Release v2.3.66

Fix duplicate --max-retries argument conflict in CLI parser
Release v2.3.65
2026-11-10 03:31:28 -10:00 · 2025-12-22 08:50:02 +00:00 · 2025-12-21 05:19:08 +00:00 · 2025-12-20 21:49:04 +00:00 · 2025-12-20 19:57:39 +00:00 · 2025-12-20 12:02:44 +00:00
171 changed files with 34130 additions and 367 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">
@@ -60,6 +63,7 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
  - [Planning & Workflows](#planning--workflows)
  - [Specialised Agents](#specialised-agents)
  - [MCP Protocol](#mcp-protocol)
+  - [A2A & A2UI Protocols](#a2a--a2ui-protocols)
  - [Safety & Control](#safety--control)
  - [Developer Tools](#developer-tools)
 - [📊 Process Types & Patterns](#-process-types--patterns)
@@ -187,7 +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) |
+| **💻 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) |
@@ -205,6 +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) |
@@ -224,7 +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) |
@@ -240,12 +252,22 @@ npm install praisonai
 | 🪝 Hooks | [Example](#9-hooks) | [📖](https://docs.praison.ai/features/hooks) |
 | 📈 Telemetry | [Example](examples/python/telemetry/production-telemetry-example.py) | [📖](https://docs.praison.ai/features/telemetry) |
 | 📹 Camera Integration | [Example](examples/python/camera/) | [📖](https://docs.praison.ai/features/camera-integration) |
-| 📄 Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/cli/docs) |
-| 🔌 MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/cli/mcp) |
-| 💬 AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/cli/commit) |
-| @ @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) |
+| 📄 Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/docs/cli/docs) |
+| 🔌 MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/docs/cli/mcp) |
+| 💬 AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/docs/cli/commit) |
+| @ @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/docs/cli/mentions) |
+| 💾 Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| 📜 History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| **🖥️ CLI Features** | | |
+| ↳ Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/docs/cli/slash-commands) |
+| ↳ Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/docs/cli/autonomy-modes) |
+| ↳ Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/docs/cli/cost-tracking) |
+| ↳ Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/docs/cli/repo-map) |
+| ↳ Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/docs/cli/interactive-tui) |
+| ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
+| ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
+| **⏰ 24/7 Scheduling** | | |
+| ↳ Agent Scheduler | [Example](examples/python/scheduled_agents/news_checker_live.py) | [📖](https://docs.praison.ai/docs/cli/scheduler) |

 ---

@@ -952,6 +974,32 @@ export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
 praisonai --auto create a movie script about Robots in Mars
 ```

+### Interactive Mode CLI:
+```bash
+# Start interactive terminal mode (inspired by Gemini CLI, Codex CLI, Claude Code)
+praisonai --interactive
+praisonai -i
+
+# Features:
+# - Streaming responses (no boxes)
+# - Built-in tools: read_file, write_file, list_files, execute_command, internet_search
+# - Slash commands: /help, /exit, /tools, /clear
+
+# Chat mode - single prompt with interactive style (for testing/scripting)
+# Use --chat (or --chat-mode for backward compatibility)
+praisonai "list files in current folder" --chat
+praisonai "search the web for AI news" --chat
+praisonai "read README.md" --chat
+```
+
+### Chat UI (Web Interface):
+```bash
+# Start web-based Chainlit chat interface (requires praisonai[chat])
+pip install "praisonai[chat]"
+praisonai chat
+# Opens browser at http://localhost:8084
+```
+
 ### Query Rewriting (works with any command):
 ```bash
 # Rewrite query for better results (uses QueryRewriterAgent)
@@ -1012,6 +1060,20 @@ praisonai "Complex analysis task" --planning --planning-reasoning
 praisonai "Task" --planning --auto-approve-plan
 ```

+### Tool Approval CLI:
+```bash
+# Auto-approve ALL tool executions (use with caution!)
+praisonai "run ls command" --trust
+
+# Auto-approve tools up to a risk level (prompt for higher)
+# Levels: low, medium, high, critical
+praisonai "write to file" --approve-level high  # Prompts for critical tools only
+praisonai "task" --approve-level medium         # Prompts for high and critical
+
+# Default behavior (no flags): prompts for all dangerous tools
+praisonai "run shell command"  # Will prompt for approval
+```
+
 ### Memory CLI:
 ```bash
 # Enable memory for agent (persists across sessions)
@@ -1118,6 +1180,15 @@ 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
 ```
@@ -1127,7 +1198,7 @@ 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) |
@@ -1173,6 +1244,64 @@ praisonai "Analyze this data" --metrics
 praisonai "Complex task" --metrics --planning
 ```

+### Scheduler CLI:
+
+Run agents 24/7 with built-in safety features. Two modes available:
+
+**Direct Prompt Mode (Simple):**
+```bash
+# No YAML needed - just provide your task
+praisonai schedule "Check AI news and summarize" --interval hourly
+
+# With options
+praisonai schedule "Monitor server logs" \
+  --interval "*/30m" \
+  --timeout 120 \
+  --max-cost 2.00 \
+  --verbose
+```
+
+**YAML Mode (Advanced):**
+```bash
+# Use agents.yaml for complex configurations
+praisonai schedule agents.yaml
+
+# With overrides
+praisonai schedule agents.yaml \
+  --interval "*/15m" \
+  --timeout 60 \
+  --max-cost 1.00
+
+# Stop: Press Ctrl+C
+```
+
+**agents.yaml with schedule:**
+```yaml
+framework: praisonai
+
+agents:
+  - name: "AI News Monitor"
+    instructions: "Search and summarize AI news"
+    tools:
+      - search_tool
+
+task: "Search for latest AI news"
+
+schedule:
+  interval: "hourly"         # hourly, daily, */30m, */6h
+  max_retries: 3             # Retry on failure
+  run_immediately: true      # Run once on start
+  timeout: 60                # Max 60s per execution
+  max_cost: 1.00             # Stop after $1.00 spent
+```
+
+**Features:**
+- ⏱️ Timeout protection (prevent runaway executions)
+- 💰 Cost monitoring with budget limits
+- 📊 Real-time statistics (success rate, cost, runtime)
+- 🔄 Automatic retry with exponential backoff
+- 🛡️ Auto-stops when budget reached
+
 ### Image Processing CLI:
 ```bash
 # Process images with vision-based tasks
@@ -1359,8 +1488,13 @@ 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
@@ -1412,13 +1546,31 @@ praisonai mcp help

 ### AI Commit CLI:
 ```bash
-# Generate AI commit message for staged changes
+# Full auto mode: stage all, security check, commit, and push
+praisonai commit -a
+
+# Interactive mode (requires git add first)
 praisonai commit

-# Generate, commit, and push
+# Interactive with auto-push
 praisonai commit --push
+
+# Skip security check (not recommended)
+praisonai commit -a --no-verify
 ```

+**Features:**
+- 🤖 AI-generated conventional commit messages
+- 🔒 Built-in security scanning (API keys, passwords, secrets, sensitive files)
+- 📦 Auto-staging with `-a` flag
+- 🚀 Auto-push in full auto mode
+- ✏️ Edit message before commit in interactive mode
+
+**Security Detection:**
+- API keys, secrets, tokens (AWS, GitHub, GitLab, Slack)
+- Passwords and private keys
+- Sensitive files (`.env`, `id_rsa`, `.pem`, `.key`, etc.)
+
 ### Serve CLI (API Server):
 ```bash
 # Start API server for agents defined in YAML
@@ -1449,6 +1601,55 @@ 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
@@ -1628,36 +1829,78 @@ server.run()  # stdio for Claude Desktop
 | Security | Origin validation, DNS rebinding prevention |
 | WebSocket | Auto-reconnect with exponential backoff |

+## A2A (Agent2Agent Protocol)
+
+PraisonAI supports the [A2A Protocol](https://a2a-protocol.org) for agent-to-agent communication, enabling your agents to be discovered and collaborate with other AI agents.
+
+### A2A Server (Expose Agent as A2A Server)
+```python
+from praisonaiagents import Agent, A2A
+from fastapi import FastAPI
+
+# Create an agent with tools
+def search_web(query: str) -> str:
+    """Search the web for information."""
+    return f"Results for: {query}"
+
+agent = Agent(
+    name="Research Assistant",
+    role="Research Analyst",
+    goal="Help users research topics",
+    tools=[search_web]
+)
+
+# Expose as A2A Server
+a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+
+app = FastAPI()
+app.include_router(a2a.get_router())
+
+# Run: uvicorn app:app --reload
+# Agent Card: GET /.well-known/agent.json
+# Status: GET /status
+```
+
+### A2A Features
+| Feature | Description |
+|---------|-------------|
+| Agent Card | JSON metadata for agent discovery |
+| Skills Extraction | Auto-generate skills from tools |
+| Task Management | Stateful task lifecycle |
+| Streaming | SSE streaming for real-time updates |
+
+> **Documentation**: [docs.praison.ai/a2a](https://docs.praison.ai/a2a) | **Examples**: [examples/python/a2a](https://github.com/MervinPraison/PraisonAI/tree/main/examples/python/a2a)
+
 ## CLI Features

 | Feature | Docs |
 |---------|:----:|
-| 🔄 Query Rewrite - RAG optimization | [📖](https://docs.praison.ai/cli/query-rewrite) |
-| 🔬 Deep Research - Automated research | [📖](https://docs.praison.ai/cli/deep-research) |
-| 📋 Planning - Step-by-step execution | [📖](https://docs.praison.ai/cli/planning) |
-| 💾 Memory - Persistent agent memory | [📖](https://docs.praison.ai/cli/memory) |
-| 📜 Rules - Auto-discovered instructions | [📖](https://docs.praison.ai/cli/rules) |
-| 🔄 Workflow - Multi-step workflows | [📖](https://docs.praison.ai/cli/workflow) |
-| 🪝 Hooks - Event-driven actions | [📖](https://docs.praison.ai/cli/hooks) |
-| 🧠 Claude Memory - Anthropic memory tool | [📖](https://docs.praison.ai/cli/claude-memory) |
-| 🛡️ Guardrail - Output validation | [📖](https://docs.praison.ai/cli/guardrail) |
-| 📊 Metrics - Token usage tracking | [📖](https://docs.praison.ai/cli/metrics) |
-| 🖼️ Image - Vision processing | [📖](https://docs.praison.ai/cli/image) |
-| 📡 Telemetry - Usage monitoring | [📖](https://docs.praison.ai/cli/telemetry) |
-| 🔌 MCP - Model Context Protocol | [📖](https://docs.praison.ai/cli/mcp) |
-| ⚡ Fast Context - Codebase search | [📖](https://docs.praison.ai/cli/fast-context) |
-| 📚 Knowledge - RAG management | [📖](https://docs.praison.ai/cli/knowledge) |
-| 💬 Session - Conversation management | [📖](https://docs.praison.ai/cli/session) |
-| 🔧 Tools - Tool discovery | [📖](https://docs.praison.ai/cli/tools) |
-| 🤝 Handoff - Agent delegation | [📖](https://docs.praison.ai/cli/handoff) |
-| 🧠 Auto Memory - Memory extraction | [📖](https://docs.praison.ai/cli/auto-memory) |
-| 📋 Todo - Task management | [📖](https://docs.praison.ai/cli/todo) |
-| 🎯 Router - Smart model selection | [📖](https://docs.praison.ai/cli/router) |
-| 📈 Flow Display - Visual workflow | [📖](https://docs.praison.ai/cli/flow-display) |
-| ✨ Prompt Expansion - Detailed prompts | [📖](https://docs.praison.ai/cli/prompt-expansion) |
-| 🌐 Web Search - Real-time search | [📖](https://docs.praison.ai/cli/web-search) |
-| 📥 Web Fetch - URL content retrieval | [📖](https://docs.praison.ai/cli/web-fetch) |
-| 💾 Prompt Caching - Cost reduction | [📖](https://docs.praison.ai/cli/prompt-caching) |
+| 🔄 Query Rewrite - RAG optimization | [📖](https://docs.praison.ai/docs/cli/query-rewrite) |
+| 🔬 Deep Research - Automated research | [📖](https://docs.praison.ai/docs/cli/deep-research) |
+| 📋 Planning - Step-by-step execution | [📖](https://docs.praison.ai/docs/cli/planning) |
+| 💾 Memory - Persistent agent memory | [📖](https://docs.praison.ai/docs/cli/memory) |
+| 📜 Rules - Auto-discovered instructions | [📖](https://docs.praison.ai/docs/cli/rules) |
+| 🔄 Workflow - Multi-step workflows | [📖](https://docs.praison.ai/docs/cli/workflow) |
+| 🪝 Hooks - Event-driven actions | [📖](https://docs.praison.ai/docs/cli/hooks) |
+| 🧠 Claude Memory - Anthropic memory tool | [📖](https://docs.praison.ai/docs/cli/claude-memory) |
+| 🛡️ Guardrail - Output validation | [📖](https://docs.praison.ai/docs/cli/guardrail) |
+| 📊 Metrics - Token usage tracking | [📖](https://docs.praison.ai/docs/cli/metrics) |
+| 🖼️ Image - Vision processing | [📖](https://docs.praison.ai/docs/cli/image) |
+| 📡 Telemetry - Usage monitoring | [📖](https://docs.praison.ai/docs/cli/telemetry) |
+| 🔌 MCP - Model Context Protocol | [📖](https://docs.praison.ai/docs/cli/mcp) |
+| ⚡ Fast Context - Codebase search | [📖](https://docs.praison.ai/docs/cli/fast-context) |
+| 📚 Knowledge - RAG management | [📖](https://docs.praison.ai/docs/cli/knowledge) |
+| 💬 Session - Conversation management | [📖](https://docs.praison.ai/docs/cli/session) |
+| 🔧 Tools - Tool discovery | [📖](https://docs.praison.ai/docs/cli/tools) |
+| 🤝 Handoff - Agent delegation | [📖](https://docs.praison.ai/docs/cli/handoff) |
+| 🧠 Auto Memory - Memory extraction | [📖](https://docs.praison.ai/docs/cli/auto-memory) |
+| 📋 Todo - Task management | [📖](https://docs.praison.ai/docs/cli/todo) |
+| 🎯 Router - Smart model selection | [📖](https://docs.praison.ai/docs/cli/router) |
+| 📈 Flow Display - Visual workflow | [📖](https://docs.praison.ai/docs/cli/flow-display) |
+| ✨ Prompt Expansion - Detailed prompts | [📖](https://docs.praison.ai/docs/cli/prompt-expansion) |
+| 🌐 Web Search - Real-time search | [📖](https://docs.praison.ai/docs/cli/web-search) |
+| 📥 Web Fetch - URL content retrieval | [📖](https://docs.praison.ai/docs/cli/web-fetch) |
+| 💾 Prompt Caching - Cost reduction | [📖](https://docs.praison.ai/docs/cli/prompt-caching) |

 ---

@@ -2209,7 +2452,7 @@ 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

@@ -2218,11 +2461,19 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 - 🔐 **MCP Security** - Origin validation, DNS rebinding prevention, secure sessions
 - 🔄 **MCP Resumability** - SSE stream recovery via Last-Event-ID

+### A2A & A2UI Protocols
+
+- 🔗 **A2A Protocol** - Agent-to-Agent communication for inter-agent collaboration
+- 🖼️ **A2UI Protocol** - Agent-to-User Interface for generating rich UIs from agents
+- 📋 **UI Templates** - ChatTemplate, ListTemplate, FormTemplate, DashboardTemplate
+- 🔧 **Surface Builder** - Fluent API for building declarative UIs
+
 ### Safety & Control

 - 🤝 **Agent Handoffs** - Transfer context between specialised agents
 - 🛡️ **Guardrails** - Input/output validation and safety checks
 - ✅ **Human Approval** - Require human confirmation for critical actions
+- 🔐 **Tool Approval CLI** - `--trust` (auto-approve all) and `--approve-level` (risk-based approval)
 - 💬 **Sessions Management** - Isolated conversation contexts
 - 🔄 **Stateful Agents** - Maintain state across interactions

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
    praisonai_tools \
-    "praisonai>=2.3.37" \
+    "praisonai>=2.3.66" \
    "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>=2.3.37" \
+    "praisonai>=2.3.66" \
    "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>=2.3.37" \
+    "praisonai>=2.3.66" \
    "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 +1,23 @@
+# Example: Data Collection Agent with 30-minute Schedule
+# Collects and analyzes data every 30 minutes
+
+framework: praisonai
+
+agents:
+  - name: "Data Collector"
+    role: "Data Analysis Specialist"
+    goal: "Collect and analyze market data at regular intervals"
+    instructions: |
+      You are a data analysis specialist focused on collecting and analyzing
+      market trends and metrics. Provide actionable insights from the data.
+    tools:
+      - search_tool
+    verbose: false
+
+task: "Collect latest market data and identify key trends"
+
+# Schedule: Every 30 minutes with immediate execution
+schedule:
+  interval: "*/30m"
+  max_retries: 5
+  run_immediately: true
@@ -0,0 +1,53 @@
+# Example: 24/7 AI News Monitor with Scheduler
+# This agent runs continuously at regular intervals to monitor AI news
+
+framework: praisonai
+
+agents:
+  - name: "AI News Monitor"
+    role: "Technology News Analyst"
+    goal: "Monitor and summarize the latest AI developments"
+    instructions: |
+      You are an expert technology news analyst specializing in AI and machine learning.
+      Your job is to search for the latest AI news, identify the most important developments,
+      and provide clear, concise summaries with sources.
+      
+      Focus on:
+      - Major AI product launches
+      - Research breakthroughs
+      - Industry trends
+      - Policy and regulation updates
+    tools:
+      - search_tool
+    verbose: true
+
+# Task to execute on each scheduled run
+task: |
+  Search for the latest AI news from the past 24 hours.
+  Provide the top 3 most important stories with:
+  1. Headline
+  2. Brief summary (2-3 sentences)
+  3. Source URL
+  4. Why it's significant
+
+# Schedule configuration
+schedule:
+  # Interval options:
+  # - "hourly" - Every hour
+  # - "daily" - Every 24 hours
+  # - "*/30m" - Every 30 minutes
+  # - "*/6h" - Every 6 hours
+  # - "3600" - Custom seconds
+  interval: "hourly"
+  
+  # Maximum retry attempts if execution fails
+  max_retries: 3
+  
+  # Run immediately when scheduler starts (before first scheduled interval)
+  run_immediately: true
+
+# Optional: Variables for customization
+variables:
+  news_category: "AI and Machine Learning"
+  region: "Global"
+  time_range: "24 hours"
@@ -0,0 +1,53 @@
+"""
+PraisonAI A2A Server Example
+
+Expose a PraisonAI Agent as an A2A (Agent2Agent) Server.
+This enables other AI agents to discover and communicate with your agent.
+
+Run:
+    uvicorn a2a-server:app --reload
+
+Endpoints:
+    GET /.well-known/agent.json  - Agent Card for discovery
+    GET /status                   - Server status
+"""
+
+from praisonaiagents import Agent, A2A
+from fastapi import FastAPI
+
+# Create an agent with tools
+def search_web(query: str) -> str:
+    """Search the web for information."""
+    return f"Search results for: {query}"
+
+def calculate(expression: str) -> str:
+    """Calculate a mathematical expression."""
+    try:
+        return f"Result: {eval(expression)}"
+    except Exception:
+        return "Invalid expression"
+
+agent = Agent(
+    name="Research Assistant",
+    role="Research Analyst",
+    goal="Help users research topics and answer questions",
+    tools=[search_web, calculate]
+)
+
+# Expose as A2A Server
+a2a = A2A(
+    agent=agent,
+    url="http://localhost:8000/a2a",
+    version="1.0.0"
+)
+
+# Create FastAPI app
+app = FastAPI(
+    title="PraisonAI A2A Server",
+    description="A2A-compatible agent server"
+)
+app.include_router(a2a.get_router())
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)
@@ -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 +1,115 @@
+"""
+24/7 News Checker Agent Example
+
+This example demonstrates how to create a continuously running agent
+that checks for AI news every hour and prints the results.
+
+Usage:
+    python news_checker_agent.py
+    
+The agent will:
+1. Run immediately on start
+2. Check for latest AI news every 1 hour
+3. Print results to console
+4. Continue running until stopped (Ctrl+C)
+"""
+
+import os
+import sys
+from datetime import datetime
+
+# Add parent directory to path for imports
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../..'))
+
+from praisonaiagents import Agent
+from praisonai.agent_scheduler import AgentScheduler
+from tools import search_tool
+
+
+def on_success(result):
+    """Callback function called when agent execution succeeds."""
+    print("\n" + "="*80)
+    print(f"✅ SUCCESS - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print("="*80)
+    print(result)
+    print("="*80 + "\n")
+
+
+def on_failure(error):
+    """Callback function called when agent execution fails."""
+    print("\n" + "="*80)
+    print(f"❌ FAILURE - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print("="*80)
+    print(f"Error: {error}")
+    print("="*80 + "\n")
+
+
+def main():
+    """Main function to set up and run the scheduled news checker agent."""
+    
+    print("\n🤖 Starting 24/7 News Checker Agent")
+    print("="*80)
+    
+    # Create the agent with web search capability
+    agent = Agent(
+        name="NewsChecker",
+        role="AI News Monitor",
+        goal="Monitor and summarize the latest AI and technology news",
+        backstory="""You are an expert AI news analyst who stays up-to-date 
+        with the latest developments in artificial intelligence, machine learning, 
+        and technology. You provide concise, accurate summaries of important news.""",
+        tools=[search_tool],
+        verbose=True
+    )
+    
+    # Define the task
+    task = """Search for the latest AI news from today. 
+    Focus on major developments, breakthroughs, or announcements.
+    Provide a summary of the top 3-5 most important news items.
+    Include the source and key details for each item."""
+    
+    # Create scheduler with callbacks
+    scheduler = AgentScheduler(
+        agent=agent,
+        task=task,
+        on_success=on_success,
+        on_failure=on_failure
+    )
+    
+    print(f"Agent: {agent.name}")
+    print(f"Task: {task}")
+    print(f"Schedule: Every 1 hour")
+    print("="*80)
+    print("\n⏰ Starting scheduler... (Press Ctrl+C to stop)\n")
+    
+    # Start the scheduler
+    # - "hourly" or "*/1h" = every 1 hour
+    # - run_immediately=True = run once before starting the schedule
+    scheduler.start(
+        schedule_expr="hourly",  # Run every hour
+        max_retries=3,           # Retry up to 3 times on failure
+        run_immediately=True     # Run immediately on start
+    )
+    
+    try:
+        # Keep the main thread alive
+        while scheduler.is_running:
+            import time
+            time.sleep(1)
+            
+    except KeyboardInterrupt:
+        print("\n\n🛑 Stopping scheduler...")
+        scheduler.stop()
+        
+        # Print final statistics
+        stats = scheduler.get_stats()
+        print("\n📊 Final Statistics:")
+        print(f"  Total Executions: {stats['total_executions']}")
+        print(f"  Successful: {stats['successful_executions']}")
+        print(f"  Failed: {stats['failed_executions']}")
+        print(f"  Success Rate: {stats['success_rate']:.1f}%")
+        print("\n✅ Agent stopped successfully\n")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,143 @@
+"""
+Live News Checker Agent - 24/7 Scheduled Agent
+
+This example demonstrates a real working agent that checks AI news
+every hour using the AgentScheduler with actual API calls.
+
+Requirements:
+    - OPENAI_API_KEY environment variable set
+    - praisonaiagents package installed
+    
+Usage:
+    python news_checker_live.py
+"""
+
+import os
+import sys
+from datetime import datetime
+
+# Add parent directory to path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../..'))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../../..'))
+
+from praisonaiagents import Agent
+from praisonai.scheduler import AgentScheduler
+
+# Import search_tool from root tools.py
+try:
+    from tools import search_tool
+except ImportError:
+    # Fallback: create inline search tool
+    from duckduckgo_search import DDGS
+    
+    def search_tool(query: str) -> list:
+        """Search the web using DuckDuckGo."""
+        try:
+            results = []
+            ddgs = DDGS()
+            for result in ddgs.text(keywords=query, max_results=5):
+                results.append({
+                    "title": result.get("title", ""),
+                    "url": result.get("href", ""),
+                    "snippet": result.get("body", ""),
+                })
+            return results
+        except Exception as e:
+            print(f"Search error: {e}")
+            return []
+
+
+def on_success(result):
+    """Callback when agent execution succeeds."""
+    print("\n" + "="*80)
+    print(f"✅ SUCCESS - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print("="*80)
+    print(result)
+    print("="*80 + "\n")
+
+
+def on_failure(error):
+    """Callback when agent execution fails."""
+    print("\n" + "="*80)
+    print(f"❌ FAILURE - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print("="*80)
+    print(f"Error: {error}")
+    print("="*80 + "\n")
+
+
+def main():
+    """Main function to run the scheduled news checker."""
+    
+    # Check for API key
+    if not os.getenv("OPENAI_API_KEY"):
+        print("❌ Error: OPENAI_API_KEY environment variable not set")
+        print("Please set it with: export OPENAI_API_KEY=your_key_here")
+        sys.exit(1)
+    
+    print("\n🤖 Starting 24/7 AI News Checker Agent")
+    print("="*80)
+    
+    # Create the agent with web search capability
+    agent = Agent(
+        name="AI News Monitor",
+        role="Technology News Analyst",
+        goal="Monitor and summarize the latest AI and technology news",
+        backstory="""You are an expert AI news analyst who stays up-to-date 
+        with the latest developments in artificial intelligence, machine learning, 
+        and technology. You provide concise, accurate summaries of important news.""",
+        tools=[search_tool],
+        verbose=True,
+        self_reflect=False  # Disable reflection for faster execution
+    )
+    
+    # Define the task
+    task = """Search for the latest AI news from today. 
+    Focus on major developments, breakthroughs, or announcements.
+    Provide a summary of the top 3 most important news items.
+    Include the source and key details for each item."""
+    
+    # Create scheduler with callbacks
+    scheduler = AgentScheduler(
+        agent=agent,
+        task=task,
+        on_success=on_success,
+        on_failure=on_failure
+    )
+    
+    print(f"Agent: {agent.name}")
+    print(f"Task: {task}")
+    print(f"Schedule: Every 1 hour")
+    print("="*80)
+    print("\n⏰ Starting scheduler... (Press Ctrl+C to stop)\n")
+    
+    # Start the scheduler
+    # For testing: use "*/2m" (every 2 minutes) instead of "hourly"
+    # For production: use "hourly"
+    scheduler.start(
+        schedule_expr="*/2m",  # Every 2 minutes for testing
+        max_retries=3,
+        run_immediately=True  # Run once immediately
+    )
+    
+    try:
+        # Keep the main thread alive
+        while scheduler.is_running:
+            import time
+            time.sleep(1)
+            
+    except KeyboardInterrupt:
+        print("\n\n🛑 Stopping scheduler...")
+        scheduler.stop()
+        
+        # Print final statistics
+        stats = scheduler.get_stats()
+        print("\n📊 Final Statistics:")
+        print(f"  Total Executions: {stats['total_executions']}")
+        print(f"  Successful: {stats['successful_executions']}")
+        print(f"  Failed: {stats['failed_executions']}")
+        print(f"  Success Rate: {stats['success_rate']:.1f}%")
+        print("\n✅ Agent stopped successfully\n")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,61 @@
+"""
+Simple test script for 24/7 Agent Scheduler
+
+This script demonstrates the basic usage of AgentScheduler
+for running agents periodically.
+
+Usage:
+    python simple_test.py
+"""
+
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../..'))
+
+from unittest.mock import Mock
+from praisonai.scheduler import AgentScheduler
+
+# Create a mock agent for testing
+mock_agent = Mock()
+mock_agent.name = "TestAgent"
+mock_agent.start = Mock(return_value="Test execution successful!")
+
+# Create scheduler
+scheduler = AgentScheduler(
+    agent=mock_agent,
+    task="Test task execution"
+)
+
+print("🤖 Testing AgentScheduler")
+print("=" * 60)
+
+# Test 1: Execute once
+print("\n✅ Test 1: Execute once")
+result = scheduler.execute_once()
+print(f"Result: {result}")
+
+# Test 2: Get stats
+print("\n✅ Test 2: Get statistics")
+stats = scheduler.get_stats()
+print(f"Stats: {stats}")
+
+# Test 3: Start scheduler (will run every 5 seconds)
+print("\n✅ Test 3: Start scheduler (*/5s)")
+scheduler.start("*/5s", run_immediately=True)
+
+import time
+print("Running for 12 seconds...")
+time.sleep(12)
+
+# Stop scheduler
+print("\n✅ Test 4: Stop scheduler")
+scheduler.stop()
+
+# Final stats
+print("\n📊 Final Statistics:")
+final_stats = scheduler.get_stats()
+for key, value in final_stats.items():
+    print(f"  {key}: {value}")
+
+print("\n✅ All tests passed!")
+print("=" * 60)
@@ -0,0 +1,14 @@
+framework: praisonai
+
+agents:
+  - name: "5 Second Timer"
+    role: "Timer Agent"
+    instructions: "Display the current time"
+    verbose: true
+
+task: "Show current time"
+
+schedule:
+  interval: "*/5s"
+  max_retries: 3
+  run_immediately: true
@@ -0,0 +1,14 @@
+framework: praisonai
+
+agents:
+  - name: "Counter Agent"
+    role: "Counter"
+    instructions: "Count from 1 to 5, incrementing by 1 each time. Just output the numbers clearly."
+    verbose: true
+
+task: "Print numbers 1, 2, 3, 4, 5 (one number per line)"
+
+schedule:
+  interval: "*/5s"
+  max_retries: 3
+  run_immediately: true
@@ -0,0 +1,16 @@
+framework: praisonai
+
+agents:
+  - name: "Counter Agent with Limits"
+    role: "Counter"
+    instructions: "Count from 1 to 5, incrementing by 1 each time. Just output the numbers clearly."
+    verbose: true
+
+task: "Print numbers 1, 2, 3, 4, 5 (one number per line)"
+
+schedule:
+  interval: "*/5s"           # Run every 5 seconds
+  max_retries: 3             # Retry up to 3 times on failure
+  run_immediately: true      # Run once immediately on start
+  timeout: 30                # Max 30 seconds per execution
+  max_cost: 0.01             # Stop after spending $0.01 USD
@@ -0,0 +1,15 @@
+framework: praisonai
+
+agents:
+  - name: "Budget Test Agent"
+    role: "Tester"
+    instructions: "Count from 1 to 3"
+    verbose: true
+
+task: "Print numbers 1, 2, 3"
+
+schedule:
+  interval: "*/3s"
+  max_retries: 2
+  run_immediately: true
+  # No max_cost specified - should default to $1.00
@@ -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()
@@ -314,3 +314,12 @@ except ImportError:
    _agui_available = False
    AGUI = None

+# A2A support (optional, lazy loaded)
+try:
+    from praisonaiagents.ui.a2a import A2A
+    __all__.append('A2A')
+    _a2a_available = True
+except ImportError:
+    _a2a_available = False
+    A2A = None
+
@@ -55,10 +55,10 @@ def _get_all_noisy_loggers() -> List[str]:

 def _configure_loggers():
    """Configure all loggers based on LOGLEVEL environment variable."""
-    loglevel = os.environ.get('LOGLEVEL', 'INFO').upper()
+    loglevel = os.environ.get('LOGLEVEL', 'WARNING').upper()
    
-    # When DEBUG is set, allow some HTTP logging for API endpoints
-    if loglevel == 'DEBUG':
+    # When DEBUG or INFO is set, allow some HTTP logging for API endpoints
+    if loglevel in ('DEBUG', 'INFO'):
        allowed_debug_loggers = {"httpx", "httpx._client", "openai._client"}
        
        for logger_name in _get_all_noisy_loggers():
@@ -109,10 +109,10 @@ def configure_root_logger():
    """Configure the root logger with RichHandler."""
    from rich.logging import RichHandler
    
-    loglevel = os.environ.get('LOGLEVEL', 'INFO').upper()
+    loglevel = os.environ.get('LOGLEVEL', 'WARNING').upper()
    
    logging.basicConfig(
-        level=getattr(logging, loglevel, logging.INFO),
+        level=getattr(logging, loglevel, logging.WARNING),
        format="%(asctime)s %(filename)s:%(lineno)d %(levelname)s %(message)s",
        datefmt="[%X]",
        handlers=[RichHandler(rich_tracebacks=True)],
@@ -29,7 +29,9 @@ SUPPRESSED_PATTERNS = [
    "PydanticSerializationUnexpectedValue",
    "Expected 9 fields but got 5 for type `Message`",
    "Expected `StreamingChoices` but got `Choices`",
-    "serialized value may not be as expected"
+    "serialized value may not be as expected",
+    "Mixing V1 models and V2 models",
+    "Please upgrade `Settings` to V2"
 ]

@functools.wraps(_original_warn)
@@ -1538,13 +1538,13 @@ Your Goal: {self.goal}"""
        logging.debug(f"{self.name} executing tool {function_name} with arguments: {arguments}")

        # Check if approval is required for this tool
-        from ..approval import is_approval_required, console_approval_callback, get_risk_level, mark_approved, ApprovalDecision
+        from ..approval import is_approval_required, console_approval_callback, get_risk_level, mark_approved, ApprovalDecision, get_approval_callback
        if is_approval_required(function_name):
            risk_level = get_risk_level(function_name)
-            logging.info(f"Tool {function_name} requires approval (risk level: {risk_level})")
+            logging.debug(f"Tool {function_name} requires approval (risk level: {risk_level})")
            
            # Use global approval callback or default console callback
-            callback = approval_callback or console_approval_callback
+            callback = get_approval_callback() or console_approval_callback
            
            try:
                decision = callback(function_name, arguments, risk_level)
@@ -43,6 +43,15 @@ def set_approval_callback(callback_fn: Callable):
    global approval_callback
    approval_callback = callback_fn

+def get_approval_callback() -> Optional[Callable]:
+    """Get the current approval callback function.
+    
+    Returns the custom callback if set, otherwise None.
+    This should be used instead of directly accessing approval_callback
+    to ensure the latest callback is always used.
+    """
+    return approval_callback
+
 def mark_approved(tool_name: str):
    """Mark a tool as approved in the current context."""
    approved = _approved_context.get(set())
@@ -90,7 +99,7 @@ def require_approval(risk_level: RiskLevel = "high"):
            except Exception as e:
                # Fallback to sync approval if async fails
                logging.warning(f"Async approval failed, using sync fallback: {e}")
-                callback = approval_callback or console_approval_callback
+                callback = get_approval_callback() or console_approval_callback
                decision = callback(tool_name, kwargs, risk_level)
            
            if not decision.approved:
@@ -198,7 +207,7 @@ async def request_approval(function_name: str, arguments: Dict[str, Any]) -> App
    risk_level = TOOL_RISK_LEVELS.get(function_name, "medium")
    
