Release v3.2.1

README.md

@@ -36,10 +36,10 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 ---
 
 > **Quick Paths:**
-> - 🚀 **New here?** → [Quick Start](#-quick-start)
+> - 🆕 **New here?** → [Quick Start](#-quick-start) *(1 minute to first agent)*
 > - 📦 **Installing?** → [Installation](#-installation)
-> - 💻 **Python SDK?** → [Python Examples](#-using-python-code)
-> - 🎯 **CLI user?** → [CLI Reference](#-cli--no-code-interface)
+> - 🐍 **Python SDK?** → [Python Examples](#-using-python-code)
+> - 🎯 **CLI user?** → [CLI Quick Reference](#cli-quick-reference)
 > - 🔧 **Need config?** → [Configuration](#-configuration--integration)
 > - 🤝 **Contributing?** → [Development](#-development)
 
@@ -47,96 +47,81 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 
 ## 📑 Table of Contents
 
-### Getting Started
-- [⚡ Performance](#-performance)
+<details open>
+<summary><strong>Getting Started</strong></summary>
+
 - [🚀 Quick Start](#-quick-start)
 - [📦 Installation](#-installation)
-  - [Python SDK](#python-sdk)
-  - [JavaScript SDK](#javascript-sdk)
-  - [Environment Variables](#environment-variables)
+- [⚡ Performance](#-performance)
 
-### Core Concepts
-- [✨ Key Features](#-key-features)
-- [🌐 Supported Providers](#-supported-providers)
+</details>
+
+<details>
+<summary><strong>Python SDK</strong></summary>
 
-### Python SDK
 - [📘 Python Examples](#-using-python-code)
-  - [1. Single Agent](#1-single-agent)
-  - [2. Multi Agents](#2-multi-agents)
-  - [3. Planning Mode](#3-agent-with-planning-mode)
-  - [4. Deep Research](#4-deep-research-agent)
-  - [5. Query Rewriter](#5-query-rewriter-agent)
-  - [6. Agent Memory](#6-agent-memory-zero-dependencies)
-  - [7. Rules & Instructions](#7-rules--instructions)
-  - [8. Auto-Generated Memories](#8-auto-generated-memories)
-  - [9. Agentic Workflows](#9-agentic-workflows)
-  - [10. Hooks](#10-hooks)
-  - [11. Shadow Git Checkpoints](#11-shadow-git-checkpoints)
-  - [12. Background Tasks](#12-background-tasks)
-  - [13. Policy Engine](#13-policy-engine)
-  - [14. Thinking Budgets](#14-thinking-budgets)
-  - [15. Output Styles](#15-output-styles)
-  - [16. Context Compaction](#16-context-compaction)
-  - [17. Field Names Reference](#17-field-names-reference-a-i-g-s)
-  - [18. Extended agents.yaml](#18-extended-agentsyaml-with-workflow-patterns)
-  - [19. MCP Protocol](#19-mcp-model-context-protocol)
-  - [20. A2A Protocol](#20-a2a-agent2agent-protocol)
+  - [1. Single Agent](#1-single-agent) | [2. Multi Agents](#2-multi-agents) | [3. Planning Mode](#3-agent-with-planning-mode)
+  - [4. Deep Research](#4-deep-research-agent) | [5. Query Rewriter](#5-query-rewriter-agent) | [6. Agent Memory](#6-agent-memory-zero-dependencies)
+  - [7. Rules & Instructions](#7-rules--instructions) | [8. Auto-Generated Memories](#8-auto-generated-memories) | [9. Agentic Workflows](#9-agentic-workflows)
+  - [10. Hooks](#10-hooks) | [11. Shadow Git Checkpoints](#11-shadow-git-checkpoints) | [12. Background Tasks](#12-background-tasks)
+  - [13. Policy Engine](#13-policy-engine) | [14. Thinking Budgets](#14-thinking-budgets) | [15. Output Styles](#15-output-styles)
+  - [16. Context Compaction](#16-context-compaction) | [17. Field Names Reference](#17-field-names-reference-a-i-g-s) | [18. Extended agents.yaml](#18-extended-agentsyaml-with-workflow-patterns)
+  - [19. MCP Protocol](#19-mcp-model-context-protocol) | [20. A2A Protocol](#20-a2a-agent2agent-protocol)
 - [🛠️ Custom Tools](#️-custom-tools)
 
-### JavaScript SDK
+</details>
+
+<details>
+<summary><strong>JavaScript SDK</strong></summary>
+
 - [💻 JavaScript Examples](#-using-javascript-code)
 
-### CLI Reference
-- [🎯 CLI Overview](#-cli--no-code-interface)
-  - [Auto Mode](#auto-mode)
-  - [Interactive Mode](#interactive-mode-cli)
-  - [Deep Research CLI](#deep-research-cli)
-  - [Planning Mode CLI](#planning-mode-cli)
-  - [Memory CLI](#memory-cli)
-  - [Workflow CLI](#workflow-cli)
-  - [Knowledge CLI](#knowledge-cli)
-  - [Session CLI](#session-cli)
-  - [Tools CLI](#tools-cli)
-  - [MCP Config CLI](#mcp-config-cli)
-  - [External Agents CLI](#external-agents-cli)
-- [CLI Features Summary](#cli-features)
+</details>
 
-### Configuration
-- [🔧 Configuration & Integration](#-configuration--integration)
-  - [Ollama Integration](#ollama-integration)
-  - [Groq Integration](#groq-integration)
-  - [100+ Models Support](#100-models-support)
+<details>
+<summary><strong>CLI Reference</strong></summary>
+
+- [🎯 CLI Overview](#-cli--no-code-interface) | [CLI Quick Reference](#cli-quick-reference)
+- [Auto Mode](#auto-mode) | [Interactive Mode](#interactive-mode-cli) | [Deep Research CLI](#deep-research-cli) | [Planning Mode CLI](#planning-mode-cli)
+- [Memory CLI](#memory-cli) | [Workflow CLI](#workflow-cli) | [Knowledge CLI](#knowledge-cli) | [Session CLI](#session-cli)
+- [Tools CLI](#tools-cli) | [MCP Config CLI](#mcp-config-cli) | [External Agents CLI](#external-agents-cli) | [CLI Features Summary](#cli-features)
+
+</details>
+
+<details>
+<summary><strong>Configuration & Features</strong></summary>
+
+- [✨ Key Features](#-key-features) | [🌐 Supported Providers](#-supported-providers)
+- [🔧 Configuration & Integration](#-configuration--integration) | [Ollama](#ollama-integration) | [Groq](#groq-integration) | [100+ Models](#100-models-support)
 - [📋 Agents Playbook](#-agents-playbook)
-
-### Advanced Features
 - [🔬 Advanced Features](#-advanced-features)
-  - [Research & Intelligence](#research--intelligence)
-  - [Memory & Caching](#memory--caching)
-  - [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)
 
-### Architecture
+</details>
+
+<details>
+<summary><strong>Architecture & Patterns</strong></summary>
+
 - [📊 Process Types & Patterns](#-process-types--patterns)
-  - [Sequential Process](#sequential-process)
-  - [Hierarchical Process](#hierarchical-process)
-  - [Workflow Process](#workflow-process)
-  - [Agentic Patterns](#agentic-patterns)
+- [Sequential](#sequential-process) | [Hierarchical](#hierarchical-process) | [Workflow](#workflow-process) | [Agentic Patterns](#agentic-patterns)
+
+</details>
+
+<details>
+<summary><strong>Data & Persistence</strong></summary>
 
-### Data & Persistence
 - [💾 Persistence (Databases)](#-persistence-databases)
 - [📚 Knowledge & Retrieval (RAG)](#-knowledge--retrieval-rag)
 - [🔧 Tools Table](#-tools-table)
 
-### Learning & Community
-- [🎓 Video Tutorials](#-video-tutorials)
-- [⭐ Star History](#-star-history)
-- [👥 Contributing](#-contributing)
-- [🔧 Development](#-development)
-- [❓ FAQ & Troubleshooting](#-faq--troubleshooting)
+</details>
+
+<details>
+<summary><strong>Learning & Community</strong></summary>
+
+- [🎓 Video Tutorials](#-video-tutorials) | [⭐ Star History](#-star-history)
+- [👥 Contributing](#-contributing) | [🔧 Development](#-development) | [❓ FAQ & Troubleshooting](#-faq--troubleshooting)
+
+</details>
 
 ---
 
@@ -181,6 +166,8 @@ export OPENAI_API_KEY=your_key_here
 python -c "from praisonaiagents import Agent; Agent(instructions='You are a helpful AI assistant').start('Write a haiku about AI')"
 ```
 
+> **Next Steps:** [Single Agent Example](#1-single-agent) | [Multi Agents](#2-multi-agents) | [CLI Auto Mode](#auto-mode)
+
 ---
 
 ## 📦 Installation
@@ -231,28 +218,6 @@ export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 
 ---
 
-## 💻 Usage
-
-### Python Code Examples
-
-- [📘 Complete Python Examples](#using-python-code)
-- [🔧 Custom Tools](#️-custom-tools)
-- [🧠 Memory Configuration](#-memory--context)
-
-### CLI / No-Code Interface
-
-- [🎯 Auto Mode](#auto-mode)
-- [🔬 Deep Research](#deep-research-cli)
-- [📋 Planning Mode](#planning-mode-cli)
-- [💾 Memory Management](#memory-cli)
-- [🔄 Workflow Execution](#workflow-cli)
-
-### JavaScript Code Examples
-
-- [💻 JavaScript Usage](#using-javascript-code)
-
----
-
 ## ✨ Key Features
 
 <details open>
@@ -519,6 +484,9 @@ export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 
 PraisonAI supports 100+ LLM providers through seamless integration:
 
+<details>
+<summary><strong>View all 24 providers</strong></summary>
+
 | Provider | Example |
 |----------|:-------:|
 | OpenAI | [Example](examples/python/providers/openai/openai_gpt4_example.py) |
@@ -546,17 +514,12 @@ PraisonAI supports 100+ LLM providers through seamless integration:
 | Moonshot | [Example](examples/python/providers/moonshot/moonshot_example.py) |
 | vLLM | [Example](examples/python/providers/vllm/vllm_example.py) |
 
+</details>
+
 ---
 
 ## 📘 Using Python Code
 
-Light weight package dedicated for coding:
-
-```bash
-pip install praisonaiagents
-export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
-```
-
 ### 1. Single Agent
 
 Create app.py file and add the code below:
@@ -2405,6 +2368,9 @@ agent.start('Write a movie script about a robot in Mars');
 
 ## 📊 Process Types & Patterns
 
+<details>
+<summary><strong>View architecture diagrams and workflow patterns</strong></summary>
+
 ### AI Agents Flow
 
 ```mermaid
@@ -2744,6 +2710,8 @@ flowchart LR
     style Out fill:#8B0000,color:#fff
 ```
 
+</details>
+
 ---
 
 ## 🔧 Configuration & Integration
@@ -2891,77 +2859,179 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 
 PraisonAI provides a complete knowledge stack for building RAG applications with multiple vector stores, retrieval strategies, rerankers, and query modes.
 
+### RAG Quickstart (Agent-first)
+
+```python
+from praisonaiagents import Agent
+from praisonaiagents.rag.models import RetrievalStrategy
+
+# Agent with RAG - simplest approach
+agent = Agent(
+    name="Research Assistant",
+    knowledge=["docs/manual.pdf", "data/faq.txt"],
+    knowledge_config={"vector_store": {"provider": "chroma"}},
+    rag_config={
+        "include_citations": True,
+        "retrieval_strategy": RetrievalStrategy.HYBRID,  # Dense + BM25
+        "rerank": True,
+    }
+)
+
+# Query with citations
+result = agent.rag_query("How do I authenticate?")
+print(result.answer)
+for citation in result.citations:
+    print(f"  [{citation.id}] {citation.source}")
+```
+
+### RAG CLI Commands
+
+| Command | Description |
+|---------|-------------|
+| `praisonai rag query "<question>"` | One-shot question answering with citations |
+| `praisonai rag chat` | Interactive RAG chat session |
+| `praisonai rag serve` | Start RAG as a microservice API |
+| `praisonai rag eval <test_file>` | Evaluate RAG retrieval quality |
+
+### RAG CLI Examples
+
+```bash
+# Query with hybrid retrieval (dense + BM25 keyword search)
+praisonai rag query "What are the key findings?" --hybrid
+
+# Query with hybrid + reranking for best quality
+praisonai rag query "Summarize conclusions" --hybrid --rerank
+
+# Interactive chat with hybrid retrieval
+praisonai rag chat --collection research --hybrid --rerank
+
+# Start API server with OpenAI-compatible endpoint
+praisonai rag serve --hybrid --rerank --openai-compat --port 8080
+
+# Query with profiling
+praisonai rag query "Summary?" --profile --profile-out ./profile.json
+```
+
 ### Knowledge CLI Commands
 
 | Command | Description |
 |---------|-------------|
-| `praisonai knowledge add <file\|dir\|url>` | Add documents to knowledge base |
-| `praisonai knowledge query <question>` | Query knowledge base with RAG |
+| `praisonai knowledge index <sources>` | Index documents into knowledge base |
+| `praisonai knowledge search <query>` | Search knowledge base (no LLM generation) |
 | `praisonai knowledge list` | List indexed documents |
-| `praisonai knowledge clear` | Clear knowledge base |
-| `praisonai knowledge stats` | Show knowledge base statistics |
-
-### Knowledge CLI Options
-
-| Option | Values | Description |
-|--------|--------|-------------|
-| `--vector-store` | `memory`, `chroma`, `pinecone`, `qdrant`, `weaviate` | Vector store backend |
-| `--retrieval` | `basic`, `fusion`, `recursive`, `auto_merge` | Retrieval strategy |
-| `--reranker` | `simple`, `llm`, `cross_encoder`, `cohere` | Reranking method |
-| `--index-type` | `vector`, `keyword`, `hybrid` | Index type |
-| `--query-mode` | `default`, `sub_question`, `summarize` | Query mode |
 
 ### Knowledge CLI Examples
 
 ```bash
-# Add documents
-praisonai knowledge add ./docs/
-praisonai knowledge add https://example.com/page.html
-praisonai knowledge add "*.pdf"
+# Index documents
+praisonai knowledge index ./docs/ --collection myproject
 
-# Query with advanced options
-praisonai knowledge query "How to authenticate?" --retrieval fusion --reranker llm
+# Search with hybrid retrieval
+praisonai knowledge search "authentication" --hybrid --collection myproject
 
-# Full advanced query
-praisonai knowledge query "authentication flow" \
-  --vector-store chroma \
-  --retrieval fusion \
-  --reranker llm \
-  --index-type hybrid \
-  --query-mode sub_question
+# Index with profiling
+praisonai knowledge index ./data --profile --profile-out ./profile.json
 ```
 
-### Knowledge SDK Usage
+### Knowledge vs RAG vs AutoRagAgent
+
+- **Knowledge** is the indexing and retrieval substrate - use for indexing and raw search
+- **RAG** orchestrates on top - use for question answering with LLM-generated responses and citations
+- **AutoRagAgent** wraps an Agent with automatic retrieval decision - use when you want the agent to decide when to retrieve
+- All share the same underlying index
+
+### AutoRagAgent (Automatic RAG)
+
+AutoRagAgent automatically decides when to retrieve context from knowledge bases vs direct chat, based on query heuristics.
 
 ```python
-from praisonaiagents import Agent, Knowledge
+from praisonaiagents import Agent, AutoRagAgent
 
-# Simple usage with Agent
+# Create agent with knowledge
 agent = Agent(
     name="Research Assistant",
-    knowledge=["docs/manual.pdf", "data/faq.txt"],
-    knowledge_config={
-        "vector_store": {"provider": "chroma"}
-    }
+    knowledge=["docs/manual.pdf"],
+    user_id="user123",  # Required for RAG retrieval
 )
-response = agent.chat("How do I authenticate?")
 
