker(session_id="test-123")
+        tracker.track_request("gpt-4o", 1000, 500)
+        
+        summary = tracker.format_summary()
+        
+        assert "test-123" in summary
+        assert "Tokens:" in summary
+        assert "Cost:" in summary
+    
+    def test_export_json(self):
+        """Test exporting to JSON."""
+        tracker = CostTracker(session_id="test-123")
+        tracker.track_request("gpt-4o", 1000, 500)
+        
+        json_str = tracker.export_json()
+        data = json.loads(json_str)
+        
+        assert "session" in data
+        assert "requests" in data
+        assert data["session"]["session_id"] == "test-123"
+        assert len(data["requests"]) == 1
+    
+    def test_end_session(self):
+        """Test ending session."""
+        tracker = CostTracker()
+        tracker.track_request("gpt-4o", 1000, 500)
+        
+        stats = tracker.end_session()
+        
+        assert stats.end_time is not None
+    
+    def test_models_used_tracking(self):
+        """Test tracking of models used."""
+        tracker = CostTracker()
+        
+        tracker.track_request("gpt-4o", 1000, 500)
+        tracker.track_request("gpt-4o", 1000, 500)
+        tracker.track_request("gpt-4o-mini", 1000, 500)
+        
+        stats = tracker.get_current_stats()
+        
+        assert stats.models_used["gpt-4o"] == 2
+        assert stats.models_used["gpt-4o-mini"] == 1
+
+
+# ============================================================================
+# CostTracker Response Tracking Tests
+# ============================================================================
+
+class TestCostTrackerResponseTracking:
+    """Tests for tracking from LLM responses."""
+    
+    def test_track_from_openai_response(self):
+        """Test tracking from OpenAI-style response."""
+        tracker = CostTracker()
+        
+        # Mock OpenAI response
+        mock_response = MagicMock()
+        mock_response.usage = MagicMock()
+        mock_response.usage.prompt_tokens = 100
+        mock_response.usage.completion_tokens = 50
+        mock_response.usage.cached_tokens = 0
+        
+        stats = tracker.track_from_response("gpt-4o", mock_response)
+        
+        assert stats is not None
+        assert stats.usage.input_tokens == 100
+        assert stats.usage.output_tokens == 50
+    
+    def test_track_from_dict_response(self):
+        """Test tracking from dict response."""
+        tracker = CostTracker()
+        
+        response = {
+            "usage": {
+                "prompt_tokens": 200,
+                "completion_tokens": 100
+            }
+        }
+        
+        stats = tracker.track_from_response("gpt-4o", response)
+        
+        assert stats is not None
+        assert stats.usage.input_tokens == 200
+        assert stats.usage.output_tokens == 100
+    
+    def test_track_from_invalid_response(self):
+        """Test tracking from invalid response returns None."""
+        tracker = CostTracker()
+        
+        stats = tracker.track_from_response("gpt-4o", "invalid response")
+        
+        assert stats is None
+
+
+# ============================================================================
+# CostTrackerHandler Tests
+# ============================================================================
+
+class TestCostTrackerHandler:
+    """Tests for CostTrackerHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = CostTrackerHandler()
+        assert handler.feature_name == "cost_tracker"
+    
+    def test_initialize(self):
+        """Test initializing tracker."""
+        handler = CostTrackerHandler()
+        tracker = handler.initialize()
+        
+        assert tracker is not None
+        assert handler.get_tracker() is tracker
+    
+    def test_initialize_with_session_id(self):
+        """Test initializing with session ID."""
+        handler = CostTrackerHandler()
+        tracker = handler.initialize(session_id="custom-123")
+        
+        assert tracker.session_id == "custom-123"
+    
+    def test_track_request(self):
+        """Test tracking request through handler."""
+        handler = CostTrackerHandler()
+        
+        stats = handler.track_request(
+            model="gpt-4o",
+            input_tokens=1000,
+            output_tokens=500
+        )
+        
+        assert stats is not None
+        assert handler.get_cost() > 0
+        assert handler.get_tokens() == 1500
+    
+    def test_get_summary(self):
+        """Test getting summary."""
+        handler = CostTrackerHandler()
+        handler.track_request("gpt-4o", 1000, 500)
+        
+        summary = handler.get_summary()
+        
+        assert "total_requests" in summary
+        assert summary["total_requests"] == 1
+    
+    def test_get_cost_before_init(self):
+        """Test getting cost before initialization."""
+        handler = CostTrackerHandler()
+        
+        assert handler.get_cost() == 0.0
+    
+    def test_get_tokens_before_init(self):
+        """Test getting tokens before initialization."""
+        handler = CostTrackerHandler()
+        
+        assert handler.get_tokens() == 0
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestCostTrackerIntegration:
+    """Integration tests for cost tracking."""
+    
+    def test_full_session_workflow(self):
+        """Test full session workflow."""
+        handler = CostTrackerHandler(verbose=False)
+        handler.initialize(session_id="integration-test")
+        
+        # Simulate multiple requests
+        models = ["gpt-4o", "gpt-4o-mini", "gpt-4o"]
+        for i, model in enumerate(models):
+            handler.track_request(
+                model=model,
+                input_tokens=1000 * (i + 1),
+                output_tokens=500 * (i + 1),
+                duration_ms=100.0 * (i + 1)
+            )
+        
+        # Verify totals
+        summary = handler.get_summary()
+        
+        assert summary["total_requests"] == 3
+        assert summary["total_input_tokens"] == 6000  # 1000 + 2000 + 3000
+        assert summary["total_output_tokens"] == 3000  # 500 + 1000 + 1500
+        assert summary["total_tokens"] == 9000
+        assert handler.get_cost() > 0
+    
+    def test_cost_calculation_accuracy(self):
+        """Test cost calculation accuracy."""
+        tracker = CostTracker()
+        
+        # Use known pricing
+        # gpt-4o: $2.50/1M input, $10.00/1M output
+        stats = tracker.track_request(
+            model="gpt-4o",
+            input_tokens=1_000_000,  # 1M tokens
+            output_tokens=1_000_000   # 1M tokens
+        )
+        
+        # Expected: $2.50 + $10.00 = $12.50
+        assert stats.cost == pytest.approx(12.50, rel=0.01)
+    
+    def test_session_persistence(self):
+        """Test session data can be exported and contains all info."""
+        tracker = CostTracker(session_id="persist-test")
+        
+        tracker.track_request("gpt-4o", 1000, 500)
+        tracker.track_request("gpt-4o-mini", 2000, 1000)
+        
+        json_str = tracker.export_json()
+        data = json.loads(json_str)
+        
+        # Verify structure
+        assert data["session"]["session_id"] == "persist-test"
+        assert len(data["requests"]) == 2
+        assert data["session"]["total_requests"] == 2
+        
+        # Verify request details preserved
+        assert data["requests"][0]["model"] == "gpt-4o"
+        assert data["requests"][1]["model"] == "gpt-4o-mini"
@@ -0,0 +1,368 @@
+"""
+Tests for Git Integration System.
+
+Test-Driven Development approach for Git operations.
+"""
+
+from pathlib import Path
+import tempfile
+import subprocess
+
+from praisonai.cli.features.git_integration import (
+    GitStatus,
+    GitCommit,
+    GitManager,
+    CommitMessageGenerator,
+    DiffViewer,
+    GitIntegrationHandler,
+)
+
+
+# ============================================================================
+# GitStatus Tests
+# ============================================================================
+
+class TestGitStatus:
+    """Tests for GitStatus dataclass."""
+    
+    def test_create_status(self):
+        """Test creating git status."""
+        status = GitStatus()
+        assert status.branch == ""
+        assert status.is_clean is True
+        assert status.staged_files == []
+    
+    def test_has_changes(self):
+        """Test has_changes property."""
+        status = GitStatus()
+        assert status.has_changes is False
+        
+        status.modified_files = ["file.py"]
+        assert status.has_changes is True
+
+
+# ============================================================================
+# GitCommit Tests
+# ============================================================================
+
+class TestGitCommit:
+    """Tests for GitCommit dataclass."""
+    
+    def test_create_commit(self):
+        """Test creating git commit."""
+        commit = GitCommit(
+            hash="abc123def456",
+            short_hash="abc123d",
+            message="Test commit",
+            author="Test User",
+            date="2024-01-01"
+        )
+        assert commit.hash == "abc123def456"
+        assert commit.message == "Test commit"
+
+
+# ============================================================================
+# GitManager Tests
+# ============================================================================
+
+class TestGitManager:
+    """Tests for GitManager."""
+    
+    def test_create_manager(self):
+        """Test creating git manager."""
+        manager = GitManager()
+        assert manager is not None
+    
+    def test_is_repo_false_for_non_repo(self):
+        """Test is_repo returns False for non-repo."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            manager = GitManager(repo_path=tmpdir)
+            assert manager.is_repo is False
+    
+    def test_is_repo_true_for_repo(self):
+        """Test is_repo returns True for git repo."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            # Initialize git repo
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            
+            manager = GitManager(repo_path=tmpdir)
+            assert manager.is_repo is True
+    
+    def test_get_status_empty_repo(self):
+        """Test getting status of empty repo."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            
+            manager = GitManager(repo_path=tmpdir)
+            status = manager.get_status()
+            
+            assert status.is_clean is True
+    
+    def test_get_status_with_changes(self):
+        """Test getting status with changes."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            
+            # Create a file
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            status = manager.get_status()
+            
+            assert "test.py" in status.untracked_files
+    
+    def test_stage_files(self):
+        """Test staging files."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            result = manager.stage_files(["test.py"])
+            
+            assert result is True
+            
+            status = manager.get_status()
+            assert "test.py" in status.staged_files
+    
+    def test_commit(self):
+        """Test creating a commit."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            subprocess.run(
+                ["git", "config", "user.email", "[email protected]"],
+                cwd=tmpdir, capture_output=True
+            )
+            subprocess.run(
+                ["git", "config", "user.name", "Test"],
+                cwd=tmpdir, capture_output=True
+            )
+            
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            manager.stage_files()
+            
+            commit = manager.commit("Test commit")
+            
+            assert commit is not None
+            assert commit.message == "Test commit"
+    
+    def test_get_log(self):
+        """Test getting commit log."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            subprocess.run(
+                ["git", "config", "user.email", "[email protected]"],
+                cwd=tmpdir, capture_output=True
+            )
+            subprocess.run(
+                ["git", "config", "user.name", "Test"],
+                cwd=tmpdir, capture_output=True
+            )
+            
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            manager.stage_files()
+            manager.commit("First commit")
+            
+            commits = manager.get_log()
+            
+            assert len(commits) >= 1
+            assert commits[0].message == "First commit"
+    
+    def test_undo_last_commit(self):
+        """Test undoing last commit."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            subprocess.run(
+                ["git", "config", "user.email", "[email protected]"],
+                cwd=tmpdir, capture_output=True
+            )
+            subprocess.run(
+                ["git", "config", "user.name", "Test"],
+                cwd=tmpdir, capture_output=True
+            )
+            
+            # Need at least 2 commits to undo one
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            manager.stage_files()
+            manager.commit("First commit")
+            
+            (Path(tmpdir) / "test2.py").write_text("# test2")
+            manager.stage_files()
+            manager.commit("Second commit")
+            
+            result = manager.undo_last_commit(soft=True)
+            
+            assert result is True
+    
+    def test_get_branches(self):
+        """Test getting branches."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            subprocess.run(
+                ["git", "config", "user.email", "[email protected]"],
+                cwd=tmpdir, capture_output=True
+            )
+            subprocess.run(
+                ["git", "config", "user.name", "Test"],
+                cwd=tmpdir, capture_output=True
+            )
+            
+            (Path(tmpdir) / "test.py").write_text("# test")
+            
+            manager = GitManager(repo_path=tmpdir)
+            manager.stage_files()
+            manager.commit("Initial commit")
+            
+            branches = manager.get_branches()
+            
+            assert len(branches) >= 1
+
+
+# ============================================================================
+# CommitMessageGenerator Tests
+# ============================================================================
+
+class TestCommitMessageGenerator:
+    """Tests for CommitMessageGenerator."""
+    
+    def test_create_generator(self):
+        """Test creating generator."""
+        generator = CommitMessageGenerator()
+        assert generator is not None
+    
+    def test_generate_empty_diff(self):
+        """Test generating message for empty diff."""
+        generator = CommitMessageGenerator(use_ai=False)
+        message = generator.generate("")
+        
+        assert message == "Empty commit"
+    
+    def test_generate_from_diff(self):
+        """Test generating message from diff."""
+        generator = CommitMessageGenerator(use_ai=False)
+        
+        diff = """
+diff --git a/test.py b/test.py
+--- a/test.py
+++ b/test.py
+@@ -1 +1,5 @@
+# New content
+def hello():
+    pass
+"""
+        
+        message = generator.generate(diff)
+        
+        assert len(message) > 0
+        assert "test" in message.lower() or "feat" in message.lower()
+
+
+# ============================================================================
+# DiffViewer Tests
+# ============================================================================
+
+class TestDiffViewer:
+    """Tests for DiffViewer."""
+    
+    def test_create_viewer(self):
+        """Test creating viewer."""
+        viewer = DiffViewer()
+        assert viewer is not None
+    
+    def test_display_diff_no_console(self):
+        """Test displaying diff without console."""
+        viewer = DiffViewer()
+        viewer._console = None
+        
+        # Should not raise
+        viewer.display_diff("test diff")
+    
+    def test_display_status_no_console(self):
+        """Test displaying status without console."""
+        viewer = DiffViewer()
+        viewer._console = None
+        
+        status = GitStatus(branch="main")
+        viewer.display_status(status)
+
+
+# ============================================================================
+# GitIntegrationHandler Tests
+# ============================================================================
+
+class TestGitIntegrationHandler:
+    """Tests for GitIntegrationHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = GitIntegrationHandler()
+        assert handler.feature_name == "git_integration"
+    
+    def test_initialize(self):
+        """Test initializing handler."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            
+            handler = GitIntegrationHandler()
+            git = handler.initialize(repo_path=tmpdir)
+            
+            assert git is not None
+            assert git.is_repo is True
+    
+    def test_show_status(self):
+        """Test showing status."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            
+            handler = GitIntegrationHandler()
+            handler.initialize(repo_path=tmpdir)
+            
+            status = handler.show_status()
+            
+            assert status is not None
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestGitIntegrationIntegration:
+    """Integration tests for Git integration."""
+    
+    def test_full_workflow(self):
+        """Test full git workflow."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            # Initialize repo
+            subprocess.run(["git", "init"], cwd=tmpdir, capture_output=True)
+            subprocess.run(
+                ["git", "config", "user.email", "[email protected]"],
+                cwd=tmpdir, capture_output=True
+            )
+            subprocess.run(
+                ["git", "config", "user.name", "Test"],
+                cwd=tmpdir, capture_output=True
+            )
+            
+            handler = GitIntegrationHandler()
+            handler.initialize(repo_path=tmpdir)
+            
+            # Create file
+            (Path(tmpdir) / "main.py").write_text("# Main file\n")
+            
+            # Check status
+            status = handler.show_status()
+            assert "main.py" in status.untracked_files
+            
+            # Commit
+            commit = handler.commit(message="Add main.py")
+            assert commit is not None
+            
+            # Check log
+            commits = handler.show_log()
+            assert len(commits) >= 1
@@ -0,0 +1,460 @@
+"""
+Tests for Interactive TUI System.
+
+Test-Driven Development approach for interactive terminal interface.
+"""
+
+from pathlib import Path
+import tempfile
+
+from praisonai.cli.features.interactive_tui import (
+    InteractiveConfig,
+    CommandCompleter,
+    HistoryManager,
+    StatusDisplay,
+    InteractiveSession,
+    InteractiveTUIHandler,
+)
+
+
+# ============================================================================
+# InteractiveConfig Tests
+# ============================================================================
+
+class TestInteractiveConfig:
+    """Tests for InteractiveConfig."""
+    
+    def test_default_config(self):
+        """Test default configuration."""
+        config = InteractiveConfig()
+        
+        assert config.prompt == ">>> "
+        assert config.multiline is True
+        assert config.enable_completions is True
+        assert config.vi_mode is False
+    
+    def test_custom_config(self):
+        """Test custom configuration."""
+        config = InteractiveConfig(
+            prompt="$ ",
+            multiline=False,
+            vi_mode=True
+        )
+        
+        assert config.prompt == "$ "
+        assert config.multiline is False
+        assert config.vi_mode is True
+
+
+# ============================================================================
+# CommandCompleter Tests
+# ============================================================================
+
+class TestCommandCompleter:
+    """Tests for CommandCompleter."""
+    
+    def test_create_completer(self):
+        """Test creating completer."""
+        completer = CommandCompleter()
+        assert completer is not None
+    
+    def test_add_commands(self):
+        """Test adding commands."""
+        completer = CommandCompleter()
+        completer.add_commands(["help", "exit", "cost"])
+        
+        assert "help" in completer.commands
+        assert "exit" in completer.commands
+    
+    def test_complete_slash_command(self):
+        """Test completing slash commands."""
+        completer = CommandCompleter(commands=["help", "history", "exit"])
+        
+        completions = completer.get_completions("/he", 3)
+        
+        assert "/help" in completions
+        # /history should also match but may be filtered
+        assert "/exit" not in completions
+    
+    def test_complete_file_mention(self):
+        """Test completing file mentions."""
+        completer = CommandCompleter()
+        completer._file_cache = ["main.py", "config.py", "utils.py"]
+        
+        completions = completer.get_completions("@main", 5)
+        
+        assert "@main.py" in completions
+    
+    def test_add_symbols(self):
+        """Test adding symbols."""