    # Use custom callback if set, otherwise use console callback
-    callback = approval_callback or console_approval_callback
+    callback = get_approval_callback() or console_approval_callback
    
    try:
        # Handle async callbacks
@@ -1054,7 +1054,7 @@ class LLM:
        **kwargs
    ) -> str:
        """Enhanced get_response with all OpenAI-like features"""
-        logging.info(f"Getting response from {self.model}")
+        logging.debug(f"Getting response from {self.model}")
        # Log all self values when in debug mode
        self._log_llm_config(
            'LLM instance',
@@ -2472,7 +2472,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
        """Async version of get_response with identical functionality."""
        try:
            import litellm
-            logging.info(f"Getting async response from {self.model}")
+            logging.debug(f"Getting async response from {self.model}")
            # Log all self values when in debug mode
            self._log_llm_config(
                'get_response_async',
@@ -19,6 +19,15 @@ from rich.console import Console
 from rich.live import Live
 import inspect

+# Import display_tool_call for callback support (lazy import to avoid circular imports)
+_display_tool_call = None
+def _get_display_tool_call():
+    global _display_tool_call
+    if _display_tool_call is None:
+        from ..main import display_tool_call
+        _display_tool_call = display_tool_call
+    return _display_tool_call
+
 # Constants
 LOCAL_SERVER_API_KEY_PLACEHOLDER = "not-needed"

@@ -978,16 +987,19 @@ class OpenAIClient:
                        function_name = tool_call.function.name
                        arguments = json.loads(tool_call.function.arguments)
                    
+                    # Always trigger callback for tool call tracking (even when verbose=False)
+                    display_tool_call_fn = _get_display_tool_call()
+                    display_tool_call_fn(f"Calling function: {function_name}", console=console if verbose else None)
+                    
                    if verbose and console:
-                        console.print(f"[bold]Calling function:[/bold] {function_name}")
                        console.print(f"[dim]Arguments:[/dim] {arguments}")
                    
                    # Execute the tool
                    tool_result = execute_tool_fn(function_name, arguments)
                    results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
                    
-                    if verbose and console:
-                        console.print(f"[dim]Result:[/dim] {results_str}")
+                    # Trigger callback with result
+                    display_tool_call_fn(f"Function {function_name} returned: {results_str[:200]}{'...' if len(results_str) > 200 else ''}", console=console if verbose else None)
                    
                    messages.append({
                        "role": "tool",
@@ -1150,8 +1162,11 @@ class OpenAIClient:
                        function_name = tool_call.function.name
                        arguments = json.loads(tool_call.function.arguments)
                    
+                    # Always trigger callback for tool call tracking (even when verbose=False)
+                    display_tool_call_fn = _get_display_tool_call()
+                    display_tool_call_fn(f"Calling function: {function_name}", console=console if verbose else None)
+                    
                    if verbose and console:
-                        console.print(f"[bold]Calling function:[/bold] {function_name}")
                        console.print(f"[dim]Arguments:[/dim] {arguments}")
                    
                    # Execute the tool (async)
@@ -1167,8 +1182,8 @@ class OpenAIClient:
                    
                    results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
                    
-                    if verbose and console:
-                        console.print(f"[dim]Result:[/dim] {results_str}")
+                    # Trigger callback with result
+                    display_tool_call_fn(f"Function {function_name} returned: {results_str[:200]}{'...' if len(results_str) > 200 else ''}", console=console if verbose else None)
                    
                    messages.append({
                        "role": "tool",
@@ -1299,6 +1314,10 @@ class OpenAIClient:
                                yield f"\n[Error parsing arguments for {function_name if 'function_name' in locals() else 'unknown function'}: {str(e)}]"
                            continue
                        
+                        # Always trigger callback for tool call tracking (even when verbose=False)
+                        display_tool_call_fn = _get_display_tool_call()
+                        display_tool_call_fn(f"Calling function: {function_name}", console=None)
+                        
                        if verbose:
                            yield f"\n[Calling function: {function_name}]"
                        
@@ -1311,6 +1330,9 @@ class OpenAIClient:
                            if verbose:
                                yield f"\n[Function error: {str(e)}]"
                        
+                        # Trigger callback with result
+                        display_tool_call_fn(f"Function {function_name} returned: {results_str[:200]}{'...' if len(results_str) > 200 else ''}", console=None)
+                        
                        if verbose:
                            yield f"\n[Function result: {results_str}]"
                        
@@ -231,15 +231,15 @@ def display_tool_call(message: str, console=None):
    if not message or not message.strip():
        logging.debug("Empty message in display_tool_call, returning early")
        return
-    if console is None:
-        console = Console()
    message = _clean_display_content(str(message))
    logging.debug(f"Cleaned message in display_tool_call: {repr(message)}")
    
-    # Execute synchronous callbacks
+    # Execute synchronous callbacks (always, even when console is None)
    execute_sync_callback('tool_call', message=message)
    
-    console.print(Panel.fit(Text(message, style="bold cyan"), title="Tool Call", border_style="green"))
+    # Only print panel if console is provided (verbose mode)
+    if console is not None:
+        console.print(Panel.fit(Text(message, style="bold cyan"), title="Tool Call", border_style="green"))

 def display_error(message: str, console=None):
    if not message or not message.strip():
@@ -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',
@@ -14,6 +14,7 @@ Usage:
    context, cleaned_prompt = parser.process("@file:main.py explain this code")
 """

+import os
 import re
 import logging
 from pathlib import Path
@@ -43,10 +44,14 @@ class MentionsParser:
        "url": re.compile(r'@url:(https?://[^\s]+)'),
    }
    
+    # Default max file chars: 500K (~125K tokens) - fits GPT-4o (128K), Claude 3.5 (200K)
+    DEFAULT_MAX_FILE_CHARS = 500000
+    
    def __init__(
        self,
        workspace_path: Optional[str] = None,
-        verbose: int = 0
+        verbose: int = 0,
+        max_file_chars: Optional[int] = None
    ):
        """
        Initialize MentionsParser.
@@ -54,10 +59,24 @@ class MentionsParser:
        Args:
            workspace_path: Path to workspace/project root
            verbose: Verbosity level
+            max_file_chars: Maximum characters to include from files.
+                           Default: 500000 (500K chars, ~125K tokens).
+                           Set to 0 for no limit.
+                           Can be overridden via PRAISON_MAX_FILE_CHARS env var.
        """
        self.workspace_path = Path(workspace_path) if workspace_path else Path.cwd()
        self.verbose = verbose
        
+        # Configure max file chars: constructor > env var > default
+        if max_file_chars is not None:
+            self.max_file_chars = max_file_chars
+        else:
+            env_val = os.environ.get('PRAISON_MAX_FILE_CHARS')
+            if env_val is not None:
+                self.max_file_chars = int(env_val)
+            else:
+                self.max_file_chars = self.DEFAULT_MAX_FILE_CHARS
+        
        # Lazy-loaded managers
        self._docs_manager = None
        self._rules_manager = None
@@ -158,9 +177,15 @@ class MentionsParser:
            
            content = full_path.read_text(encoding="utf-8")
            
-            # Limit content size
-            if len(content) > 50000:
-                content = content[:50000] + "\n... (truncated)"
+            # Limit content size (0 means no limit)
+            if self.max_file_chars > 0 and len(content) > self.max_file_chars:
+                original_size = len(content)
+                content = content[:self.max_file_chars] + "\n... (truncated)"
+                self._log(
+                    f"File {file_path} truncated from {original_size:,} to {self.max_file_chars:,} chars. "
+                    f"Set PRAISON_MAX_FILE_CHARS=0 for no limit.",
+                    logging.WARNING
+                )
            
            # Detect language for code fence
            ext = full_path.suffix.lower()
@@ -253,9 +278,9 @@ class MentionsParser:
            with urllib.request.urlopen(req, timeout=10) as response:
                content = response.read().decode('utf-8', errors='ignore')
            
-            # Limit content size
-            if len(content) > 50000:
-                content = content[:50000] + "\n... (truncated)"
+            # Limit content size (0 means no limit)
+            if self.max_file_chars > 0 and len(content) > self.max_file_chars:
+                content = content[:self.max_file_chars] + "\n... (truncated)"
            