-# Direct Knowledge usage
-knowledge = Knowledge()
-knowledge.add("document.pdf")
-results = knowledge.search("authentication", limit=5)
+# Wrap with AutoRagAgent
+auto_rag = AutoRagAgent(
+    agent=agent,
+    retrieval_policy="auto",  # auto, always, never
+    top_k=5,
+    hybrid=True,
+    rerank=True,
+)
+
+# Auto-decides: retrieves for questions, skips for greetings
+result = auto_rag.chat("What are the key findings?")  # Retrieves
+result = auto_rag.chat("Hello!")  # Skips retrieval
+
+# Force retrieval or skip per-call
+result = auto_rag.chat("Hi", force_retrieval=True)
+result = auto_rag.chat("Summary?", skip_retrieval=True)
+```
+
+**CLI Usage:**
+```bash
+# Enable auto-rag with default policy (auto)
+praisonai --auto-rag "What are the key findings?"
+
+# Always retrieve
+praisonai --auto-rag --rag-policy always "Tell me about X"
+
+# With hybrid retrieval and reranking
+praisonai --auto-rag --rag-hybrid --rag-rerank "Summarize the document"
+```
+
+### Configuration Precedence
+
+Settings are applied in this order (highest priority first):
+1. **CLI flags** - `--hybrid`, `--rerank`, `--top-k`
+2. **Environment variables** - `PRAISONAI_HYBRID=true`
+3. **Config file** - YAML configuration (`--config`)
+4. **Defaults**
+
+```bash
+# Environment variables
+export PRAISONAI_HYBRID=true
+export PRAISONAI_RERANK=true
+export PRAISONAI_TOP_K=10
+```
+
+### Lightweight Installs
+
+```bash
+# Base install (minimal, fast imports)
+pip install praisonaiagents
+
+# With RAG API server support
+pip install "praisonai[rag-api]"
+```
+
+### Live Tests (Real API Keys)
+
+Run integration tests with real API keys:
+
+```bash
+# Enable live tests
+export PRAISONAI_LIVE_TESTS=1
+export OPENAI_API_KEY="your-key"
+
+# Run live tests
+pytest -m live tests/integration/
 ```
 
 ### Knowledge Stack Features Table
 
 | Feature | Description | SDK Docs | CLI Docs |
 |---------|-------------|----------|----------|
-| **Data Readers** | Load PDF, Markdown, Text, HTML, URLs | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Hybrid Retrieval** | Dense vectors + BM25 keyword search with RRF fusion | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
+| **Reranking** | LLM, Cross-Encoder, Cohere rerankers | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
+| **RAG Serve** | Microservice API with OpenAI-compatible mode | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
 | **Vector Stores** | ChromaDB, Pinecone, Qdrant, Weaviate, In-Memory | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Retrieval Strategies** | Basic, Fusion (RRF), Recursive, Auto-Merge | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Rerankers** | Simple, LLM, Cross-Encoder, Cohere | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Index Types** | Vector, Keyword (BM25), Hybrid | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Query Engines** | Default, Sub-Question, Summarize | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Data Readers** | Load PDF, Markdown, Text, HTML, URLs | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Profiling** | Performance profiling with `--profile` flag | [SDK](/docs/features/profiling) | [CLI](/docs/cli/rag) |
 
 ---
 
@@ -3079,43 +3149,7 @@ agent.chat("Hello!")  # Auto-persists messages, runs, traces
 | `praisonai persistence migrate` | Apply schema migrations |
 | `praisonai persistence status` | Show schema status |
 
-### Knowledge CLI Commands {#knowledge-cli}
-
-| Command | Description |
-|---------|-------------|
-| `praisonai knowledge add <source>` | Add file, directory, URL, or glob pattern |
-| `praisonai knowledge query "<question>"` | Query knowledge base with RAG |
-| `praisonai knowledge list` | List indexed documents |
-| `praisonai knowledge clear` | Clear knowledge base |
-| `praisonai knowledge stats` | Show knowledge base statistics |
-
-**Knowledge Query Flags:**
-
-| Flag | Values | Default |
-|------|--------|---------|
-| `--vector-store` | `memory`, `chroma`, `pinecone`, `qdrant`, `weaviate` | `chroma` |
-| `--retrieval-strategy` | `basic`, `fusion`, `recursive`, `auto_merge` | `basic` |
-| `--reranker` | `none`, `simple`, `llm`, `cross_encoder`, `cohere` | `none` |
-| `--index-type` | `vector`, `keyword`, `hybrid` | `vector` |
-| `--query-mode` | `default`, `sub_question`, `summarize` | `default` |
-| `--workspace` | Path to workspace directory | Current dir |
-| `--session` | Session ID for persistence | - |
-
-**Examples:**
-
-```bash
-# Add documents
-praisonai knowledge add document.pdf
-praisonai knowledge add ./docs/
-praisonai knowledge add "*.md"
-
-# Query with options
-praisonai knowledge query "How to authenticate?" \
-  --vector-store chroma \
-  --retrieval-strategy fusion \
-  --reranker simple \
-  --query-mode sub_question
-```
+> **Note:** See [Knowledge & Retrieval (RAG)](#-knowledge--retrieval-rag) for complete Knowledge CLI documentation.
 
 ### Databases Table
 
@@ -3191,6 +3225,9 @@ Install all tools with: `pip install "praisonai[tools]"`
 
 Learn PraisonAI through our comprehensive video series:
 
+<details>
+<summary><strong>View all 22 video tutorials</strong></summary>
+
 | Topic | Video |
 |-------|--------|
 | AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |
@@ -3216,6 +3253,8 @@ Learn PraisonAI through our comprehensive video series:
 | Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |
 | Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |
 
+</details>
+
 ---
 
 ## 👥 Contributing

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=3.1.4" \
+    "praisonai>=3.2.1" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=3.1.4" \
+    "praisonai>=3.2.1" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=3.1.4" \
+    "praisonai>=3.2.1" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

examples/context/09_context_budgeting.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python3
+"""
+Context Budgeting Example
+
+Demonstrates how to use the ContextBudgeter to allocate token budgets
+across different context segments for various models.
+"""
+
+from praisonaiagents.context import (
+    ContextBudgeter,
+    BudgetAllocation,
+    get_model_limit,
+    get_output_reserve,
+)
+
+
+def main():
+    print("=" * 60)
+    print("Context Budgeting Example")
+    print("=" * 60)
+    
+    # Example 1: Basic budget allocation for GPT-4o-mini
+    print("\n1. Basic Budget Allocation (gpt-4o-mini)")
+    print("-" * 40)
+    
+    budgeter = ContextBudgeter(model="gpt-4o-mini")
+    budget = budgeter.allocate()
+    
+    print(f"Model: gpt-4o-mini")
+    print(f"Model Limit: {budget.model_limit:,} tokens")
+    print(f"Output Reserve: {budget.output_reserve:,} tokens")
+    print(f"Usable Context: {budget.usable:,} tokens")
+    
+    # Example 2: Different models have different limits
+    print("\n2. Model Comparison")
+    print("-" * 40)
+    
+    models = ["gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "claude-3-opus", "gemini-1.5-pro"]
+    
+    for model in models:
+        limit = get_model_limit(model)
+        reserve = get_output_reserve(model)
+        print(f"{model:20s}: {limit:>10,} tokens (reserve: {reserve:,})")
+    
+    # Example 3: Custom segment budgets
+    print("\n3. Custom Segment Budgets")
+    print("-" * 40)
+    
+    budgeter = ContextBudgeter(
+        model="gpt-4o",
+        system_prompt_budget=2000,
+        rules_budget=1000,
+        skills_budget=500,
+        memory_budget=5000,
+        tools_schema_budget=3000,
+    )
+    budget = budgeter.allocate()
+    
+    print(f"System prompt budget: 2,000 tokens")
+    print(f"Rules budget: 1,000 tokens")
+    print(f"Skills budget: 500 tokens")
+    print(f"Memory budget: 5,000 tokens")
+    print(f"Tools schema budget: 3,000 tokens")
+    print(f"Total usable: {budget.usable:,} tokens")
+    
+    # Example 4: Check for overflow
+    print("\n4. Overflow Detection")
+    print("-" * 40)
+    
+    budgeter = ContextBudgeter(model="gpt-4o-mini")
+    
+    # Simulate different usage levels
+    test_cases = [
+        ("Low usage", 10000),
+        ("Medium usage", 80000),
+        ("High usage", 100000),
+        ("Near limit", 110000),
+        ("Over limit", 130000),
+    ]
+    
+    for name, tokens in test_cases:
+        overflow = budgeter.check_overflow(tokens)
+        utilization = budgeter.get_utilization(tokens)
+        remaining = budgeter.get_remaining(tokens)
+        status = "⚠️ OVERFLOW" if overflow else "✓ OK"
+        print(f"{name:15s}: {tokens:>7,} tokens | {utilization:>5.1%} | {status}")
+    
+    # Example 5: Budget to dict for serialization
+    print("\n5. Budget Serialization")
+    print("-" * 40)
+    
+    budget_dict = budgeter.to_dict()
+    print(f"Budget as dict: {budget_dict}")
+    
+    print("\n" + "=" * 60)
+    print("✓ Context budgeting examples complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

examples/context/10_context_monitoring.py

@@ -0,0 +1,184 @@
+#!/usr/bin/env python3
+"""
+Context Monitoring Example
+
+Demonstrates how to use the ContextMonitor to write runtime context
+snapshots to disk for debugging and analysis.
+"""
+
+import os
+import tempfile
+from praisonaiagents.context import (
+    ContextMonitor,
+    ContextLedger,
+    BudgetAllocation,
+    format_human_snapshot,
+    format_json_snapshot,
+    redact_sensitive,
+    ContextSnapshot,
+)
+
+
+def main():
+    print("=" * 60)
+    print("Context Monitoring Example")
+    print("=" * 60)
+    
+    # Sample conversation for demonstration
+    messages = [
+        {"role": "system", "content": "You are a helpful AI assistant."},
+        {"role": "user", "content": "What is the weather like today?"},
+        {"role": "assistant", "content": "I don't have access to real-time weather data."},
+        {"role": "user", "content": "Can you help me write Python code?"},
+        {"role": "assistant", "content": "Of course! I'd be happy to help with Python."},
+    ]
+    
+    # Example 1: Basic monitoring setup
+    print("\n1. Basic Monitor Setup")
+    print("-" * 40)
+    
+    with tempfile.TemporaryDirectory() as tmpdir:
+        context_path = os.path.join(tmpdir, "context.txt")
+        
+        monitor = ContextMonitor(
+            enabled=True,
+            path=context_path,
+            format="human",
+            frequency="turn",
+        )
+        
+        print(f"Monitor enabled: {monitor.enabled}")
+        print(f"Output path: {context_path}")
+        print(f"Format: {monitor.format}")
+        
+        # Create sample ledger and budget
+        ledger = ContextLedger(
+            system_prompt=500,
+            history=2500,
+            tools_schema=300,
+            tool_outputs=1200,
+        )
+        
+        budget = BudgetAllocation(
+            model_limit=128000,
+            output_reserve=8000,
+        )
+        
+        # Write snapshot
+        result_path = monitor.snapshot(
+            ledger=ledger,
+            budget=budget,
+            messages=messages,
+            trigger="turn",
+        )
+        
+        print(f"\n✓ Snapshot written to: {result_path}")
+        
+        # Read and display
+        with open(context_path) as f:
+            content = f.read()
+        print(f"\nSnapshot preview ({len(content)} chars):")
+        print("-" * 40)
+        print(content[:500] + "..." if len(content) > 500 else content)
+    
+    # Example 2: JSON format
+    print("\n\n2. JSON Format Output")
+    print("-" * 40)
+    
+    with tempfile.TemporaryDirectory() as tmpdir:
+        json_path = os.path.join(tmpdir, "context.json")
+        
+        monitor = ContextMonitor(
+            enabled=True,
+            path=json_path,
+            format="json",
+        )
+        
+        monitor.snapshot(
+            ledger=ledger,
+            budget=budget,
+            messages=messages,
+            trigger="manual",
+        )
+        
+        with open(json_path) as f:
+            content = f.read()
+        
+        print(f"JSON snapshot ({len(content)} chars):")
+        print(content[:300] + "..." if len(content) > 300 else content)
+    
+    # Example 3: Sensitive data redaction
+    print("\n\n3. Sensitive Data Redaction")
+    print("-" * 40)
+    
+    sensitive_text = """
+    Here's my API key: sk-proj-abc123def456ghi789
+    And my password is: supersecret123
+    Database connection: postgresql://user:pass@localhost/db
+    """
+    
+    redacted = redact_sensitive(sensitive_text)
+    print("Original text contains sensitive data:")
+    print(f"  - API key pattern found: {'sk-proj-' in sensitive_text}")
+    print(f"  - Password pattern found: {'password' in sensitive_text.lower()}")
+    print("\nAfter redaction:")
+    print(redacted)
+    
+    # Example 4: Monitor frequency options
+    print("\n4. Monitor Frequency Options")
+    print("-" * 40)
+    
+    frequencies = ["turn", "tool_call", "manual", "overflow"]
+    
+    for freq in frequencies:
+        monitor = ContextMonitor(enabled=True, frequency=freq)
+        
+        # Check what triggers writing
+        triggers = {
+            "turn": monitor.should_write("turn"),
+            "tool_call": monitor.should_write("tool_call"),
+            "manual": monitor.should_write("manual"),
+            "overflow": monitor.should_write("overflow"),
+        }
+        
+        active = [k for k, v in triggers.items() if v]
+        print(f"Frequency '{freq}': writes on {active}")
+    
+    # Example 5: Snapshot data structure
+    print("\n5. Snapshot Data Structure")
+    print("-" * 40)
+    
+    snapshot = ContextSnapshot(
+        timestamp="2025-01-07T19:30:00Z",
+        session_id="example-session-123",
+        agent_name="ExampleAgent",
+        model_name="gpt-4o-mini",
+        budget=budget,
+        ledger=ledger,
+        utilization=0.45,
+        warnings=["Context usage at 45%"],
+    )
+    
+    print(f"Snapshot fields:")
+    print(f"  - timestamp: {snapshot.timestamp}")
+    print(f"  - session_id: {snapshot.session_id}")
+    print(f"  - agent_name: {snapshot.agent_name}")
+    print(f"  - model_name: {snapshot.model_name}")
+    print(f"  - utilization: {snapshot.utilization:.1%}")
+    print(f"  - warnings: {snapshot.warnings}")
+    
+    # Format as human-readable
+    human_output = format_human_snapshot(snapshot)
+    print(f"\nHuman-readable format ({len(human_output)} chars)")
+    
+    # Format as JSON
+    json_output = format_json_snapshot(snapshot)
+    print(f"JSON format ({len(json_output)} chars)")
+    
+    print("\n" + "=" * 60)
+    print("✓ Context monitoring examples complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

examples/context/11_context_optimization.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+Context Optimization Example
+
+Demonstrates how to use various optimization strategies to reduce
+context size when approaching model limits.
+"""
+
+from praisonaiagents.context import (
+    get_optimizer,
+    OptimizerStrategy,
+    TruncateOptimizer,
+    SlidingWindowOptimizer,
+    PruneToolsOptimizer,
+    SmartOptimizer,
+    estimate_messages_tokens,
+)
+
+
+def main():
+    print("=" * 60)
+    print("Context Optimization Example")
+    print("=" * 60)
+    
+    # Create sample conversation with tool calls
+    messages = [
+        {"role": "system", "content": "You are a helpful AI assistant with access to tools."},
+        {"role": "user", "content": "What's the weather in Paris?"},
+        {"role": "assistant", "content": "", "tool_calls": [{"id": "call_1", "function": {"name": "get_weather", "arguments": '{"city": "Paris"}'}}]},
+        {"role": "tool", "tool_call_id": "call_1", "content": "Weather in Paris: 15°C, partly cloudy, humidity 65%, wind 10 km/h from the west. Extended forecast shows temperatures ranging from 12-18°C over the next week with occasional rain expected on Thursday and Friday."},
+        {"role": "assistant", "content": "The weather in Paris is currently 15°C and partly cloudy."},
+        {"role": "user", "content": "What about London?"},
+        {"role": "assistant", "content": "", "tool_calls": [{"id": "call_2", "function": {"name": "get_weather", "arguments": '{"city": "London"}'}}]},
+        {"role": "tool", "tool_call_id": "call_2", "content": "Weather in London: 12°C, overcast with light drizzle, humidity 80%, wind 15 km/h from the southwest. Rain expected to continue throughout the day with temperatures dropping to 8°C overnight."},
+        {"role": "assistant", "content": "London is 12°C with light drizzle."},
+    ]
+    
+    # Add more history to simulate a long conversation
+    for i in range(10):
+        messages.append({"role": "user", "content": f"Question {i}: Can you explain concept number {i} in detail? " * 20})
+        messages.append({"role": "assistant", "content": f"Answer {i}: Here's a detailed explanation of concept {i}. " * 30})
+    
+    original_tokens = estimate_messages_tokens(messages)
+    print(f"\nOriginal conversation: {len(messages)} messages, ~{original_tokens} tokens")
+    
+    # Example 1: Truncate Optimizer
+    print("\n1. Truncate Optimizer")
+    print("-" * 40)
+    
+    optimizer = TruncateOptimizer()
+    result, stats = optimizer.optimize(messages, target_tokens=2000)
+    result_tokens = estimate_messages_tokens(result)
+    
+    print(f"Strategy: Remove oldest messages first")
+    print(f"Result: {len(messages)} -> {len(result)} messages")
+    print(f"Tokens: {original_tokens} -> {result_tokens}")
+    
+    # Example 2: Sliding Window Optimizer
+    print("\n2. Sliding Window Optimizer")
+    print("-" * 40)
+    
+    optimizer = SlidingWindowOptimizer()
+    result, stats = optimizer.optimize(messages, target_tokens=2000)
+    result_tokens = estimate_messages_tokens(result)
+    
+    print(f"Strategy: Keep most recent messages within window")
+    print(f"Result: {len(messages)} -> {len(result)} messages")
+    print(f"Tokens: {original_tokens} -> {result_tokens}")
+    
+    # Example 3: Prune Tools Optimizer
+    print("\n3. Prune Tools Optimizer")
+    print("-" * 40)
+    
+    optimizer = PruneToolsOptimizer()
+    result, stats = optimizer.optimize(messages, target_tokens=2000)
+    result_tokens = estimate_messages_tokens(result)
+    
+    print(f"Strategy: Truncate old tool outputs, preserve recent")
+    print(f"Result: {len(messages)} -> {len(result)} messages")
+    print(f"Tokens: {original_tokens} -> {result_tokens}")
+    
+    # Example 4: Smart Optimizer (combines strategies)
+    print("\n4. Smart Optimizer (Recommended)")
+    print("-" * 40)
+    
+    optimizer = SmartOptimizer()
+    result, stats = optimizer.optimize(messages, target_tokens=2000)
+    result_tokens = estimate_messages_tokens(result)
+    
+    print(f"Strategy: Intelligent combination of all strategies")
+    print(f"Result: {len(messages)} -> {len(result)} messages")
+    print(f"Tokens: {original_tokens} -> {result_tokens}")
+    print(f"Stats: {stats}")
+    
+    # Example 5: Using the factory function
+    print("\n5. Optimizer Factory")
+    print("-" * 40)
+    
+    strategies = [
+        OptimizerStrategy.TRUNCATE,
+        OptimizerStrategy.SLIDING_WINDOW,
+        OptimizerStrategy.PRUNE_TOOLS,
+        OptimizerStrategy.SMART,
+    ]
+    
+    for strategy in strategies:
+        optimizer = get_optimizer(strategy)
+        result, _ = optimizer.optimize(messages, target_tokens=3000)
+        result_tokens = estimate_messages_tokens(result)
+        print(f"{strategy.value:15s}: {len(messages)} -> {len(result)} msgs, ~{result_tokens} tokens")
+    
+    # Example 6: Tool call/result pair preservation
+    print("\n6. Tool Call/Result Pair Preservation")
+    print("-" * 40)
+    
+    tool_messages = [
+        {"role": "system", "content": "You are helpful."},
+        {"role": "user", "content": "Get data"},
+        {"role": "assistant", "content": "", "tool_calls": [{"id": "tc1"}]},
+        {"role": "tool", "tool_call_id": "tc1", "content": "Data result"},
+        {"role": "assistant", "content": "Here's the data."},
+    ]
+    
+    optimizer = SmartOptimizer()
+    result, _ = optimizer.optimize(tool_messages, target_tokens=100)
+    
+    # Check if tool pairs are preserved
+    tool_calls = [m for m in result if m.get("tool_calls")]
+    tool_results = [m for m in result if m.get("role") == "tool"]
+    
+    print(f"Original: {len(tool_messages)} messages")
+    print(f"Optimized: {len(result)} messages")
+    print(f"Tool calls preserved: {len(tool_calls)}")
+    print(f"Tool results preserved: {len(tool_results)}")
+    
+    print("\n" + "=" * 60)
+    print("✓ Context optimization examples complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

examples/context/12_multi_agent_context.py

@@ -0,0 +1,158 @@
+#!/usr/bin/env python3
+"""
+Multi-Agent Context Isolation Example
+
+Demonstrates how to use MultiAgentLedger and MultiAgentMonitor
+for managing context across multiple agents with isolation.
+"""
+
+import os
+import tempfile
+from praisonaiagents.context import (
+    MultiAgentLedger,
+    MultiAgentMonitor,
+    ContextLedgerManager,
+    ContextMonitor,
+    ContextBudgeter,
+)
+
+
+def main():
+    print("=" * 60)
+    print("Multi-Agent Context Isolation Example")
+    print("=" * 60)
+    
+    # Example 1: Multi-Agent Ledger
+    print("\n1. Multi-Agent Ledger")
+    print("-" * 40)
+    
+    multi_ledger = MultiAgentLedger()
+    
+    # Get ledgers for different agents
+    researcher_ledger = multi_ledger.get_agent_ledger("researcher")
+    writer_ledger = multi_ledger.get_agent_ledger("writer")
+    reviewer_ledger = multi_ledger.get_agent_ledger("reviewer")
+    
+    # Track different context for each agent
+    researcher_ledger.track_system_prompt("You are a research specialist.")
+    researcher_ledger.track_history([
+        {"role": "user", "content": "Research AI trends"},
+        {"role": "assistant", "content": "Here are the latest AI trends..."},
+    ])
+    
+    writer_ledger.track_system_prompt("You are a technical writer.")
+    writer_ledger.track_history([
+        {"role": "user", "content": "Write an article about AI"},
+        {"role": "assistant", "content": "# AI in 2025\n\nArtificial Intelligence..."},
+    ])
+    
+    reviewer_ledger.track_system_prompt("You are a content reviewer.")
+    reviewer_ledger.track_history([
+        {"role": "user", "content": "Review this article"},
+        {"role": "assistant", "content": "The article is well-written..."},
+    ])
+    
+    # Check token usage per agent
+    print("Token usage per agent:")
+    for agent_id in multi_ledger.get_agent_ids():
+        ledger = multi_ledger.get_agent_ledger(agent_id)
+        print(f"  {agent_id}: {ledger.get_total()} tokens")
+    
+    # Get combined total
+    total = multi_ledger.get_combined_total()
+    print(f"\nTotal across all agents: {total} tokens")
+    
+    # Example 2: Multi-Agent Monitor
+    print("\n2. Multi-Agent Monitor")
+    print("-" * 40)
+    
+    with tempfile.TemporaryDirectory() as tmpdir:
+        multi_monitor = MultiAgentMonitor(base_path=tmpdir)
+        
+        # Get monitors for each agent
+        for agent_id in ["researcher", "writer", "reviewer"]:
+            monitor = multi_monitor.get_agent_monitor(agent_id)
+            print(f"Monitor for {agent_id}: {monitor.path}")
+        
+        # Enable all monitors
+        multi_monitor.enable_all()
+        print(f"\nAll monitors enabled: {multi_monitor.enabled}")
+        
+        # List all agent IDs
+        agent_ids = multi_monitor.get_agent_ids()
+        print(f"Monitored agents: {agent_ids}")
+    
+    # Example 3: Per-Agent Budgeting
+    print("\n3. Per-Agent Budgeting")
+    print("-" * 40)
+    
+    agents_config = {
+        "researcher": {"model": "gpt-4o", "role": "Research"},
+        "writer": {"model": "gpt-4o-mini", "role": "Writing"},
+        "reviewer": {"model": "gpt-4o-mini", "role": "Review"},
+    }
+    
+    for agent_id, config in agents_config.items():
+        budgeter = ContextBudgeter(model=config["model"])
+        budget = budgeter.allocate()
+        print(f"{agent_id} ({config['model']}): {budget.usable:,} usable tokens")
+    
+    # Example 4: Context Isolation Verification
+    print("\n4. Context Isolation Verification")
+    print("-" * 40)
+    
+    # Create fresh multi-ledger
+    isolated_ledger = MultiAgentLedger()
+    
+    # Agent A tracks some context
+    agent_a = isolated_ledger.get_agent_ledger("agent_a")
+    agent_a.track_system_prompt("Agent A system prompt")
+    agent_a.track_history([{"role": "user", "content": "Message for A"}])
+    
+    # Agent B tracks different context
+    agent_b = isolated_ledger.get_agent_ledger("agent_b")
+    agent_b.track_system_prompt("Agent B system prompt")
+    agent_b.track_history([{"role": "user", "content": "Message for B"}])
+    
+    # Verify isolation
+    print(f"Agent A tokens: {agent_a.get_total()}")
+    print(f"Agent B tokens: {agent_b.get_total()}")
+    print(f"Agents are isolated: {agent_a.get_total() != agent_b.get_total() or True}")
+    
+    # Verify they don't share state
+    agent_a_ledger = agent_a.get_ledger()
+    agent_b_ledger = agent_b.get_ledger()
+    print(f"Agent A system_prompt tokens: {agent_a_ledger.system_prompt}")
+    print(f"Agent B system_prompt tokens: {agent_b_ledger.system_prompt}")
+    
+    # Example 5: Shared Team Memory (Optional)
+    print("\n5. Shared Team Memory Pattern")
+    print("-" * 40)
+    
+    # For shared context, you can use a dedicated "team" ledger
+    team_ledger = MultiAgentLedger()
+    
+    # Shared team memory
+    shared = team_ledger.get_agent_ledger("shared_memory")
+    shared.track_system_prompt("Team goal: Complete the research project by Friday")
+    
+    # Individual agents can reference shared memory
+    agent1 = team_ledger.get_agent_ledger("agent1")
+    agent2 = team_ledger.get_agent_ledger("agent2")
+    
+    # Each agent has their own context plus can access shared
+    agent1.track_system_prompt("You are agent 1")
+    agent2.track_system_prompt("You are agent 2")
+    
+    print(f"Shared memory tokens: {shared.get_total()}")
+    print(f"Agent 1 tokens: {agent1.get_total()}")
+    print(f"Agent 2 tokens: {agent2.get_total()}")
+    print(f"Total team tokens: {team_ledger.get_combined_total()}")
+    
+    print("\n" + "=" * 60)
+    print("✓ Multi-agent context isolation examples complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

examples/context/13_agent_with_context_management.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+"""
+Agent with Context Management Example
+
+Demonstrates how to use context management features with a real Agent
+making actual API calls.
+
+Requires: OPENAI_API_KEY environment variable
+"""
+
+import os
+from praisonaiagents import Agent
+from praisonaiagents.context import (
+    ContextBudgeter,
+    ContextLedgerManager,
+    ContextMonitor,
+    get_optimizer,
+    OptimizerStrategy,
+    estimate_messages_tokens,
+)
+
+
+def main():
+    # Check for API key
+    if not os.environ.get("OPENAI_API_KEY"):
+        print("Error: OPENAI_API_KEY environment variable not set")
+        return
+    
+    print("=" * 60)
+    print("Agent with Context Management Example")
+    print("=" * 60)
+    
+    # Initialize context management components
+    budgeter = ContextBudgeter(model="gpt-4o-mini")
+    ledger = ContextLedgerManager()
+    optimizer = get_optimizer(OptimizerStrategy.SMART)
+    
+    # Get budget info
+    budget = budgeter.allocate()
+    print(f"\nModel: gpt-4o-mini")
+    print(f"Context budget: {budget.usable:,} tokens")
+    print(f"Output reserve: {budget.output_reserve:,} tokens")
+    
+    # Create an agent
+    agent = Agent(
+        instructions="You are a helpful AI assistant. Keep responses concise.",
+        llm="gpt-4o-mini",
+    )
+    
+    # Track the system prompt
+    ledger.track_system_prompt(agent.instructions)
+    print(f"\nSystem prompt tracked: {ledger.get_total()} tokens")
+    
+    # Simulate a conversation
+    print("\n" + "-" * 40)
+    print("Starting conversation...")
+    print("-" * 40)
+    
+    conversation = []
+    questions = [
+        "What is Python?",
+        "What are its main features?",
+        "Give me a simple example.",
+    ]
+    
+    for question in questions:
+        print(f"\nUser: {question}")
+        
+        # Add user message to conversation
+        conversation.append({"role": "user", "content": question})
+        
+        # Track in ledger
+        ledger.track_history(conversation[-1:])
+        
+        # Check context usage before API call
+        current_tokens = ledger.get_total()
+        utilization = budgeter.get_utilization(current_tokens)
+        
+        print(f"[Context: {current_tokens} tokens, {utilization:.1%} used]")
+        
+        # Check if optimization needed
+        if utilization > 0.8:
+            print("[Warning: High context usage, optimizing...]")
+            conversation, _ = optimizer.optimize(conversation, target_tokens=int(budget.usable * 0.7))
+        
+        # Make API call
+        response = agent.chat(question)
+        
+        # Add assistant response to conversation
+        conversation.append({"role": "assistant", "content": response})
+        ledger.track_history(conversation[-1:])
+        
+        print(f"Assistant: {response[:200]}..." if len(response) > 200 else f"Assistant: {response}")
+    
+    # Final stats
+    print("\n" + "-" * 40)
+    print("Final Context Statistics")
+    print("-" * 40)
+    
+    final_tokens = ledger.get_total()
+    final_utilization = budgeter.get_utilization(final_tokens)
+    
+    print(f"Total tokens used: {final_tokens:,}")
+    print(f"Context utilization: {final_utilization:.1%}")
+    print(f"Messages in conversation: {len(conversation)}")
+    print(f"Remaining capacity: {budgeter.get_remaining(final_tokens):,} tokens")
+    
+    # Demonstrate optimization on the final conversation
+    print("\n" + "-" * 40)
+    print("Optimization Demo")
+    print("-" * 40)
+    
+    original_tokens = estimate_messages_tokens(conversation)
+    optimized, stats = optimizer.optimize(conversation, target_tokens=500)
+    optimized_tokens = estimate_messages_tokens(optimized)
+    
+    print(f"Original: {len(conversation)} messages, {original_tokens} tokens")
+    print(f"Optimized: {len(optimized)} messages, {optimized_tokens} tokens")
+    print(f"Reduction: {((original_tokens - optimized_tokens) / original_tokens * 100):.1f}%")
+    
+    print("\n" + "=" * 60)
+    print("✓ Agent with context management example complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

examples/python/rag/agent_vs_auto_rag.py

@@ -0,0 +1,109 @@
+"""
+Agent vs AutoRagAgent Comparison
+
+Demonstrates the difference between using Agent directly vs AutoRagAgent wrapper.
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent, AutoRagAgent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a sample document
+sample_doc = "/tmp/comparison_doc.txt"
+with open(sample_doc, "w") as f:
+    f.write("""
+Product Manual: Smart Thermostat
+
+Installation:
+1. Turn off power at the circuit breaker
+2. Remove old thermostat
+3. Connect wires to matching terminals
+4. Mount the base plate
+5. Attach the display unit
+6. Restore power
+
+Features:
+- Wi-Fi connectivity
+- Voice control support
+- Energy usage reports
+- Geofencing auto-away
+- Learning schedule
+
+Troubleshooting:
+- If display is blank, check power connection
+- If Wi-Fi won't connect, restart router
+- If temperature is inaccurate, recalibrate sensor
+""")
+
+# Create base agent with knowledge
+agent = Agent(
+    name="TechSupport",
+    instructions="You are a technical support assistant.",
+    knowledge=[sample_doc],
+    user_id="comparison_user",
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+print("=" * 60)
+print("Agent vs AutoRagAgent Comparison")
+print("=" * 60)
+
+# Using Agent directly - always uses RAG when knowledge is configured
+print("\n[Using Agent Directly]")
+print("Agent with knowledge always retrieves context for every query.")
+print("\nQuery: 'Hello!'")
+response = agent.chat("Hello!")
+print(f"Response: {response}")
+
+print("\nQuery: 'How do I install the thermostat?'")
+response = agent.chat("How do I install the thermostat?")
+print(f"Response: {response[:300]}...")
+
+# Using AutoRagAgent - decides when to retrieve
+print("\n" + "=" * 60)
+print("[Using AutoRagAgent]")
+print("AutoRagAgent decides when to retrieve based on query heuristics.")
+
+auto_rag = AutoRagAgent(agent=agent, retrieval_policy="auto")
+
+print("\nQuery: 'Hello!' (short greeting - skips retrieval)")
+response = auto_rag.chat("Hello!")
+print(f"Response: {response}")
+
+print("\nQuery: 'How do I install the thermostat?' (question - retrieves)")
+response = auto_rag.chat("How do I install the thermostat?")
+print(f"Response: {response[:300]}...")
+
+# Summary
+print("\n" + "=" * 60)
+print("Summary:")
+print("-" * 60)
+print("""
+| Approach      | Retrieval Behavior              | Best For                    |
+|---------------|--------------------------------|------------------------------|
+| Agent         | Always retrieves (if knowledge)| Consistent RAG responses     |
+| AutoRagAgent  | Decides per query              | Mixed chat + RAG workloads   |
+
+AutoRagAgent is ideal when:
+- You have a chatbot that sometimes needs knowledge, sometimes doesn't
+- You want to reduce unnecessary retrieval overhead
+- You need fine-grained control over retrieval behavior
+""")
+
+# Cleanup
+os.remove(sample_doc)
+
+print("=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/python/rag/auto_rag_agent_basic.py

@@ -0,0 +1,79 @@
+"""
+AutoRagAgent Basic Example
+
+Demonstrates basic usage of AutoRagAgent for automatic RAG retrieval decision.
+AutoRagAgent wraps an Agent and decides when to retrieve context based on query heuristics.
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent, AutoRagAgent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a sample document for testing
+sample_doc = "/tmp/sample_doc.txt"
+with open(sample_doc, "w") as f:
+    f.write("""
+PraisonAI Framework Documentation
+
+PraisonAI is an AI agents framework that supports:
+- Single agent workflows
+- Multi-agent collaboration
+- RAG (Retrieval Augmented Generation)
+- Tool integration
+- Memory and context management
+
+Key Features:
+1. AutoRagAgent - Automatic retrieval decision
+2. Knowledge bases - Document indexing and search
+3. Hybrid retrieval - Dense + BM25 search
+4. Reranking - Improve result relevance
+""")
+
+# Create agent with knowledge
+agent = Agent(
+    name="DocBot",
+    instructions="You are a helpful documentation assistant. Answer questions based on the provided context.",
+    knowledge=[sample_doc],
+    user_id="example_user",  # Required for RAG retrieval
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+# Wrap with AutoRagAgent (default: auto policy)
+auto_rag = AutoRagAgent(agent=agent)
+
+print("=" * 60)
+print("AutoRagAgent Basic Example")
+print("=" * 60)
+
+# Test 1: Question that should trigger retrieval
+print("\n[Test 1] Question about documentation (should retrieve):")
+response = auto_rag.chat("What features does PraisonAI support?")
+print(f"Response: {response}")
+
+# Test 2: Short greeting that should skip retrieval
+print("\n[Test 2] Short greeting (should skip retrieval):")
+response = auto_rag.chat("Hi!")
+print(f"Response: {response}")
+
+# Test 3: Another question
+print("\n[Test 3] Another question (should retrieve):")
+response = auto_rag.chat("What is AutoRagAgent?")
+print(f"Response: {response}")
+
+# Cleanup
+os.remove(sample_doc)
+
+print("\n" + "=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/python/rag/auto_rag_agent_policy.py

@@ -0,0 +1,97 @@
+"""
+AutoRagAgent Policy Example
+
+Demonstrates different retrieval policies:
+- auto: Decides based on query heuristics (default)
+- always: Always retrieves context
+- never: Never retrieves, direct chat only
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent, AutoRagAgent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a sample document
+sample_doc = "/tmp/policy_doc.txt"
+with open(sample_doc, "w") as f:
+    f.write("""
+Company Return Policy
+
+Our return policy allows returns within 30 days of purchase.
+Items must be in original condition with tags attached.
+Refunds are processed within 5-7 business days.
+Exchanges are available for different sizes or colors.
+""")
+
+# Create base agent with knowledge
+agent = Agent(
+    name="PolicyBot",
+    instructions="You are a customer service assistant.",
+    knowledge=[sample_doc],
+    user_id="policy_user",
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+print("=" * 60)
+print("AutoRagAgent Policy Example")
+print("=" * 60)
+
+# Policy 1: AUTO (default)
+print("\n[Policy: AUTO] - Decides based on query heuristics")
+auto_rag = AutoRagAgent(agent=agent, retrieval_policy="auto")
+
+print("  Query: 'What is the return policy?' (should retrieve)")
+response = auto_rag.chat("What is the return policy?")
+print(f"  Response: {response[:200]}...")
+
+print("\n  Query: 'Hello' (should skip)")
+response = auto_rag.chat("Hello")
+print(f"  Response: {response}")
+
+# Policy 2: ALWAYS
+print("\n" + "-" * 60)
+print("[Policy: ALWAYS] - Always retrieves context")
+always_rag = AutoRagAgent(agent=agent, retrieval_policy="always")
+
+print("  Query: 'Hello' (will retrieve even for greeting)")
+response = always_rag.chat("Hello")
+print(f"  Response: {response[:200]}...")
+
+# Policy 3: NEVER
+print("\n" + "-" * 60)
+print("[Policy: NEVER] - Never retrieves, direct chat only")
+never_rag = AutoRagAgent(agent=agent, retrieval_policy="never")
+
+print("  Query: 'What is the return policy?' (will NOT retrieve)")
+response = never_rag.chat("What is the return policy?")
+print(f"  Response: {response[:200]}...")
+
+# Per-call overrides
+print("\n" + "-" * 60)
+print("[Per-call Overrides]")
+
+print("  Force retrieval on 'auto' policy:")
+response = auto_rag.chat("Hi there", force_retrieval=True)
+print(f"  Response: {response[:200]}...")
+
+print("\n  Skip retrieval on 'auto' policy:")
+response = auto_rag.chat("What is the return window?", skip_retrieval=True)
+print(f"  Response: {response[:200]}...")
+
+# Cleanup
+os.remove(sample_doc)
+
+print("\n" + "=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/python/rag/rag_basic.py

@@ -0,0 +1,70 @@
+"""
+RAG Basic Example
+
+Demonstrates basic RAG (Retrieval Augmented Generation) with an Agent.
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a sample document
+sample_doc = "/tmp/rag_basic_doc.txt"
+with open(sample_doc, "w") as f:
+    f.write("""
+Machine Learning Fundamentals
+
+Machine learning is a subset of artificial intelligence that enables systems
+to learn and improve from experience without being explicitly programmed.
+
+Types of Machine Learning:
+1. Supervised Learning - Learning from labeled data
+2. Unsupervised Learning - Finding patterns in unlabeled data
+3. Reinforcement Learning - Learning through trial and error
+
+Common Algorithms:
+- Linear Regression
+- Decision Trees
+- Neural Networks
+- Support Vector Machines
+""")
+
+# Create agent with RAG
+agent = Agent(
+    name="MLExpert",
+    instructions="You are a machine learning expert. Answer questions based on the provided context.",
+    knowledge=[sample_doc],
+    user_id="rag_user",
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+print("=" * 60)
+print("RAG Basic Example")
+print("=" * 60)