+        completer = CommandCompleter()
+        completer.add_symbols(["MyClass", "my_function"])
+        
+        assert "MyClass" in completer._symbol_cache
+    
+    def test_refresh_files(self):
+        """Test refreshing file cache."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "test.py").write_text("# test")
+            (Path(tmpdir) / "main.py").write_text("# main")
+            
+            completer = CommandCompleter()
+            completer.refresh_files(Path(tmpdir))
+            
+            assert len(completer._file_cache) >= 2
+
+
+# ============================================================================
+# HistoryManager Tests
+# ============================================================================
+
+class TestHistoryManager:
+    """Tests for HistoryManager."""
+    
+    def test_create_manager(self):
+        """Test creating history manager."""
+        manager = HistoryManager()
+        assert manager is not None
+    
+    def test_add_entry(self):
+        """Test adding history entry."""
+        manager = HistoryManager()
+        manager.add("first command")
+        manager.add("second command")
+        
+        assert len(manager.get_all()) == 2
+    
+    def test_no_duplicate_consecutive(self):
+        """Test no duplicate consecutive entries."""
+        manager = HistoryManager()
+        manager.add("same command")
+        manager.add("same command")
+        
+        assert len(manager.get_all()) == 1
+    
+    def test_get_previous(self):
+        """Test getting previous entry."""
+        manager = HistoryManager()
+        manager.add("first")
+        manager.add("second")
+        manager.add("third")
+        
+        assert manager.get_previous() == "third"
+        assert manager.get_previous() == "second"
+        assert manager.get_previous() == "first"
+    
+    def test_get_next(self):
+        """Test getting next entry."""
+        manager = HistoryManager()
+        manager.add("first")
+        manager.add("second")
+        
+        manager.get_previous()  # second
+        manager.get_previous()  # first
+        
+        assert manager.get_next() == "second"
+    
+    def test_search(self):
+        """Test searching history."""
+        manager = HistoryManager()
+        manager.add("/help")
+        manager.add("/exit")
+        manager.add("/help model")
+        
+        results = manager.search("/help")
+        
+        assert len(results) == 2
+        assert "/help" in results
+        assert "/help model" in results
+    
+    def test_clear(self):
+        """Test clearing history."""
+        manager = HistoryManager()
+        manager.add("command")
+        manager.clear()
+        
+        assert len(manager.get_all()) == 0
+    
+    def test_persistent_history(self):
+        """Test persistent history file."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            history_file = Path(tmpdir) / "history.txt"
+            
+            # Create and add entries
+            manager1 = HistoryManager(history_file=str(history_file))
+            manager1.add("command1")
+            manager1.add("command2")
+            
+            # Create new manager with same file
+            manager2 = HistoryManager(history_file=str(history_file))
+            
+            assert len(manager2.get_all()) == 2
+
+
+# ============================================================================
+# StatusDisplay Tests
+# ============================================================================
+
+class TestStatusDisplay:
+    """Tests for StatusDisplay."""
+    
+    def test_create_display(self):
+        """Test creating status display."""
+        display = StatusDisplay()
+        assert display is not None
+    
+    def test_set_status(self):
+        """Test setting status."""
+        display = StatusDisplay()
+        display.set_status("model", "gpt-4o")
+        
+        assert display._status_items["model"] == "gpt-4o"
+    
+    def test_clear_status(self):
+        """Test clearing status."""
+        display = StatusDisplay()
+        display.set_status("key", "value")
+        display.clear_status("key")
+        
+        assert "key" not in display._status_items
+    
+    def test_print_welcome(self):
+        """Test printing welcome message."""
+        display = StatusDisplay()
+        display._console = None  # Force no console
+        
+        # Should not raise without console
+        display.print_welcome()
+    
+    def test_print_response(self):
+        """Test printing response."""
+        display = StatusDisplay()
+        display._console = None  # Force no console
+        
+        display.print_response("Test response")
+    
+    def test_print_error(self):
+        """Test printing error."""
+        display = StatusDisplay()
+        display._console = None  # Force no console
+        
+        display.print_error("Test error")
+
+
+# ============================================================================
+# InteractiveSession Tests
+# ============================================================================
+
+class TestInteractiveSession:
+    """Tests for InteractiveSession."""
+    
+    def test_create_session(self):
+        """Test creating session."""
+        session = InteractiveSession()
+        assert session is not None
+    
+    def test_create_session_with_config(self):
+        """Test creating session with config."""
+        config = InteractiveConfig(prompt="$ ")
+        session = InteractiveSession(config=config)
+        
+        assert session.config.prompt == "$ "
+    
+    def test_add_commands(self):
+        """Test adding commands."""
+        session = InteractiveSession()
+        session.add_commands(["help", "exit"])
+        
+        assert "help" in session.completer.commands
+    
+    def test_add_symbols(self):
+        """Test adding symbols."""
+        session = InteractiveSession()
+        session.add_symbols(["MyClass"])
+        
+        assert "MyClass" in session.completer._symbol_cache
+    
+    def test_process_empty_input(self):
+        """Test processing empty input."""
+        session = InteractiveSession()
+        result = session.process_input("")
+        
+        assert result is None
+    
+    def test_process_slash_command(self):
+        """Test processing slash command."""
+        command_called = []
+        
+        def on_command(cmd):
+            command_called.append(cmd)
+            return {"type": "help"}
+        
+        session = InteractiveSession(on_command=on_command)
+        session.process_input("/help")
+        
+        assert len(command_called) == 1
+        assert command_called[0] == "/help"
+    
+    def test_process_regular_input(self):
+        """Test processing regular input."""
+        input_received = []
+        
+        def on_input(text):
+            input_received.append(text)
+            return "Response"
+        
+        session = InteractiveSession(on_input=on_input)
+        result = session.process_input("Hello world")
+        
+        assert len(input_received) == 1
+        assert result == "Response"
+    
+    def test_exit_command_stops_session(self):
+        """Test exit command stops session."""
+        def on_command(cmd):
+            return {"type": "exit"}
+        
+        session = InteractiveSession(on_command=on_command)
+        session._running = True
+        
+        session.process_input("/exit")
+        
+        assert session._running is False
+    
+    def test_history_tracking(self):
+        """Test that input is added to history."""
+        session = InteractiveSession()
+        session.process_input("test command")
+        
+        assert "test command" in session.history.get_all()
+    
+    def test_stop_session(self):
+        """Test stopping session."""
+        session = InteractiveSession()
+        session._running = True
+        
+        session.stop()
+        
+        assert session._running is False
+
+
+# ============================================================================
+# InteractiveTUIHandler Tests
+# ============================================================================
+
+class TestInteractiveTUIHandler:
+    """Tests for InteractiveTUIHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = InteractiveTUIHandler()
+        assert handler.feature_name == "interactive_tui"
+    
+    def test_initialize(self):
+        """Test initializing handler."""
+        handler = InteractiveTUIHandler()
+        session = handler.initialize()
+        
+        assert session is not None
+        assert handler.get_session() is session
+    
+    def test_initialize_with_config(self):
+        """Test initializing with config."""
+        handler = InteractiveTUIHandler()
+        config = InteractiveConfig(prompt="$ ")
+        
+        session = handler.initialize(config=config)
+        
+        assert session.config.prompt == "$ "
+    
+    def test_initialize_with_callbacks(self):
+        """Test initializing with callbacks."""
+        handler = InteractiveTUIHandler()
+        
+        def on_input(text):
+            return "response"
+        
+        def on_command(cmd):
+            return {"type": "help"}
+        
+        session = handler.initialize(on_input=on_input, on_command=on_command)
+        
+        assert session.on_input is on_input
+        assert session.on_command is on_command
+    
+    def test_stop(self):
+        """Test stopping handler."""
+        handler = InteractiveTUIHandler()
+        handler.initialize()
+        handler._session._running = True
+        
+        handler.stop()
+        
+        assert handler._session._running is False
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestInteractiveTUIIntegration:
+    """Integration tests for Interactive TUI."""
+    
+    def test_full_session_workflow(self):
+        """Test full session workflow."""
+        
+        def on_input(text):
+            return f"Echo: {text}"
+        
+        def on_command(cmd):
+            if cmd == "/exit":
+                return {"type": "exit"}
+            return {"type": "command", "message": f"Executed: {cmd}"}
+        
+        handler = InteractiveTUIHandler()
+        session = handler.initialize(on_input=on_input, on_command=on_command)
+        
+        # Process various inputs
+        result1 = session.process_input("Hello")
+        assert result1 == "Echo: Hello"
+        
+        result2 = session.process_input("/help")
+        assert result2 == "Executed: /help"
+        
+        # Exit
+        session.process_input("/exit")
+        assert session._running is False
+    
+    def test_completion_integration(self):
+        """Test completion integration."""
+        handler = InteractiveTUIHandler()
+        session = handler.initialize()
+        
+        # Add commands and symbols
+        session.add_commands(["help", "exit", "cost"])
+        session.add_symbols(["MyClass", "my_function"])
+        
+        # Test completions
+        completions = session.completer.get_completions("/he", 3)
+        assert "/help" in completions
+        
+        completions = session.completer.get_completions("My", 2)
+        assert "MyClass" in completions
+    
+    def test_history_integration(self):
+        """Test history integration."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            history_file = Path(tmpdir) / "history.txt"
+            
+            config = InteractiveConfig(history_file=str(history_file))
+            handler = InteractiveTUIHandler()
+            session = handler.initialize(config=config)
+            
+            # Add some history
+            session.process_input("command 1")
+            session.process_input("command 2")
+            
+            # Check history
+            history = session.history.get_all()
+            assert "command 1" in history
+            assert "command 2" in history
@@ -0,0 +1,611 @@
+"""
+Tests for Repository Map System.
+
+Test-Driven Development approach for codebase mapping.
+"""
+
+import pytest
+from pathlib import Path
+import tempfile
+
+from praisonai.cli.features.repo_map import (
+    Symbol,
+    FileMap,
+    RepoMapConfig,
+    SymbolExtractor,
+    SymbolRanker,
+    RepoMap,
+    RepoMapHandler,
+)
+
+
+# ============================================================================
+# Symbol Tests
+# ============================================================================
+
+class TestSymbol:
+    """Tests for Symbol dataclass."""
+    
+    def test_create_symbol(self):
+        """Test creating a symbol."""
+        symbol = Symbol(
+            name="MyClass",
+            kind="class",
+            file_path="test.py",
+            line_number=10
+        )
+        assert symbol.name == "MyClass"
+        assert symbol.kind == "class"
+        assert symbol.file_path == "test.py"
+        assert symbol.line_number == 10
+    
+    def test_symbol_with_signature(self):
+        """Test symbol with signature."""
+        symbol = Symbol(
+            name="my_function",
+            kind="function",
+            file_path="test.py",
+            line_number=5,
+            signature="def my_function(x, y):"
+        )
+        assert symbol.signature == "def my_function(x, y):"
+    
+    def test_symbol_with_parent(self):
+        """Test method symbol with parent class."""
+        symbol = Symbol(
+            name="method",
+            kind="method",
+            file_path="test.py",
+            line_number=15,
+            parent="MyClass"
+        )
+        assert symbol.parent == "MyClass"
+        assert symbol.qualified_name == "MyClass.method"
+    
+    def test_symbol_qualified_name_no_parent(self):
+        """Test qualified name without parent."""
+        symbol = Symbol(
+            name="function",
+            kind="function",
+            file_path="test.py",
+            line_number=1
+        )
+        assert symbol.qualified_name == "function"
+    
+    def test_symbol_hash(self):
+        """Test symbol hashing for sets."""
+        s1 = Symbol("test", "function", "file.py", 1)
+        s2 = Symbol("test", "function", "file.py", 1)
+        s3 = Symbol("test", "function", "file.py", 2)
+        
+        assert hash(s1) == hash(s2)
+        assert hash(s1) != hash(s3)
+
+
+# ============================================================================
+# FileMap Tests
+# ============================================================================
+
+class TestFileMap:
+    """Tests for FileMap dataclass."""
+    
+    def test_create_file_map(self):
+        """Test creating a file map."""
+        file_map = FileMap(file_path="test.py")
+        assert file_map.file_path == "test.py"
+        assert file_map.symbols == []
+    
+    def test_add_symbol(self):
+        """Test adding symbols to file map."""
+        file_map = FileMap(file_path="test.py")
+        symbol = Symbol("test", "function", "test.py", 1)
+        
+        file_map.add_symbol(symbol)
+        
+        assert len(file_map.symbols) == 1
+        assert file_map.symbols[0].name == "test"
+    
+    def test_get_summary(self):
+        """Test getting file summary."""
+        file_map = FileMap(file_path="test.py")
+        file_map.add_symbol(Symbol(
+            "MyClass", "class", "test.py", 1,
+            signature="class MyClass:"
+        ))
+        file_map.add_symbol(Symbol(
+            "my_func", "function", "test.py", 10,
+            signature="def my_func(x):"
+        ))
+        
+        summary = file_map.get_summary()
+        
+        assert "test.py:" in summary
+        assert "class MyClass:" in summary or "MyClass" in summary
+
+
+# ============================================================================
+# RepoMapConfig Tests
+# ============================================================================
+
+class TestRepoMapConfig:
+    """Tests for RepoMapConfig."""
+    
+    def test_default_config(self):
+        """Test default configuration."""
+        config = RepoMapConfig()
+        
+        assert config.max_tokens == 1024
+        assert config.max_files == 50
+        assert ".py" in config.file_extensions
+        assert "__pycache__" in config.exclude_patterns
+    
+    def test_custom_config(self):
+        """Test custom configuration."""
+        config = RepoMapConfig(
+            max_tokens=2048,
+            max_files=100,
+            file_extensions={".py", ".js"}
+        )
+        
+        assert config.max_tokens == 2048
+        assert config.max_files == 100
+        assert len(config.file_extensions) == 2
+
+
+# ============================================================================
+# SymbolExtractor Tests
+# ============================================================================
+
+class TestSymbolExtractor:
+    """Tests for SymbolExtractor."""
+    
+    def test_create_extractor(self):
+        """Test creating extractor."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        assert extractor is not None
+    
+    def test_extract_python_class(self):
+        """Test extracting Python class."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+class MyClass:
+    def __init__(self):
+        pass
+    
+    def method(self):
+        pass
+"""
+        
+        symbols = extractor.extract_symbols("test.py", content)
+        
+        class_symbols = [s for s in symbols if s.kind == "class"]
+        assert len(class_symbols) >= 1
+        assert class_symbols[0].name == "MyClass"
+    
+    def test_extract_python_function(self):
+        """Test extracting Python function."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+def my_function(x, y):
+    return x + y
+
+def another_function():
+    pass
+"""
+        
+        symbols = extractor.extract_symbols("test.py", content)
+        
+        func_symbols = [s for s in symbols if s.kind == "function"]
+        assert len(func_symbols) >= 2
+        names = [s.name for s in func_symbols]
+        assert "my_function" in names
+        assert "another_function" in names
+    
+    def test_extract_python_method(self):
+        """Test extracting Python method."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+class MyClass:
+    def method_one(self):
+        pass
+    
+    def method_two(self, x):
+        return x
+"""
+        
+        symbols = extractor.extract_symbols("test.py", content)
+        
+        method_symbols = [s for s in symbols if s.kind == "method"]
+        assert len(method_symbols) >= 2
+        
+        # Check parent is set
+        for method in method_symbols:
+            assert method.parent == "MyClass"
+    
+    def test_extract_javascript_class(self):
+        """Test extracting JavaScript class."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+class MyComponent {
+    constructor() {}
+}
+
+export class AnotherClass {}
+"""
+        
+        symbols = extractor.extract_symbols("test.js", content)
+        
+        class_symbols = [s for s in symbols if s.kind == "class"]
+        assert len(class_symbols) >= 1
+    
+    def test_extract_javascript_function(self):
+        """Test extracting JavaScript function."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+function myFunction() {}
+
+const arrowFunc = () => {};
+
+async function asyncFunc() {}
+"""
+        
+        symbols = extractor.extract_symbols("test.js", content)
+        
+        func_symbols = [s for s in symbols if s.kind == "function"]
+        assert len(func_symbols) >= 1
+    
+    def test_extract_go_symbols(self):
+        """Test extracting Go symbols."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+type MyStruct struct {
+    Name string
+}
+
+func MyFunction() {}
+
+func (m *MyStruct) Method() {}
+"""
+        
+        symbols = extractor.extract_symbols("test.go", content)
+        
+        assert len(symbols) >= 2
+    
+    def test_extract_rust_symbols(self):
+        """Test extracting Rust symbols."""
+        extractor = SymbolExtractor(use_tree_sitter=False)
+        
+        content = """
+pub struct MyStruct {
+    field: i32,
+}
+
+fn my_function() {}
+
+pub async fn async_func() {}
+"""
+        
+        symbols = extractor.extract_symbols("test.rs", content)
+        
+        assert len(symbols) >= 2
+
+
+# ============================================================================
+# SymbolRanker Tests
+# ============================================================================
+
+class TestSymbolRanker:
+    """Tests for SymbolRanker."""
+    
+    def test_create_ranker(self):
+        """Test creating ranker."""
+        ranker = SymbolRanker()
+        assert ranker is not None
+    
+    def test_analyze_references(self):
+        """Test analyzing references."""