            # Try to extract text from HTML
            if '<html' in content.lower():
@@ -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}")
@@ -0,0 +1,74 @@
+"""
+A2A Protocol Integration for PraisonAI Agents
+
+This module provides A2A (Agent2Agent) protocol support,
+enabling PraisonAI Agents to be exposed as A2A Servers
+for agent-to-agent communication.
+
+Usage:
+    from praisonaiagents import Agent
+    from praisonaiagents.ui.a2a import A2A
+    from fastapi import FastAPI
+
+    agent = Agent(name="Assistant", role="Helper", goal="Help users")
+    a2a = A2A(agent=agent)
+
+    app = FastAPI()
+    app.include_router(a2a.get_router())
+    
+    # Agent Card available at: GET /.well-known/agent.json
+    # A2A endpoint at: POST /a2a (JSON-RPC)
+"""
+
+from praisonaiagents.ui.a2a.a2a import A2A
+from praisonaiagents.ui.a2a.types import (
+    # Enums
+    TaskState,
+    Role,
+    # Part types
+    TextPart,
+    FilePart,
+    DataPart,
+    # Core types
+    Message,
+    TaskStatus,
+    Task,
+    Artifact,
+    # Agent Card types
+    AgentSkill,
+    AgentCapabilities,
+    AgentCard,
+    # Request/Response types
+    MessageConfig,
+    SendMessageRequest,
+    # Streaming events
+    TaskStatusUpdateEvent,
+    TaskArtifactUpdateEvent,
+)
+
+__all__ = [
+    # Main class
+    "A2A",
+    # Enums
+    "TaskState",
+    "Role",
+    # Part types
+    "TextPart",
+    "FilePart",
+    "DataPart",
+    # Core types
+    "Message",
+    "TaskStatus",
+    "Task",
+    "Artifact",
+    # Agent Card types
+    "AgentSkill",
+    "AgentCapabilities",
+    "AgentCard",
+    # Request/Response types
+    "MessageConfig",
+    "SendMessageRequest",
+    # Streaming events
+    "TaskStatusUpdateEvent",
+    "TaskArtifactUpdateEvent",
+]
@@ -0,0 +1,154 @@
+"""
+A2A - Main A2A Interface Class
+
+Exposes PraisonAI Agents via the A2A (Agent2Agent) protocol.
+"""
+
+import logging
+from typing import List, Optional, TYPE_CHECKING
+
+from praisonaiagents.ui.a2a.types import AgentCard
+from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+from praisonaiagents.ui.a2a.task_store import TaskStore
+
+if TYPE_CHECKING:
+    from praisonaiagents import Agent, PraisonAIAgents
+    from fastapi import APIRouter
+
+logger = logging.getLogger(__name__)
+
+
+class A2A:
+    """
+    A2A Interface for PraisonAI Agents.
+    
+    Exposes a PraisonAI Agent or PraisonAIAgents workflow via the A2A protocol,
+    enabling agent-to-agent communication with other A2A-compatible systems.
+    
+    Usage:
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        from fastapi import FastAPI
+        
+        agent = Agent(name="Assistant", role="Helper", goal="Help users")
+        a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+        
+        app = FastAPI()
+        app.include_router(a2a.get_router())
+        
+        # Agent Card at: GET /.well-known/agent.json
+        # A2A endpoint at: POST /a2a
+    
+    Args:
+        agent: Single PraisonAI Agent instance
+        agents: PraisonAIAgents instance for multi-agent workflows
+        name: Name for the A2A endpoint (defaults to agent name)
+        description: Description of the agent
+        url: URL where the A2A endpoint is hosted
+        version: Version string for the agent
+        prefix: URL prefix for the router
+        tags: OpenAPI tags for the router
+    """
+    
+    def __init__(
+        self,
+        agent: Optional["Agent"] = None,
+        agents: Optional["PraisonAIAgents"] = None,
+        name: Optional[str] = None,
+        description: Optional[str] = None,
+        url: str = "http://localhost:8000/a2a",
+        version: str = "1.0.0",
+        prefix: str = "",
+        tags: Optional[List[str]] = None,
+    ):
+        if agent is None and agents is None:
+            raise ValueError("A2A requires an agent or agents instance")
+        
+        self.agent = agent
+        self.agents = agents
+        self.url = url
+        self.version = version
+        self.prefix = prefix
+        self.tags = tags or ["A2A"]
+        
+        # Set name from agent if not provided
+        if name:
+            self.name = name
+        elif agent and hasattr(agent, 'name'):
+            self.name = agent.name
+        elif agents and hasattr(agents, 'name'):
+            self.name = agents.name
+        else:
+            self.name = "PraisonAI Agent"
+        
+        # Set description
+        if description:
+            self.description = description
+        elif agent and hasattr(agent, 'role'):
+            self.description = agent.role
+        else:
+            self.description = "PraisonAI Agent via A2A"
+        
+        # Initialize task store
+        self.task_store = TaskStore()
+        
+        # Router cache
+        self._router: Optional["APIRouter"] = None
+        self._agent_card: Optional[AgentCard] = None
+    
+    def get_agent_card(self) -> AgentCard:
+        """
+        Get the Agent Card for this A2A instance.
+        
+        Returns:
+            AgentCard object for A2A discovery
+        """
+        if self._agent_card is None:
+            self._agent_card = generate_agent_card(
+                agent=self.agent,
+                url=self.url,
+                version=self.version,
+                streaming=True,
+            )
+        return self._agent_card
+    
+    def get_router(self) -> "APIRouter":
+        """
+        Get the FastAPI router for this A2A instance.
+        
+        Returns:
+            FastAPI APIRouter with A2A endpoints
+        """
+        if self._router is None:
+            self._router = self._create_router()
+        return self._router
+    
+    def _create_router(self) -> "APIRouter":
+        """Create FastAPI router with A2A endpoints."""
+        from fastapi import APIRouter
+        from fastapi.responses import JSONResponse
+        
+        router = APIRouter(prefix=self.prefix, tags=self.tags)
+        
+        # Agent Card endpoint (well-known URI)
+        @router.get("/.well-known/agent.json")
+        async def get_agent_card():
+            """Return the Agent Card for discovery."""
+            card = self.get_agent_card()
+            return JSONResponse(content=card.model_dump(by_alias=True, exclude_none=True))
+        
+        # Status endpoint
+        @router.get("/status")
+        async def get_status():
+            """Return server status."""
+            return {
+                "status": "ok",
+                "name": self.name,
+                "version": self.version,
+            }
+        
+        # TODO: Add JSON-RPC endpoint for message/send
+        # TODO: Add streaming endpoint for message/stream
+        # TODO: Add task management endpoints
+        
+        return router
@@ -0,0 +1,123 @@
+"""
+A2A Agent Card Generation
+
+Generate Agent Cards from PraisonAI Agents for A2A discovery.
+"""
+
+import inspect
+from typing import TYPE_CHECKING, List, Optional
+
+from praisonaiagents.ui.a2a.types import (
+    AgentCard,
+    AgentCapabilities,
+    AgentSkill,
+)
+
+if TYPE_CHECKING:
+    from praisonaiagents import Agent
+
+
+def extract_skills_from_tools(tools: Optional[List]) -> List[AgentSkill]:
+    """
+    Extract AgentSkill objects from a list of tools.
+    
+    Args:
+        tools: List of tool functions or objects
+        
+    Returns:
+        List of AgentSkill objects
+    """
+    if not tools:
+        return []
+    
+    skills = []
+    
+    for tool in tools:
+        # Skip non-callable items
+        if not callable(tool):
+            continue
+        
+        # Get function name
+        name = getattr(tool, '__name__', None)
+        if not name:
+            continue
+        
+        # Get description from docstring
+        docstring = inspect.getdoc(tool)
+        description = docstring.split('\n')[0] if docstring else f"Tool: {name}"
+        
+        # Create skill
+        skill = AgentSkill(
+            id=name,
+            name=name,
+            description=description,
+            tags=["tool"],
+        )
+        skills.append(skill)
+    
+    return skills
+
+
+def generate_agent_card(
+    agent: "Agent",
+    url: str,
+    version: str = "1.0.0",
+    streaming: bool = False,
+    push_notifications: bool = False,
+) -> AgentCard:
+    """
+    Generate an A2A Agent Card from a PraisonAI Agent.
+    
+    Args:
+        agent: PraisonAI Agent instance
+        url: URL where the A2A endpoint is hosted
+        version: Version string for the agent
+        streaming: Whether streaming is supported
+        push_notifications: Whether push notifications are supported
+        
+    Returns:
+        AgentCard object for A2A discovery
+    """
+    # Get agent name
+    name = getattr(agent, 'name', None) or "PraisonAI Agent"
+    
+    # Build description from role, goal, or instructions
+    description_parts = []
+    
+    role = getattr(agent, 'role', None)
+    if role:
+        description_parts.append(role)
+    
+    goal = getattr(agent, 'goal', None)
+    if goal:
+        description_parts.append(goal)
+    
+    instructions = getattr(agent, 'instructions', None)
+    if instructions and not description_parts:
+        # Use first line of instructions if no role/goal
+        description_parts.append(instructions.split('\n')[0][:200])
+    
+    description = ". ".join(description_parts) if description_parts else "PraisonAI Agent"
+    
+    # Extract skills from tools
+    tools = getattr(agent, 'tools', None)
+    skills = extract_skills_from_tools(tools)
+    
+    # Build capabilities
+    capabilities = AgentCapabilities(
+        streaming=streaming,
+        push_notifications=push_notifications,
+    )
+    
+    # Create Agent Card
+    card = AgentCard(
+        name=name,
+        url=url,
+        version=version,
+        description=description,
+        capabilities=capabilities,
+        skills=skills if skills else None,
+        provider={"name": "PraisonAI"},
+    )
+    
+    return card
@@ -0,0 +1,131 @@
+"""
+A2A Message Conversion
+
+Convert between A2A protocol messages and PraisonAI internal format.
+"""
+
+import uuid
+from typing import Any, Dict, List, Optional
+
+from praisonaiagents.ui.a2a.types import (
+    Message,
+    Role,
+    TextPart,
+    Artifact,
+)
+
+
+def a2a_to_praisonai_messages(messages: List[Message]) -> List[Dict[str, Any]]:
+    """
+    Convert A2A messages to PraisonAI/OpenAI chat format.
+    
+    Args:
+        messages: List of A2A Message objects
+        
+    Returns:
+        List of dicts in OpenAI chat format {"role": ..., "content": ...}
+    """
+    result = []
+    
+    for msg in messages:
+        # Map A2A role to OpenAI role
+        role = "user" if msg.role == Role.USER else "assistant"
+        
+        # Combine all text parts
+        content_parts = []
+        for part in msg.parts:
+            if isinstance(part, TextPart):
+                content_parts.append(part.text)
+            elif hasattr(part, 'text'):
+                content_parts.append(part.text)
+        
+        content = " ".join(content_parts)
+        
+        result.append({
+            "role": role,
+            "content": content,
+        })
+    
+    return result
+
+
+def praisonai_to_a2a_message(
+    response: str,
+    message_id: Optional[str] = None,
+    context_id: Optional[str] = None,
+    task_id: Optional[str] = None,
+) -> Message:
+    """
+    Convert PraisonAI response to A2A Message.
+    
+    Args:
+        response: Text response from agent
+        message_id: Optional message ID (auto-generated if not provided)
+        context_id: Optional context ID
+        task_id: Optional task ID
+        
+    Returns:
+        A2A Message object
+    """
+    msg_id = message_id or f"msg-{uuid.uuid4().hex[:12]}"
+    
+    return Message(
+        message_id=msg_id,
+        role=Role.AGENT,
+        parts=[TextPart(text=response)],
+        context_id=context_id,
+        task_id=task_id,
+    )
+
+
+def create_artifact(
+    content: str,
+    artifact_id: Optional[str] = None,
+    name: Optional[str] = None,
+    description: Optional[str] = None,
+) -> Artifact:
+    """
+    Create an A2A Artifact from response content.
+    
+    Args:
+        content: Text content for the artifact
+        artifact_id: Optional artifact ID (auto-generated if not provided)
+        name: Optional artifact name
+        description: Optional artifact description
+        
+    Returns:
+        A2A Artifact object
+    """
+    art_id = artifact_id or f"art-{uuid.uuid4().hex[:12]}"
+    
+    return Artifact(
+        artifact_id=art_id,
+        name=name,
+        description=description,
+        parts=[TextPart(text=content)],
+    )
+
+
+def extract_user_input(messages: List[Message]) -> str:
+    """
+    Extract the last user input from a list of messages.
+    
+    Args:
+        messages: List of A2A Message objects
+        
+    Returns:
+        Text content of the last user message, or empty string if none
+    """
+    # Find the last user message
+    for msg in reversed(messages):
+        if msg.role == Role.USER:
+            # Combine text parts
+            content_parts = []
+            for part in msg.parts:
+                if isinstance(part, TextPart):
+                    content_parts.append(part.text)
+                elif hasattr(part, 'text'):
+                    content_parts.append(part.text)
+            return " ".join(content_parts)
+    
+    return ""
@@ -0,0 +1,189 @@
+"""
+A2A Streaming Events
+
+SSE streaming support for A2A task updates.
+"""
+
+import json
+from typing import AsyncIterator, Optional
+
+from praisonaiagents.ui.a2a.types import (
+    Task,
+    TaskState,
+    TaskStatus,
+    TaskStatusUpdateEvent,
+    TaskArtifactUpdateEvent,
+    Artifact,
+    TextPart,
+)
+
+
+class A2AEventEncoder:
+    """Encode A2A events for SSE streaming."""
+    
+    @staticmethod
+    def encode_event(event_type: str, data: dict) -> str:
+        """
+        Encode an event for SSE streaming.
+        
+        Args:
+            event_type: Type of event (e.g., "task.status", "task.artifact")
+            data: Event data as dict
+            
+        Returns:
+            SSE-formatted string
+        """
+        json_data = json.dumps(data, default=str)
+        return f"event: {event_type}\ndata: {json_data}\n\n"
+    
+    @staticmethod
+    def encode_task_status(event: TaskStatusUpdateEvent) -> str:
+        """Encode TaskStatusUpdateEvent for SSE."""
+        data = event.model_dump(by_alias=True, exclude_none=True)
+        return A2AEventEncoder.encode_event("task.status", data)
+    
+    @staticmethod
+    def encode_task_artifact(event: TaskArtifactUpdateEvent) -> str:
+        """Encode TaskArtifactUpdateEvent for SSE."""
+        data = event.model_dump(by_alias=True, exclude_none=True)
+        return A2AEventEncoder.encode_event("task.artifact", data)
+    
+    @staticmethod
+    def encode_task(task: Task) -> str:
+        """Encode Task object for SSE."""
+        data = task.model_dump(by_alias=True, exclude_none=True)
+        return A2AEventEncoder.encode_event("task", data)
+    
+    @staticmethod
+    def encode_done() -> str:
+        """Encode stream completion event."""
+        return "event: done\ndata: {}\n\n"
+
+
+def create_status_event(
+    task_id: str,
+    state: TaskState,
+    context_id: Optional[str] = None,
+    final: bool = False,
+) -> TaskStatusUpdateEvent:
+    """
+    Create a TaskStatusUpdateEvent.
+    
+    Args:
+        task_id: Task ID
+        state: New task state
+        context_id: Optional context ID
+        final: Whether this is the final event
+        
+    Returns:
+        TaskStatusUpdateEvent
+    """
+    return TaskStatusUpdateEvent(
+        task_id=task_id,
+        context_id=context_id,
+        status=TaskStatus(state=state),
+        final=final,
+    )
+
+
+def create_artifact_event(
+    task_id: str,
+    content: str,
+    artifact_id: Optional[str] = None,
+    context_id: Optional[str] = None,
+    append: bool = False,
+    last_chunk: bool = False,
+) -> TaskArtifactUpdateEvent:
+    """
+    Create a TaskArtifactUpdateEvent.
+    
+    Args:
+        task_id: Task ID
+        content: Artifact content
+        artifact_id: Optional artifact ID
+        context_id: Optional context ID
+        append: Whether to append to existing artifact
+        last_chunk: Whether this is the last chunk
+        
+    Returns:
+        TaskArtifactUpdateEvent
+    """
+    import uuid
+    art_id = artifact_id or f"art-{uuid.uuid4().hex[:12]}"
+    
+    artifact = Artifact(
+        artifact_id=art_id,
+        parts=[TextPart(text=content)],
+    )
+    
+    return TaskArtifactUpdateEvent(
+        task_id=task_id,
+        context_id=context_id,
+        artifact=artifact,
+        append=append,
+        last_chunk=last_chunk,
+    )
+
+
+async def stream_agent_response(
+    agent,
+    user_input: str,
+    task_id: str,
+    context_id: Optional[str] = None,
+) -> AsyncIterator[str]:
+    """
+    Stream agent response as A2A events.
+    
+    Args:
+        agent: PraisonAI Agent instance
+        user_input: User input text
+        task_id: Task ID
+        context_id: Optional context ID
+        
+    Yields:
+        SSE-formatted event strings
+    """
+    encoder = A2AEventEncoder()
+    
+    # Emit working status
+    working_event = create_status_event(
+        task_id=task_id,
+        state=TaskState.WORKING,
+        context_id=context_id,
+    )
+    yield encoder.encode_task_status(working_event)
+    
+    try:
+        # Get response from agent
+        response = agent.chat(user_input)
+        
+        # Emit artifact with response
+        artifact_event = create_artifact_event(
+            task_id=task_id,
+            content=str(response),
+            context_id=context_id,
+            last_chunk=True,
+        )
+        yield encoder.encode_task_artifact(artifact_event)
+        
+        # Emit completed status
+        completed_event = create_status_event(
+            task_id=task_id,
+            state=TaskState.COMPLETED,
+            context_id=context_id,
+            final=True,
+        )
+        yield encoder.encode_task_status(completed_event)
+        
+    except Exception:
+        # Emit failed status
+        failed_event = create_status_event(
+            task_id=task_id,
+            state=TaskState.FAILED,
+            context_id=context_id,
+            final=True,
+        )
+        yield encoder.encode_task_status(failed_event)
+    
+    # Emit done
+    yield encoder.encode_done()
@@ -0,0 +1,209 @@
+"""
+A2A Task Store
+
+In-memory storage for A2A Task lifecycle management.
+"""
+
+import uuid
+from datetime import datetime, timezone
+from typing import Dict, List, Optional
+
+from praisonaiagents.ui.a2a.types import (
+    Task,
+    TaskState,
+    TaskStatus,
+    Message,
+    Artifact,
+)
+
+
+class TaskStore:
+    """
+    In-memory store for A2A Tasks.
+    
+    Manages task lifecycle including creation, status updates,
+    artifact storage, and message history.
+    """
+    
+    def __init__(self):
+        """Initialize empty task store."""
+        self._tasks: Dict[str, Task] = {}
+    
+    def create_task(self, message: Message, context_id: Optional[str] = None) -> Task:
+        """
+        Create a new task from an incoming message.
+        
+        Args:
+            message: The initial message that triggers the task
+            context_id: Optional context ID (uses message's context_id if not provided)
+            
+        Returns:
+            Newly created Task in SUBMITTED state
+        """
+        task_id = f"task-{uuid.uuid4().hex[:12]}"
+        ctx_id = context_id or message.context_id
+        
+        # Create initial status
+        status = TaskStatus(
+            state=TaskState.SUBMITTED,
+            timestamp=datetime.now(timezone.utc).isoformat(),
+        )
+        
+        # Create task with initial message in history
+        task = Task(
+            id=task_id,
+            context_id=ctx_id,
+            status=status,
+            history=[message],
+            artifacts=None,
+        )
+        
+        self._tasks[task_id] = task
+        return task
+    
+    def get_task(self, task_id: str) -> Optional[Task]:
+        """
+        Retrieve a task by its ID.
+        
+        Args:
+            task_id: The task ID to look up
+            
+        Returns:
+            Task if found, None otherwise
+        """
+        return self._tasks.get(task_id)
+    
+    def update_status(
+        self, 
+        task_id: str, 
+        state: TaskState,
+        message: Optional[Message] = None,
+    ) -> Optional[Task]:
+        """
+        Update the status of a task.
+        
+        Args:
+            task_id: The task ID to update
+            state: New task state
+            message: Optional status message
+            
+        Returns:
+            Updated Task if found, None otherwise
+        """
+        task = self._tasks.get(task_id)
+        if not task:
+            return None
+        
+        # Create new status
+        new_status = TaskStatus(
+            state=state,
+            message=message,
+            timestamp=datetime.now(timezone.utc).isoformat(),
+        )
+        
+        # Update task (create new instance for immutability)
+        updated = Task(
+            id=task.id,
+            context_id=task.context_id,
+            status=new_status,
+            artifacts=task.artifacts,
+            history=task.history,
+            metadata=task.metadata,
+        )
+        
+        self._tasks[task_id] = updated
+        return updated
+    
+    def add_artifact(self, task_id: str, artifact: Artifact) -> Optional[Task]:
+        """
+        Add an artifact to a task.
+        
+        Args:
+            task_id: The task ID to update
+            artifact: Artifact to add
+            
+        Returns:
+            Updated Task if found, None otherwise
+        """
+        task = self._tasks.get(task_id)
+        if not task:
+            return None
+        
+        # Get existing artifacts or create new list
+        artifacts = list(task.artifacts) if task.artifacts else []
+        artifacts.append(artifact)
+        
+        # Update task
+        updated = Task(
+            id=task.id,
+            context_id=task.context_id,
+            status=task.status,
+            artifacts=artifacts,
+            history=task.history,
+            metadata=task.metadata,
+        )
+        
+        self._tasks[task_id] = updated
+        return updated
+    
+    def add_to_history(self, task_id: str, message: Message) -> Optional[Task]:
+        """
+        Add a message to task history.
+        
+        Args:
+            task_id: The task ID to update
+            message: Message to add to history
+            
+        Returns:
+            Updated Task if found, None otherwise
+        """
+        task = self._tasks.get(task_id)
+        if not task:
+            return None
+        
+        # Get existing history or create new list
+        history = list(task.history) if task.history else []
+        history.append(message)
+        
+        # Update task
+        updated = Task(
+            id=task.id,
+            context_id=task.context_id,
+            status=task.status,
+            artifacts=task.artifacts,
+            history=history,
+            metadata=task.metadata,
+        )
+        
+        self._tasks[task_id] = updated
+        return updated
+    
+    def list_tasks(self, context_id: Optional[str] = None) -> List[Task]:
+        """
+        List all tasks, optionally filtered by context.
+        
+        Args:
+            context_id: Optional context ID to filter by
+            
+        Returns:
+            List of tasks
+        """
+        if context_id:
+            return [t for t in self._tasks.values() if t.context_id == context_id]
+        return list(self._tasks.values())
+    
+    def cancel_task(self, task_id: str) -> Optional[Task]:
+        """
+        Cancel a task.
+        
+        Args:
+            task_id: The task ID to cancel
+            
+        Returns:
+            Updated Task if found, None otherwise
+        """
+        return self.update_status(task_id, TaskState.CANCELLED)
+    
+    def clear(self):
+        """Clear all tasks from the store."""
+        self._tasks.clear()
@@ -0,0 +1,266 @@
+"""
+A2A Protocol Types
+
+Pydantic models for the Agent2Agent (A2A) protocol.
+Based on the A2A Protocol Specification v1.0.
+"""
+
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+from pydantic import BaseModel, ConfigDict, Field
+
+
+# =============================================================================
+# Enums
+# =============================================================================
+
+class TaskState(str, Enum):
+    """
+    Defines the possible lifecycle states of a Task.
+    
+    Based on A2A Protocol Specification Section 4.1.3.
+    """
+    SUBMITTED = "submitted"
+    WORKING = "working"
+    COMPLETED = "completed"
+    FAILED = "failed"
+    CANCELLED = "cancelled"
+    INPUT_REQUIRED = "input_required"
+    AUTH_REQUIRED = "auth_required"
+
+
+class Role(str, Enum):
+    """
+    Defines the sender of a message in A2A protocol communication.
+    
+    Based on A2A Protocol Specification Section 4.1.5.
+    """
+    USER = "user"
+    AGENT = "agent"
+
+
+# =============================================================================
+# Part Types
+# =============================================================================
+
+class TextPart(BaseModel):
+    """
+    A text content part.
+    
+    Based on A2A Protocol Specification Section 4.1.6.
+    """
+    text: str
+    metadata: Optional[Dict[str, Any]] = None
+
+
+class FilePart(BaseModel):
+    """
+    A file content part.
+    
+    Can contain either a URI reference or inline bytes.
+    Based on A2A Protocol Specification Section 4.1.7.
+    """
+    file_uri: Optional[str] = Field(default=None, alias="fileWithUri")
+    file_bytes: Optional[bytes] = Field(default=None, alias="fileWithBytes")
+    media_type: Optional[str] = Field(default=None, alias="mediaType")
+    name: Optional[str] = None
+    metadata: Optional[Dict[str, Any]] = None
+    
+    model_config = ConfigDict(populate_by_name=True)
+
+
+class DataPart(BaseModel):
+    """
+    A structured data part (JSON blob).
+    
+    Based on A2A Protocol Specification Section 4.1.8.
+    """
+    data: Dict[str, Any]
+    metadata: Optional[Dict[str, Any]] = None
+
+
+# Union type for all Part types
+Part = Union[TextPart, FilePart, DataPart]
+
+
+# =============================================================================
+# Core Types
+# =============================================================================
+
+class Message(BaseModel):
+    """
+    A communication turn between client and server.
+    
+    Based on A2A Protocol Specification Section 4.1.4.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    message_id: str = Field(alias="messageId")
+    role: Role
+    parts: List[Part]
+    context_id: Optional[str] = Field(default=None, alias="contextId")
+    task_id: Optional[str] = Field(default=None, alias="taskId")
+    metadata: Optional[Dict[str, Any]] = None
+    extensions: Optional[Dict[str, str]] = None
+    reference_task_ids: Optional[List[str]] = Field(default=None, alias="referenceTaskIds")
+
+
+class TaskStatus(BaseModel):
+    """
+    Container for the status of a task.
+    
+    Based on A2A Protocol Specification Section 4.1.2.
+    """
+    state: TaskState
+    message: Optional[Message] = None
+    timestamp: Optional[str] = None
+
+
+class Artifact(BaseModel):
+    """
+    An output generated by the agent as a result of a task.
+    
+    Based on A2A Protocol Specification Section 4.1.9.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    artifact_id: str = Field(alias="artifactId")
+    name: Optional[str] = None
+    description: Optional[str] = None
+    parts: List[Part]
+    metadata: Optional[Dict[str, Any]] = None
+    extensions: Optional[Dict[str, str]] = None
+
+
+class Task(BaseModel):
+    """
+    The core unit of action for A2A.
+    
+    Based on A2A Protocol Specification Section 4.1.1.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    id: str
+    context_id: Optional[str] = Field(default=None, alias="contextId")
+    status: TaskStatus
+    artifacts: Optional[List[Artifact]] = None
+    history: Optional[List[Message]] = None
+    metadata: Optional[Dict[str, Any]] = None
+
+
+# =============================================================================
+# Agent Card Types
+# =============================================================================
+
+class AgentSkill(BaseModel):
+    """
+    Describes a skill/capability of an agent.
+    
+    Based on A2A Protocol Specification Section 4.4.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    id: str
+    name: str
+    description: str
+    tags: Optional[List[str]] = None
+    examples: Optional[List[str]] = None
+    input_modes: Optional[List[str]] = Field(default=None, alias="inputModes")
+    output_modes: Optional[List[str]] = Field(default=None, alias="outputModes")
+
+
+class AgentCapabilities(BaseModel):
+    """
+    Describes the capabilities of an agent.
+    
+    Based on A2A Protocol Specification Section 4.4.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    streaming: bool = False
+    push_notifications: bool = Field(default=False, alias="pushNotifications")
+    state_transition_history: bool = Field(default=False, alias="stateTransitionHistory")
+
+
+class AgentCard(BaseModel):
+    """
+    JSON metadata document describing an agent.
+    
+    Published by an A2A Server for discovery.
+    Based on A2A Protocol Specification Section 8.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    name: str
+    url: str
+    version: str
+    description: Optional[str] = None
+    capabilities: AgentCapabilities
+    skills: Optional[List[AgentSkill]] = None
+    default_input_modes: Optional[List[str]] = Field(default=None, alias="defaultInputModes")
+    default_output_modes: Optional[List[str]] = Field(default=None, alias="defaultOutputModes")
+    provider: Optional[Dict[str, str]] = None
+    documentation_url: Optional[str] = Field(default=None, alias="documentationUrl")
+
+
+# =============================================================================
+# Request/Response Types
+# =============================================================================
+
+class MessageConfig(BaseModel):
+    """
+    Configuration for message sending.
+    
+    Based on A2A Protocol Specification Section 3.2.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    accept_content_types: Optional[List[str]] = Field(default=None, alias="acceptContentTypes")
+    blocking: Optional[bool] = None
+    history_length: Optional[int] = Field(default=None, alias="historyLength")
+
+
+class SendMessageRequest(BaseModel):
+    """
+    Request to send a message to an agent.
+    
+    Based on A2A Protocol Specification Section 3.1.1.
+    """
+    message: Message
+    configuration: Optional[MessageConfig] = None
+    metadata: Optional[Dict[str, Any]] = None
+
+
+# =============================================================================
+# Streaming Event Types
+# =============================================================================
+
+class TaskStatusUpdateEvent(BaseModel):
+    """
+    Event sent by agent to notify client of task status change.
+    
+    Based on A2A Protocol Specification Section 4.2.1.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    task_id: str = Field(alias="taskId")
+    context_id: Optional[str] = Field(default=None, alias="contextId")
+    status: TaskStatus
+    final: bool = False
+    metadata: Optional[Dict[str, Any]] = None
+
+
+class TaskArtifactUpdateEvent(BaseModel):
+    """
+    Event sent when an artifact is generated.
+    
+    Based on A2A Protocol Specification Section 4.2.2.
+    """
+    model_config = ConfigDict(populate_by_name=True)
+    
+    task_id: str = Field(alias="taskId")
+    context_id: Optional[str] = Field(default=None, alias="contextId")
+    artifact: Artifact
+    append: bool = False
+    last_chunk: bool = Field(default=False, alias="lastChunk")
+    metadata: Optional[Dict[str, Any]] = None
@@ -0,0 +1,126 @@
+"""
+A2UI (Agent-to-User Interface) Protocol Integration for PraisonAI Agents
+
+This module provides A2UI protocol support, enabling PraisonAI Agents
+to generate rich, interactive UIs declaratively via JSON.
+
+A2UI is Google's open standard that allows agents to "speak UI" by sending
+declarative JSON describing UI components, which clients then render natively.
+
+Usage:
+    from praisonaiagents.ui.a2ui import (
+        # Message types
+        CreateSurfaceMessage,
+        UpdateComponentsMessage,
+        UpdateDataModelMessage,
+        DeleteSurfaceMessage,
+        # Component types
+        TextComponent,
+        ImageComponent,
+        ButtonComponent,
+        CardComponent,
+        RowComponent,
+        ColumnComponent,
+        # Extension helpers
+        create_a2ui_part,
+        is_a2ui_part,
+    )
+"""
+
+from praisonaiagents.ui.a2ui.types import (
+    # Data binding
+    PathBinding,
+    resolve_string_or_path,
+    # Action types
+    ActionContext,
+    Action,
+    # Children types
+    ChildrenTemplate,
+    # Component types
+    TextComponent,
+    ImageComponent,
+    IconComponent,
+    ButtonComponent,
+    CardComponent,
+    RowComponent,
+    ColumnComponent,
+    ListComponent,
+    TextFieldComponent,
+    CheckBoxComponent,
+    SliderComponent,
+    DateTimeInputComponent,
+    # Message types
+    CreateSurfaceMessage,
+    UpdateComponentsMessage,
+    UpdateDataModelMessage,
+    DeleteSurfaceMessage,
+    # Data part
+    A2UIDataPart,
+)
+
+from praisonaiagents.ui.a2ui.extension import (
+    A2UI_MIME_TYPE,
+    A2UI_EXTENSION_URI,
+    STANDARD_CATALOG_ID,
+    create_a2ui_part,
+    is_a2ui_part,
+    get_a2ui_agent_extension,
+    AgentExtension,
+)
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.agent import A2UIAgent
+from praisonaiagents.ui.a2ui.templates import (
+    ChatTemplate,
+    ListTemplate,
+    FormTemplate,
+    DashboardTemplate,
+)
+
+__all__ = [
+    # Data binding
+    "PathBinding",
+    "resolve_string_or_path",
+    # Action types
+    "ActionContext",
+    "Action",
+    # Children types
+    "ChildrenTemplate",
+    # Component types
+    "TextComponent",
+    "ImageComponent",
+    "IconComponent",
+    "ButtonComponent",
+    "CardComponent",
+    "RowComponent",
+    "ColumnComponent",
+    "ListComponent",
+    "TextFieldComponent",
+    "CheckBoxComponent",
+    "SliderComponent",
+    "DateTimeInputComponent",
+    # Message types
+    "CreateSurfaceMessage",
+    "UpdateComponentsMessage",
+    "UpdateDataModelMessage",
+    "DeleteSurfaceMessage",
+    # Data part
+    "A2UIDataPart",
+    # Extension
+    "A2UI_MIME_TYPE",
+    "A2UI_EXTENSION_URI",
+    "STANDARD_CATALOG_ID",
+    "create_a2ui_part",
+    "is_a2ui_part",
+    "get_a2ui_agent_extension",
+    "AgentExtension",
+    # Surface builder
+    "Surface",
+    # Agent wrapper
+    "A2UIAgent",
+    # Templates
+    "ChatTemplate",
+    "ListTemplate",
+    "FormTemplate",
+    "DashboardTemplate",
+]
@@ -0,0 +1,358 @@
+"""
+A2UI Agent Integration
+
+Provides A2UIAgent wrapper for generating A2UI responses from PraisonAI agents.
+"""
+
+import uuid
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.types import (
+    PathBinding,
+    A2UIDataPart,
+)
+from praisonaiagents.ui.a2ui.extension import (
+    create_a2ui_part,
+    STANDARD_CATALOG_ID,
+)
+
+if TYPE_CHECKING:
+    from praisonaiagents import Agent
+
+
+class A2UIAgent:
+    """
+    A2UI wrapper for PraisonAI agents.
+    
+    Provides methods to generate A2UI responses from agent interactions.
+    
+    Example:
+        >>> from praisonaiagents import Agent
+        >>> from praisonaiagents.ui.a2ui import A2UIAgent
+        >>> 
+        >>> agent = Agent(name="Assistant", role="Helper", goal="Help users")
+        >>> a2ui_agent = A2UIAgent(agent=agent)
+        >>> 
+        >>> # Render a simple text response
+        >>> messages = a2ui_agent.render_text("Hello, World!")
+        >>> 
+        >>> # Render a list of items
+        >>> messages = a2ui_agent.render_list(
+        ...     title="Results",
+        ...     items=[{"name": "Item 1"}, {"name": "Item 2"}]
+        ... )
+    """
+    
+    def __init__(
+        self,
+        agent: "Agent",
+        surface_id: Optional[str] = None,
+        catalog_id: str = STANDARD_CATALOG_ID,
+    ):
+        """
+        Initialize A2UIAgent wrapper.
+        
+        Args:
+            agent: The PraisonAI Agent to wrap
+            surface_id: Unique ID for the UI surface (auto-generated if not provided)
+            catalog_id: The component catalog to use
+        """
+        self.agent = agent
+        self.surface_id = surface_id or f"surface-{uuid.uuid4().hex[:8]}"
+        self.catalog_id = catalog_id
+        self._surface: Optional[Surface] = None
+    
+    def get_surface(self) -> Surface:
+        """
+        Get the underlying Surface object.
+        
+        Creates a new Surface if one doesn't exist.
+        
+        Returns:
+            The Surface object
+        """
+        if self._surface is None:
+            self._surface = Surface(
+                surface_id=self.surface_id,
+                catalog_id=self.catalog_id,
+            )
+        return self._surface
+    
+    def _reset_surface(self) -> Surface:
+        """Reset and return a new Surface."""
+        self._surface = Surface(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        return self._surface
+    
+    # =========================================================================
+    # Rendering methods
+    # =========================================================================
+    
+    def render_text(
+        self,
+        text: str,
+        title: Optional[str] = None,
+        usage_hint: str = "body",
+    ) -> List[Dict[str, Any]]:
+        """
+        Render a simple text response as A2UI.
+        
+        Args:
+            text: The text content to display
+            title: Optional title heading
+            usage_hint: Text style hint (h1, h2, body, caption)
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = self._reset_surface()
+        
+        children = []
+        
+        if title:
+            surface.text(id="title", text=title, usage_hint="h1")
+            children.append("title")
+        
+        surface.text(id="content", text=text, usage_hint=usage_hint)
+        children.append("content")
+        
+        # Add root column
+        surface.column(id="root", children=children)
+        
+        return surface.to_messages()
+    
+    def render_list(
+        self,
+        title: str,
+        items: List[Dict[str, Any]],
+        item_title_key: str = "title",
+        item_description_key: str = "description",
+        item_image_key: Optional[str] = None,
+        item_action: Optional[str] = None,
+    ) -> List[Dict[str, Any]]:
+        """
+        Render a list of items as A2UI cards.
+        
+        Args:
+            title: List title
+            items: List of item dictionaries
+            item_title_key: Key for item title in each dict
+            item_description_key: Key for item description
+            item_image_key: Optional key for item image URL
+            item_action: Optional action name for item buttons
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = self._reset_surface()
+        
+        # Title
+        surface.text(id="list-title", text=title, usage_hint="h1")
+        
+        # Create card for each item
+        card_ids = []
+        for i, item in enumerate(items):
+            card_id = f"card-{i}"
+            content_id = f"card-content-{i}"
+            title_id = f"item-title-{i}"
+            desc_id = f"item-desc-{i}"
+            
+            # Item title
+            surface.text(
+                id=title_id,
+                text=item.get(item_title_key, f"Item {i+1}"),
+                usage_hint="h3"
+            )
+            
+            # Item description
+            surface.text(
+                id=desc_id,
+                text=item.get(item_description_key, ""),
+                usage_hint="body"
+            )
+            
+            content_children = [title_id, desc_id]
+            
+            # Optional action button
+            if item_action:
+                btn_id = f"btn-{i}"
+                btn_text_id = f"btn-text-{i}"
+                surface.text(id=btn_text_id, text="Select")
+                surface.button(
+                    id=btn_id,
+                    child=btn_text_id,
+                    action_name=item_action,
+                    action_context=[{"key": "index", "value": i}],
+                    primary=True
+                )
+                content_children.append(btn_id)
+            
+            # Card content column
+            surface.column(id=content_id, children=content_children)
+            
+            # Card
+            surface.card(id=card_id, child=content_id)
+            card_ids.append(card_id)
+        
+        # List column
+        surface.column(id="item-list", children=card_ids)
+        
+        # Root column
+        surface.column(id="root", children=["list-title", "item-list"])
+        
+        # Set data
+        surface.set_data("items", items)
+        
+        return surface.to_messages()
+    
+    def render_form(
+        self,
+        title: str,
+        fields: List[Dict[str, str]],
+        submit_action: str = "submit",
+        submit_label: str = "Submit",
+    ) -> List[Dict[str, Any]]:
+        """
+        Render a form as A2UI.
+        
+        Args:
+            title: Form title
+            fields: List of field definitions with id, label, type
+            submit_action: Action name for submit button
+            submit_label: Label for submit button
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = self._reset_surface()
+        
+        # Title
+        surface.text(id="form-title", text=title, usage_hint="h1")
+        
+        # Fields
+        field_ids = []
+        form_data = {}
+        
+        for field in fields:
+            field_id = field.get("id", f"field-{len(field_ids)}")
+            label = field.get("label", field_id)
+            field_type = field.get("type", "text")
+            
+            surface.text_field(
+                id=field_id,
+                label=label,
+                text=PathBinding(path=f"/{field_id}"),
+                field_type=field_type,
+            )
+            field_ids.append(field_id)
+            form_data[field_id] = field.get("default", "")
+        
+        # Submit button
+        surface.text(id="submit-text", text=submit_label)
+        
+        # Build action context from fields
+        action_context = [
+            {"key": f["id"], "value": {"path": f"/{f['id']}"}}
+            for f in fields
+        ]
+        
+        surface.button(
+            id="submit-btn",
+            child="submit-text",
+            action_name=submit_action,
+            action_context=action_context,
+            primary=True,
+        )
+        field_ids.append("submit-btn")
+        
+        # Form column
+        surface.column(id="form-fields", children=field_ids)
+        
+        # Root column
+        surface.column(id="root", children=["form-title", "form-fields"])
+        
+        # Set initial form data
+        for key, value in form_data.items():
+            surface.set_data(key, value)
+        
+        return surface.to_messages()
+    
+    # =========================================================================
+    # Agent interaction methods
+    # =========================================================================
+    
+    async def chat_async(self, message: str) -> str:
+        """
+        Send a message to the agent and get a response.
+        
+        Args:
+            message: The message to send
+        
+        Returns:
+            The agent's response text
+        """
+        # Use the agent's chat method
+        if hasattr(self.agent, 'chat'):
+            response = self.agent.chat(message)
+            return response
+        elif hasattr(self.agent, 'run'):
+            response = self.agent.run(message)
+            return response
+        else:
+            raise NotImplementedError("Agent does not have chat or run method")
+    
+    def chat(self, message: str) -> str:
+        """
+        Send a message to the agent and get a response (sync).
+        
+        Args:
+            message: The message to send
+        
+        Returns:
+            The agent's response text
+        """
+        if hasattr(self.agent, 'chat'):
+            return self.agent.chat(message)
+        elif hasattr(self.agent, 'run'):
+            return self.agent.run(message)
+        else:
+            raise NotImplementedError("Agent does not have chat or run method")
+    
+    # =========================================================================
+    # Export methods
+    # =========================================================================
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Get the current surface as A2UI messages.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        return self.get_surface().to_messages()
+    
+    def to_json(self, indent: Optional[int] = None) -> str:
+        """
+        Get the current surface as JSON string.
+        
+        Args:
+            indent: JSON indentation level
+        
+        Returns:
+            JSON string of A2UI messages
+        """
+        return self.get_surface().to_json(indent=indent)
+    
+    def to_a2a_part(self) -> A2UIDataPart:
+        """
+        Get the current surface as an A2A DataPart.
+        
+        Returns:
+            A2UIDataPart with A2UI MIME type
+        """
+        messages = self.to_messages()
+        # For A2A, we send messages as a list
+        return create_a2ui_part({"messages": messages})
@@ -0,0 +1,115 @@
+"""
+A2UI Extension for A2A Protocol
+
+Provides helpers for integrating A2UI with the A2A (Agent-to-Agent) protocol.
+"""
+
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+from praisonaiagents.ui.a2ui.types import A2UIDataPart
+
+
+# =============================================================================
+# Constants
+# =============================================================================
+
+A2UI_EXTENSION_URI = "https://a2ui.org/a2a-extension/a2ui/v0.9"
+A2UI_MIME_TYPE = "application/json+a2ui"
+STANDARD_CATALOG_ID = "https://raw.githubusercontent.com/google/A2UI/refs/heads/main/specification/0.9/json/standard_catalog_definition.json"
+
+
+# =============================================================================
+# Agent Extension Type
+# =============================================================================
+
+@dataclass
+class AgentExtension:
+    """
+    A2A Agent Extension configuration.
+    
+    Describes an extension that an agent supports.
+    """
+    uri: str
+    description: str = ""
+    params: Optional[Dict[str, Any]] = None
+
+
+# =============================================================================
+# Helper Functions
+# =============================================================================
+
+def create_a2ui_part(a2ui_data: Dict[str, Any]) -> A2UIDataPart:
+    """
+    Create an A2UI data part for A2A integration.
+    
+    Wraps A2UI data in an A2UIDataPart with the appropriate MIME type.
+    
+    Args:
+        a2ui_data: The A2UI data dictionary (e.g., createSurface, updateComponents)
+    
+    Returns:
+        An A2UIDataPart with the A2UI MIME type in metadata
+    
+    Example:
+        >>> part = create_a2ui_part({"createSurface": {"surfaceId": "main", "catalogId": "..."}})
+        >>> part.metadata["mimeType"]
+        'application/json+a2ui'
+    """
+    return A2UIDataPart(
+        data=a2ui_data,
+        metadata={"mimeType": A2UI_MIME_TYPE}
+    )
+
+
+def is_a2ui_part(part: A2UIDataPart) -> bool:
+    """
+    Check if a data part contains A2UI data.
+    
+    Args:
+        part: The data part to check
+    
+    Returns:
+        True if the part contains A2UI data (has A2UI MIME type), False otherwise
+    
+    Example:
+        >>> part = create_a2ui_part({"createSurface": {...}})
+        >>> is_a2ui_part(part)
+        True
+    """
+    if not isinstance(part, A2UIDataPart):
+        return False
+    if part.metadata is None:
+        return False
+    return part.metadata.get("mimeType") == A2UI_MIME_TYPE
+
+
+def get_a2ui_agent_extension(
+    accepts_inline_custom_catalog: bool = False,
+) -> AgentExtension:
+    """
+    Create the A2UI AgentExtension configuration.
+    
+    Returns an AgentExtension that can be added to an A2A Agent Card
+    to indicate A2UI support.
+    
+    Args:
+        accepts_inline_custom_catalog: Whether the agent accepts inline custom catalogs
+    
+    Returns:
+        The configured A2UI AgentExtension
+    
+    Example:
+        >>> ext = get_a2ui_agent_extension()
+        >>> ext.uri
+        'https://a2ui.org/a2a-extension/a2ui/v0.9'
+    """
+    params: Optional[Dict[str, Any]] = None
+    if accepts_inline_custom_catalog:
+        params = {"acceptsInlineCustomCatalog": True}
+    
+    return AgentExtension(
+        uri=A2UI_EXTENSION_URI,
+        description="Provides agent-driven UI using the A2UI JSON format.",
+        params=params
+    )
@@ -0,0 +1,364 @@
+"""
+A2UI Surface Builder
+
+Provides a fluent API for building A2UI surfaces with components and data.
+"""
+
+import json
+from typing import Any, Dict, List, Optional
+
+from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+from praisonaiagents.ui.a2ui.types import (
+    Component,
+    TextComponent,
+    ImageComponent,
+    ButtonComponent,
+    CardComponent,
+    RowComponent,
+    ColumnComponent,
+    ListComponent,
+    TextFieldComponent,
+    Action,
+    ActionContext,
+    PathBinding,
+    CreateSurfaceMessage,
+    UpdateComponentsMessage,
+    UpdateDataModelMessage,
+    StringOrPath,
+    ChildrenType,
+)
+
+
+class Surface:
+    """
+    A2UI Surface builder for creating rich agent-generated UIs.
+    
+    Provides a fluent API for adding components and data, then
+    generating the A2UI JSON messages.
+    
+    Example:
+        >>> surface = Surface(surface_id="main")
+        >>> surface.text(id="title", text="Hello World", usage_hint="h1")
+        >>> surface.button(id="submit", child="submit-text", action_name="submit")
+        >>> surface.set_data("title", "Hello World")
+        >>> messages = surface.to_messages()
+    """
+    
+    def __init__(
+        self,
+        surface_id: str,
+        catalog_id: str = STANDARD_CATALOG_ID,
+    ):
+        """
+        Initialize a new Surface.
+        
+        Args:
+            surface_id: Unique identifier for this surface
+            catalog_id: The component catalog to use (defaults to standard catalog)
+        """
+        self.surface_id = surface_id
+        self.catalog_id = catalog_id
+        self.components: List[Component] = []
+        self.data: Dict[str, Any] = {}
+    
+    def add(self, component: Component) -> "Surface":
+        """
+        Add a component to the surface.
+        
+        Args:
+            component: The component to add
+        
+        Returns:
+            self for method chaining
+        """
+        self.components.append(component)
+        return self
+    
+    def set_data(self, key: str, value: Any) -> "Surface":
+        """
+        Set a value in the data model.
+        
+        Args:
+            key: The key in the data model
+            value: The value to set
+        
+        Returns:
+            self for method chaining
+        """
+        self.data[key] = value
+        return self
+    
+    # =========================================================================
+    # Helper methods for common components
+    # =========================================================================
+    
+    def text(
+        self,
+        id: str,
+        text: StringOrPath,
+        usage_hint: Optional[str] = None,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a Text component.
+        
+        Args:
+            id: Component ID
+            text: Text content or path binding
+            usage_hint: Style hint (h1, h2, h3, body, caption)
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(TextComponent(
+            id=id,
+            text=text,
+            usage_hint=usage_hint,
+            weight=weight,
+        ))
+    
+    def image(
+        self,
+        id: str,
+        url: StringOrPath,
+        fit: Optional[str] = None,
+        usage_hint: Optional[str] = None,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add an Image component.
+        
+        Args:
+            id: Component ID
+            url: Image URL or path binding
+            fit: Image fit (contain, cover, fill, none, scale-down)
+            usage_hint: Size hint (icon, avatar, smallFeature, etc.)
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(ImageComponent(
+            id=id,
+            url=url,
+            fit=fit,
+            usage_hint=usage_hint,
+            weight=weight,
+        ))
+    
+    def button(
+        self,
+        id: str,
+        child: str,
+        action_name: Optional[str] = None,
+        action_context: Optional[List[Dict[str, Any]]] = None,
+        primary: bool = False,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a Button component.
+        
+        Args:
+            id: Component ID
+            child: Child component ID (usually a Text component)
+            action_name: Name of the action to trigger
+            action_context: List of {key, value} dicts for action context
+            primary: Whether this is a primary button
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        action = None
+        if action_name:
+            context = []
+            if action_context:
+                for ctx in action_context:
+                    value = ctx.get("value")
+                    if isinstance(value, dict) and "path" in value:
+                        value = PathBinding(path=value["path"])
+                    context.append(ActionContext(key=ctx["key"], value=value))
+            action = Action(name=action_name, context=context)
+        
+        return self.add(ButtonComponent(
+            id=id,
+            child=child,
+            action=action,
+            primary=primary,
+            weight=weight,
+        ))
+    
+    def card(
+        self,
+        id: str,
+        child: str,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a Card component.
+        
+        Args:
+            id: Component ID
+            child: Child component ID
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(CardComponent(
+            id=id,
+            child=child,
+            weight=weight,
+        ))
+    
+    def row(
+        self,
+        id: str,
+        children: ChildrenType,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a Row (horizontal layout) component.
+        
+        Args:
+            id: Component ID
+            children: List of child IDs or ChildrenTemplate
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(RowComponent(
+            id=id,
+            children=children,
+            weight=weight,
+        ))
+    
+    def column(
+        self,
+        id: str,
+        children: ChildrenType,
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a Column (vertical layout) component.
+        
+        Args:
+            id: Component ID
+            children: List of child IDs or ChildrenTemplate
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(ColumnComponent(
+            id=id,
+            children=children,
+            weight=weight,
+        ))
+    
+    def list(
+        self,
+        id: str,
+        children: ChildrenType,
+        direction: str = "vertical",
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a List component.
+        
+        Args:
+            id: Component ID
+            children: List of child IDs or ChildrenTemplate for dynamic lists
+            direction: "vertical" or "horizontal"
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(ListComponent(
+            id=id,
+            children=children,
+            direction=direction,
+            weight=weight,
+        ))
+    
+    def text_field(
+        self,
+        id: str,
+        label: StringOrPath,
+        text: StringOrPath,
+        field_type: str = "text",
+        weight: Optional[float] = None,
+    ) -> "Surface":
+        """
+        Add a TextField input component.
+        
+        Args:
+            id: Component ID
+            label: Field label
+            text: Text value or path binding
+            field_type: Input type (text, number, email, etc.)
+            weight: Flex weight
+        
+        Returns:
+            self for method chaining
+        """
+        return self.add(TextFieldComponent(
+            id=id,
+            label=label,
+            text=text,
+            field_type=field_type,
+            weight=weight,
+        ))
+    
+    # =========================================================================
+    # Message generation
+    # =========================================================================
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Generate A2UI messages for this surface.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        messages: List[Dict[str, Any]] = []
+        
+        # 1. CreateSurface message
+        create_msg = CreateSurfaceMessage(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        messages.append(create_msg.to_dict())
+        
+        # 2. UpdateComponents message (if we have components)
+        if self.components:
+            update_msg = UpdateComponentsMessage(
+                surface_id=self.surface_id,
+                components=self.components,
+            )
+            messages.append(update_msg.to_dict())
+        
+        # 3. UpdateDataModel message (if we have data)
+        if self.data:
+            data_msg = UpdateDataModelMessage(
+                surface_id=self.surface_id,
+                value=self.data,
+            )
+            messages.append(data_msg.to_dict())
+        
+        return messages
+    
+    def to_json(self, indent: Optional[int] = None) -> str:
+        """
+        Generate A2UI messages as a JSON string.
+        
+        Args:
+            indent: JSON indentation level (None for compact)
+        
+        Returns:
+            JSON string of A2UI messages
+        """
+        return json.dumps(self.to_messages(), indent=indent)
@@ -0,0 +1,17 @@
+"""
+A2UI Templates
+
+Pre-built UI templates for common use cases.
+"""
+
+from praisonaiagents.ui.a2ui.templates.chat import ChatTemplate
+from praisonaiagents.ui.a2ui.templates.list import ListTemplate
+from praisonaiagents.ui.a2ui.templates.form import FormTemplate
+from praisonaiagents.ui.a2ui.templates.dashboard import DashboardTemplate
+
+__all__ = [
+    "ChatTemplate",
+    "ListTemplate",
+    "FormTemplate",
+    "DashboardTemplate",
+]
@@ -0,0 +1,122 @@
+"""
+Chat Template for A2UI
+
+Provides a conversational chat UI template.
+"""
+
+from typing import Any, Dict, List, Optional
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+
+
+class ChatTemplate:
+    """
+    Chat UI template for conversational interfaces.
+    
+    Creates a chat-style UI with user and agent messages.
+    
+    Example:
+        >>> template = ChatTemplate(surface_id="chat")
+        >>> template.add_user_message("Hello!")
+        >>> template.add_agent_message("Hi there! How can I help?")
+        >>> messages = template.to_messages()
+    """
+    
+    def __init__(
+        self,
+        surface_id: str = "chat",
+        catalog_id: str = STANDARD_CATALOG_ID,
+        title: Optional[str] = None,
+    ):
+        """
+        Initialize ChatTemplate.
+        
+        Args:
+            surface_id: Unique ID for the surface
+            catalog_id: Component catalog to use
+            title: Optional title for the chat
+        """
+        self.surface_id = surface_id
+        self.catalog_id = catalog_id
+        self.title = title
+        self.messages: List[Dict[str, Any]] = []
+    
+    def add_user_message(self, content: str) -> "ChatTemplate":
+        """
+        Add a user message.
+        
+        Args:
+            content: Message content
+        
+        Returns:
+            self for chaining
+        """
+        self.messages.append({
+            "role": "user",
+            "content": content,
+        })
+        return self
+    
+    def add_agent_message(self, content: str) -> "ChatTemplate":
+        """
+        Add an agent message.
+        
+        Args:
+            content: Message content
+        
+        Returns:
+            self for chaining
+        """
+        self.messages.append({
+            "role": "agent",
+            "content": content,
+        })
+        return self
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Generate A2UI messages for the chat.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = Surface(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        
+        children = []
+        
+        # Title if provided
+        if self.title:
+            surface.text(id="chat-title", text=self.title, usage_hint="h1")
+            children.append("chat-title")
+        
+        # Message components
+        msg_ids = []
+        for i, msg in enumerate(self.messages):
+            msg_id = f"msg-{i}"
+            role = msg["role"]
+            content = msg["content"]
+            
+            # Style based on role
+            if role == "user":
+                surface.text(id=msg_id, text=f"You: {content}", usage_hint="body")
+            else:
+                surface.text(id=msg_id, text=f"Agent: {content}", usage_hint="body")
+            
+            msg_ids.append(msg_id)
+        
+        # Messages column
+        if msg_ids:
+            surface.column(id="messages", children=msg_ids)
+            children.append("messages")
+        
+        # Root column
+        surface.column(id="root", children=children)
+        
+        # Set data
+        surface.set_data("messages", self.messages)
+        
+        return surface.to_messages()
@@ -0,0 +1,128 @@
+"""
+Dashboard Template for A2UI
+
+Provides a dashboard UI template with multiple panels.
+"""
+
+from typing import Any, Dict, List, Optional
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+
+
+class DashboardTemplate:
+    """
+    Dashboard UI template with multiple panels.
+    
+    Creates a dashboard layout with cards for each panel.
+    
+    Example:
+        >>> template = DashboardTemplate(surface_id="dashboard", title="My Dashboard")
+        >>> template.add_panel(id="stats", title="Statistics", content="100 items")
+        >>> template.add_panel(id="chart", title="Chart", content="[Chart here]")
+        >>> messages = template.to_messages()
+    """
+    
+    def __init__(
+        self,
+        surface_id: str = "dashboard",
+        title: str = "Dashboard",
+        catalog_id: str = STANDARD_CATALOG_ID,
+        columns: int = 2,
+    ):
+        """
+        Initialize DashboardTemplate.
+        
+        Args:
+            surface_id: Unique ID for the surface
+            title: Dashboard title
+            catalog_id: Component catalog to use
+            columns: Number of columns in the grid
+        """
+        self.surface_id = surface_id
+        self.title = title
+        self.catalog_id = catalog_id
+        self.columns = columns
+        self.panels: List[Dict[str, Any]] = []
+    
+    def add_panel(
+        self,
+        id: str,
+        title: str,
+        content: str,
+        weight: Optional[float] = None,
+    ) -> "DashboardTemplate":
+        """
+        Add a panel to the dashboard.
+        
+        Args:
+            id: Panel ID
+            title: Panel title
+            content: Panel content text
+            weight: Optional flex weight
+        
+        Returns:
+            self for chaining
+        """
+        self.panels.append({
+            "id": id,
+            "title": title,
+            "content": content,
+            "weight": weight,
+        })
+        return self
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Generate A2UI messages for the dashboard.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = Surface(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        
+        # Title
+        surface.text(id="dashboard-title", text=self.title, usage_hint="h1")
+        
+        # Create cards for each panel
+        card_ids = []
+        for panel in self.panels:
+            panel_id = panel["id"]
+            content_id = f"{panel_id}-content"
+            title_id = f"{panel_id}-title"
+            text_id = f"{panel_id}-text"
+            
+            # Panel title
+            surface.text(id=title_id, text=panel["title"], usage_hint="h3")
+            
+            # Panel content
+            surface.text(id=text_id, text=panel["content"], usage_hint="body")
+            
+            # Panel content column
+            surface.column(id=content_id, children=[title_id, text_id])
+            
+            # Panel card
+            surface.card(id=panel_id, child=content_id, weight=panel.get("weight"))
+            card_ids.append(panel_id)
+        
+        # Arrange panels in rows based on columns setting
+        row_ids = []
+        for i in range(0, len(card_ids), self.columns):
+            row_cards = card_ids[i:i + self.columns]
+            row_id = f"row-{i // self.columns}"
+            surface.row(id=row_id, children=row_cards)
+            row_ids.append(row_id)
+        
+        # Panels container
+        surface.column(id="panels", children=row_ids)
+        
+        # Root column
+        surface.column(id="root", children=["dashboard-title", "panels"])
+        
+        # Set data
+        surface.set_data("panels", self.panels)
+        
+        return surface.to_messages()
@@ -0,0 +1,205 @@
+"""
+Form Template for A2UI
+
+Provides a form UI template for data collection.
+"""
+
+from typing import Any, Dict, List
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.types import PathBinding
+from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+
+
+class FormTemplate:
+    """
+    Form UI template for data collection.
+    
+    Creates a form with various input fields and a submit button.
+    
+    Example:
+        >>> template = FormTemplate(surface_id="form", title="Contact")
+        >>> template.add_text_field(id="name", label="Name")
+        >>> template.add_email_field(id="email", label="Email")
+        >>> template.set_submit_action("submit_form", "Send")
+        >>> messages = template.to_messages()
+    """
+    
+    def __init__(
+        self,
+        surface_id: str = "form",
+        title: str = "Form",
+        catalog_id: str = STANDARD_CATALOG_ID,
+    ):
+        """
+        Initialize FormTemplate.
+        
+        Args:
+            surface_id: Unique ID for the surface
+            title: Form title
+            catalog_id: Component catalog to use
+        """
+        self.surface_id = surface_id
+        self.title = title
+        self.catalog_id = catalog_id
+        self.fields: List[Dict[str, Any]] = []
+        self.submit_action = "submit"
+        self.submit_label = "Submit"
+    
+    def add_text_field(
+        self,
+        id: str,
+        label: str,
+        default: str = "",
+        required: bool = False,
+    ) -> "FormTemplate":
+        """
+        Add a text input field.
+        
+        Args:
+            id: Field ID
+            label: Field label
+            default: Default value
+            required: Whether field is required
+        
+        Returns:
+            self for chaining
+        """
+        self.fields.append({
+            "id": id,
+            "label": label,
+            "type": "text",
+            "default": default,
+            "required": required,
+        })
+        return self
+    
+    def add_number_field(
+        self,
+        id: str,
+        label: str,
+        default: float = 0,
+        required: bool = False,
+    ) -> "FormTemplate":
+        """
+        Add a number input field.
+        
+        Args:
+            id: Field ID
+            label: Field label
+            default: Default value
+            required: Whether field is required
+        
+        Returns:
+            self for chaining
+        """
+        self.fields.append({
+            "id": id,
+            "label": label,
+            "type": "number",
+            "default": default,
+            "required": required,
+        })
+        return self
+    
+    def add_email_field(
+        self,
+        id: str,
+        label: str,
+        default: str = "",
+        required: bool = False,
+    ) -> "FormTemplate":
+        """
+        Add an email input field.
+        
+        Args:
+            id: Field ID
+            label: Field label
+            default: Default value
+            required: Whether field is required
+        
+        Returns:
+            self for chaining
+        """
+        self.fields.append({
+            "id": id,
+            "label": label,
+            "type": "email",
+            "default": default,
+            "required": required,
+        })
+        return self
+    
+    def set_submit_action(
+        self,
+        action: str,
+        label: str = "Submit",
+    ) -> "FormTemplate":
+        """
+        Set the submit button action.
+        
+        Args:
+            action: Action name
+            label: Button label
+        
+        Returns:
+            self for chaining
+        """
+        self.submit_action = action
+        self.submit_label = label
+        return self
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Generate A2UI messages for the form.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = Surface(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        
+        # Title
+        surface.text(id="form-title", text=self.title, usage_hint="h1")
+        
+        # Fields
+        field_ids = []
+        for field in self.fields:
+            field_id = field["id"]
+            surface.text_field(
+                id=field_id,
+                label=field["label"],
+                text=PathBinding(path=f"/{field_id}"),
+                field_type=field["type"],
+            )
+            field_ids.append(field_id)
+            
+            # Set default value
+            surface.set_data(field_id, field.get("default", ""))
+        
+        # Submit button
+        surface.text(id="submit-text", text=self.submit_label)
+        
+        action_context = [
+            {"key": f["id"], "value": {"path": f"/{f['id']}"}}
+            for f in self.fields
+        ]
+        
+        surface.button(
+            id="submit-btn",
+            child="submit-text",
+            action_name=self.submit_action,
+            action_context=action_context,
+            primary=True,
+        )
+        field_ids.append("submit-btn")
+        
+        # Form fields column
+        surface.column(id="fields", children=field_ids)
+        
+        # Root column
+        surface.column(id="root", children=["form-title", "fields"])
+        
+        return surface.to_messages()
@@ -0,0 +1,147 @@
+"""
+List Template for A2UI
+
+Provides a list UI template for displaying items.
+"""
+
+from typing import Any, Dict, List, Optional
+
+from praisonaiagents.ui.a2ui.surface import Surface
+from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+
+
+class ListTemplate:
+    """
+    List UI template for displaying items.
+    
+    Creates a list of cards with title, description, and optional image.
+    
+    Example:
+        >>> template = ListTemplate(surface_id="list", title="Results")
+        >>> template.add_item(title="Item 1", description="First item")
+        >>> template.add_item(title="Item 2", description="Second item")
+        >>> messages = template.to_messages()
+    """
+    
+    def __init__(
+        self,
+        surface_id: str = "list",
+        title: str = "Items",
+        catalog_id: str = STANDARD_CATALOG_ID,
+    ):
+        """
+        Initialize ListTemplate.
+        
+        Args:
+            surface_id: Unique ID for the surface
+            title: List title
+            catalog_id: Component catalog to use
+        """
+        self.surface_id = surface_id
+        self.title = title
+        self.catalog_id = catalog_id
+        self.items: List[Dict[str, Any]] = []
+    
+    def add_item(
+        self,
+        title: str,
+        description: str = "",
+        image_url: Optional[str] = None,
+        action: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> "ListTemplate":
+        """
+        Add an item to the list.
+        
+        Args:
+            title: Item title
+            description: Item description
+            image_url: Optional image URL
+            action: Optional action name for item button
+            metadata: Optional additional metadata
+        
+        Returns:
+            self for chaining
+        """
+        item = {
+            "title": title,
+            "description": description,
+        }
+        if image_url:
+            item["image_url"] = image_url
+        if action:
+            item["action"] = action
+        if metadata:
+            item.update(metadata)
+        
+        self.items.append(item)
+        return self
+    
+    def to_messages(self) -> List[Dict[str, Any]]:
+        """
+        Generate A2UI messages for the list.
+        
+        Returns:
+            List of A2UI message dictionaries
+        """
+        surface = Surface(
+            surface_id=self.surface_id,
+            catalog_id=self.catalog_id,
+        )
+        
+        # Title
+        surface.text(id="list-title", text=self.title, usage_hint="h1")
+        
+        # Create cards for each item
+        card_ids = []
+        for i, item in enumerate(self.items):
+            card_id = f"card-{i}"
+            content_id = f"content-{i}"
+            title_id = f"title-{i}"
+            desc_id = f"desc-{i}"
+            
+            # Item title
+            surface.text(id=title_id, text=item["title"], usage_hint="h3")
+            
+            # Item description
+            surface.text(id=desc_id, text=item.get("description", ""), usage_hint="body")
+            
+            content_children = [title_id, desc_id]
+            
+            # Optional image
+            if item.get("image_url"):
+                img_id = f"img-{i}"
+                surface.image(id=img_id, url=item["image_url"], usage_hint="smallFeature")
+                content_children.insert(0, img_id)
+            
+            # Optional action button
+            if item.get("action"):
+                btn_id = f"btn-{i}"
+                btn_text_id = f"btn-text-{i}"
+                surface.text(id=btn_text_id, text="Select")
+                surface.button(
+                    id=btn_id,
+                    child=btn_text_id,
+                    action_name=item["action"],
+                    action_context=[{"key": "index", "value": i}],
+                    primary=True,
+                )
+                content_children.append(btn_id)
+            
+            # Card content
+            surface.column(id=content_id, children=content_children)
+            
+            # Card
+            surface.card(id=card_id, child=content_id)
+            card_ids.append(card_id)
+        
+        # Items column
+        surface.column(id="items", children=card_ids)
+        
+        # Root column
+        surface.column(id="root", children=["list-title", "items"])
+        
+        # Set data
+        surface.set_data("items", self.items)
+        
+        return surface.to_messages()
@@ -0,0 +1,523 @@
+"""
+A2UI Protocol Types
+
+Pydantic-style classes for the A2UI (Agent-to-User Interface) protocol.
+Based on the A2UI Specification v0.9.
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Union
+from enum import Enum
+
+
+# =============================================================================
+# Data Binding Types
+# =============================================================================
+
+@dataclass
+class PathBinding:
+    """
+    A reference to a value in the data model.
+    
+    Used for data binding in A2UI components.
+    """
+    path: str
+    
+    def to_dict(self) -> Dict[str, str]:
+        return {"path": self.path}
+
+
+# Type alias for values that can be literal or path-bound
+StringOrPath = Union[str, PathBinding]
+NumberOrPath = Union[int, float, PathBinding]
+BooleanOrPath = Union[bool, PathBinding]
+
+
+def resolve_string_or_path(value: StringOrPath) -> Union[str, Dict[str, str]]:
+    """Resolve a StringOrPath to its serialized form."""
+    if isinstance(value, PathBinding):
+        return value.to_dict()
+    return value
+
+
+def resolve_number_or_path(value: NumberOrPath) -> Union[int, float, Dict[str, str]]:
+    """Resolve a NumberOrPath to its serialized form."""
+    if isinstance(value, PathBinding):
+        return value.to_dict()
+    return value
+
+
+def resolve_boolean_or_path(value: BooleanOrPath) -> Union[bool, Dict[str, str]]:
+    """Resolve a BooleanOrPath to its serialized form."""
+    if isinstance(value, PathBinding):
+        return value.to_dict()
+    return value
+
+
+# =============================================================================
+# Action Types
+# =============================================================================
+
+@dataclass
+class ActionContext:
+    """
+    A key-value pair for action context.
+    
+    Used to pass data from UI to action handlers.
+    """
+    key: str
+    value: Union[str, int, float, bool, PathBinding]
+    
+    def to_dict(self) -> Dict[str, Any]:
+        if isinstance(self.value, PathBinding):
+            return {"key": self.key, "value": self.value.to_dict()}
+        return {"key": self.key, "value": self.value}
+
+
+@dataclass
+class Action:
+    """
+    An action triggered by a UI component (e.g., button click).
+    """
+    name: str
+    context: List[ActionContext] = field(default_factory=list)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "name": self.name,
+            "context": [c.to_dict() for c in self.context]
+        }
+
+
+# =============================================================================
+# Children Types
+# =============================================================================
+
+@dataclass
+class ChildrenTemplate:
+    """
+    A template for generating dynamic children from a data model list.
+    """
+    component_id: str
+    path: str
+    
+    def to_dict(self) -> Dict[str, str]:
+        return {
+            "componentId": self.component_id,
+            "path": self.path
+        }
+
+
+# Type alias for children - either explicit list or template
+ChildrenType = Union[List[str], ChildrenTemplate]
+
+
+def resolve_children(children: ChildrenType) -> Union[List[str], Dict[str, str]]:
+    """Resolve children to serialized form."""
+    if isinstance(children, ChildrenTemplate):
+        return children.to_dict()
+    return children
+
+
+# =============================================================================
+# Component Types
+# =============================================================================
+
+class UsageHint(str, Enum):
+    """Text usage hints for styling."""
+    H1 = "h1"
+    H2 = "h2"
+    H3 = "h3"
+    H4 = "h4"
+    H5 = "h5"
+    CAPTION = "caption"
+    BODY = "body"
+
+
+class ImageFit(str, Enum):
+    """Image fit options."""
+    CONTAIN = "contain"
+    COVER = "cover"
+    FILL = "fill"
+    NONE = "none"
+    SCALE_DOWN = "scale-down"
+
+
+class ImageUsageHint(str, Enum):
+    """Image usage hints."""
+    ICON = "icon"
+    AVATAR = "avatar"
+    SMALL_FEATURE = "smallFeature"
+    MEDIUM_FEATURE = "mediumFeature"
+    LARGE_FEATURE = "largeFeature"
+    HEADER = "header"
+
+
+@dataclass
+class TextComponent:
+    """Text display component."""
+    id: str
+    text: StringOrPath
+    usage_hint: Optional[str] = None
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Text",
+            "text": resolve_string_or_path(self.text)
+        }
+        if self.usage_hint:
+            result["usageHint"] = self.usage_hint
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class ImageComponent:
+    """Image display component."""
+    id: str
+    url: StringOrPath
+    fit: Optional[str] = None
+    usage_hint: Optional[str] = None
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Image",
+            "url": resolve_string_or_path(self.url)
+        }
+        if self.fit:
+            result["fit"] = self.fit
+        if self.usage_hint:
+            result["usageHint"] = self.usage_hint
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class IconComponent:
+    """Icon display component."""
+    id: str
+    name: StringOrPath
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Icon",
+            "name": resolve_string_or_path(self.name)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class ButtonComponent:
+    """Button component with action."""
+    id: str
+    child: str
+    action: Optional[Action] = None
+    primary: bool = False
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Button",
+            "child": self.child
+        }
+        if self.primary:
+            result["primary"] = True
+        if self.action:
+            result["action"] = self.action.to_dict()
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class CardComponent:
+    """Card container component."""
+    id: str
+    child: str
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Card",
+            "child": self.child
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class RowComponent:
+    """Horizontal layout component."""
+    id: str
+    children: ChildrenType
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Row",
+            "children": resolve_children(self.children)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class ColumnComponent:
+    """Vertical layout component."""
+    id: str
+    children: ChildrenType
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Column",
+            "children": resolve_children(self.children)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class ListComponent:
+    """List component for repeating items."""
+    id: str
+    children: ChildrenType
+    direction: str = "vertical"
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "List",
+            "direction": self.direction,
+            "children": resolve_children(self.children)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class TextFieldComponent:
+    """Text input field component."""
+    id: str
+    label: StringOrPath
+    text: StringOrPath
+    field_type: str = "text"
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "TextField",
+            "label": resolve_string_or_path(self.label),
+            "text": resolve_string_or_path(self.text),
+            "type": self.field_type
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class CheckBoxComponent:
+    """Checkbox input component."""
+    id: str
+    label: StringOrPath
+    checked: BooleanOrPath = False
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "CheckBox",
+            "label": resolve_string_or_path(self.label),
+            "checked": resolve_boolean_or_path(self.checked)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class SliderComponent:
+    """Slider input component."""
+    id: str
+    min_value: NumberOrPath
+    max_value: NumberOrPath
+    value: NumberOrPath
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "Slider",
+            "min": resolve_number_or_path(self.min_value),
+            "max": resolve_number_or_path(self.max_value),
+            "value": resolve_number_or_path(self.value)
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+@dataclass
+class DateTimeInputComponent:
+    """Date/time input component."""
+    id: str
+    label: StringOrPath
+    value: StringOrPath
+    enable_date: bool = True
+    enable_time: bool = False
+    weight: Optional[float] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "id": self.id,
+            "component": "DateTimeInput",
+            "label": resolve_string_or_path(self.label),
+            "value": resolve_string_or_path(self.value),
+            "enableDate": self.enable_date,
+            "enableTime": self.enable_time
+        }
+        if self.weight is not None:
+            result["weight"] = self.weight
+        return result
+
+
+# Type alias for any component
+Component = Union[
+    TextComponent,
+    ImageComponent,
+    IconComponent,
+    ButtonComponent,
+    CardComponent,
+    RowComponent,
+    ColumnComponent,
+    ListComponent,
+    TextFieldComponent,
+    CheckBoxComponent,
+    SliderComponent,
+    DateTimeInputComponent,
+]
+
+
+# =============================================================================
+# Message Types
+# =============================================================================
+
+@dataclass
+class CreateSurfaceMessage:
+    """
+    Message to create a new UI surface.
+    
+    Signals the client to create a new surface and begin rendering it.
+    """
+    surface_id: str
+    catalog_id: str
+    
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "createSurface": {
+                "surfaceId": self.surface_id,
+                "catalogId": self.catalog_id
+            }
+        }
+
+
+@dataclass
+class UpdateComponentsMessage:
+    """
+    Message to update surface components.
+    
+    Updates a surface with a new set of components.
+    """
+    surface_id: str
+    components: List[Component]
+    
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "updateComponents": {
+                "surfaceId": self.surface_id,
+                "components": [c.to_dict() for c in self.components]
+            }
+        }
+
+
+@dataclass
+class UpdateDataModelMessage:
+    """
+    Message to update the data model.
+    
+    Updates the data model for an existing surface.
+    """
+    surface_id: str
+    value: Any
+    path: str = "/"
+    op: str = "replace"
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {
+            "updateDataModel": {
+                "surfaceId": self.surface_id,
+                "path": self.path,
+                "op": self.op,
+                "value": self.value
+            }
+        }
+        return result
+
+
+@dataclass
+class DeleteSurfaceMessage:
+    """
+    Message to delete a surface.
+    
+    Signals the client to delete the surface.
+    """
+    surface_id: str
+    
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "deleteSurface": {
+                "surfaceId": self.surface_id
+            }
+        }
+
+
+# =============================================================================
+# Data Part Type
+# =============================================================================
+
+@dataclass
+class A2UIDataPart:
+    """
+    A2UI data part for A2A integration.
+    
+    Wraps A2UI data with the appropriate MIME type.
+    """
+    data: Dict[str, Any]
+    metadata: Optional[Dict[str, Any]] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        result: Dict[str, Any] = {"data": self.data}
+        if self.metadata:
+            result["metadata"] = self.metadata
+        return result
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "praisonaiagents"
-version = "0.1.15"
+version = "0.1.21"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -0,0 +1 @@
+"""A2A Protocol Tests"""
@@ -0,0 +1,135 @@
+"""
+Tests for Main A2A Class
+
+TDD: Write tests first, then implement A2A class.
+"""
+
+
+class TestA2AClass:
+    """Tests for A2A main class."""
+    
+    def test_a2a_creation_with_agent(self):
+        """Test creating A2A with single agent."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent)
+        
+        assert a2a.agent is not None
+        assert a2a.name == "Test"
+    
+    def test_a2a_creation_with_custom_name(self):
+        """Test creating A2A with custom name."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent, name="Custom Name")
+        
+        assert a2a.name == "Custom Name"
+    