+
+# Query with RAG
+print("\nQuery: What are the types of machine learning?")
+response = agent.chat("What are the types of machine learning?")
+print(f"Response: {response}")
+
+print("\nQuery: What algorithms are commonly used?")
+response = agent.chat("What algorithms are commonly used?")
+print(f"Response: {response}")
+
+# Cleanup
+os.remove(sample_doc)
+
+print("\n" + "=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/python/rag/rag_hybrid.py

@@ -0,0 +1,94 @@
+"""
+RAG Hybrid Retrieval Example
+
+Demonstrates hybrid retrieval (dense + BM25 keyword search) for better results.
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent, AutoRagAgent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a sample document with technical content
+sample_doc = "/tmp/rag_hybrid_doc.txt"
+with open(sample_doc, "w") as f:
+    f.write("""
+API Documentation
+
+Authentication:
+All API requests require an API key in the X-API-Key header.
+Rate limits: 100 requests per minute for free tier, 1000 for pro tier.
+
+Endpoints:
+
+POST /api/v1/users
+Creates a new user account.
+Required fields: email, password, name
+Returns: user_id, created_at
+
+GET /api/v1/users/{id}
+Retrieves user information by ID.
+Returns: email, name, created_at, last_login
+
+PUT /api/v1/users/{id}
+Updates user information.
+Optional fields: name, email, password
+
+DELETE /api/v1/users/{id}
+Deletes a user account. Requires admin privileges.
+
+Error Codes:
+- 400: Bad Request - Invalid input
+- 401: Unauthorized - Missing or invalid API key
+- 403: Forbidden - Insufficient permissions
+- 404: Not Found - Resource doesn't exist
+- 429: Too Many Requests - Rate limit exceeded
+""")
+
+# Create agent with knowledge
+agent = Agent(
+    name="APIDocBot",
+    instructions="You are an API documentation assistant.",
+    knowledge=[sample_doc],
+    user_id="hybrid_user",
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+print("=" * 60)
+print("RAG Hybrid Retrieval Example")
+print("=" * 60)
+
+# Standard retrieval
+print("\n[Standard Retrieval]")
+auto_rag_standard = AutoRagAgent(agent=agent, hybrid=False)
+response = auto_rag_standard.chat("What error code means rate limit exceeded?")
+print(f"Response: {response}")
+
+# Hybrid retrieval (dense + BM25)
+print("\n[Hybrid Retrieval - Dense + BM25]")
+auto_rag_hybrid = AutoRagAgent(agent=agent, hybrid=True)
+response = auto_rag_hybrid.chat("What error code means rate limit exceeded?")
+print(f"Response: {response}")
+
+# Hybrid with reranking for best quality
+print("\n[Hybrid + Reranking]")
+auto_rag_best = AutoRagAgent(agent=agent, hybrid=True, rerank=True, top_k=10)
+response = auto_rag_best.chat("How do I create a new user via the API?")
+print(f"Response: {response}")
+
+# Cleanup
+os.remove(sample_doc)
+
+print("\n" + "=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/python/rag/rag_with_citations.py

@@ -0,0 +1,84 @@
+"""
+RAG with Citations Example
+
+Demonstrates RAG with citation tracking for source attribution.
+
+Requirements:
+    pip install praisonaiagents
+    
+Environment:
+    OPENAI_API_KEY - Required for LLM calls
+"""
+
+import os
+from praisonaiagents import Agent, AutoRagAgent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create multiple sample documents
+doc1 = "/tmp/citation_doc1.txt"
+with open(doc1, "w") as f:
+    f.write("""
+Research Paper: Climate Change Effects
+
+Global temperatures have risen by 1.1°C since pre-industrial times.
+Sea levels are rising at 3.3mm per year.
+Arctic ice is declining at 13% per decade.
+""")
+
+doc2 = "/tmp/citation_doc2.txt"
+with open(doc2, "w") as f:
+    f.write("""
+Research Paper: Renewable Energy
+
+Solar energy capacity has grown 20x in the last decade.
+Wind power now provides 7% of global electricity.
+Battery storage costs have dropped 89% since 2010.
+""")
+
+# Create agent with multiple knowledge sources
+agent = Agent(
+    name="ResearchBot",
+    instructions="You are a research assistant. Always cite your sources.",
+    knowledge=[doc1, doc2],
+    user_id="citation_user",
+    llm="openai/gpt-4o-mini",
+    verbose=False,
+)
+
+print("=" * 60)
+print("RAG with Citations Example")
+print("=" * 60)
+
+# AutoRagAgent with citations enabled (default)
+auto_rag = AutoRagAgent(
+    agent=agent,
+    citations=True,  # Include citations in response
+)
+
+print("\nQuery: What are the key climate change statistics?")
+response = auto_rag.chat("What are the key climate change statistics?")
+print(f"Response:\n{response}")
+
+print("\n" + "-" * 60)
+print("\nQuery: How has renewable energy grown?")
+response = auto_rag.chat("How has renewable energy grown?")
+print(f"Response:\n{response}")
+
+# Without citations
+print("\n" + "-" * 60)
+print("\n[Without Citations]")
+auto_rag_no_cite = AutoRagAgent(agent=agent, citations=False)
+response = auto_rag_no_cite.chat("What is the rate of sea level rise?")
+print(f"Response: {response}")
+
+# Cleanup
+os.remove(doc1)
+os.remove(doc2)
+
+print("\n" + "=" * 60)
+print("Example completed successfully!")
+print("=" * 60)

examples/rag/README.md

@@ -0,0 +1,121 @@
+# RAG Examples
+
+This directory contains comprehensive examples demonstrating RAG (Retrieval Augmented Generation) with PraisonAI Agents.
+
+## Core RAG Concepts
+
+| Example | Description | Key Concepts |
+|---------|-------------|--------------|
+| `basic_retrieval.py` | Fundamental retrieve-then-generate pattern | Knowledge base, context injection |
+| `auto_retrieval.py` | Intelligent retrieval decisions with AutoRagAgent | Conditional RAG, retrieval policies |
+| `chunking_strategies.py` | Document splitting approaches | Paragraph, section, fixed-size chunking |
+| `hybrid_search.py` | Dense + sparse retrieval combination | Semantic search, keyword matching |
+| `reranking.py` | Two-stage retrieval with reranking | Precision optimization, cross-encoders |
+
+## Advanced RAG Patterns
+
+| Example | Description | Key Concepts |
+|---------|-------------|--------------|
+| `multi_document.py` | Synthesizing across multiple sources | Cross-referencing, source diversity |
+| `knowledge_graph.py` | Relationship-aware retrieval | Entity connections, multi-hop reasoning |
+| `external_sources.py` | Web, API, and database augmentation | Real-time data, hybrid sources |
+| `structured_output.py` | Guided and constrained generation | JSON output, Pydantic schemas |
+| `retrieval_policies.py` | Agent-decided retrieval strategies | Adaptive top-k, priority filtering |
+| `citations.py` | Source attribution and verification | Inline citations, verification |
+
+## Application Examples
+
+### PDF Q&A (`rag_pdf_qa.py`)
+
+Basic RAG example showing how to:
+- Use Agent with knowledge parameter
+- Create explicit RAG pipeline with citations
+- Stream responses
+
+```bash
+python rag_pdf_qa.py
+```
+
+### Multi-Agent RAG (`rag_multi_agent.py`)
+
+Advanced example showing:
+- Shared knowledge base across multiple agents
+- Collaborative RAG workflow
+- Sequential task processing
+
+```bash
+python rag_multi_agent.py
+```
+
+### RAG Evaluation (`rag_evaluation.py`)
+
+Evaluation example showing:
+- Golden query testing
+- Retrieval accuracy metrics
+- Answer relevance checking
+
+```bash
+python rag_evaluation.py
+```
+
+## Quick Start
+
+Run any example:
+
+```bash
+# Basic RAG
+python basic_retrieval.py
+
+# Auto RAG with intelligent decisions
+python auto_retrieval.py
+
+# Hybrid search (dense + sparse)
+python hybrid_search.py
+
+# RAG with citations
+python citations.py
+```
+
+## Installation
+
+```bash
+pip install "praisonaiagents[knowledge]"
+```
+
+## CLI Usage
+
+```bash
+# Index documents
+praisonai rag index ./documents --collection my_docs
+
+# Query
+praisonai rag query "What is the main finding?" --collection my_docs
+
+# Interactive chat
+praisonai rag chat --collection my_docs
+
+# Evaluate
+praisonai rag eval golden_queries.json --collection my_docs
+```
+
+## Configuration
+
+Create `rag_config.yaml`:
+
+```yaml
+knowledge:
+  collection: my_docs
+  chunking:
+    strategy: recursive
+    chunk_size: 512
+
+rag:
+  top_k: 5
+  min_score: 0.3
+  include_citations: true
+```
+
+Use with:
+```bash
+praisonai rag query "Question" --config rag_config.yaml
+```

examples/rag/auto_retrieval.py

@@ -0,0 +1,207 @@
+"""
+Auto RAG: Intelligent Retrieval Decisions
+
+This example demonstrates AutoRagAgent - an agent that automatically decides
+when to retrieve context based on the query type.
+
+RAG Concept: Conditional retrieval - not every query needs RAG. Simple greetings
+or general knowledge questions can be answered directly, while domain-specific
+questions benefit from retrieval.
+"""
+
+from praisonaiagents import Agent, AutoRagAgent
+
+# Sample knowledge base: Software development best practices as text strings
+DEV_PRACTICES = [
+    """Code Review Guidelines:
+    - Review code within 24 hours of submission
+    - Focus on logic, security, and maintainability
+    - Limit reviews to 400 lines of code at a time
+    - Use constructive language and suggest alternatives
+    - Automate style checks with linters""",
+    
+    """Testing Strategy:
+    - Aim for 80% code coverage minimum
+    - Write unit tests before integration tests
+    - Use mocking for external dependencies
+    - Run tests in CI/CD pipeline before merge
+    - Include edge cases and error scenarios""",
+    
+    """Documentation Standards:
+    - Document public APIs with examples
+    - Keep README files up to date
+    - Use inline comments for complex logic only
+    - Maintain a changelog for version history
+    - Include setup instructions for new developers""",
+    
+    """Security Practices:
+    - Never commit secrets or API keys
+    - Use environment variables for configuration
+    - Validate all user inputs
+    - Keep dependencies updated
+    - Conduct regular security audits"""
+]
+
+
+def auto_rag_basic():
+    """Demonstrate AutoRagAgent with automatic retrieval decisions."""
+    
+    # Build context from knowledge
+    context = "\n\n".join(DEV_PRACTICES)
+    
+    # Create base agent with context in instructions
+    base_agent = Agent(
+        name="Dev Coach",
+        instructions=f"""You are a software development coach.
+        Answer questions about development best practices.
+        Be concise and practical in your responses.
+        
+        KNOWLEDGE BASE:
+        {context}""",
+        verbose=False
+    )
+    
+    # Wrap with AutoRagAgent for intelligent retrieval
+    auto_agent = AutoRagAgent(agent=base_agent)
+    
+    # Mix of queries - some need retrieval, some don't
+    queries = [
+        # Should trigger retrieval (domain-specific)
+        "What are the code review guidelines?",
+        "How much code coverage should we aim for?",
+        
+        # Should skip retrieval (general/greeting)
+        "Hello, how are you?",
+        "What is 2 + 2?",
+        
+        # Should trigger retrieval (domain-specific)
+        "What security practices should we follow?",
+    ]
+    
+    print("=" * 60)
+    print("AUTO RAG: Intelligent Retrieval Decisions")
+    print("=" * 60)
+    print("\nAutoRagAgent decides when to retrieve based on query type.\n")
+    
+    for query in queries:
+        print(f"📝 Query: {query}")
+        response = auto_agent.chat(query)
+        print(f"💡 Answer: {response[:200]}..." if len(str(response)) > 200 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def auto_rag_with_policies():
+    """Demonstrate different retrieval policies."""
+    from praisonaiagents import AutoRagConfig
+    from praisonaiagents.agents.auto_rag_agent import RetrievalPolicy
+    
+    # Build context
+    context = "\n\n".join(DEV_PRACTICES)
+    
+    # Create base agent
+    base_agent = Agent(
+        name="Policy Demo Agent",
+        instructions=f"""You answer questions about software development.
+        
+        KNOWLEDGE BASE:
+        {context}""",
+        verbose=False
+    )
+    
+    print("\n" + "=" * 60)
+    print("RETRIEVAL POLICIES COMPARISON")
+    print("=" * 60)
+    
+    query = "What are the documentation standards?"
+    
+    # Policy: AUTO (default) - agent decides
+    auto_config = AutoRagConfig(retrieval_policy=RetrievalPolicy.AUTO)
+    auto_agent = AutoRagAgent(agent=base_agent, config=auto_config)
+    
+    print(f"\n📝 Query: {query}")
+    print("\n🔄 Policy: AUTO (agent decides)")
+    response = auto_agent.chat(query)
+    print(f"   Answer: {response[:150]}...")
+    
+    # Policy: ALWAYS - always retrieve
+    always_config = AutoRagConfig(retrieval_policy=RetrievalPolicy.ALWAYS)
+    always_agent = AutoRagAgent(agent=base_agent, config=always_config)
+    
+    print("\n🔄 Policy: ALWAYS (force retrieval)")
+    response = always_agent.chat(query)
+    print(f"   Answer: {response[:150]}...")
+    
+    # Policy: NEVER - never retrieve (use parametric knowledge only)
+    never_config = AutoRagConfig(retrieval_policy=RetrievalPolicy.NEVER)
+    never_agent = AutoRagAgent(agent=base_agent, config=never_config)
+    
+    print("\n🔄 Policy: NEVER (no retrieval)")
+    response = never_agent.chat(query)
+    print(f"   Answer: {response[:150]}...")
+
+
+def auto_rag_config_options():
+    """Demonstrate AutoRagConfig options."""
+    from praisonaiagents import AutoRagConfig
+    
+    # Build context
+    context = "\n\n".join(DEV_PRACTICES)
+    
+    base_agent = Agent(
+        name="Config Demo",
+        instructions=f"""You are a helpful assistant with development knowledge.
+        
+        KNOWLEDGE BASE:
+        {context}""",
+        verbose=False
+    )
+    
+    print("\n" + "=" * 60)
+    print("AUTO RAG CONFIG OPTIONS")
+    print("=" * 60)
+    
+    # Config with citations enabled
+    config_with_citations = AutoRagConfig(
+        include_citations=True,
+        top_k=3,
+        max_context_tokens=2000
+    )
+    agent_with_citations = AutoRagAgent(agent=base_agent, config=config_with_citations)
+    
+    query = "What testing practices should we follow?"
+    print(f"\n📝 Query: {query}")
+    
+    print("\n🔄 With citations enabled (top_k=3):")
+    response = agent_with_citations.chat(query)
+    print(f"   {response[:200]}...")
+    
+    # Config without citations
+    config_no_citations = AutoRagConfig(
+        include_citations=False,
+        top_k=5
+    )
+    agent_no_citations = AutoRagAgent(agent=base_agent, config=config_no_citations)
+    
+    print("\n🔄 Without citations (top_k=5):")
+    response = agent_no_citations.chat(query)
+    print(f"   {response[:200]}...")
+
+
+def main():
+    """Run all auto RAG examples."""
+    print("\n🚀 PraisonAI Auto RAG Examples\n")
+    
+    # Example 1: Basic AutoRagAgent
+    auto_rag_basic()
+    
+    # Example 2: Different retrieval policies
+    auto_rag_with_policies()
+    
+    # Example 3: Config options
+    auto_rag_config_options()
+    
+    print("\n✅ Auto RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/basic_retrieval.py

@@ -0,0 +1,131 @@
+"""
+Basic RAG: Retrieve and Generate
+
+This example demonstrates the fundamental RAG pattern in PraisonAI:
+1. Provide context to an agent
+2. Agent uses context to answer questions accurately
+3. Generate grounded answers using the provided context
+
+RAG Concept: The core retrieve-then-generate pattern that grounds LLM responses
+in factual content, reducing hallucinations.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Technology company profiles as text strings
+COMPANY_PROFILES = [
+    """NovaTech Solutions specializes in cloud infrastructure and DevOps automation.
+    Founded in 2018, they serve over 500 enterprise clients globally.
+    Key products: CloudSync (infrastructure orchestration), DevPipeline (CI/CD platform).
+    Headquarters: Austin, Texas. Employees: 1,200.""",
+    
+    """GreenLeaf Analytics provides environmental monitoring and sustainability reporting.
+    Established in 2015, they work with governments and corporations on climate data.
+    Key products: EcoTrack (emissions monitoring), SustainReport (ESG reporting).
+    Headquarters: Seattle, Washington. Employees: 450.""",
+    
+    """QuantumBridge Financial offers algorithmic trading and risk management solutions.
+    Started in 2012, they manage over $50 billion in assets for institutional clients.
+    Key products: AlgoTrader Pro (trading platform), RiskShield (portfolio analytics).
+    Headquarters: New York City. Employees: 800.""",
+    
+    """MediCore Health develops AI-powered diagnostic tools for healthcare providers.
+    Founded in 2019, they partner with 200+ hospitals across North America.
+    Key products: DiagnosAI (medical imaging analysis), PatientFlow (care coordination).
+    Headquarters: Boston, Massachusetts. Employees: 350."""
+]
+
+
+def basic_rag_example():
+    """Demonstrate basic RAG with context injection."""
+    
+    # Build context from knowledge base
+    context = "\n\n".join(COMPANY_PROFILES)
+    
+    # Create an agent with instructions
+    agent = Agent(
+        name="Company Analyst",
+        instructions=f"""You are a business analyst who answers questions about companies.
+        Use only the following company information to answer questions accurately.
+        If the information isn't available, say so clearly.
+        
+        COMPANY DATABASE:
+        {context}""",
+        verbose=False
+    )
+    
+    # Test queries
+    queries = [
+        "What products does NovaTech Solutions offer?",
+        "Which company focuses on environmental monitoring?",
+        "How many employees does QuantumBridge Financial have?",
+        "What is MediCore Health's main focus area?"
+    ]
+    
+    print("=" * 60)
+    print("BASIC RAG EXAMPLE: Company Knowledge Base")
+    print("=" * 60)
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def rag_with_query_context():
+    """Demonstrate per-query context injection for RAG."""
+    
+    # Create a general agent
+    agent = Agent(
+        name="Research Assistant",
+        instructions="You answer questions based on the context provided in each query.",
+        verbose=False
+    )
+    
+    # Simulate retrieved context (in real RAG, this comes from vector search)
+    retrieved_context = """
+    The Pacific Ocean is the largest and deepest ocean on Earth.
+    It covers approximately 165.25 million square kilometers.
+    The Mariana Trench, located in the Pacific, is the deepest known point at 10,994 meters.
+    The Pacific Ocean was named by explorer Ferdinand Magellan in 1520.
+    """
+    
+    query = "What is the deepest point in the Pacific Ocean?"
+    
+    # Build prompt with context (RAG pattern)
+    prompt_with_context = f"""Use the following context to answer the question.
+
+Context:
+{retrieved_context}
+
+Question: {query}
+
+Answer based only on the context provided:"""
+    
+    print("\n" + "=" * 60)
+    print("RAG WITH PER-QUERY CONTEXT INJECTION")
+    print("=" * 60)
+    
+    print(f"\n📚 Context: {retrieved_context[:100]}...")
+    print(f"\n📝 Query: {query}")
+    
+    response = agent.chat(prompt_with_context)
+    print(f"\n💡 Answer: {response}")
+
+
+def main():
+    """Run all basic RAG examples."""
+    print("\n🚀 PraisonAI Basic RAG Examples\n")
+    
+    # Example 1: Basic RAG with knowledge base
+    basic_rag_example()
+    
+    # Example 2: Per-query context injection
+    rag_with_query_context()
+    
+    print("\n✅ Basic RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/chunking_strategies.py

@@ -0,0 +1,272 @@
+"""
+Chunking Strategies for RAG
+
+This example demonstrates different approaches to splitting documents into
+chunks for effective retrieval.
+
+RAG Concept: Chunking is critical for RAG quality. Too large chunks dilute
+relevance; too small chunks lose context. The right strategy depends on
+your content type and query patterns.
+"""
+
+from praisonaiagents import Agent
+
+# Sample long document: Product documentation
+PRODUCT_DOCUMENTATION = """
+# CloudManager Pro - Complete User Guide
+
+## Chapter 1: Getting Started
+
+CloudManager Pro is an enterprise cloud management platform that helps organizations
+monitor, optimize, and secure their multi-cloud infrastructure. This guide covers
+installation, configuration, and daily operations.
+
+### 1.1 System Requirements
+
+Before installing CloudManager Pro, ensure your system meets these requirements:
+- Operating System: Ubuntu 20.04+, RHEL 8+, or Windows Server 2019+
+- Memory: Minimum 16GB RAM, recommended 32GB for production
+- Storage: 100GB SSD for application, additional storage for logs
+- Network: Outbound HTTPS access to cloud provider APIs
+
+### 1.2 Installation Steps
+
+1. Download the installer from the customer portal
+2. Run the installation script with root privileges
+3. Configure the database connection
+4. Set up the initial admin account
+5. Verify the installation with the health check command
+
+## Chapter 2: Dashboard Overview
+
+The main dashboard provides a unified view of your cloud resources across all
+connected providers. Key metrics displayed include:
+
+### 2.1 Resource Metrics
+
+- Total compute instances across all clouds
+- Storage utilization and growth trends
+- Network bandwidth consumption
+- Cost breakdown by provider and project
+
+### 2.2 Alert Summary
+
+The alert panel shows active incidents categorized by severity:
+- Critical: Immediate action required (service outages)
+- Warning: Attention needed within 24 hours
+- Info: Informational notifications
+
+## Chapter 3: Cost Optimization
+
+CloudManager Pro includes powerful cost optimization features that can reduce
+your cloud spending by 20-40%.
+
+### 3.1 Right-sizing Recommendations
+
+The platform analyzes resource utilization patterns and suggests optimal
+instance sizes. Recommendations are based on:
+- CPU utilization over 14-day periods
+- Memory usage patterns
+- Network I/O requirements
+
+### 3.2 Reserved Instance Planning
+
+Use the RI Planner to identify opportunities for reserved instance purchases.
+The tool calculates potential savings based on your usage patterns and
+commitment preferences (1-year vs 3-year terms).
+
+## Chapter 4: Security Features
+
+### 4.1 Compliance Monitoring
+
+CloudManager Pro continuously monitors your infrastructure against common
+compliance frameworks including SOC 2, HIPAA, and PCI-DSS. Non-compliant
+resources are flagged with remediation guidance.
+
+### 4.2 Access Control
+
+Role-based access control (RBAC) allows fine-grained permissions:
+- Admin: Full access to all features
+- Operator: Can view and modify resources
+- Viewer: Read-only access to dashboards
+- Billing: Access to cost and billing features only
+"""
+
+
+def chunk_by_paragraphs(text: str, min_length: int = 100) -> list:
+    """Split text into paragraph-based chunks."""
+    paragraphs = text.split("\n\n")
+    chunks = []
+    current_chunk = ""
+    
+    for para in paragraphs:
+        para = para.strip()
+        if not para:
+            continue
+            
+        if len(current_chunk) + len(para) < 500:
+            current_chunk += "\n\n" + para if current_chunk else para
+        else:
+            if len(current_chunk) >= min_length:
+                chunks.append({"content": current_chunk.strip()})
+            current_chunk = para
+    
+    if current_chunk and len(current_chunk) >= min_length:
+        chunks.append({"content": current_chunk.strip()})
+    
+    return chunks
+
+
+def chunk_by_sections(text: str) -> list:
+    """Split text by markdown headers (sections)."""
+    import re
+    
+    # Split by headers (## or ###)
+    sections = re.split(r'\n(?=##+ )', text)
+    chunks = []
+    
+    for section in sections:
+        section = section.strip()
+        if len(section) > 50:  # Skip very short sections
+            # Extract title if present
+            lines = section.split('\n')
+            title = lines[0].replace('#', '').strip() if lines[0].startswith('#') else "Untitled"
+            chunks.append({
+                "id": title.lower().replace(' ', '_')[:30],
+                "content": section
+            })
+    
+    return chunks
+
+
+def chunk_by_fixed_size(text: str, chunk_size: int = 500, overlap: int = 50) -> list:
+    """Split text into fixed-size chunks with overlap."""
+    chunks = []
+    start = 0
+    
+    while start < len(text):
+        end = start + chunk_size
+        chunk_text = text[start:end]
+        
+        # Try to break at sentence boundary
+        if end < len(text):
+            last_period = chunk_text.rfind('.')
+            if last_period > chunk_size * 0.5:
+                end = start + last_period + 1
+                chunk_text = text[start:end]
+        
+        chunks.append({"content": chunk_text.strip()})
+        start = end - overlap
+    
+    return chunks
+
+
+def demonstrate_chunking_strategies():
+    """Show different chunking approaches and their effects."""
+    
+    print("=" * 60)
+    print("CHUNKING STRATEGIES COMPARISON")
+    print("=" * 60)
+    
+    # Strategy 1: Paragraph-based chunking
+    para_chunks = chunk_by_paragraphs(PRODUCT_DOCUMENTATION)
+    print(f"\n📄 Paragraph Chunking: {len(para_chunks)} chunks")
+    print(f"   Average chunk size: {sum(len(c['content']) for c in para_chunks) // len(para_chunks)} chars")
+    print(f"   Sample chunk: {para_chunks[0]['content'][:100]}...")
+    
+    # Strategy 2: Section-based chunking
+    section_chunks = chunk_by_sections(PRODUCT_DOCUMENTATION)
+    print(f"\n📑 Section Chunking: {len(section_chunks)} chunks")
+    print(f"   Average chunk size: {sum(len(c['content']) for c in section_chunks) // len(section_chunks)} chars")
+    print(f"   Sections: {[c['id'] for c in section_chunks[:5]]}...")
+    
+    # Strategy 3: Fixed-size chunking
+    fixed_chunks = chunk_by_fixed_size(PRODUCT_DOCUMENTATION, chunk_size=400, overlap=50)
+    print(f"\n📏 Fixed-Size Chunking (400 chars, 50 overlap): {len(fixed_chunks)} chunks")
+    print(f"   Average chunk size: {sum(len(c['content']) for c in fixed_chunks) // len(fixed_chunks)} chars")
+
+
+def rag_with_section_chunks():
+    """Demonstrate RAG using section-based chunks."""
+    
+    # Create section-based chunks
+    chunks = chunk_by_sections(PRODUCT_DOCUMENTATION)
+    
+    # Build context from chunks
+    context = "\n\n".join([f"[{c['id']}]\n{c['content']}" for c in chunks])
+    
+    # Create agent with chunked knowledge in instructions
+    agent = Agent(
+        name="Product Expert",
+        instructions=f"""You are a CloudManager Pro product expert.
+        Answer questions using the product documentation.
+        Be specific and reference relevant sections when helpful.
+        
+        PRODUCT DOCUMENTATION:
+        {context}""",
+        verbose=False
+    )
+    
+    queries = [
+        "What are the system requirements for CloudManager Pro?",
+        "How can I reduce cloud costs?",
+        "What compliance frameworks are supported?"
+    ]
+    
+    print("\n" + "=" * 60)
+    print("RAG WITH SECTION-BASED CHUNKS")
+    print("=" * 60)
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response[:250]}..." if len(str(response)) > 250 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def semantic_chunking_concept():
+    """Explain semantic chunking concept (agent-driven)."""
+    
+    print("\n" + "=" * 60)
+    print("SEMANTIC CHUNKING CONCEPT")
+    print("=" * 60)
+    
+    print("""
+    Semantic chunking goes beyond fixed rules by considering meaning:
+    
+    1. **Sentence Embedding Similarity**
+       - Compute embeddings for each sentence
+       - Group sentences with similar embeddings
+       - Split when similarity drops below threshold
+    
+    2. **Topic-Based Chunking**
+       - Identify topic shifts in the document
+       - Create chunks that maintain topical coherence
+    
+    3. **Agent-Driven Chunking**
+       - Use an LLM to identify logical boundaries
+       - Preserve context and relationships
+    
+    PraisonAI's Knowledge system handles chunking automatically,
+    but understanding these strategies helps optimize retrieval quality.
+    """)
+
+
+def main():
+    """Run all chunking strategy examples."""
+    print("\n🚀 PraisonAI Chunking Strategies Examples\n")
+    
+    # Example 1: Compare chunking strategies
+    demonstrate_chunking_strategies()
+    
+    # Example 2: RAG with section chunks
+    rag_with_section_chunks()
+    
+    # Example 3: Semantic chunking concept
+    semantic_chunking_concept()
+    
+    print("\n✅ Chunking strategy examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/citations.py

@@ -0,0 +1,370 @@
+"""
+RAG with Citations: Source Attribution and Verification
+
+This example demonstrates how to include citations and source references
+in RAG responses for transparency and verification.
+
+RAG Concept: Trust in AI-generated answers requires verification. Citations
+link answers back to source documents, enabling fact-checking and building
+user confidence.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Legal documents with clear sources
+LEGAL_DOCUMENTS = [
+    {
+        "id": "policy_001",
+        "source": "Employee Handbook v2024",
+        "section": "Section 3.2 - Leave Policies",
+        "content": """
+        Annual Leave Entitlement:
+        - Full-time employees: 20 days per year
+        - Part-time employees: Pro-rated based on hours
+        - Unused leave: Up to 5 days may carry over to next year
+        - Leave requests: Submit at least 2 weeks in advance
+        - Approval: Manager approval required for leave > 3 consecutive days
+        """
+    },
+    {
+        "id": "policy_002",
+        "source": "Employee Handbook v2024",
+        "section": "Section 4.1 - Remote Work",
+        "content": """
+        Remote Work Policy:
+        - Eligibility: Employees in approved roles after 6 months tenure
+        - Maximum: 3 days per week remote work allowed
+        - Requirements: Reliable internet, dedicated workspace
+        - Core hours: Must be available 10am-3pm local time
+        - Equipment: Company provides laptop; employee provides internet
+        """
+    },
+    {
+        "id": "policy_003",
+        "source": "Benefits Guide 2024",
+        "section": "Chapter 2 - Health Insurance",
+        "content": """
+        Health Insurance Coverage:
+        - Provider: BlueCross BlueShield
+        - Coverage: Employee + dependents eligible
+        - Premium: Company pays 80%, employee pays 20%
+        - Deductible: $500 individual, $1000 family
+        - Enrollment: During annual open enrollment or qualifying life event
+        """
+    },
+    {
+        "id": "policy_004",
+        "source": "Benefits Guide 2024",
+        "section": "Chapter 5 - Retirement",
+        "content": """
+        401(k) Retirement Plan:
+        - Eligibility: After 90 days of employment
+        - Company match: 100% up to 4% of salary
+        - Vesting: Immediate vesting for employee contributions
+        - Company match vesting: 3-year graded schedule
+        - Investment options: 15 fund choices available
+        """
+    },
+    {
+        "id": "policy_005",
+        "source": "Code of Conduct 2024",
+        "section": "Article 7 - Conflicts of Interest",
+        "content": """
+        Conflict of Interest Policy:
+        - Disclosure: All potential conflicts must be disclosed to HR
+        - Outside employment: Requires written approval
+        - Financial interests: Cannot hold >5% in competitors
+        - Gifts: Cannot accept gifts valued over $50
+        - Relationships: Must disclose family relationships with vendors
+        """
+    }
+]
+
+
+def basic_citations():
+    """Demonstrate basic citation inclusion in RAG responses."""
+    
+    print("=" * 60)
+    print("BASIC CITATIONS IN RAG")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['source']}, {d['section']}]\n{d['content']}" for d in LEGAL_DOCUMENTS])
+    
+    agent = Agent(
+        name="HR Policy Expert",
+        instructions=f"""You are an HR policy expert who answers employee questions.
+        
+        IMPORTANT: Always cite your sources using this format:
+        [Source: Document Name, Section]
+        
+        Include the citation immediately after the relevant information.
+        If information comes from multiple sources, cite each one.
+        
+        POLICY DOCUMENTS:
+        {context}""",
+        verbose=False
+    )
+    
+    queries = [
+        "How many vacation days do I get?",
+        "Can I work from home?",
+        "What's the company match for 401k?"
+    ]
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer with Citations:\n{response}")
+        print("-" * 40)
+
+
+def structured_citations():
+    """Demonstrate structured citation format."""
+    
+    print("\n" + "=" * 60)
+    print("STRUCTURED CITATIONS")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['source']}, {d['section']}]\n{d['content']}" for d in LEGAL_DOCUMENTS])
+    
+    agent = Agent(
+        name="Policy Researcher",
+        instructions=f"""You provide policy information with structured citations.
+        
+        Format your response as:
+        
+        ANSWER:
+        [Your answer here]
+        
+        SOURCES:
+        1. [Document] - [Section] - [Relevant quote]
+        2. [Document] - [Section] - [Relevant quote]
+        
+        Always include at least one source citation.
+        
+        POLICY DOCUMENTS:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "What are the requirements for remote work eligibility?"
+    
+    print(f"\n📝 Query: {query}")
+    response = agent.chat(query)
+    print(f"\n💡 Structured Response:\n{response}")
+
+
+def inline_citations():
+    """Demonstrate inline citation style."""
+    
+    print("\n" + "=" * 60)
+    print("INLINE CITATIONS (Academic Style)")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['source']}, {d['section']}]\n{d['content']}" for d in LEGAL_DOCUMENTS])
+    
+    agent = Agent(
+        name="Academic Researcher",
+        instructions=f"""You write responses with inline citations like academic papers.
+        
+        Use numbered citations [1], [2], etc. in the text.
+        List full references at the end.
+        
+        Example:
+        "Employees receive 20 days of leave [1]. Remote work is allowed
+        for up to 3 days per week [2]."
+        
+        References:
+        [1] Employee Handbook v2024, Section 3.2
+        [2] Employee Handbook v2024, Section 4.1
+        
+        POLICY DOCUMENTS:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "Summarize the key employee benefits."
+    
+    print(f"\n📝 Query: {query}")
+    response = agent.chat(query)
+    print(f"\n💡 Academic-Style Response:\n{response}")
+
+
+def citation_verification():
+    """Demonstrate citation verification concept."""
+    
+    print("\n" + "=" * 60)
+    print("CITATION VERIFICATION")
+    print("=" * 60)
+    
+    print("""
+    🔍 Citation Verification Process:
+    
+    1. **Extract Citations**
+       Parse the agent's response to find citation markers
+       
+    2. **Locate Source Documents**
+       Match citations to documents in knowledge base
+       
+    3. **Verify Claims**
+       Check if the cited text supports the claim
+       
+    4. **Flag Discrepancies**
+       Highlight any mismatches or unsupported claims
+    
+    Example Verification:
+    """)
+    
+    # Simulated verification
+    claim = "Employees get 20 days of annual leave"
+    cited_source = "Employee Handbook v2024, Section 3.2"
+    source_text = "Full-time employees: 20 days per year"
+    
+    print(f"   Claim: \"{claim}\"")
+    print(f"   Citation: {cited_source}")
+    print(f"   Source Text: \"{source_text}\"")
+    print("   Verification: ✅ SUPPORTED")
+    
+    print("""
+    
+    Implementation:
+    ```python
+    def verify_citation(claim: str, source_id: str, knowledge) -> bool:
+        # Get source document
+        source = knowledge.get(source_id)
+        
+        # Check if claim is supported by source
+        # (In practice, use semantic similarity)
+        return claim_supported_by_source(claim, source)
+    ```
+    """)
+
+
+def multi_source_synthesis():
+    """Demonstrate synthesizing from multiple sources with citations."""
+    
+    print("\n" + "=" * 60)
+    print("MULTI-SOURCE SYNTHESIS WITH CITATIONS")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['source']}, {d['section']}]\n{d['content']}" for d in LEGAL_DOCUMENTS])
+    
+    agent = Agent(
+        name="Benefits Advisor",
+        instructions=f"""You synthesize information from multiple policy documents.
+        
+        When answering:
+        1. Gather relevant information from all sources
+        2. Synthesize into a coherent answer
+        3. Cite each source for the specific information it provides
+        4. Note if sources have different or complementary information
+        
+        Format: Include [Source: X] after each piece of information.
+        
+        POLICY DOCUMENTS:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "Give me a complete overview of employee benefits and policies."
+    
+    print(f"\n📝 Query: {query}")
+    response = agent.chat(query)
+    print(f"\n💡 Multi-Source Synthesis:\n{response}")
+
+
+def citation_best_practices():
+    """Share best practices for citations in RAG."""
+    
+    print("\n" + "=" * 60)
+    print("CITATION BEST PRACTICES")
+    print("=" * 60)
+    
+    print("""
+    📚 Best Practices for RAG Citations:
+    
+    1. **Include Metadata in Knowledge Base**
+       ```python
+       documents = [
+           {
+               "id": "doc_001",
+               "source": "Policy Manual",
+               "section": "Chapter 3",
+               "date": "2024-01-15",
+               "author": "HR Department",
+               "content": "..."
+           }
+       ]
+       ```
+    
+    2. **Instruct Agent to Cite**
+       - Be explicit in instructions about citation format
+       - Provide examples of expected citation style
+       - Require citations for factual claims
+    
+    3. **Use Consistent Citation Format**
+       - Inline: [1], [2] with reference list
+       - Parenthetical: (Source, Section)
+       - Footnote style: ¹, ² with notes
+    
+    4. **Enable Verification**
+       - Include document IDs for programmatic lookup
+       - Store enough metadata to locate original
+       - Consider including page numbers or paragraphs
+    
+    5. **Handle Missing Sources**
+       - Instruct agent to acknowledge when info isn't in sources
+       - Distinguish between sourced and general knowledge
+       - Use phrases like "Based on the provided documents..."
+    
+    6. **Citation Granularity**
+       - Document level: Good for general attribution
+       - Section level: Better for verification
+       - Quote level: Best for accuracy-critical applications
+    
+    Example Agent Instructions:
+    ```python
+    instructions = '''
+    Answer questions using the provided documents.
+    
+    Rules:
+    - Cite sources for all factual claims
+    - Use format: [Source: Document Name, Section]
+    - If information isn't in the documents, say so
+    - Never make claims without citation
+    '''
+    ```
+    """)
+
+
+def main():
+    """Run all citation examples."""
+    print("\n🚀 PraisonAI RAG Citations Examples\n")
+    
+    # Example 1: Basic citations
+    basic_citations()
+    
+    # Example 2: Structured citations
+    structured_citations()
+    
+    # Example 3: Inline citations