+        ranker = SymbolRanker()
+        
+        file_maps = {
+            "a.py": FileMap(
+                file_path="a.py",
+                symbols=[Symbol("MyClass", "class", "a.py", 1)]
+            ),
+            "b.py": FileMap(
+                file_path="b.py",
+                symbols=[Symbol("use_class", "function", "b.py", 1)]
+            )
+        }
+        
+        all_content = {
+            "a.py": "class MyClass:\n    pass",
+            "b.py": "from a import MyClass\nobj = MyClass()"
+        }
+        
+        ranker.analyze_references(file_maps, all_content)
+        
+        # MyClass should have references
+        my_class = file_maps["a.py"].symbols[0]
+        assert my_class.references > 0
+    
+    def test_get_top_symbols(self):
+        """Test getting top symbols."""
+        ranker = SymbolRanker()
+        
+        file_maps = {
+            "test.py": FileMap(
+                file_path="test.py",
+                symbols=[
+                    Symbol("HighRef", "class", "test.py", 1, references=10),
+                    Symbol("LowRef", "function", "test.py", 10, references=1),
+                    Symbol("MedRef", "function", "test.py", 20, references=5),
+                ]
+            )
+        }
+        
+        # Manually set references
+        file_maps["test.py"].symbols[0].references = 10
+        file_maps["test.py"].symbols[1].references = 1
+        file_maps["test.py"].symbols[2].references = 5
+        
+        top = ranker.get_top_symbols(file_maps, max_symbols=2)
+        
+        assert len(top) == 2
+        assert top[0].name == "HighRef"
+
+
+# ============================================================================
+# RepoMap Tests
+# ============================================================================
+
+class TestRepoMap:
+    """Tests for RepoMap."""
+    
+    @pytest.fixture
+    def temp_repo(self):
+        """Create a temporary repository."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            # Create some test files
+            (Path(tmpdir) / "main.py").write_text("""
+class Application:
+    def __init__(self):
+        self.config = Config()
+    
+    def run(self):
+        pass
+
+def main():
+    app = Application()
+    app.run()
+""")
+            
+            (Path(tmpdir) / "config.py").write_text("""
+class Config:
+    def __init__(self):
+        self.debug = False
+    
+    def load(self):
+        pass
+""")
+            
+            (Path(tmpdir) / "utils.py").write_text("""
+def helper_function():
+    pass
+
+def format_output(data):
+    return str(data)
+""")
+            
+            yield tmpdir
+    
+    def test_create_repo_map(self, temp_repo):
+        """Test creating a repo map."""
+        repo_map = RepoMap(root=temp_repo)
+        assert repo_map.root == Path(temp_repo)
+    
+    def test_scan_repository(self, temp_repo):
+        """Test scanning a repository."""
+        repo_map = RepoMap(root=temp_repo)
+        repo_map.scan()
+        
+        assert len(repo_map._file_maps) > 0
+    
+    def test_get_map(self, temp_repo):
+        """Test getting the repository map."""
+        repo_map = RepoMap(root=temp_repo)
+        map_str = repo_map.get_map()
+        
+        assert len(map_str) > 0
+        # Should contain file names
+        assert "main.py" in map_str or "config.py" in map_str
+    
+    def test_get_map_with_focus(self, temp_repo):
+        """Test getting map with focus files."""
+        repo_map = RepoMap(root=temp_repo)
+        repo_map.scan()
+        
+        map_str = repo_map.get_map(focus_files=["main.py"])
+        
+        assert "main.py" in map_str
+    
+    def test_get_file_symbols(self, temp_repo):
+        """Test getting symbols for a specific file."""
+        repo_map = RepoMap(root=temp_repo)
+        repo_map.scan()
+        
+        symbols = repo_map.get_file_symbols("main.py")
+        
+        assert len(symbols) > 0
+    
+    def test_get_symbol_context(self, temp_repo):
+        """Test getting context for a symbol."""
+        repo_map = RepoMap(root=temp_repo)
+        repo_map.scan()
+        
+        context = repo_map.get_symbol_context("Application")
+        
+        if context:  # May not find if symbol extraction differs
+            assert "Application" in context
+    
+    def test_refresh(self, temp_repo):
+        """Test refreshing the map."""
+        repo_map = RepoMap(root=temp_repo)
+        repo_map.scan()
+        
+        initial_count = len(repo_map._file_maps)
+        
+        repo_map.refresh()
+        
+        assert len(repo_map._file_maps) == initial_count
+
+
+# ============================================================================
+# RepoMapHandler Tests
+# ============================================================================
+
+class TestRepoMapHandler:
+    """Tests for RepoMapHandler."""
+    
+    @pytest.fixture
+    def temp_repo(self):
+        """Create a temporary repository."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "test.py").write_text("""
+class TestClass:
+    def test_method(self):
+        pass
+""")
+            yield tmpdir
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = RepoMapHandler()
+        assert handler.feature_name == "repo_map"
+    
+    def test_initialize(self, temp_repo):
+        """Test initializing handler."""
+        handler = RepoMapHandler()
+        repo_map = handler.initialize(root=temp_repo)
+        
+        assert repo_map is not None
+    
+    def test_get_map(self, temp_repo):
+        """Test getting map through handler."""
+        handler = RepoMapHandler()
+        handler.initialize(root=temp_repo)
+        
+        map_str = handler.get_map()
+        
+        assert len(map_str) > 0
+    
+    def test_refresh(self, temp_repo):
+        """Test refreshing through handler."""
+        handler = RepoMapHandler()
+        handler.initialize(root=temp_repo)
+        handler.get_map()
+        
+        handler.refresh()
+        
+        # Should not raise
+        map_str = handler.get_map()
+        assert len(map_str) > 0
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestRepoMapIntegration:
+    """Integration tests for RepoMap."""
+    
+    @pytest.fixture
+    def complex_repo(self):
+        """Create a more complex repository."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            # Create directory structure
+            src_dir = Path(tmpdir) / "src"
+            src_dir.mkdir()
+            
+            (src_dir / "app.py").write_text("""
+from .models import User
+from .utils import format_name
+
+class Application:
+    def __init__(self):
+        self.users = []
+    
+    def add_user(self, name):
+        user = User(format_name(name))
+        self.users.append(user)
+        return user
+    
+    def get_users(self):
+        return self.users
+""")
+            
+            (src_dir / "models.py").write_text("""
+class User:
+    def __init__(self, name):
+        self.name = name
+    
+    def __repr__(self):
+        return f"User({self.name})"
+
+class Admin(User):
+    def __init__(self, name, role):
+        super().__init__(name)
+        self.role = role
+""")
+            
+            (src_dir / "utils.py").write_text("""
+def format_name(name):
+    return name.strip().title()
+
+def validate_email(email):
+    return '@' in email
+""")
+            
+            yield tmpdir
+    
+    def test_full_scan_and_map(self, complex_repo):
+        """Test full scan and map generation."""
+        repo_map = RepoMap(root=complex_repo)
+        repo_map.scan()
+        
+        map_str = repo_map.get_map()
+        
+        # Should contain key symbols
+        assert len(map_str) > 0
+    
+    def test_symbol_ranking(self, complex_repo):
+        """Test that frequently referenced symbols rank higher."""
+        repo_map = RepoMap(root=complex_repo)
+        repo_map.scan()
+        
+        # User is referenced in multiple files
+        top_symbols = repo_map.ranker.get_top_symbols(repo_map._file_maps)
+        
+        # Should have some symbols
+        assert len(top_symbols) > 0
+    
+    def test_handler_workflow(self, complex_repo):
+        """Test complete handler workflow."""
+        handler = RepoMapHandler(verbose=False)
+        handler.initialize(root=complex_repo)
+        
+        # Get initial map
+        map1 = handler.get_map()
+        assert len(map1) > 0
+        
+        # Refresh
+        handler.refresh()
+        
+        # Get map again
+        map2 = handler.get_map()
+        assert len(map2) > 0
@@ -0,0 +1,373 @@
+"""
+Tests for Sandbox Executor System.
+
+Test-Driven Development approach for sandboxed execution.
+"""
+
+import tempfile
+
+from praisonai.cli.features.sandbox_executor import (
+    SandboxMode,
+    SandboxPolicy,
+    ExecutionResult,
+    CommandValidator,
+    SubprocessSandbox,
+    SandboxExecutorHandler,
+)
+
+
+# ============================================================================
+# SandboxMode Tests
+# ============================================================================
+
+class TestSandboxMode:
+    """Tests for SandboxMode enum."""
+    
+    def test_mode_values(self):
+        """Test mode enum values."""
+        assert SandboxMode.DISABLED.value == "disabled"
+        assert SandboxMode.BASIC.value == "basic"
+        assert SandboxMode.STRICT.value == "strict"
+        assert SandboxMode.NETWORK_ISOLATED.value == "network_isolated"
+    
+    def test_from_string_valid(self):
+        """Test parsing valid mode strings."""
+        assert SandboxMode.from_string("disabled") == SandboxMode.DISABLED
+        assert SandboxMode.from_string("basic") == SandboxMode.BASIC
+        assert SandboxMode.from_string("strict") == SandboxMode.STRICT
+    
+    def test_from_string_with_hyphen(self):
+        """Test parsing mode strings with hyphens."""
+        assert SandboxMode.from_string("network-isolated") == SandboxMode.NETWORK_ISOLATED
+    
+    def test_from_string_case_insensitive(self):
+        """Test case insensitive parsing."""
+        assert SandboxMode.from_string("BASIC") == SandboxMode.BASIC
+        assert SandboxMode.from_string("Strict") == SandboxMode.STRICT
+
+
+# ============================================================================
+# SandboxPolicy Tests
+# ============================================================================
+
+class TestSandboxPolicy:
+    """Tests for SandboxPolicy."""
+    
+    def test_default_policy(self):
+        """Test default policy."""
+        policy = SandboxPolicy()
+        
+        assert policy.mode == SandboxMode.DISABLED
+        assert policy.max_memory_mb == 512
+        assert policy.allow_network is True
+    
+    def test_for_mode_disabled(self):
+        """Test policy for disabled mode."""
+        policy = SandboxPolicy.for_mode(SandboxMode.DISABLED)
+        
+        assert policy.mode == SandboxMode.DISABLED
+    
+    def test_for_mode_basic(self):
+        """Test policy for basic mode."""
+        policy = SandboxPolicy.for_mode(SandboxMode.BASIC)
+        
+        assert policy.mode == SandboxMode.BASIC
+        assert policy.allow_network is True
+    
+    def test_for_mode_strict(self):
+        """Test policy for strict mode."""
+        policy = SandboxPolicy.for_mode(SandboxMode.STRICT)
+        
+        assert policy.mode == SandboxMode.STRICT
+        assert policy.max_memory_mb == 256
+        assert "curl" in policy.blocked_commands
+    
+    def test_for_mode_network_isolated(self):
+        """Test policy for network isolated mode."""
+        policy = SandboxPolicy.for_mode(SandboxMode.NETWORK_ISOLATED)
+        
+        assert policy.mode == SandboxMode.NETWORK_ISOLATED
+        assert policy.allow_network is False
+
+
+# ============================================================================
+# ExecutionResult Tests
+# ============================================================================
+
+class TestExecutionResult:
+    """Tests for ExecutionResult."""
+    
+    def test_create_result(self):
+        """Test creating execution result."""
+        result = ExecutionResult(
+            success=True,
+            exit_code=0,
+            stdout="output",
+            stderr="",
+            duration_ms=100.0,
+            was_sandboxed=True
+        )
+        
+        assert result.success is True
+        assert result.exit_code == 0
+        assert result.stdout == "output"
+    
+    def test_output_property(self):
+        """Test output property."""
+        result = ExecutionResult(
+            success=True,
+            exit_code=0,
+            stdout="out",
+            stderr="err",
+            duration_ms=100.0,
+            was_sandboxed=True
+        )
+        
+        assert result.output == "outerr"
+    
+    def test_policy_violations(self):
+        """Test policy violations."""
+        result = ExecutionResult(
+            success=False,
+            exit_code=-1,
+            stdout="",
+            stderr="blocked",
+            duration_ms=0.0,
+            was_sandboxed=True,
+            policy_violations=["Command blocked"]
+        )
+        
+        assert len(result.policy_violations) == 1
+
+
+# ============================================================================
+# CommandValidator Tests
+# ============================================================================
+
+class TestCommandValidator:
+    """Tests for CommandValidator."""
+    
+    def test_validate_disabled_mode(self):
+        """Test validation in disabled mode."""
+        policy = SandboxPolicy(mode=SandboxMode.DISABLED)
+        validator = CommandValidator(policy)
+        
+        violations = validator.validate("rm -rf /")
+        
+        assert len(violations) == 0  # No validation in disabled mode
+    
+    def test_validate_blocked_command(self):
+        """Test validation of blocked command."""
+        policy = SandboxPolicy(
+            mode=SandboxMode.BASIC,
+            blocked_commands={"rm", "sudo"}
+        )
+        validator = CommandValidator(policy)
+        
+        violations = validator.validate("rm file.txt")
+        
+        assert len(violations) > 0
+        assert "rm" in violations[0]
+    
+    def test_validate_dangerous_pattern(self):
+        """Test validation of dangerous patterns."""
+        policy = SandboxPolicy(mode=SandboxMode.BASIC)
+        validator = CommandValidator(policy)
+        
+        violations = validator.validate("echo test | sh")
+        
+        assert len(violations) > 0
+    
+    def test_validate_blocked_path(self):
+        """Test validation of blocked paths."""
+        policy = SandboxPolicy(
+            mode=SandboxMode.BASIC,
+            blocked_paths={"/etc", "/var"}
+        )
+        validator = CommandValidator(policy)
+        
+        violations = validator.validate("cat /etc/passwd")
+        
+        assert len(violations) > 0
+    
+    def test_is_allowed(self):
+        """Test is_allowed method."""
+        policy = SandboxPolicy(
+            mode=SandboxMode.BASIC,
+            blocked_commands={"rm"}
+        )
+        validator = CommandValidator(policy)
+        
+        assert validator.is_allowed("ls -la") is True
+        assert validator.is_allowed("rm file.txt") is False
+
+
+# ============================================================================
+# SubprocessSandbox Tests
+# ============================================================================
+
+class TestSubprocessSandbox:
+    """Tests for SubprocessSandbox."""
+    
+    def test_create_sandbox(self):
+        """Test creating sandbox."""
+        sandbox = SubprocessSandbox()
+        assert sandbox is not None
+    
+    def test_execute_disabled_mode(self):
+        """Test execution in disabled mode."""
+        policy = SandboxPolicy(mode=SandboxMode.DISABLED)
+        sandbox = SubprocessSandbox(policy=policy)
+        
+        result = sandbox.execute("echo hello")
+        
+        assert result.success is True
+        assert "hello" in result.stdout
+        assert result.was_sandboxed is False
+    
+    def test_execute_basic_mode(self):
+        """Test execution in basic mode."""
+        policy = SandboxPolicy.for_mode(SandboxMode.BASIC)
+        sandbox = SubprocessSandbox(policy=policy)
+        
+        result = sandbox.execute("echo hello")
+        
+        assert result.success is True
+        assert "hello" in result.stdout
+        assert result.was_sandboxed is True
+    
+    def test_execute_blocked_command(self):
+        """Test execution of blocked command."""
+        policy = SandboxPolicy(
+            mode=SandboxMode.BASIC,
+            blocked_commands={"rm"}
+        )
+        sandbox = SubprocessSandbox(policy=policy)
+        
+        result = sandbox.execute("rm test.txt")
+        
+        assert result.success is False
+        assert len(result.policy_violations) > 0
+    
+    def test_execute_timeout(self):
+        """Test execution timeout."""
+        policy = SandboxPolicy(mode=SandboxMode.BASIC)
+        sandbox = SubprocessSandbox(policy=policy)
+        
+        result = sandbox.execute("sleep 10", timeout=0.1)
+        
+        assert result.success is False
+        assert "timed out" in result.stderr.lower()
+    
+    def test_execute_with_working_dir(self):
+        """Test execution with working directory."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            policy = SandboxPolicy(mode=SandboxMode.BASIC)
+            sandbox = SubprocessSandbox(policy=policy, working_dir=tmpdir)
+            
+            result = sandbox.execute("pwd")
+            
+            assert result.success is True
+            assert tmpdir in result.stdout
+
+
+# ============================================================================
+# SandboxExecutorHandler Tests
+# ============================================================================
+
+class TestSandboxExecutorHandler:
+    """Tests for SandboxExecutorHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = SandboxExecutorHandler()
+        assert handler.feature_name == "sandbox_executor"
+        assert handler.is_enabled is False
+    
+    def test_initialize_disabled(self):
+        """Test initializing with disabled mode."""
+        handler = SandboxExecutorHandler()
+        sandbox = handler.initialize(mode="disabled")
+        
+        assert sandbox is not None
+        assert handler.is_enabled is False
+    
+    def test_initialize_basic(self):
+        """Test initializing with basic mode."""
+        handler = SandboxExecutorHandler()
+        sandbox = handler.initialize(mode="basic")
+        
+        assert sandbox is not None
+        assert handler.is_enabled is True
+    
+    def test_execute(self):
+        """Test executing command."""
+        handler = SandboxExecutorHandler()
+        handler.initialize(mode="basic")
+        
+        result = handler.execute("echo test")
+        
+        assert result.success is True
+        assert "test" in result.stdout
+    
+    def test_validate_command(self):
+        """Test validating command."""
+        handler = SandboxExecutorHandler()
+        handler.initialize(mode="basic")
+        
+        violations = handler.validate_command("echo hello")
+        assert len(violations) == 0
+    
+    def test_get_mode(self):
+        """Test getting mode."""