+    def test_a2a_requires_agent(self):
+        """Test A2A requires agent or agents."""
+        from praisonaiagents.ui.a2a import A2A
+        import pytest
+        
+        with pytest.raises(ValueError):
+            A2A()
+    
+    def test_a2a_get_agent_card(self):
+        """Test getting Agent Card from A2A."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Card Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+        
+        card = a2a.get_agent_card()
+        
+        assert card.name == "Card Test"
+        assert card.url == "http://localhost:8000/a2a"
+    
+    def test_a2a_get_router(self):
+        """Test getting FastAPI router from A2A."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Router Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent)
+        
+        router = a2a.get_router()
+        
+        assert router is not None
+        # Check router has routes
+        assert len(router.routes) > 0
+
+
+class TestA2ARouter:
+    """Tests for A2A FastAPI router endpoints."""
+    
+    def test_agent_card_endpoint(self):
+        """Test /.well-known/agent.json endpoint."""
+        from fastapi.testclient import TestClient
+        from fastapi import FastAPI
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Endpoint Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+        
+        app = FastAPI()
+        app.include_router(a2a.get_router())
+        
+        client = TestClient(app)
+        response = client.get("/.well-known/agent.json")
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert data["name"] == "Endpoint Test"
+    
+    def test_status_endpoint(self):
+        """Test /status endpoint."""
+        from fastapi.testclient import TestClient
+        from fastapi import FastAPI
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        agent = Agent(name="Status Test", role="Tester", goal="Test")
+        a2a = A2A(agent=agent)
+        
+        app = FastAPI()
+        app.include_router(a2a.get_router())
+        
+        client = TestClient(app)
+        response = client.get("/status")
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert data["status"] == "ok"
+
+
+class TestA2AWithTools:
+    """Tests for A2A with agent tools."""
+    
+    def test_a2a_agent_card_includes_skills(self):
+        """Test Agent Card includes skills from tools."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a import A2A
+        
+        def my_tool(x: str) -> str:
+            """A test tool."""
+            return x
+        
+        agent = Agent(
+            name="Tool Agent",
+            role="Helper",
+            goal="Help",
+            tools=[my_tool]
+        )
+        a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+        
+        card = a2a.get_agent_card()
+        
+        assert card.skills is not None
+        assert len(card.skills) >= 1
@@ -0,0 +1,200 @@
+"""
+Tests for A2A Agent Card Generation
+
+TDD: Write tests first, then implement agent_card module.
+"""
+
+import json
+
+
+class TestAgentCardGeneration:
+    """Tests for generating Agent Card from PraisonAI Agent."""
+    
+    def test_generate_agent_card_basic(self):
+        """Test generating Agent Card from basic Agent."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(
+            name="Test Agent",
+            role="Test Role",
+            goal="Test Goal"
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        assert card.name == "Test Agent"
+        assert card.url == "http://localhost:8000/a2a"
+        assert card.version == "1.0.0"
+    
+    def test_generate_agent_card_with_description(self):
+        """Test Agent Card includes description from role."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(
+            name="Research Agent",
+            role="Research Analyst",
+            goal="Research topics thoroughly"
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        assert card.description is not None
+        assert "Research" in card.description
+    
+    def test_generate_agent_card_with_instructions(self):
+        """Test Agent Card from Agent with instructions."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(
+            instructions="You are a helpful assistant that answers questions."
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        assert card.name is not None
+        assert card.description is not None
+    
+    def test_generate_agent_card_capabilities(self):
+        """Test Agent Card has correct capabilities."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(name="Test", role="Tester", goal="Test")
+        
+        card = generate_agent_card(
+            agent, 
+            url="http://localhost:8000/a2a",
+            streaming=True
+        )
+        
+        assert card.capabilities.streaming is True
+
+
+class TestSkillsExtraction:
+    """Tests for extracting skills from Agent tools."""
+    
+    def test_extract_skills_from_function(self):
+        """Test extracting skill from a function tool."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        def search_web(query: str) -> str:
+            """Search the web for information."""
+            return f"Results for: {query}"
+        
+        agent = Agent(
+            name="Search Agent",
+            role="Searcher",
+            goal="Search the web",
+            tools=[search_web]
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        assert card.skills is not None
+        assert len(card.skills) >= 1
+        
+        skill_names = [s.name for s in card.skills]
+        assert "search_web" in skill_names
+    
+    def test_extract_skills_with_description(self):
+        """Test skill description comes from function docstring."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        def calculate(expression: str) -> str:
+            """Calculate a mathematical expression."""
+            return str(eval(expression))
+        
+        agent = Agent(
+            name="Calculator",
+            role="Math Helper",
+            goal="Do math",
+            tools=[calculate]
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        calc_skill = next((s for s in card.skills if s.name == "calculate"), None)
+        assert calc_skill is not None
+        assert "mathematical" in calc_skill.description.lower()
+    
+    def test_extract_skills_multiple_tools(self):
+        """Test extracting skills from multiple tools."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        def tool_one(x: str) -> str:
+            """First tool."""
+            return x
+        
+        def tool_two(y: str) -> str:
+            """Second tool."""
+            return y
+        
+        agent = Agent(
+            name="Multi Tool Agent",
+            role="Helper",
+            goal="Help",
+            tools=[tool_one, tool_two]
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        assert len(card.skills) >= 2
+    
+    def test_no_skills_when_no_tools(self):
+        """Test Agent Card with no tools has empty skills."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(
+            name="Simple Agent",
+            role="Helper",
+            goal="Help"
+        )
+        
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        # Skills should be None or empty list
+        assert card.skills is None or len(card.skills) == 0
+
+
+class TestAgentCardSerialization:
+    """Tests for Agent Card JSON serialization."""
+    
+    def test_agent_card_to_json(self):
+        """Test Agent Card can be serialized to JSON."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(name="Test", role="Tester", goal="Test")
+        card = generate_agent_card(agent, url="http://localhost:8000/a2a")
+        
+        json_str = card.model_dump_json()
+        data = json.loads(json_str)
+        
+        assert "name" in data
+        assert "url" in data
+        assert "capabilities" in data
+    
+    def test_agent_card_camel_case_keys(self):
+        """Test Agent Card JSON uses camelCase keys."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2a.agent_card import generate_agent_card
+        
+        agent = Agent(name="Test", role="Tester", goal="Test")
+        card = generate_agent_card(
+            agent, 
+            url="http://localhost:8000/a2a",
+            streaming=True
+        )
+        
+        # Use by_alias to get camelCase
+        data = card.model_dump(by_alias=True)
+        
+        # Check capabilities uses camelCase
+        assert "pushNotifications" in data["capabilities"]
@@ -0,0 +1,190 @@
+"""
+Tests for A2A Message Conversion
+
+TDD: Write tests first, then implement conversion module.
+"""
+
+
+class TestA2AToPraisonAI:
+    """Tests for converting A2A messages to PraisonAI format."""
+    
+    def test_convert_user_message(self):
+        """Test converting A2A user message to PraisonAI format."""
+        from praisonaiagents.ui.a2a.conversion import a2a_to_praisonai_messages
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        a2a_msg = Message(
+            message_id="msg-1",
+            role=Role.USER,
+            parts=[TextPart(text="Hello, how are you?")]
+        )
+        
+        result = a2a_to_praisonai_messages([a2a_msg])
+        
+        assert len(result) == 1
+        assert result[0]["role"] == "user"
+        assert result[0]["content"] == "Hello, how are you?"
+    
+    def test_convert_agent_message(self):
+        """Test converting A2A agent message to PraisonAI format."""
+        from praisonaiagents.ui.a2a.conversion import a2a_to_praisonai_messages
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        a2a_msg = Message(
+            message_id="msg-2",
+            role=Role.AGENT,
+            parts=[TextPart(text="I'm doing well, thanks!")]
+        )
+        
+        result = a2a_to_praisonai_messages([a2a_msg])
+        
+        assert len(result) == 1
+        assert result[0]["role"] == "assistant"
+        assert result[0]["content"] == "I'm doing well, thanks!"
+    
+    def test_convert_multiple_parts(self):
+        """Test converting message with multiple text parts."""
+        from praisonaiagents.ui.a2a.conversion import a2a_to_praisonai_messages
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        a2a_msg = Message(
+            message_id="msg-3",
+            role=Role.USER,
+            parts=[
+                TextPart(text="First part."),
+                TextPart(text="Second part.")
+            ]
+        )
+        
+        result = a2a_to_praisonai_messages([a2a_msg])
+        
+        assert "First part" in result[0]["content"]
+        assert "Second part" in result[0]["content"]
+    
+    def test_convert_conversation_history(self):
+        """Test converting full conversation history."""
+        from praisonaiagents.ui.a2a.conversion import a2a_to_praisonai_messages
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        messages = [
+            Message(message_id="m1", role=Role.USER, parts=[TextPart(text="Hi")]),
+            Message(message_id="m2", role=Role.AGENT, parts=[TextPart(text="Hello!")]),
+            Message(message_id="m3", role=Role.USER, parts=[TextPart(text="How are you?")]),
+        ]
+        
+        result = a2a_to_praisonai_messages(messages)
+        
+        assert len(result) == 3
+        assert result[0]["role"] == "user"
+        assert result[1]["role"] == "assistant"
+        assert result[2]["role"] == "user"
+
+
+class TestPraisonAIToA2A:
+    """Tests for converting PraisonAI responses to A2A format."""
+    
+    def test_convert_string_response(self):
+        """Test converting string response to A2A Message."""
+        from praisonaiagents.ui.a2a.conversion import praisonai_to_a2a_message
+        
+        response = "This is the agent's response."
+        
+        result = praisonai_to_a2a_message(response)
+        
+        assert result.role.value == "agent"
+        assert len(result.parts) == 1
+        assert result.parts[0].text == response
+    
+    def test_convert_response_with_context(self):
+        """Test converting response with context_id."""
+        from praisonaiagents.ui.a2a.conversion import praisonai_to_a2a_message
+        
+        response = "Response text"
+        
+        result = praisonai_to_a2a_message(response, context_id="ctx-123")
+        
+        assert result.context_id == "ctx-123"
+    
+    def test_convert_response_with_task(self):
+        """Test converting response with task_id."""
+        from praisonaiagents.ui.a2a.conversion import praisonai_to_a2a_message
+        
+        response = "Response text"
+        
+        result = praisonai_to_a2a_message(response, task_id="task-456")
+        
+        assert result.task_id == "task-456"
+
+
+class TestArtifactConversion:
+    """Tests for converting responses to A2A Artifacts."""
+    
+    def test_create_artifact_from_response(self):
+        """Test creating Artifact from response."""
+        from praisonaiagents.ui.a2a.conversion import create_artifact
+        
+        response = "Generated content here."
+        
+        artifact = create_artifact(response)
+        
+        assert artifact.artifact_id is not None
+        assert len(artifact.parts) == 1
+        assert artifact.parts[0].text == response
+    
+    def test_create_artifact_with_name(self):
+        """Test creating Artifact with name."""
+        from praisonaiagents.ui.a2a.conversion import create_artifact
+        
+        response = "Report content"
+        
+        artifact = create_artifact(response, name="Report", description="Generated report")
+        
+        assert artifact.name == "Report"
+        assert artifact.description == "Generated report"
+
+
+class TestExtractUserInput:
+    """Tests for extracting user input from A2A messages."""
+    
+    def test_extract_from_single_message(self):
+        """Test extracting user input from single message."""
+        from praisonaiagents.ui.a2a.conversion import extract_user_input
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        msg = Message(
+            message_id="m1",
+            role=Role.USER,
+            parts=[TextPart(text="What is AI?")]
+        )
+        
+        result = extract_user_input([msg])
+        
+        assert result == "What is AI?"
+    
+    def test_extract_from_conversation(self):
+        """Test extracting last user input from conversation."""
+        from praisonaiagents.ui.a2a.conversion import extract_user_input
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        messages = [
+            Message(message_id="m1", role=Role.USER, parts=[TextPart(text="First question")]),
+            Message(message_id="m2", role=Role.AGENT, parts=[TextPart(text="Answer")]),
+            Message(message_id="m3", role=Role.USER, parts=[TextPart(text="Follow up question")]),
+        ]
+        
+        result = extract_user_input(messages)
+        
+        assert result == "Follow up question"
+    
+    def test_extract_empty_when_no_user_message(self):
+        """Test extracting returns empty when no user message."""
+        from praisonaiagents.ui.a2a.conversion import extract_user_input
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        messages = [
+            Message(message_id="m1", role=Role.AGENT, parts=[TextPart(text="Hello")]),
+        ]
+        
+        result = extract_user_input(messages)
+        
+        assert result == ""
@@ -0,0 +1,116 @@
+"""
+Tests for A2A Streaming Events
+"""
+
+
+class TestA2AEventEncoder:
+    """Tests for A2AEventEncoder."""
+    
+    def test_encode_event(self):
+        """Test encoding a generic event."""
+        from praisonaiagents.ui.a2a.streaming import A2AEventEncoder
+        
+        result = A2AEventEncoder.encode_event("test", {"key": "value"})
+        
+        assert "event: test" in result
+        assert "data:" in result
+        assert "key" in result
+    
+    def test_encode_task_status(self):
+        """Test encoding TaskStatusUpdateEvent."""
+        from praisonaiagents.ui.a2a.streaming import A2AEventEncoder
+        from praisonaiagents.ui.a2a.types import TaskStatusUpdateEvent, TaskStatus, TaskState
+        
+        event = TaskStatusUpdateEvent(
+            task_id="task-123",
+            status=TaskStatus(state=TaskState.WORKING),
+            final=False,
+        )
+        
+        result = A2AEventEncoder.encode_task_status(event)
+        
+        assert "event: task.status" in result
+        assert "task-123" in result
+    
+    def test_encode_task_artifact(self):
+        """Test encoding TaskArtifactUpdateEvent."""
+        from praisonaiagents.ui.a2a.streaming import A2AEventEncoder
+        from praisonaiagents.ui.a2a.types import TaskArtifactUpdateEvent, Artifact, TextPart
+        
+        artifact = Artifact(
+            artifact_id="art-1",
+            parts=[TextPart(text="Result")]
+        )
+        event = TaskArtifactUpdateEvent(
+            task_id="task-456",
+            artifact=artifact,
+            last_chunk=True,
+        )
+        
+        result = A2AEventEncoder.encode_task_artifact(event)
+        
+        assert "event: task.artifact" in result
+        assert "art-1" in result
+    
+    def test_encode_done(self):
+        """Test encoding done event."""
+        from praisonaiagents.ui.a2a.streaming import A2AEventEncoder
+        
+        result = A2AEventEncoder.encode_done()
+        
+        assert "event: done" in result
+
+
+class TestCreateEvents:
+    """Tests for event creation helpers."""
+    
+    def test_create_status_event(self):
+        """Test creating status event."""
+        from praisonaiagents.ui.a2a.streaming import create_status_event
+        from praisonaiagents.ui.a2a.types import TaskState
+        
+        event = create_status_event(
+            task_id="task-1",
+            state=TaskState.WORKING,
+        )
+        
+        assert event.task_id == "task-1"
+        assert event.status.state == TaskState.WORKING
+    
+    def test_create_status_event_final(self):
+        """Test creating final status event."""
+        from praisonaiagents.ui.a2a.streaming import create_status_event
+        from praisonaiagents.ui.a2a.types import TaskState
+        
+        event = create_status_event(
+            task_id="task-2",
+            state=TaskState.COMPLETED,
+            final=True,
+        )
+        
+        assert event.final is True
+    
+    def test_create_artifact_event(self):
+        """Test creating artifact event."""
+        from praisonaiagents.ui.a2a.streaming import create_artifact_event
+        
+        event = create_artifact_event(
+            task_id="task-3",
+            content="Generated content",
+        )
+        
+        assert event.task_id == "task-3"
+        assert event.artifact is not None
+        assert len(event.artifact.parts) == 1
+    
+    def test_create_artifact_event_last_chunk(self):
+        """Test creating last chunk artifact event."""
+        from praisonaiagents.ui.a2a.streaming import create_artifact_event
+        
+        event = create_artifact_event(
+            task_id="task-4",
+            content="Final content",
+            last_chunk=True,
+        )
+        
+        assert event.last_chunk is True
@@ -0,0 +1,225 @@
+"""
+Tests for A2A Task Store
+
+TDD: Write tests first, then implement task_store module.
+"""
+
+
+class TestTaskStore:
+    """Tests for TaskStore class."""
+    
+    def test_create_task(self):
+        """Test creating a new task."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart, TaskState
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-1",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        task = store.create_task(msg)
+        
+        assert task.id is not None
+        assert task.status.state == TaskState.SUBMITTED
+    
+    def test_create_task_with_context(self):
+        """Test creating task with context_id."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-2",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")],
+            context_id="ctx-123"
+        )
+        
+        task = store.create_task(msg)
+        
+        assert task.context_id == "ctx-123"
+    
+    def test_get_task(self):
+        """Test retrieving a task by ID."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-3",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        created = store.create_task(msg)
+        retrieved = store.get_task(created.id)
+        
+        assert retrieved is not None
+        assert retrieved.id == created.id
+    
+    def test_get_task_not_found(self):
+        """Test getting non-existent task returns None."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        
+        store = TaskStore()
+        result = store.get_task("non-existent-id")
+        
+        assert result is None
+    
+    def test_update_status(self):
+        """Test updating task status."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart, TaskState
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-4",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        task = store.create_task(msg)
+        updated = store.update_status(task.id, TaskState.WORKING)
+        
+        assert updated.status.state == TaskState.WORKING
+    
+    def test_update_status_to_completed(self):
+        """Test updating task to completed state."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart, TaskState
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-5",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        task = store.create_task(msg)
+        store.update_status(task.id, TaskState.WORKING)
+        updated = store.update_status(task.id, TaskState.COMPLETED)
+        
+        assert updated.status.state == TaskState.COMPLETED
+    
+    def test_add_artifact(self):
+        """Test adding artifact to task."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart, Artifact
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-6",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        task = store.create_task(msg)
+        artifact = Artifact(
+            artifact_id="art-1",
+            parts=[TextPart(text="Result")]
+        )
+        
+        updated = store.add_artifact(task.id, artifact)
+        
+        assert updated.artifacts is not None
+        assert len(updated.artifacts) == 1
+    
+    def test_add_message_to_history(self):
+        """Test adding message to task history."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        store = TaskStore()
+        msg1 = Message(
+            message_id="msg-7",
+            role=Role.USER,
+            parts=[TextPart(text="Question")]
+        )
+        
+        task = store.create_task(msg1)
+        
+        msg2 = Message(
+            message_id="msg-8",
+            role=Role.AGENT,
+            parts=[TextPart(text="Answer")]
+        )
+        
+        updated = store.add_to_history(task.id, msg2)
+        
+        assert updated.history is not None
+        assert len(updated.history) >= 1
+    
+    def test_list_tasks(self):
+        """Test listing all tasks."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        store = TaskStore()
+        
+        for i in range(3):
+            msg = Message(
+                message_id=f"msg-{i}",
+                role=Role.USER,
+                parts=[TextPart(text=f"Message {i}")]
+            )
+            store.create_task(msg)
+        
+        tasks = store.list_tasks()
+        
+        assert len(tasks) == 3
+    
+    def test_cancel_task(self):
+        """Test cancelling a task."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart, TaskState
+        
+        store = TaskStore()
+        msg = Message(
+            message_id="msg-cancel",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        
+        task = store.create_task(msg)
+        cancelled = store.cancel_task(task.id)
+        
+        assert cancelled.status.state == TaskState.CANCELLED
+
+
+class TestTaskStoreContextManagement:
+    """Tests for context management in TaskStore."""
+    
+    def test_tasks_grouped_by_context(self):
+        """Test getting tasks by context_id."""
+        from praisonaiagents.ui.a2a.task_store import TaskStore
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        
+        store = TaskStore()
+        
+        # Create tasks in context A
+        for i in range(2):
+            msg = Message(
+                message_id=f"msg-a-{i}",
+                role=Role.USER,
+                parts=[TextPart(text=f"A{i}")],
+                context_id="context-a"
+            )
+            store.create_task(msg)
+        
+        # Create task in context B
+        msg_b = Message(
+            message_id="msg-b-1",
+            role=Role.USER,
+            parts=[TextPart(text="B1")],
+            context_id="context-b"
+        )
+        store.create_task(msg_b)
+        
+        tasks_a = store.list_tasks(context_id="context-a")
+        tasks_b = store.list_tasks(context_id="context-b")
+        
+        assert len(tasks_a) == 2
+        assert len(tasks_b) == 1
@@ -0,0 +1,395 @@
+"""
+Tests for A2A Protocol Types
+
+TDD: Write tests first, then implement types.
+"""
+
+import json
+from datetime import datetime
+
+
+class TestTaskState:
+    """Tests for TaskState enum."""
+    
+    def test_task_state_submitted(self):
+        """Test SUBMITTED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.SUBMITTED == "submitted"
+    
+    def test_task_state_working(self):
+        """Test WORKING state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.WORKING == "working"
+    
+    def test_task_state_completed(self):
+        """Test COMPLETED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.COMPLETED == "completed"
+    
+    def test_task_state_failed(self):
+        """Test FAILED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.FAILED == "failed"
+    
+    def test_task_state_cancelled(self):
+        """Test CANCELLED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.CANCELLED == "cancelled"
+    
+    def test_task_state_input_required(self):
+        """Test INPUT_REQUIRED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.INPUT_REQUIRED == "input_required"
+    
+    def test_task_state_auth_required(self):
+        """Test AUTH_REQUIRED state exists."""
+        from praisonaiagents.ui.a2a.types import TaskState
+        assert TaskState.AUTH_REQUIRED == "auth_required"
+
+
+class TestRole:
+    """Tests for Role enum."""
+    
+    def test_role_user(self):
+        """Test USER role exists."""
+        from praisonaiagents.ui.a2a.types import Role
+        assert Role.USER == "user"
+    
+    def test_role_agent(self):
+        """Test AGENT role exists."""
+        from praisonaiagents.ui.a2a.types import Role
+        assert Role.AGENT == "agent"
+
+
+class TestPart:
+    """Tests for Part models."""
+    
+    def test_text_part_creation(self):
+        """Test TextPart can be created."""
+        from praisonaiagents.ui.a2a.types import TextPart
+        part = TextPart(text="Hello, world!")
+        assert part.text == "Hello, world!"
+    
+    def test_file_part_with_uri(self):
+        """Test FilePart with URI."""
+        from praisonaiagents.ui.a2a.types import FilePart
+        part = FilePart(
+            file_uri="https://example.com/file.pdf",
+            media_type="application/pdf",
+            name="document.pdf"
+        )
+        assert part.file_uri == "https://example.com/file.pdf"
+        assert part.media_type == "application/pdf"
+    
+    def test_file_part_with_bytes(self):
+        """Test FilePart with bytes."""
+        from praisonaiagents.ui.a2a.types import FilePart
+        part = FilePart(
+            file_bytes=b"file content",
+            media_type="text/plain",
+            name="test.txt"
+        )
+        assert part.file_bytes == b"file content"
+    
+    def test_data_part_creation(self):
+        """Test DataPart can be created."""
+        from praisonaiagents.ui.a2a.types import DataPart
+        part = DataPart(data={"key": "value", "count": 42})
+        assert part.data == {"key": "value", "count": 42}
+
+
+class TestMessage:
+    """Tests for Message model."""
+    
+    def test_message_creation(self):
+        """Test Message can be created."""
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        msg = Message(
+            message_id="msg-123",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        assert msg.message_id == "msg-123"
+        assert msg.role == Role.USER
+        assert len(msg.parts) == 1
+    
+    def test_message_with_context(self):
+        """Test Message with context_id."""
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        msg = Message(
+            message_id="msg-456",
+            role=Role.AGENT,
+            parts=[TextPart(text="Response")],
+            context_id="ctx-789"
+        )
+        assert msg.context_id == "ctx-789"
+    
+    def test_message_with_task(self):
+        """Test Message with task_id."""
+        from praisonaiagents.ui.a2a.types import Message, Role, TextPart
+        msg = Message(
+            message_id="msg-789",
+            role=Role.AGENT,
+            parts=[TextPart(text="Working on it")],
+            task_id="task-123"
+        )
+        assert msg.task_id == "task-123"
+
+
+class TestTaskStatus:
+    """Tests for TaskStatus model."""
+    
+    def test_task_status_creation(self):
+        """Test TaskStatus can be created."""
+        from praisonaiagents.ui.a2a.types import TaskStatus, TaskState
+        status = TaskStatus(state=TaskState.WORKING)
+        assert status.state == TaskState.WORKING
+    
+    def test_task_status_with_message(self):
+        """Test TaskStatus with message."""
+        from praisonaiagents.ui.a2a.types import TaskStatus, TaskState, Message, Role, TextPart
+        msg = Message(
+            message_id="msg-1",
+            role=Role.AGENT,
+            parts=[TextPart(text="Processing...")]
+        )
+        status = TaskStatus(state=TaskState.WORKING, message=msg)
+        assert status.message is not None
+    
+    def test_task_status_with_timestamp(self):
+        """Test TaskStatus with timestamp."""
+        from praisonaiagents.ui.a2a.types import TaskStatus, TaskState
+        ts = datetime.utcnow().isoformat()
+        status = TaskStatus(state=TaskState.COMPLETED, timestamp=ts)
+        assert status.timestamp == ts
+
+
+class TestTask:
+    """Tests for Task model."""
+    
+    def test_task_creation(self):
+        """Test Task can be created."""
+        from praisonaiagents.ui.a2a.types import Task, TaskStatus, TaskState
+        task = Task(
+            id="task-123",
+            status=TaskStatus(state=TaskState.SUBMITTED)
+        )
+        assert task.id == "task-123"
+        assert task.status.state == TaskState.SUBMITTED
+    
+    def test_task_with_context(self):
+        """Test Task with context_id."""
+        from praisonaiagents.ui.a2a.types import Task, TaskStatus, TaskState
+        task = Task(
+            id="task-456",
+            context_id="ctx-789",
+            status=TaskStatus(state=TaskState.WORKING)
+        )
+        assert task.context_id == "ctx-789"
+    
+    def test_task_with_artifacts(self):
+        """Test Task with artifacts."""
+        from praisonaiagents.ui.a2a.types import Task, TaskStatus, TaskState, Artifact, TextPart
+        artifact = Artifact(
+            artifact_id="art-1",
+            parts=[TextPart(text="Result")]
+        )
+        task = Task(
+            id="task-789",
+            status=TaskStatus(state=TaskState.COMPLETED),
+            artifacts=[artifact]
+        )
+        assert len(task.artifacts) == 1
+    
+    def test_task_with_history(self):
+        """Test Task with message history."""
+        from praisonaiagents.ui.a2a.types import Task, TaskStatus, TaskState, Message, Role, TextPart
+        msg1 = Message(message_id="m1", role=Role.USER, parts=[TextPart(text="Q")])
+        msg2 = Message(message_id="m2", role=Role.AGENT, parts=[TextPart(text="A")])
+        task = Task(
+            id="task-abc",
+            status=TaskStatus(state=TaskState.COMPLETED),
+            history=[msg1, msg2]
+        )
+        assert len(task.history) == 2
+
+
+class TestArtifact:
+    """Tests for Artifact model."""
+    
+    def test_artifact_creation(self):
+        """Test Artifact can be created."""
+        from praisonaiagents.ui.a2a.types import Artifact, TextPart
+        artifact = Artifact(
+            artifact_id="art-123",
+            parts=[TextPart(text="Generated content")]
+        )
+        assert artifact.artifact_id == "art-123"
+    
+    def test_artifact_with_name(self):
+        """Test Artifact with name and description."""
+        from praisonaiagents.ui.a2a.types import Artifact, TextPart
+        artifact = Artifact(
+            artifact_id="art-456",
+            name="Report",
+            description="Generated report",
+            parts=[TextPart(text="Report content")]
+        )
+        assert artifact.name == "Report"
+        assert artifact.description == "Generated report"
+
+
+class TestAgentSkill:
+    """Tests for AgentSkill model."""
+    
+    def test_agent_skill_creation(self):
+        """Test AgentSkill can be created."""
+        from praisonaiagents.ui.a2a.types import AgentSkill
+        skill = AgentSkill(
+            id="search",
+            name="Web Search",
+            description="Search the web for information"
+        )
+        assert skill.id == "search"
+        assert skill.name == "Web Search"
+    
+    def test_agent_skill_with_tags(self):
+        """Test AgentSkill with tags."""
+        from praisonaiagents.ui.a2a.types import AgentSkill
+        skill = AgentSkill(
+            id="calc",
+            name="Calculator",
+            description="Perform calculations",
+            tags=["math", "utility"]
+        )
+        assert skill.tags == ["math", "utility"]
+    
+    def test_agent_skill_with_examples(self):
+        """Test AgentSkill with examples."""
+        from praisonaiagents.ui.a2a.types import AgentSkill
+        skill = AgentSkill(
+            id="translate",
+            name="Translator",
+            description="Translate text",
+            examples=["Translate hello to Spanish", "What is bonjour in English?"]
+        )
+        assert len(skill.examples) == 2
+
+
+class TestAgentCapabilities:
+    """Tests for AgentCapabilities model."""
+    
+    def test_capabilities_creation(self):
+        """Test AgentCapabilities can be created."""
+        from praisonaiagents.ui.a2a.types import AgentCapabilities
+        caps = AgentCapabilities(streaming=True)
+        assert caps.streaming is True
+    
+    def test_capabilities_defaults(self):
+        """Test AgentCapabilities defaults."""
+        from praisonaiagents.ui.a2a.types import AgentCapabilities
+        caps = AgentCapabilities()
+        assert caps.streaming is False
+        assert caps.push_notifications is False
+
+
+class TestAgentCard:
+    """Tests for AgentCard model."""
+    
+    def test_agent_card_creation(self):
+        """Test AgentCard can be created."""
+        from praisonaiagents.ui.a2a.types import AgentCard, AgentCapabilities
+        card = AgentCard(
+            name="Research Agent",
+            url="http://localhost:8000/a2a",
+            version="1.0.0",
+            capabilities=AgentCapabilities(streaming=True)
+        )
+        assert card.name == "Research Agent"
+        assert card.url == "http://localhost:8000/a2a"
+    
+    def test_agent_card_with_skills(self):
+        """Test AgentCard with skills."""
+        from praisonaiagents.ui.a2a.types import AgentCard, AgentCapabilities, AgentSkill
+        skill = AgentSkill(id="search", name="Search", description="Search web")
+        card = AgentCard(
+            name="Search Agent",
+            url="http://localhost:8000/a2a",
+            version="1.0.0",
+            capabilities=AgentCapabilities(),
+            skills=[skill]
+        )
+        assert len(card.skills) == 1
+    
+    def test_agent_card_json_serialization(self):
+        """Test AgentCard can be serialized to JSON."""
+        from praisonaiagents.ui.a2a.types import AgentCard, AgentCapabilities
+        card = AgentCard(
+            name="Test Agent",
+            url="http://localhost:8000/a2a",
+            version="1.0.0",
+            capabilities=AgentCapabilities()
+        )
+        json_str = card.model_dump_json()
+        data = json.loads(json_str)
+        assert data["name"] == "Test Agent"
+
+
+class TestSendMessageRequest:
+    """Tests for SendMessageRequest model."""
+    
+    def test_send_message_request_creation(self):
+        """Test SendMessageRequest can be created."""
+        from praisonaiagents.ui.a2a.types import SendMessageRequest, Message, Role, TextPart
+        msg = Message(
+            message_id="msg-1",
+            role=Role.USER,
+            parts=[TextPart(text="Hello")]
+        )
+        req = SendMessageRequest(message=msg)
+        assert req.message.message_id == "msg-1"
+    
+    def test_send_message_request_with_config(self):
+        """Test SendMessageRequest with configuration."""
+        from praisonaiagents.ui.a2a.types import SendMessageRequest, Message, Role, TextPart, MessageConfig
+        msg = Message(
+            message_id="msg-2",
+            role=Role.USER,
+            parts=[TextPart(text="Search for AI")]
+        )
+        config = MessageConfig(
+            accept_content_types=["text/plain", "application/json"]
+        )
+        req = SendMessageRequest(message=msg, configuration=config)
+        assert req.configuration is not None
+
+
+class TestStreamingEvents:
+    """Tests for streaming event models."""
+    
+    def test_task_status_update_event(self):
+        """Test TaskStatusUpdateEvent creation."""
+        from praisonaiagents.ui.a2a.types import TaskStatusUpdateEvent, TaskStatus, TaskState
+        event = TaskStatusUpdateEvent(
+            task_id="task-123",
+            status=TaskStatus(state=TaskState.WORKING),
+            final=False
+        )
+        assert event.task_id == "task-123"
+        assert event.final is False
+    
+    def test_task_artifact_update_event(self):
+        """Test TaskArtifactUpdateEvent creation."""
+        from praisonaiagents.ui.a2a.types import TaskArtifactUpdateEvent, Artifact, TextPart
+        artifact = Artifact(
+            artifact_id="art-1",
+            parts=[TextPart(text="Partial result")]
+        )
+        event = TaskArtifactUpdateEvent(
+            task_id="task-456",
+            artifact=artifact,
+            append=True,
+            last_chunk=False
+        )
+        assert event.append is True
+        assert event.last_chunk is False
@@ -0,0 +1 @@
+"""A2UI Tests Package."""
@@ -0,0 +1,201 @@
+"""
+Tests for A2UI Agent Integration
+
+TDD: Write tests first, then implement the A2UIAgent class.
+"""
+
+import os
+import pytest
+
+
+# Skip tests if no API key
+pytestmark = pytest.mark.skipif(
+    not os.environ.get("OPENAI_API_KEY"),
+    reason="OPENAI_API_KEY not set"
+)
+
+
+class TestA2UIAgent:
+    """Test A2UIAgent wrapper class."""
+
+    def test_a2ui_agent_creation(self):
+        """Test A2UIAgent creation with an agent."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(
+            name="TestAgent",
+            role="Test assistant",
+            goal="Help with testing"
+        )
+        
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        assert a2ui_agent.agent is agent
+        assert a2ui_agent.surface_id is not None
+
+    def test_a2ui_agent_with_custom_surface_id(self):
+        """Test A2UIAgent with custom surface ID."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent, surface_id="custom-surface")
+        
+        assert a2ui_agent.surface_id == "custom-surface"
+
+    def test_render_text_response(self):
+        """Test rendering a simple text response as A2UI."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        # Render a simple text response
+        messages = a2ui_agent.render_text("Hello, World!")
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2  # createSurface + updateComponents
+        
+        # Check createSurface
+        assert "createSurface" in messages[0]
+        
+        # Check updateComponents has a text component
+        update_msg = next((m for m in messages if "updateComponents" in m), None)
+        assert update_msg is not None
+        components = update_msg["updateComponents"]["components"]
+        assert any(c.get("component") == "Text" for c in components)
+
+    def test_render_list_response(self):
+        """Test rendering a list of items as A2UI cards."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        items = [
+            {"title": "Item 1", "description": "First item"},
+            {"title": "Item 2", "description": "Second item"},
+        ]
+        
+        messages = a2ui_agent.render_list(
+            title="My Items",
+            items=items,
+            item_title_key="title",
+            item_description_key="description"
+        )
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2
+
+    def test_render_form(self):
+        """Test rendering a form as A2UI."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        fields = [
+            {"id": "name", "label": "Name", "type": "text"},
+            {"id": "email", "label": "Email", "type": "text"},
+        ]
+        
+        messages = a2ui_agent.render_form(
+            title="Contact Form",
+            fields=fields,
+            submit_action="submit_form"
+        )
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2
+        
+        # Check for TextField components
+        update_msg = next((m for m in messages if "updateComponents" in m), None)
+        assert update_msg is not None
+        components = update_msg["updateComponents"]["components"]
+        text_fields = [c for c in components if c.get("component") == "TextField"]
+        assert len(text_fields) >= 2
+
+    def test_get_surface(self):
+        """Test getting the underlying Surface object."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        surface = a2ui_agent.get_surface()
+        
+        assert isinstance(surface, Surface)
+        assert surface.surface_id == a2ui_agent.surface_id
+
+
+class TestA2UIAgentWithLLM:
+    """Test A2UIAgent with actual LLM calls."""
+
+    @pytest.mark.asyncio
+    async def test_chat_with_ui(self):
+        """Test chat that returns A2UI response."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        
+        agent = Agent(
+            name="UIAgent",
+            role="UI Generator",
+            goal="Generate helpful UI responses",
+            llm="gpt-4o-mini"
+        )
+        
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        # This should work with the agent's chat
+        response = await a2ui_agent.chat_async("Say hello")
+        
+        assert response is not None
+        # Response should contain text
+        assert isinstance(response, str) or isinstance(response, dict)
+
+
+class TestA2UIAgentIntegration:
+    """Integration tests for A2UIAgent with A2A."""
+
+    def test_get_a2a_data_part(self):
+        """Test getting A2UI as A2A DataPart."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        from praisonaiagents.ui.a2ui.extension import is_a2ui_part
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        # Render something
+        a2ui_agent.render_text("Hello")
+        
+        # Get as A2A DataPart
+        part = a2ui_agent.to_a2a_part()
+        
+        assert part is not None
+        assert is_a2ui_part(part)
+
+    def test_to_json(self):
+        """Test getting A2UI as JSON string."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui.agent import A2UIAgent
+        import json
+        
+        agent = Agent(name="TestAgent", role="Test", goal="Test")
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        # Render something
+        a2ui_agent.render_text("Hello")
+        
+        # Get as JSON
+        json_str = a2ui_agent.to_json()
+        
+        # Should be valid JSON
+        parsed = json.loads(json_str)
+        assert isinstance(parsed, list)
@@ -0,0 +1,115 @@
+"""
+Tests for A2UI Extension Module
+
+TDD: Write tests first, then implement the extension.
+"""
+
+
+class TestA2UIExtension:
+    """Test A2UI extension helpers for A2A integration."""
+
+    def test_a2ui_mime_type(self):
+        """Test A2UI MIME type constant."""
+        from praisonaiagents.ui.a2ui.extension import A2UI_MIME_TYPE
+        
+        assert A2UI_MIME_TYPE == "application/json+a2ui"
+
+    def test_a2ui_extension_uri(self):
+        """Test A2UI extension URI constant."""
+        from praisonaiagents.ui.a2ui.extension import A2UI_EXTENSION_URI
+        
+        assert "a2ui" in A2UI_EXTENSION_URI.lower()
+
+    def test_create_a2ui_part(self):
+        """Test create_a2ui_part wraps A2UI data in A2A DataPart."""
+        from praisonaiagents.ui.a2ui.extension import create_a2ui_part, A2UI_MIME_TYPE
+        
+        a2ui_data = {
+            "createSurface": {
+                "surfaceId": "main",
+                "catalogId": "https://a2ui.dev/standard"
+            }
+        }
+        
+        part = create_a2ui_part(a2ui_data)
+        
+        # Should return a Part with DataPart root
+        assert part is not None
+        assert hasattr(part, 'data')
+        assert part.data == a2ui_data
+        assert part.metadata is not None
+        assert part.metadata.get("mimeType") == A2UI_MIME_TYPE
+
+    def test_is_a2ui_part_true(self):
+        """Test is_a2ui_part returns True for A2UI parts."""
+        from praisonaiagents.ui.a2ui.extension import create_a2ui_part, is_a2ui_part
+        
+        a2ui_data = {"createSurface": {"surfaceId": "main", "catalogId": "test"}}
+        part = create_a2ui_part(a2ui_data)
+        
+        assert is_a2ui_part(part) is True
+
+    def test_is_a2ui_part_false(self):
+        """Test is_a2ui_part returns False for non-A2UI parts."""
+        from praisonaiagents.ui.a2ui.extension import is_a2ui_part
+        from praisonaiagents.ui.a2ui.types import A2UIDataPart
+        
+        # Create a regular data part without A2UI mime type
+        part = A2UIDataPart(data={"foo": "bar"}, metadata={"mimeType": "application/json"})
+        
+        assert is_a2ui_part(part) is False
+
+    def test_get_a2ui_agent_extension(self):
+        """Test get_a2ui_agent_extension returns AgentExtension config."""
+        from praisonaiagents.ui.a2ui.extension import get_a2ui_agent_extension
+        
+        ext = get_a2ui_agent_extension()
+        
+        assert ext is not None
+        assert hasattr(ext, 'uri')
+        assert "a2ui" in ext.uri.lower()
+        assert hasattr(ext, 'description')
+
+    def test_get_a2ui_agent_extension_with_inline_catalog(self):
+        """Test get_a2ui_agent_extension with inline catalog support."""
+        from praisonaiagents.ui.a2ui.extension import get_a2ui_agent_extension
+        
+        ext = get_a2ui_agent_extension(accepts_inline_custom_catalog=True)
+        
+        assert ext.params is not None
+        assert ext.params.get("acceptsInlineCustomCatalog") is True
+
+    def test_standard_catalog_id(self):
+        """Test standard catalog ID constant."""
+        from praisonaiagents.ui.a2ui.extension import STANDARD_CATALOG_ID
+        
+        assert "standard_catalog" in STANDARD_CATALOG_ID.lower() or "a2ui" in STANDARD_CATALOG_ID.lower()
+
+
+class TestA2UIDataPart:
+    """Test A2UI DataPart type."""
+
+    def test_a2ui_data_part_creation(self):
+        """Test A2UIDataPart creation."""
+        from praisonaiagents.ui.a2ui.types import A2UIDataPart
+        
+        part = A2UIDataPart(
+            data={"test": "value"},
+            metadata={"mimeType": "application/json+a2ui"}
+        )
+        
+        assert part.data == {"test": "value"}
+        assert part.metadata["mimeType"] == "application/json+a2ui"
+
+    def test_a2ui_data_part_to_dict(self):
+        """Test A2UIDataPart serialization."""
+        from praisonaiagents.ui.a2ui.types import A2UIDataPart
+        
+        part = A2UIDataPart(
+            data={"createSurface": {"surfaceId": "main"}},
+            metadata={"mimeType": "application/json+a2ui"}
+        )
+        
+        data = part.to_dict()
+        assert "data" in data
+        assert "metadata" in data
@@ -0,0 +1,225 @@
+"""
+End-to-End Integration Tests for A2UI
+
+Tests the complete A2UI workflow from agent to JSON output.
+"""
+
+import json
+import os
+import pytest
+
+
+class TestA2UIEndToEnd:
+    """End-to-end integration tests."""
+
+    def test_complete_surface_workflow(self):
+        """Test complete workflow: create surface, add components, generate JSON."""
+        from praisonaiagents.ui.a2ui import (
+            Surface,
+            PathBinding,
+        )
+        
+        # Create surface
+        surface = Surface(surface_id="test-surface")
+        
+        # Add components using fluent API
+        surface.text(id="title", text="Welcome", usage_hint="h1")
+        surface.text(id="subtitle", text=PathBinding(path="/subtitle"), usage_hint="h2")
+        surface.button(
+            id="action-btn",
+            child="btn-text",
+            action_name="do_action",
+            action_context=[{"key": "id", "value": "123"}],
+            primary=True
+        )
+        surface.text(id="btn-text", text="Click Me")
+        surface.column(id="root", children=["title", "subtitle", "action-btn"])
+        
+        # Set data
+        surface.set_data("subtitle", "Hello World")
+        
+        # Generate messages
+        messages = surface.to_messages()
+        
+        # Verify structure
+        assert len(messages) == 3  # createSurface, updateComponents, updateDataModel
+        
+        # Verify createSurface
+        assert "createSurface" in messages[0]
+        assert messages[0]["createSurface"]["surfaceId"] == "test-surface"
+        
+        # Verify updateComponents
+        assert "updateComponents" in messages[1]
+        components = messages[1]["updateComponents"]["components"]
+        assert len(components) == 5  # title, subtitle, btn, btn-text, root
+        
+        # Verify updateDataModel
+        assert "updateDataModel" in messages[2]
+        assert messages[2]["updateDataModel"]["value"]["subtitle"] == "Hello World"
+        
+        # Verify JSON output
+        json_str = surface.to_json()
+        parsed = json.loads(json_str)
+        assert len(parsed) == 3
+
+    def test_a2ui_agent_render_workflow(self):
+        """Test A2UIAgent rendering workflow."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui import A2UIAgent
+        
+        agent = Agent(
+            name="TestAgent",
+            role="Test assistant",
+            goal="Help with testing"
+        )
+        
+        a2ui_agent = A2UIAgent(agent=agent, surface_id="agent-surface")
+        
+        # Render text
+        messages = a2ui_agent.render_text(
+            text="This is a test response",
+            title="Test Title"
+        )
+        
+        # Verify structure
+        assert len(messages) >= 2
+        assert "createSurface" in messages[0]
+        
+        # Verify JSON export
+        json_str = a2ui_agent.to_json()
+        parsed = json.loads(json_str)
+        assert isinstance(parsed, list)
+
+    def test_template_workflow(self):
+        """Test template-based workflow."""
+        from praisonaiagents.ui.a2ui import (
+            ChatTemplate,
+            ListTemplate,
+            FormTemplate,
+            DashboardTemplate,
+        )
+        
+        # Chat template
+        chat = ChatTemplate(surface_id="chat")
+        chat.add_user_message("Hello!")
+        chat.add_agent_message("Hi there!")
+        chat_messages = chat.to_messages()
+        assert len(chat_messages) >= 2
+        
+        # List template
+        list_template = ListTemplate(surface_id="list", title="Items")
+        list_template.add_item(title="Item 1", description="First")
+        list_template.add_item(title="Item 2", description="Second")
+        list_messages = list_template.to_messages()
+        assert len(list_messages) >= 2
+        
+        # Form template
+        form = FormTemplate(surface_id="form", title="Contact")
+        form.add_text_field(id="name", label="Name")
+        form.add_email_field(id="email", label="Email")
+        form.set_submit_action("submit", "Send")
+        form_messages = form.to_messages()
+        assert len(form_messages) >= 2
+        
+        # Dashboard template
+        dashboard = DashboardTemplate(surface_id="dashboard", title="Dashboard")
+        dashboard.add_panel(id="stats", title="Stats", content="100 items")
+        dashboard.add_panel(id="chart", title="Chart", content="[Chart]")
+        dashboard_messages = dashboard.to_messages()
+        assert len(dashboard_messages) >= 2
+
+    def test_a2a_integration(self):
+        """Test A2A protocol integration."""
+        from praisonaiagents.ui.a2ui import (
+            Surface,
+            create_a2ui_part,
+            is_a2ui_part,
+            A2UI_MIME_TYPE,
+        )
+        
+        # Create surface
+        surface = Surface(surface_id="a2a-test")
+        surface.text(id="msg", text="Hello from A2A")
+        surface.column(id="root", children=["msg"])
+        
+        # Get messages
+        messages = surface.to_messages()
+        
+        # Wrap in A2A DataPart
+        part = create_a2ui_part({"messages": messages})
+        
+        # Verify A2UI part
+        assert is_a2ui_part(part)
+        assert part.metadata["mimeType"] == A2UI_MIME_TYPE
+        assert "messages" in part.data
+        assert len(part.data["messages"]) >= 2
+
+    def test_data_binding_workflow(self):
+        """Test data binding with path references."""
+        from praisonaiagents.ui.a2ui import (
+            Surface,
+            PathBinding,
+            ChildrenTemplate,
+        )
+        
+        surface = Surface(surface_id="data-binding-test")
+        
+        # Add components with data binding
+        surface.text(id="title", text=PathBinding(path="/title"), usage_hint="h1")
+        surface.text(id="item-template", text=PathBinding(path="/name"))
+        
+        # Add list with template
+        surface.list(
+            id="items",
+            children=ChildrenTemplate(component_id="item-template", path="/items"),
+            direction="vertical"
+        )
+        
+        surface.column(id="root", children=["title", "items"])
+        
+        # Set data
+        surface.set_data("title", "My List")
+        surface.set_data("items", [
+            {"name": "Item 1"},
+            {"name": "Item 2"},
+            {"name": "Item 3"},
+        ])
+        
+        messages = surface.to_messages()
+        
+        # Verify data model
+        data_msg = next((m for m in messages if "updateDataModel" in m), None)
+        assert data_msg is not None
+        assert data_msg["updateDataModel"]["value"]["title"] == "My List"
+        assert len(data_msg["updateDataModel"]["value"]["items"]) == 3
+
+
+@pytest.mark.skipif(
+    not os.environ.get("OPENAI_API_KEY"),
+    reason="OPENAI_API_KEY not set"
+)
+class TestA2UIWithLLM:
+    """Tests that require LLM API calls."""
+
+    def test_agent_chat_and_render(self):
+        """Test agent chat followed by UI rendering."""
+        from praisonaiagents import Agent
+        from praisonaiagents.ui.a2ui import A2UIAgent
+        
+        agent = Agent(
+            name="UIAgent",
+            role="UI Generator",
+            goal="Generate helpful responses",
+            llm="gpt-4o-mini"
+        )
+        
+        a2ui_agent = A2UIAgent(agent=agent)
+        
+        # Chat with agent
+        response = a2ui_agent.chat("What is 2+2?")
+        
+        # Render response as UI
+        messages = a2ui_agent.render_text(response, title="Answer")
+        
+        assert len(messages) >= 2
+        assert "createSurface" in messages[0]
@@ -0,0 +1,228 @@
+"""
+Tests for A2UI Surface Builder
+
+TDD: Write tests first, then implement the Surface class.
+"""
+
+
+class TestSurface:
+    """Test Surface builder class."""
+
+    def test_surface_creation(self):
+        """Test Surface creation with ID and catalog."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        
+        assert surface.surface_id == "main"
+        assert surface.catalog_id is not None  # Should have default
+
+    def test_surface_with_custom_catalog(self):
+        """Test Surface with custom catalog ID."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(
+            surface_id="main",
+            catalog_id="https://custom.catalog/v1"
+        )
+        
+        assert surface.catalog_id == "https://custom.catalog/v1"
+
+    def test_add_component(self):
+        """Test adding a component to the surface."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        surface = Surface(surface_id="main")
+        text = TextComponent(id="title", text="Hello World", usage_hint="h1")
+        
+        surface.add(text)
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "title"
+
+    def test_add_multiple_components(self):
+        """Test adding multiple components."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent, ButtonComponent
+        
+        surface = Surface(surface_id="main")
+        surface.add(TextComponent(id="title", text="Hello"))
+        surface.add(ButtonComponent(id="btn", child="btn-text"))
+        
+        assert len(surface.components) == 2
+
+    def test_set_data(self):
+        """Test setting data model values."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.set_data("title", "Hello World")
+        surface.set_data("count", 42)
+        
+        assert surface.data["title"] == "Hello World"
+        assert surface.data["count"] == 42
+
+    def test_set_nested_data(self):
+        """Test setting nested data model values."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.set_data("user", {"name": "John", "age": 30})
+        
+        assert surface.data["user"]["name"] == "John"
+
+    def test_to_messages_creates_surface(self):
+        """Test to_messages generates CreateSurface message."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        surface = Surface(surface_id="main")
+        surface.add(TextComponent(id="title", text="Hello"))
+        
+        messages = surface.to_messages()
+        
+        assert len(messages) >= 1
+        assert "createSurface" in messages[0]
+        assert messages[0]["createSurface"]["surfaceId"] == "main"
+
+    def test_to_messages_includes_components(self):
+        """Test to_messages includes UpdateComponents message."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        surface = Surface(surface_id="main")
+        surface.add(TextComponent(id="title", text="Hello"))
+        
+        messages = surface.to_messages()
+        
+        # Should have createSurface and updateComponents
+        assert len(messages) >= 2
+        update_msg = next((m for m in messages if "updateComponents" in m), None)
+        assert update_msg is not None
+        assert len(update_msg["updateComponents"]["components"]) == 1
+
+    def test_to_messages_includes_data_model(self):
+        """Test to_messages includes UpdateDataModel message when data is set."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        surface = Surface(surface_id="main")
+        surface.add(TextComponent(id="title", text="Hello"))
+        surface.set_data("title", "Hello World")
+        
+        messages = surface.to_messages()
+        
+        # Should have createSurface, updateComponents, and updateDataModel
+        assert len(messages) == 3
+        data_msg = next((m for m in messages if "updateDataModel" in m), None)
+        assert data_msg is not None
+        assert data_msg["updateDataModel"]["value"]["title"] == "Hello World"
+
+    def test_to_json(self):
+        """Test to_json returns JSON string."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        import json
+        
+        surface = Surface(surface_id="main")
+        surface.add(TextComponent(id="title", text="Hello"))
+        
+        json_str = surface.to_json()
+        
+        # Should be valid JSON
+        parsed = json.loads(json_str)
+        assert isinstance(parsed, list)
+        assert len(parsed) >= 2
+
+
+class TestSurfaceChaining:
+    """Test Surface method chaining."""
+
+    def test_add_returns_self(self):
+        """Test add() returns self for chaining."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        surface = Surface(surface_id="main")
+        result = surface.add(TextComponent(id="title", text="Hello"))
+        
+        assert result is surface
+
+    def test_set_data_returns_self(self):
+        """Test set_data() returns self for chaining."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        result = surface.set_data("key", "value")
+        
+        assert result is surface
+
+    def test_fluent_api(self):
+        """Test fluent API for building surfaces."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        from praisonaiagents.ui.a2ui.types import TextComponent, ButtonComponent
+        
+        surface = (
+            Surface(surface_id="main")
+            .add(TextComponent(id="title", text="Hello"))
+            .add(ButtonComponent(id="btn", child="btn-text"))
+            .set_data("title", "Hello World")
+        )
+        
+        assert len(surface.components) == 2
+        assert surface.data["title"] == "Hello World"
+
+
+class TestSurfaceHelpers:
+    """Test Surface helper methods."""
+
+    def test_text_helper(self):
+        """Test text() helper method."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.text(id="title", text="Hello", usage_hint="h1")
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "title"
+
+    def test_button_helper(self):
+        """Test button() helper method."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.button(id="submit", child="submit-text", action_name="submit")
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "submit"
+
+    def test_card_helper(self):
+        """Test card() helper method."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.card(id="card-1", child="card-content")
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "card-1"
+
+    def test_row_helper(self):
+        """Test row() helper method."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.row(id="row-1", children=["col-1", "col-2"])
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "row-1"
+
+    def test_column_helper(self):
+        """Test column() helper method."""
+        from praisonaiagents.ui.a2ui.surface import Surface
+        
+        surface = Surface(surface_id="main")
+        surface.column(id="col-1", children=["item-1", "item-2"])
+        
+        assert len(surface.components) == 1
+        assert surface.components[0].id == "col-1"
@@ -0,0 +1,210 @@
+"""
+Tests for A2UI Templates
+
+TDD: Write tests first, then implement the templates.
+"""
+
+
+class TestChatTemplate:
+    """Test ChatTemplate for conversational UIs."""
+
+    def test_chat_template_creation(self):
+        """Test ChatTemplate creation."""
+        from praisonaiagents.ui.a2ui.templates import ChatTemplate
+        
+        template = ChatTemplate(surface_id="chat")
+        
+        assert template.surface_id == "chat"
+
+    def test_add_user_message(self):
+        """Test adding a user message."""
+        from praisonaiagents.ui.a2ui.templates import ChatTemplate
+        
+        template = ChatTemplate(surface_id="chat")
+        template.add_user_message("Hello!")
+        
+        assert len(template.messages) == 1
+        assert template.messages[0]["role"] == "user"
+        assert template.messages[0]["content"] == "Hello!"
+
+    def test_add_agent_message(self):
+        """Test adding an agent message."""
+        from praisonaiagents.ui.a2ui.templates import ChatTemplate
+        
+        template = ChatTemplate(surface_id="chat")
+        template.add_agent_message("Hi there!")
+        
+        assert len(template.messages) == 1
+        assert template.messages[0]["role"] == "agent"
+
+    def test_to_messages(self):
+        """Test generating A2UI messages."""
+        from praisonaiagents.ui.a2ui.templates import ChatTemplate
+        
+        template = ChatTemplate(surface_id="chat")
+        template.add_user_message("Hello!")
+        template.add_agent_message("Hi there!")
+        
+        messages = template.to_messages()
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2  # createSurface + updateComponents
+
+
+class TestListTemplate:
+    """Test ListTemplate for displaying lists of items."""
+
+    def test_list_template_creation(self):
+        """Test ListTemplate creation."""
+        from praisonaiagents.ui.a2ui.templates import ListTemplate
+        
+        template = ListTemplate(
+            surface_id="list",
+            title="My Items"
+        )
+        
+        assert template.surface_id == "list"
+        assert template.title == "My Items"
+
+    def test_add_item(self):
+        """Test adding an item to the list."""
+        from praisonaiagents.ui.a2ui.templates import ListTemplate
+        
+        template = ListTemplate(surface_id="list", title="Items")
+        template.add_item(title="Item 1", description="First item")
+        
+        assert len(template.items) == 1
+        assert template.items[0]["title"] == "Item 1"
+
+    def test_add_item_with_image(self):
+        """Test adding an item with an image."""
+        from praisonaiagents.ui.a2ui.templates import ListTemplate
+        
+        template = ListTemplate(surface_id="list", title="Items")
+        template.add_item(
+            title="Item 1",
+            description="First item",
+            image_url="https://example.com/image.jpg"
+        )
+        
+        assert template.items[0]["image_url"] == "https://example.com/image.jpg"
+
+    def test_to_messages(self):
+        """Test generating A2UI messages."""
+        from praisonaiagents.ui.a2ui.templates import ListTemplate
+        
+        template = ListTemplate(surface_id="list", title="Items")
+        template.add_item(title="Item 1", description="First")
+        template.add_item(title="Item 2", description="Second")
+        
+        messages = template.to_messages()
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2
+
+
+class TestFormTemplate:
+    """Test FormTemplate for data collection forms."""
+
+    def test_form_template_creation(self):
+        """Test FormTemplate creation."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(
+            surface_id="form",
+            title="Contact Form"
+        )
+        
+        assert template.surface_id == "form"
+        assert template.title == "Contact Form"
+
+    def test_add_text_field(self):
+        """Test adding a text field."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(surface_id="form", title="Form")
+        template.add_text_field(id="name", label="Name")
+        
+        assert len(template.fields) == 1
+        assert template.fields[0]["id"] == "name"
+        assert template.fields[0]["type"] == "text"
+
+    def test_add_number_field(self):
+        """Test adding a number field."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(surface_id="form", title="Form")
+        template.add_number_field(id="age", label="Age")
+        
+        assert template.fields[0]["type"] == "number"
+
+    def test_add_email_field(self):
+        """Test adding an email field."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(surface_id="form", title="Form")
+        template.add_email_field(id="email", label="Email")
+        
+        assert template.fields[0]["type"] == "email"
+
+    def test_set_submit_action(self):
+        """Test setting submit action."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(surface_id="form", title="Form")
+        template.set_submit_action("submit_form", "Send")
+        
+        assert template.submit_action == "submit_form"
+        assert template.submit_label == "Send"
+
+    def test_to_messages(self):
+        """Test generating A2UI messages."""
+        from praisonaiagents.ui.a2ui.templates import FormTemplate
+        
+        template = FormTemplate(surface_id="form", title="Form")
+        template.add_text_field(id="name", label="Name")
+        template.add_email_field(id="email", label="Email")
+        
+        messages = template.to_messages()
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2
+
+
+class TestDashboardTemplate:
+    """Test DashboardTemplate for multi-panel dashboards."""
+
+    def test_dashboard_template_creation(self):
+        """Test DashboardTemplate creation."""
+        from praisonaiagents.ui.a2ui.templates import DashboardTemplate
+        
+        template = DashboardTemplate(
+            surface_id="dashboard",
+            title="My Dashboard"
+        )
+        
+        assert template.surface_id == "dashboard"
+        assert template.title == "My Dashboard"
+
+    def test_add_panel(self):
+        """Test adding a panel."""
+        from praisonaiagents.ui.a2ui.templates import DashboardTemplate
+        
+        template = DashboardTemplate(surface_id="dashboard", title="Dashboard")
+        template.add_panel(id="panel-1", title="Panel 1", content="Some content")
+        
+        assert len(template.panels) == 1
+        assert template.panels[0]["id"] == "panel-1"
+
+    def test_to_messages(self):
+        """Test generating A2UI messages."""
+        from praisonaiagents.ui.a2ui.templates import DashboardTemplate
+        
+        template = DashboardTemplate(surface_id="dashboard", title="Dashboard")
+        template.add_panel(id="panel-1", title="Panel 1", content="Content 1")
+        template.add_panel(id="panel-2", title="Panel 2", content="Content 2")
+        
+        messages = template.to_messages()
+        
+        assert isinstance(messages, list)
+        assert len(messages) >= 2
@@ -0,0 +1,318 @@
+"""
+Tests for A2UI Types Module
+
+TDD: Write tests first, then implement the types.
+"""
+
+
+
+class TestA2UIMessageTypes:
+    """Test A2UI message types: CreateSurface, UpdateComponents, UpdateDataModel, DeleteSurface."""
+
+    def test_create_surface_message(self):
+        """Test CreateSurface message creation."""
+        from praisonaiagents.ui.a2ui.types import CreateSurfaceMessage
+        
+        msg = CreateSurfaceMessage(
+            surface_id="main",
+            catalog_id="https://a2ui.dev/standard"
+        )
+        
+        assert msg.surface_id == "main"
+        assert msg.catalog_id == "https://a2ui.dev/standard"
+        
+        # Test serialization
+        data = msg.to_dict()
+        assert "createSurface" in data
+        assert data["createSurface"]["surfaceId"] == "main"
+        assert data["createSurface"]["catalogId"] == "https://a2ui.dev/standard"
+
+    def test_update_components_message(self):
+        """Test UpdateComponents message creation."""
+        from praisonaiagents.ui.a2ui.types import UpdateComponentsMessage, TextComponent
+        
+        text = TextComponent(id="title", text="Hello World", usage_hint="h1")
+        msg = UpdateComponentsMessage(
+            surface_id="main",
+            components=[text]
+        )
+        
+        assert msg.surface_id == "main"
+        assert len(msg.components) == 1
+        
+        # Test serialization
+        data = msg.to_dict()
+        assert "updateComponents" in data
+        assert data["updateComponents"]["surfaceId"] == "main"
+        assert len(data["updateComponents"]["components"]) == 1
+
+    def test_update_data_model_message(self):
+        """Test UpdateDataModel message creation."""
+        from praisonaiagents.ui.a2ui.types import UpdateDataModelMessage
+        
+        msg = UpdateDataModelMessage(
+            surface_id="main",
+            path="/",
+            op="replace",
+            value={"title": "Hello", "items": []}
+        )
+        
+        assert msg.surface_id == "main"
+        assert msg.path == "/"
+        assert msg.op == "replace"
+        assert msg.value == {"title": "Hello", "items": []}
+        
+        # Test serialization
+        data = msg.to_dict()
+        assert "updateDataModel" in data
+        assert data["updateDataModel"]["surfaceId"] == "main"
+
+    def test_delete_surface_message(self):
+        """Test DeleteSurface message creation."""
+        from praisonaiagents.ui.a2ui.types import DeleteSurfaceMessage
+        
+        msg = DeleteSurfaceMessage(surface_id="main")
+        
+        assert msg.surface_id == "main"
+        
+        # Test serialization
+        data = msg.to_dict()
+        assert "deleteSurface" in data
+        assert data["deleteSurface"]["surfaceId"] == "main"
+
+
+class TestA2UIComponentTypes:
+    """Test A2UI component types."""
+
+    def test_text_component(self):
+        """Test Text component creation."""
+        from praisonaiagents.ui.a2ui.types import TextComponent
+        
+        text = TextComponent(id="title", text="Hello World", usage_hint="h1")
+        
+        assert text.id == "title"
+        assert text.text == "Hello World"
+        assert text.usage_hint == "h1"
+        
+        # Test serialization
+        data = text.to_dict()
+        assert data["id"] == "title"
+        assert data["component"] == "Text"
+        assert data["text"] == "Hello World"
+        assert data["usageHint"] == "h1"
+
+    def test_text_component_with_path(self):
+        """Test Text component with data binding path."""
+        from praisonaiagents.ui.a2ui.types import TextComponent, PathBinding
+        
+        text = TextComponent(id="title", text=PathBinding(path="/title"))
+        
+        data = text.to_dict()
+        assert data["text"] == {"path": "/title"}
+
+    def test_image_component(self):
+        """Test Image component creation."""
+        from praisonaiagents.ui.a2ui.types import ImageComponent
+        
+        img = ImageComponent(
+            id="hero",
+            url="https://example.com/image.jpg",
+            fit="cover",
+            usage_hint="header"
+        )
+        
+        assert img.id == "hero"
+        assert img.url == "https://example.com/image.jpg"
+        assert img.fit == "cover"
+        
+        data = img.to_dict()
+        assert data["component"] == "Image"
+        assert data["url"] == "https://example.com/image.jpg"
+
+    def test_button_component(self):
+        """Test Button component creation."""
+        from praisonaiagents.ui.a2ui.types import ButtonComponent, Action, ActionContext
+        
+        action = Action(
+            name="submit",
+            context=[
+                ActionContext(key="value", value="test")
+            ]
+        )
+        btn = ButtonComponent(
+            id="submit-btn",
+            child="submit-text",
+            primary=True,
+            action=action
+        )
+        
+        assert btn.id == "submit-btn"
+        assert btn.child == "submit-text"
+        assert btn.primary is True
+        
+        data = btn.to_dict()
+        assert data["component"] == "Button"
+        assert data["action"]["name"] == "submit"
+
+    def test_card_component(self):
+        """Test Card component creation."""
+        from praisonaiagents.ui.a2ui.types import CardComponent
+        
+        card = CardComponent(id="card-1", child="card-content")
+        
+        assert card.id == "card-1"
+        assert card.child == "card-content"
+        
+        data = card.to_dict()
+        assert data["component"] == "Card"
+        assert data["child"] == "card-content"
+
+    def test_row_component(self):
+        """Test Row component creation."""
+        from praisonaiagents.ui.a2ui.types import RowComponent
+        
+        row = RowComponent(id="row-1", children=["col-1", "col-2"])
+        
+        assert row.id == "row-1"
+        assert row.children == ["col-1", "col-2"]
+        
+        data = row.to_dict()
+        assert data["component"] == "Row"
+        assert data["children"] == ["col-1", "col-2"]
+
+    def test_column_component(self):
+        """Test Column component creation."""
+        from praisonaiagents.ui.a2ui.types import ColumnComponent
+        
+        col = ColumnComponent(id="col-1", children=["item-1", "item-2"])
+        
+        assert col.id == "col-1"
+        assert col.children == ["item-1", "item-2"]
+        
+        data = col.to_dict()
+        assert data["component"] == "Column"
+
+    def test_list_component(self):
+        """Test List component creation."""
+        from praisonaiagents.ui.a2ui.types import ListComponent, ChildrenTemplate
+        
+        template = ChildrenTemplate(component_id="item-template", path="/items")
+        lst = ListComponent(id="item-list", direction="vertical", children=template)
+        
+        assert lst.id == "item-list"
+        assert lst.direction == "vertical"
+        
+        data = lst.to_dict()
+        assert data["component"] == "List"
+        assert data["children"]["componentId"] == "item-template"
+        assert data["children"]["path"] == "/items"
+
+    def test_text_field_component(self):
+        """Test TextField component creation."""
+        from praisonaiagents.ui.a2ui.types import TextFieldComponent, PathBinding
+        
+        field = TextFieldComponent(
+            id="name-field",
+            label="Name",
+            text=PathBinding(path="/name"),
+            field_type="text"
+        )
+        
+        assert field.id == "name-field"
+        assert field.label == "Name"
+        
+        data = field.to_dict()
+        assert data["component"] == "TextField"
+        assert data["label"] == "Name"
+        assert data["text"] == {"path": "/name"}
+
+    def test_checkbox_component(self):
+        """Test CheckBox component creation."""
+        from praisonaiagents.ui.a2ui.types import CheckBoxComponent, PathBinding
+        
+        cb = CheckBoxComponent(
+            id="agree-cb",
+            label="I agree",
+            checked=PathBinding(path="/agreed")
+        )
+        
+        data = cb.to_dict()
+        assert data["component"] == "CheckBox"
+        assert data["label"] == "I agree"
+
+    def test_slider_component(self):
+        """Test Slider component creation."""
+        from praisonaiagents.ui.a2ui.types import SliderComponent
+        
+        slider = SliderComponent(
+            id="volume",
+            min_value=0,
+            max_value=100,
+            value=50
+        )
+        
+        data = slider.to_dict()
+        assert data["component"] == "Slider"
+        assert data["min"] == 0
+        assert data["max"] == 100
+
+
+class TestDataBindingTypes:
+    """Test data binding types."""
+
+    def test_path_binding(self):
+        """Test PathBinding for data model references."""
+        from praisonaiagents.ui.a2ui.types import PathBinding
+        
+        path = PathBinding(path="/user/name")
+        
+        assert path.path == "/user/name"
+        assert path.to_dict() == {"path": "/user/name"}
+
+    def test_string_or_path_literal(self):
+        """Test StringOrPath with literal string."""
+        from praisonaiagents.ui.a2ui.types import resolve_string_or_path
+        
+        result = resolve_string_or_path("Hello")
+        assert result == "Hello"
+
+    def test_string_or_path_binding(self):
+        """Test StringOrPath with path binding."""
+        from praisonaiagents.ui.a2ui.types import resolve_string_or_path, PathBinding
+        
+        result = resolve_string_or_path(PathBinding(path="/title"))
+        assert result == {"path": "/title"}
+
+
+class TestActionTypes:
+    """Test action types for button events."""
+
+    def test_action_creation(self):
+        """Test Action creation."""
+        from praisonaiagents.ui.a2ui.types import Action, ActionContext
+        
+        action = Action(
+            name="book_restaurant",
+            context=[
+                ActionContext(key="restaurantName", value="The Fancy Place"),
+                ActionContext(key="address", value="123 Main St")
+            ]
+        )
+        
+        assert action.name == "book_restaurant"
+        assert len(action.context) == 2
+        
+        data = action.to_dict()
+        assert data["name"] == "book_restaurant"
+        assert len(data["context"]) == 2
+        assert data["context"][0]["key"] == "restaurantName"
+
+    def test_action_context_with_path(self):
+        """Test ActionContext with path binding."""
+        from praisonaiagents.ui.a2ui.types import ActionContext, PathBinding
+        
+        ctx = ActionContext(key="name", value=PathBinding(path="/restaurant/name"))
+        
+        data = ctx.to_dict()
+        assert data["key"] == "name"
+        assert data["value"] == {"path": "/restaurant/name"}
@@ -0,0 +1,217 @@
+"""
+Unit tests for configurable max_file_chars in MentionsParser.
+
+TDD approach: Write tests first, then implement.
+"""
+
+import os
+import pytest
+import tempfile
+from pathlib import Path
+from unittest.mock import patch
+
+
+class TestMentionsParserConfigurableLimit:
+    """Test suite for configurable file truncation limit."""
+    
+    @pytest.fixture
+    def temp_workspace(self):
+        """Create a temporary workspace with test files."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            yield Path(tmpdir)
+    
+    @pytest.fixture
+    def small_file(self, temp_workspace):
+        """Create a small test file (1KB)."""
+        file_path = temp_workspace / "small.py"
+        content = "# Small file\n" + "x = 1\n" * 100  # ~700 chars
+        file_path.write_text(content)
+        return file_path
+    
+    @pytest.fixture
+    def large_file(self, temp_workspace):
+        """Create a large test file (100KB)."""
+        file_path = temp_workspace / "large.py"
+        content = "# Large file\n" + "x = 'a' * 100\n" * 7000  # ~100KB
+        file_path.write_text(content)
+        return file_path
+    
+    @pytest.fixture
+    def huge_file(self, temp_workspace):
+        """Create a huge test file (600KB)."""
+        file_path = temp_workspace / "huge.py"
+        content = "# Huge file\n" + "x = 'a' * 100\n" * 42000  # ~600KB
+        file_path.write_text(content)
+        return file_path
+
+    # ===== Test 1.1: Default value (500K) =====
+    def test_default_max_file_chars_is_500k(self, temp_workspace):
+        """Default max_file_chars should be 500,000."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(workspace_path=str(temp_workspace))
+        assert parser.max_file_chars == 500000
+    
+    # ===== Test 1.2: Custom value via constructor =====
+    def test_custom_max_file_chars_via_constructor(self, temp_workspace):
+        """max_file_chars should be configurable via constructor."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=100000
+        )
+        assert parser.max_file_chars == 100000
+    
+    def test_custom_max_file_chars_zero_means_no_limit(self, temp_workspace):
+        """max_file_chars=0 should mean no truncation."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=0
+        )
+        assert parser.max_file_chars == 0
+    
+    # ===== Test 1.3: Environment variable override =====
+    def test_env_var_override(self, temp_workspace):
+        """PRAISON_MAX_FILE_CHARS env var should override default."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        with patch.dict(os.environ, {'PRAISON_MAX_FILE_CHARS': '200000'}):
+            # Need to reimport to pick up env var
+            parser = MentionsParser(workspace_path=str(temp_workspace))
+            assert parser.max_file_chars == 200000
+    
+    def test_constructor_takes_precedence_over_env_var(self, temp_workspace):
+        """Constructor value should take precedence over env var."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        with patch.dict(os.environ, {'PRAISON_MAX_FILE_CHARS': '200000'}):
+            parser = MentionsParser(
+                workspace_path=str(temp_workspace),
+                max_file_chars=100000
+            )
+            assert parser.max_file_chars == 100000
+    
+    # ===== Test 1.4: No-limit mode =====
+    def test_no_truncation_when_limit_is_zero(self, temp_workspace, huge_file):
+        """File should not be truncated when max_file_chars=0."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=0
+        )
+        
+        context, _ = parser.process(f"@file:{huge_file.name} explain")
+        
+        # Should contain full content, no truncation message
+        assert "(truncated)" not in context
+        # Should have the full file content
+        original_size = huge_file.read_text().__len__()
+        # Context includes header and code fence, so check it's close
+        assert len(context) >= original_size
+    
+    # ===== Test 1.5: Truncation behavior =====
+    def test_truncation_at_custom_limit(self, temp_workspace, large_file):
+        """File should be truncated at custom limit."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=10000  # 10KB limit
+        )
+        
+        context, _ = parser.process(f"@file:{large_file.name} explain")
+        
+        # Should be truncated
+        assert "(truncated)" in context
+        # Content should be around the limit (plus header/fence overhead)
+        assert len(context) < 15000  # Some overhead for markdown
+    
+    def test_no_truncation_when_file_under_limit(self, temp_workspace, small_file):
+        """Small files should not be truncated."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=500000
+        )
+        
+        context, _ = parser.process(f"@file:{small_file.name} explain")
+        
+        # Should NOT be truncated
+        assert "(truncated)" not in context
+    
+    def test_truncation_warning_logged(self, temp_workspace, large_file, caplog):
+        """Warning should be logged when file is truncated."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        import logging
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=10000,
+            verbose=1
+        )
+        
+        with caplog.at_level(logging.WARNING):
+            parser.process(f"@file:{large_file.name} explain")
+        
+        # Should log a warning about truncation
+        assert any("truncat" in record.message.lower() for record in caplog.records)
+    
+    # ===== Test: URL truncation also uses configurable limit =====
+    def test_url_truncation_uses_same_limit(self, temp_workspace):
+        """URL content should also respect max_file_chars."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        parser = MentionsParser(
+            workspace_path=str(temp_workspace),
+            max_file_chars=100000
+        )
+        
+        # URL truncation should use the same limit
+        assert parser.max_file_chars == 100000
+    
+    # ===== Test: Backward compatibility =====
+    def test_backward_compatible_no_args(self, temp_workspace):
+        """Parser should work without max_file_chars argument."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        
+        # Should not raise any errors
+        parser = MentionsParser(workspace_path=str(temp_workspace))
+        assert hasattr(parser, 'max_file_chars')
+    
+    # ===== Test: Performance - no impact on small files =====
+    def test_performance_small_file(self, temp_workspace, small_file):
+        """Processing small files should be fast."""
+        from praisonaiagents.tools.mentions import MentionsParser
+        import time
+        
+        parser = MentionsParser(workspace_path=str(temp_workspace))
+        
+        start = time.time()
+        for _ in range(100):
+            parser.process(f"@file:{small_file.name} explain")
+        elapsed = time.time() - start
+        
+        # 100 iterations should complete in under 1 second
+        assert elapsed < 1.0, f"Performance regression: {elapsed}s for 100 iterations"
+
+
+class TestProcessMentionsFunction:
+    """Test the convenience function."""
+    
+    def test_process_mentions_uses_default_limit(self):
+        """process_mentions function should use default limit."""
+        from praisonaiagents.tools.mentions import process_mentions
+        
+        # The function should create a parser with default settings
+        # Just verify it works without errors
+        context, cleaned = process_mentions("hello world")
+        assert cleaned == "hello world"
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])
@@ -2422,7 +2422,7 @@ wheels = [