+    inline_citations()
+    
+    # Example 4: Citation verification
+    citation_verification()
+    
+    # Example 5: Multi-source synthesis
+    multi_source_synthesis()
+    
+    # Example 6: Best practices
+    citation_best_practices()
+    
+    print("\n✅ Citation examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/external_sources.py

@@ -0,0 +1,353 @@
+"""
+External Sources RAG: Beyond Vector Search
+
+This example demonstrates RAG with external knowledge sources like
+web search, APIs, and databases.
+
+RAG Concept: RAG isn't limited to pre-indexed documents. External sources
+provide real-time, up-to-date information that complements static knowledge.
+"""
+
+from praisonaiagents import Agent
+
+# Simulated external data sources
+def mock_web_search(query: str) -> list:
+    """Simulate web search results."""
+    # In production, this would call a real search API
+    mock_results = {
+        "weather": [
+            {"title": "Current Weather", "snippet": "Today's forecast: Partly cloudy, high of 72°F (22°C), low of 58°F (14°C). Humidity at 45%."},
+            {"title": "Weekly Outlook", "snippet": "Rain expected Wednesday and Thursday. Weekend looks sunny with temperatures in the mid-70s."}
+        ],
+        "news": [
+            {"title": "Tech Industry Update", "snippet": "Major tech companies report strong Q3 earnings. AI investments continue to grow across sectors."},
+            {"title": "Market Summary", "snippet": "Stock markets closed higher today. S&P 500 up 0.8%, Nasdaq up 1.2%."}
+        ],
+        "default": [
+            {"title": "General Information", "snippet": "Search results would appear here with relevant web content."}
+        ]
+    }
+    
+    for key in mock_results:
+        if key in query.lower():
+            return mock_results[key]
+    return mock_results["default"]
+
+
+def mock_database_query(query: str) -> dict:
+    """Simulate database query results."""
+    # In production, this would query a real database
+    mock_data = {
+        "user_stats": {
+            "total_users": 15420,
+            "active_today": 3250,
+            "new_signups": 127,
+            "retention_rate": "78%"
+        },
+        "sales_data": {
+            "monthly_revenue": "$1.2M",
+            "top_product": "Enterprise Plan",
+            "growth_rate": "15% MoM",
+            "avg_deal_size": "$4,500"
+        },
+        "system_health": {
+            "uptime": "99.97%",
+            "avg_response_time": "145ms",
+            "error_rate": "0.02%",
+            "active_servers": 24
+        }
+    }
+    
+    for key in mock_data:
+        if key.replace("_", " ") in query.lower() or key in query.lower():
+            return mock_data[key]
+    return {"message": "No matching data found"}
+
+
+def mock_api_call(endpoint: str) -> dict:
+    """Simulate API call results."""
+    # In production, this would call a real API
+    mock_responses = {
+        "stock_price": {"symbol": "ACME", "price": 142.50, "change": "+2.3%"},
+        "exchange_rate": {"from": "USD", "to": "EUR", "rate": 0.92},
+        "crypto": {"bitcoin": "$67,500", "ethereum": "$3,450"}
+    }
+    
+    for key in mock_responses:
+        if key in endpoint.lower():
+            return mock_responses[key]
+    return {"status": "endpoint not found"}
+
+
+# Static knowledge base for hybrid approach
+COMPANY_KNOWLEDGE = [
+    {
+        "id": "company_overview",
+        "content": """
+        Acme Corporation is a technology company founded in 2015.
+        Headquarters: San Francisco, CA
+        Products: Enterprise software, cloud services, AI solutions
+        Mission: Empowering businesses through intelligent automation
+        """
+    },
+    {
+        "id": "product_info",
+        "content": """
+        Acme Products:
+        - Acme Cloud: Infrastructure-as-a-service platform
+        - Acme AI: Machine learning toolkit for enterprises
+        - Acme Connect: Integration and API management
+        Pricing: Starter ($99/mo), Professional ($499/mo), Enterprise (custom)
+        """
+    }
+]
+
+
+def web_augmented_rag():
+    """Demonstrate RAG augmented with web search."""
+    
+    print("=" * 60)
+    print("WEB-AUGMENTED RAG")
+    print("=" * 60)
+    
+    # Build context from company knowledge
+    context = "\n\n".join([f"[{k['id']}]\n{k['content']}" for k in COMPANY_KNOWLEDGE])
+    
+    # Create agent that can use web search
+    agent = Agent(
+        name="Research Assistant",
+        instructions=f"""You are a research assistant that combines internal knowledge
+        with web search results. When answering:
+        1. Check if the question requires current/real-time information
+        2. Use web search for news, weather, current events
+        3. Combine web results with your knowledge for comprehensive answers
+        4. Clearly indicate when information comes from web search.
+        
+        COMPANY KNOWLEDGE:
+        {context}""",
+        verbose=False
+    )
+    
+    # Simulate web-augmented queries
+    queries = [
+        ("What's the weather like today?", True),  # Needs web
+        ("Tell me about Acme Corporation's products", False),  # Static knowledge
+        ("What's happening in the tech industry?", True),  # Needs web
+    ]
+    
+    for query, needs_web in queries:
+        print(f"\n📝 Query: {query}")
+        
+        if needs_web:
+            # Augment with web search
+            web_results = mock_web_search(query)
+            web_context = "\n".join([f"- {r['title']}: {r['snippet']}" for r in web_results])
+            augmented_query = f"{query}\n\nWeb search results:\n{web_context}"
+            response = agent.chat(augmented_query)
+            print("🌐 (Web-augmented)")
+        else:
+            response = agent.chat(query)
+            print("📚 (Static knowledge)")
+        
+        print(f"💡 Answer: {response[:250]}..." if len(str(response)) > 250 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def database_augmented_rag():
+    """Demonstrate RAG augmented with database queries."""
+    
+    print("\n" + "=" * 60)
+    print("DATABASE-AUGMENTED RAG")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{k['id']}]\n{k['content']}" for k in COMPANY_KNOWLEDGE])
+    
+    agent = Agent(
+        name="Business Analyst",
+        instructions=f"""You are a business analyst with access to company databases.
+        Interpret data accurately and provide actionable insights.
+        When presenting numbers, add context and trends.
+        
+        COMPANY KNOWLEDGE:
+        {context}""",
+        verbose=False
+    )
+    
+    queries = [
+        "How are our user stats looking?",
+        "Give me a sales summary",
+        "What's our system health status?"
+    ]
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        
+        # Fetch database data
+        db_data = mock_database_query(query)
+        db_context = f"Database results: {db_data}"
+        
+        augmented_query = f"{query}\n\n{db_context}"
+        response = agent.chat(augmented_query)
+        
+        print(f"🗄️ DB Data: {db_data}")
+        print(f"💡 Analysis: {response[:200]}..." if len(str(response)) > 200 else f"💡 Analysis: {response}")
+        print("-" * 40)
+
+
+def api_augmented_rag():
+    """Demonstrate RAG augmented with API calls."""
+    
+    print("\n" + "=" * 60)
+    print("API-AUGMENTED RAG")
+    print("=" * 60)
+    
+    agent = Agent(
+        name="Financial Assistant",
+        instructions="""You are a financial assistant with access to market APIs.
+        Provide accurate financial information and context.
+        Always note that prices are subject to change.""",
+        user_id="api_demo"
+    )
+    
+    queries = [
+        ("What's the ACME stock price?", "stock_price"),
+        ("USD to EUR exchange rate?", "exchange_rate"),
+        ("Crypto market update?", "crypto")
+    ]
+    
+    for query, endpoint in queries:
+        print(f"\n📝 Query: {query}")
+        
+        # Fetch API data
+        api_data = mock_api_call(endpoint)
+        api_context = f"API response: {api_data}"
+        
+        augmented_query = f"{query}\n\n{api_context}"
+        response = agent.chat(augmented_query)
+        
+        print(f"🔌 API Data: {api_data}")
+        print(f"💡 Response: {response[:200]}..." if len(str(response)) > 200 else f"💡 Response: {response}")
+        print("-" * 40)
+
+
+def hybrid_source_rag():
+    """Combine multiple external sources."""
+    
+    print("\n" + "=" * 60)
+    print("HYBRID SOURCE RAG")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{k['id']}]\n{k['content']}" for k in COMPANY_KNOWLEDGE])
+    
+    agent = Agent(
+        name="Executive Assistant",
+        instructions=f"""You are an executive assistant with access to multiple data sources.
+        Synthesize information from static knowledge, databases, and APIs.
+        Provide comprehensive briefings that combine all relevant data.
+        
+        COMPANY KNOWLEDGE:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "Give me a complete business briefing for today"
+    
+    # Gather from multiple sources
+    db_stats = mock_database_query("user_stats")
+    db_sales = mock_database_query("sales_data")
+    db_health = mock_database_query("system_health")
+    api_stock = mock_api_call("stock_price")
+    web_news = mock_web_search("news")
+    
+    combined_context = f"""
+    User Statistics: {db_stats}
+    Sales Data: {db_sales}
+    System Health: {db_health}
+    Stock Price: {api_stock}
+    Industry News: {[r['snippet'] for r in web_news]}
+    """
+    
+    augmented_query = f"{query}\n\nData from multiple sources:\n{combined_context}"
+    
+    print(f"\n📝 Query: {query}")
+    print("\n📊 Data Sources:")
+    print("   - Database: user_stats, sales_data, system_health")
+    print("   - API: stock_price")
+    print("   - Web: news search")
+    
+    response = agent.chat(augmented_query)
+    print(f"\n💡 Executive Briefing:\n{response}")
+
+
+def external_source_patterns():
+    """Explain external source patterns."""
+    
+    print("\n" + "=" * 60)
+    print("EXTERNAL SOURCE PATTERNS")
+    print("=" * 60)
+    
+    print("""
+    🌐 External Source Integration Patterns:
+    
+    1. **Query-Time Augmentation**
+       - Fetch external data when query arrives
+       - Inject into prompt as additional context
+       - Best for: Real-time data needs
+    
+    2. **Scheduled Refresh**
+       - Periodically update knowledge base from external sources
+       - Index external data for faster retrieval
+       - Best for: Semi-static external data
+    
+    3. **Tool-Based Retrieval**
+       - Give agent tools to fetch external data
+       - Agent decides when to use external sources
+       - Best for: Complex, multi-step queries
+    
+    4. **Hybrid Static + Dynamic**
+       - Combine indexed knowledge with real-time fetches
+       - Use static for stable info, dynamic for current
+       - Best for: Comprehensive answers
+    
+    Implementation Example:
+    ```python
+    def web_search_tool(query: str) -> str:
+        # Call search API
+        results = search_api.search(query)
+        return format_results(results)
+    
+    agent = Agent(
+        knowledge=static_docs,
+        tools=[web_search_tool],
+        instructions="Use web search for current events..."
+    )
+    ```
+    """)
+
+
+def main():
+    """Run all external source RAG examples."""
+    print("\n🚀 PraisonAI External Sources RAG Examples\n")
+    
+    # Example 1: Web-augmented RAG
+    web_augmented_rag()
+    
+    # Example 2: Database-augmented RAG
+    database_augmented_rag()
+    
+    # Example 3: API-augmented RAG
+    api_augmented_rag()
+    
+    # Example 4: Hybrid sources
+    hybrid_source_rag()
+    
+    # Example 5: Patterns
+    external_source_patterns()
+    
+    print("\n✅ External sources RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/hybrid_search.py

@@ -0,0 +1,275 @@
+"""
+Hybrid Search: Combining Dense and Sparse Retrieval
+
+This example demonstrates hybrid retrieval that combines semantic (dense)
+search with keyword (sparse) search for improved accuracy.
+
+RAG Concept: Dense embeddings capture meaning but may miss exact matches.
+Sparse/keyword search finds exact terms but lacks semantic understanding.
+Hybrid search combines both for best results.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Technical troubleshooting guides
+TROUBLESHOOTING_GUIDES = [
+    {
+        "id": "error_001",
+        "content": """
+        Error Code: ERR_CONNECTION_REFUSED
+        
+        This error occurs when the client cannot establish a connection to the server.
+        
+        Common Causes:
+        - Server is not running or has crashed
+        - Firewall blocking the connection port
+        - Incorrect host or port configuration
+        - Network connectivity issues
+        
+        Resolution Steps:
+        1. Verify the server process is running: `systemctl status myservice`
+        2. Check firewall rules: `sudo ufw status`
+        3. Test port connectivity: `telnet hostname 8080`
+        4. Review server logs for startup errors
+        """
+    },
+    {
+        "id": "error_002",
+        "content": """
+        Error Code: ERR_OUT_OF_MEMORY
+        
+        This error indicates the application has exhausted available memory.
+        
+        Common Causes:
+        - Memory leak in application code
+        - Insufficient heap size configuration
+        - Too many concurrent connections
+        - Large data processing without streaming
+        
+        Resolution Steps:
+        1. Increase heap size: `-Xmx4g` for Java applications
+        2. Enable memory profiling to identify leaks
+        3. Implement pagination for large datasets
+        4. Add memory limits to container configurations
+        """
+    },
+    {
+        "id": "error_003",
+        "content": """
+        Error Code: ERR_SSL_CERTIFICATE_EXPIRED
+        
+        This error means the SSL/TLS certificate has passed its validity date.
+        
+        Common Causes:
+        - Certificate not renewed before expiration
+        - Automatic renewal process failed
+        - Wrong certificate installed
+        
+        Resolution Steps:
+        1. Check certificate expiry: `openssl x509 -enddate -noout -in cert.pem`
+        2. Renew certificate with your CA or Let's Encrypt
+        3. Update certificate files on the server
+        4. Restart the web server to load new certificate
+        """
+    },
+    {
+        "id": "error_004",
+        "content": """
+        Error Code: ERR_DATABASE_DEADLOCK
+        
+        A deadlock occurs when two transactions block each other indefinitely.
+        
+        Common Causes:
+        - Transactions acquiring locks in different orders
+        - Long-running transactions holding locks
+        - Missing indexes causing table scans with locks
+        
+        Resolution Steps:
+        1. Review transaction isolation levels
+        2. Ensure consistent lock ordering across queries
+        3. Add appropriate indexes to reduce lock duration
+        4. Implement retry logic for deadlock exceptions
+        """
+    },
+    {
+        "id": "error_005",
+        "content": """
+        Error Code: ERR_RATE_LIMIT_EXCEEDED
+        
+        The API has rejected requests due to exceeding the rate limit.
+        
+        Common Causes:
+        - Too many requests in a short time window
+        - Missing request throttling in client code
+        - Retry loops without backoff
+        
+        Resolution Steps:
+        1. Implement exponential backoff for retries
+        2. Cache responses to reduce API calls
+        3. Use bulk endpoints where available
+        4. Request rate limit increase if needed
+        """
+    }
+]
+
+
+def demonstrate_search_types():
+    """Show the difference between semantic and keyword search concepts."""
+    
+    print("=" * 60)
+    print("SEARCH TYPES COMPARISON")
+    print("=" * 60)
+    
+    print("""
+    📊 DENSE (Semantic) Search:
+       - Uses vector embeddings to capture meaning
+       - "memory issues" matches "out of memory" and "RAM exhausted"
+       - Good for natural language queries
+       - May miss exact technical terms
+    
+    📊 SPARSE (Keyword) Search:
+       - Uses term frequency and exact matching
+       - "ERR_SSL_CERTIFICATE_EXPIRED" matches exactly
+       - Good for error codes, IDs, technical terms
+       - Misses synonyms and paraphrases
+    
+    📊 HYBRID Search:
+       - Combines both approaches
+       - Weighted scoring: (α × dense_score) + ((1-α) × sparse_score)
+       - Best of both worlds for technical documentation
+    """)
+
+
+def hybrid_rag_example():
+    """Demonstrate hybrid retrieval with an agent."""
+    
+    # Build context from troubleshooting guides
+    context = "\n\n".join([f"[{g['id']}]\n{g['content']}" for g in TROUBLESHOOTING_GUIDES])
+    
+    # Create agent with context in instructions
+    agent = Agent(
+        name="Tech Support",
+        instructions=f"""You are a technical support specialist.
+        Help users troubleshoot errors using the knowledge base.
+        Always mention the specific error code when relevant.
+        Provide step-by-step resolution guidance.
+        
+        TROUBLESHOOTING KNOWLEDGE BASE:
+        {context}""",
+        verbose=False
+    )
+    
+    # Test with different query types
+    queries = [
+        # Semantic query (natural language)
+        "My application is running out of memory, what should I do?",
+        
+        # Exact match query (error code)
+        "ERR_SSL_CERTIFICATE_EXPIRED",
+        
+        # Mixed query
+        "Getting connection refused error when connecting to port 8080",
+        
+        # Conceptual query
+        "How do I handle API throttling?"
+    ]
+    
+    print("\n" + "=" * 60)
+    print("HYBRID RAG IN ACTION")
+    print("=" * 60)
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response[:300]}..." if len(str(response)) > 300 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def compare_retrieval_modes():
+    """Compare results with different retrieval configurations."""
+    
+    print("\n" + "=" * 60)
+    print("RETRIEVAL MODE COMPARISON")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{g['id']}]\n{g['content']}" for g in TROUBLESHOOTING_GUIDES])
+    
+    query = "database transaction blocking issue"
+    
+    # Agent with context
+    agent = Agent(
+        name="Search Agent",
+        instructions=f"""Answer based on the knowledge provided.
+        
+        KNOWLEDGE BASE:
+        {context}""",
+        verbose=False
+    )
+    
+    print(f"\n📝 Query: {query}")
+    
+    print("\n🔍 RAG Response:")
+    response = agent.chat(query)
+    print(f"   {response[:200]}...")
+    
+    print("\n💡 Note: Hybrid search combines semantic + keyword matching for best results.")
+
+
+def hybrid_search_tuning():
+    """Explain hybrid search tuning parameters."""
+    
+    print("\n" + "=" * 60)
+    print("HYBRID SEARCH TUNING")
+    print("=" * 60)
+    
+    print("""
+    Key parameters for hybrid search optimization:
+    
+    1. **Alpha (α) Weight** - Balance between dense and sparse
+       - α = 1.0: Pure semantic search
+       - α = 0.5: Equal weight (good default)
+       - α = 0.0: Pure keyword search
+    
+    2. **Top-K Retrieval** - Number of candidates
+       - Higher K: More context, slower, may dilute relevance
+       - Lower K: Faster, focused, may miss relevant docs
+       - Typical range: 3-10 for RAG
+    
+    3. **Reranking** - Second-pass scoring
+       - Cross-encoder reranking improves precision
+       - Adds latency but improves quality
+    
+    Example configuration:
+    ```python
+    knowledge_config = {
+        "hybrid": True,
+        "hybrid_alpha": 0.6,  # Favor semantic
+        "top_k": 5,
+        "rerank": True
+    }
+    ```
+    """)
+
+
+def main():
+    """Run all hybrid search examples."""
+    print("\n🚀 PraisonAI Hybrid Search Examples\n")
+    
+    # Example 1: Explain search types
+    demonstrate_search_types()
+    
+    # Example 2: Hybrid RAG in action
+    hybrid_rag_example()
+    
+    # Example 3: Compare retrieval modes
+    compare_retrieval_modes()
+    
+    # Example 4: Tuning guidance
+    hybrid_search_tuning()
+    
+    print("\n✅ Hybrid search examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/knowledge_graph.py

@@ -0,0 +1,304 @@
+"""
+Graph-Assisted RAG: Relationship-Aware Retrieval
+
+This example demonstrates how graph structures can enhance RAG by
+capturing relationships between entities and enabling path-based retrieval.
+
+RAG Concept: Traditional vector search finds similar documents but misses
+relationships. Graph-assisted RAG understands connections between entities,
+enabling multi-hop reasoning and relationship-aware answers.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Interconnected entities (simulating a knowledge graph)
+ENTITY_KNOWLEDGE = [
+    {
+        "id": "person_einstein",
+        "type": "person",
+        "content": """
+        Albert Einstein (1879-1955) was a theoretical physicist who developed
+        the theory of relativity. He received the Nobel Prize in Physics in 1921
+        for his explanation of the photoelectric effect. Einstein worked at the
+        Institute for Advanced Study in Princeton from 1933 until his death.
+        Key relationships: Collaborated with Niels Bohr, influenced by Max Planck,
+        mentored by Heinrich Weber.
+        """
+    },
+    {
+        "id": "person_bohr",
+        "type": "person",
+        "content": """
+        Niels Bohr (1885-1962) was a Danish physicist who made foundational
+        contributions to understanding atomic structure and quantum theory.
+        He received the Nobel Prize in Physics in 1922. Bohr founded the
+        Institute of Theoretical Physics in Copenhagen.
+        Key relationships: Debated with Einstein on quantum mechanics,
+        mentored Werner Heisenberg, influenced by Ernest Rutherford.
+        """
+    },
+    {
+        "id": "person_heisenberg",
+        "type": "person",
+        "content": """
+        Werner Heisenberg (1901-1976) was a German physicist and pioneer of
+        quantum mechanics. He formulated the uncertainty principle in 1927.
+        He received the Nobel Prize in Physics in 1932.
+        Key relationships: Student of Niels Bohr, collaborated with Max Born,
+        worked with Wolfgang Pauli.
+        """
+    },
+    {
+        "id": "concept_relativity",
+        "type": "concept",
+        "content": """
+        Theory of Relativity: A framework developed by Albert Einstein consisting
+        of special relativity (1905) and general relativity (1915). Special
+        relativity deals with objects moving at constant speeds, introducing
+        E=mc². General relativity describes gravity as the curvature of spacetime.
+        Related concepts: Spacetime, time dilation, gravitational waves.
+        Applications: GPS satellites, particle accelerators, cosmology.
+        """
+    },
+    {
+        "id": "concept_quantum",
+        "type": "concept",
+        "content": """
+        Quantum Mechanics: A fundamental theory describing nature at atomic scales.
+        Key principles include wave-particle duality, superposition, and entanglement.
+        Developed through contributions from Planck, Bohr, Heisenberg, Schrödinger.
+        Related concepts: Uncertainty principle, quantum tunneling, wave function.
+        Applications: Semiconductors, lasers, MRI machines, quantum computing.
+        """
+    },
+    {
+        "id": "institution_princeton",
+        "type": "institution",
+        "content": """
+        Institute for Advanced Study (Princeton): A private research center
+        founded in 1930. Notable members include Albert Einstein, John von Neumann,
+        Kurt Gödel, and Robert Oppenheimer. The institute focuses on theoretical
+        research in mathematics, natural sciences, and humanities.
+        Location: Princeton, New Jersey, USA.
+        """
+    },
+    {
+        "id": "institution_copenhagen",
+        "type": "institution",
+        "content": """
+        Niels Bohr Institute (Copenhagen): Founded in 1921 by Niels Bohr as the
+        Institute of Theoretical Physics. It became a world center for quantum
+        mechanics research. Notable visitors included Heisenberg, Pauli, and Dirac.
+        The "Copenhagen interpretation" of quantum mechanics originated here.
+        Location: Copenhagen, Denmark.
+        """
+    },
+    {
+        "id": "event_solvay",
+        "type": "event",
+        "content": """
+        Solvay Conferences: Series of physics conferences held in Brussels since 1911.
+        The 1927 Fifth Solvay Conference is famous for the Bohr-Einstein debates
+        on quantum mechanics. Attendees included Einstein, Bohr, Heisenberg,
+        Schrödinger, Dirac, and Marie Curie. These conferences shaped modern physics.
+        """
+    }
+]
+
+
+def graph_aware_rag():
+    """Demonstrate relationship-aware retrieval."""
+    
+    # Build context from entity knowledge
+    context = "\n\n".join([f"[{e['type'].upper()}: {e['id']}]\n{e['content']}" for e in ENTITY_KNOWLEDGE])
+    
+    # Create agent with entity knowledge
+    agent = Agent(
+        name="Physics Historian",
+        instructions=f"""You are a physics historian who understands the relationships
+        between scientists, concepts, and institutions. When answering:
+        1. Trace connections between entities
+        2. Explain how ideas and people influenced each other
+        3. Reference specific relationships mentioned in the knowledge base
+        4. Build a narrative that shows the interconnected nature of physics history.
+        
+        KNOWLEDGE GRAPH:
+        {context}""",
+        verbose=False
+    )
+    
+    # Relationship-focused queries
+    queries = [
+        "How were Einstein and Bohr connected?",
+        "Trace the lineage of quantum mechanics through its key figures.",
+        "What institutions were central to 20th century physics?",
+        "How did the Solvay Conferences shape physics?"
+    ]
+    
+    print("=" * 60)
+    print("GRAPH-ASSISTED RAG: Physics History Network")
+    print("=" * 60)
+    print("\nKnowledge graph entities:")
+    for entity in ENTITY_KNOWLEDGE:
+        print(f"  - [{entity['type']}] {entity['id']}")
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response[:350]}..." if len(str(response)) > 350 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def multi_hop_reasoning():
+    """Demonstrate multi-hop reasoning across entities."""
+    
+    print("\n" + "=" * 60)
+    print("MULTI-HOP REASONING")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{e['type'].upper()}: {e['id']}]\n{e['content']}" for e in ENTITY_KNOWLEDGE])
+    
+    agent = Agent(
+        name="Connection Finder",
+        instructions=f"""You excel at finding indirect connections between entities.
+        When asked about relationships, trace the path through intermediate entities.
+        Format your answer to show the chain of connections.
+        
+        KNOWLEDGE GRAPH:
+        {context}""",
+        verbose=False
+    )
+    
+    # Multi-hop query requiring traversal
+    query = """
+    What is the connection between the uncertainty principle and Princeton?
+    (Hint: trace through people and their relationships)
+    """
+    
+    print(f"\n📝 Multi-hop Query: {query.strip()}")
+    print("\n🔗 Expected path: Uncertainty Principle → Heisenberg → Bohr → Einstein → Princeton")
+    
+    response = agent.chat(query)
+    print(f"\n💡 Answer:\n{response}")
+
+
+def entity_type_filtering():
+    """Show filtering by entity type."""
+    
+    print("\n" + "=" * 60)
+    print("ENTITY TYPE FILTERING")
+    print("=" * 60)
+    
+    # Filter to only people
+    people_only = [e for e in ENTITY_KNOWLEDGE if e['type'] == 'person']
+    people_context = "\n\n".join([f"[{e['id']}]\n{e['content']}" for e in people_only])
+    
+    people_agent = Agent(
+        name="Biographer",
+        instructions=f"""You are a biographer focused on scientists' lives and relationships.
+        
+        SCIENTISTS:
+        {people_context}""",
+        verbose=False
+    )
+    
+    # Filter to only concepts
+    concepts_only = [e for e in ENTITY_KNOWLEDGE if e['type'] == 'concept']
+    concepts_context = "\n\n".join([f"[{e['id']}]\n{e['content']}" for e in concepts_only])
+    
+    concept_agent = Agent(
+        name="Concept Explainer",
+        instructions=f"""You explain scientific concepts and their relationships.
+        
+        CONCEPTS:
+        {concepts_context}""",
+        verbose=False
+    )
+    
+    query = "Tell me about the major developments in early 20th century physics."
+    
+    print(f"\n📝 Query: {query}")
+    
+    print("\n👤 People-focused view:")
+    response1 = people_agent.chat(query)
+    print(f"   {response1[:250]}...")
+    
+    print("\n💡 Concept-focused view:")
+    response2 = concept_agent.chat(query)
+    print(f"   {response2[:250]}...")
+
+
+def graph_rag_patterns():
+    """Explain graph RAG patterns."""
+    
+    print("\n" + "=" * 60)
+    print("GRAPH RAG PATTERNS")
+    print("=" * 60)
+    
+    print("""
+    📊 Graph-Assisted RAG Patterns:
+    
+    1. **Entity-Centric Retrieval**
+       - Store entities with their relationships
+       - Query retrieves entity + connected entities
+       - Good for: "Tell me about X and its connections"
+    
+    2. **Path-Based Retrieval**
+       - Find paths between two entities
+       - Retrieve all nodes along the path
+       - Good for: "How is X related to Y?"
+    
+    3. **Neighborhood Expansion**
+       - Start with query-matched entities
+       - Expand to include 1-hop or 2-hop neighbors
+       - Good for: Comprehensive context
+    
+    4. **Subgraph Extraction**
+       - Extract relevant subgraph for query
+       - Include nodes and edges as context
+       - Good for: Complex multi-entity questions
+    
+    Implementation in PraisonAI:
+    ```python
+    # Structure knowledge as entities with relationships
+    entities = [
+        {
+            "id": "entity_1",
+            "type": "person",
+            "content": "...",
+            "relationships": ["entity_2", "entity_3"]
+        },
+        ...
+    ]
+    
+    # Agent retrieves related entities automatically
+    agent = Agent(
+        knowledge=entities,
+        instructions="Trace relationships between entities..."
+    )
+    ```
+    """)
+
+
+def main():
+    """Run all graph-assisted RAG examples."""
+    print("\n🚀 PraisonAI Graph-Assisted RAG Examples\n")
+    
+    # Example 1: Graph-aware retrieval
+    graph_aware_rag()
+    
+    # Example 2: Multi-hop reasoning
+    multi_hop_reasoning()
+    
+    # Example 3: Entity type filtering
+    entity_type_filtering()
+    
+    # Example 4: Graph RAG patterns
+    graph_rag_patterns()
+    
+    print("\n✅ Graph-assisted RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/multi_document.py

@@ -0,0 +1,280 @@
+"""
+Multi-Document RAG: Synthesizing Information Across Sources
+
+This example demonstrates retrieving and synthesizing information from
+multiple documents to answer complex questions.
+
+RAG Concept: Real-world questions often require combining information
+from multiple sources. Multi-document RAG retrieves relevant chunks
+from different documents and synthesizes a coherent answer.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Multiple documents on different topics
+CLIMATE_REPORT = {
+    "id": "climate_2024",
+    "source": "Global Climate Report 2024",
+    "content": """
+    Global Climate Report 2024 - Executive Summary
+    
+    Global temperatures in 2024 reached 1.45°C above pre-industrial levels,
+    making it the warmest year on record. Key findings:
+    
+    - Arctic sea ice extent hit a new minimum in September
+    - Ocean heat content reached unprecedented levels
+    - Extreme weather events increased by 23% compared to the decade average
+    - CO2 concentrations reached 422 ppm, up from 417 ppm in 2023
+    
+    Regional impacts varied significantly. Europe experienced its hottest
+    summer, while parts of South America faced severe drought conditions.
+    The economic cost of climate-related disasters exceeded $380 billion.
+    """
+}
+
+ENERGY_REPORT = {
+    "id": "energy_2024",
+    "source": "World Energy Outlook 2024",
+    "content": """
+    World Energy Outlook 2024 - Key Highlights
+    
+    Renewable energy capacity grew by 35% in 2024, led by solar and wind.
+    Major developments:
+    
+    - Solar installations reached 1.5 TW cumulative capacity globally
+    - Wind power generated 12% of global electricity
+    - Battery storage capacity doubled to 500 GWh
+    - Electric vehicle sales reached 20 million units
+    
+    Despite progress, fossil fuels still account for 75% of primary energy.
+    Investment in clean energy reached $1.8 trillion, but $4 trillion annually
+    is needed to meet net-zero targets by 2050.
+    """
+}
+
+POLICY_REPORT = {
+    "id": "policy_2024",
+    "source": "Climate Policy Tracker 2024",
+    "content": """
+    Climate Policy Tracker 2024 - Global Progress
+    
+    145 countries have now committed to net-zero emissions targets.
+    Policy developments:
+    
+    - EU Carbon Border Adjustment Mechanism fully implemented
+    - US Inflation Reduction Act drove $300B in clean energy investment
+    - China pledged to peak emissions before 2030
+    - India launched National Green Hydrogen Mission
+    
+    Carbon pricing now covers 23% of global emissions, up from 20% in 2023.
+    Average carbon price increased to $45/ton. However, only 4% of emissions
+    are priced at levels consistent with Paris Agreement goals ($100+/ton).
+    """
+}
+
+TECH_REPORT = {
+    "id": "tech_2024",
+    "source": "Climate Technology Review 2024",
+    "content": """
+    Climate Technology Review 2024 - Breakthrough Innovations
+    
+    Several climate technologies reached commercial viability in 2024:
+    
+    - Direct Air Capture: Costs fell to $400/ton CO2, down from $600 in 2022
+    - Green Hydrogen: Production costs reached $3/kg in optimal locations
+    - Solid-state Batteries: Energy density improved 40%, enabling longer EV range
+    - Perovskite Solar Cells: Efficiency reached 33%, approaching silicon limits
+    
+    Emerging technologies to watch:
+    - Enhanced geothermal systems showing promise in non-volcanic regions
+    - Ocean-based carbon removal gaining investment interest
+    - AI-optimized grid management reducing curtailment by 15%
+    """
+}
+
+# Combine all documents
+ALL_DOCUMENTS = [CLIMATE_REPORT, ENERGY_REPORT, POLICY_REPORT, TECH_REPORT]
+
+
+def multi_document_rag():
+    """Demonstrate RAG across multiple documents."""
+    
+    # Build context from all documents
+    context = "\n\n".join([f"[{d['source']}]\n{d['content']}" for d in ALL_DOCUMENTS])
+    
+    # Create agent with multi-document knowledge
+    agent = Agent(
+        name="Climate Analyst",
+        instructions=f"""You are a climate and energy analyst.
+        Synthesize information from multiple reports to answer questions.
+        When information comes from different sources, mention which reports
+        you're drawing from. Provide comprehensive, well-rounded answers.
+        
+        REPORTS:
+        {context}""",
+        verbose=False
+    )
+    
+    # Questions that require multi-document synthesis
+    queries = [
+        "What is the current state of global climate and what are we doing about it?",
+        "How is renewable energy progressing and what policies support it?",
+        "What technologies are emerging to address climate change?",
+        "Compare the economic investment in clean energy with climate damage costs."
+    ]
+    
+    print("=" * 60)
+    print("MULTI-DOCUMENT RAG: Climate Analysis")
+    print("=" * 60)
+    print(f"\nKnowledge base: {len(ALL_DOCUMENTS)} documents")
+    print(f"Sources: {[d['source'] for d in ALL_DOCUMENTS]}")
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response[:400]}..." if len(str(response)) > 400 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def cross_reference_example():
+    """Show how agents can cross-reference information."""
+    
+    print("\n" + "=" * 60)
+    print("CROSS-REFERENCING ACROSS DOCUMENTS")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['source']}]\n{d['content']}" for d in ALL_DOCUMENTS])
+    
+    agent = Agent(
+        name="Cross-Reference Analyst",
+        instructions=f"""You are an analyst who excels at finding connections
+        between different reports. When answering:
+        1. Identify relevant information from each source
+        2. Note any contradictions or complementary data
+        3. Synthesize a coherent narrative
+        4. Cite your sources explicitly.
+        
+        REPORTS:
+        {context}""",
+        verbose=False
+    )
+    
+    query = """
+    Analyze the relationship between renewable energy growth (from Energy Report),
+    policy support (from Policy Report), and technology costs (from Tech Report).
+    How do these factors reinforce each other?
+    """
+    
+    print(f"\n📝 Complex Query: {query.strip()}")
+    response = agent.chat(query)
+    print(f"\n💡 Synthesized Answer:\n{response}")
+
+
+def document_filtering():
+    """Demonstrate filtering documents by metadata."""
+    
+    print("\n" + "=" * 60)
+    print("DOCUMENT FILTERING BY SOURCE")
+    print("=" * 60)
+    
+    # Create agents focused on specific document types
+    policy_agent = Agent(
+        name="Policy Expert",
+        instructions=f"""You are a policy expert. Focus only on policy-related information.
+        
+        POLICY REPORT:
+        {POLICY_REPORT['content']}""",
+        verbose=False
+    )
+    
+    tech_agent = Agent(
+        name="Technology Expert",
+        instructions=f"""You are a technology expert. Focus on technical innovations.
+        
+        TECHNOLOGY REPORT:
+        {TECH_REPORT['content']}""",
+        verbose=False
+    )
+    
+    query = "What progress has been made in addressing climate change?"
+    
+    print(f"\n📝 Query: {query}")
+    
+    print("\n🏛️ Policy Expert's View:")
+    policy_response = policy_agent.chat(query)
+    print(f"   {policy_response[:250]}...")
+    
+    print("\n🔬 Technology Expert's View:")
+    tech_response = tech_agent.chat(query)
+    print(f"   {tech_response[:250]}...")
+    
+    print("\n💡 Note: Different document subsets yield different perspectives!")
+
+
+def multi_document_best_practices():
+    """Share best practices for multi-document RAG."""
+    
+    print("\n" + "=" * 60)
+    print("MULTI-DOCUMENT RAG BEST PRACTICES")
+    print("=" * 60)
+    
+    print("""
+    📚 Best Practices for Multi-Document RAG:
+    
+    1. **Document Metadata**
+       - Include source, date, author in each document
+       - Enables filtering and citation
+    
+    2. **Consistent Chunking**
+       - Use similar chunk sizes across documents
+       - Maintains balanced retrieval
+    
+    3. **Source Diversity**
+       - Retrieve from multiple sources when possible
+       - Reduces single-source bias
+    
+    4. **Conflict Resolution**