+        handler = SandboxExecutorHandler()
+        
+        assert handler.get_mode() == "disabled"
+        
+        handler.initialize(mode="strict")
+        assert handler.get_mode() == "strict"
+
+
+# ============================================================================
+# Integration Tests
+# ============================================================================
+
+class TestSandboxIntegration:
+    """Integration tests for Sandbox."""
+    
+    def test_full_workflow_disabled(self):
+        """Test full workflow with sandbox disabled."""
+        handler = SandboxExecutorHandler()
+        handler.initialize(mode="disabled")
+        
+        # Should execute without sandboxing
+        result = handler.execute("echo hello")
+        
+        assert result.success is True
+        assert result.was_sandboxed is False
+    
+    def test_full_workflow_basic(self):
+        """Test full workflow with basic sandbox."""
+        handler = SandboxExecutorHandler()
+        handler.initialize(mode="basic")
+        
+        # Safe command should work
+        result = handler.execute("echo hello")
+        assert result.success is True
+        assert result.was_sandboxed is True
+        
+        # Blocked command should fail
+        result = handler.execute("rm -rf /")
+        assert result.success is False
+        assert len(result.policy_violations) > 0
+    
+    def test_strict_mode_isolation(self):
+        """Test strict mode isolation."""
+        handler = SandboxExecutorHandler()
+        handler.initialize(mode="strict")
+        
+        # Should work in isolated environment
+        result = handler.execute("echo $HOME")
+        
+        assert result.success is True
+        assert result.was_sandboxed is True
@@ -0,0 +1,608 @@
+"""
+Tests for Slash Commands System.
+
+Test-Driven Development approach:
+1. Write tests first
+2. Implement features to pass tests
+3. Refactor while keeping tests green
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+import time
+
+from praisonai.cli.features.slash_commands import (
+    SlashCommand,
+    CommandContext,
+    CommandKind,
+    SlashCommandRegistry,
+    SlashCommandParser,
+    SlashCommandHandler,
+    create_default_registry,
+    cmd_help,
+    cmd_cost,
+    cmd_clear,
+    cmd_model,
+    cmd_tokens,
+    cmd_plan,
+    cmd_exit,
+)
+
+
+# ============================================================================
+# SlashCommand Tests
+# ============================================================================
+
+class TestSlashCommand:
+    """Tests for SlashCommand dataclass."""
+    
+    def test_create_basic_command(self):
+        """Test creating a basic slash command."""
+        cmd = SlashCommand(
+            name="test",
+            description="A test command"
+        )
+        assert cmd.name == "test"
+        assert cmd.description == "A test command"
+        assert cmd.action is None
+        assert cmd.alt_names == []
+        assert cmd.sub_commands == []
+        assert cmd.kind == CommandKind.BUILT_IN
+        assert cmd.auto_execute is True
+    
+    def test_create_command_with_action(self):
+        """Test creating a command with an action."""
+        def my_action(ctx, args):
+            return {"result": "success"}
+        
+        cmd = SlashCommand(
+            name="mycommand",
+            description="My command",
+            action=my_action
+        )
+        assert cmd.action is not None
+        result = cmd.action(None, "")
+        assert result == {"result": "success"}
+    
+    def test_create_command_with_aliases(self):
+        """Test creating a command with aliases."""
+        cmd = SlashCommand(
+            name="help",
+            description="Show help",
+            alt_names=["h", "?"]
+        )
+        assert "h" in cmd.alt_names
+        assert "?" in cmd.alt_names
+    
+    def test_create_command_with_subcommands(self):
+        """Test creating a command with sub-commands."""
+        sub1 = SlashCommand(name="sub1", description="Sub 1")
+        sub2 = SlashCommand(name="sub2", description="Sub 2")
+        
+        cmd = SlashCommand(
+            name="parent",
+            description="Parent command",
+            sub_commands=[sub1, sub2]
+        )
+        assert len(cmd.sub_commands) == 2
+        assert cmd.sub_commands[0].name == "sub1"
+    
+    def test_empty_name_raises_error(self):
+        """Test that empty name raises ValueError."""
+        with pytest.raises(ValueError, match="Command name cannot be empty"):
+            SlashCommand(name="", description="Empty name")
+    
+    def test_command_kinds(self):
+        """Test different command kinds."""
+        builtin = SlashCommand(name="builtin", description="Built-in", kind=CommandKind.BUILT_IN)
+        custom = SlashCommand(name="custom", description="Custom", kind=CommandKind.CUSTOM)
+        mcp = SlashCommand(name="mcp", description="MCP", kind=CommandKind.MCP)
+        
+        assert builtin.kind == CommandKind.BUILT_IN
+        assert custom.kind == CommandKind.CUSTOM
+        assert mcp.kind == CommandKind.MCP
+
+
+# ============================================================================
+# CommandContext Tests
+# ============================================================================
+
+class TestCommandContext:
+    """Tests for CommandContext dataclass."""
+    
+    def test_create_default_context(self):
+        """Test creating a default context."""
+        ctx = CommandContext()
+        assert ctx.agent is None
+        assert ctx.config == {}
+        assert ctx.session_id is None
+        assert ctx.total_tokens == 0
+        assert ctx.total_cost == 0.0
+        assert ctx.prompt_count == 0
+    
+    def test_context_with_metrics(self):
+        """Test context with metrics."""
+        ctx = CommandContext(
+            total_tokens=1500,
+            total_cost=0.0045,
+            prompt_count=3
+        )
+        assert ctx.total_tokens == 1500
+        assert ctx.total_cost == 0.0045
+        assert ctx.prompt_count == 3
+    
+    def test_context_with_session(self):
+        """Test context with session info."""
+        start_time = time.time()
+        ctx = CommandContext(
+            session_id="test-session-123",
+            session_start_time=start_time
+        )
+        assert ctx.session_id == "test-session-123"
+        assert ctx.session_start_time == start_time
+
+
+# ============================================================================
+# SlashCommandRegistry Tests
+# ============================================================================
+
+class TestSlashCommandRegistry:
+    """Tests for SlashCommandRegistry."""
+    
+    def test_register_command(self):
+        """Test registering a command."""
+        registry = SlashCommandRegistry()
+        cmd = SlashCommand(name="test", description="Test")
+        
+        registry.register(cmd)
+        
+        assert registry.get("test") is not None
+        assert registry.get("test").name == "test"
+    
+    def test_register_command_with_aliases(self):
+        """Test registering a command with aliases."""
+        registry = SlashCommandRegistry()
+        cmd = SlashCommand(
+            name="help",
+            description="Help",
+            alt_names=["h", "?"]
+        )
+        
+        registry.register(cmd)
+        
+        # Should be accessible by name and aliases
+        assert registry.get("help") is not None
+        assert registry.get("h") is not None
+        assert registry.get("?") is not None
+        
+        # All should return the same command
+        assert registry.get("help") == registry.get("h")
+        assert registry.get("h") == registry.get("?")
+    
+    def test_get_nonexistent_command(self):
+        """Test getting a non-existent command."""
+        registry = SlashCommandRegistry()
+        assert registry.get("nonexistent") is None
+    
+    def test_unregister_command(self):
+        """Test unregistering a command."""
+        registry = SlashCommandRegistry()
+        cmd = SlashCommand(name="test", description="Test", alt_names=["t"])
+        
+        registry.register(cmd)
+        assert registry.get("test") is not None
+        
+        result = registry.unregister("test")
+        assert result is True
+        assert registry.get("test") is None
+        assert registry.get("t") is None  # Alias should also be removed
+    
+    def test_unregister_nonexistent(self):
+        """Test unregistering a non-existent command."""
+        registry = SlashCommandRegistry()
+        result = registry.unregister("nonexistent")
+        assert result is False
+    
+    def test_get_all_commands(self):
+        """Test getting all commands."""
+        registry = SlashCommandRegistry()
+        registry.register(SlashCommand(name="cmd1", description="Cmd 1"))
+        registry.register(SlashCommand(name="cmd2", description="Cmd 2"))
+        registry.register(SlashCommand(name="cmd3", description="Cmd 3"))
+        
+        all_cmds = registry.get_all()
+        assert len(all_cmds) == 3
+        names = [cmd.name for cmd in all_cmds]
+        assert "cmd1" in names
+        assert "cmd2" in names
+        assert "cmd3" in names
+    
+    def test_get_names(self):
+        """Test getting all command names including aliases."""
+        registry = SlashCommandRegistry()
+        registry.register(SlashCommand(name="help", description="Help", alt_names=["h"]))
+        registry.register(SlashCommand(name="exit", description="Exit", alt_names=["q", "quit"]))
+        
+        names = registry.get_names()
+        assert "help" in names
+        assert "h" in names
+        assert "exit" in names
+        assert "q" in names
+        assert "quit" in names
+
+
+# ============================================================================
+# SlashCommandParser Tests
+# ============================================================================
+
+class TestSlashCommandParser:
+    """Tests for SlashCommandParser."""
+    
+    @pytest.fixture
+    def parser(self):
+        """Create a parser with test commands."""
+        registry = SlashCommandRegistry()
+        registry.register(SlashCommand(name="help", description="Help", alt_names=["h"]))
+        registry.register(SlashCommand(name="cost", description="Cost"))
+        registry.register(SlashCommand(
+            name="memory",
+            description="Memory",
+            sub_commands=[
+                SlashCommand(name="add", description="Add memory"),
+                SlashCommand(name="list", description="List memories"),
+            ]
+        ))
+        return SlashCommandParser(registry)
+    
+    def test_is_slash_command(self, parser):
+        """Test slash command detection."""
+        assert parser.is_slash_command("/help") is True
+        assert parser.is_slash_command("/cost") is True
+        assert parser.is_slash_command("help") is False
+        assert parser.is_slash_command("") is False
+    
+    def test_is_not_code_comment(self, parser):
+        """Test that code comments are not detected as commands."""
+        assert parser.is_slash_command("// This is a comment") is False
+        assert parser.is_slash_command("/* Block comment */") is False
+    
+    def test_parse_simple_command(self, parser):
+        """Test parsing a simple command."""
+        result = parser.parse("/help")
+        
+        assert result.command is not None
+        assert result.command.name == "help"
+        assert result.args == ""
+        assert result.canonical_path == ["help"]
+        assert result.error is None
+    
+    def test_parse_command_with_args(self, parser):
+        """Test parsing a command with arguments."""
+        result = parser.parse("/help model")
+        
+        assert result.command is not None
+        assert result.command.name == "help"
+        assert result.args == "model"
+    
+    def test_parse_command_by_alias(self, parser):
+        """Test parsing a command by alias."""
+        result = parser.parse("/h")
+        
+        assert result.command is not None
+        assert result.command.name == "help"
+    
+    def test_parse_subcommand(self, parser):
+        """Test parsing a sub-command."""
+        result = parser.parse("/memory add some data")
+        
+        assert result.command is not None
+        assert result.command.name == "add"
+        assert result.args == "some data"
+        assert result.canonical_path == ["memory", "add"]
+    
+    def test_parse_unknown_command(self, parser):
+        """Test parsing an unknown command."""
+        result = parser.parse("/unknown")
+        
+        assert result.command is None
+        assert result.canonical_path == []
+    
+    def test_parse_empty_command(self, parser):
+        """Test parsing empty command."""
+        result = parser.parse("/")
+        
+        assert result.error == "Empty command"
+    
+    def test_parse_not_slash_command(self, parser):
+        """Test parsing non-slash command."""
+        result = parser.parse("regular text")
+        
+        assert result.error == "Not a slash command"
+
+
+# ============================================================================
+# Built-in Command Tests
+# ============================================================================
+
+class TestBuiltinCommands:
+    """Tests for built-in commands."""
+    
+    @pytest.fixture
+    def context(self):
+        """Create a test context."""
+        ctx = CommandContext(
+            total_tokens=1000,
+            total_cost=0.003,
+            prompt_count=5,
+            session_start_time=time.time() - 120  # 2 minutes ago
+        )
+        ctx.config["command_registry"] = create_default_registry()
+        return ctx
+    
+    def test_cmd_help_general(self, context):
+        """Test general help command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_help(context, "")
+        
+        assert result["type"] == "help"
+    
+    def test_cmd_help_specific(self, context):
+        """Test help for specific command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_help(context, "cost")
+        
+        assert result["type"] == "help"
+        assert result["command"] == "cost"
+    
+    def test_cmd_help_unknown(self, context):
+        """Test help for unknown command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_help(context, "unknown_cmd")
+        
+        assert result["type"] == "error"
+    
+    def test_cmd_cost(self, context):
+        """Test cost command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_cost(context, "")
+        
+        assert result["type"] == "stats"
+        assert result["tokens"] == 1000
+        assert result["cost"] == 0.003
+        assert result["prompts"] == 5
+    
+    def test_cmd_clear(self, context):
+        """Test clear command."""
+        mock_agent = MagicMock()
+        context.agent = mock_agent
+        
+        with patch('rich.console.Console.print'):
+            result = cmd_clear(context, "")
+        
+        assert result["type"] == "clear"
+        mock_agent.clear_history.assert_called_once()
+    
+    def test_cmd_model_show(self, context):
+        """Test model command without args (show current)."""
+        mock_agent = MagicMock()
+        mock_agent.llm = MagicMock(model="gpt-4o")
+        context.agent = mock_agent
+        
+        with patch('rich.console.Console.print'):
+            result = cmd_model(context, "")
+        
+        assert result["type"] == "model_info"
+        assert result["model"] == "gpt-4o"
+    
+    def test_cmd_model_change(self, context):
+        """Test model command with args (change model)."""
+        mock_agent = MagicMock()
+        context.agent = mock_agent
+        
+        with patch('rich.console.Console.print'):
+            result = cmd_model(context, "gpt-4o-mini")
+        
+        assert result["type"] == "model_change"
+        assert result["model"] == "gpt-4o-mini"
+    
+    def test_cmd_tokens(self, context):
+        """Test tokens command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_tokens(context, "")
+        
+        assert result["type"] == "tokens"
+        assert result["total"] == 1000
+    
+    def test_cmd_plan_with_args(self, context):
+        """Test plan command with task."""
+        with patch('rich.console.Console.print'):
+            result = cmd_plan(context, "build a REST API")
+        
+        assert result["type"] == "submit_prompt"
+        assert "build a REST API" in result["content"]
+    
+    def test_cmd_plan_without_args(self, context):
+        """Test plan command without task."""
+        with patch('rich.console.Console.print'):
+            result = cmd_plan(context, "")
+        
+        assert result["type"] == "help"
+    
+    def test_cmd_exit(self, context):
+        """Test exit command."""
+        with patch('rich.console.Console.print'):
+            result = cmd_exit(context, "")
+        
+        assert result["type"] == "exit"
+
+
+# ============================================================================
+# SlashCommandHandler Tests
+# ============================================================================
+
+class TestSlashCommandHandler:
+    """Tests for SlashCommandHandler."""
+    
+    def test_handler_creation(self):
+        """Test handler creation."""
+        handler = SlashCommandHandler()
+        assert handler.registry is not None
+        assert handler.parser is not None
+    
+    def test_is_command(self):
+        """Test command detection."""
+        handler = SlashCommandHandler()
+        
+        assert handler.is_command("/help") is True
+        assert handler.is_command("/cost") is True
+        assert handler.is_command("regular text") is False
+    
+    def test_execute_help(self):
+        """Test executing help command."""
+        handler = SlashCommandHandler()
+        
+        with patch('rich.console.Console.print'):
+            result = handler.execute("/help")
+        
+        assert result is not None
+        assert result["type"] == "help"
+    
+    def test_execute_unknown_command(self):
+        """Test executing unknown command."""
+        handler = SlashCommandHandler()
+        
+        result = handler.execute("/unknown_command_xyz")
+        
+        assert result is not None
+        assert result["type"] == "error"
+    
+    def test_execute_non_command(self):
+        """Test executing non-command text."""
+        handler = SlashCommandHandler()
+        
+        result = handler.execute("regular text")
+        
+        assert result is None
+    
+    def test_register_custom_command(self):
+        """Test registering a custom command."""
+        handler = SlashCommandHandler()
+        
+        def custom_action(ctx, args):
+            return {"type": "custom", "args": args}
+        
+        handler.register_command(SlashCommand(
+            name="custom",
+            description="Custom command",
+            action=custom_action
+        ))
+        
+        result = handler.execute("/custom test args")
+        
+        assert result is not None
+        assert result["type"] == "custom"
+        assert result["args"] == "test args"
+    
+    def test_get_completions(self):
+        """Test command completions."""
+        handler = SlashCommandHandler()
+        
+        completions = handler.get_completions("/he")
+        assert "/help" in completions
+        
+        completions = handler.get_completions("/co")
+        assert "/cost" in completions
+        assert "/commit" in completions
+        
+        completions = handler.get_completions("regular")
+        assert completions == []
+    
+    def test_set_context(self):
+        """Test setting context."""
+        handler = SlashCommandHandler()
+        ctx = CommandContext(total_tokens=500)
+        
+        handler.set_context(ctx)
+        
+        assert handler._context is ctx
+        assert "command_registry" in ctx.config
+
+
+# ============================================================================
+# Default Registry Tests
+# ============================================================================
+
+class TestDefaultRegistry:
+    """Tests for default command registry."""
+    
+    def test_default_registry_has_core_commands(self):
+        """Test that default registry has core commands."""
+        registry = create_default_registry()
+        
+        # Core commands should exist
+        assert registry.get("help") is not None
+        assert registry.get("cost") is not None
+        assert registry.get("clear") is not None
+        assert registry.get("model") is not None
+        assert registry.get("tokens") is not None
+        assert registry.get("plan") is not None
+        assert registry.get("exit") is not None
+    
+    def test_default_registry_aliases(self):
+        """Test that default registry has aliases."""