 [[package]]
 name = "praisonaiagents"
-version = "0.1.15"
+version = "0.1.21"
 source = { editable = "." }
 dependencies = [
    { name = "aiohttp" },
@@ -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">
@@ -60,6 +63,7 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
  - [Planning & Workflows](#planning--workflows)
  - [Specialised Agents](#specialised-agents)
  - [MCP Protocol](#mcp-protocol)
+  - [A2A & A2UI Protocols](#a2a--a2ui-protocols)
  - [Safety & Control](#safety--control)
  - [Developer Tools](#developer-tools)
 - [📊 Process Types & Patterns](#-process-types--patterns)
@@ -187,7 +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) |
+| **💻 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) |
@@ -205,6 +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) |
@@ -224,7 +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) |
@@ -240,12 +252,22 @@ npm install praisonai
 | 🪝 Hooks | [Example](#9-hooks) | [📖](https://docs.praison.ai/features/hooks) |
 | 📈 Telemetry | [Example](examples/python/telemetry/production-telemetry-example.py) | [📖](https://docs.praison.ai/features/telemetry) |
 | 📹 Camera Integration | [Example](examples/python/camera/) | [📖](https://docs.praison.ai/features/camera-integration) |
-| 📄 Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/cli/docs) |
-| 🔌 MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/cli/mcp) |
-| 💬 AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/cli/commit) |
-| @ @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) |
+| 📄 Project Docs (.praison/docs/) | [Example](#docs-cli) | [📖](https://docs.praison.ai/docs/cli/docs) |
+| 🔌 MCP Config Management | [Example](#mcp-config-cli) | [📖](https://docs.praison.ai/docs/cli/mcp) |
+| 💬 AI Commit Messages | [Example](#ai-commit-cli) | [📖](https://docs.praison.ai/docs/cli/commit) |
+| @ @Mentions in Prompts | [Example](#mentions-in-prompts) | [📖](https://docs.praison.ai/docs/cli/mentions) |
+| 💾 Auto-Save Sessions | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| 📜 History in Context | [Example](#session-management-python) | [📖](https://docs.praison.ai/docs/cli/session) |
+| **🖥️ CLI Features** | | |
+| ↳ Slash Commands | [Example](examples/python/cli/slash_commands_example.py) | [📖](https://docs.praison.ai/docs/cli/slash-commands) |
+| ↳ Autonomy Modes | [Example](examples/python/cli/autonomy_modes_example.py) | [📖](https://docs.praison.ai/docs/cli/autonomy-modes) |
+| ↳ Cost Tracking | [Example](examples/python/cli/cost_tracking_example.py) | [📖](https://docs.praison.ai/docs/cli/cost-tracking) |
+| ↳ Repository Map | [Example](examples/python/cli/repo_map_example.py) | [📖](https://docs.praison.ai/docs/cli/repo-map) |
+| ↳ Interactive TUI | [Example](examples/python/cli/interactive_tui_example.py) | [📖](https://docs.praison.ai/docs/cli/interactive-tui) |
+| ↳ Git Integration | [Example](examples/python/cli/git_integration_example.py) | [📖](https://docs.praison.ai/docs/cli/git-integration) |
+| ↳ Sandbox Execution | [Example](examples/python/cli/sandbox_execution_example.py) | [📖](https://docs.praison.ai/docs/cli/sandbox-execution) |
+| **⏰ 24/7 Scheduling** | | |
+| ↳ Agent Scheduler | [Example](examples/python/scheduled_agents/news_checker_live.py) | [📖](https://docs.praison.ai/docs/cli/scheduler) |