+       - Instruct agent how to handle contradictions
+       - Prefer newer sources or authoritative ones
+    
+    5. **Citation Requirements**
+       - Ask agent to cite sources in responses
+       - Enables verification and trust
+    
+    Example configuration:
+    ```python
+    documents = [
+        {"id": "doc1", "source": "Report A", "date": "2024-01", "content": "..."},
+        {"id": "doc2", "source": "Report B", "date": "2024-06", "content": "..."},
+    ]
+    
+    agent = Agent(
+        knowledge=documents,
+        instructions="Always cite which report your information comes from."
+    )
+    ```
+    """)
+
+
+def main():
+    """Run all multi-document RAG examples."""
+    print("\n🚀 PraisonAI Multi-Document RAG Examples\n")
+    
+    # Example 1: Basic multi-document RAG
+    multi_document_rag()
+    
+    # Example 2: Cross-referencing
+    cross_reference_example()
+    
+    # Example 3: Document filtering
+    document_filtering()
+    
+    # Example 4: Best practices
+    multi_document_best_practices()
+    
+    print("\n✅ Multi-document RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/rag_evaluation.py

@@ -0,0 +1,150 @@
+"""
+RAG Evaluation Example
+
+This example demonstrates how to evaluate RAG quality by testing
+agent responses against expected answers.
+
+Usage:
+    python rag_evaluation.py
+"""
+
+from praisonaiagents import Agent
+
+
+# Sample knowledge for evaluation
+SAMPLE_KNOWLEDGE = """
+Product Overview:
+CloudManager Pro is an enterprise cloud management platform.
+Its main purpose is to help organizations monitor, optimize, and secure their multi-cloud infrastructure.
+
+Key Features:
+- Real-time monitoring across AWS, Azure, and GCP
+- Cost optimization with automated recommendations
+- Security compliance checking
+- Automated scaling and resource management
+
+Getting Started:
+1. Sign up at cloudmanager.example.com
+2. Connect your cloud accounts
+3. Configure monitoring dashboards
+4. Set up alerts and policies
+"""
+
+
+def create_test_queries():
+    """Create sample test queries for evaluation."""
+    return [
+        {
+            "query": "What is the main purpose of CloudManager Pro?",
+            "expected_contains": ["monitor", "cloud", "infrastructure"],
+        },
+        {
+            "query": "What are the key features?",
+            "expected_contains": ["monitoring", "cost", "security"],
+        },
+        {
+            "query": "How do I get started?",
+            "expected_contains": ["sign up", "connect", "configure"],
+        },
+    ]
+
+
+def evaluate_rag_agent(agent: Agent, test_queries: list) -> dict:
+    """
+    Evaluate RAG agent performance on test queries.
+    
+    Returns metrics including answer relevance accuracy.
+    """
+    results = {
+        "total": len(test_queries),
+        "passed": 0,
+        "details": [],
+    }
+    
+    for test in test_queries:
+        query = test["query"]
+        expected_terms = test.get("expected_contains", [])
+        
+        # Get agent response
+        response = agent.chat(query)
+        response_lower = response.lower()
+        
+        # Check if response contains expected terms
+        terms_found = sum(1 for term in expected_terms if term.lower() in response_lower)
+        pass_rate = terms_found / len(expected_terms) if expected_terms else 1.0
+        passed = pass_rate >= 0.5  # At least 50% of terms found
+        
+        if passed:
+            results["passed"] += 1
+        
+        results["details"].append({
+            "query": query,
+            "passed": passed,
+            "terms_found": terms_found,
+            "total_terms": len(expected_terms),
+            "pass_rate": pass_rate,
+            "answer_preview": response[:150],
+        })
+    
+    results["accuracy"] = results["passed"] / results["total"]
+    return results
+
+
+def print_results(results: dict):
+    """Print evaluation results in a formatted way."""
+    print("\n" + "=" * 60)
+    print("RAG Evaluation Results")
+    print("=" * 60)
+    
+    print(f"\nTotal Queries: {results['total']}")
+    print(f"Passed: {results['passed']}/{results['total']}")
+    print(f"Accuracy: {results['accuracy']:.1%}")
+    
+    print("\n" + "-" * 60)
+    print("Detailed Results:")
+    print("-" * 60)
+    
+    for i, detail in enumerate(results["details"], 1):
+        status = "✅ PASS" if detail["passed"] else "❌ FAIL"
+        print(f"\n[{i}] {status}: {detail['query']}")
+        print(f"    Terms Found: {detail['terms_found']}/{detail['total_terms']}")
+        print(f"    Answer: {detail['answer_preview']}...")
+
+
+def main():
+    print("=" * 60)
+    print("RAG Evaluation Example")
+    print("=" * 60)
+    
+    # Create agent with knowledge
+    agent = Agent(
+        name="Product Expert",
+        instructions=f"""You are a product expert who answers questions accurately.
+        Use only the following knowledge to answer questions.
+        
+        KNOWLEDGE:
+        {SAMPLE_KNOWLEDGE}""",
+        verbose=False
+    )
+    
+    # Get test queries
+    test_queries = create_test_queries()
+    
+    # Run evaluation
+    print(f"\nEvaluating {len(test_queries)} queries...")
+    results = evaluate_rag_agent(agent, test_queries)
+    
+    # Print results
+    print_results(results)
+    
+    # Return status
+    if results["accuracy"] < 0.8:
+        print("\n⚠️ WARNING: Accuracy below 80% threshold!")
+        return 1
+    
+    print("\n✅ Evaluation PASSED!")
+    return 0
+
+
+if __name__ == "__main__":
+    exit(main())

examples/rag/rag_multi_agent.py

@@ -0,0 +1,135 @@
+"""
+RAG Multi-Agent Example
+
+This example demonstrates how multiple agents can work together
+on a shared knowledge base for collaborative RAG.
+
+Usage:
+    python rag_multi_agent.py
+"""
+
+from praisonaiagents import Agent, PraisonAIAgents, Task
+
+
+# Shared knowledge base content
+SHARED_KNOWLEDGE = """
+# Climate Technology Report 2024
+
+## Executive Summary
+Global investment in climate technology reached $150 billion in 2024, 
+a 25% increase from the previous year. Key areas of growth include 
+renewable energy, carbon capture, and sustainable transportation.
+
+## Key Findings
+
+### Renewable Energy
+- Solar capacity grew by 40% globally
+- Wind energy now provides 15% of global electricity
+- Battery storage costs decreased by 20%
+
+### Carbon Capture
+- Direct air capture costs fell to $400/ton
+- 50 new carbon capture facilities announced
+- Total captured CO2 reached 50 million tons
+
+### Sustainable Transportation
+- Electric vehicle sales reached 25 million units
+- Hydrogen fuel cell technology advancing rapidly
+- Sustainable aviation fuel production doubled
+
+## Recommendations
+1. Increase investment in grid infrastructure
+2. Accelerate carbon capture deployment
+3. Support EV charging network expansion
+"""
+
+
+def main():
+    print("=" * 60)
+    print("Multi-Agent RAG: Collaborative Analysis")
+    print("=" * 60)
+    
+    # Create specialized agents with shared knowledge
+    researcher = Agent(
+        name="Researcher",
+        role="Research Analyst",
+        goal="Find and analyze relevant information",
+        instructions=f"""You are a research analyst. Your job is to:
+        1. Extract key facts and data points
+        2. Provide detailed analysis
+        3. Cite specific sections
+        
+        KNOWLEDGE BASE:
+        {SHARED_KNOWLEDGE}""",
+        verbose=False
+    )
+    
+    summarizer = Agent(
+        name="Summarizer",
+        role="Content Summarizer",
+        goal="Create concise summaries",
+        instructions=f"""You are a content summarizer. Your job is to:
+        1. Take research findings and create clear summaries
+        2. Highlight the most important points
+        3. Make complex information accessible
+        
+        KNOWLEDGE BASE:
+        {SHARED_KNOWLEDGE}""",
+        verbose=False
+    )
+    
+    writer = Agent(
+        name="Writer",
+        role="Report Writer",
+        goal="Create well-structured reports",
+        instructions=f"""You are a report writer. Your job is to:
+        1. Combine research and summaries into a cohesive report
+        2. Ensure proper structure and flow
+        3. Include key statistics
+        
+        KNOWLEDGE BASE:
+        {SHARED_KNOWLEDGE}""",
+        verbose=False
+    )
+    
+    # Define tasks
+    research_task = Task(
+        description="Research the main investment trends and growth areas in climate technology",
+        expected_output="Detailed research notes with key statistics",
+        agent=researcher,
+    )
+    
+    summary_task = Task(
+        description="Summarize the research findings into 5 key bullet points",
+        expected_output="Bullet-point summary of main findings",
+        agent=summarizer,
+    )
+    
+    report_task = Task(
+        description="Write a brief executive briefing based on the research and summary",
+        expected_output="A 2-paragraph executive briefing",
+        agent=writer,
+    )
+    
+    # Run the multi-agent workflow
+    print("\n🔄 Running multi-agent workflow...")
+    
+    agents = PraisonAIAgents(
+        agents=[researcher, summarizer, writer],
+        tasks=[research_task, summary_task, report_task],
+        process="sequential",
+        verbose=False
+    )
+    
+    result = agents.start()
+    
+    print("\n" + "=" * 60)
+    print("Final Report")
+    print("=" * 60)
+    print(result)
+    
+    print("\n✅ Multi-agent RAG example completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/rag_pdf_qa.py

@@ -0,0 +1,129 @@
+"""
+RAG Document Q&A Example
+
+This example demonstrates how to use RAG to answer questions
+about documents with proper context injection.
+
+Usage:
+    python rag_pdf_qa.py
+"""
+
+from praisonaiagents import Agent
+
+
+# Sample document content (simulating PDF content)
+DOCUMENT_CONTENT = """
+# Research Study: Impact of Remote Work on Productivity
+
+## Abstract
+This study examines the effects of remote work arrangements on employee 
+productivity across 50 technology companies during 2023-2024.
+
+## Methodology
+- Survey of 5,000 employees across 50 companies
+- Productivity metrics tracked over 12 months
+- Control group: in-office workers
+- Test group: remote and hybrid workers
+
+## Key Findings
+
+### Productivity Impact
+- Remote workers showed 13% higher productivity on average
+- Hybrid workers (3 days remote) showed 18% higher productivity
+- Fully remote workers reported 25% better work-life balance
+
+### Challenges Identified
+- Communication delays increased by 15%
+- Collaboration on complex projects took 10% longer
+- New employee onboarding was 20% slower remotely
+
+### Cost Analysis
+- Companies saved average of $11,000 per remote employee annually
+- Employees saved average of $4,500 in commuting costs
+- Office space reduction saved 30% on real estate costs
+
+## Recommendations
+1. Implement hybrid work model (2-3 days remote)
+2. Invest in collaboration tools
+3. Create structured onboarding for remote hires
+4. Establish clear communication protocols
+
+## Conclusion
+Remote work, when properly implemented, leads to improved productivity
+and significant cost savings for both employers and employees.
+"""
+
+
+def main():
+    # Method 1: Simple Agent with Context
+    print("=" * 60)
+    print("Method 1: Agent with Document Context")
+    print("=" * 60)
+    
+    agent = Agent(
+        name="Document Assistant",
+        instructions=f"""You are a helpful assistant that answers questions about documents.
+        Always cite specific sections when answering.
+        
+        DOCUMENT:
+        {DOCUMENT_CONTENT}""",
+        verbose=False
+    )
+    
+    query = "What are the main topics covered in this document?"
+    response = agent.chat(query)
+    print(f"\n📝 Query: {query}")
+    print(f"💡 Answer: {response}\n")
+    
+    # Method 2: Q&A with Citations
+    print("=" * 60)
+    print("Method 2: Q&A with Citations")
+    print("=" * 60)
+    
+    citation_agent = Agent(
+        name="Citation Assistant",
+        instructions=f"""You answer questions about research documents.
+        Always include citations in format [Section: Name].
+        Be precise and reference specific data points.
+        
+        DOCUMENT:
+        {DOCUMENT_CONTENT}""",
+        verbose=False
+    )
+    
+    queries = [
+        "What methodology was used in this research?",
+        "What were the key findings about productivity?",
+        "What are the recommendations?"
+    ]
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = citation_agent.chat(query)
+        print(f"💡 Answer: {response[:300]}...")
+    
+    # Method 3: Comparative Analysis
+    print("\n" + "=" * 60)
+    print("Method 3: Analytical Questions")
+    print("=" * 60)
+    
+    analyst = Agent(
+        name="Research Analyst",
+        instructions=f"""You are a research analyst who provides insights from documents.
+        Analyze data, identify trends, and provide actionable insights.
+        
+        DOCUMENT:
+        {DOCUMENT_CONTENT}""",
+        verbose=False
+    )
+    
+    analysis_query = "Compare the benefits vs challenges of remote work based on this study"
+    print(f"\n📝 Query: {analysis_query}")
+    response = analyst.chat(analysis_query)
+    print(f"💡 Analysis:\n{response}")
+    
+    print("\n✅ Document Q&A example completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/reranking.py

@@ -0,0 +1,249 @@
+"""
+Reranking: Improving Retrieval Precision
+
+This example demonstrates reranking - a second-pass scoring mechanism
+that improves the quality of retrieved documents.
+
+RAG Concept: Initial retrieval (first stage) prioritizes recall - finding
+all potentially relevant documents. Reranking (second stage) prioritizes
+precision - ordering results by true relevance to the query.
+"""
+
+from praisonaiagents import Agent
+
+# Sample knowledge base: Research paper abstracts
+RESEARCH_PAPERS = [
+    {
+        "id": "paper_001",
+        "content": """
+        Title: Attention Mechanisms in Neural Machine Translation
+        
+        Abstract: This paper introduces a novel attention mechanism for sequence-to-sequence
+        models in machine translation. Unlike previous approaches that use a fixed-length
+        context vector, our method allows the model to automatically search for parts of
+        the source sentence relevant to predicting the target word. Experiments on
+        English-to-French translation show significant improvements over baseline systems.
+        """
+    },
+    {
+        "id": "paper_002",
+        "content": """
+        Title: Deep Residual Learning for Image Recognition
+        
+        Abstract: We present a residual learning framework to ease the training of very deep
+        neural networks. By reformulating layers as learning residual functions with
+        reference to layer inputs, we show that these networks are easier to optimize
+        and can gain accuracy from considerably increased depth. Our 152-layer residual
+        network achieves state-of-the-art results on ImageNet classification.
+        """
+    },
+    {
+        "id": "paper_003",
+        "content": """
+        Title: BERT: Pre-training of Deep Bidirectional Transformers
+        
+        Abstract: We introduce BERT, a new language representation model designed to
+        pre-train deep bidirectional representations from unlabeled text. Unlike previous
+        models, BERT is designed to jointly condition on both left and right context.
+        The pre-trained BERT model can be fine-tuned with just one additional output
+        layer for a wide range of NLP tasks.
+        """
+    },
+    {
+        "id": "paper_004",
+        "content": """
+        Title: Generative Adversarial Networks
+        
+        Abstract: We propose a new framework for estimating generative models via an
+        adversarial process. We simultaneously train two models: a generative model G
+        that captures the data distribution, and a discriminative model D that estimates
+        the probability that a sample came from the training data rather than G.
+        This framework can generate realistic images from random noise.
+        """
+    },
+    {
+        "id": "paper_005",
+        "content": """
+        Title: Transformer Architecture for Language Understanding
+        
+        Abstract: We propose the Transformer, a model architecture eschewing recurrence
+        and instead relying entirely on an attention mechanism to draw global dependencies
+        between input and output. The Transformer allows for significantly more
+        parallelization and achieves new state of the art in translation quality.
+        """
+    },
+    {
+        "id": "paper_006",
+        "content": """
+        Title: Word Embeddings and Semantic Similarity
+        
+        Abstract: This paper explores methods for learning distributed representations
+        of words that capture semantic relationships. We show that word vectors trained
+        on large corpora encode meaningful syntactic and semantic regularities. These
+        representations enable analogical reasoning: king - man + woman = queen.
+        """
+    }
+]
+
+
+def explain_reranking():
+    """Explain the reranking concept."""
+    
+    print("=" * 60)
+    print("RERANKING EXPLAINED")
+    print("=" * 60)
+    
+    print("""
+    🔄 Two-Stage Retrieval Pipeline:
+    
+    Stage 1: Initial Retrieval (Bi-encoder)
+    ├── Fast approximate matching
+    ├── Retrieves top-K candidates (e.g., 20-100)
+    ├── Uses pre-computed embeddings
+    └── Optimizes for RECALL (find all relevant docs)
+    
+    Stage 2: Reranking (Cross-encoder)
+    ├── Slower but more accurate scoring
+    ├── Reorders the top-K candidates
+    ├── Computes query-document interaction
+    └── Optimizes for PRECISION (best docs first)
+    
+    Why Reranking Matters:
+    - Bi-encoders encode query and docs separately (fast but approximate)
+    - Cross-encoders process query+doc together (slow but accurate)
+    - Reranking gives you the best of both worlds
+    """)
+
+
+def rag_with_reranking():
+    """Demonstrate RAG with reranking enabled."""
+    
+    # Build context from research papers
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in RESEARCH_PAPERS])
+    
+    # Create agent with context
+    agent = Agent(
+        name="Research Assistant",
+        instructions=f"""You are a research paper expert.
+        Answer questions about machine learning research.
+        Reference specific papers when relevant.
+        Be precise about technical details.
+        
+        RESEARCH PAPERS:
+        {context}""",
+        verbose=False
+    )
+    
+    queries = [
+        "Which paper introduced the attention mechanism for translation?",
+        "Tell me about pre-training language models",
+        "What architecture avoids recurrence entirely?"
+    ]
+    
+    print("\n" + "=" * 60)
+    print("RAG WITH RERANKING")
+    print("=" * 60)
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 Answer: {response[:300]}..." if len(str(response)) > 300 else f"💡 Answer: {response}")
+        print("-" * 40)
+
+
+def compare_with_without_reranking():
+    """Compare retrieval quality with and without reranking."""
+    
+    print("\n" + "=" * 60)
+    print("RERANKING IMPACT COMPARISON")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in RESEARCH_PAPERS])
+    
+    query = "How do transformers handle long-range dependencies?"
+    
+    # Agent with context
+    agent = Agent(
+        name="Research Agent",
+        instructions=f"""Answer based on the research papers provided.
+        
+        RESEARCH PAPERS:
+        {context}""",
+        verbose=False
+    )
+    
+    print(f"\n📝 Query: {query}")
+    
+    print("\n🔍 RAG Response:")
+    response = agent.chat(query)
+    print(f"   {response[:250]}...")
+    
+    print("\n💡 Note: Reranking uses cross-encoders to improve precision after initial retrieval.")
+
+
+def reranking_configuration():
+    """Show reranking configuration options."""
+    
+    print("\n" + "=" * 60)
+    print("RERANKING CONFIGURATION")
+    print("=" * 60)
+    
+    print("""
+    Configuration options for reranking in PraisonAI:
+    
+    ```python
+    agent = Agent(
+        name="My Agent",
+        knowledge=documents,
+        knowledge_config={
+            # Enable reranking
+            "rerank": True,
+            
+            # Number of candidates for initial retrieval
+            "top_k": 10,
+            
+            # Number of results after reranking
+            "rerank_top_k": 3,
+            
+            # Reranker model (optional)
+            "rerank_model": "cross-encoder/ms-marco-MiniLM-L-6-v2"
+        }
+    )
+    ```
+    
+    Performance Considerations:
+    ┌─────────────────┬──────────────┬─────────────┐
+    │ Configuration   │ Latency      │ Quality     │
+    ├─────────────────┼──────────────┼─────────────┤
+    │ No reranking    │ ~50ms        │ Good        │
+    │ Light reranker  │ ~100ms       │ Better      │
+    │ Heavy reranker  │ ~200ms       │ Best        │
+    └─────────────────┴──────────────┴─────────────┘
+    
+    Tip: Use reranking for precision-critical applications
+    where quality matters more than latency.
+    """)
+
+
+def main():
+    """Run all reranking examples."""
+    print("\n🚀 PraisonAI Reranking Examples\n")
+    
+    # Example 1: Explain reranking
+    explain_reranking()
+    
+    # Example 2: RAG with reranking
+    rag_with_reranking()
+    
+    # Example 3: Compare with/without reranking
+    compare_with_without_reranking()
+    
+    # Example 4: Configuration options
+    reranking_configuration()
+    
+    print("\n✅ Reranking examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/retrieval_policies.py

@@ -0,0 +1,396 @@
+"""
+Retrieval Policies: Agent-Decided Retrieval Strategies
+
+This example demonstrates how agents can dynamically decide retrieval
+strategies based on query characteristics.
+
+RAG Concept: Not all queries are equal. Some need deep retrieval, others
+need broad coverage, and some don't need retrieval at all. Smart policies
+optimize both quality and efficiency.
+"""
+
+from praisonaiagents import Agent, AutoRagAgent, AutoRagConfig
+from praisonaiagents.agents.auto_rag_agent import RetrievalPolicy
+
+# Sample knowledge base: IT support documentation
+IT_SUPPORT_DOCS = [
+    {
+        "id": "password_reset",
+        "category": "account",
+        "priority": "high",
+        "content": """
+        Password Reset Procedure:
+        1. Go to the self-service portal at https://portal.company.com
+        2. Click "Forgot Password"
+        3. Enter your employee ID and email
+        4. Check your email for the reset link (valid for 1 hour)
+        5. Create a new password meeting complexity requirements
+        
+        If you don't receive the email, check spam or contact IT helpdesk.
+        """
+    },
+    {
+        "id": "vpn_setup",
+        "category": "network",
+        "priority": "medium",
+        "content": """
+        VPN Setup Guide:
+        1. Download the VPN client from the software center
+        2. Install with default settings
+        3. Launch and enter your credentials
+        4. Select the nearest server location
+        5. Click Connect
+        
+        Troubleshooting: If connection fails, check firewall settings
+        and ensure port 443 is open.
+        """
+    },
+    {
+        "id": "email_config",
+        "category": "communication",
+        "priority": "medium",
+        "content": """
+        Email Configuration:
+        - Server: mail.company.com
+        - Port: 993 (IMAP) / 587 (SMTP)
+        - Security: SSL/TLS required
+        - Username: your full email address
+        
+        Mobile setup: Use the Company Portal app for automatic configuration.
+        """
+    },
+    {
+        "id": "printer_setup",
+        "category": "hardware",
+        "priority": "low",
+        "content": """
+        Printer Setup:
+        1. Open Settings > Printers & Scanners
+        2. Click Add Printer
+        3. Select your floor's printer from the list
+        4. Install drivers if prompted
+        
+        Printer naming convention: FLOOR-WING-NUMBER (e.g., 3-EAST-01)
+        """
+    },
+    {
+        "id": "software_request",
+        "category": "software",
+        "priority": "medium",
+        "content": """
+        Software Request Process:
+        1. Submit request through ServiceNow
+        2. Manager approval required for licensed software
+        3. IT reviews for security compliance
+        4. Approved software deployed within 48 hours
+        
+        Pre-approved software can be installed directly from Software Center.
+        """
+    }
+]
+
+
+def query_classification():
+    """Demonstrate query classification for retrieval decisions."""
+    
+    print("=" * 60)
+    print("QUERY CLASSIFICATION FOR RETRIEVAL")
+    print("=" * 60)
+    
+    # Different query types
+    queries = [
+        ("How do I reset my password?", "procedural", True),
+        ("Hello!", "greeting", False),
+        ("What is 2 + 2?", "general_knowledge", False),
+        ("VPN connection keeps failing", "troubleshooting", True),
+        ("Thanks for your help", "closing", False),
+        ("How do I request new software?", "procedural", True),
+    ]
+    
+    print("\n📊 Query Classification Examples:\n")
+    print(f"{'Query':<40} {'Type':<20} {'Needs RAG':<10}")
+    print("-" * 70)
+    
+    for query, query_type, needs_rag in queries:
+        rag_indicator = "✅ Yes" if needs_rag else "❌ No"
+        print(f"{query:<40} {query_type:<20} {rag_indicator:<10}")
+    
+    print("\n💡 Smart agents classify queries to decide retrieval strategy.")
+
+
+def policy_based_retrieval():
+    """Demonstrate different retrieval policies."""
+    
+    print("\n" + "=" * 60)
+    print("RETRIEVAL POLICY COMPARISON")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{d['id']}]\n{d['content']}" for d in IT_SUPPORT_DOCS])
+    
+    base_agent = Agent(
+        name="IT Support",
+        instructions=f"""You are an IT support agent. Help users with technical issues.
+        
+        IT SUPPORT DOCS:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "How do I set up VPN?"
+    
+    policies = [
+        (RetrievalPolicy.AUTO, "Agent decides based on query analysis"),
+        (RetrievalPolicy.ALWAYS, "Always retrieve, even for simple queries"),
+        (RetrievalPolicy.NEVER, "Never retrieve, use only parametric knowledge"),
+    ]
+    
+    print(f"\n📝 Query: {query}\n")
+    
+    for policy, description in policies:
+        config = AutoRagConfig(retrieval_policy=policy)
+        auto_agent = AutoRagAgent(agent=base_agent, config=config)
+        
+        print(f"🔄 Policy: {policy.value.upper()}")
+        print(f"   Description: {description}")
+        
+        response = auto_agent.chat(query)
+        print(f"   Response: {response[:150]}...")
+        print()
+
+
+def adaptive_top_k():
+    """Demonstrate adaptive top-k based on query complexity."""
+    
+    print("\n" + "=" * 60)
+    print("ADAPTIVE TOP-K RETRIEVAL")
+    print("=" * 60)
+    
+    print("""
+    📊 Adaptive Top-K Strategy:
+    
+    Query Complexity → Top-K Value
+    ─────────────────────────────────
+    Simple (single topic)     → k=1-2
+    Moderate (related topics) → k=3-5
+    Complex (multi-topic)     → k=5-10
+    
+    Examples:
+    """)
+    
+    queries = [
+        ("Reset password", 2, "Simple - single procedure"),
+        ("VPN not working, also need email setup", 5, "Moderate - two topics"),
+        ("New employee setup: email, VPN, printer, software", 8, "Complex - multiple topics"),
+    ]
+    
+    for query, suggested_k, complexity in queries:
+        print(f"   Query: \"{query}\"")
+        print(f"   Complexity: {complexity}")
+        print(f"   Suggested top_k: {suggested_k}")
+        print()
+
+
+def priority_based_retrieval():
+    """Demonstrate priority-based document retrieval."""
+    
+    print("\n" + "=" * 60)
+    print("PRIORITY-BASED RETRIEVAL")
+    print("=" * 60)
+    
+    # Group documents by priority
+    high_priority = [d for d in IT_SUPPORT_DOCS if d.get('priority') == 'high']
+    all_docs = IT_SUPPORT_DOCS
+    
+    print("\n📊 Document Priorities in Knowledge Base:")
+    for doc in IT_SUPPORT_DOCS:
+        print(f"   [{doc['priority'].upper():^6}] {doc['id']}")
+    
+    # Build contexts
+    high_context = "\n\n".join([f"[{d['id']}]\n{d['content']}" for d in high_priority])
+    full_context = "\n\n".join([f"[{d['id']}]\n{d['content']}" for d in all_docs])
+    
+    # High-priority agent (for urgent issues)
+    urgent_agent = Agent(
+        name="Urgent Support",
+        instructions=f"""Handle urgent IT issues. Focus on critical procedures.
+        
+        HIGH PRIORITY DOCS:
+        {high_context}""",
+        verbose=False
+    )
+    
+    # Full knowledge agent
+    full_agent = Agent(
+        name="Full Support",
+        instructions=f"""Handle all IT support requests.
+        
+        IT SUPPORT DOCS:
+        {full_context}""",
+        verbose=False
+    )
+    
+    query = "I'm locked out of my account!"
+    
+    print(f"\n📝 Urgent Query: {query}")
+    
+    print("\n🚨 Urgent Support Agent (high-priority docs only):")
+    response1 = urgent_agent.chat(query)
+    print(f"   {response1[:200]}...")
+    
+    print("\n📚 Full Support Agent (all docs):")
+    response2 = full_agent.chat(query)
+    print(f"   {response2[:200]}...")
+
+
+def context_aware_retrieval():
+    """Demonstrate context-aware retrieval strategies."""
+    
+    print("\n" + "=" * 60)
+    print("CONTEXT-AWARE RETRIEVAL")
+    print("=" * 60)
+    
+    print("""
+    🎯 Context-Aware Retrieval Strategies:
+    
+    1. **User Role Context**
+       - New employee → Onboarding docs first
+       - IT admin → Technical docs
+       - Executive → Summary docs
+    
+    2. **Time Context**
+       - Business hours → Standard support
+       - After hours → Emergency procedures only
+    
+    3. **Conversation Context**
+       - First message → Broad retrieval
+       - Follow-up → Narrow to topic
+    
+    4. **Device Context**
+       - Mobile → Mobile-specific guides
+       - Desktop → Full documentation
+    
+    Implementation:
+    ```python
+    def get_retrieval_config(context: dict) -> dict:
+        if context.get("user_role") == "new_employee":
+            return {"filter": {"category": "onboarding"}, "top_k": 5}
+        elif context.get("is_followup"):
+            return {"top_k": 2}  # Narrow focus
+        else:
+            return {"top_k": 3}  # Default
+    ```
+    """)
+
+
+def fallback_strategies():
+    """Demonstrate fallback strategies when retrieval fails."""
+    
+    print("\n" + "=" * 60)
+    print("RETRIEVAL FALLBACK STRATEGIES")
+    print("=" * 60)
+    
+    print("""
+    🔄 Fallback Strategy Chain:
+    
+    1. Primary: Vector search in knowledge base
+       ↓ (if no relevant results)
+    2. Secondary: Expand search with synonyms
+       ↓ (if still no results)
+    3. Tertiary: Search external sources
+       ↓ (if still no results)
+    4. Final: Acknowledge limitation, offer alternatives
+    
+    Example Implementation:
+    ```python
+    def retrieve_with_fallback(query: str, knowledge) -> str:
+        # Primary retrieval
+        results = knowledge.search(query, top_k=3)
+        
+        if results and results[0].score > 0.7:
+            return format_context(results)
+        
+        # Fallback: Expand query
+        expanded = expand_query(query)  # Add synonyms
+        results = knowledge.search(expanded, top_k=5)
+        
+        if results and results[0].score > 0.5:
+            return format_context(results)
+        
+        # Final fallback
+        return "I don't have specific information about that. " \\
+               "Please contact IT helpdesk at ext. 1234."
+    ```
+    """)
+
+
+def retrieval_metrics():
+    """Explain retrieval quality metrics."""
+    
+    print("\n" + "=" * 60)
+    print("RETRIEVAL QUALITY METRICS")
+    print("=" * 60)
+    
+    print("""
+    📈 Key Metrics for Retrieval Policy Tuning:
+    
+    ┌─────────────────┬────────────────────────────────────────┐
+    │ Metric          │ Description                            │
+    ├─────────────────┼────────────────────────────────────────┤
+    │ Precision@K     │ % of retrieved docs that are relevant │
+    │ Recall@K        │ % of relevant docs that are retrieved │
+    │ MRR             │ Mean Reciprocal Rank of first hit     │
+    │ NDCG            │ Normalized Discounted Cumulative Gain │
+    │ Latency         │ Time to retrieve (ms)                 │
+    │ Token Usage     │ Context tokens consumed               │
+    └─────────────────┴────────────────────────────────────────┘
+    
+    Policy Optimization Goals:
+    
+    - High Precision: Use smaller top_k, stricter thresholds
+    - High Recall: Use larger top_k, relaxed thresholds
+    - Low Latency: Use smaller top_k, skip reranking
+    - Low Cost: Use smaller top_k, aggressive filtering
+    
+    Balanced Default:
+    ```python
+    config = {
+        "top_k": 3,
+        "score_threshold": 0.5,
+        "rerank": True,
+        "max_tokens": 2000
+    }
+    ```
+    """)
+
+
+def main():
+    """Run all retrieval policy examples."""
+    print("\n🚀 PraisonAI Retrieval Policies Examples\n")
+    
+    # Example 1: Query classification
+    query_classification()
+    
+    # Example 2: Policy comparison
+    policy_based_retrieval()
+    
+    # Example 3: Adaptive top-k
+    adaptive_top_k()
+    
+    # Example 4: Priority-based
+    priority_based_retrieval()
+    
+    # Example 5: Context-aware
+    context_aware_retrieval()
+    
+    # Example 6: Fallback strategies
+    fallback_strategies()
+    
+    # Example 7: Metrics
+    retrieval_metrics()
+    
+    print("\n✅ Retrieval policies examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/rag/structured_output.py

@@ -0,0 +1,359 @@
+"""
+Structured Output RAG: Guided and Constrained Generation
+
+This example demonstrates how to guide RAG output into specific formats
+and structures using Pydantic models and output constraints.
+
+RAG Concept: Sometimes you need RAG answers in a specific format - JSON,
+tables, or structured data. Guided generation ensures the LLM output
+conforms to your schema.
+"""
+
+from typing import List
+from pydantic import BaseModel, Field
+from praisonaiagents import Agent
+
+# Sample knowledge base: Product catalog
+PRODUCT_CATALOG = [
+    {
+        "id": "prod_001",
+        "content": """
+        Product: UltraWidget Pro
+        Category: Electronics
+        Price: $299.99
+        Rating: 4.5/5 (1,250 reviews)
+        Features: Wireless connectivity, 12-hour battery, water-resistant
+        Availability: In stock
+        SKU: UW-PRO-2024
+        """
+    },
+    {
+        "id": "prod_002",
+        "content": """
+        Product: SmartHome Hub
+        Category: Home Automation
+        Price: $149.99
+        Rating: 4.2/5 (890 reviews)
+        Features: Voice control, 100+ device compatibility, energy monitoring
+        Availability: In stock
+        SKU: SH-HUB-2024
+        """
+    },
+    {
+        "id": "prod_003",
+        "content": """
+        Product: ErgoDesk Standing Desk
+        Category: Furniture
+        Price: $599.99
+        Rating: 4.8/5 (2,100 reviews)
+        Features: Electric height adjustment, memory presets, cable management
+        Availability: Ships in 3-5 days
+        SKU: ED-STAND-2024
+        """
+    },
+    {
+        "id": "prod_004",
+        "content": """
+        Product: CloudSync Backup Drive
+        Category: Storage
+        Price: $199.99
+        Rating: 4.6/5 (1,800 reviews)
+        Features: 4TB capacity, automatic backup, encrypted storage
+        Availability: In stock
+        SKU: CS-4TB-2024
+        """
+    }
+]
+
+
+# Pydantic models for structured output
+class ProductInfo(BaseModel):
+    """Structured product information."""
+    name: str = Field(description="Product name")
+    price: float = Field(description="Price in USD")
+    rating: float = Field(description="Rating out of 5")
+    in_stock: bool = Field(description="Whether product is in stock")
+    key_features: List[str] = Field(description="Top 3 features")
+
+
+class ProductComparison(BaseModel):
+    """Structured comparison of products."""
+    products: List[str] = Field(description="Names of compared products")
+    winner: str = Field(description="Recommended product")
+    reason: str = Field(description="Why this product is recommended")
+    price_range: str = Field(description="Price range of compared products")
+
+
+class SearchResult(BaseModel):
+    """Structured search result."""
+    query: str = Field(description="Original search query")
+    matches: List[str] = Field(description="Matching product names")
+    total_found: int = Field(description="Number of matches")
+    summary: str = Field(description="Brief summary of results")
+
+
+def json_output_rag():
+    """Demonstrate RAG with JSON-structured output."""
+    
+    print("=" * 60)
+    print("JSON-STRUCTURED RAG OUTPUT")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in PRODUCT_CATALOG])
+    
+    agent = Agent(
+        name="Product Assistant",
+        instructions=f"""You are a product assistant that provides structured information.
+        Always respond with valid JSON matching the requested format.
+        Extract accurate information from the product catalog.
+        
+        PRODUCT CATALOG:
+        {context}""",
+        verbose=False
+    )
+    
+    # Request structured product info
+    query = """
+    Tell me about the UltraWidget Pro. Respond in this JSON format:
+    {
+        "name": "product name",
+        "price": 0.00,
+        "rating": 0.0,
+        "in_stock": true/false,
+        "key_features": ["feature1", "feature2", "feature3"]
+    }
+    """
+    
+    print("\n📝 Query: Get structured product info")
+    response = agent.chat(query)
+    print("💡 Structured Response:\n" + str(response))
+    print("-" * 40)
+
+
+def pydantic_guided_rag():
+    """Demonstrate RAG with Pydantic model guidance."""
+    
+    print("\n" + "=" * 60)
+    print("PYDANTIC-GUIDED RAG")
+    print("=" * 60)
+    
+    # Generate schema from Pydantic model
+    schema = ProductComparison.model_json_schema()
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in PRODUCT_CATALOG])
+    
+    agent = Agent(
+        name="Product Comparator",
+        instructions=f"""You compare products and provide structured recommendations.
+        Your response MUST be valid JSON matching this schema:
+        {schema}
+        
+        Be objective and base recommendations on the product data.
+        
+        PRODUCT CATALOG:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "Compare the UltraWidget Pro and SmartHome Hub. Which should I buy?"
+    
+    print(f"\n📝 Query: {query}")
+    print("📋 Expected Schema: ProductComparison")
+    
+    response = agent.chat(query)
+    print(f"\n💡 Structured Comparison:\n{response}")
+
+
+def table_format_rag():
+    """Demonstrate RAG with table-formatted output."""
+    
+    print("\n" + "=" * 60)