+        registry = create_default_registry()
+        
+        # Help aliases
+        assert registry.get("h") is not None
+        assert registry.get("?") is not None
+        
+        # Exit aliases
+        assert registry.get("q") is not None
+        assert registry.get("quit") is not None
+        
+        # Cost aliases
+        assert registry.get("usage") is not None
+        assert registry.get("stats") is not None
+
+
+# ============================================================================
+# Integration Tests (require real execution)
+# ============================================================================
+
+class TestSlashCommandsIntegration:
+    """Integration tests for slash commands."""
+    
+    def test_full_command_flow(self):
+        """Test full command execution flow."""
+        handler = SlashCommandHandler(verbose=True)
+        
+        # Set up context
+        ctx = CommandContext(
+            total_tokens=2500,
+            total_cost=0.0075,
+            prompt_count=10,
+            session_start_time=time.time() - 300
+        )
+        handler.set_context(ctx)
+        
+        # Execute commands
+        with patch('rich.console.Console.print'):
+            help_result = handler.execute("/help")
+            cost_result = handler.execute("/cost")
+            tokens_result = handler.execute("/tokens")
+        
+        assert help_result["type"] == "help"
+        assert cost_result["type"] == "stats"
+        assert cost_result["tokens"] == 2500
+        assert tokens_result["type"] == "tokens"
+    
+    def test_command_with_special_characters(self):
+        """Test commands with special characters in args."""
+        handler = SlashCommandHandler()
+        
+        with patch('rich.console.Console.print'):
+            result = handler.execute("/plan Build a REST API with /users endpoint")
+        
+        assert result is not None
+        assert result["type"] == "submit_prompt"
+        assert "/users" in result["content"]
@@ -0,0 +1 @@
+"""Tests for CLI integrations."""
@@ -0,0 +1,295 @@
+"""
+Tests for BaseCLIIntegration class.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+import asyncio
+import json
+from unittest.mock import patch, MagicMock, AsyncMock
+import sys
+import os
+
+# Add the praisonai package to the path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestBaseCLIIntegration:
+    """Tests for the BaseCLIIntegration abstract base class."""
+    
+    def test_import_base_integration(self):
+        """Test that BaseCLIIntegration can be imported."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        assert BaseCLIIntegration is not None
+    
+    def test_base_integration_is_abstract(self):
+        """Test that BaseCLIIntegration cannot be instantiated directly."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        with pytest.raises(TypeError):
+            BaseCLIIntegration()
+    
+    def test_concrete_implementation_requires_cli_command(self):
+        """Test that concrete implementations must define cli_command."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class IncompleteIntegration(BaseCLIIntegration):
+            pass
+        
+        with pytest.raises(TypeError):
+            IncompleteIntegration()
+    
+    def test_is_available_returns_false_for_missing_cli(self):
+        """Test is_available returns False when CLI is not installed."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "nonexistent_cli_tool_12345"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        assert integration.is_available is False
+    
+    def test_is_available_caches_result(self):
+        """Test that is_available caches the availability check."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "nonexistent_cli_12345"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        # First call
+        result1 = integration.is_available
+        # Second call should use cache
+        result2 = integration.is_available
+        assert result1 == result2
+    
+    def test_workspace_default_is_current_dir(self):
+        """Test that default workspace is current directory."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "test"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        assert integration.workspace == "."
+    
+    def test_workspace_can_be_set(self):
+        """Test that workspace can be set during initialization."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "test"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration(workspace="/custom/path")
+        assert integration.workspace == "/custom/path"
+    
+    def test_timeout_default_is_300(self):
+        """Test that default timeout is 300 seconds."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "test"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        assert integration.timeout == 300
+    
+    def test_as_tool_returns_callable(self):
+        """Test that as_tool returns a callable function."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "test"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return "test result"
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        tool = integration.as_tool()
+        assert callable(tool)
+    
+    def test_as_tool_has_correct_name(self):
+        """Test that the tool function has the correct name."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "my_cli"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        tool = integration.as_tool()
+        assert tool.__name__ == "my_cli_tool"
+    
+    def test_as_tool_has_docstring(self):
+        """Test that the tool function has a docstring."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "test"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        tool = integration.as_tool()
+        assert tool.__doc__ is not None
+        assert "test" in tool.__doc__
+
+
+class TestBaseCLIIntegrationAsync:
+    """Async tests for BaseCLIIntegration."""
+    
+    @pytest.mark.asyncio
+    async def test_execute_async_runs_command(self):
+        """Test that execute_async runs a command."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "echo"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return await self.execute_async(["echo", prompt])
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        result = await integration.execute("hello")
+        assert "hello" in result
+    
+    @pytest.mark.asyncio
+    async def test_execute_async_handles_timeout(self):
+        """Test that execute_async handles timeout."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "sleep"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return await self.execute_async(["sleep", "10"], timeout=0.1)
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        with pytest.raises(TimeoutError):
+            await integration.execute("test")
+    
+    @pytest.mark.asyncio
+    async def test_execute_async_captures_stderr(self):
+        """Test that execute_async captures stderr."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "bash"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                stdout, stderr = await self.execute_async_with_stderr(
+                    ["bash", "-c", "echo error >&2"]
+                )
+                return stderr
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration = TestIntegration()
+        result = await integration.execute("test")
+        assert "error" in result
+
+
+class TestAvailabilityCache:
+    """Tests for the availability caching mechanism."""
+    
+    def test_availability_cache_is_class_level(self):
+        """Test that availability cache is shared across instances."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        class TestIntegration(BaseCLIIntegration):
+            @property
+            def cli_command(self) -> str:
+                return "shared_test_cli"
+            
+            async def execute(self, prompt: str, **options) -> str:
+                return ""
+            
+            async def stream(self, prompt: str, **options):
+                yield {}
+        
+        integration1 = TestIntegration()
+        integration2 = TestIntegration()
+        
+        # Access is_available on first instance
+        _ = integration1.is_available
+        
+        # Second instance should use cached value
+        assert "shared_test_cli" in BaseCLIIntegration._availability_cache
+    
+    def test_clear_availability_cache(self):
+        """Test that availability cache can be cleared."""
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        # Clear cache
+        BaseCLIIntegration._availability_cache.clear()
+        assert len(BaseCLIIntegration._availability_cache) == 0
@@ -0,0 +1,173 @@
+"""
+Tests for ClaudeCodeIntegration.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+import json
+from unittest.mock import patch, AsyncMock, MagicMock
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestClaudeCodeIntegration:
+    """Tests for ClaudeCodeIntegration class."""
+    
+    def test_import_claude_code_integration(self):
+        """Test that ClaudeCodeIntegration can be imported."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        assert ClaudeCodeIntegration is not None
+    
+    def test_cli_command_is_claude(self):
+        """Test that cli_command returns 'claude'."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        integration = ClaudeCodeIntegration()
+        assert integration.cli_command == "claude"
+    
+    def test_inherits_from_base(self):
+        """Test that ClaudeCodeIntegration inherits from BaseCLIIntegration."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        integration = ClaudeCodeIntegration()
+        assert isinstance(integration, BaseCLIIntegration)
+    
+    def test_default_options(self):
+        """Test default options are set correctly."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        assert integration.output_format == "json"
+        assert integration.skip_permissions is True
+    
+    def test_custom_options(self):
+        """Test custom options can be set."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(
+            output_format="text",
+            skip_permissions=False,
+            system_prompt="You are a Python expert"
+        )
+        assert integration.output_format == "text"
+        assert integration.skip_permissions is False
+        assert integration.system_prompt == "You are a Python expert"
+    
+    def test_build_command_basic(self):
+        """Test building basic command."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        cmd = integration._build_command("Hello")
+        
+        assert cmd[0] == "claude"
+        assert "-p" in cmd
+        assert "Hello" in cmd
+        assert "--output-format" in cmd
+        assert "json" in cmd
+    
+    def test_build_command_with_continue(self):
+        """Test building command with continue flag."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        cmd = integration._build_command("Hello", continue_session=True)
+        
+        assert "--continue" in cmd
+    
+    def test_build_command_with_system_prompt(self):
+        """Test building command with system prompt."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(system_prompt="Be helpful")
+        cmd = integration._build_command("Hello")
+        
+        assert "--append-system-prompt" in cmd
+        assert "Be helpful" in cmd
+    
+    def test_build_command_with_allowed_tools(self):
+        """Test building command with allowed tools."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(allowed_tools=["Read", "Write"])
+        cmd = integration._build_command("Hello")
+        
+        assert "--allowedTools" in cmd
+
+
+class TestClaudeCodeIntegrationAsync:
+    """Async tests for ClaudeCodeIntegration."""
+    
+    @pytest.mark.asyncio
+    async def test_execute_parses_json_output(self):
+        """Test that execute parses JSON output correctly."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        
+        mock_output = json.dumps({
+            "result": "Hello, world!",
+            "cost_usd": 0.001
+        })
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = mock_output
+            result = await integration.execute("Say hello")
+            
+            assert "Hello, world!" in result
+    
+    @pytest.mark.asyncio
+    async def test_execute_handles_text_output(self):
+        """Test that execute handles text output format."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(output_format="text")
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = "Hello, world!"
+            result = await integration.execute("Say hello")
+            
+            assert result == "Hello, world!"
+    
+    @pytest.mark.asyncio
+    async def test_stream_yields_events(self):
+        """Test that stream yields parsed events."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        
+        async def mock_stream(*args, **kwargs):
+            yield '{"type": "assistant", "content": "Hello"}'
+            yield '{"type": "result", "content": "Done"}'
+        
+        with patch.object(integration, 'stream_async', side_effect=mock_stream):
+            events = []
+            async for event in integration.stream("Say hello"):
+                events.append(event)
+            
+            assert len(events) >= 0  # May be empty if stream_async not called correctly
+
+
+class TestClaudeCodeSDKIntegration:
+    """Tests for Claude Code SDK integration (when available)."""
+    
+    def test_sdk_available_property(self):
+        """Test sdk_available property."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration()
+        # Should be a boolean
+        assert isinstance(integration.sdk_available, bool)
+    
+    def test_use_sdk_option(self):
+        """Test use_sdk option."""
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        integration = ClaudeCodeIntegration(use_sdk=True)
+        assert integration.use_sdk is True
+        
+        integration2 = ClaudeCodeIntegration(use_sdk=False)
+        assert integration2.use_sdk is False
@@ -0,0 +1,154 @@
+"""
+Tests for CodexCLIIntegration.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+import json
+from unittest.mock import patch, AsyncMock
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestCodexCLIIntegration:
+    """Tests for CodexCLIIntegration class."""
+    
+    def test_import_codex_cli_integration(self):
+        """Test that CodexCLIIntegration can be imported."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        assert CodexCLIIntegration is not None
+    
+    def test_cli_command_is_codex(self):
+        """Test that cli_command returns 'codex'."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        integration = CodexCLIIntegration()
+        assert integration.cli_command == "codex"
+    
+    def test_inherits_from_base(self):
+        """Test that CodexCLIIntegration inherits from BaseCLIIntegration."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        integration = CodexCLIIntegration()
+        assert isinstance(integration, BaseCLIIntegration)
+    
+    def test_default_options(self):
+        """Test default options are set correctly."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration()
+        assert integration.full_auto is False
+        assert integration.sandbox == "default"
+    
+    def test_full_auto_option(self):
+        """Test full_auto option can be set."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(full_auto=True)
+        assert integration.full_auto is True
+    
+    def test_sandbox_option(self):
+        """Test sandbox option can be set."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(sandbox="danger-full-access")
+        assert integration.sandbox == "danger-full-access"
+    
+    def test_build_command_basic(self):
+        """Test building basic command."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration()
+        cmd = integration._build_command("Fix the bug")
+        
+        assert cmd[0] == "codex"
+        assert "exec" in cmd
+        assert "Fix the bug" in cmd
+    
+    def test_build_command_with_full_auto(self):
+        """Test building command with full_auto."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(full_auto=True)
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "--full-auto" in cmd
+    
+    def test_build_command_with_json(self):
+        """Test building command with JSON output."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(json_output=True)
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "--json" in cmd
+    
+    def test_build_command_with_sandbox(self):
+        """Test building command with sandbox."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(sandbox="danger-full-access")
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "--sandbox" in cmd
+        assert "danger-full-access" in cmd
+
+
+class TestCodexCLIIntegrationAsync:
+    """Async tests for CodexCLIIntegration."""
+    
+    @pytest.mark.asyncio
+    async def test_execute_returns_result(self):
+        """Test that execute returns the result."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration()
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = "Task completed successfully"
+            result = await integration.execute("Fix the bug")
+            
+            assert "Task completed" in result
+    
+    @pytest.mark.asyncio
+    async def test_execute_parses_json_events(self):
+        """Test that execute parses JSON events when json_output is True."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(json_output=True)
+        
+        mock_output = '\n'.join([
+            '{"type":"thread.started","thread_id":"123"}',
+            '{"type":"item.completed","item":{"type":"agent_message","text":"Done"}}',
+            '{"type":"turn.completed"}'
+        ])
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = mock_output
+            result = await integration.execute("Fix the bug")
+            
+            assert "Done" in result
+
+
+class TestCodexCLIStructuredOutput:
+    """Tests for Codex CLI structured output."""
+    
+    def test_output_schema_option(self):
+        """Test output_schema option."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(output_schema="/path/to/schema.json")
+        assert integration.output_schema == "/path/to/schema.json"
+    
+    def test_build_command_with_output_schema(self):
+        """Test building command with output schema."""
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        integration = CodexCLIIntegration(output_schema="/path/to/schema.json")
+        cmd = integration._build_command("Extract metadata")
+        
+        assert "--output-schema" in cmd
+        assert "/path/to/schema.json" in cmd
@@ -0,0 +1,177 @@
+"""
+Tests for CursorCLIIntegration.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+import json
+from unittest.mock import patch, AsyncMock
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestCursorCLIIntegration:
+    """Tests for CursorCLIIntegration class."""
+    
+    def test_import_cursor_cli_integration(self):
+        """Test that CursorCLIIntegration can be imported."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        assert CursorCLIIntegration is not None
+    
+    def test_cli_command_is_cursor_agent(self):
+        """Test that cli_command returns 'cursor-agent'."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        integration = CursorCLIIntegration()
+        assert integration.cli_command == "cursor-agent"
+    
+    def test_inherits_from_base(self):
+        """Test that CursorCLIIntegration inherits from BaseCLIIntegration."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        assert isinstance(integration, BaseCLIIntegration)
+    
+    def test_default_options(self):
+        """Test default options are set correctly."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        assert integration.output_format == "json"
+        assert integration.force is False
+    
+    def test_force_option(self):
+        """Test force option can be set."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(force=True)
+        assert integration.force is True
+    
+    def test_model_option(self):
+        """Test model option can be set."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(model="gpt-5")
+        assert integration.model == "gpt-5"
+    
+    def test_build_command_basic(self):
+        """Test building basic command."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        cmd = integration._build_command("Fix the bug")
+        
+        assert cmd[0] == "cursor-agent"
+        assert "-p" in cmd
+        assert "Fix the bug" in cmd
+        assert "--output-format" in cmd
+        assert "json" in cmd
+    
+    def test_build_command_with_force(self):
+        """Test building command with force flag."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(force=True)
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "--force" in cmd
+    
+    def test_build_command_with_model(self):
+        """Test building command with model."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(model="gpt-5")
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "-m" in cmd
+        assert "gpt-5" in cmd
+    
+    def test_build_command_with_stream_partial(self):
+        """Test building command with stream partial output."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(stream_partial=True)
+        cmd = integration._build_command("Fix the bug")
+        
+        assert "--stream-partial-output" in cmd
+
+
+class TestCursorCLIIntegrationAsync:
+    """Async tests for CursorCLIIntegration."""
+    
+    @pytest.mark.asyncio
+    async def test_execute_parses_json_output(self):
+        """Test that execute parses JSON output correctly."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        
+        mock_output = json.dumps({
+            "result": "Bug fixed successfully"
+        })
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = mock_output
+            result = await integration.execute("Fix the bug")
+            
+            assert "Bug fixed" in result
+    
+    @pytest.mark.asyncio
+    async def test_execute_handles_text_output(self):
+        """Test that execute handles text output format."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(output_format="text")
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = "Bug fixed successfully"
+            result = await integration.execute("Fix the bug")
+            
+            assert result == "Bug fixed successfully"
+
+
+class TestCursorCLIEnvironment:
+    """Tests for Cursor CLI environment handling."""
+    
+    def test_get_env_includes_cursor_api_key(self):
+        """Test that get_env includes Cursor API key."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        
+        with patch.dict(os.environ, {"CURSOR_API_KEY": "test-key"}):
+            env = integration.get_env()
+            assert "CURSOR_API_KEY" in env
+    
+    def test_api_key_required_for_headless(self):
+        """Test that API key is required for headless mode."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration()
+        # Should not raise, just return env without key if not set
+        env = integration.get_env()
+        assert isinstance(env, dict)
+
+
+class TestCursorCLISession:
+    """Tests for Cursor CLI session management."""
+    
+    def test_resume_option(self):
+        """Test resume option."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(resume_session="session-123")
+        assert integration.resume_session == "session-123"
+    
+    def test_build_command_with_resume(self):
+        """Test building command with resume."""