 ---

@@ -952,6 +974,32 @@ export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
 praisonai --auto create a movie script about Robots in Mars
 ```

+### Interactive Mode CLI:
+```bash
+# Start interactive terminal mode (inspired by Gemini CLI, Codex CLI, Claude Code)
+praisonai --interactive
+praisonai -i
+
+# Features:
+# - Streaming responses (no boxes)
+# - Built-in tools: read_file, write_file, list_files, execute_command, internet_search
+# - Slash commands: /help, /exit, /tools, /clear
+
+# Chat mode - single prompt with interactive style (for testing/scripting)
+# Use --chat (or --chat-mode for backward compatibility)
+praisonai "list files in current folder" --chat
+praisonai "search the web for AI news" --chat
+praisonai "read README.md" --chat
+```
+
+### Chat UI (Web Interface):
+```bash
+# Start web-based Chainlit chat interface (requires praisonai[chat])
+pip install "praisonai[chat]"
+praisonai chat
+# Opens browser at http://localhost:8084
+```
+
 ### Query Rewriting (works with any command):
 ```bash
 # Rewrite query for better results (uses QueryRewriterAgent)
@@ -1012,6 +1060,20 @@ praisonai "Complex analysis task" --planning --planning-reasoning
 praisonai "Task" --planning --auto-approve-plan
 ```

+### Tool Approval CLI:
+```bash
+# Auto-approve ALL tool executions (use with caution!)
+praisonai "run ls command" --trust
+
+# Auto-approve tools up to a risk level (prompt for higher)
+# Levels: low, medium, high, critical
+praisonai "write to file" --approve-level high  # Prompts for critical tools only
+praisonai "task" --approve-level medium         # Prompts for high and critical
+
+# Default behavior (no flags): prompts for all dangerous tools
+praisonai "run shell command"  # Will prompt for approval
+```
+
 ### Memory CLI:
 ```bash
 # Enable memory for agent (persists across sessions)
@@ -1118,6 +1180,15 @@ 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
 ```
@@ -1127,7 +1198,7 @@ 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) |
@@ -1173,6 +1244,64 @@ praisonai "Analyze this data" --metrics
 praisonai "Complex task" --metrics --planning
 ```

+### Scheduler CLI:
+
+Run agents 24/7 with built-in safety features. Two modes available:
+
+**Direct Prompt Mode (Simple):**
+```bash
+# No YAML needed - just provide your task
+praisonai schedule "Check AI news and summarize" --interval hourly
+
+# With options
+praisonai schedule "Monitor server logs" \
+  --interval "*/30m" \
+  --timeout 120 \
+  --max-cost 2.00 \
+  --verbose
+```
+
+**YAML Mode (Advanced):**
+```bash
+# Use agents.yaml for complex configurations
+praisonai schedule agents.yaml
+
+# With overrides
+praisonai schedule agents.yaml \
+  --interval "*/15m" \
+  --timeout 60 \
+  --max-cost 1.00
+
+# Stop: Press Ctrl+C
+```
+
+**agents.yaml with schedule:**
+```yaml
+framework: praisonai
+
+agents:
+  - name: "AI News Monitor"
+    instructions: "Search and summarize AI news"
+    tools:
+      - search_tool
+
+task: "Search for latest AI news"
+
+schedule:
+  interval: "hourly"         # hourly, daily, */30m, */6h
+  max_retries: 3             # Retry on failure
+  run_immediately: true      # Run once on start
+  timeout: 60                # Max 60s per execution
+  max_cost: 1.00             # Stop after $1.00 spent
+```
+
+**Features:**
+- ⏱️ Timeout protection (prevent runaway executions)
+- 💰 Cost monitoring with budget limits
+- 📊 Real-time statistics (success rate, cost, runtime)
+- 🔄 Automatic retry with exponential backoff
+- 🛡️ Auto-stops when budget reached
+
 ### Image Processing CLI:
 ```bash
 # Process images with vision-based tasks
@@ -1359,8 +1488,13 @@ 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
@@ -1412,13 +1546,31 @@ praisonai mcp help

 ### AI Commit CLI:
 ```bash
-# Generate AI commit message for staged changes
+# Full auto mode: stage all, security check, commit, and push
+praisonai commit -a
+
+# Interactive mode (requires git add first)
 praisonai commit

-# Generate, commit, and push
+# Interactive with auto-push
 praisonai commit --push
+
+# Skip security check (not recommended)
+praisonai commit -a --no-verify
 ```

+**Features:**
+- 🤖 AI-generated conventional commit messages
+- 🔒 Built-in security scanning (API keys, passwords, secrets, sensitive files)
+- 📦 Auto-staging with `-a` flag
+- 🚀 Auto-push in full auto mode
+- ✏️ Edit message before commit in interactive mode
+
+**Security Detection:**
+- API keys, secrets, tokens (AWS, GitHub, GitLab, Slack)
+- Passwords and private keys
+- Sensitive files (`.env`, `id_rsa`, `.pem`, `.key`, etc.)
+
 ### Serve CLI (API Server):
 ```bash
 # Start API server for agents defined in YAML
@@ -1449,6 +1601,55 @@ 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
@@ -1628,36 +1829,78 @@ server.run()  # stdio for Claude Desktop
 | Security | Origin validation, DNS rebinding prevention |
 | WebSocket | Auto-reconnect with exponential backoff |