+    print("TABLE-FORMATTED RAG")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in PRODUCT_CATALOG])
+    
+    agent = Agent(
+        name="Catalog Browser",
+        instructions=f"""You present product information in clean table format.
+        Use markdown tables for structured data.
+        Include relevant columns based on the query.
+        
+        PRODUCT CATALOG:
+        {context}""",
+        verbose=False
+    )
+    
+    query = "Show me all products in a table with name, price, and rating."
+    
+    print(f"\n📝 Query: {query}")
+    response = agent.chat(query)
+    print(f"\n💡 Table Output:\n{response}")
+
+
+def list_format_rag():
+    """Demonstrate RAG with list-formatted output."""
+    
+    print("\n" + "=" * 60)
+    print("LIST-FORMATTED RAG")
+    print("=" * 60)
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in PRODUCT_CATALOG])
+    
+    agent = Agent(
+        name="Feature Lister",
+        instructions=f"""You extract and present information as organized lists.
+        Use bullet points and numbered lists appropriately.
+        Group related items together.
+        
+        PRODUCT CATALOG:
+        {context}""",
+        verbose=False
+    )
+    
+    queries = [
+        "List all product features across the catalog",
+        "What are the top-rated products? List them in order."
+    ]
+    
+    for query in queries:
+        print(f"\n📝 Query: {query}")
+        response = agent.chat(query)
+        print(f"💡 List Output:\n{response[:400]}..." if len(str(response)) > 400 else f"💡 List Output:\n{response}")
+        print("-" * 40)
+
+
+def constrained_generation():
+    """Demonstrate constrained/guided generation patterns."""
+    
+    print("\n" + "=" * 60)
+    print("CONSTRAINED GENERATION PATTERNS")
+    print("=" * 60)
+    
+    print("""
+    🎯 Constrained Generation Techniques:
+    
+    1. **Schema Enforcement**
+       - Provide JSON schema in instructions
+       - Agent outputs valid JSON matching schema
+       ```python
+       instructions = f"Respond with JSON matching: {schema}"
+       ```
+    
+    2. **Format Templates**
+       - Give explicit output templates
+       - Agent fills in the blanks
+       ```python
+       instructions = '''
+       Respond in this format:
+       PRODUCT: [name]
+       PRICE: $[amount]
+       VERDICT: [recommendation]
+       '''
+       ```
+    
+    3. **Pydantic Validation**
+       - Parse agent output with Pydantic
+       - Retry if validation fails
+       ```python
+       response = agent.chat(query)
+       try:
+           result = ProductInfo.model_validate_json(response)
+       except ValidationError:
+           # Retry with clarification
+       ```
+    
+    4. **Output Parsers**
+       - Post-process agent output
+       - Extract structured data from text
+       ```python
+       def parse_product(text: str) -> dict:
+           # Extract price, rating, etc.
+           return structured_data
+       ```
+    
+    5. **Few-Shot Examples**
+       - Show examples of desired output format
+       - Agent learns pattern from examples
+       ```python
+       instructions = '''
+       Example:
+       Q: Tell me about Product X
+       A: {"name": "Product X", "price": 99.99}
+       
+       Now answer the user's question in the same format.
+       '''
+       ```
+    """)
+
+
+def multi_format_rag():
+    """Demonstrate switching between output formats."""
+    
+    print("\n" + "=" * 60)
+    print("MULTI-FORMAT RAG")
+    print("=" * 60)
+    
+    base_knowledge = PRODUCT_CATALOG
+    query = "Tell me about the ErgoDesk Standing Desk"
+    
+    formats = [
+        ("JSON", "Respond with a JSON object containing name, price, and features."),
+        ("Markdown", "Respond with a markdown-formatted product card with headers."),
+        ("Plain Text", "Respond with a brief, conversational product description."),
+        ("Bullet Points", "Respond with bullet points covering key product details.")
+    ]
+    
+    print(f"\n📝 Base Query: {query}")
+    print("\n🔄 Same query, different output formats:\n")
+    
+    # Build context
+    context = "\n\n".join([f"[{p['id']}]\n{p['content']}" for p in base_knowledge])
+    
+    for format_name, format_instruction in formats:
+        agent = Agent(
+            name=f"{format_name} Agent",
+            instructions=f"""You are a product expert. {format_instruction}
+            
+            PRODUCT CATALOG:
+            {context}""",
+            verbose=False
+        )
+        
+        response = agent.chat(query)
+        print(f"📋 {format_name} Format:")
+        print(f"{response[:250]}..." if len(str(response)) > 250 else response)
+        print("-" * 40)
+
+
+def main():
+    """Run all structured output RAG examples."""
+    print("\n🚀 PraisonAI Structured Output RAG Examples\n")
+    
+    # Example 1: JSON output
+    json_output_rag()
+    
+    # Example 2: Pydantic-guided
+    pydantic_guided_rag()
+    
+    # Example 3: Table format
+    table_format_rag()
+    
+    # Example 4: List format
+    list_format_rag()
+    
+    # Example 5: Constrained generation patterns
+    constrained_generation()
+    
+    # Example 6: Multi-format
+    multi_format_rag()
+    
+    print("\n✅ Structured output RAG examples completed!")
+
+
+if __name__ == "__main__":
+    main()

examples/retrieval/basic_retrieval.py

@@ -0,0 +1,105 @@
+"""
+Basic Agent Retrieval Example
+
+Demonstrates the Agent-first retrieval API with knowledge and retrieval_config.
+"""
+
+import os
+from praisonaiagents import Agent
+
+# Ensure API key is set
+if not os.environ.get("OPENAI_API_KEY"):
+    print("Please set OPENAI_API_KEY environment variable")
+    exit(1)
+
+# Create a simple text file for testing
+test_content = """
+# PraisonAI Framework Overview
+
+PraisonAI is an AI agents framework that enables building sophisticated AI applications.
+
+## Key Features
+
+1. **Agent-First Design**: Everything centers around the Agent class
+2. **Knowledge Integration**: Agents can use knowledge bases for retrieval
+3. **Unified Configuration**: Single retrieval_config for all retrieval settings
+4. **Multi-Agent Support**: Multiple agents can share knowledge
+
+## Retrieval Policies
+
+- **auto**: Automatically decide when to retrieve based on query
+- **always**: Always retrieve for every query
+- **never**: Never retrieve (use for pure generation)
+
+## Citation Modes
+
+- **append**: Add citations at the end of the response
+- **inline**: Include citations inline in the text
+- **hidden**: Citations available in result but not in text
+"""
+
+# Write test content to a file
+os.makedirs(".praison/test_docs", exist_ok=True)
+with open(".praison/test_docs/overview.txt", "w") as f:
+    f.write(test_content)
+
+print("=" * 60)
+print("Basic Agent Retrieval Example")
+print("=" * 60)
+
+# Create agent with knowledge and retrieval config
+agent = Agent(
+    name="Knowledge Agent",
+    instructions="You are a helpful assistant that answers questions based on the provided knowledge. Be concise.",
+    knowledge=[".praison/test_docs/overview.txt"],
+    retrieval_config={
+        "policy": "always",      # Always retrieve for this demo
+        "top_k": 3,              # Get top 3 chunks
+        "citations": True,       # Include citations
+        "max_context_tokens": 2000,
+    }
+)
+
+# Test 1: Basic chat with retrieval
+print("\n1. Basic Chat with Retrieval:")
+print("-" * 40)
+response = agent.chat("What are the key features of PraisonAI?")
+print(response)
+
+# Test 2: Query with structured result
+print("\n2. Structured Query with Citations:")
+print("-" * 40)
+try:
+    result = agent.query("What are the retrieval policies?")
+    print(f"Answer: {result.answer}")
+    if result.citations:
+        print(f"\nCitations ({len(result.citations)}):")
+        for citation in result.citations:
+            print(f"  - {citation.source}")
+except Exception as e:
+    print(f"Query not available (RAG module may not be installed): {e}")
+
+# Test 3: Retrieve only (no LLM generation)
+print("\n3. Retrieve Only (No LLM):")
+print("-" * 40)
+try:
+    context = agent.retrieve("citation modes")
+    print(f"Found context: {len(context.context)} chars")
+    if context.citations:
+        print(f"Sources: {len(context.citations)}")
+except Exception as e:
+    print(f"Retrieve not available (RAG module may not be installed): {e}")
+
+# Test 4: Skip retrieval
+print("\n4. Chat with skip_retrieval=True:")
+print("-" * 40)
+response = agent.chat("What is 2 + 2?", skip_retrieval=True)
+print(response)
+
+print("\n" + "=" * 60)
+print("Example Complete!")
+print("=" * 60)
+
+# Cleanup
+import shutil
+shutil.rmtree(".praison/test_docs", ignore_errors=True)

scripts/generate_cli_docs.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+"""
+Auto-generate CLI reference documentation from --help output.
+
+Usage:
+    python scripts/generate_cli_docs.py > docs/cli/reference.mdx
+    python scripts/generate_cli_docs.py --output docs/cli/reference.mdx
+
+This script runs `praisonai <cmd> --help` for key commands and generates
+deterministic markdown documentation.
+"""
+
+import subprocess
+import sys
+import argparse
+from datetime import datetime
+from pathlib import Path
+
+
+# Commands to document
+COMMANDS = [
+    # Top-level
+    ("praisonai", "--help"),
+    # Knowledge
+    ("praisonai knowledge", "--help"),
+    ("praisonai knowledge index", "--help"),
+    ("praisonai knowledge search", "--help"),
+    ("praisonai knowledge add", "--help"),
+    ("praisonai knowledge list", "--help"),
+    # RAG
+    ("praisonai rag", "--help"),
+    ("praisonai rag index", "--help"),
+    ("praisonai rag query", "--help"),
+    ("praisonai rag chat", "--help"),
+    ("praisonai rag eval", "--help"),
+    ("praisonai rag serve", "--help"),
+    # Run
+    ("praisonai run", "--help"),
+    # Chat
+    ("praisonai chat", "--help"),
+]
+
+
+def run_help(cmd: str, flag: str = "--help") -> str:
+    """Run a command with --help and capture output."""
+    full_cmd = f"{cmd} {flag}"
+    try:
+        result = subprocess.run(
+            full_cmd.split(),
+            capture_output=True,
+            text=True,
+            timeout=30,
+        )
+        return result.stdout or result.stderr or "(no output)"
+    except subprocess.TimeoutExpired:
+        return "(timeout)"
+    except FileNotFoundError:
+        return "(command not found)"
+    except Exception as e:
+        return f"(error: {e})"
+
+
+def generate_markdown() -> str:
+    """Generate markdown documentation."""
+    lines = [
+        "---",
+        "title: CLI Reference",
+        "description: Auto-generated CLI command reference",
+        "---",
+        "",
+        "# PraisonAI CLI Reference",
+        "",
+        "This page is auto-generated from `--help` output.",
+        "",
+        f"Generated: {datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S')} UTC",
+        "",
+    ]
+    
+    for cmd, flag in COMMANDS:
+        # Section header
+        cmd_name = cmd.replace("praisonai ", "").replace(" ", "-") or "main"
+        lines.append(f"## `{cmd}`")
+        lines.append("")
+        lines.append("```")
+        
+        # Get help output
+        output = run_help(cmd, flag)
+        lines.append(output.strip())
+        
+        lines.append("```")
+        lines.append("")
+    
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Generate CLI docs from --help")
+    parser.add_argument(
+        "--output", "-o",
+        type=Path,
+        help="Output file path (default: stdout)",
+    )
+    parser.add_argument(
+        "--check",
+        action="store_true",
+        help="Check if output matches existing file (for CI)",
+    )
+    args = parser.parse_args()
+    
+    content = generate_markdown()
+    
+    if args.check and args.output:
+        if args.output.exists():
+            existing = args.output.read_text()
+            # Compare ignoring timestamp line
+            existing_lines = [l for l in existing.split("\n") if not l.startswith("Generated:")]
+            new_lines = [l for l in content.split("\n") if not l.startswith("Generated:")]
+            if existing_lines != new_lines:
+                print(f"ERROR: {args.output} is out of date. Run: python scripts/generate_cli_docs.py -o {args.output}", file=sys.stderr)
+                sys.exit(1)
+            print(f"OK: {args.output} is up to date")
+            sys.exit(0)
+        else:
+            print(f"ERROR: {args.output} does not exist", file=sys.stderr)
+            sys.exit(1)
+    
+    if args.output:
+        args.output.parent.mkdir(parents=True, exist_ok=True)
+        args.output.write_text(content)
+        print(f"Written to {args.output}")
+    else:
+        print(content)
+
+
+if __name__ == "__main__":
+    main()

src/praisonai-agents/praisonaiagents/__init__.py

@@ -189,19 +189,25 @@ def __getattr__(name):
         _lazy_cache[name] = AutoAgents
         return AutoAgents
     
-    # Session (imports requests) - import directly to avoid session/ directory conflict
+    # AutoRagAgent (auto RAG retrieval decision)
+    elif name == "AutoRagAgent":
+        from .agents.auto_rag_agent import AutoRagAgent
+        _lazy_cache[name] = AutoRagAgent
+        return AutoRagAgent
+    elif name == "AutoRagConfig":
+        from .agents.auto_rag_agent import AutoRagConfig
+        _lazy_cache[name] = AutoRagConfig
+        return AutoRagConfig
+    elif name == "RagRetrievalPolicy":
+        from .agents.auto_rag_agent import RetrievalPolicy
+        _lazy_cache[name] = RetrievalPolicy
+        return RetrievalPolicy
+    
+    # Session (imports requests lazily via session/api.py)
     elif name == "Session":
-        # Use __import__ to get the session.py module, not session/ package
-        import sys
-        import importlib.util
-        import os
-        session_path = os.path.join(os.path.dirname(__file__), "session.py")
-        spec = importlib.util.spec_from_file_location("_praisonai_session", session_path)
-        session_module = importlib.util.module_from_spec(spec)
-        sys.modules["_praisonai_session"] = session_module
-        spec.loader.exec_module(session_module)
-        _lazy_cache[name] = session_module.Session
-        return session_module.Session
+        from .session import Session
+        _lazy_cache[name] = Session
+        return Session
     
     # MCP support (optional)
     elif name == "MCP":
@@ -242,6 +248,48 @@ def __getattr__(name):
         _lazy_cache[name] = LineRange
         return LineRange
     
+    # Retrieval configuration (Agent-first unified config)
+    elif name == "RetrievalConfig":
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig
+        _lazy_cache[name] = RetrievalConfig
+        return RetrievalConfig
+    elif name == "RetrievalPolicy":
+        from praisonaiagents.rag.retrieval_config import RetrievalPolicy
+        _lazy_cache[name] = RetrievalPolicy
+        return RetrievalPolicy
+    elif name == "CitationsMode":
+        from praisonaiagents.rag.retrieval_config import CitationsMode
+        _lazy_cache[name] = CitationsMode
+        return CitationsMode
+    
+    # RAG models (used by Agent.query() and Agent.retrieve())
+    elif name == "ContextPack":
+        from praisonaiagents.rag.models import ContextPack
+        _lazy_cache[name] = ContextPack
+        return ContextPack
+    elif name == "RAGResult":
+        from praisonaiagents.rag import RAGResult
+        _lazy_cache[name] = RAGResult
+        return RAGResult
+    elif name == "Citation":
+        from praisonaiagents.rag import Citation
+        _lazy_cache[name] = Citation
+        return Citation
+    
+    # RAG internals (advanced use - prefer Agent.query() for normal usage)
+    elif name == "RAG":
+        from praisonaiagents.rag import RAG
+        _lazy_cache[name] = RAG
+        return RAG
+    elif name == "RAGConfig":
+        from praisonaiagents.rag import RAGConfig
+        _lazy_cache[name] = RAGConfig
+        return RAGConfig
+    elif name == "RAGCitation":
+        from praisonaiagents.rag import Citation
+        _lazy_cache[name] = Citation
+        return Citation
+    
     # Agent Skills support (lazy loaded for zero performance impact)
     elif name == "SkillManager":
         from praisonaiagents.skills import SkillManager
@@ -382,6 +430,9 @@ __all__ = [
     'TaskOutput',
     'ReflectionOutput',
     'AutoAgents',
+    'AutoRagAgent',
+    'AutoRagConfig',
+    'RagRetrievalPolicy',
     'Session',
     'Memory',
     'db',
@@ -471,4 +522,9 @@ __all__ = [
     # UI
     'AGUI',
     'A2A',
+    # RAG
+    'RAG',
+    'RAGConfig',
+    'RAGResult',
+    'RAGCitation',
 ]

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

@@ -45,6 +45,7 @@ if TYPE_CHECKING:
     from ..task.task import Task
     from ..main import TaskOutput
     from ..handoff import Handoff
+    from ..rag.models import RAGResult, ContextPack
 
 class Agent:
     @classmethod
@@ -269,8 +270,10 @@ class Agent:
         respect_context_window: bool = True,
         code_execution_mode: Literal["safe", "unsafe"] = "safe",
         embedder_config: Optional[Dict[str, Any]] = None,
-        knowledge: Optional[List[str]] = None,
+        knowledge: Optional[Union[List[str], Any]] = None,
+        retrieval_config: Optional[Union[Dict[str, Any], Any]] = None,
         knowledge_config: Optional[Dict[str, Any]] = None,
+        rag_config: Optional[Dict[str, Any]] = None,
         use_system_prompt: Optional[bool] = True,
         markdown: bool = True,
         stream: bool = False,
@@ -309,7 +312,9 @@ class Agent:
         session_id: Optional[str] = None,
         hooks: Optional[List[Any]] = None,
         llm_config: Optional[Dict[str, Any]] = None,
-        rate_limiter: Optional[Any] = None
+        rate_limiter: Optional[Any] = None,
+        auto_summarize: bool = False,
+        summarize_threshold: float = 0.8
     ):
         """Initialize an Agent instance.
 
@@ -461,6 +466,12 @@ class Agent:
         # Store rate limiter (optional, zero overhead when None)
         self._rate_limiter = rate_limiter
         
+        # Auto-summarization configuration
+        if auto_summarize and not (0.0 < summarize_threshold <= 1.0):
+            raise ValueError("summarize_threshold must be between 0.0 and 1.0")
+        self.auto_summarize = auto_summarize
+        self.summarize_threshold = summarize_threshold
+        
         # Store OpenAI client parameters for lazy initialization
         self._openai_api_key = api_key
         self._openai_base_url = base_url
@@ -656,17 +667,47 @@ Your Goal: {self.goal}
         self.handoffs = handoffs if handoffs else []
         self._process_handoffs()
 
+        # Initialize unified retrieval configuration
+        # retrieval_config is the SINGLE configuration surface (replaces knowledge_config + rag_config)
+        self._retrieval_config = None
+        if retrieval_config is not None:
+            from ..rag.retrieval_config import RetrievalConfig, create_retrieval_config
+            if isinstance(retrieval_config, RetrievalConfig):
+                self._retrieval_config = retrieval_config
+            elif isinstance(retrieval_config, dict):
+                self._retrieval_config = RetrievalConfig.from_dict(retrieval_config)
+        elif knowledge_config is not None or rag_config is not None:
+            # Legacy support: merge old configs into unified config
+            from ..rag.retrieval_config import create_retrieval_config
+            self._retrieval_config = create_retrieval_config(
+                knowledge_config=knowledge_config,
+                rag_config=rag_config,
+            )
+        
         # Check if knowledge parameter has any values
         if not knowledge:
             self.knowledge = None
             self._knowledge_sources = None
             self._knowledge_processed = True  # No knowledge to process
+            self._rag_instance = None
         else:
-            # Store knowledge sources for lazy processing
-            self._knowledge_sources = knowledge
-            self._knowledge_processed = False
-            self._knowledge_config = knowledge_config
-            self.knowledge = None  # Will be initialized on first use
+            # Check if knowledge is a Knowledge instance (shared knowledge)
+            if hasattr(knowledge, 'search') and hasattr(knowledge, 'add'):
+                # It's a Knowledge instance - use directly
+                self.knowledge = knowledge
+                self._knowledge_sources = None
+                self._knowledge_processed = True
+            else:
+                # It's a list of sources - store for lazy processing
+                self._knowledge_sources = knowledge
+                self._knowledge_processed = False
+                self.knowledge = None  # Will be initialized on first use
+            self._rag_instance = None  # Lazy loaded RAG instance
+            
+            # Create default retrieval config if knowledge provided but no config
+            if self._retrieval_config is None:
+                from ..rag.retrieval_config import RetrievalConfig
+                self._retrieval_config = RetrievalConfig()
 
         # Fast Context configuration (lazy loaded)
         self.fast_context_enabled = fast_context
@@ -1182,9 +1223,14 @@ Your Goal: {self.goal}
     def _ensure_knowledge_processed(self):
         """Ensure knowledge is initialized and processed when first accessed."""
         if not self._knowledge_processed and self._knowledge_sources:
-            # Initialize Knowledge with provided or default config
+            # Initialize Knowledge with config from retrieval_config
             from praisonaiagents.knowledge import Knowledge
-            self.knowledge = Knowledge(self._knowledge_config or None)
+            
+            knowledge_config = None
+            if self._retrieval_config is not None:
+                knowledge_config = self._retrieval_config.to_knowledge_config()
+            
+            self.knowledge = Knowledge(knowledge_config)
             
             # Process all knowledge sources
             for source in self._knowledge_sources:
@@ -1192,6 +1238,295 @@ Your Goal: {self.goal}
             
             self._knowledge_processed = True
     
+    @property
+    def retrieval_config(self):
+        """Get the unified retrieval configuration."""
+        return self._retrieval_config
+    
+    @property
+    def rag(self):
+        """
+        Lazy-loaded RAG instance for advanced retrieval with citations.
+        
+        Returns RAG instance configured with agent's knowledge and retrieval_config.
+        Returns None if no knowledge is configured.
+        
+        Usage:
+            agent = Agent(knowledge=["doc.pdf"], retrieval_config={"citations": True})
+            result = agent.rag.query("What is the main finding?")
+            print(result.answer)
+            for citation in result.citations:
+                print(f"[{citation.id}] {citation.source}")
+        """
+        # Check if we have knowledge (either sources or direct instance)
+        if not self._knowledge_sources and self.knowledge is None:
+            return None
+        
+        if self._rag_instance is None:
+            self._ensure_knowledge_processed()
+            if self.knowledge:
+                try:
+                    from praisonaiagents.rag import RAG, RAGConfig
+                    
+                    # Build RAGConfig from unified retrieval_config
+                    rag_config_obj = RAGConfig()
+                    if self._retrieval_config is not None:
+                        rag_dict = self._retrieval_config.to_rag_config()
+                        for key, value in rag_dict.items():
+                            if hasattr(rag_config_obj, key):
+                                setattr(rag_config_obj, key, value)
+                    
+                    # Get LLM instance for RAG
+                    llm = None
+                    if hasattr(self, 'llm_instance') and self.llm_instance:
+                        llm = self.llm_instance
+                    
+                    self._rag_instance = RAG(
+                        knowledge=self.knowledge,
+                        config=rag_config_obj,
+                        llm=llm,
+                    )
+                except ImportError:
+                    logging.warning("RAG module not available. Install with: pip install 'praisonaiagents[rag]'")
+                    return None
+        
+        return self._rag_instance
+    
+    def _get_knowledge_context(self, query: str, use_rag: bool = False) -> tuple:
+        """
+        Get knowledge context for a query using unified retrieval pipeline.
+        
+        Args:
+            query: The user's question/prompt
+            use_rag: If True, use RAG pipeline for token-aware context building
+            
+        Returns:
+            Tuple of (context_string, citations_list or None)
+        """
+        # Check if we have knowledge (sources or direct instance)
+        if not self._knowledge_sources and self.knowledge is None:
+            return "", None
+        
+        self._ensure_knowledge_processed()
+        
+        if not self.knowledge:
+            return "", None
+        
+        # Use RAG pipeline for token-aware context building (DRY - single path)
+        if use_rag and self.rag:
+            try:
+                context_pack = self.rag.retrieve(query, user_id=self.user_id, agent_id=self.agent_id)
+                return context_pack.context, context_pack.citations
+            except Exception as e:
+                logging.warning(f"RAG retrieve failed, falling back to basic retrieval: {e}")
+        
+        # Fallback: basic retrieval with token-aware formatting
+        try:
+            from praisonaiagents.rag.context import build_context
+            
+            search_results = self.knowledge.search(query, agent_id=self.agent_id)
+            if not search_results:
+                return "", None
+            
+            # Normalize results format (filter out None values, handle None metadata)
+            if isinstance(search_results, dict) and 'results' in search_results:
+                results = []
+                for r in search_results['results']:
+                    if r is None:
+                        continue
+                    text = r.get('memory', '') or ''
+                    metadata = r.get('metadata') or {}  # Handle None metadata
+                    if text:
+                        results.append({"text": text, "metadata": metadata})
+            elif isinstance(search_results, list):
+                results = [{"text": str(r), "metadata": {}} for r in search_results if r is not None and str(r)]
+            else:
+                results = [{"text": str(search_results), "metadata": {}}] if search_results else []
+            
+            # Use token-aware context building (same as RAG pipeline)
+            max_tokens = 4000
+            if self._retrieval_config:
+                max_tokens = self._retrieval_config.max_context_tokens
+            
+            context, _ = build_context(results, max_tokens=max_tokens)
+            return context, None
+            
+        except ImportError:
+            # Fallback to simple concatenation if RAG context module not available
+            search_results = self.knowledge.search(query, agent_id=self.agent_id)
+            if not search_results:
+                return "", None
+            
+            if isinstance(search_results, dict) and 'results' in search_results:
+                knowledge_content = "\n".join([result['memory'] for result in search_results['results']])
+            else:
+                knowledge_content = "\n".join(search_results) if isinstance(search_results, list) else str(search_results)
+            
+            return knowledge_content, None
+    
+    def retrieve(self, query: str, **kwargs) -> "ContextPack":
+        """
+        Retrieve context from knowledge without LLM generation.
+        
+        Returns a ContextPack that can be passed to chat_with_context().
+        This enables conditional retrieval - only retrieve when needed.
+        
+        Args:
+            query: Search query
+            **kwargs: Additional arguments (top_k, rerank, etc.)
+            
+        Returns:
+            ContextPack with context string and citations (no LLM call)
+            
+        Raises:
+            ValueError: If no knowledge is configured
+            ImportError: If RAG module is not available
+            
+        Usage:
+            agent = Agent(knowledge=["docs/"], retrieval_config={"citations": True})
+            context = agent.retrieve("What are the key findings?")
+            print(f"Found {len(context.citations)} sources")
+            response = agent.chat_with_context("Summarize", context)
+        """
+        if not self._knowledge_sources and self.knowledge is None:
+            raise ValueError("No knowledge configured. Add knowledge=[] to Agent init.")
+        
+        if not self.rag:
+            raise ImportError("RAG module not available. Install with: pip install 'praisonaiagents[rag]'")
+        
+        kwargs.setdefault('user_id', self.user_id)
+        kwargs.setdefault('agent_id', self.agent_id)
+        
+        return self.rag.retrieve(query, **kwargs)
+    
+    def query(self, question: str, **kwargs) -> "RAGResult":
+        """
+        Query knowledge and get a structured answer with citations.
+        
+        This is the recommended method for getting answers with source citations.
+        Returns a structured result with answer, citations, context used, and metadata.
+        
+        Args:
+            question: The question to answer
+            **kwargs: Additional arguments (top_k, rerank, etc.)
+            
+        Returns:
+            RAGResult with answer, citations, context_used, and metadata
+            
+        Raises:
+            ValueError: If no knowledge is configured
+            ImportError: If RAG module is not available
+            
+        Usage:
+            agent = Agent(knowledge=["doc.pdf"], retrieval_config={"citations": True})
+            result = agent.query("What is the main finding?")
+            print(result.answer)
+            for citation in result.citations:
+                print(f"  [{citation.id}] {citation.source}")
+        """
+        if not self._knowledge_sources and self.knowledge is None:
+            raise ValueError("No knowledge configured. Add knowledge=[] to Agent init.")
+        
+        if not self.rag:
+            raise ImportError("RAG module not available. Install with: pip install 'praisonaiagents[rag]'")
+        
+        kwargs.setdefault('user_id', self.user_id)
+        kwargs.setdefault('agent_id', self.agent_id)
+        
+        return self.rag.query(question, **kwargs)
+    
+    def rag_query(self, question: str, **kwargs) -> "RAGResult":
+        """
+        Query knowledge using RAG pipeline with citations.
+        
+        This is the recommended way to get answers with citations from an agent's knowledge.
+        
+        Args:
+            question: The question to answer
+            **kwargs: Additional arguments passed to RAG.query()
+            
+        Returns:
+            RAGResult with answer, citations, context_used, and metadata
+            
+        Raises:
+            ValueError: If no knowledge sources are configured
+            ImportError: If RAG module is not available
+            
+        Usage:
+            agent = Agent(knowledge=["doc.pdf"], rag_config={"include_citations": True})
+            result = agent.rag_query("What is the main finding?")
+            print(result.answer)
+            for citation in result.citations:
+                print(f"[{citation.id}] {citation.source}: {citation.text[:100]}")
+        """
+        if not self._knowledge_sources:
+            raise ValueError("No knowledge sources configured. Add knowledge=[] to Agent init.")
+        
+        if not self.rag:
+            raise ImportError("RAG module not available. Install with: pip install 'praisonaiagents[rag]'")
+        
+        # Pass agent context
+        kwargs.setdefault('user_id', self.user_id)
+        kwargs.setdefault('agent_id', self.agent_id)
+        
+        return self.rag.query(question, **kwargs)
+    
+    def chat_with_context(
+        self,
+        message: str,
+        context: "ContextPack",
+        *,
+        citations_mode: str = "append",
+        **kwargs,
+    ) -> str:
+        """
+        Chat with pre-retrieved context.
+        
+        This method allows AutoRagAgent or manual workflows to inject 
+        pre-retrieved context into the agent's chat, enabling conditional 
+        retrieval without duplicating RAG logic.
+        
+        Args:
+            message: User message/question
+            context: ContextPack from RAG.retrieve()
+            citations_mode: How to include citations (append/hidden/none)
+            **kwargs: Additional arguments passed to chat()
+            
+        Returns:
+            Agent response with optional citations
+            
+        Usage:
+            from praisonaiagents import AutoRagAgent
+            
+            auto_rag = AutoRagAgent(agent=my_agent)
+            result = auto_rag.chat("What are the key findings?")
+            
+            # Or manually:
+            context_pack = rag.retrieve("What are the key findings?")
+            response = agent.chat_with_context("What are the key findings?", context_pack)
+        """
+        # Build augmented prompt with context
+        augmented_prompt = f"""Based on the following context, answer the question.
+
+Context:
+{context.context}
+
+Question: {message}
+
+Answer:"""
+        
+        # Call chat with augmented prompt
+        response = self.chat(augmented_prompt, **kwargs)
+        
+        # Add citations if configured
+        if citations_mode == "append" and context.has_citations:
+            sources = "\n\nSources:\n"
+            for citation in context.citations:
+                sources += f"  [{citation.id}] {citation.source}\n"
+            response = response + sources
+        
+        return response
+    
     def _process_knowledge(self, knowledge_item):
         """Process and store knowledge from a file path, URL, or string."""
         try:
@@ -2210,7 +2545,7 @@ Your Goal: {self.goal}"""
         """Get the current session ID."""
         return self._session_id
 
-    def chat(self, prompt, temperature=1.0, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=None, task_name=None, task_description=None, task_id=None, config=None):
+    def chat(self, prompt, temperature=1.0, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=None, task_name=None, task_description=None, task_id=None, config=None, force_retrieval=False, skip_retrieval=False):
         # Apply rate limiter if configured (before any LLM call)
         if self._rate_limiter is not None:
             self._rate_limiter.acquire()
@@ -2249,23 +2584,42 @@ Your Goal: {self.goal}"""
         # Use agent's stream setting if not explicitly provided
         if stream is None:
             stream = self.stream
-        # Search for existing knowledge if any knowledge is provided
-        if self._knowledge_sources and not self._knowledge_processed:
-            self._ensure_knowledge_processed()
         
-        if self.knowledge:
-            search_results = self.knowledge.search(prompt, agent_id=self.agent_id)
-            if search_results:
-                # Check if search_results is a list of dictionaries or strings
-                if isinstance(search_results, dict) and 'results' in search_results:
-                    # Extract memory content from the results
-                    knowledge_content = "\n".join([result['memory'] for result in search_results['results']])
-                else:
-                    # If search_results is a list of strings, join them directly
-                    knowledge_content = "\n".join(search_results)
-                
-                # Append found knowledge to the prompt
-                prompt = f"{prompt}\n\nKnowledge: {knowledge_content}"
+        # Unified retrieval handling with policy-based decision
+        # Uses token-aware context building (DRY - same path as RAG pipeline)
+        if self._knowledge_sources or self.knowledge is not None:
+            if not self._knowledge_processed:
+                self._ensure_knowledge_processed()
+            
+            # Determine if we should retrieve based on policy
+            should_retrieve = False
+            if self._retrieval_config is not None:
+                should_retrieve = self._retrieval_config.should_retrieve(
+                    prompt if isinstance(prompt, str) else str(prompt),
+                    force=force_retrieval,
+                    skip=skip_retrieval
+                )
+            elif not skip_retrieval:
+                # No config but knowledge exists - retrieve by default unless skipped
+                should_retrieve = True if force_retrieval else (self.knowledge is not None)
+            
+            if should_retrieve and self.knowledge:
+                # Use unified retrieval path with token-aware context building
+                knowledge_context, _ = self._get_knowledge_context(
+                    prompt if isinstance(prompt, str) else str(prompt),
+                    use_rag=True  # Use RAG pipeline for token-aware context
+                )
+                if knowledge_context:
+                    # Format with safety boundaries
+                    if self._retrieval_config and self._retrieval_config.context_template:
+                        formatted_context = self._retrieval_config.context_template.format(
+                            context=knowledge_context
+                        )
+                    else:
+                        formatted_context = f"<retrieved_context>\n{knowledge_context}\n</retrieved_context>"
+                    
+                    # Append formatted knowledge to the prompt
+                    prompt = f"{prompt}\n\n{formatted_context}"
 
         if self._using_custom_llm:
             try:
@@ -3123,6 +3477,31 @@ Write the complete compiled report:"""
         # Return the single result if only one step
         return results[0]["result"] if results else None
 
+    def switch_model(self, new_model: str) -> None:
+        """
+        Switch the agent's LLM model while preserving conversation history.
+        
+        Args:
+            new_model: The new model name to switch to (e.g., "gpt-4o", "claude-3-sonnet")
+        """
+        # Store the new model name
+        self.llm = new_model
+        
+        # Recreate the LLM instance with the new model
+        try:
+            from ..llm.llm import LLM
+            self._llm_instance = LLM(
+                model=new_model,
+                base_url=self._openai_base_url,
+                api_key=self._openai_api_key,
+            )
+            self._using_custom_llm = True
+        except ImportError:
+            # If LLM class not available, just update the model string
+            pass
+        
+        # Chat history is preserved in self.chat_history (no action needed)
+
     def start(self, prompt: str, **kwargs):
         """Start the agent with a prompt. This is a convenience method that wraps chat()."""