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        integration = CursorCLIIntegration(resume_session="session-123")
+        cmd = integration._build_command("Continue the task")
+        
+        assert "--resume" in cmd
+        assert "session-123" in cmd
@@ -0,0 +1,170 @@
+"""
+Tests for ExternalAgentsHandler.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+from unittest.mock import patch, MagicMock
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestExternalAgentsHandler:
+    """Tests for ExternalAgentsHandler class."""
+    
+    def test_import_external_agents_handler(self):
+        """Test that ExternalAgentsHandler can be imported."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        assert ExternalAgentsHandler is not None
+    
+    def test_feature_name(self):
+        """Test that feature_name is correct."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        handler = ExternalAgentsHandler()
+        assert handler.feature_name == "external_agents"
+    
+    def test_flag_name(self):
+        """Test that flag_name is correct."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        handler = ExternalAgentsHandler()
+        assert handler.flag_name == "external-agent"
+    
+    def test_supported_integrations(self):
+        """Test that all integrations are supported."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        handler = ExternalAgentsHandler()
+        
+        assert "claude" in handler.INTEGRATIONS
+        assert "gemini" in handler.INTEGRATIONS
+        assert "codex" in handler.INTEGRATIONS
+        assert "cursor" in handler.INTEGRATIONS
+    
+    def test_get_integration_claude(self):
+        """Test getting Claude integration."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        from praisonai.integrations.claude_code import ClaudeCodeIntegration
+        
+        handler = ExternalAgentsHandler()
+        integration = handler.get_integration("claude")
+        
+        assert isinstance(integration, ClaudeCodeIntegration)
+    
+    def test_get_integration_gemini(self):
+        """Test getting Gemini integration."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        handler = ExternalAgentsHandler()
+        integration = handler.get_integration("gemini")
+        
+        assert isinstance(integration, GeminiCLIIntegration)
+    
+    def test_get_integration_codex(self):
+        """Test getting Codex integration."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        from praisonai.integrations.codex_cli import CodexCLIIntegration
+        
+        handler = ExternalAgentsHandler()
+        integration = handler.get_integration("codex")
+        
+        assert isinstance(integration, CodexCLIIntegration)
+    
+    def test_get_integration_cursor(self):
+        """Test getting Cursor integration."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        from praisonai.integrations.cursor_cli import CursorCLIIntegration
+        
+        handler = ExternalAgentsHandler()
+        integration = handler.get_integration("cursor")
+        
+        assert isinstance(integration, CursorCLIIntegration)
+    
+    def test_get_integration_invalid(self):
+        """Test getting invalid integration raises error."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        
+        with pytest.raises(ValueError):
+            handler.get_integration("invalid")
+    
+    def test_list_integrations(self):
+        """Test listing all integrations."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        integrations = handler.list_integrations()
+        
+        assert len(integrations) == 4
+        assert all(name in integrations for name in ["claude", "gemini", "codex", "cursor"])
+    
+    def test_check_availability(self):
+        """Test checking integration availability."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        availability = handler.check_availability()
+        
+        assert isinstance(availability, dict)
+        assert "claude" in availability
+        assert isinstance(availability["claude"], bool)
+
+
+class TestExternalAgentsHandlerConfig:
+    """Tests for ExternalAgentsHandler configuration."""
+    
+    def test_apply_to_agent_config_adds_tool(self):
+        """Test that apply_to_agent_config adds tool to config."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        config = {"tools": []}
+        
+        # Mock the integration to be available
+        with patch.object(handler, 'get_integration') as mock_get:
+            mock_integration = MagicMock()
+            mock_integration.is_available = True
+            mock_integration.as_tool.return_value = lambda x: x
+            mock_get.return_value = mock_integration
+            
+            result = handler.apply_to_agent_config(config, "claude")
+            
+            assert len(result["tools"]) == 1
+    
+    def test_apply_to_agent_config_skips_unavailable(self):
+        """Test that apply_to_agent_config skips unavailable integrations."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        config = {"tools": []}
+        
+        with patch.object(handler, 'get_integration') as mock_get:
+            mock_integration = MagicMock()
+            mock_integration.is_available = False
+            mock_get.return_value = mock_integration
+            
+            result = handler.apply_to_agent_config(config, "claude")
+            
+            assert len(result["tools"]) == 0
+
+
+class TestExternalAgentsHandlerExecution:
+    """Tests for ExternalAgentsHandler execution."""
+    
+    def test_execute_returns_integration(self):
+        """Test that execute returns the integration."""
+        from praisonai.cli.features.external_agents import ExternalAgentsHandler
+        
+        handler = ExternalAgentsHandler()
+        
+        with patch.object(handler, 'get_integration') as mock_get:
+            mock_integration = MagicMock()
+            mock_integration.is_available = True
+            mock_get.return_value = mock_integration
+            
+            result = handler.execute(integration_name="claude")
+            
+            assert result == mock_integration
@@ -0,0 +1,168 @@
+"""
+Tests for GeminiCLIIntegration.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import pytest
+import json
+from unittest.mock import patch, AsyncMock
+import sys
+import os
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..', '..'))
+
+
+class TestGeminiCLIIntegration:
+    """Tests for GeminiCLIIntegration class."""
+    
+    def test_import_gemini_cli_integration(self):
+        """Test that GeminiCLIIntegration can be imported."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        assert GeminiCLIIntegration is not None
+    
+    def test_cli_command_is_gemini(self):
+        """Test that cli_command returns 'gemini'."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        integration = GeminiCLIIntegration()
+        assert integration.cli_command == "gemini"
+    
+    def test_inherits_from_base(self):
+        """Test that GeminiCLIIntegration inherits from BaseCLIIntegration."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        from praisonai.integrations.base import BaseCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        assert isinstance(integration, BaseCLIIntegration)
+    
+    def test_default_options(self):
+        """Test default options are set correctly."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        assert integration.output_format == "json"
+        assert integration.model == "gemini-2.5-pro"
+    
+    def test_custom_model(self):
+        """Test custom model can be set."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration(model="gemini-2.5-flash")
+        assert integration.model == "gemini-2.5-flash"
+    
+    def test_build_command_basic(self):
+        """Test building basic command."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        cmd = integration._build_command("Hello")
+        
+        assert cmd[0] == "gemini"
+        assert "-p" in cmd
+        assert "Hello" in cmd
+        assert "--output-format" in cmd
+        assert "json" in cmd
+    
+    def test_build_command_with_model(self):
+        """Test building command with model."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration(model="gemini-2.5-flash")
+        cmd = integration._build_command("Hello")
+        
+        assert "-m" in cmd
+        assert "gemini-2.5-flash" in cmd
+    
+    def test_build_command_with_include_directories(self):
+        """Test building command with include directories."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration(include_directories=["../lib", "../docs"])
+        cmd = integration._build_command("Hello")
+        
+        assert "--include-directories" in cmd
+
+
+class TestGeminiCLIIntegrationAsync:
+    """Async tests for GeminiCLIIntegration."""
+    
+    @pytest.mark.asyncio
+    async def test_execute_parses_json_output(self):
+        """Test that execute parses JSON output correctly."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        
+        mock_output = json.dumps({
+            "response": "Hello, world!",
+            "stats": {"models": {}}
+        })
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = mock_output
+            result = await integration.execute("Say hello")
+            
+            assert "Hello, world!" in result
+    
+    @pytest.mark.asyncio
+    async def test_execute_handles_text_output(self):
+        """Test that execute handles text output format."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration(output_format="text")
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = "Hello, world!"
+            result = await integration.execute("Say hello")
+            
+            assert result == "Hello, world!"
+    
+    @pytest.mark.asyncio
+    async def test_get_stats_returns_usage_info(self):
+        """Test that get_stats returns usage information."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        
+        mock_output = json.dumps({
+            "response": "Hello",
+            "stats": {
+                "models": {
+                    "gemini-2.5-pro": {
+                        "tokens": {"prompt": 100, "candidates": 50}
+                    }
+                }
+            }
+        })
+        
+        with patch.object(integration, 'execute_async', new_callable=AsyncMock) as mock_exec:
+            mock_exec.return_value = mock_output
+            result, stats = await integration.execute_with_stats("Say hello")
+            
+            assert stats is not None
+            assert "models" in stats
+
+
+class TestGeminiCLIEnvironment:
+    """Tests for Gemini CLI environment handling."""
+    
+    def test_get_env_includes_google_api_key(self):
+        """Test that get_env includes Google API key."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        
+        with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
+            env = integration.get_env()
+            assert "GOOGLE_API_KEY" in env
+    
+    def test_get_env_includes_gemini_api_key(self):
+        """Test that get_env includes Gemini API key."""
+        from praisonai.integrations.gemini_cli import GeminiCLIIntegration
+        
+        integration = GeminiCLIIntegration()
+        
+        with patch.dict(os.environ, {"GEMINI_API_KEY": "test-key"}):
+            env = integration.get_env()
+            # Should map GEMINI_API_KEY to GOOGLE_API_KEY
+            assert "GOOGLE_API_KEY" in env or "GEMINI_API_KEY" in env
@@ -0,0 +1,743 @@
+"""
+Unit tests for AutoGenerator and WorkflowAutoGenerator classes.
+
+Tests cover:
+- Default model value (gpt-4o-mini)
+- Tools preservation (not replaced with [''])
+- LiteLLM fallback to OpenAI
+- Lazy loading of client
+- Timeout and max_retries configuration
+"""
+
+import pytest
+import os
+import sys
+from unittest.mock import Mock, patch, MagicMock
+import json
+import tempfile
+
+# Add the source path for imports
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
+
+try:
+    from praisonai.auto import AutoGenerator, WorkflowAutoGenerator, LITELLM_AVAILABLE
+except ImportError as e:
+    pytest.skip(f"Could not import required modules: {e}", allow_module_level=True)
+
+
+class TestAutoGeneratorDefaultModel:
+    """Test suite for default model configuration."""
+    
+    def test_default_model_is_gpt4o_mini(self):
+        """Test that default model is gpt-4o-mini, not gpt-5-nano."""
+        # Clear environment variables to test defaults
+        with patch.dict(os.environ, {}, clear=True):
+            # Set required API key
+            os.environ['OPENAI_API_KEY'] = 'test-key'
+            
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            # Check that default model is gpt-4o-mini
+            assert generator.config_list[0]['model'] == 'gpt-4o-mini'
+    
+    def test_model_from_environment_variable(self):
+        """Test that MODEL_NAME environment variable is respected."""
+        with patch.dict(os.environ, {'MODEL_NAME': 'custom-model', 'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            assert generator.config_list[0]['model'] == 'custom-model'
+    
+    def test_openai_model_name_fallback(self):
+        """Test that OPENAI_MODEL_NAME is used as fallback."""
+        with patch.dict(os.environ, {'OPENAI_MODEL_NAME': 'gpt-4', 'OPENAI_API_KEY': 'test-key'}, clear=True):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            assert generator.config_list[0]['model'] == 'gpt-4'
+
+
+class TestAutoGeneratorToolsPreservation:
+    """Test suite for tools preservation in generated YAML."""
+    
+    def test_tools_are_preserved_in_convert_and_save(self):
+        """Test that generated tools are preserved, not replaced with ['']."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            # Mock JSON data with tools
+            json_data = {
+                'roles': {
+                    'researcher': {
+                        'role': 'Researcher',
+                        'goal': 'Research topics',
+                        'backstory': 'Expert researcher',
+                        'tools': ['ScrapeWebsiteTool', 'WebsiteSearchTool'],
+                        'tasks': {
+                            'research_task': {
+                                'description': 'Research the topic',
+                                'expected_output': 'Research report'
+                            }
+                        }
+                    }
+                }
+            }
+            
+            # Use a temporary file
+            with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+                generator.agent_file = f.name
+            
+            try:
+                generator.convert_and_save(json_data, merge=False)
+                
+                # Read the saved file
+                import yaml
+                with open(generator.agent_file, 'r') as f:
+                    saved_data = yaml.safe_load(f)
+                
+                # Check that tools are preserved
+                assert saved_data['roles']['researcher']['tools'] == ['ScrapeWebsiteTool', 'WebsiteSearchTool']
+            finally:
+                os.unlink(generator.agent_file)
+    
+    def test_tools_preserved_in_merge(self):
+        """Test that tools are preserved when merging with existing file."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            # Create existing file
+            existing_data = {
+                'framework': 'praisonai',
+                'topic': 'Existing topic',
+                'roles': {},
+                'dependencies': []
+            }
+            
+            # New JSON data with tools
+            new_json_data = {
+                'roles': {
+                    'writer': {
+                        'role': 'Writer',
+                        'goal': 'Write content',
+                        'backstory': 'Expert writer',
+                        'tools': ['FileReadTool', 'TXTSearchTool'],
+                        'tasks': {
+                            'write_task': {
+                                'description': 'Write the content',
+                                'expected_output': 'Written content'
+                            }
+                        }
+                    }
+                }
+            }
+            
+            # Use a temporary file
+            import yaml
+            with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+                yaml.dump(existing_data, f)
+                generator.agent_file = f.name
+            
+            try:
+                generator.convert_and_save(new_json_data, merge=True)
+                
+                # Read the saved file
+                with open(generator.agent_file, 'r') as f:
+                    saved_data = yaml.safe_load(f)
+                
+                # Check that tools are preserved
+                assert saved_data['roles']['writer']['tools'] == ['FileReadTool', 'TXTSearchTool']
+            finally:
+                os.unlink(generator.agent_file)
+
+
+class TestAutoGeneratorLazyLoading:
+    """Test suite for lazy loading of client."""
+    
+    def test_client_is_not_created_on_init(self):
+        """Test that client is not created during __init__."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            # Check that _client is None (lazy loading)
+            assert generator._client is None
+    
+    def test_client_is_created_on_first_access(self):
+        """Test that client is created on first access."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            # Access client property
+            with patch('praisonai.auto.instructor') as mock_instructor:
+                mock_instructor.from_litellm.return_value = Mock()
+                mock_instructor.patch.return_value = Mock()
+                
+                client = generator.client
+                
+                # Check that client is now set
+                assert generator._client is not None
+
+
+class TestAutoGeneratorLiteLLMFallback:
+    """Test suite for LiteLLM fallback to OpenAI."""
+    
+    def test_uses_litellm_when_available(self):
+        """Test that LiteLLM is used when available via from_provider."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            with patch('praisonai.auto.LITELLM_AVAILABLE', True):
+                with patch('praisonai.auto.instructor') as mock_instructor:
+                    mock_instructor.from_provider.return_value = Mock()
+                    
+                    generator = AutoGenerator(
+                        topic="Test topic",
+                        framework="praisonai"
+                    )
+                    
+                    # Access client to trigger creation
+                    _ = generator.client
+                    
+                    # Check that from_provider was called with litellm prefix
+                    mock_instructor.from_provider.assert_called_once()
+                    call_args = mock_instructor.from_provider.call_args[0][0]
+                    assert call_args.startswith('litellm/')
+    
+    def test_falls_back_to_openai_when_litellm_unavailable(self):
+        """Test that OpenAI SDK is used when LiteLLM is not available."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            with patch('praisonai.auto.LITELLM_AVAILABLE', False):
+                with patch('praisonai.auto.instructor') as mock_instructor:
+                    with patch('praisonai.auto.OpenAI') as mock_openai:
+                        mock_instructor.patch.return_value = Mock()
+                        mock_openai.return_value = Mock()
+                        
+                        generator = AutoGenerator(
+                            topic="Test topic",
+                            framework="praisonai"
+                        )
+                        
+                        # Access client to trigger creation
+                        _ = generator.client
+                        
+                        # Check that patch was called (OpenAI fallback)
+                        mock_instructor.patch.assert_called_once()
+
+
+class TestWorkflowAutoGenerator:
+    """Test suite for WorkflowAutoGenerator."""
+    
+    def test_default_model_is_gpt4o_mini(self):
+        """Test that default model is gpt-4o-mini."""
+        with patch.dict(os.environ, {}, clear=True):
+            os.environ['OPENAI_API_KEY'] = 'test-key'
+            
+            generator = WorkflowAutoGenerator(
+                topic="Test workflow"
+            )
+            
+            assert generator.config_list[0]['model'] == 'gpt-4o-mini'
+    
+    def test_lazy_loading(self):
+        """Test that client uses lazy loading."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(
+                topic="Test workflow"
+            )
+            
+            assert generator._client is None
+    
+    def test_litellm_fallback(self):
+        """Test LiteLLM fallback to OpenAI."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            with patch('praisonai.auto.LITELLM_AVAILABLE', False):
+                with patch('praisonai.auto.instructor') as mock_instructor:
+                    with patch('praisonai.auto.OpenAI') as mock_openai:
+                        mock_instructor.patch.return_value = Mock()
+                        mock_openai.return_value = Mock()
+                        
+                        generator = WorkflowAutoGenerator(
+                            topic="Test workflow"
+                        )
+                        
+                        # Access client to trigger creation
+                        _ = generator.client
+                        
+                        # Check that patch was called (OpenAI fallback)
+                        mock_instructor.patch.assert_called_once()
+
+
+class TestAutoGeneratorJSONMode:
+    """Test suite for JSON mode (critical fix for nested Dict structures)."""
+    
+    def test_uses_json_mode_not_tools_mode(self):
+        """Test that JSON mode is used instead of TOOLS mode for OpenAI fallback.
+        
+        TOOLS mode doesn't handle nested Dict[str, ...] structures properly,
+        causing validation errors. JSON mode works correctly.