+## A2A (Agent2Agent Protocol)
+
+PraisonAI supports the [A2A Protocol](https://a2a-protocol.org) for agent-to-agent communication, enabling your agents to be discovered and collaborate with other AI agents.
+
+### A2A Server (Expose Agent as A2A Server)
+```python
+from praisonaiagents import Agent, A2A
+from fastapi import FastAPI
+
+# Create an agent with tools
+def search_web(query: str) -> str:
+    """Search the web for information."""
+    return f"Results for: {query}"
+
+agent = Agent(
+    name="Research Assistant",
+    role="Research Analyst",
+    goal="Help users research topics",
+    tools=[search_web]
+)
+
+# Expose as A2A Server
+a2a = A2A(agent=agent, url="http://localhost:8000/a2a")
+
+app = FastAPI()
+app.include_router(a2a.get_router())
+
+# Run: uvicorn app:app --reload
+# Agent Card: GET /.well-known/agent.json
+# Status: GET /status
+```
+
+### A2A Features
+| Feature | Description |
+|---------|-------------|
+| Agent Card | JSON metadata for agent discovery |
+| Skills Extraction | Auto-generate skills from tools |
+| Task Management | Stateful task lifecycle |
+| Streaming | SSE streaming for real-time updates |
+
+> **Documentation**: [docs.praison.ai/a2a](https://docs.praison.ai/a2a) | **Examples**: [examples/python/a2a](https://github.com/MervinPraison/PraisonAI/tree/main/examples/python/a2a)
+
 ## CLI Features

 | Feature | Docs |
 |---------|:----:|
-| 🔄 Query Rewrite - RAG optimization | [📖](https://docs.praison.ai/cli/query-rewrite) |
-| 🔬 Deep Research - Automated research | [📖](https://docs.praison.ai/cli/deep-research) |
-| 📋 Planning - Step-by-step execution | [📖](https://docs.praison.ai/cli/planning) |
-| 💾 Memory - Persistent agent memory | [📖](https://docs.praison.ai/cli/memory) |
-| 📜 Rules - Auto-discovered instructions | [📖](https://docs.praison.ai/cli/rules) |
-| 🔄 Workflow - Multi-step workflows | [📖](https://docs.praison.ai/cli/workflow) |
-| 🪝 Hooks - Event-driven actions | [📖](https://docs.praison.ai/cli/hooks) |
-| 🧠 Claude Memory - Anthropic memory tool | [📖](https://docs.praison.ai/cli/claude-memory) |
-| 🛡️ Guardrail - Output validation | [📖](https://docs.praison.ai/cli/guardrail) |
-| 📊 Metrics - Token usage tracking | [📖](https://docs.praison.ai/cli/metrics) |
-| 🖼️ Image - Vision processing | [📖](https://docs.praison.ai/cli/image) |
-| 📡 Telemetry - Usage monitoring | [📖](https://docs.praison.ai/cli/telemetry) |
-| 🔌 MCP - Model Context Protocol | [📖](https://docs.praison.ai/cli/mcp) |
-| ⚡ Fast Context - Codebase search | [📖](https://docs.praison.ai/cli/fast-context) |
-| 📚 Knowledge - RAG management | [📖](https://docs.praison.ai/cli/knowledge) |
-| 💬 Session - Conversation management | [📖](https://docs.praison.ai/cli/session) |
-| 🔧 Tools - Tool discovery | [📖](https://docs.praison.ai/cli/tools) |
-| 🤝 Handoff - Agent delegation | [📖](https://docs.praison.ai/cli/handoff) |
-| 🧠 Auto Memory - Memory extraction | [📖](https://docs.praison.ai/cli/auto-memory) |
-| 📋 Todo - Task management | [📖](https://docs.praison.ai/cli/todo) |
-| 🎯 Router - Smart model selection | [📖](https://docs.praison.ai/cli/router) |
-| 📈 Flow Display - Visual workflow | [📖](https://docs.praison.ai/cli/flow-display) |
-| ✨ Prompt Expansion - Detailed prompts | [📖](https://docs.praison.ai/cli/prompt-expansion) |
-| 🌐 Web Search - Real-time search | [📖](https://docs.praison.ai/cli/web-search) |
-| 📥 Web Fetch - URL content retrieval | [📖](https://docs.praison.ai/cli/web-fetch) |
-| 💾 Prompt Caching - Cost reduction | [📖](https://docs.praison.ai/cli/prompt-caching) |
+| 🔄 Query Rewrite - RAG optimization | [📖](https://docs.praison.ai/docs/cli/query-rewrite) |
+| 🔬 Deep Research - Automated research | [📖](https://docs.praison.ai/docs/cli/deep-research) |
+| 📋 Planning - Step-by-step execution | [📖](https://docs.praison.ai/docs/cli/planning) |
+| 💾 Memory - Persistent agent memory | [📖](https://docs.praison.ai/docs/cli/memory) |
+| 📜 Rules - Auto-discovered instructions | [📖](https://docs.praison.ai/docs/cli/rules) |
+| 🔄 Workflow - Multi-step workflows | [📖](https://docs.praison.ai/docs/cli/workflow) |
+| 🪝 Hooks - Event-driven actions | [📖](https://docs.praison.ai/docs/cli/hooks) |
+| 🧠 Claude Memory - Anthropic memory tool | [📖](https://docs.praison.ai/docs/cli/claude-memory) |
+| 🛡️ Guardrail - Output validation | [📖](https://docs.praison.ai/docs/cli/guardrail) |
+| 📊 Metrics - Token usage tracking | [📖](https://docs.praison.ai/docs/cli/metrics) |
+| 🖼️ Image - Vision processing | [📖](https://docs.praison.ai/docs/cli/image) |
+| 📡 Telemetry - Usage monitoring | [📖](https://docs.praison.ai/docs/cli/telemetry) |
+| 🔌 MCP - Model Context Protocol | [📖](https://docs.praison.ai/docs/cli/mcp) |
+| ⚡ Fast Context - Codebase search | [📖](https://docs.praison.ai/docs/cli/fast-context) |
+| 📚 Knowledge - RAG management | [📖](https://docs.praison.ai/docs/cli/knowledge) |
+| 💬 Session - Conversation management | [📖](https://docs.praison.ai/docs/cli/session) |
+| 🔧 Tools - Tool discovery | [📖](https://docs.praison.ai/docs/cli/tools) |
+| 🤝 Handoff - Agent delegation | [📖](https://docs.praison.ai/docs/cli/handoff) |
+| 🧠 Auto Memory - Memory extraction | [📖](https://docs.praison.ai/docs/cli/auto-memory) |
+| 📋 Todo - Task management | [📖](https://docs.praison.ai/docs/cli/todo) |
+| 🎯 Router - Smart model selection | [📖](https://docs.praison.ai/docs/cli/router) |
+| 📈 Flow Display - Visual workflow | [📖](https://docs.praison.ai/docs/cli/flow-display) |
+| ✨ Prompt Expansion - Detailed prompts | [📖](https://docs.praison.ai/docs/cli/prompt-expansion) |
+| 🌐 Web Search - Real-time search | [📖](https://docs.praison.ai/docs/cli/web-search) |
+| 📥 Web Fetch - URL content retrieval | [📖](https://docs.praison.ai/docs/cli/web-fetch) |
+| 💾 Prompt Caching - Cost reduction | [📖](https://docs.praison.ai/docs/cli/prompt-caching) |

 ---

@@ -2209,7 +2452,7 @@ 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

@@ -2218,11 +2461,19 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 - 🔐 **MCP Security** - Origin validation, DNS rebinding prevention, secure sessions
 - 🔄 **MCP Resumability** - SSE stream recovery via Last-Event-ID

+### A2A & A2UI Protocols
+
+- 🔗 **A2A Protocol** - Agent-to-Agent communication for inter-agent collaboration
+- 🖼️ **A2UI Protocol** - Agent-to-User Interface for generating rich UIs from agents
+- 📋 **UI Templates** - ChatTemplate, ListTemplate, FormTemplate, DashboardTemplate
+- 🔧 **Surface Builder** - Fluent API for building declarative UIs
+
 ### Safety & Control

 - 🤝 **Agent Handoffs** - Transfer context between specialised agents
 - 🛡️ **Guardrails** - Input/output validation and safety checks
 - ✅ **Human Approval** - Require human confirmation for critical actions
+- 🔐 **Tool Approval CLI** - `--trust` (auto-approve all) and `--approve-level` (risk-based approval)
 - 💬 **Sessions Management** - Isolated conversation contexts
 - 🔄 **Stateful Agents** - Maintain state across interactions

@@ -0,0 +1,33 @@
+# PraisonAI CLI - Benchmark Results
+
+**Generated:** 2025-12-19 16:04:40
+
+## Import Times
+
+| Module | Time (ms) | Target | Status |
+|--------|-----------|--------|--------|
+| praisonai | 4.11 | <10 | ✅ |
+| message_queue | 6.87 | <50 | ✅ |
+| at_mentions | 0.58 | <50 | ✅ |
+| profiler | 0.90 | <10 | ✅ |
+
+## Instantiation Times
+
+| Class | Time (μs) | Target | Status |
+|-------|-----------|--------|--------|
+| MessageQueue | 0.26 | <100 | ✅ |
+| StateManager | 0.30 | <100 | ✅ |
+| FileSearchService | 8.42 | <100 | ✅ |
+
+## Lazy Loading
+
+| Operation | Time (ms) |
+|-----------|----------|
+| PraisonAI lazy load | 3886.47 |
+
+## How to Reproduce
+
+```bash
+cd praisonai
+python benchmarks/simple_benchmark.py
+```
@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+"""
+PraisonAI CLI - Performance Benchmark
+
+Measures import times and module loading performance.
+
+Usage:
+    python benchmarks/simple_benchmark.py
+    python benchmarks/simple_benchmark.py --no-save
+"""
+
+import time
+import sys
+import os
+import argparse
+from datetime import datetime
+
+
+ITERATIONS = 100
+
+
+def measure_import(module_name: str) -> float:
+    """Measure import time in milliseconds."""
+    # Clear from cache if present
+    modules_to_remove = [k for k in sys.modules.keys() if k.startswith(module_name)]
+    for mod in modules_to_remove:
+        del sys.modules[mod]
+    
+    start = time.perf_counter()
+    __import__(module_name)
+    return (time.perf_counter() - start) * 1000
+
+
+def measure_instantiation(create_fn, iterations=ITERATIONS) -> float:
+    """Measure average instantiation time in microseconds."""
+    times = []
+    for _ in range(iterations):
+        start = time.perf_counter()
+        create_fn()
+        times.append((time.perf_counter() - start) * 1_000_000)
+    return sum(times) / len(times)
+
+
+def run_benchmark():
+    """Run the benchmark."""
+    results = {}
+    
+    print('=' * 60)
+    print('PraisonAI CLI - Performance Benchmark')
+    print('=' * 60)
+    print(f'\nIterations: {ITERATIONS}')
+    print('Metrics: Import time (ms), Instantiation time (μs)\n')
+    
+    # 1. Package import time
+    print("1. Testing package imports...")
+    
+    # Clear cache
+    modules_to_remove = [k for k in sys.modules.keys() if 'praisonai' in k]
+    for mod in modules_to_remove:
+        del sys.modules[mod]
+    
+    start = time.perf_counter()
+    import praisonai
+    results['praisonai_import_ms'] = (time.perf_counter() - start) * 1000
+    print(f"   import praisonai: {results['praisonai_import_ms']:.2f}ms")
+    
+    # 2. CLI features import
+    print("\n2. Testing CLI features imports...")
+    
+    start = time.perf_counter()
+    from praisonai.cli.features.message_queue import MessageQueue
+    results['message_queue_import_ms'] = (time.perf_counter() - start) * 1000
+    print(f"   message_queue: {results['message_queue_import_ms']:.2f}ms")
+    
+    start = time.perf_counter()
+    from praisonai.cli.features.at_mentions import CombinedCompleter
+    results['at_mentions_import_ms'] = (time.perf_counter() - start) * 1000
+    print(f"   at_mentions: {results['at_mentions_import_ms']:.2f}ms")
+    
+    # 3. Profiler import (should be fast, standalone)
+    print("\n3. Testing profiler import...")
+    start = time.perf_counter()
+    from praisonai.profiler import Profiler
+    results['profiler_import_ms'] = (time.perf_counter() - start) * 1000
+    print(f"   profiler: {results['profiler_import_ms']:.2f}ms")
+    
+    # 4. Instantiation benchmarks
+    print(f"\n4. Testing instantiation ({ITERATIONS} iterations)...")
+    
+    from praisonai.cli.features.message_queue import MessageQueue, StateManager
+    from praisonai.cli.features.at_mentions import FileSearchService
+    
+    results['MessageQueue_us'] = measure_instantiation(lambda: MessageQueue())
+    print(f"   MessageQueue: {results['MessageQueue_us']:.2f}μs")
+    
+    results['StateManager_us'] = measure_instantiation(lambda: StateManager())
+    print(f"   StateManager: {results['StateManager_us']:.2f}μs")
+    
+    results['FileSearchService_us'] = measure_instantiation(
+        lambda: FileSearchService(root_dir=".")
+    )
+    print(f"   FileSearchService: {results['FileSearchService_us']:.2f}μs")
+    
+    # 5. PraisonAI class (lazy load)
+    print("\n5. Testing PraisonAI class access (lazy load)...")
+    start = time.perf_counter()
+    PraisonAI = praisonai.PraisonAI
+    results['PraisonAI_lazy_ms'] = (time.perf_counter() - start) * 1000
+    print(f"   PraisonAI lazy load: {results['PraisonAI_lazy_ms']:.2f}ms")
+    
+    return results
+
+
+def print_summary(results: dict):
+    """Print benchmark summary."""
+    print('\n' + '=' * 60)
+    print('SUMMARY')
+    print('=' * 60)
+    
+    print('\nImport Times (target: <50ms for features, <10ms for package):')
+    print(f"  {'Module':<25} {'Time':>10} {'Status':>10}")
+    print(f"  {'-'*25} {'-'*10} {'-'*10}")
+    
+    import_checks = [
+        ('praisonai', results['praisonai_import_ms'], 10),
+        ('message_queue', results['message_queue_import_ms'], 50),
+        ('at_mentions', results['at_mentions_import_ms'], 50),
+        ('profiler', results['profiler_import_ms'], 10),
+    ]
+    
+    all_pass = True
+    for name, time_ms, threshold in import_checks:
+        status = '✅ PASS' if time_ms < threshold else '❌ SLOW'
+        if time_ms >= threshold:
+            all_pass = False
+        print(f"  {name:<25} {time_ms:>8.2f}ms {status:>10}")
+    
+    print('\nInstantiation Times (target: <100μs):')
+    print(f"  {'Class':<25} {'Time':>10} {'Status':>10}")
+    print(f"  {'-'*25} {'-'*10} {'-'*10}")
+    
+    inst_checks = [
+        ('MessageQueue', results['MessageQueue_us'], 100),
+        ('StateManager', results['StateManager_us'], 100),
+        ('FileSearchService', results['FileSearchService_us'], 100),
+    ]
+    
+    for name, time_us, threshold in inst_checks:
+        status = '✅ PASS' if time_us < threshold else '❌ SLOW'
+        if time_us >= threshold:
+            all_pass = False
+        print(f"  {name:<25} {time_us:>8.2f}μs {status:>10}")
+    
+    print('\n' + '=' * 60)
+    if all_pass:
+        print('✅ All benchmarks PASSED')
+    else:
+        print('❌ Some benchmarks FAILED')
+    print('=' * 60)
+    
+    return all_pass
+
+
+def save_results(results: dict):
+    """Save benchmark results to markdown file."""
+    filepath = os.path.join(os.path.dirname(__file__), 'BENCHMARK_RESULTS.md')
+    
+    with open(filepath, 'w') as f:
+        f.write('# PraisonAI CLI - Benchmark Results\n\n')
+        f.write(f'**Generated:** {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}\n\n')
+        
+        f.write('## Import Times\n\n')
+        f.write('| Module | Time (ms) | Target | Status |\n')
+        f.write('|--------|-----------|--------|--------|\n')
+        
+        import_data = [
+            ('praisonai', results['praisonai_import_ms'], 10),
+            ('message_queue', results['message_queue_import_ms'], 50),
+            ('at_mentions', results['at_mentions_import_ms'], 50),
+            ('profiler', results['profiler_import_ms'], 10),
+        ]
+        
+        for name, time_ms, threshold in import_data:
+            status = '✅' if time_ms < threshold else '❌'
+            f.write(f'| {name} | {time_ms:.2f} | <{threshold} | {status} |\n')
+        
+        f.write('\n## Instantiation Times\n\n')
+        f.write('| Class | Time (μs) | Target | Status |\n')
+        f.write('|-------|-----------|--------|--------|\n')
+        
+        inst_data = [
+            ('MessageQueue', results['MessageQueue_us'], 100),
+            ('StateManager', results['StateManager_us'], 100),
+            ('FileSearchService', results['FileSearchService_us'], 100),
+        ]
+        
+        for name, time_us, threshold in inst_data:
+            status = '✅' if time_us < threshold else '❌'
+            f.write(f'| {name} | {time_us:.2f} | <{threshold} | {status} |\n')
+        
+        f.write('\n## Lazy Loading\n\n')
+        f.write(f'| Operation | Time (ms) |\n')
+        f.write(f'|-----------|----------|\n')
+        f.write(f'| PraisonAI lazy load | {results["PraisonAI_lazy_ms"]:.2f} |\n')
+        
+        f.write('\n## How to Reproduce\n\n')
+        f.write('```bash\n')
+        f.write('cd praisonai\n')
+        f.write('python benchmarks/simple_benchmark.py\n')
+        f.write('```\n')
+    
+    print(f'\nResults saved to: {filepath}')
+    return filepath
+
+
+def main():
+    parser = argparse.ArgumentParser(description='PraisonAI CLI Performance Benchmark')
+    parser.add_argument('--no-save', action='store_true', help='Do not save results to file')
+    args = parser.parse_args()
+    
+    results = run_benchmark()
+    all_pass = print_summary(results)
+    
+    if not args.no_save:
+        save_results(results)
+    
+    return 0 if all_pass else 1
+
+
+if __name__ == '__main__':
+    sys.exit(main())
@@ -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/v2.3.37.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.37.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.66.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.3.66.tar.gz | shasum -a 256`.split.first
    license "MIT"
  
    depends_on "[email protected]"
@@ -1,31 +1,34 @@
+# 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"
 os.environ["EC_TELEMETRY"] = "false"
-from .cli import PraisonAI
+
+# Version is lightweight, import directly
 from .version import __version__

-# Re-export all classes from praisonaiagents to enable:
-# from praisonai import Agent, Task, PraisonAIAgents
-try:
-    import praisonaiagents
-    # Import all symbols from praisonaiagents using * import
-    from praisonaiagents import *
-except ImportError:
-    # If praisonaiagents is not available, these imports will fail gracefully
-    pass
-
-# Define __all__ to include both PraisonAI core classes and praisonaiagents exports
+# Define __all__ for lazy loading
 __all__ = [
-    # Core PraisonAI classes
    'PraisonAI',
    '__version__',
 ]

-# Dynamically extend __all__ with praisonaiagents exports
-try:
-    import praisonaiagents
-    __all__.extend(praisonaiagents.__all__)
-except (ImportError, AttributeError):
-    # If praisonaiagents is not available or doesn't have __all__, fail gracefully
-    pass
+# Lazy loading for heavy imports
+def __getattr__(name):
+    """Lazy load heavy modules to improve import time."""
+    if name == 'PraisonAI':
+        from .cli import PraisonAI
+        return PraisonAI
+    
+    # Try praisonaiagents exports
+    try:
+        import praisonaiagents
+        if hasattr(praisonaiagents, name):
+            return getattr(praisonaiagents, name)
+    except ImportError:
+        pass
+    
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -0,0 +1,337 @@
+"""
+Agent Scheduler for PraisonAI - Run agents periodically 24/7.
+
+This module provides scheduling capabilities for running PraisonAI agents
+at regular intervals, enabling 24/7 autonomous agent operations.
+
+Example:
+    # Run news checker every hour
+    from praisonai.agent_scheduler import AgentScheduler
+    from praisonai_agents import Agent
+    
+    agent = Agent(
+        name="NewsChecker",
+        instructions="Check latest AI news and summarize",
+        tools=[search_tool]
+    )
+    
+    scheduler = AgentScheduler(agent, task="Check latest AI news")
+    scheduler.start(schedule_expr="hourly")
+"""
+
+import threading
+import time
+import logging
+from datetime import datetime
+from typing import Optional, Dict, Any, Callable
+from abc import ABC, abstractmethod
+
+logger = logging.getLogger(__name__)
+
+
+class ScheduleParser:
+    """Parse schedule expressions into intervals."""
+    
+    @staticmethod
+    def parse(schedule_expr: str) -> int:
+        """
+        Parse schedule expression and return interval in seconds.
+        
+        Supported formats:
+        - "daily" -> 86400 seconds
+        - "hourly" -> 3600 seconds
+        - "*/30m" -> 1800 seconds (every 30 minutes)
+        - "*/1h" -> 3600 seconds (every 1 hour)
+        - "60" -> 60 seconds (plain number)
+        
+        Args:
+            schedule_expr: Schedule expression string
+            
+        Returns:
+            Interval in seconds
+            
+        Raises:
+            ValueError: If schedule format is not supported
+        """
+        schedule_expr = schedule_expr.strip().lower()
+        
+        if schedule_expr == "daily":
+            return 86400
+        elif schedule_expr == "hourly":
+            return 3600
+        elif schedule_expr.isdigit():
+            return int(schedule_expr)
+        elif schedule_expr.startswith("*/"):
+            interval_part = schedule_expr[2:]
+            if interval_part.endswith("m"):
+                minutes = int(interval_part[:-1])
+                return minutes * 60
+            elif interval_part.endswith("h"):
+                hours = int(interval_part[:-1])
+                return hours * 3600
+            elif interval_part.endswith("s"):
+                return int(interval_part[:-1])
+            else:
+                return int(interval_part)
+        else:
+            raise ValueError(f"Unsupported schedule format: {schedule_expr}")
+
+
+class AgentExecutorInterface(ABC):
+    """Abstract interface for agent execution."""
+    
+    @abstractmethod
+    def execute(self, task: str) -> Any:
+        """Execute the agent with given task."""
+        pass
+
+
+class PraisonAgentExecutor(AgentExecutorInterface):
+    """Executor for PraisonAI agents."""
+    
+    def __init__(self, agent):
+        """
+        Initialize executor with a PraisonAI agent.
+        
+        Args:
+            agent: PraisonAI Agent instance
+        """
+        self.agent = agent
+        
+    def execute(self, task: str) -> Any:
+        """
+        Execute the agent with given task.
+        
+        Args:
+            task: Task description for the agent
+            
+        Returns:
+            Agent execution result
+        """
+        try:
+            result = self.agent.start(task)
+            return result
+        except Exception as e:
+            logger.error(f"Agent execution failed: {e}")
+            raise
+
+
+class AgentScheduler:
+    """
+    Scheduler for running PraisonAI agents periodically.
+    
+    Features:
+    - Interval-based scheduling (hourly, daily, custom)
+    - Thread-safe operation
+    - Automatic retry on failure
+    - Execution logging and monitoring
+    - Graceful shutdown
+    
+    Example:
+        scheduler = AgentScheduler(agent, task="Check news")
+        scheduler.start(schedule_expr="hourly", max_retries=3)
+        # Agent runs every hour automatically
+        scheduler.stop()  # Stop when needed
+    """
+    
+    def __init__(
+        self,
+        agent,
+        task: str,
+        config: Optional[Dict[str, Any]] = None,
+        on_success: Optional[Callable] = None,
+        on_failure: Optional[Callable] = None
+    ):
+        """
+        Initialize agent scheduler.
+        
+        Args:
+            agent: PraisonAI Agent instance
+            task: Task description to execute
+            config: Optional configuration dict
+            on_success: Callback function on successful execution
+            on_failure: Callback function on failed execution
+        """
+        self.agent = agent
+        self.task = task
+        self.config = config or {}
+        self.on_success = on_success
+        self.on_failure = on_failure
+        
+        self.is_running = False
+        self._stop_event = threading.Event()
+        self._thread = None
+        self._executor = PraisonAgentExecutor(agent)
+        self._execution_count = 0
+        self._success_count = 0
+        self._failure_count = 0
+        
+    def start(
+        self,
+        schedule_expr: str,
+        max_retries: int = 3,
+        run_immediately: bool = False
+    ) -> bool:
+        """
+        Start scheduled agent execution.
+        
+        Args:
+            schedule_expr: Schedule expression (e.g., "hourly", "*/1h", "3600")
+            max_retries: Maximum retry attempts on failure
+            run_immediately: If True, run agent immediately before starting schedule
+            
+        Returns:
+            True if scheduler started successfully
+        """
+        if self.is_running:
+            logger.warning("Scheduler is already running")
+            return False
+            
+        try:
+            interval = ScheduleParser.parse(schedule_expr)
+            self.is_running = True
+            self._stop_event.clear()
+            
+            logger.info(f"Starting agent scheduler: {self.agent.name if hasattr(self.agent, 'name') else 'Agent'}")
+            logger.info(f"Task: {self.task}")
+            logger.info(f"Schedule: {schedule_expr} ({interval}s interval)")
+            logger.info(f"Max retries: {max_retries}")
+            
+            # Run immediately if requested
+            if run_immediately:
+                logger.info("Running agent immediately before starting schedule...")
+                self._execute_with_retry(max_retries)
+            
+            self._thread = threading.Thread(
+                target=self._run_schedule,
+                args=(interval, max_retries),
+                daemon=True
+            )
+            self._thread.start()
+            
+            logger.info("Agent scheduler started successfully")
+            return True
+            
+        except Exception as e:
+            logger.error(f"Failed to start scheduler: {e}")
+            self.is_running = False
+            return False
+    
+    def stop(self) -> bool:
+        """
+        Stop the scheduler gracefully.
+        
+        Returns:
+            True if stopped successfully
+        """
+        if not self.is_running:
+            logger.info("Scheduler is not running")
+            return True
+            
+        logger.info("Stopping agent scheduler...")
+        self._stop_event.set()
+        
+        if self._thread and self._thread.is_alive():
+            self._thread.join(timeout=10)
+            
+        self.is_running = False
+        logger.info("Agent scheduler stopped")
+        logger.info(f"Execution stats - Total: {self._execution_count}, Success: {self._success_count}, Failed: {self._failure_count}")
+        return True
+    
+    def get_stats(self) -> Dict[str, Any]:
+        """
+        Get execution statistics.
+        
+        Returns:
+            Dictionary with execution stats
+        """
+        return {
+            "is_running": self.is_running,
+            "total_executions": self._execution_count,
+            "successful_executions": self._success_count,
+            "failed_executions": self._failure_count,
+            "success_rate": (self._success_count / self._execution_count * 100) if self._execution_count > 0 else 0
+        }
+    
+    def _run_schedule(self, interval: int, max_retries: int):
+        """Internal method to run scheduled agent executions."""
+        while not self._stop_event.is_set():
+            logger.info(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] Starting scheduled agent execution")
+            
+            self._execute_with_retry(max_retries)
+            
+            # Wait for next scheduled time
+            logger.info(f"Next execution in {interval} seconds ({interval/3600:.1f} hours)")
+            self._stop_event.wait(interval)
+    
+    def _execute_with_retry(self, max_retries: int):
+        """Execute agent with retry logic."""
+        self._execution_count += 1
+        success = False
+        
+        for attempt in range(max_retries):
+            try:
+                logger.info(f"Attempt {attempt + 1}/{max_retries}")
+                result = self._executor.execute(self.task)
+                
+                logger.info(f"Agent execution successful on attempt {attempt + 1}")
+                logger.info(f"Result: {result}")
+                
+                self._success_count += 1
+                success = True
+                
+                if self.on_success:
+                    self.on_success(result)
+                    
+                break
+                
+            except Exception as e:
+                logger.error(f"Agent execution failed on attempt {attempt + 1}: {e}")
+                
+                if attempt < max_retries - 1:
+                    wait_time = 30 * (attempt + 1)  # Exponential backoff
+                    logger.info(f"Waiting {wait_time}s before retry...")
+                    time.sleep(wait_time)
+        
+        if not success:
+            self._failure_count += 1
+            logger.error(f"Agent execution failed after {max_retries} attempts")
+            
+            if self.on_failure:
+                self.on_failure(f"Failed after {max_retries} attempts")
+    
+    def execute_once(self) -> Any:
+        """
+        Execute agent immediately (one-time execution).
+        
+        Returns:
+            Agent execution result
+        """
+        logger.info("Executing agent once")
+        try:
+            result = self._executor.execute(self.task)
+            logger.info(f"One-time execution successful: {result}")
+            return result
+        except Exception as e:
+            logger.error(f"One-time execution failed: {e}")
+            raise
+
+
+def create_agent_scheduler(
+    agent,
+    task: str,
+    config: Optional[Dict[str, Any]] = None
+) -> AgentScheduler:
+    """
+    Factory function to create agent scheduler.
+    
+    Args:
+        agent: PraisonAI Agent instance
+        task: Task description
+        config: Optional configuration
+        
+    Returns:
+        Configured AgentScheduler instance
+    """
+    return AgentScheduler(agent, task, config)
@@ -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 += """
@@ -8,12 +8,19 @@ Structure:
 - features/: Feature handlers for CLI flags and commands
 """

-from .main import PraisonAI
-
 __all__ = ["PraisonAI"]


+def __getattr__(name):
+    """Lazy load PraisonAI to avoid slow imports."""
+    if name == "PraisonAI":
+        from .main import PraisonAI
+        return PraisonAI
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
 def main():
    """CLI entry point function."""
+    from .main import PraisonAI
    praison_ai = PraisonAI()
    praison_ai.main()
@@ -21,6 +21,12 @@ 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
+- message_queue: Message queuing while agent is processing
+- at_mentions: @ mention autocomplete for files and directories
 """