+        """
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            with patch('praisonai.auto.LITELLM_AVAILABLE', False):
+                with patch('praisonai.auto.instructor') as mock_instructor:
+                    with patch('praisonai.auto.OpenAI') as mock_openai:
+                        mock_instructor.patch.return_value = Mock()
+                        mock_instructor.Mode.JSON = 'JSON_MODE'
+                        mock_openai.return_value = Mock()
+                        
+                        generator = AutoGenerator(
+                            topic="Test topic",
+                            framework="praisonai"
+                        )
+                        
+                        # Access client to trigger creation
+                        _ = generator.client
+                        
+                        # Verify JSON mode was used
+                        call_kwargs = mock_instructor.patch.call_args[1]
+                        assert call_kwargs['mode'] == 'JSON_MODE'
+    
+    def test_workflow_generator_uses_json_mode(self):
+        """Test that WorkflowAutoGenerator also uses JSON mode."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            with patch('praisonai.auto.LITELLM_AVAILABLE', False):
+                with patch('praisonai.auto.instructor') as mock_instructor:
+                    with patch('praisonai.auto.OpenAI') as mock_openai:
+                        mock_instructor.patch.return_value = Mock()
+                        mock_instructor.Mode.JSON = 'JSON_MODE'
+                        mock_openai.return_value = Mock()
+                        
+                        generator = WorkflowAutoGenerator(
+                            topic="Test workflow"
+                        )
+                        
+                        # Access client to trigger creation
+                        _ = generator.client
+                        
+                        # Verify JSON mode was used
+                        call_kwargs = mock_instructor.patch.call_args[1]
+                        assert call_kwargs['mode'] == 'JSON_MODE'
+
+
+class TestAutoGeneratorImprovedPrompt:
+    """Test suite for improved task analysis prompt."""
+    
+    def test_prompt_includes_complexity_analysis(self):
+        """Test that the prompt includes task complexity analysis."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            prompt = generator.get_user_content()
+            
+            # Check for complexity analysis steps
+            assert "TASK COMPLEXITY ANALYSIS" in prompt
+            assert "DETERMINE OPTIMAL TEAM SIZE" in prompt
+            assert "Simple tasks: 1-2 agents" in prompt
+            assert "Complex tasks: 3-4 agents" in prompt
+    
+    def test_prompt_discourages_unnecessary_complexity(self):
+        """Test that the prompt discourages unnecessary complexity."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            prompt = generator.get_user_content()
+            
+            assert "meaningful specialization" in prompt
+            assert "Avoid unnecessary complexity" in prompt
+
+
+class TestWorkflowPatterns:
+    """Test suite for workflow patterns including new orchestrator-workers and evaluator-optimizer."""
+    
+    def test_get_prompt_sequential(self):
+        """Test that sequential pattern generates correct prompt."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test topic")
+            prompt = generator._get_prompt("sequential")
+            assert "sequential" in prompt.lower()
+            assert "Sequential Workflow" in prompt
+    
+    def test_get_prompt_orchestrator_workers(self):
+        """Test that orchestrator-workers pattern generates correct prompt."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test topic")
+            prompt = generator._get_prompt("orchestrator-workers")
+            assert "orchestrator" in prompt.lower()
+            assert "workers" in prompt.lower()
+            assert "synthesizer" in prompt.lower()
+    
+    def test_get_prompt_evaluator_optimizer(self):
+        """Test that evaluator-optimizer pattern generates correct prompt."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test topic")
+            prompt = generator._get_prompt("evaluator-optimizer")
+            assert "evaluator" in prompt.lower()
+            assert "generator" in prompt.lower()
+            assert "loop" in prompt.lower()
+            assert "APPROVED" in prompt
+
+
+class TestPatternRecommendation:
+    """Test suite for pattern recommendation based on task type."""
+    
+    def test_recommend_sequential_for_simple_task(self):
+        """Test that sequential is recommended for simple tasks."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Write a blog post")
+            assert generator.recommend_pattern() == "sequential"
+    
+    def test_recommend_parallel_for_concurrent_tasks(self):
+        """Test that parallel is recommended for concurrent tasks."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Research from multiple sources simultaneously")
+            assert generator.recommend_pattern() == "parallel"
+    
+    def test_recommend_orchestrator_for_complex_tasks(self):
+        """Test that orchestrator-workers is recommended for complex tasks."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Comprehensive analysis and break down the problem")
+            assert generator.recommend_pattern() == "orchestrator-workers"
+    
+    def test_recommend_evaluator_for_quality_tasks(self):
+        """Test that evaluator-optimizer is recommended for quality-focused tasks."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Refine and improve the content quality")
+            assert generator.recommend_pattern() == "evaluator-optimizer"
+    
+    def test_recommend_routing_for_classification_tasks(self):
+        """Test that routing is recommended for classification tasks."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Classify and route different types of requests")
+            assert generator.recommend_pattern() == "routing"
+
+
+class TestAutoGeneratorConfiguration:
+    """Test suite for configuration options."""
+    
+    def test_custom_config_list(self):
+        """Test that custom config_list is respected."""
+        custom_config = [
+            {
+                'model': 'custom-model',
+                'base_url': 'https://custom.api.com',
+                'api_key': 'custom-key'
+            }
+        ]
+        
+        generator = AutoGenerator(
+            topic="Test topic",
+            framework="praisonai",
+            config_list=custom_config
+        )
+        
+        assert generator.config_list == custom_config
+    
+    def test_base_url_priority(self):
+        """Test base_url environment variable priority."""
+        with patch.dict(os.environ, {
+            'OPENAI_BASE_URL': 'https://priority.api.com',
+            'OPENAI_API_BASE': 'https://fallback.api.com',
+            'OPENAI_API_KEY': 'test-key'
+        }):
+            generator = AutoGenerator(
+                topic="Test topic",
+                framework="praisonai"
+            )
+            
+            assert generator.config_list[0]['base_url'] == 'https://priority.api.com'
+
+
+class TestBaseAutoGenerator:
+    """Test suite for BaseAutoGenerator shared functionality."""
+    
+    def test_analyze_complexity_simple(self):
+        """Test that simple tasks are detected correctly."""
+        from praisonai.auto import BaseAutoGenerator
+        
+        simple_tasks = [
+            "Write a haiku about spring",
+            "Create a simple summary",
+            "Write a brief poem",
+            "Make a quick list"
+        ]
+        
+        for task in simple_tasks:
+            assert BaseAutoGenerator.analyze_complexity(task) == 'simple', f"Failed for: {task}"
+    
+    def test_analyze_complexity_complex(self):
+        """Test that complex tasks are detected correctly."""
+        from praisonai.auto import BaseAutoGenerator
+        
+        complex_tasks = [
+            "Comprehensive market analysis and report",
+            "Research and write a detailed analysis",
+            "Multi-step process to coordinate teams",
+            "In-depth investigation of multiple sources"
+        ]
+        
+        for task in complex_tasks:
+            assert BaseAutoGenerator.analyze_complexity(task) == 'complex', f"Failed for: {task}"
+    
+    def test_analyze_complexity_moderate(self):
+        """Test that moderate tasks are detected correctly."""
+        from praisonai.auto import BaseAutoGenerator
+        
+        moderate_tasks = [
+            "Research AI trends",
+            "Analyze customer feedback",
+            "Design a workflow"
+        ]
+        
+        for task in moderate_tasks:
+            assert BaseAutoGenerator.analyze_complexity(task) == 'moderate', f"Failed for: {task}"
+    
+    def test_get_available_tools(self):
+        """Test that available tools list is returned correctly."""
+        from praisonai.auto import BaseAutoGenerator, AVAILABLE_TOOLS
+        
+        tools = BaseAutoGenerator.get_available_tools()
+        
+        # Should return a copy, not the original
+        assert tools == AVAILABLE_TOOLS
+        assert tools is not AVAILABLE_TOOLS
+        
+        # Should contain expected tools
+        assert "WebsiteSearchTool" in tools
+        assert "PDFSearchTool" in tools
+        assert "ScrapeWebsiteTool" in tools
+
+
+class TestWorkflowDynamicAgentCount:
+    """Test suite for dynamic agent count in WorkflowAutoGenerator."""
+    
+    def test_prompt_includes_complexity_analysis(self):
+        """Test that workflow prompt includes complexity analysis."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Research AI trends")
+            prompt = generator._get_prompt("sequential")
+            
+            assert "STEP 1: ANALYZE TASK COMPLEXITY" in prompt
+            assert "STEP 2: DESIGN WORKFLOW" in prompt
+            assert "STEP 3: ASSIGN TOOLS" in prompt
+    
+    def test_prompt_includes_tools_list(self):
+        """Test that workflow prompt includes available tools."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Research AI trends")
+            prompt = generator._get_prompt("sequential")
+            
+            assert "Available Tools:" in prompt
+            assert "WebsiteSearchTool" in prompt
+            assert "PDFSearchTool" in prompt
+    
+    def test_simple_task_gets_fewer_agents_guidance(self):
+        """Test that simple tasks get 1-2 agents guidance."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Write a simple haiku")
+            prompt = generator._get_prompt("sequential")
+            
+            assert "1-2 agents" in prompt
+            assert "simple task detected" in prompt
+    
+    def test_complex_task_gets_more_agents_guidance(self):
+        """Test that complex tasks get 3-4 agents guidance."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Comprehensive market analysis and detailed report")
+            prompt = generator._get_prompt("sequential")
+            
+            assert "3-4 agents" in prompt
+            assert "complex task detected" in prompt
+
+
+# =============================================================================
+# TODO 2: Single-Agent Option Tests
+# =============================================================================
+class TestSingleAgentOption:
+    """Test suite for single-agent generation option."""
+    
+    def test_single_agent_structure_exists(self):
+        """Test that SingleAgentStructure Pydantic model exists."""
+        from praisonai.auto import SingleAgentStructure
+        assert SingleAgentStructure is not None
+    
+    def test_auto_generator_has_single_agent_mode(self):
+        """Test that AutoGenerator supports single_agent parameter."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Write a haiku",
+                framework="praisonai",
+                single_agent=True
+            )
+            assert generator.single_agent == True
+    
+    def test_workflow_generator_has_single_agent_mode(self):
+        """Test that WorkflowAutoGenerator supports single_agent parameter."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(
+                topic="Write a haiku",
+                single_agent=True
+            )
+            assert generator.single_agent == True
+
+
+# =============================================================================
+# TODO 3: LLM-Based Pattern Recommendation Tests
+# =============================================================================
+class TestLLMPatternRecommendation:
+    """Test suite for LLM-based pattern recommendation."""
+    
+    def test_recommend_pattern_llm_method_exists(self):
+        """Test that recommend_pattern_llm method exists."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test task")
+            assert hasattr(generator, 'recommend_pattern_llm')
+    
+    def test_pattern_recommendation_pydantic_model_exists(self):
+        """Test that PatternRecommendation Pydantic model exists."""
+        from praisonai.auto import PatternRecommendation
+        assert PatternRecommendation is not None
+    
+    def test_pattern_recommendation_has_required_fields(self):
+        """Test PatternRecommendation has pattern, reasoning, confidence."""
+        from praisonai.auto import PatternRecommendation
+        fields = PatternRecommendation.model_fields
+        assert 'pattern' in fields
+        assert 'reasoning' in fields
+        assert 'confidence' in fields
+
+
+# =============================================================================
+# TODO 4: Validation Gates Tests
+# =============================================================================
+class TestValidationGates:
+    """Test suite for validation gates in workflows."""
+    
+    def test_validation_gate_model_exists(self):
+        """Test that ValidationGate Pydantic model exists."""
+        from praisonai.auto import ValidationGate
+        assert ValidationGate is not None
+    
+    def test_validation_gate_has_required_fields(self):
+        """Test ValidationGate has criteria, pass_action, fail_action."""
+        from praisonai.auto import ValidationGate
+        fields = ValidationGate.model_fields
+        assert 'criteria' in fields
+        assert 'pass_action' in fields
+        assert 'fail_action' in fields
+    
+    def test_workflow_structure_supports_gates(self):
+        """Test that WorkflowStructure has optional gates field."""
+        from praisonai.auto import WorkflowStructure
+        fields = WorkflowStructure.model_fields
+        assert 'gates' in fields
+
+
+# =============================================================================
+# TODO 6: Pattern Support for AutoGenerator Tests
+# =============================================================================
+class TestAutoGeneratorPatternSupport:
+    """Test suite for pattern support in AutoGenerator."""
+    
+    def test_auto_generator_accepts_pattern_parameter(self):
+        """Test that AutoGenerator accepts pattern parameter."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Research and write",
+                framework="praisonai",
+                pattern="parallel"
+            )
+            assert generator.pattern == "parallel"
+    
+    def test_auto_generator_has_recommend_pattern(self):
+        """Test that AutoGenerator has recommend_pattern method."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(topic="Test", framework="praisonai")
+            assert hasattr(generator, 'recommend_pattern')
+    
+    def test_auto_generator_prompt_includes_pattern(self):
+        """Test that AutoGenerator prompt includes pattern guidance."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = AutoGenerator(
+                topic="Research from multiple sources",
+                framework="praisonai",
+                pattern="parallel"
+            )
+            prompt = generator.get_user_content()
+            assert "parallel" in prompt.lower()
+
+
+# =============================================================================
+# TODO 7: Merge Support for WorkflowAutoGenerator Tests
+# =============================================================================
+class TestWorkflowMergeSupport:
+    """Test suite for merge support in WorkflowAutoGenerator."""
+    
+    def test_workflow_generator_accepts_merge_parameter(self):
+        """Test that WorkflowAutoGenerator.generate accepts merge parameter."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test task")
+            # Check that generate method accepts merge parameter
+            import inspect
+            sig = inspect.signature(generator.generate)
+            assert 'merge' in sig.parameters
+    
+    def test_merge_with_existing_workflow_method_exists(self):
+        """Test that merge_with_existing_workflow method exists."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test task")
+            assert hasattr(generator, 'merge_with_existing_workflow')
+
+
+# =============================================================================
+# TODO 10: Framework Support for WorkflowAutoGenerator Tests
+# =============================================================================
+class TestWorkflowFrameworkSupport:
+    """Test suite for framework support in WorkflowAutoGenerator."""
+    
+    def test_workflow_generator_accepts_framework_parameter(self):
+        """Test that WorkflowAutoGenerator accepts framework parameter."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(
+                topic="Test task",
+                framework="crewai"
+            )
+            assert generator.framework == "crewai"
+    
+    def test_workflow_generator_default_framework_is_praisonai(self):
+        """Test that default framework is praisonai."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(topic="Test task")
+            assert generator.framework == "praisonai"
+    
+    def test_save_workflow_respects_framework(self):
+        """Test that _save_workflow uses the specified framework."""
+        with patch.dict(os.environ, {'OPENAI_API_KEY': 'test-key'}):
+            generator = WorkflowAutoGenerator(
+                topic="Test task",
+                framework="crewai"
+            )
+            # The framework should be stored and used in output
+            assert generator.framework == "crewai"
+
+
+if __name__ == '__main__':
+    pytest.main([__file__, '-v'])
@@ -0,0 +1,580 @@
+"""
+Unit tests for Model Routing features.
+
+Tests cover:
+1. Model config parsing from agents.yaml/workflow.yaml
+2. Per-agent LLM field support
+3. Unified CLI Router with ModelRouter
+4. Custom model profiles
+
+TDD approach - tests written before implementation.
+"""
+
+import pytest
+import yaml
+import os
+import sys
+
+# Add parent directory to path for imports
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
+
+
+# =============================================================================
+# Feature 1: Model Config in YAML
+# =============================================================================
+
+class TestModelConfigParsing:
+    """Tests for parsing 'models' section from agents.yaml/workflow.yaml."""
+    
+    def test_parse_models_section_basic(self):
+        """Test parsing basic models configuration from YAML."""
+        yaml_content = """
+name: Test Workflow
+description: Test workflow with custom models
+
+models:
+  gpt-4o-mini:
+    provider: openai
+    complexity: [simple, moderate]
+    cost_per_1k: 0.00075
+    capabilities: [text, function-calling]
+
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+
+steps:
+  - agent: researcher
+    action: "Research: {{input}}"
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        # Verify models section exists
+        assert 'models' in config
+        assert 'gpt-4o-mini' in config['models']
+        
+        model_config = config['models']['gpt-4o-mini']
+        assert model_config['provider'] == 'openai'
+        assert model_config['complexity'] == ['simple', 'moderate']
+        assert model_config['cost_per_1k'] == 0.00075
+        assert 'text' in model_config['capabilities']
+    
+    def test_parse_multiple_models(self):
+        """Test parsing multiple model configurations."""
+        yaml_content = """
+models:
+  gpt-4o-mini:
+    provider: openai
+    complexity: [simple, moderate]
+    cost_per_1k: 0.00075
+    capabilities: [text, function-calling]
+  
+  claude-3-5-sonnet:
+    provider: anthropic
+    complexity: [moderate, complex, very_complex]
+    cost_per_1k: 0.009
+    capabilities: [text, vision, function-calling]
+  
+  custom-openrouter-model:
+    provider: openrouter
+    complexity: [moderate, complex]
+    cost_per_1k: 0.001
+    capabilities: [text]
+    context_window: 32000
+
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        assert len(config['models']) == 3
+        assert 'gpt-4o-mini' in config['models']
+        assert 'claude-3-5-sonnet' in config['models']
+        assert 'custom-openrouter-model' in config['models']
+        
+        # Verify custom model has context_window
+        custom_model = config['models']['custom-openrouter-model']
+        assert custom_model.get('context_window') == 32000
+    
+    def test_parse_model_with_all_fields(self):
+        """Test parsing model with all optional fields."""
+        yaml_content = """
+models:
+  full-model:
+    provider: openai
+    complexity: [simple, moderate, complex]
+    cost_per_1k: 0.005
+    capabilities: [text, vision, function-calling, streaming]
+    context_window: 128000
+    supports_tools: true
+    supports_streaming: true
+    strengths: [reasoning, code-generation, analysis]
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        model = config['models']['full-model']
+        assert model['provider'] == 'openai'
+        assert model['context_window'] == 128000
+        assert model['supports_tools'] is True
+        assert model['supports_streaming'] is True
+        assert 'reasoning' in model['strengths']
+    
+    def test_models_section_optional(self):
+        """Test that models section is optional - backward compatibility."""
+        yaml_content = """
+name: Simple Workflow
+
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+
+steps:
+  - agent: researcher
+    action: "Research: {{input}}"
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        # models section should not exist
+        assert 'models' not in config or config.get('models') is None
+        # But agents should still work
+        assert 'agents' in config
+
+
+class TestModelConfigToModelProfile:
+    """Tests for converting YAML model config to ModelProfile objects."""
+    
+    def test_convert_yaml_to_model_profile(self):
+        """Test converting YAML model config to ModelProfile."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        yaml_model_config = {
+            'provider': 'openai',
+            'complexity': ['simple', 'moderate'],
+            'cost_per_1k': 0.00075,
+            'capabilities': ['text', 'function-calling'],
+            'context_window': 128000,
+            'supports_tools': True,
+            'strengths': ['speed', 'cost-effective']
+        }
+        
+        handler = RouterHandler()
+        profile = handler.yaml_to_model_profile('gpt-4o-mini', yaml_model_config)
+        
+        assert profile is not None
+        assert profile.name == 'gpt-4o-mini'
+        assert profile.provider == 'openai'
+        assert profile.cost_per_1k_tokens == 0.00075
+        assert profile.context_window == 128000
+    
+    def test_convert_complexity_strings_to_enum(self):
+        """Test converting complexity strings to TaskComplexity enum."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        yaml_model_config = {
+            'provider': 'anthropic',
+            'complexity': ['moderate', 'complex', 'very_complex'],
+            'cost_per_1k': 0.009,
+            'capabilities': ['text']
+        }
+        
+        handler = RouterHandler()
+        profile = handler.yaml_to_model_profile('claude-3-5-sonnet', yaml_model_config)
+        
+        # Complexity range should be (MODERATE, VERY_COMPLEX)
+        min_complexity, max_complexity = profile.complexity_range
+        assert min_complexity.value == 2  # MODERATE
+        assert max_complexity.value == 4  # VERY_COMPLEX
+
+
+class TestRouterWithCustomModels:
+    """Tests for RouterHandler using custom models from YAML."""
+    
+    def test_router_loads_custom_models(self):
+        """Test that router loads custom models from YAML config."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        models_config = {
+            'my-custom-model': {
+                'provider': 'openrouter',
+                'complexity': ['simple', 'moderate'],
+                'cost_per_1k': 0.001,
+                'capabilities': ['text', 'function-calling']
+            }
+        }
+        
+        handler = RouterHandler()
+        handler.load_models_from_config(models_config)
+        
+        # Custom model should be available
+        assert 'my-custom-model' in handler.get_available_models()
+    
+    def test_router_selects_custom_model(self):
+        """Test that router can select custom model based on complexity."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        models_config = {
+            'cheap-model': {
+                'provider': 'custom',
+                'complexity': ['simple'],
+                'cost_per_1k': 0.0001,
+                'capabilities': ['text']
+            },
+            'expensive-model': {
+                'provider': 'custom',
+                'complexity': ['complex', 'very_complex'],
+                'cost_per_1k': 0.05,
+                'capabilities': ['text', 'function-calling']
+            }
+        }
+        
+        handler = RouterHandler()
+        handler.load_models_from_config(models_config)
+        
+        # Simple task should select cheap model
+        simple_model = handler.select_model("What is 2+2?")
+        assert simple_model == 'cheap-model'
+        
+        # Complex task should select expensive model
+        complex_model = handler.select_model(
+            "Analyze the comprehensive impact of quantum computing on cybersecurity"
+        )
+        assert complex_model == 'expensive-model'
+    
+    def test_router_merges_with_default_models(self):
+        """Test that custom models merge with default models."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        models_config = {
+            'my-custom-model': {
+                'provider': 'openrouter',
+                'complexity': ['moderate'],
+                'cost_per_1k': 0.002,
+                'capabilities': ['text']
+            }
+        }
+        
+        handler = RouterHandler()
+        handler.load_models_from_config(models_config, merge_with_defaults=True)
+        
+        available = handler.get_available_models()
+        
+        # Should have both custom and default models
+        assert 'my-custom-model' in available
+        assert 'gpt-4o-mini' in available  # Default model
+
+
+# =============================================================================
+# Feature 2: Per-Agent LLM Field
+# =============================================================================
+
+class TestPerAgentLLM:
+    """Tests for per-agent LLM configuration in YAML."""
+    
+    def test_parse_agent_with_llm_field(self):
+        """Test parsing agent with explicit llm field."""
+        yaml_content = """
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+    llm: gpt-4o
+    
+  writer:
+    name: Writer
+    role: Content Writer
+    goal: Write content
+    llm: claude-3-5-sonnet-20241022
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        assert config['agents']['researcher']['llm'] == 'gpt-4o'
+        assert config['agents']['writer']['llm'] == 'claude-3-5-sonnet-20241022'
+    
+    def test_parse_agent_with_llm_routing(self):
+        """Test parsing agent with llm_routing strategy."""
+        yaml_content = """
+agents:
+  smart_agent:
+    name: Smart Agent
+    role: Adaptive Assistant
+    goal: Handle various tasks
+    llm_routing: auto
+    llm_models:
+      - gpt-4o-mini
+      - gpt-4o
+      - claude-3-5-sonnet-20241022
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        agent = config['agents']['smart_agent']
+        assert agent['llm_routing'] == 'auto'
+        assert len(agent['llm_models']) == 3
+    
+    def test_agent_llm_defaults_when_not_specified(self):
+        """Test that agent uses default LLM when not specified."""
+        yaml_content = """
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+    # No llm field - should use default
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        # llm field should not exist
+        assert 'llm' not in config['agents']['researcher']
+    
+    def test_agent_llm_with_provider_prefix(self):
+        """Test parsing agent LLM with provider/model format."""
+        yaml_content = """
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+    llm: openrouter/anthropic/claude-3-5-sonnet
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        assert config['agents']['researcher']['llm'] == 'openrouter/anthropic/claude-3-5-sonnet'
+
+
+class TestAgentCreationWithLLM:
+    """Tests for creating Agent objects with LLM from YAML config."""
+    
+    def test_create_agent_with_custom_llm(self):
+        """Test that Agent config with custom LLM is properly parsed."""
+        agent_config = {
+            'name': 'Researcher',
+            'role': 'Research Analyst',
+            'goal': 'Research topics',
+            'llm': 'gpt-4o'
+        }
+        
+        # This tests the parsing logic, not actual agent creation
+        llm_value = agent_config.get('llm', 'gpt-4o-mini')
+        assert llm_value == 'gpt-4o'
+    
+    def test_agent_config_with_routing_strategy(self):
+        """Test agent config with routing strategy is properly structured."""
+        agent_config = {
+            'name': 'Smart Agent',
+            'role': 'Adaptive Assistant',
+            'goal': 'Handle various tasks',
+            'llm_routing': 'cost-optimized',
+            'llm_models': ['gpt-4o-mini', 'gpt-4o', 'claude-3-5-sonnet-20241022']
+        }
+        
+        # Verify structure
+        assert agent_config['llm_routing'] == 'cost-optimized'
+        assert isinstance(agent_config['llm_models'], list)
+        assert len(agent_config['llm_models']) == 3
+
+
+# =============================================================================
+# Feature 3: Unified CLI Router with ModelRouter
+# =============================================================================
+
+class TestUnifiedRouter:
+    """Tests for unified RouterHandler that uses ModelRouter internally."""
+    
+    def test_router_handler_uses_model_router(self):
+        """Test that RouterHandler uses ModelRouter for selection."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        handler = RouterHandler()
+        
+        # Should have internal model_router
+        assert hasattr(handler, 'model_router') or hasattr(handler, '_model_router')
+    
+    def test_router_complexity_analysis_matches(self):
+        """Test that complexity analysis is consistent."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        handler = RouterHandler()
+        
+        # Simple prompts
+        assert handler.analyze_complexity("What is 2+2?") == 'simple'
+        assert handler.analyze_complexity("Define photosynthesis") == 'simple'
+        
+        # Complex prompts
+        assert handler.analyze_complexity(
+            "Analyze and research the comprehensive impact of AI on healthcare"
+        ) == 'complex'
+    
+    def test_router_cost_threshold(self):
+        """Test router respects cost threshold."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        handler = RouterHandler()
+        handler.set_cost_threshold(0.001)  # Max $0.001 per 1k tokens
+        
+        # Should only select cheap models
+        model = handler.select_model("Complex analysis task")
+        
+        # Model should be within cost threshold
+        model_cost = handler.get_model_cost(model)
+        assert model_cost <= 0.001
+    
+    def test_router_provider_preference(self):
+        """Test router respects provider preference."""
+        from praisonai.cli.features.router import RouterHandler
+        
+        handler = RouterHandler()
+        
+        # Prefer Anthropic
+        model = handler.select_model(
+            "Write a detailed analysis",
+            preferred_provider='anthropic'
+        )
+        
+        assert 'claude' in model.lower()
+
+
+class TestRouterIntegrationWithWorkflow:
+    """Tests for router integration with workflow execution."""
+    
+    def test_workflow_uses_models_config(self):
+        """Test that workflow uses models config for routing."""
+        yaml_content = """
+name: Routing Workflow
+
+models:
+  fast-model:
+    provider: openai
+    complexity: [simple]
+    cost_per_1k: 0.0001
+    capabilities: [text]
+  
+  smart-model:
+    provider: anthropic
+    complexity: [complex, very_complex]
+    cost_per_1k: 0.01
+    capabilities: [text, function-calling]
+
+workflow:
+  verbose: true
+  router: true  # Enable model routing
+
+agents:
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics
+    llm_routing: auto  # Use auto-routing with models config
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        # Verify workflow has router enabled
+        assert config['workflow'].get('router') is True
+        
+        # Verify agent has routing enabled
+        assert config['agents']['researcher']['llm_routing'] == 'auto'
+        
+        # Verify models are defined
+        assert 'fast-model' in config['models']
+        assert 'smart-model' in config['models']
+
+
+# =============================================================================
+# Integration Tests
+# =============================================================================
+
+class TestEndToEndModelRouting:
+    """End-to-end tests for model routing feature."""
+    
+    def test_full_yaml_with_model_routing(self):
+        """Test complete YAML with all model routing features."""
+        yaml_content = """
+name: Full Model Routing Workflow
+description: Demonstrates all model routing features
+
+# Custom models configuration
+models:
+  cheap-fast:
+    provider: openai
+    complexity: [simple]
+    cost_per_1k: 0.0001
+    capabilities: [text]
+    context_window: 16000
+  
+  balanced:
+    provider: openai
+    complexity: [moderate]
+    cost_per_1k: 0.001
+    capabilities: [text, function-calling]
+    context_window: 128000
+  
+  premium:
+    provider: anthropic
+    complexity: [complex, very_complex]
+    cost_per_1k: 0.015
+    capabilities: [text, vision, function-calling]
+    context_window: 200000
+    strengths: [reasoning, analysis, code-generation]
+
+workflow:
+  verbose: true
+  router: true
+  routing_strategy: cost-optimized
+
+agents:
+  classifier:
+    name: Classifier
+    role: Request Classifier
+    goal: Classify incoming requests
+    llm: cheap-fast  # Always use cheap model for classification
+  
+  researcher:
+    name: Researcher
+    role: Research Analyst
+    goal: Research topics thoroughly
+    llm_routing: auto  # Auto-select based on task
+    llm_models: [balanced, premium]
+  
+  writer:
+    name: Writer
+    role: Content Writer
+    goal: Write high-quality content
+    llm: premium  # Always use premium for writing
+
+steps:
+  - agent: classifier
+    action: "Classify: {{input}}"
+    
+  - name: routing
+    route:
+      simple: [researcher]
+      complex: [researcher, writer]
+      default: [researcher]
+"""
+        config = yaml.safe_load(yaml_content)
+        
+        # Verify complete structure
+        assert 'models' in config
+        assert len(config['models']) == 3
+        
+        assert 'workflow' in config
+        assert config['workflow']['router'] is True
+        assert config['workflow']['routing_strategy'] == 'cost-optimized'
+        
+        assert 'agents' in config
+        assert config['agents']['classifier']['llm'] == 'cheap-fast'
+        assert config['agents']['researcher']['llm_routing'] == 'auto'
+        assert config['agents']['writer']['llm'] == 'premium'
+        
+        assert 'steps' in config
+        assert len(config['steps']) == 2
+
+
+if __name__ == '__main__':
+    pytest.main([__file__, '-v'])
Author	SHA1	Message	Date
Mervin Praison	397874ccfc	Release v2.3.45	2025-12-19 12:16:12 +00:00
Mervin Praison	2016902e9a	docs: Add examples README with quick links to docs	2025-12-19 11:14:24 +00:00
Mervin Praison	d2d19511da	docs: Update README with Model Router info and fix links - Rename 'Router Agent' to 'Model Router' for consistency - Fix docs link to point to /features/model-router - Add model-routing template CLI command - Add link to Model Router documentation	2025-12-19 11:13:48 +00:00
Mervin Praison	bc9579b497	Add Code category with individual examples for external CLI integrations - Add Code category in Key Features table (like Workflows) - Add individual examples for each external agent: - claude_code_example.py - gemini_cli_example.py - codex_cli_example.py - cursor_cli_example.py - external_agents_example.py (all integrations) - code_editing_example.py - Link to individual docs pages for each integration - Organize code-related features under Code category	2025-12-19 11:07:25 +00:00
Mervin Praison	3161389341	Add External Agents CLI documentation to README - Add External Agents feature to Key Features table - Update Code Editing docs link to /code/editing - Add External Agents CLI section with examples - Include Python API usage examples - Add environment variables documentation - Link to detailed docs at docs.praison.ai/code/external-agents	2025-12-19 11:01:24 +00:00
Mervin Praison	b01eb2b8fa	Release v2.3.44	2025-12-19 10:50:33 +00:00
Mervin Praison	e609fb7425	Release v2.3.43	2025-12-19 10:32:33 +00:00
Mervin Praison	168ef98473	feat: Implement all remaining AutoAgents improvements (TDD) TODO 2: Single-Agent Option - Add SingleAgentStructure Pydantic model - Add single_agent parameter to AutoGenerator and WorkflowAutoGenerator TODO 3: LLM-Based Pattern Recommendation - Add PatternRecommendation Pydantic model (pattern, reasoning, confidence) - Add recommend_pattern_llm() method to WorkflowAutoGenerator TODO 4: Validation Gates - Add ValidationGate Pydantic model (criteria, pass_action, fail_action) - Add optional gates field to WorkflowStructure TODO 6: Pattern Support for AutoGenerator - Add pattern parameter to AutoGenerator - Add recommend_pattern() method to AutoGenerator - Add pattern-specific guidance in get_user_content() TODO 7: Merge Support for WorkflowAutoGenerator - Add merge parameter to generate() method - Add merge_with_existing_workflow() method TODO 10: Framework Support for WorkflowAutoGenerator - Add framework parameter to WorkflowAutoGenerator - Default framework is 'praisonai' Test Coverage: - 51 tests pass (up from 34) - 17 new tests added using TDD approach - All tests verify new functionality	2025-12-19 10:29:40 +00:00
Mervin Praison	ce2c2926f9	refactor: Add BaseAutoGenerator class and improve WorkflowAutoGenerator - Create BaseAutoGenerator with shared functionality (DRY principle) - Lazy-loaded instructor client (LiteLLM or OpenAI fallback) - Environment variable handling for model/API configuration - analyze_complexity() static method for task complexity detection - get_available_tools() static method for tool list - AVAILABLE_TOOLS constant shared between generators - Update AutoGenerator to inherit from BaseAutoGenerator - Removes ~40 lines of duplicate code - Maintains all existing functionality - Update WorkflowAutoGenerator to inherit from BaseAutoGenerator - Removes ~40 lines of duplicate code - Add dynamic agent count based on task complexity - Add tools list to workflow prompts - Improved prompt with 3-step analysis - Add 8 new unit tests for new functionality - TestBaseAutoGenerator: complexity analysis, tools list - TestWorkflowDynamicAgentCount: prompt improvements All 34 tests pass with no performance impact.	2025-12-19 10:23:29 +00:00
Mervin Praison	0a569e2b46	docs: Add AutoAgents workflow patterns examples and update README - Add autoagents_workflow_patterns.py with all 6 workflow patterns - Update auto_agents_example.py with new features and CLI examples - Add orchestrator-workers and evaluator-optimizer patterns to README CLI section - Update pattern options table with all 6 patterns - Add documentation links to examples	2025-12-19 09:54:05 +00:00
Mervin Praison	054aea8f66	Add MCP Registry badge and ignore MCP tokens	2025-12-18 22:18:33 +00:00
Mervin Praison	34f1293cfc	Release v2.3.42	2025-12-18 22:13:08 +00:00
Mervin Praison	7c1e32afc0	upate	2025-12-18 22:11:02 +00:00
Mervin Praison	1125c835ec	Release v2.3.41	2025-12-18 22:09:58 +00:00