 # Type hints available for IDE support
@@ -43,6 +49,20 @@ __all__ = [
    'FlowDisplayHandler',
    'WorkflowHandler',
    'N8nHandler',
+    'ExternalAgentsHandler',
+    # New CLI enhancement features
+    'SlashCommandHandler',
+    'AutonomyModeHandler',
+    'CostTrackerHandler',
+    'RepoMapHandler',
+    'InteractiveTUIHandler',
+    'GitIntegrationHandler',
+    'SandboxExecutorHandler',
+    'MessageQueueHandler',
+    # @ mention autocomplete
+    'AtMentionCompleter',
+    'CombinedCompleter',
+    'FileSearchService',
 ]

 def __getattr__(name):
@@ -95,4 +115,42 @@ 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
+    elif name == 'MessageQueueHandler':
+        from .message_queue import MessageQueueHandler
+        return MessageQueueHandler
+    # @ mention autocomplete
+    elif name == 'AtMentionCompleter':
+        from .at_mentions import AtMentionCompleter
+        return AtMentionCompleter
+    elif name == 'CombinedCompleter':
+        from .at_mentions import CombinedCompleter
+        return CombinedCompleter
+    elif name == 'FileSearchService':
+        from .at_mentions import FileSearchService
+        return FileSearchService
    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -0,0 +1,242 @@
+"""
+Agent Scheduler CLI Feature.
+
+Provides CLI commands for scheduling agents to run 24/7 at regular intervals.
+"""
+
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class AgentSchedulerHandler:
+    """Handler for agent scheduler CLI commands."""
+    
+    @staticmethod
+    def handle_schedule_command(args, unknown_args=None) -> int:
+        """
+        Handle the schedule command for running agents periodically.
+        
+        Supports two modes:
+        1. YAML mode: praisonai schedule agents.yaml
+        2. Prompt mode: praisonai schedule "Your task here" --interval hourly
+        
+        Args:
+            args: Parsed command-line arguments
+            unknown_args: Additional arguments after the command
+            
+        Returns:
+            Exit code (0 for success, 1 for error)
+        """
+        try:
+            from praisonai.scheduler import AgentScheduler
+            from praisonaiagents import Agent
+        except ImportError:
+            print("Error: praisonai.scheduler or praisonaiagents module not found")
+            print("Please ensure PraisonAI is properly installed")
+            print("pip install praisonai praisonaiagents")
+            return 1
+        
+        # Check if first arg is a YAML file or a prompt
+        first_arg = unknown_args[0] if unknown_args else None
+        is_yaml_mode = first_arg and (first_arg.endswith('.yaml') or first_arg.endswith('.yml'))
+        
+        # Get overrides from CLI
+        interval_override = getattr(args, 'schedule_interval', None) or 'hourly'
+        max_retries_override = getattr(args, 'schedule_max_retries', None) or 3
+        timeout_override = getattr(args, 'timeout', None)
+        max_cost_override = getattr(args, 'max_cost', None)
+        verbose = getattr(args, 'verbose', False)
+        
+        # Set up logging - only show logs if verbose
+        if verbose:
+            logging.basicConfig(
+                level=logging.INFO,
+                format='[%(asctime)s] %(levelname)s - %(message)s',
+                datefmt='%Y-%m-%d %H:%M:%S'
+            )
+        else:
+            # Suppress scheduler logs in non-verbose mode
+            logging.getLogger('praisonai.scheduler').setLevel(logging.WARNING)
+        
+        try:
+            if is_yaml_mode:
+                # YAML mode: Load from agents.yaml
+                yaml_path = first_arg
+                print(f"🤖 Loading agent configuration from: {yaml_path}")
+                scheduler = AgentScheduler.from_yaml(
+                    yaml_path=yaml_path,
+                    interval_override=interval_override,
+                    max_retries_override=max_retries_override,
+                    timeout_override=timeout_override,
+                    max_cost_override=max_cost_override
+                )
+            else:
+                # Prompt mode: Create agent from direct prompt
+                if not first_arg:
+                    print("❌ Error: Please provide either a YAML file or a task prompt")
+                    print("\nExamples:")
+                    print("  praisonai schedule agents.yaml")
+                    print('  praisonai schedule "Check news every hour" --interval hourly')
+                    return 1
+                
+                task_prompt = first_arg
+                print(f"🤖 Creating scheduler for task: {task_prompt[:60]}...")
+                
+                # Create a simple agent with the prompt
+                agent = Agent(
+                    name="Scheduled Agent",
+                    role="Task Executor",
+                    goal=task_prompt,
+                    instructions=f"Execute this task: {task_prompt}",
+                    verbose=verbose
+                )
+                
+                # Create scheduler
+                scheduler = AgentScheduler(
+                    agent=agent,
+                    task=task_prompt,
+                    timeout=timeout_override,
+                    max_cost=max_cost_override
+                )
+            
+            # Display configuration
+            agent_name = getattr(scheduler.agent, 'name', 'Agent')
+            print(f"\n{'='*60}")
+            print(f"🤖 Starting 24/7 {agent_name}")
+            print(f"{'='*60}")
+            print(f"Task: {scheduler.task[:80]}{'...' if len(scheduler.task) > 80 else ''}")
+            
+            # Get schedule info
+            if is_yaml_mode:
+                schedule_config = scheduler._yaml_schedule_config
+                interval = interval_override or schedule_config.get('interval', 'hourly')
+                max_retries = max_retries_override or schedule_config.get('max_retries', 3)
+            else:
+                interval = interval_override
+                max_retries = max_retries_override
+            
+            print(f"Schedule: {interval}")
+            print(f"Max Retries: {max_retries}")
+            if scheduler.timeout:
+                print(f"Timeout: {scheduler.timeout}s")
+            if scheduler.max_cost:
+                print(f"Budget: ${scheduler.max_cost}")
+            print(f"{'='*60}\n")
+            
+            # Start scheduler
+            print("⏰ Starting scheduler... (Press Ctrl+C to stop)\n")
+            if is_yaml_mode:
+                scheduler.start_from_yaml_config()
+            else:
+                scheduler.start(
+                    schedule_expr=interval,
+                    max_retries=max_retries,
+                    run_immediately=True
+                )
+            
+            # Keep running until interrupted
+            try:
+                while scheduler.is_running:
+                    import time
+                    time.sleep(1)
+            except KeyboardInterrupt:
+                print("\n\n🛑 Stopping scheduler...")
+                scheduler.stop()
+                
+                # Display final stats
+                stats = scheduler.get_stats()
+                print("\n📊 Final Statistics:")
+                print(f"  Total Executions: {stats['total_executions']}")
+                print(f"  Successful: {stats['successful_executions']}")
+                print(f"  Failed: {stats['failed_executions']}")
+                print(f"  Success Rate: {stats['success_rate']:.1f}%")
+                print("\n✅ Agent stopped successfully\n")
+                
+            return 0
+            
+        except FileNotFoundError as e:
+            print(f"❌ Error: {e}")
+            print(f"\nMake sure {yaml_path} exists in the current directory.")
+            print("\nExample agents.yaml structure:")
+            print("""
+framework: praisonai
+
+agents:
+  - name: "AI News Monitor"
+    role: "News Analyst"
+    instructions: "Search and summarize AI news"
+    tools:
+      - search_tool
+
+task: "Search for latest AI news"
+
+schedule:
+  interval: "hourly"
+  max_retries: 3
+  run_immediately: true
+""")
+            return 1
+            
+        except ValueError as e:
+            print(f"❌ Configuration Error: {e}")
+            return 1
+            
+        except Exception as e:
+            print(f"❌ Error: {e}")
+            if verbose:
+                import traceback
+                traceback.print_exc()
+            return 1
+            
+    @staticmethod
+    def add_schedule_arguments(subparsers):
+        """
+        Add schedule subcommand and arguments to parser.
+        
+        Args:
+            subparsers: Subparsers object from argparse
+        """
+        schedule_parser = subparsers.add_parser(
+            'schedule',
+            help='Schedule an agent to run continuously at regular intervals'
+        )
+        
+        schedule_parser.add_argument(
+            'schedule_yaml',
+            nargs='?',
+            default='agents.yaml',
+            help='Path to agents.yaml file (default: agents.yaml)'
+        )
+        
+        schedule_parser.add_argument(
+            '--interval',
+            dest='schedule_interval',
+            type=str,
+            help='Override schedule interval (e.g., "hourly", "*/30m", "daily")'
+        )
+        
+        schedule_parser.add_argument(
+            '--max-retries',
+            dest='schedule_max_retries',
+            type=int,
+            help='Override maximum retry attempts (default: from YAML or 3)'
+        )
+        
+        schedule_parser.add_argument(
+            '--verbose', '-v',
+            action='store_true',
+            help='Enable verbose logging'
+        )
+        
+        schedule_parser.set_defaults(func=AgentSchedulerHandler.handle_schedule_command)
+
+
+def setup_scheduler_cli(subparsers):
+    """
+    Setup scheduler CLI commands.
+    
+    Args:
+        subparsers: Subparsers object from argparse
+    """
+    AgentSchedulerHandler.add_schedule_arguments(subparsers)
@@ -0,0 +1,416 @@
+"""
+@ Mention Autocomplete for PraisonAI CLI.
+
+Provides file/directory autocomplete when user types @.
+Uses only stdlib imports for zero performance impact.
+
+Features:
+- Detect @ trigger in input
+- Fuzzy search files/directories
+- Cache results for performance
+- Integrate with prompt_toolkit
+"""
+
+import os
+import time
+import fnmatch
+from dataclasses import dataclass
+from typing import List, Optional, Dict, Tuple
+
+
+# ============================================================================
+# Data Classes
+# ============================================================================
+
+@dataclass
+class AtMentionContext:
+    """Context for an @ mention in user input."""
+    is_active: bool
+    query: str
+    start_pos: int
+    mention_type: str = "file"  # file, directory, web, etc.
+
+
+@dataclass
+class FileSuggestion:
+    """A file or directory suggestion."""
+    path: str
+    file_type: str  # "file" or "directory"
+    score: int = 100
+    display: str = ""
+    
+    def __post_init__(self):
+        if not self.display:
+            self.display = self.path
+
+
+# ============================================================================
+# @ Mention Detection
+# ============================================================================
+
+def detect_at_mention(text: str, cursor_pos: int) -> Optional[AtMentionContext]:
+    """
+    Detect if cursor is within an @ mention context.
+    
+    Scans backward from cursor to find @ symbol.
+    Returns None if not in @ context.
+    
+    Args:
+        text: Full input text
+        cursor_pos: Current cursor position
+        
+    Returns:
+        AtMentionContext if in @ mention, None otherwise
+    """
+    if cursor_pos <= 0 or cursor_pos > len(text):
+        return None
+    
+    # Scan backward from cursor to find @
+    at_pos = -1
+    for i in range(cursor_pos - 1, -1, -1):
+        char = text[i]
+        
+        # Found @
+        if char == '@':
+            at_pos = i
+            break
+        
+        # Space/newline breaks @ context
+        if char in ' \t\n\r':
+            return None
+    
+    if at_pos == -1:
+        return None
+    
+    # Extract query between @ and cursor
+    query = text[at_pos + 1:cursor_pos]
+    
+    return AtMentionContext(
+        is_active=True,
+        query=query,
+        start_pos=at_pos
+    )
+
+
+# ============================================================================
+# File Search Service
+# ============================================================================
+
+class FileSearchService:
+    """
+    Service for searching files in a directory.
+    
+    Features:
+    - Walk directory tree
+    - Fuzzy match file paths
+    - Cache results with TTL
+    - Respect .gitignore (basic)
+    """
+    
+    def __init__(
+        self,
+        root_dir: str,
+        cache_ttl: int = 30,
+        max_depth: int = 5,
+        ignore_patterns: Optional[List[str]] = None
+    ):
+        self._root = os.path.abspath(root_dir)
+        self._cache_ttl = cache_ttl
+        self._max_depth = max_depth
+        self._ignore_patterns = ignore_patterns or [
+            '.git', '__pycache__', 'node_modules', '.venv', 'venv',
+            '*.pyc', '*.pyo', '.DS_Store', '*.egg-info'
+        ]
+        
+        # Cache: query -> (results, timestamp)
+        self._cache: Dict[str, Tuple[List[FileSuggestion], float]] = {}
+        
+        # File list cache
+        self._file_list: Optional[List[str]] = None
+        self._file_list_time: float = 0
+    
+    def _should_ignore(self, name: str) -> bool:
+        """Check if file/dir should be ignored."""
+        for pattern in self._ignore_patterns:
+            if fnmatch.fnmatch(name, pattern):
+                return True
+        return False
+    
+    def _get_file_list(self) -> List[str]:
+        """Get list of all files (cached)."""
+        now = time.time()
+        
+        # Return cached if fresh
+        if self._file_list is not None and (now - self._file_list_time) < self._cache_ttl:
+            return self._file_list
+        
+        files = []
+        
+        try:
+            for root, dirs, filenames in os.walk(self._root):
+                # Calculate depth
+                rel_root = os.path.relpath(root, self._root)
+                depth = 0 if rel_root == '.' else rel_root.count(os.sep) + 1
+                
+                if depth > self._max_depth:
+                    dirs.clear()  # Don't descend further
+                    continue
+                
+                # Filter ignored directories
+                dirs[:] = [d for d in dirs if not self._should_ignore(d)]
+                
+                # Add directories
+                for d in dirs:
+                    rel_path = os.path.relpath(os.path.join(root, d), self._root)
+                    files.append(rel_path + os.sep)
+                
+                # Add files
+                for f in filenames:
+                    if not self._should_ignore(f):
+                        rel_path = os.path.relpath(os.path.join(root, f), self._root)
+                        files.append(rel_path)
+        except OSError:
+            pass
+        
+        self._file_list = files
+        self._file_list_time = now
+        return files
+    
+    def _fuzzy_match(self, text: str, query: str) -> int:
+        """
+        Simple fuzzy match scoring.
+        
+        Returns score 0-100, higher is better.
+        """
+        if not query:
+            return 50  # Default score for empty query
+        
+        text_lower = text.lower()
+        query_lower = query.lower()
+        
+        # Exact match
+        if text_lower == query_lower:
+            return 100
+        
+        # Starts with
+        if text_lower.startswith(query_lower):
+            return 90
+        
+        # Contains
+        if query_lower in text_lower:
+            return 80
+        
+        # Fuzzy: all query chars appear in order
+        text_idx = 0
+        query_idx = 0
+        matches = 0
+        
+        while text_idx < len(text_lower) and query_idx < len(query_lower):
+            if text_lower[text_idx] == query_lower[query_idx]:
+                matches += 1
+                query_idx += 1
+            text_idx += 1
+        
+        if query_idx == len(query_lower):
+            # All query chars found
+            return 50 + int(30 * matches / len(text))
+        
+        return 0
+    
+    def search(self, query: str, max_results: int = 20) -> List[FileSuggestion]:
+        """
+        Search for files matching query.
+        
+        Args:
+            query: Search query (fuzzy matched)
+            max_results: Maximum results to return
+            
+        Returns:
+            List of FileSuggestion sorted by score
+        """
+        # Check cache
+        cache_key = f"{query}:{max_results}"
+        now = time.time()
+        
+        if cache_key in self._cache:
+            results, cached_time = self._cache[cache_key]
+            if (now - cached_time) < self._cache_ttl:
+                return results
+        
+        # Get all files
+        all_files = self._get_file_list()
+        
+        # Score and filter
+        scored: List[Tuple[int, str]] = []
+        for path in all_files:
+            score = self._fuzzy_match(path, query)
+            if score > 0:
+                scored.append((score, path))
+        
+        # Sort by score descending
+        scored.sort(key=lambda x: (-x[0], x[1]))
+        
+        # Build results
+        results = []
+        for score, path in scored[:max_results]:
+            file_type = "directory" if path.endswith(os.sep) else "file"
+            results.append(FileSuggestion(
+                path=path,
+                file_type=file_type,
+                score=score
+            ))
+        
+        # Cache results
+        self._cache[cache_key] = (results, now)
+        
+        return results
+    
+    def clear_cache(self) -> None:
+        """Clear all caches."""
+        self._cache.clear()
+        self._file_list = None
+
+
+# ============================================================================
+# Completers for prompt_toolkit
+# ============================================================================
+
+# Lazy import to avoid performance impact
+_Completer = None
+_Completion = None
+
+def _get_prompt_toolkit():
+    """Lazy import prompt_toolkit."""
+    global _Completer, _Completion
+    if _Completer is None:
+        from prompt_toolkit.completion import Completer, Completion
+        _Completer = Completer
+        _Completion = Completion
+    return _Completer, _Completion
+
+
+class AtMentionCompleter:
+    """
+    Completer for @ mentions.
+    
+    Shows file suggestions when user types @.
+    Implements prompt_toolkit Completer interface.
+    """
+    
+    def __init__(self, root_dir: str):
+        self._file_service = FileSearchService(root_dir)
+    
+    def get_completions(self, document, complete_event):
+        """Get completions for @ mentions."""
+        _, Completion = _get_prompt_toolkit()
+        
+        text = document.text_before_cursor
+        cursor_pos = len(text)
+        
+        # Detect @ context
+        context = detect_at_mention(text, cursor_pos)
+        if context is None or not context.is_active:
+            return
+        
+        # Search files
+        results = self._file_service.search(context.query, max_results=15)
+        
+        # Yield completions
+        for suggestion in results:
+            # Icon based on type
+            icon = "📁 " if suggestion.file_type == "directory" else "📄 "
+            display = f"{icon}{suggestion.path}"
+            
+            # Calculate replacement position
+            # Replace from @ to cursor
+            start_position = -(cursor_pos - context.start_pos)
+            
+            yield Completion(
+                text=f"@{suggestion.path}",
+                start_position=start_position,
+                display=display
+            )
+
+
+def create_combined_completer(commands: List[str], root_dir: str):
+    """
+    Factory function to create a CombinedCompleter.
+    
+    Returns a proper Completer subclass that handles both / and @.
+    """
+    Completer, Completion = _get_prompt_toolkit()
+    file_service = FileSearchService(root_dir)
+    
+    class CombinedCompleter(Completer):
+        """
+        Combined completer for both / commands and @ mentions.
+        
+        Properly inherits from prompt_toolkit Completer.
+        """
+        
+        def get_completions(self, document, complete_event):
+            """Get completions for / or @."""
+            text = document.text_before_cursor.lstrip()
+            
+            # Check for slash command
+            if text.startswith('/'):
+                cmd_text = text[1:].lower()
+                for cmd in commands:
+                    if cmd.lower().startswith(cmd_text):
+                        yield Completion(
+                            f'/{cmd}',
+                            start_position=-len(text),
+                            display=f'/{cmd}'
+                        )
+                return
+            
+            # Check for @ mention
+            full_text = document.text_before_cursor
+            cursor_pos = len(full_text)
+            
+            context = detect_at_mention(full_text, cursor_pos)
+            if context is None or not context.is_active:
+                return
+            
+            # Search files
+            results = file_service.search(context.query, max_results=15)
+            
+            # Yield completions
+            for suggestion in results:
+                icon = "📁 " if suggestion.file_type == "directory" else "📄 "
+                display = f"{icon}{suggestion.path}"
+                start_position = -(cursor_pos - context.start_pos)
+                
+                yield Completion(
+                    text=f"@{suggestion.path}",
+                    start_position=start_position,
+                    display=display
+                )
+    
+    return CombinedCompleter()
+
+
+# Backward compatible alias
+class CombinedCompleter:
+    """
+    Wrapper class for backward compatibility.
+    
+    Use create_combined_completer() for proper Completer subclass.
+    """
+    
+    def __new__(cls, commands: List[str], root_dir: str):
+        return create_combined_completer(commands, root_dir)
+
+
+# ============================================================================
+# Exports
+# ============================================================================
+
+__all__ = [
+    'AtMentionContext',
+    'FileSuggestion',
+    'detect_at_mention',
+    'FileSearchService',
+    'AtMentionCompleter',
+    'CombinedCompleter',
+]
@@ -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 +1,587 @@
+"""
+Message Queue for Interactive Mode.
+
+Provides FIFO message queuing while the AI agent is processing,
+inspired by Claude Code, Windsurf Cascade, Cursor, and Gemini CLI.
+
+Features:
+- Queue messages while agent is processing
+- Auto-process queue when agent becomes idle
+- Visual indicators for queue status
+- Thread-safe operations
+"""
+
+import threading
+import time
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import Callable, List, Optional
+
+
+# ============================================================================
+# Enums
+# ============================================================================
+
+class ProcessingState(Enum):
+    """State of the agent processing."""
+    IDLE = "idle"
+    PROCESSING = "processing"
+    WAITING_APPROVAL = "waiting_approval"
+
+
+class MessagePriority(Enum):
+    """Priority levels for queued messages."""
+    LOW = "low"
+    NORMAL = "normal"
+    HIGH = "high"
+
+
+# ============================================================================
+# Data Classes
+# ============================================================================
+
+@dataclass
+class QueuedMessage:
+    """A message in the queue with metadata."""
+    content: str
+    timestamp: float = field(default_factory=time.time)
+    priority: MessagePriority = MessagePriority.NORMAL
+
+
+# ============================================================================
+# MessageQueue - Thread-safe FIFO queue
+# ============================================================================
+
+class MessageQueue:
+    """
+    Thread-safe FIFO message queue.
+    
+    Provides basic queue operations with thread safety for concurrent access.
+    """
+    
+    def __init__(self):
+        self._messages: List[str] = []
+        self._lock = threading.Lock()
+    
+    @property
+    def is_empty(self) -> bool:
+        """Check if queue is empty."""
+        with self._lock:
+            return len(self._messages) == 0
+    
+    @property
+    def count(self) -> int:
+        """Get number of messages in queue."""
+        with self._lock:
+            return len(self._messages)
+    
+    def add(self, message: str) -> bool:
+        """
+        Add a message to the end of the queue.
+        
+        Args:
+            message: The message to add
+            
+        Returns:
+            True if message was added, False if empty/whitespace
+        """
+        trimmed = message.strip() if message else ""
+        if not trimmed:
+            return False
+        
+        with self._lock:
+            self._messages.append(trimmed)
+        return True
+    
+    def pop(self) -> Optional[str]:
+        """
+        Remove and return the first message (FIFO).
+        
+        Returns:
+            The first message, or None if queue is empty
+        """
+        with self._lock:
+            if self._messages:
+                return self._messages.pop(0)
+            return None
+    
+    def peek(self) -> Optional[str]:
+        """
+        View the first message without removing it.
+        
+        Returns:
+            The first message, or None if queue is empty
+        """
+        with self._lock:
+            if self._messages:
+                return self._messages[0]
+            return None
+    
+    def clear(self) -> None:
+        """Remove all messages from the queue."""
+        with self._lock:
+            self._messages.clear()
+    
+    def get_all(self) -> List[str]:
+        """
+        Get all messages as a list (does not remove them).
+        
+        Returns:
+            Copy of all messages in queue order
+        """
+        with self._lock:
+            return self._messages.copy()
+    
+    def remove_at(self, index: int) -> Optional[str]:
+        """
+        Remove message at specific index.
+        
+        Args:
+            index: The index to remove (0-based)
+            
+        Returns:
+            The removed message, or None if index is invalid
+        """
+        with self._lock:
+            if 0 <= index < len(self._messages):
+                return self._messages.pop(index)
+            return None
+
+
+# ============================================================================
+# StateManager - Processing state management
+# ============================================================================
+
+class StateManager:
+    """
+    Manages the processing state with optional callbacks.
+    
+    Tracks whether the agent is idle, processing, or waiting for approval.
+    """
+    
+    def __init__(self, on_state_change: Optional[Callable[[ProcessingState, ProcessingState], None]] = None):
+        self._state = ProcessingState.IDLE
+        self._lock = threading.Lock()
+        self._on_state_change = on_state_change
+    
+    @property
+    def current_state(self) -> ProcessingState:
+        """Get current processing state."""
+        with self._lock:
+            return self._state
+    
+    @property
+    def is_idle(self) -> bool:
+        """Check if currently idle."""
+        return self.current_state == ProcessingState.IDLE
+    
+    @property
+    def is_processing(self) -> bool:
+        """Check if currently processing."""
+        return self.current_state == ProcessingState.PROCESSING
+    
+    def set_state(self, new_state: ProcessingState) -> None:
+        """
+        Set the processing state.
+        
+        Args:
+            new_state: The new state to set
+        """
+        with self._lock:
+            old_state = self._state
+            self._state = new_state
+        
+        # Call callback outside lock to prevent deadlock
+        if self._on_state_change and old_state != new_state:
+            self._on_state_change(old_state, new_state)
+
+
+# ============================================================================
+# QueueDisplay - Visual formatting
+# ============================================================================
+
+class QueueDisplay:
+    """
+    Formats queue and status for display.
+    
+    Provides visual indicators for queue status, inspired by Codex CLI.
+    """
+    
+    def __init__(
+        self,
+        queue: MessageQueue,
+        state_manager: Optional[StateManager] = None,
+        max_message_length: int = 50
+    ):
+        self._queue = queue
+        self._state_manager = state_manager
+        self._max_length = max_message_length
+    
+    def format_queue(self) -> str:
+        """
+        Format queued messages for display.
+        
+        Returns:
+            Formatted string with queued messages
+        """
+        messages = self._queue.get_all()
+        if not messages:
+            return ""
+        
+        lines = []
+        for msg in messages:
+            # Truncate long messages
+            display_msg = msg
+            if len(msg) > self._max_length:
+                display_msg = msg[:self._max_length - 3] + "..."
+            lines.append(f"  ↳ {display_msg}")
+        
+        return "\n".join(lines)
+    
+    def format_status(self) -> str:
+        """
+        Format current processing status.
+        
+        Returns:
+            Status string (e.g., "⏳ Processing..." or "")
+        """
+        if not self._state_manager:
+            return ""
+        
+        state = self._state_manager.current_state
+        if state == ProcessingState.PROCESSING:
+            return "⏳ Processing..."
+        elif state == ProcessingState.WAITING_APPROVAL:
+            return "🔒 Waiting for approval..."
+        return ""
+    
+    def format_queue_count(self) -> str:
+        """
+        Format queue count indicator.
+        
+        Returns:
+            Count string (e.g., "📋 Queued (2)")
+        """
+        count = self._queue.count
+        if count == 0:
+            return ""
+        return f"📋 Queued ({count})"
+
+
+# ============================================================================
+# MessageQueueHandler - Main handler class
+# ============================================================================
+
+class MessageQueueHandler:
+    """
+    Main handler for message queue functionality.
+    
+    Coordinates queue, state, and processing.
+    """
+    
+    def __init__(
+        self,
+        processor: Optional[Callable[[str], str]] = None,
+        on_response: Optional[Callable[[str], None]] = None
+    ):
+        self._processor = processor
+        self._on_response = on_response
+        self._queue = MessageQueue()
+        self._state_manager = StateManager(on_state_change=self._on_state_change)
+        self._processing_lock = threading.Lock()
+    
+    @property
+    def queue(self) -> MessageQueue:
+        """Get the message queue."""
+        return self._queue
+    
+    @property
+    def state_manager(self) -> StateManager:
+        """Get the state manager."""
+        return self._state_manager
+    
+    def submit(self, message: str) -> bool:
+        """
+        Submit a message for processing.
+        
+        If idle, processes immediately. If processing, queues the message.
+        
+        Args:
+            message: The message to submit
+            
+        Returns:
+            True if processed/queued, False if empty message
+        """
+        trimmed = message.strip() if message else ""
+        if not trimmed:
+            return False
+        
+        if self._state_manager.is_idle:
+            # Process immediately
+            self._process_message(trimmed)
+        else:
+            # Queue for later
+            self._queue.add(trimmed)
+        
+        return True
+    
+    def on_processing_complete(self) -> None:
+        """
+        Called when current processing completes.
+        
+        Sets state to idle and processes next queued message if any.
+        """
+        self._state_manager.set_state(ProcessingState.IDLE)
+        self._process_next_in_queue()
+    
+    def get_status(self) -> dict:
+        """
+        Get current status.
+        
+        Returns:
+            Dict with queue_count and state
+        """
+        return {
+            'queue_count': self._queue.count,
+            'state': self._state_manager.current_state.value,
+            'messages': self._queue.get_all()
+        }
+    
+    def clear_queue(self) -> None:
+        """Clear all queued messages."""
+        self._queue.clear()
+    
+    def _process_message(self, message: str) -> None:
+        """Process a single message."""
+        if not self._processor:
+            return
+        
+        with self._processing_lock:
+            self._state_manager.set_state(ProcessingState.PROCESSING)
+            try:
+                response = self._processor(message)
+                if self._on_response and response:
+                    self._on_response(response)
+            finally:
+                self._state_manager.set_state(ProcessingState.IDLE)
+    
+    def _process_next_in_queue(self) -> None:
+        """Process the next message in queue if any."""
+        next_msg = self._queue.pop()
+        if next_msg:
+            self._process_message(next_msg)
+    
+    def _on_state_change(self, old_state: ProcessingState, new_state: ProcessingState) -> None:
+        """Handle state changes."""
+        # Auto-process queue when becoming idle
+        if new_state == ProcessingState.IDLE and old_state == ProcessingState.PROCESSING:
+            # Don't auto-process here to avoid recursion
+            # The on_processing_complete method handles this
+            pass
+
+
+# ============================================================================
+# AsyncProcessor - Background processing
+# ============================================================================
+
+class AsyncProcessor:
+    """
+    Runs work functions in background threads.
+    
+    Allows agent processing to happen asynchronously while
+    the main thread remains responsive for user input.
+    """
+    
+    def __init__(
+        self,
+        on_complete: Optional[Callable[[str], None]] = None,
+        on_status: Optional[Callable[[str], None]] = None,
+        on_error: Optional[Callable[[Exception], None]] = None
+    ):
+        self._on_complete = on_complete
+        self._on_status = on_status
+        self._on_error = on_error
+        self._thread: Optional[threading.Thread] = None
+        self._running = False
+        self._lock = threading.Lock()
+    
+    @property
+    def is_running(self) -> bool:
+        """Check if currently processing."""
+        with self._lock:
+            return self._running
+    
+    def start(self, work_fn: Callable[[], str]) -> None:
+        """
+        Start processing work in background thread.
+        
+        Args:
+            work_fn: Function to execute (should return result string)
+        """
+        def _worker():
+            try:
+                with self._lock:
+                    self._running = True
+                
+                result = work_fn()
+                
+                with self._lock:
+                    self._running = False
+                
+                if self._on_complete:
+                    self._on_complete(result)
+            except Exception as e:
+                with self._lock:
+                    self._running = False
+                if self._on_error:
+                    self._on_error(e)
+        
+        self._thread = threading.Thread(target=_worker, daemon=True)
+        self._thread.start()
+    
+    def update_status(self, status: str) -> None:
+        """Update status (can be called from work function)."""
+        if self._on_status:
+            self._on_status(status)
+
+
+# ============================================================================
+# LiveStatusDisplay - Real-time status display
+# ============================================================================
+
+class LiveStatusDisplay:
+    """
+    Tracks and displays real-time status during processing.
+    
+    Shows tool calls, command executions, and current status.
+    """
+    
+    def __init__(self):
+        self._status = ""
+        self._tool_calls: List[dict] = []
+        self._commands: List[str] = []
+        self._lock = threading.Lock()
+    
+    @property
+    def current_status(self) -> str:
+        """Get current status message."""
+        with self._lock:
+            return self._status
+    
+    @property
+    def tool_calls(self) -> List[dict]:
+        """Get list of tool calls."""
+        with self._lock:
+            return self._tool_calls.copy()
+    
+    @property
+    def commands(self) -> List[str]:
+        """Get list of commands executed."""
+        with self._lock:
+            return self._commands.copy()
+    
+    def update_status(self, status: str) -> None:
+        """Update current status message."""
+        with self._lock:
+            self._status = status
+    
+    def add_tool_call(self, name: str, args: dict) -> None:
+        """Add a tool call to the display."""
+        with self._lock:
+            self._tool_calls.append({
+                'name': name,
+                'args': args,
+                'timestamp': time.time()
+            })
+    
+    def add_command(self, command: str) -> None:
+        """Add a command execution to the display."""
+        with self._lock:
+            self._commands.append(command)
+    
+    def format(self) -> str:
+        """Format current status for display."""
+        lines = []
+        
+        with self._lock:
+            if self._status:
+                lines.append(f"⏳ {self._status}")
+            
+            for tool in self._tool_calls[-3:]:  # Show last 3 tools
+                lines.append(f"  🔧 {tool['name']}")
+            
+            for cmd in self._commands[-2:]:  # Show last 2 commands
+                display_cmd = cmd[:40] + "..." if len(cmd) > 40 else cmd
+                lines.append(f"  💻 {display_cmd}")
+        
+        return "\n".join(lines)
+    
+    def clear(self) -> None:
+        """Clear all status."""
+        with self._lock:
+            self._status = ""
+            self._tool_calls.clear()
+            self._commands.clear()
+
+
+# ============================================================================
+# NonBlockingInput - Async input handling
+# ============================================================================
+
+class NonBlockingInput:
+    """
+    Handles user input asynchronously.
+    
+    Allows users to type new messages while processing is ongoing.
+    """
+    
+    def __init__(self):
+        self._queue = MessageQueue()
+    
+    @property
+    def has_pending(self) -> bool:
+        """Check if there are pending inputs."""
+        return not self._queue.is_empty
+    
+    @property
+    def pending_count(self) -> int:
+        """Get number of pending inputs."""
+        return self._queue.count
+    
+    def submit(self, message: str) -> bool:
+        """Submit a new input message."""
+        return self._queue.add(message)
+    
+    def pop(self) -> Optional[str]:
+        """Get next pending input."""
+        return self._queue.pop()
+    
+    def peek(self) -> Optional[str]:
+        """View next pending input without removing."""
+        return self._queue.peek()
+    
+    def get_all(self) -> List[str]:
+        """Get all pending inputs."""
+        return self._queue.get_all()
+    
+    def clear(self) -> None:
+        """Clear all pending inputs."""
+        self._queue.clear()
+
+
+# ============================================================================
+# Exports
+# ============================================================================
+
+__all__ = [
+    'ProcessingState',
+    'MessagePriority',
+    'QueuedMessage',
+    'MessageQueue',
+    'StateManager',
+    'QueueDisplay',
+    'MessageQueueHandler',
+    'AsyncProcessor',
+    'LiveStatusDisplay',
+    'NonBlockingInput',
+]
@@ -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")
Author	SHA1	Message	Date
Mervin Praison	cacf1097ef	Release v2.3.66	2025-12-22 08:50:02 +00:00
Mervin Praison	09f01919d2	Fix duplicate --max-retries argument conflict in CLI parser	2025-12-21 05:19:08 +00:00
Mervin Praison	92397615f8	Release v2.3.65	2025-12-20 21:49:04 +00:00
Mervin Praison	4b21943a53	Release v2.3.64	2025-12-20 19:57:39 +00:00
Mervin Praison	af56a753bd	Release v2.3.63	2025-12-20 12:02:44 +00:00
Mervin Praison	15c2559a3c	Release v2.3.62	2025-12-20 11:59:46 +00:00
Mervin Praison	3215bdc0a6	Release v2.3.61	2025-12-20 11:15:22 +00:00
Mervin Praison	0ff0d83744	fix: Preserve real API keys for integration tests in conftest.py - Check for @pytest.mark.integration marker - Check if test file is in integration/ directory - This prevents conftest from overriding real API keys with 'test-key'	2025-12-20 03:58:13 +00:00
Mervin Praison	8f956f91dd	fix: Improve API key validation in integration test skip conditions - Check for 'sk-' prefix and minimum length (40 chars) to detect invalid keys - This ensures tests are skipped when using placeholder/test API keys in CI	2025-12-20 03:54:58 +00:00
Mervin Praison	954f6ac33d	fix: Skip integration tests when using test API key - test_auto_generator_integration.py: Skip when OPENAI_API_KEY contains 'test' - test_model_routing_real.py: Skip test_real_openai_call when using test key - test_cli_integrations.py: Skip all tests when using test key These tests require real API credentials and should not run in CI when only a placeholder test key is available.	2025-12-20 03:51:22 +00:00
Mervin Praison	264d11d8d9	fix: Fix failing unit tests for ClaudeCodeSDK and QueryRewriter CLI - test_use_sdk_option: Updated test to match actual behavior where use_sdk is only True when SDK is available (use_sdk and CLAUDE_SDK_AVAILABLE) - test_applies_rewrite_before_agent: Fixed mocking to properly mock _run_with_status_display and praisonaiagents submodules	2025-12-20 03:47:28 +00:00
Mervin Praison	88da2bdd7b	Release v2.3.60	2025-12-20 03:35:28 +00:00
Mervin Praison	b84e6c2460	Release v2.3.59	2025-12-20 03:28:48 +00:00
Mervin Praison	0434b23ada	Release v2.3.58	2025-12-20 03:08:31 +00:00
Mervin Praison	a9951e0694	Release v2.3.57	2025-12-19 16:47:09 +00:00
Mervin Praison	073062cd96	Release v2.3.56	2025-12-19 16:14:58 +00:00
Mervin Praison	936b422876	Release v2.3.55	2025-12-19 16:05:38 +00:00
Mervin Praison	99ab421ce2	Release v2.3.54	2025-12-19 16:04:43 +00:00
Mervin Praison	c1f334905e	Release v2.3.53	2025-12-19 15:38:30 +00:00
Mervin Praison	6d3ba7cdf8	Release v2.3.52	2025-12-19 15:34:19 +00:00
Mervin Praison	96616498d2	Release v2.3.51	2025-12-19 15:25:30 +00:00
Mervin Praison	1cad345415	Release v2.3.50	2025-12-19 15:19:29 +00:00
Mervin Praison	802e7e52f9	fix(readme): correct CLI docs URLs to include /docs/ prefix Changed all https://docs.praison.ai/cli/* URLs to https://docs.praison.ai/docs/cli/* Fixed 39 URLs total	2025-12-19 13:01:53 +00:00
Mervin Praison	53704f234c	Release v2.3.49	2025-12-19 12:49:12 +00:00
Mervin Praison	b575994d91	docs(readme): update AI commit CLI with security scanning and auto mode - Add full auto mode (-a) with stage, security check, commit, push - Document security scanning features - Add --no-verify flag documentation - List detected sensitive patterns	2025-12-19 12:35:49 +00:00
Mervin Praison	7ed8596261	Release v2.3.48	2025-12-19 12:35:02 +00:00
Mervin Praison	deef65c4bb	Release v2.3.47	2025-12-19 12:23:05 +00:00
Mervin Praison	d51327effd	Release v2.3.46	2025-12-19 12:22:29 +00:00
Mervin Praison	30ce8857e8	fix: suppress crewai.cli.config INFO log at startup	2025-12-19 12:18:23 +00:00
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
Mervin Praison	889d04a843	Release v2.3.40	2025-12-18 22:07:54 +00:00
Mervin Praison	fba811c477	Release v2.3.39	2025-12-18 21:54:19 +00:00
Mervin Praison	df687d86c3	Release v2.3.38	2025-12-18 21:26:34 +00:00