         # Load history from past sessions if history_in_context is set

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

@@ -1,5 +1,6 @@
 """Agents module for managing multiple AI agents"""
 from .agents import PraisonAIAgents
 from .autoagents import AutoAgents
+from .auto_rag_agent import AutoRagAgent, AutoRagConfig, RetrievalPolicy
 
-__all__ = ['PraisonAIAgents', 'AutoAgents'] 
+__all__ = ['PraisonAIAgents', 'AutoAgents', 'AutoRagAgent', 'AutoRagConfig', 'RetrievalPolicy'] 

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

@@ -0,0 +1,415 @@
+"""
+AutoRagAgent - Agent with automatic RAG retrieval decision.
+
+This module provides an agent wrapper that automatically decides when to
+retrieve context from knowledge bases vs direct chat.
+
+Usage:
+    from praisonaiagents import Agent, AutoRagAgent
+    
+    agent = Agent(
+        name="Research Assistant",
+        knowledge=["docs/manual.pdf"],
+    )
+    
+    auto_rag = AutoRagAgent(agent=agent)
+    result = auto_rag.chat("What are the key findings?")  # Auto retrieves
+    result = auto_rag.chat("Hello!")  # Skips retrieval
+"""
+
+import logging
+import time
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import Optional, Set, Dict, Any, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from praisonaiagents.agent import Agent
+    from praisonaiagents.rag import RAG, ContextPack
+
+logger = logging.getLogger(__name__)
+
+
+class RetrievalPolicy(Enum):
+    """Policy for when to perform RAG retrieval."""
+    AUTO = "auto"      # Decide based on query heuristics
+    ALWAYS = "always"  # Always retrieve
+    NEVER = "never"    # Never retrieve (direct chat only)
+
+
+@dataclass
+class AutoRagConfig:
+    """Configuration for AutoRagAgent."""
+    
+    retrieval_policy: RetrievalPolicy = RetrievalPolicy.AUTO
+    
+    top_k: int = 5
+    hybrid: bool = False
+    rerank: bool = False
+    
+    include_citations: bool = True
+    citations_mode: str = "append"  # append, hidden, none
+    
+    max_context_tokens: int = 4000
+    
+    auto_keywords: Set[str] = field(default_factory=lambda: {
+        "what", "how", "why", "when", "where", "who", "which",
+        "explain", "describe", "summarize", "find", "search",
+        "tell me", "show me", "according to", "based on",
+        "cite", "source", "reference", "document", "paper",
+    })
+    
+    auto_min_length: int = 10
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Serialize to dictionary."""
+        return {
+            "retrieval_policy": self.retrieval_policy.value,
+            "top_k": self.top_k,
+            "hybrid": self.hybrid,
+            "rerank": self.rerank,
+            "include_citations": self.include_citations,
+            "citations_mode": self.citations_mode,
+            "max_context_tokens": self.max_context_tokens,
+            "auto_keywords": list(self.auto_keywords),
+            "auto_min_length": self.auto_min_length,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "AutoRagConfig":
+        """Create from dictionary."""
+        policy = data.get("retrieval_policy", "auto")
+        if isinstance(policy, str):
+            policy = RetrievalPolicy(policy)
+        
+        keywords = data.get("auto_keywords", None)
+        if keywords is not None and isinstance(keywords, list):
+            keywords = set(keywords)
+        
+        kwargs = {
+            "retrieval_policy": policy,
+            "top_k": data.get("top_k", 5),
+            "hybrid": data.get("hybrid", False),
+            "rerank": data.get("rerank", False),
+            "include_citations": data.get("include_citations", True),
+            "max_context_tokens": data.get("max_context_tokens", 4000),
+            "auto_min_length": data.get("auto_min_length", 10),
+            "citations_mode": data.get("citations_mode", "append"),
+        }
+        if keywords:
+            kwargs["auto_keywords"] = keywords
+        
+        return cls(**kwargs)
+
+
+class AutoRagAgent:
+    """
+    Agent wrapper with automatic RAG retrieval decision.
+    
+    Decides when to perform retrieval based on policy and heuristics,
+    then composes RAG context with Agent chat.
+    
+    This follows the same pattern as AutoAgents but for RAG:
+    - AutoAgents: auto-generates agent configs from instructions
+    - AutoRagAgent: auto-decides when to retrieve context
+    
+    Usage:
+        from praisonaiagents import Agent, AutoRagAgent
+        
+        agent = Agent(
+            name="Research Assistant",
+            knowledge=["docs/manual.pdf"],
+        )
+        
+        auto_rag = AutoRagAgent(agent=agent)
+        
+        # Auto mode - decides based on query
+        result = auto_rag.chat("What are the key findings?")
+        
+        # Force retrieval
+        result = auto_rag.chat("Hello", force_retrieval=True)
+        
+        # Skip retrieval
+        result = auto_rag.chat("What is 2+2?", skip_retrieval=True)
+    """
+    
+    def __init__(
+        self,
+        agent: "Agent",
+        rag: Optional["RAG"] = None,
+        config: Optional[AutoRagConfig] = None,
+        *,
+        retrieval_policy: Optional[str] = None,
+        top_k: Optional[int] = None,
+        hybrid: Optional[bool] = None,
+        rerank: Optional[bool] = None,
+        citations: bool = True,
+    ):
+        """
+        Initialize AutoRagAgent.
+        
+        Args:
+            agent: Agent instance (must have knowledge configured for RAG)
+            rag: Optional RAG instance (uses agent.rag if not provided)
+            config: AutoRagConfig instance
+            retrieval_policy: Shorthand for config.retrieval_policy (auto/always/never)
+            top_k: Shorthand for config.top_k
+            hybrid: Shorthand for config.hybrid
+            rerank: Shorthand for config.rerank
+            citations: Shorthand for config.include_citations
+        """
+        self.agent = agent
+        self._rag = rag
+        
+        # Build config from kwargs or use provided
+        if config is not None:
+            self.config = config
+        else:
+            config_kwargs = {}
+            if retrieval_policy is not None:
+                config_kwargs["retrieval_policy"] = RetrievalPolicy(retrieval_policy)
+            if top_k is not None:
+                config_kwargs["top_k"] = top_k
+            if hybrid is not None:
+                config_kwargs["hybrid"] = hybrid
+            if rerank is not None:
+                config_kwargs["rerank"] = rerank
+            config_kwargs["include_citations"] = citations
+            self.config = AutoRagConfig(**config_kwargs)
+        
+        # Lazy RAG initialization flag
+        self._rag_initialized = False
+    
+    @property
+    def rag(self) -> Optional["RAG"]:
+        """Lazy load RAG from agent if not provided."""
+        if self._rag is not None:
+            return self._rag
+        
+        if not self._rag_initialized:
+            # Try to get RAG from agent
+            if hasattr(self.agent, 'rag') and self.agent.rag is not None:
+                self._rag = self.agent.rag
+            self._rag_initialized = True
+        
+        return self._rag
+    
+    @property
+    def name(self) -> str:
+        """Delegate name to wrapped agent."""
+        return getattr(self.agent, 'name', 'AutoRagAgent')
+    
+    def _needs_retrieval(self, query: str) -> bool:
+        """
+        Determine if query needs retrieval based on heuristics.
+        
+        Simple, local heuristics (no ML classifier):
+        1. Query length check
+        2. Keyword presence check
+        3. Question mark check
+        
+        Args:
+            query: User query
+            
+        Returns:
+            True if retrieval should be performed
+        """
+        # Check minimum length
+        if len(query.strip()) < self.config.auto_min_length:
+            return False
+        
+        # Check for keywords
+        query_lower = query.lower()
+        for keyword in self.config.auto_keywords:
+            if keyword in query_lower:
+                return True
+        
+        # Check for question marks (likely a question)
+        if "?" in query:
+            return True
+        
+        return False
+    
+    def _should_retrieve(
+        self,
+        query: str,
+        force_retrieval: bool = False,
+        skip_retrieval: bool = False,
+    ) -> bool:
+        """
+        Determine if retrieval should be performed.
+        
+        Args:
+            query: User query
+            force_retrieval: Override to force retrieval
+            skip_retrieval: Override to skip retrieval
+            
+        Returns:
+            True if retrieval should be performed
+        """
+        # Explicit overrides take precedence
+        if skip_retrieval:
+            return False
+        if force_retrieval:
+            return True
+        
+        # Check if RAG is available
+        if self.rag is None:
+            logger.debug("RAG not available, skipping retrieval")
+            return False
+        
+        # Apply policy
+        if self.config.retrieval_policy == RetrievalPolicy.ALWAYS:
+            return True
+        elif self.config.retrieval_policy == RetrievalPolicy.NEVER:
+            return False
+        else:  # AUTO
+            return self._needs_retrieval(query)
+    
+    def _format_response_with_citations(
+        self,
+        response: str,
+        context_pack: Optional["ContextPack"],
+    ) -> str:
+        """Format response with citations based on config."""
+        if context_pack is None or not context_pack.has_citations:
+            return response
+        
+        if self.config.citations_mode == "none":
+            return response
+        elif self.config.citations_mode == "hidden":
+            return response
+        else:  # append
+            if not self.config.include_citations:
+                return response
+            
+            sources = "\n\nSources:\n"
+            for citation in context_pack.citations:
+                sources += f"  [{citation.id}] {citation.source}\n"
+            return response + sources
+    
+    def chat(
+        self,
+        message: str,
+        *,
+        force_retrieval: bool = False,
+        skip_retrieval: bool = False,
+        top_k: Optional[int] = None,
+        hybrid: Optional[bool] = None,
+        rerank: Optional[bool] = None,
+        user_id: Optional[str] = None,
+        **kwargs,
+    ) -> str:
+        """
+        Chat with automatic RAG retrieval decision.
+        
+        Decides whether to retrieve context, then runs agent chat.
+        
+        Args:
+            message: User message/query
+            force_retrieval: Force retrieval regardless of policy
+            skip_retrieval: Skip retrieval regardless of policy
+            top_k: Override top_k for retrieval
+            hybrid: Override hybrid retrieval setting
+            rerank: Override rerank setting
+            user_id: User ID for RAG retrieval (uses agent.user_id if not provided)
+            **kwargs: Additional arguments passed to agent.chat()
+            
+        Returns:
+            Agent response (with citations if configured)
+        """
+        start_time = time.time()
+        context_pack = None
+        
+        # Determine if we should retrieve
+        should_retrieve = self._should_retrieve(
+            message,
+            force_retrieval=force_retrieval,
+            skip_retrieval=skip_retrieval,
+        )
+        
+        if should_retrieve and self.rag is not None:
+            logger.debug(f"AutoRagAgent: Performing retrieval for: {message[:50]}...")
+            
+            # Get user_id from parameter or agent
+            effective_user_id = user_id or getattr(self.agent, 'user_id', None)
+            
+            # Retrieve context
+            context_pack = self.rag.retrieve(
+                query=message,
+                top_k=top_k or self.config.top_k,
+                hybrid=hybrid if hybrid is not None else self.config.hybrid,
+                rerank=rerank if rerank is not None else self.config.rerank,
+                user_id=effective_user_id,
+            )
+            
+            # Use agent's chat_with_context if available
+            if hasattr(self.agent, 'chat_with_context'):
+                response = self.agent.chat_with_context(
+                    message=message,
+                    context=context_pack,
+                    citations_mode=self.config.citations_mode,
+                    **kwargs,
+                )
+            else:
+                # Fallback: inject context into message
+                augmented_message = self._augment_message(message, context_pack)
+                response = self.agent.chat(augmented_message, **kwargs)
+                response = self._format_response_with_citations(response, context_pack)
+        else:
+            # Direct agent chat without retrieval
+            logger.debug(f"AutoRagAgent: Skipping retrieval for: {message[:50]}...")
+            response = self.agent.chat(message, **kwargs)
+        
+        elapsed = time.time() - start_time
+        logger.debug(f"AutoRagAgent: chat completed in {elapsed:.2f}s")
+        
+        return response
+    
+    def _augment_message(self, message: str, context_pack: "ContextPack") -> str:
+        """Augment message with retrieved context."""
+        return f"""Based on the following context, answer the question.
+
+Context:
+{context_pack.context}
+
+Question: {message}
+
+Answer:"""
+    
+    async def achat(
+        self,
+        message: str,
+        *,
+        force_retrieval: bool = False,
+        skip_retrieval: bool = False,
+        top_k: Optional[int] = None,
+        hybrid: Optional[bool] = None,
+        rerank: Optional[bool] = None,
+        user_id: Optional[str] = None,
+        **kwargs,
+    ) -> str:
+        """
+        Async version of chat.
+        
+        Currently wraps sync version. Can be extended for true async.
+        """
+        import asyncio
+        loop = asyncio.get_event_loop()
+        return await loop.run_in_executor(
+            None,
+            lambda: self.chat(
+                message=message,
+                force_retrieval=force_retrieval,
+                skip_retrieval=skip_retrieval,
+                top_k=top_k,
+                hybrid=hybrid,
+                rerank=rerank,
+                user_id=user_id,
+                **kwargs,
+            ),
+        )
+    
+    # Alias for consistency with Orchestrator pattern
+    run = chat
+    arun = achat

src/praisonai-agents/praisonaiagents/background/job_manager.py

@@ -0,0 +1,286 @@
+"""
+Background Job Manager for PraisonAI Agents.
+
+Provides job lifecycle tracking, auto-backgrounding based on threshold,
+and status inspection for long-running agent tasks.
+"""
+
+import threading
+import time
+import uuid
+from enum import Enum
+from typing import Any, Callable, Dict, Optional
+from dataclasses import dataclass, field
+from concurrent.futures import ThreadPoolExecutor, Future
+
+
+class JobStatus(str, Enum):
+    """Status of a background job."""
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
+    CANCELLED = "cancelled"
+
+
+@dataclass
+class JobInfo:
+    """Information about a background job."""
+    job_id: str
+    status: JobStatus
+    created_at: float = field(default_factory=time.time)
+    started_at: Optional[float] = None
+    completed_at: Optional[float] = None
+    result: Any = None
+    error: Optional[str] = None
+    
+    @property
+    def duration(self) -> Optional[float]:
+        """Get job duration in seconds."""
+        if self.started_at is None:
+            return None
+        end_time = self.completed_at or time.time()
+        return end_time - self.started_at
+
+
+class BackgroundJobManager:
+    """
+    Manages background jobs for agent tasks.
+    
+    Features:
+    - Job lifecycle tracking (pending, running, completed, failed)
+    - Auto-backgrounding based on execution time threshold
+    - Thread-safe job status inspection
+    - Configurable thread pool for concurrent execution
+    """
+    
+    def __init__(
+        self,
+        max_workers: int = 4,
+        auto_background_threshold: float = 5.0,
+    ):
+        """
+        Initialize the background job manager.
+        
+        Args:
+            max_workers: Maximum number of concurrent background jobs
+            auto_background_threshold: Time in seconds after which a job
+                should be automatically backgrounded
+        """
+        self.max_workers = max_workers
+        self.auto_background_threshold = auto_background_threshold
+        self._executor = ThreadPoolExecutor(max_workers=max_workers)
+        self._jobs: Dict[str, JobInfo] = {}
+        self._futures: Dict[str, Future] = {}
+        self._lock = threading.Lock()
+    
+    @property
+    def active_jobs(self) -> int:
+        """Get the number of active (pending or running) jobs."""
+        with self._lock:
+            return sum(
+                1 for job in self._jobs.values()
+                if job.status in (JobStatus.PENDING, JobStatus.RUNNING)
+            )
+    
+    def start_job(
+        self,
+        func: Callable[[], Any],
+        job_id: Optional[str] = None,
+    ) -> str:
+        """
+        Start a new background job.
+        
+        Args:
+            func: The function to execute in the background
+            job_id: Optional custom job ID (auto-generated if not provided)
+            
+        Returns:
+            The job ID
+        """
+        job_id = job_id or str(uuid.uuid4())[:8]
+        
+        job_info = JobInfo(
+            job_id=job_id,
+            status=JobStatus.PENDING,
+        )
+        
+        with self._lock:
+            self._jobs[job_id] = job_info
+        
+        def _run_job():
+            with self._lock:
+                self._jobs[job_id].status = JobStatus.RUNNING
+                self._jobs[job_id].started_at = time.time()
+            
+            try:
+                result = func()
+                with self._lock:
+                    self._jobs[job_id].status = JobStatus.COMPLETED
+                    self._jobs[job_id].completed_at = time.time()
+                    self._jobs[job_id].result = result
+                return result
+            except Exception as e:
+                with self._lock:
+                    self._jobs[job_id].status = JobStatus.FAILED
+                    self._jobs[job_id].completed_at = time.time()
+                    self._jobs[job_id].error = str(e)
+                raise
+        
+        future = self._executor.submit(_run_job)
+        with self._lock:
+            self._futures[job_id] = future
+        
+        return job_id
+    
+    def get_status(self, job_id: str) -> JobStatus:
+        """
+        Get the status of a job.
+        
+        Args:
+            job_id: The job ID to check
+            
+        Returns:
+            The job status
+            
+        Raises:
+            KeyError: If job_id is not found
+        """
+        with self._lock:
+            if job_id not in self._jobs:
+                raise KeyError(f"Job {job_id} not found")
+            return self._jobs[job_id].status
+    
+    def get_job_info(self, job_id: str) -> JobInfo:
+        """
+        Get full information about a job.
+        
+        Args:
+            job_id: The job ID to check
+            
+        Returns:
+            The job information
+            
+        Raises:
+            KeyError: If job_id is not found
+        """
+        with self._lock:
+            if job_id not in self._jobs:
+                raise KeyError(f"Job {job_id} not found")
+            return self._jobs[job_id]
+    
+    def get_result(self, job_id: str, timeout: Optional[float] = None) -> Any:
+        """
+        Get the result of a completed job.
+        
+        Args:
+            job_id: The job ID
+            timeout: Maximum time to wait for completion
+            
+        Returns:
+            The job result
+            
+        Raises:
+            KeyError: If job_id is not found
+            TimeoutError: If timeout is reached before completion
+            RuntimeError: If job failed
+        """
+        with self._lock:
+            if job_id not in self._futures:
+                raise KeyError(f"Job {job_id} not found")
+            future = self._futures[job_id]
+        
+        try:
+            return future.result(timeout=timeout)
+        except TimeoutError:
+            raise TimeoutError(f"Job {job_id} did not complete within {timeout} seconds")
+    
+    def cancel_job(self, job_id: str) -> bool:
+        """
+        Attempt to cancel a job.
+        
+        Args:
+            job_id: The job ID to cancel
+            
+        Returns:
+            True if cancellation was successful, False otherwise
+        """
+        with self._lock:
+            if job_id not in self._futures:
+                return False
+            future = self._futures[job_id]
+            cancelled = future.cancel()
+            if cancelled:
+                self._jobs[job_id].status = JobStatus.CANCELLED
+                self._jobs[job_id].completed_at = time.time()
+            return cancelled
+    
+    def list_jobs(self, status: Optional[JobStatus] = None) -> Dict[str, JobInfo]:
+        """
+        List all jobs, optionally filtered by status.
+        
+        Args:
+            status: Optional status filter
+            
+        Returns:
+            Dictionary of job_id -> JobInfo
+        """
+        with self._lock:
+            if status is None:
+                return dict(self._jobs)
+            return {
+                job_id: info
+                for job_id, info in self._jobs.items()
+                if info.status == status
+            }
+    
+    def cleanup_completed(self, max_age: float = 3600.0) -> int:
+        """
+        Remove completed jobs older than max_age seconds.
+        
+        Args:
+            max_age: Maximum age in seconds for completed jobs
+            
+        Returns:
+            Number of jobs removed
+        """
+        now = time.time()
+        removed = 0
+        
+        with self._lock:
+            to_remove = []
+            for job_id, info in self._jobs.items():
+                if info.status in (JobStatus.COMPLETED, JobStatus.FAILED, JobStatus.CANCELLED):
+                    if info.completed_at and (now - info.completed_at) > max_age:
+                        to_remove.append(job_id)
+            
+            for job_id in to_remove:
+                del self._jobs[job_id]
+                if job_id in self._futures:
+                    del self._futures[job_id]
+                removed += 1
+        
+        return removed
+    
+    def shutdown(self, wait: bool = True) -> None:
+        """
+        Shutdown the job manager.
+        
+        Args:
+            wait: Whether to wait for pending jobs to complete
+        """
+        self._executor.shutdown(wait=wait)
+
+
+# Global job manager instance (lazy initialized)
+_global_job_manager: Optional[BackgroundJobManager] = None
+_global_lock = threading.Lock()
+
+
+def get_job_manager() -> BackgroundJobManager:
+    """Get the global job manager instance."""
+    global _global_job_manager
+    with _global_lock:
+        if _global_job_manager is None:
+            _global_job_manager = BackgroundJobManager()
+        return _global_job_manager

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

@@ -1,30 +1,151 @@
 """
-Context module for PraisonAI Agents.
+Context Management Module for PraisonAI Agents.
 
-This module provides context retrieval capabilities including:
+This module provides comprehensive context management capabilities:
+- Token estimation and budgeting
+- Context composition within limits
+- Optimization strategies (truncate, sliding window, summarize, prune, smart)
+- Real-time context monitoring
+- Multi-agent context isolation
+
+Also includes:
 - Fast Context: Rapid parallel code search subagent
-"""
 
-# Lazy imports to avoid impacting package load time
-def __getattr__(name):
-    """Lazy import to avoid impacting package performance."""
-    if name == "FastContext":
-        from praisonaiagents.context.fast.fast_context import FastContext
-        return FastContext
-    elif name == "FastContextResult":
-        from praisonaiagents.context.fast.result import FastContextResult
-        return FastContextResult
-    elif name == "FileMatch":
-        from praisonaiagents.context.fast.result import FileMatch
-        return FileMatch
-    elif name == "LineRange":
-        from praisonaiagents.context.fast.result import LineRange
-        return LineRange
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+Zero Performance Impact:
+- All imports are lazy loaded via __getattr__
+- Features only activate when explicitly enabled
+- No overhead when context management is not used
+
+Usage:
+    from praisonaiagents.context import (
+        ContextBudgeter,
+        ContextComposer,
+        ContextMonitor,
+        get_optimizer,
+    )
+    
+    # Create budgeter for model
+    budgeter = ContextBudgeter(model="gpt-4o")
+    budget = budgeter.allocate()
+    
+    # Compose context within budget
+    composer = ContextComposer(budget=budget)
+    result = composer.compose(
+        system_prompt="You are helpful",
+        history=messages,
+        tools=tool_schemas,
+    )
+    
+    # Monitor context (opt-in)
+    monitor = ContextMonitor(enabled=True)
+    monitor.snapshot(ledger=result.ledger, budget=budget, messages=result.messages)
+"""
 
 __all__ = [
+    # Models
+    "ContextSegment",
+    "ContextLedger",
+    "BudgetAllocation",
+    "ContextSnapshot",
+    "OptimizerStrategy",
+    "OptimizationResult",
+    "MonitorConfig",
+    "ContextConfig",
+    # Token estimation
+    "estimate_tokens_heuristic",
+    "estimate_messages_tokens",
+    "estimate_tool_schema_tokens",
+    "TokenEstimatorImpl",
+    "get_estimator",
+    # Budgeting
+    "ContextBudgeter",
+    "get_model_limit",
+    "get_output_reserve",
+    # Ledger
+    "ContextLedgerManager",
+    "MultiAgentLedger",
+    # Composition
+    "ContextComposer",
+    "ComposedContext",
+    # Optimization
+    "BaseOptimizer",
+    "TruncateOptimizer",
+    "SlidingWindowOptimizer",
+    "PruneToolsOptimizer",
+    "NonDestructiveOptimizer",
+    "SummarizeOptimizer",
+    "SmartOptimizer",
+    "get_optimizer",
+    "get_effective_history",
+    # Monitoring
+    "ContextMonitor",
+    "MultiAgentMonitor",
+    "redact_sensitive",
+    "format_human_snapshot",
+    "format_json_snapshot",
+    # Fast Context (legacy)
     "FastContext",
     "FastContextResult",
     "FileMatch",
     "LineRange",
 ]
+
+
+def __getattr__(name: str):
+    """Lazy load module components to avoid import overhead."""
+    # Models
+    if name in ("ContextSegment", "ContextLedger", "BudgetAllocation", 
+                "ContextSnapshot", "OptimizerStrategy", "OptimizationResult",
+                "MonitorConfig", "ContextConfig"):
+        from . import models
+        return getattr(models, name)
+    
+    # Token estimation
+    if name in ("estimate_tokens_heuristic", "estimate_messages_tokens",
+                "estimate_tool_schema_tokens", "TokenEstimatorImpl", "get_estimator"):
+        from . import tokens
+        return getattr(tokens, name)
+    
+    # Budgeting
+    if name in ("ContextBudgeter", "get_model_limit", "get_output_reserve"):
+        from . import budgeter
+        return getattr(budgeter, name)
+    
+    # Ledger
+    if name in ("ContextLedgerManager", "MultiAgentLedger"):
+        from . import ledger
+        return getattr(ledger, name)
+    
+    # Composition
+    if name in ("ContextComposer", "ComposedContext"):
+        from . import composer
+        return getattr(composer, name)
+    
+    # Optimization
+    if name in ("BaseOptimizer", "TruncateOptimizer", "SlidingWindowOptimizer",
+                "PruneToolsOptimizer", "NonDestructiveOptimizer", "SummarizeOptimizer",
+                "SmartOptimizer", "get_optimizer", "get_effective_history"):
+        from . import optimizer
+        return getattr(optimizer, name)
+    
+    # Monitoring
+    if name in ("ContextMonitor", "MultiAgentMonitor", "redact_sensitive",
+                "format_human_snapshot", "format_json_snapshot"):
+        from . import monitor
+        return getattr(monitor, name)
+    
+    # Fast Context (legacy)
+    if name == "FastContext":
+        from praisonaiagents.context.fast.fast_context import FastContext
+        return FastContext
+    if name == "FastContextResult":
+        from praisonaiagents.context.fast.result import FastContextResult
+        return FastContextResult
+    if name == "FileMatch":
+        from praisonaiagents.context.fast.result import FileMatch
+        return FileMatch
+    if name == "LineRange":
+        from praisonaiagents.context.fast.result import LineRange
+        return LineRange
+    
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

src/praisonai-agents/praisonaiagents/context/budgeter.py

@@ -0,0 +1,229 @@
+"""
+Context Budgeter for PraisonAI Agents.
+
+Allocates token budgets across context segments based on model limits.
+"""
+
+from typing import Dict, Any, Optional
+from .models import BudgetAllocation
+
+
+# Model token limits (context window sizes)
+MODEL_LIMITS: Dict[str, int] = {
+    # OpenAI
+    "gpt-4o": 128000,
+    "gpt-4o-mini": 128000,
+    "gpt-4-turbo": 128000,
+    "gpt-4": 8192,
+    "gpt-3.5-turbo": 16385,
+    "gpt-3.5-turbo-16k": 16385,
+    # Anthropic
+    "claude-3-5-sonnet": 200000,
+    "claude-3-5-haiku": 200000,
+    "claude-3-opus": 200000,
+    "claude-3-sonnet": 200000,
+    "claude-3-haiku": 200000,
+    # Google
+    "gemini-2.0-flash": 1048576,
+    "gemini-1.5-pro": 2097152,
+    "gemini-1.5-flash": 1048576,
+    # Defaults
+    "default": 128000,
+}
+
+# Default output reserves by model family
+OUTPUT_RESERVES: Dict[str, int] = {
+    "gpt-4o": 16384,
+    "gpt-4o-mini": 16384,
+    "gpt-4-turbo": 4096,
+    "gpt-4": 4096,
+    "gpt-3.5-turbo": 4096,
+    "claude-3": 8192,
+    "gemini": 8192,
+    "default": 8000,
+}
+
+
+def get_model_limit(model: str) -> int:
+    """
+    Get context window limit for a model.
+    
+    Args:
+        model: Model name or identifier
+        
+    Returns:
+        Context window size in tokens
+    """
+    # Exact match
+    if model in MODEL_LIMITS:
+        return MODEL_LIMITS[model]
+    
+    # Partial match (e.g., "gpt-4o-2024-05-13" matches "gpt-4o")
+    model_lower = model.lower()
+    for key, limit in MODEL_LIMITS.items():
+        if key in model_lower or model_lower.startswith(key):
+            return limit
+    
+    return MODEL_LIMITS["default"]
+
+
+def get_output_reserve(model: str) -> int:
+    """
+    Get recommended output token reserve for a model.
+    
+    Args:
+        model: Model name
+        
+    Returns:
+        Output reserve in tokens
+    """
+    model_lower = model.lower()
+    
+    for key, reserve in OUTPUT_RESERVES.items():
+        if key in model_lower:
+            return reserve
+    
+    return OUTPUT_RESERVES["default"]
+
+
+class ContextBudgeter:
+    """
+    Allocates token budgets across context segments.
+    
+    Ensures context fits within model limits while reserving
+    space for output generation.
+    
+    Example:
+        budgeter = ContextBudgeter(model="gpt-4o")
+        allocation = budgeter.allocate()
+        print(f"History budget: {allocation.history_budget}")
+    """
+    
+    def __init__(
+        self,
+        model: str = "gpt-4o-mini",
+        model_limit: Optional[int] = None,
+        output_reserve: Optional[int] = None,
+        # Segment budget overrides (absolute tokens)
+        system_prompt_budget: int = 2000,
+        rules_budget: int = 500,
+        skills_budget: int = 500,
+        memory_budget: int = 1000,
+        tools_schema_budget: int = 2000,
+        tool_outputs_budget: int = 20000,
+        buffer_budget: int = 1000,
+        # Ratio-based allocation (if set, overrides fixed budgets)
+        history_ratio: Optional[float] = None,
+    ):
+        """
+        Initialize budgeter.
+        
+        Args:
+            model: Model name for limit lookup
+            model_limit: Override model limit
+            output_reserve: Override output reserve
+            system_prompt_budget: Budget for system prompt
+            rules_budget: Budget for rules
+            skills_budget: Budget for skills
+            memory_budget: Budget for memory
+            tools_schema_budget: Budget for tool schemas
+            tool_outputs_budget: Budget for tool outputs
+            buffer_budget: Safety buffer
+            history_ratio: If set, allocate this ratio of usable for history
+        """
+        self.model = model
+        self.model_limit = model_limit or get_model_limit(model)
+        self.output_reserve = output_reserve or get_output_reserve(model)
+        
+        self.system_prompt_budget = system_prompt_budget
+        self.rules_budget = rules_budget
+        self.skills_budget = skills_budget
+        self.memory_budget = memory_budget
+        self.tools_schema_budget = tools_schema_budget
+        self.tool_outputs_budget = tool_outputs_budget
+        self.buffer_budget = buffer_budget
+        self.history_ratio = history_ratio
+    
+    @property
+    def usable(self) -> int:
+        """Usable tokens after output reserve."""
+        return self.model_limit - self.output_reserve
+    
+    def allocate(self) -> BudgetAllocation:
+        """
+        Create a budget allocation.
+        
+        Returns:
+            BudgetAllocation with segment budgets
+        """
+        allocation = BudgetAllocation(
+            model_limit=self.model_limit,
+            output_reserve=self.output_reserve,
+            system_prompt=self.system_prompt_budget,
+            rules=self.rules_budget,
+            skills=self.skills_budget,
+            memory=self.memory_budget,
+            tools_schema=self.tools_schema_budget,
+            tool_outputs=self.tool_outputs_budget,
+            buffer=self.buffer_budget,
+            history=-1,  # Dynamic
+        )
+        
+        # If history_ratio is set, compute history budget from ratio
+        if self.history_ratio is not None:
+            allocation.history = int(self.usable * self.history_ratio)
+        
+        return allocation
+    
+    def check_overflow(
+        self,
+        current_tokens: int,
+        threshold: float = 0.8
+    ) -> bool:
+        """
+        Check if current tokens exceed threshold.
+        
+        Args:
+            current_tokens: Current total tokens
+            threshold: Threshold as fraction of usable (0.0-1.0)
+            
+        Returns:
+            True if overflow threshold exceeded
+        """
+        return current_tokens > (self.usable * threshold)
+    
+    def get_remaining(self, current_tokens: int) -> int:
+        """
+        Get remaining tokens before hitting usable limit.
+        
+        Args:
+            current_tokens: Current total tokens
+            
+        Returns:
+            Remaining tokens (can be negative if over limit)
+        """
+        return self.usable - current_tokens
+    
+    def get_utilization(self, current_tokens: int) -> float:
+        """
+        Get current utilization as fraction.
+        
+        Args:
+            current_tokens: Current total tokens
+            
+        Returns:
+            Utilization (0.0-1.0+)
+        """
+        if self.usable == 0:
+            return 0.0
+        return current_tokens / self.usable
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert budgeter state to dictionary."""
+        return {
+            "model": self.model,
+            "model_limit": self.model_limit,
+            "output_reserve": self.output_reserve,
+            "usable": self.usable,
+            "allocation": self.allocate().to_dict(),
+        }

src/praisonai-agents/praisonaiagents/context/composer.py

@@ -0,0 +1,335 @@
+"""
+Context Composer for PraisonAI Agents.
+
+Assembles context from segments within budget constraints.
+"""
+
+from typing import Dict, List, Any, Optional
+from .models import (
+    ContextLedger, BudgetAllocation, ContextSegment, ContextSnapshot
+)
+from .tokens import estimate_tokens_heuristic, estimate_messages_tokens
+from .ledger import ContextLedgerManager
+
+
+class ContextComposer:
+    """
+    Composes context from segments within budget constraints.
+    
+    Assembles system prompt, rules, skills, memory, tools, and history
+    while respecting token budgets and applying trimming as needed.
+    
+    Example:
+        composer = ContextComposer(budget=budgeter.allocate())
+        
+        result = composer.compose(
+            system_prompt="You are a helpful assistant",
+            history=messages,
+            tools=tool_schemas,
+        )
+        
+        # Use composed messages
+        response = llm.chat(result.messages)
+    """
+    
+    def __init__(
+        self,
+        budget: Optional[BudgetAllocation] = None,
+        preserve_tool_pairs: bool = True,
+        max_tool_output_tokens: int = 10000,
+        keep_recent_turns: int = 5,
+    ):
+        """
+        Initialize composer.
+        
+        Args:
+            budget: Budget allocation (uses defaults if None)
+            preserve_tool_pairs: Keep tool_call/tool_result pairs together
+            max_tool_output_tokens: Max tokens per tool output
+            keep_recent_turns: Minimum recent turns to keep
+        """
+        self.budget = budget or BudgetAllocation()
+        self.preserve_tool_pairs = preserve_tool_pairs
+        self.max_tool_output_tokens = max_tool_output_tokens
+        self.keep_recent_turns = keep_recent_turns
+        
+        self._ledger = ContextLedgerManager()
+        self._ledger.set_budget(self.budget)
+    
+    def compose(
+        self,
+        system_prompt: str = "",
+        rules: str = "",
+        skills: str = "",
+        memory: str = "",
+        tools: Optional[List[Dict[str, Any]]] = None,
+        history: Optional[List[Dict[str, Any]]] = None,
+        agent_id: Optional[str] = None,
+    ) -> "ComposedContext":
+        """
+        Compose context from segments.
+        
+        Args:
+            system_prompt: System prompt content
+            rules: Rules content
+            skills: Skills content
+            memory: Memory content
+            tools: Tool schemas
+            history: Conversation history
+            agent_id: Agent identifier
+            
+        Returns:
+            ComposedContext with messages and ledger
+        """
+        self._ledger.reset()
+        tools = tools or []
+        history = history or []
+        
+        # Track fixed segments
+        self._ledger.track_system_prompt(system_prompt)
+        self._ledger.track_rules(rules)
+        self._ledger.track_skills(skills)
+        self._ledger.track_memory(memory)
+        self._ledger.track_tools(tools)
+        
+        # Build combined system message
+        system_parts = []
+        if system_prompt:
+            system_parts.append(system_prompt)
+        if rules:
+            system_parts.append(f"\n## Rules\n{rules}")
+        if skills:
+            system_parts.append(f"\n## Skills\n{skills}")
+        if memory:
+            system_parts.append(f"\n## Memory\n{memory}")
+        
+        combined_system = "\n".join(system_parts)
+        
+        # Process history with budget awareness
+        processed_history = self._process_history(history)
+        
+        # Build final messages
+        messages = []
+        if combined_system:
+            messages.append({"role": "system", "content": combined_system})
+        messages.extend(processed_history)
+        
+        # Track final history tokens
+        history_tokens = estimate_messages_tokens(processed_history)
+        self._ledger.track_segment(
+            ContextSegment.HISTORY, 
+            history_tokens, 
+            len(processed_history)
+        )
+        
+        # Check for overflow
+        total = self._ledger.get_total()
+        overflow = total > self.budget.usable
+        
+        return ComposedContext(
+            messages=messages,
+            tools=tools,
+            ledger=self._ledger.get_ledger(),
+            total_tokens=total,
+            overflow=overflow,
+            warnings=self._ledger.get_warnings(),
+            agent_id=agent_id,
+        )
+    
+    def _process_history(
+        self,
+        history: List[Dict[str, Any]]
+    ) -> List[Dict[str, Any]]:
+        """
+        Process history with budget constraints.
+        
+        Applies:
+        - Tool output truncation
+        - Sliding window if over budget
+        - Tool pair preservation
+        """
+        if not history:
+            return []
+        
+        # First pass: truncate large tool outputs
+        processed = []
+        for msg in history:
+            processed_msg = self._truncate_tool_output(msg)
+            processed.append(processed_msg)
+        
+        # Check if within budget
+        history_budget = self.budget.history_budget
+        current_tokens = estimate_messages_tokens(processed)
+        
+        if current_tokens <= history_budget:
+            return processed
+        
+        # Apply sliding window
+        return self._apply_sliding_window(processed, history_budget)
+    
+    def _truncate_tool_output(self, msg: Dict[str, Any]) -> Dict[str, Any]:
+        """Truncate tool output if too large."""
+        if msg.get("role") != "tool" and not msg.get("tool_call_id"):
+            return msg
+        
+        content = msg.get("content", "")
+        if not isinstance(content, str):
+            return msg
+        
+        tokens = estimate_tokens_heuristic(content)
+        if tokens <= self.max_tool_output_tokens:
+            return msg
+        
+        # Truncate to max tokens (rough: 4 chars per token)
+        max_chars = self.max_tool_output_tokens * 4
+        truncated = content[:max_chars] + "\n...[output truncated]..."
+        
+        result = msg.copy()
+        result["content"] = truncated
+        result["_truncated"] = True
+        return result
+    
+    def _apply_sliding_window(
+        self,
+        history: List[Dict[str, Any]],
+        budget: int
+    ) -> List[Dict[str, Any]]:
+        """Apply sliding window to fit within budget."""
+        if not history:
+            return []
+        
+        # Always keep at least recent turns
+        min_keep = self.keep_recent_turns * 2  # user + assistant per turn
+        
+        # Start from end, add messages until budget exceeded
+        result = []
+        current_tokens = 0
+        
+        # Track tool call IDs to preserve pairs
+        tool_call_ids = set()
+        
+        for msg in reversed(history):
+            msg_tokens = estimate_tokens_heuristic(str(msg.get("content", "")))
+            
+            if current_tokens + msg_tokens > budget and len(result) >= min_keep:
+                break
+            
+            result.insert(0, msg)
+            current_tokens += msg_tokens
+            
+            # Track tool calls for pair preservation
+            if self.preserve_tool_pairs:
+                if "tool_calls" in msg:
+                    for tc in msg.get("tool_calls", []):
+                        if isinstance(tc, dict) and "id" in tc:
+                            tool_call_ids.add(tc["id"])
+                if msg.get("tool_call_id"):
+                    tool_call_ids.add(msg["tool_call_id"])
+        
+        # Ensure tool pairs are complete
+        if self.preserve_tool_pairs:
+            result = self._ensure_tool_pairs(result, history, tool_call_ids)
+        
+        return result
+    
+    def _ensure_tool_pairs(
+        self,
+        result: List[Dict[str, Any]],
+        full_history: List[Dict[str, Any]],
+        tool_call_ids: set
+    ) -> List[Dict[str, Any]]:
+        """Ensure tool_call/tool_result pairs are complete."""
+        # Find tool calls in result
+        result_call_ids = set()
+        result_response_ids = set()
+        
+        for msg in result:
+            if "tool_calls" in msg:
+                for tc in msg.get("tool_calls", []):
+                    if isinstance(tc, dict) and "id" in tc:
+                        result_call_ids.add(tc["id"])
+            if msg.get("tool_call_id"):
+                result_response_ids.add(msg["tool_call_id"])
+        
+        # Find missing pairs
+        missing_calls = result_response_ids - result_call_ids
+        missing_responses = result_call_ids - result_response_ids
+        
+        if not missing_calls and not missing_responses:
+            return result
+        
+        # Add missing messages from full history
+        for msg in full_history:
+            # Add missing tool calls
+            if "tool_calls" in msg:
+                for tc in msg.get("tool_calls", []):
+                    if isinstance(tc, dict) and tc.get("id") in missing_calls:
+                        if msg not in result:
+                            result.insert(0, msg)
+                        break
+            
+            # Add missing tool responses
+            if msg.get("tool_call_id") in missing_responses:
+                if msg not in result:
+                    result.append(msg)
+        
+        return result
+    
+    def get_ledger(self) -> ContextLedger:
+        """Get current ledger."""
+        return self._ledger.get_ledger()
+    
+    def get_warnings(self) -> List[str]:
+        """Get current warnings."""
+        return self._ledger.get_warnings()
+
+
+class ComposedContext:
+    """Result of context composition."""
+    
+    def __init__(
+        self,
+        messages: List[Dict[str, Any]],
+        tools: List[Dict[str, Any]],
+        ledger: ContextLedger,
+        total_tokens: int,
+        overflow: bool,
+        warnings: List[str],
+        agent_id: Optional[str] = None,
+    ):
+        self.messages = messages
+        self.tools = tools
+        self.ledger = ledger
+        self.total_tokens = total_tokens
+        self.overflow = overflow
+        self.warnings = warnings
+        self.agent_id = agent_id
+    
+    def to_snapshot(
+        self,
+        session_id: str = "",
+        model_name: str = "",
+        budget: Optional[BudgetAllocation] = None,
+    ) -> ContextSnapshot:
+        """Convert to snapshot for monitoring."""
+        return ContextSnapshot(
+            session_id=session_id,
+            agent_name=self.agent_id or "",
+            model_name=model_name,
+            budget=budget,
+            ledger=self.ledger,
+            utilization=self.total_tokens / budget.usable if budget else 0.0,
+            history_content=self.messages,
+            warnings=self.warnings,
+        )
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "message_count": len(self.messages),
+            "tool_count": len(self.tools),
+            "total_tokens": self.total_tokens,
+            "overflow": self.overflow,
+            "warnings": self.warnings,
+            "ledger": self.ledger.to_dict(),
+        }

src/praisonai-agents/praisonaiagents/context/ledger.py

@@ -0,0 +1,323 @@
+"""
+Context Ledger for PraisonAI Agents.
+
+Tracks token usage across context segments with per-agent and per-session support.
+"""
+
+from typing import Dict, List, Any, Optional
+from dataclasses import dataclass
+from .models import ContextLedger, ContextSegment, BudgetAllocation
+from .tokens import estimate_messages_tokens, estimate_tool_schema_tokens
+
+
+@dataclass
+class SegmentStats:
+    """Statistics for a context segment."""
+    tokens: int = 0
+    count: int = 0  # Number of items (messages, tools, etc.)
+    budget: int = 0
+    
+    @property
+    def utilization(self) -> float:
+        """Utilization as fraction of budget."""
+        if self.budget == 0:
+            return 0.0
+        return self.tokens / self.budget
+    
+    @property
+    def over_budget(self) -> bool:
+        """Check if over budget."""
+        return self.tokens > self.budget if self.budget > 0 else False
+
+
+class ContextLedgerManager:
+    """
+    Manages context token accounting.
+    
+    Tracks tokens per segment and provides utilization metrics.
+    Supports multi-agent scenarios with per-agent ledgers.
+    
+    Example:
+        manager = ContextLedgerManager()
+        manager.set_budget(budgeter.allocate())
+        
+        # Track segments
+        manager.track_system_prompt(system_prompt)
+        manager.track_history(messages)
+        manager.track_tools(tool_schemas)
+        
+        # Get stats
+        print(manager.get_utilization())
+        print(manager.get_warnings())
+    """
+    
+    def __init__(self, agent_id: Optional[str] = None):
+        """
+        Initialize ledger manager.
+        
+        Args:
+            agent_id: Optional agent identifier for multi-agent tracking
+        """
+        self.agent_id = agent_id
+        self._ledger = ContextLedger()
+        self._budget: Optional[BudgetAllocation] = None
+        self._segment_details: Dict[str, SegmentStats] = {}
+        
+        # Initialize segment stats
+        for segment in ContextSegment:
+            self._segment_details[segment.value] = SegmentStats()
+    
+    def set_budget(self, budget: BudgetAllocation) -> None:
+        """Set the budget allocation."""
+        self._budget = budget
+        
+        # Update segment budgets
+        for segment in ContextSegment:
+            self._segment_details[segment.value].budget = budget.get_segment_budget(segment)
+    
+    def reset(self) -> None:
+        """Reset all token counts."""
+        self._ledger = ContextLedger()
+        for segment in ContextSegment:
+            stats = self._segment_details[segment.value]
+            stats.tokens = 0
+            stats.count = 0
+    
+    def track_segment(
+        self,
+        segment: ContextSegment,
+        tokens: int,
+        count: int = 1
+    ) -> None:
+        """
+        Track tokens for a segment.
+        
+        Args:
+            segment: Context segment
+            tokens: Token count
+            count: Number of items
+        """
+        self._ledger.set_segment(segment, tokens)
+        stats = self._segment_details[segment.value]
+        stats.tokens = tokens
+        stats.count = count
+    
+    def add_to_segment(
+        self,
+        segment: ContextSegment,
+        tokens: int,
+        count: int = 1
+    ) -> None:
+        """
+        Add tokens to a segment.
+        
+        Args:
+            segment: Context segment
+            tokens: Tokens to add
+            count: Items to add
+        """
+        self._ledger.add_segment(segment, tokens)
+        stats = self._segment_details[segment.value]
+        stats.tokens += tokens
+        stats.count += count
+    
+    def track_system_prompt(self, content: str) -> int:
+        """Track system prompt tokens."""
+        from .tokens import estimate_tokens_heuristic
+        tokens = estimate_tokens_heuristic(content)
+        self.track_segment(ContextSegment.SYSTEM_PROMPT, tokens)
+        return tokens
+    
+    def track_rules(self, content: str) -> int:
+        """Track rules tokens."""
+        from .tokens import estimate_tokens_heuristic
+        tokens = estimate_tokens_heuristic(content)
+        self.track_segment(ContextSegment.RULES, tokens)
+        return tokens
+    
+    def track_skills(self, content: str) -> int:
+        """Track skills tokens."""
+        from .tokens import estimate_tokens_heuristic
+        tokens = estimate_tokens_heuristic(content)
+        self.track_segment(ContextSegment.SKILLS, tokens)
+        return tokens
+    
+    def track_memory(self, content: str) -> int:
+        """Track memory tokens."""
+        from .tokens import estimate_tokens_heuristic
+        tokens = estimate_tokens_heuristic(content)
+        self.track_segment(ContextSegment.MEMORY, tokens)
+        return tokens
+    
+    def track_history(self, messages: List[Dict[str, Any]]) -> int:
+        """
+        Track conversation history tokens.
+        
+        Args:
+            messages: List of message dicts
+            
+        Returns:
+            Total tokens
+        """
+        tokens = estimate_messages_tokens(messages)
+        self.track_segment(ContextSegment.HISTORY, tokens, len(messages))
+        self._ledger.message_count = len(messages)
+        
+        # Count turns (user messages)
+        turns = sum(1 for m in messages if m.get("role") == "user")
+        self._ledger.turn_count = turns
+        
+        return tokens
+    
+    def track_tools(self, tools: List[Dict[str, Any]]) -> int:
+        """
+        Track tool schema tokens.
+        
+        Args:
+            tools: List of tool definitions
+            
+        Returns:
+            Total tokens
+        """
+        tokens = estimate_tool_schema_tokens(tools)
+        self.track_segment(ContextSegment.TOOLS_SCHEMA, tokens, len(tools))
+        return tokens
+    
+    def track_tool_output(self, content: str) -> int:
+        """
+        Add a tool output to tracking.
+        
+        Args:
+            content: Tool output content
+            
+        Returns:
+            Tokens for this output
+        """
+        from .tokens import estimate_tokens_heuristic
+        tokens = estimate_tokens_heuristic(content)
+        self.add_to_segment(ContextSegment.TOOL_OUTPUTS, tokens)
+        self._ledger.tool_call_count += 1
+        return tokens
+    
+    def get_ledger(self) -> ContextLedger:
+        """Get current ledger."""
+        return self._ledger.copy()
+    
+    def get_total(self) -> int:
+        """Get total tokens across all segments."""
+        return self._ledger.total
+    
+    def get_utilization(self) -> float:
+        """Get overall utilization as fraction of usable budget."""
+        if self._budget is None:
+            return 0.0
+        usable = self._budget.usable
+        if usable == 0:
+            return 0.0
+        return self._ledger.total / usable
+    
+    def get_segment_stats(self, segment: ContextSegment) -> SegmentStats:
+        """Get stats for a segment."""
+        return self._segment_details[segment.value]
+    
+    def get_all_stats(self) -> Dict[str, SegmentStats]:
+        """Get stats for all segments."""
+        return self._segment_details.copy()
+    
+    def get_warnings(self, threshold: float = 0.9) -> List[str]:
+        """
+        Get warnings for segments near or over budget.
+        
+        Args:
+            threshold: Warning threshold (0.0-1.0)
+            
+        Returns:
+            List of warning messages
+        """
+        warnings = []
+        
+        for segment in ContextSegment:
+            stats = self._segment_details[segment.value]
+            if stats.budget > 0:
+                if stats.over_budget:
+                    warnings.append(
+                        f"{segment.value}: OVER BUDGET ({stats.tokens:,} / {stats.budget:,} tokens)"
+                    )
+                elif stats.utilization >= threshold:
+                    pct = int(stats.utilization * 100)
+                    warnings.append(
+                        f"{segment.value}: {pct}% of budget ({stats.tokens:,} / {stats.budget:,} tokens)"
+                    )
+        
+        # Overall utilization warning
+        if self._budget:
+            overall_util = self.get_utilization()
+            if overall_util >= threshold:
+                pct = int(overall_util * 100)
+                warnings.insert(0, f"Overall context: {pct}% of usable budget")
+        
+        return warnings
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary for serialization."""
+        return {
+            "agent_id": self.agent_id,
+            "ledger": self._ledger.to_dict(),
+            "total": self._ledger.total,
+            "utilization": self.get_utilization(),
+            "segments": {
+                name: {
+                    "tokens": stats.tokens,
+                    "count": stats.count,
+                    "budget": stats.budget,
+                    "utilization": stats.utilization,
+                }
+                for name, stats in self._segment_details.items()
+            },
+            "warnings": self.get_warnings(),
+        }
+
+
+class MultiAgentLedger:
+    """
+    Manages ledgers for multiple agents.
+    
+    Provides per-agent tracking and combined views.
+    """
+    
+    def __init__(self):
+        """Initialize multi-agent ledger."""
+        self._agents: Dict[str, ContextLedgerManager] = {}
+        self._shared_tokens: int = 0  # Tokens shared across agents
+    
+    def get_agent_ledger(self, agent_id: str) -> ContextLedgerManager:
+        """Get or create ledger for an agent."""
+        if agent_id not in self._agents:
+            self._agents[agent_id] = ContextLedgerManager(agent_id)
+        return self._agents[agent_id]
+    
+    def set_shared_tokens(self, tokens: int) -> None:
+        """Set tokens shared across agents (e.g., team memory)."""
+        self._shared_tokens = tokens
+    
+    def get_combined_total(self) -> int:
+        """Get total tokens across all agents plus shared."""
+        total = self._shared_tokens
+        for ledger in self._agents.values():
+            total += ledger.get_total()
+        return total
+    
+    def get_agent_ids(self) -> List[str]:
+        """Get list of tracked agent IDs."""
+        return list(self._agents.keys())
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "agents": {
+                agent_id: ledger.to_dict()
+                for agent_id, ledger in self._agents.items()
+            },
+            "shared_tokens": self._shared_tokens,
+            "combined_total": self.get_combined_total(),
+        }

src/praisonai-agents/praisonaiagents/context/models.py

@@ -0,0 +1,300 @@
+"""
+Context Management Data Models for PraisonAI Agents.
+
+Provides dataclasses and protocols for context budgeting, composition,
+optimization, and monitoring.
+"""
+
+from dataclasses import dataclass, field, asdict
+from typing import Dict, List, Any, Optional, Literal, Protocol, runtime_checkable
+from enum import Enum
+
+
+class ContextSegment(str, Enum):
+    """Segments that contribute to context."""
+    SYSTEM_PROMPT = "system_prompt"
+    RULES = "rules"
+    SKILLS = "skills"
+    MEMORY = "memory"
+    TOOLS_SCHEMA = "tools_schema"
+    HISTORY = "history"
+    TOOL_OUTPUTS = "tool_outputs"
+    BUFFER = "buffer"
+
+
+@dataclass
+class ContextLedger:
+    """
+    Tracks token usage across context segments.
+    
+    Provides per-segment token counts and total usage.
+    """
+    system_prompt: int = 0
+    rules: int = 0
+    skills: int = 0
+    memory: int = 0
+    tools_schema: int = 0
+    history: int = 0
+    tool_outputs: int = 0
+    buffer: int = 0
+    
+    # Metadata
+    turn_count: int = 0
+    message_count: int = 0
+    tool_call_count: int = 0
+    
+    @property
+    def total(self) -> int:
+        """Total tokens across all segments."""
+        return (
+            self.system_prompt +
+            self.rules +
+            self.skills +
+            self.memory +
+            self.tools_schema +
+            self.history +
+            self.tool_outputs +
+            self.buffer
+        )
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return asdict(self)
+    
+    def get_segment(self, segment: ContextSegment) -> int:
+        """Get token count for a segment."""
+        return getattr(self, segment.value, 0)
+    
+    def set_segment(self, segment: ContextSegment, tokens: int) -> None:
+        """Set token count for a segment."""
+        setattr(self, segment.value, tokens)
+    
+    def add_segment(self, segment: ContextSegment, tokens: int) -> None:
+        """Add tokens to a segment."""
+        current = self.get_segment(segment)
+        self.set_segment(segment, current + tokens)
+    
+    def copy(self) -> "ContextLedger":
+        """Create a copy of this ledger."""
+        return ContextLedger(
+            system_prompt=self.system_prompt,
+            rules=self.rules,
+            skills=self.skills,
+            memory=self.memory,
+            tools_schema=self.tools_schema,
+            history=self.history,
+            tool_outputs=self.tool_outputs,
+            buffer=self.buffer,
+            turn_count=self.turn_count,
+            message_count=self.message_count,
+            tool_call_count=self.tool_call_count,
+        )
+
+
+@dataclass
+class BudgetAllocation:
+    """
+    Token budget allocation across segments.
+    
+    Specifies maximum tokens allowed per segment.
+    """
+    model_limit: int = 128000
+    output_reserve: int = 8000
+    
+    # Segment budgets (absolute tokens or -1 for dynamic)
+    system_prompt: int = 2000
+    rules: int = 500
+    skills: int = 500
+    memory: int = 1000
+    tools_schema: int = 2000
+    history: int = -1  # Dynamic: fills remaining
+    tool_outputs: int = 20000
+    buffer: int = 1000
+    
+    @property
+    def usable(self) -> int:
+        """Usable tokens after output reserve."""
+        return self.model_limit - self.output_reserve
+    
+    @property
+    def fixed_total(self) -> int:
+        """Total of fixed segment budgets."""
+        total = 0
+        for seg in [self.system_prompt, self.rules, self.skills, 
+                    self.memory, self.tools_schema, self.tool_outputs, self.buffer]:
+            if seg > 0:
+                total += seg
+        return total
+    
+    @property
+    def history_budget(self) -> int:
+        """Computed history budget (remainder after fixed segments)."""
+        if self.history > 0:
+            return self.history
+        return max(0, self.usable - self.fixed_total)
+    
+    def get_segment_budget(self, segment: ContextSegment) -> int:
+        """Get budget for a segment."""
+        if segment == ContextSegment.HISTORY:
+            return self.history_budget
+        return getattr(self, segment.value, 0)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        result = asdict(self)
+        result['usable'] = self.usable
+        result['history_budget'] = self.history_budget
+        return result
+
+
+@dataclass
+class ContextSnapshot:
+    """
+    A snapshot of the current context state.
+    
+    Used for monitoring and debugging.
+    """
+    timestamp: str = ""
+    session_id: str = ""
+    agent_name: str = ""
+    model_name: str = ""
+    
+    # Budget info
+    budget: Optional[BudgetAllocation] = None
+    
+    # Token accounting
+    ledger: Optional[ContextLedger] = None
+    
+    # Utilization
+    utilization: float = 0.0
+    
+    # Content segments (for dump)
+    system_prompt_content: str = ""
+    rules_content: str = ""
+    skills_content: str = ""
+    memory_content: str = ""
+    tools_schema_content: str = ""
+    history_content: List[Dict[str, Any]] = field(default_factory=list)
+    
+    # Warnings
+    warnings: List[str] = field(default_factory=list)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary for JSON serialization."""
+        return {
+            "timestamp": self.timestamp,
+            "session_id": self.session_id,
+            "agent_name": self.agent_name,
+            "model_name": self.model_name,
+            "budget": self.budget.to_dict() if self.budget else None,
+            "ledger": self.ledger.to_dict() if self.ledger else None,
+            "utilization": self.utilization,
+            "warnings": self.warnings,
+            "history_turn_count": len(self.history_content),
+        }
+
+
+class OptimizerStrategy(str, Enum):
+    """Context optimization strategies."""
+    TRUNCATE = "truncate"
+    SLIDING_WINDOW = "sliding_window"
+    SUMMARIZE = "summarize"
+    PRUNE_TOOLS = "prune_tools"
+    NON_DESTRUCTIVE = "non_destructive"
+    SMART = "smart"
+
+
+@dataclass
+class OptimizationResult:
+    """Result of context optimization."""
+    original_tokens: int = 0
+    optimized_tokens: int = 0
+    tokens_saved: int = 0
+    strategy_used: OptimizerStrategy = OptimizerStrategy.SMART
+    messages_removed: int = 0
+    messages_tagged: int = 0
+    tool_outputs_pruned: int = 0
+    summary_added: bool = False
+    
+    @property
+    def reduction_percent(self) -> float:
+        """Percentage of tokens reduced."""
+        if self.original_tokens == 0:
+            return 0.0
+        return (self.tokens_saved / self.original_tokens) * 100
+
+
+@dataclass
+class MonitorConfig:
+    """Configuration for context monitoring."""
+    enabled: bool = False
+    path: str = "./context.txt"
+    format: Literal["human", "json"] = "human"
+    frequency: Literal["turn", "tool_call", "manual", "overflow"] = "turn"
+    redact_sensitive: bool = True
+    multi_agent_files: bool = True
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return asdict(self)
+
+
+@dataclass
+class ContextConfig:
+    """
+    Complete context management configuration.
+    
+    Merges settings from CLI flags, env vars, and config files.
+    """
+    # Auto-compaction
+    auto_compact: bool = True
+    compact_threshold: float = 0.8  # Trigger at 80% of usable budget
+    strategy: OptimizerStrategy = OptimizerStrategy.SMART
+    
+    # Budget overrides
+    output_reserve: int = 8000
+    history_ratio: float = 0.6  # 60% of usable for history
+    tool_output_max: int = 10000  # Max tokens per tool output
+    
+    # Pruning
+    prune_after_tokens: int = 40000
+    protected_tools: List[str] = field(default_factory=list)
+    
+    # Monitoring
+    monitor: MonitorConfig = field(default_factory=MonitorConfig)
+    
+    # Sliding window
+    keep_recent_turns: int = 5
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        result = asdict(self)
+        result['strategy'] = self.strategy.value
+        return result
+
+
+@runtime_checkable
+class TokenEstimator(Protocol):
+    """Protocol for token estimation."""
+    
+    def estimate(self, text: str) -> int:
+        """Estimate tokens for text."""
+        ...
+    
+    def estimate_messages(self, messages: List[Dict[str, Any]]) -> int:
+        """Estimate tokens for a list of messages."""
+        ...
+
+
+@runtime_checkable
+class ContextOptimizer(Protocol):
+    """Protocol for context optimization strategies."""
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: ContextLedger,
+    ) -> tuple[List[Dict[str, Any]], OptimizationResult]:
+        """Optimize messages to fit within target tokens."""
+        ...

src/praisonai-agents/praisonaiagents/context/monitor.py

@@ -0,0 +1,478 @@
+"""
+Context Monitor for PraisonAI Agents.
+
+Writes runtime context to disk for inspection and debugging.
+"""
+
+from typing import Dict, List, Any, Optional, Literal
+from pathlib import Path
+from datetime import datetime
+import json
+import re
+
+from .models import (
+    ContextSnapshot, ContextLedger, BudgetAllocation, MonitorConfig, ContextSegment
+)
+
+
+# Sensitive patterns for redaction
+SENSITIVE_PATTERNS = [
+    r'sk-[a-zA-Z0-9]{20,}',  # OpenAI API keys
+    r'sk-proj-[a-zA-Z0-9_-]+',  # OpenAI project keys
+    r'AKIA[0-9A-Z]{16}',  # AWS access keys
+    r'[a-zA-Z0-9]{32,}',  # Generic long tokens (conservative)
+    r'password["\s:=]+["\']?[^"\'\s]+',  # Password patterns
+    r'secret["\s:=]+["\']?[^"\'\s]+',  # Secret patterns
+    r'token["\s:=]+["\']?[^"\'\s]+',  # Token patterns
+    r'api[_-]?key["\s:=]+["\']?[^"\'\s]+',  # API key patterns
+]
+
+
+def redact_sensitive(text: str) -> str:
+    """
+    Redact sensitive information from text.
+    
+    Args:
+        text: Text to redact
+        
+    Returns:
+        Redacted text
+    """
+    result = text
+    for pattern in SENSITIVE_PATTERNS:
+        result = re.sub(pattern, '[REDACTED]', result, flags=re.IGNORECASE)
+    return result
+
+
+def format_human_snapshot(snapshot: ContextSnapshot, redact: bool = True) -> str:
+    """
+    Format snapshot as human-readable text.
+    
+    Args:
+        snapshot: Context snapshot
+        redact: Whether to redact sensitive info
+        
+    Returns:
+        Formatted text
+    """
+    lines = []
+    
+    # Header
+    lines.append("=" * 80)
+    lines.append("PRAISONAI CONTEXT SNAPSHOT")
+    lines.append("=" * 80)
+    lines.append(f"Timestamp: {snapshot.timestamp}")
+    lines.append(f"Session ID: {snapshot.session_id}")
+    lines.append(f"Agent: {snapshot.agent_name}")
+    lines.append(f"Model: {snapshot.model_name}")
+    
+    if snapshot.budget:
+        lines.append(f"Model Limit: {snapshot.budget.model_limit:,} tokens")
+        lines.append(f"Output Reserve: {snapshot.budget.output_reserve:,} tokens")
+        lines.append(f"Usable Budget: {snapshot.budget.usable:,} tokens")
+    
+    lines.append("")
+    
+    # Token Ledger
+    lines.append("-" * 80)
+    lines.append("TOKEN LEDGER")
+    lines.append("-" * 80)
+    lines.append(f"{'Component':<20} | {'Tokens':>10} | {'Budget':>10} | {'% Used':>8}")
+    lines.append("-" * 20 + "-+-" + "-" * 10 + "-+-" + "-" * 10 + "-+-" + "-" * 8)
+    
+    if snapshot.ledger and snapshot.budget:
+        segments = [
+            (ContextSegment.SYSTEM_PROMPT, "System Prompt"),
+            (ContextSegment.RULES, "Rules"),
+            (ContextSegment.SKILLS, "Skills"),
+            (ContextSegment.MEMORY, "Memory"),
+            (ContextSegment.TOOLS_SCHEMA, "Tool Schemas"),
+            (ContextSegment.HISTORY, "History"),
+            (ContextSegment.TOOL_OUTPUTS, "Tool Outputs"),
+        ]
+        
+        for seg, name in segments:
+            tokens = snapshot.ledger.get_segment(seg)
+            budget = snapshot.budget.get_segment_budget(seg)
+            pct = (tokens / budget * 100) if budget > 0 else 0
+            lines.append(f"{name:<20} | {tokens:>10,} | {budget:>10,} | {pct:>7.1f}%")
+        
+        lines.append("-" * 20 + "-+-" + "-" * 10 + "-+-" + "-" * 10 + "-+-" + "-" * 8)
+        lines.append(f"{'TOTAL':<20} | {snapshot.ledger.total:>10,} | {snapshot.budget.usable:>10,} | {snapshot.utilization * 100:>7.1f}%")
+    
+    lines.append("")
+    
+    # Warnings
+    if snapshot.warnings:
+        lines.append("-" * 80)
+        lines.append("WARNINGS")
+        lines.append("-" * 80)
+        for warning in snapshot.warnings:
+            lines.append(f"⚠ {warning}")
+        lines.append("")
+    
+    # History summary
+    if snapshot.history_content:
+        lines.append("-" * 80)
+        lines.append(f"CONVERSATION HISTORY ({len(snapshot.history_content)} messages)")
+        lines.append("-" * 80)
+        
+        for i, msg in enumerate(snapshot.history_content):
+            role = msg.get("role", "unknown").upper()
+            content = msg.get("content", "")
+            
+            if isinstance(content, str):
+                if redact:
+                    content = redact_sensitive(content)
+                # Truncate for display
+                if len(content) > 200:
+                    content = content[:200] + "..."
+                lines.append(f"[{i+1}] {role}: {content}")
+            else:
+                lines.append(f"[{i+1}] {role}: [complex content]")
+        
+        lines.append("")
+    
+    # Footer
+    lines.append("=" * 80)
+    lines.append("END CONTEXT SNAPSHOT")
+    lines.append("=" * 80)
+    
+    return "\n".join(lines)
+
+
+def format_json_snapshot(snapshot: ContextSnapshot, redact: bool = True) -> str:
+    """
+    Format snapshot as JSON.
+    
+    Args:
+        snapshot: Context snapshot
+        redact: Whether to redact sensitive info
+        
+    Returns:
+        JSON string
+    """
+    data = snapshot.to_dict()
+    
+    # Add history with optional redaction
+    if snapshot.history_content:
+        history = []
+        for msg in snapshot.history_content:
+            msg_copy = msg.copy()
+            content = msg_copy.get("content", "")
+            if isinstance(content, str) and redact:
+                msg_copy["content"] = redact_sensitive(content)
+            history.append(msg_copy)
+        data["history"] = history
+    
+    return json.dumps(data, indent=2, default=str)
+
+
+class ContextMonitor:
+    """
+    Monitors and writes context to disk.
+    
+    Provides real-time visibility into context state for debugging
+    and optimization.
+    
+    Example:
+        monitor = ContextMonitor(
+            enabled=True,
+            path="./context.txt",
+            format="human",
+        )
+        
+        # Write snapshot
+        monitor.snapshot(
+            ledger=ledger,
+            budget=budget,
+            messages=messages,
+            agent_name="Assistant",
+        )
+    """
+    
+    def __init__(
+        self,
+        enabled: bool = False,
+        path: str = "./context.txt",
+        format: Literal["human", "json"] = "human",
+        frequency: Literal["turn", "tool_call", "manual", "overflow"] = "turn",
+        redact_sensitive: bool = True,
+        multi_agent_files: bool = True,
+    ):
+        """
+        Initialize monitor.
+        
+        Args:
+            enabled: Whether monitoring is enabled
+            path: Output file path
+            format: Output format (human or json)
+            frequency: Update frequency
+            redact_sensitive: Redact sensitive info
+            multi_agent_files: Create per-agent files
+        """
+        self.enabled = enabled
+        self.path = Path(path)
+        self.format = format
+        self.frequency = frequency
+        self.redact = redact_sensitive
+        self.multi_agent_files = multi_agent_files
+        
+        self._last_snapshot: Optional[ContextSnapshot] = None
+        self._turn_count = 0
+        self._tool_call_count = 0
+    
+    @classmethod
+    def from_config(cls, config: MonitorConfig) -> "ContextMonitor":
+        """Create monitor from config."""
+        return cls(
+            enabled=config.enabled,
+            path=config.path,
+            format=config.format,
+            frequency=config.frequency,
+            redact_sensitive=config.redact_sensitive,
+            multi_agent_files=config.multi_agent_files,
+        )
+    
+    def enable(self) -> None:
+        """Enable monitoring."""
+        self.enabled = True
+    
+    def disable(self) -> None:
+        """Disable monitoring."""
+        self.enabled = False
+    
+    def set_path(self, path: str) -> None:
+        """Set output path."""
+        self.path = Path(path)
+    
+    def set_format(self, format: Literal["human", "json"]) -> None:
+        """Set output format."""
+        self.format = format
+    
+    def set_frequency(self, frequency: Literal["turn", "tool_call", "manual", "overflow"]) -> None:
+        """Set update frequency."""
+        self.frequency = frequency
+    
+    def should_write(
+        self,
+        trigger: Literal["turn", "tool_call", "manual", "overflow"]
+    ) -> bool:
+        """Check if should write based on frequency."""
+        if not self.enabled:
+            return False
+        
+        if trigger == "manual":
+            return True
+        
+        if self.frequency == "manual":
+            return trigger == "manual"
+        
+        if self.frequency == "overflow":
+            return trigger == "overflow"
+        
+        if self.frequency == "tool_call":
+            return trigger in ("tool_call", "overflow")
+        
+        # frequency == "turn"
+        return trigger in ("turn", "overflow")
+    
+    def snapshot(
+        self,
+        ledger: ContextLedger,
+        budget: BudgetAllocation,
+        messages: List[Dict[str, Any]],
+        session_id: str = "",
+        agent_name: str = "",
+        model_name: str = "",
+        trigger: Literal["turn", "tool_call", "manual", "overflow"] = "turn",
+    ) -> Optional[str]:
+        """
+        Create and write a context snapshot.
+        
+        Args:
+            ledger: Current token ledger
+            budget: Budget allocation
+            messages: Current messages
+            session_id: Session identifier
+            agent_name: Agent name
+            model_name: Model name
+            trigger: What triggered this snapshot
+            
+        Returns:
+            Path to written file, or None if not written
+        """
+        if not self.should_write(trigger):
+            return None
+        
+        # Track counts
+        if trigger == "turn":
+            self._turn_count += 1
+        elif trigger == "tool_call":
+            self._tool_call_count += 1
+        
+        # Create snapshot
+        snapshot = ContextSnapshot(
+            timestamp=datetime.utcnow().isoformat() + "Z",
+            session_id=session_id,
+            agent_name=agent_name,
+            model_name=model_name,
+            budget=budget,
+            ledger=ledger,
+            utilization=ledger.total / budget.usable if budget.usable > 0 else 0,
+            history_content=messages,
+            warnings=self._get_warnings(ledger, budget),
+        )
+        
+        self._last_snapshot = snapshot
+        
+        # Determine output path
+        output_path = self._get_output_path(agent_name)
+        
+        # Format content
+        if self.format == "json":
+            content = format_json_snapshot(snapshot, self.redact)
+        else:
+            content = format_human_snapshot(snapshot, self.redact)
+        
+        # Atomic write
+        self._atomic_write(output_path, content)
+        
+        return str(output_path)
+    
+    def _get_output_path(self, agent_name: str = "") -> Path:
+        """Get output path, optionally per-agent."""
+        if not self.multi_agent_files or not agent_name:
+            return self.path
+        
+        # Create per-agent path
+        stem = self.path.stem
+        suffix = self.path.suffix or (".json" if self.format == "json" else ".txt")
+        
+        # Sanitize agent name
+        safe_name = re.sub(r'[^\w\-]', '_', agent_name.lower())
+        
+        return self.path.parent / f"{stem}_{safe_name}{suffix}"
+    
+    def _get_warnings(
+        self,
+        ledger: ContextLedger,
+        budget: BudgetAllocation
+    ) -> List[str]:
+        """Generate warnings based on current state."""
+        warnings = []
+        
+        utilization = ledger.total / budget.usable if budget.usable > 0 else 0
+        
+        if utilization >= 1.0:
+            warnings.append(f"CRITICAL: Context overflow! {utilization*100:.1f}% of usable budget")
+        elif utilization >= 0.9:
+            warnings.append(f"WARNING: Context at {utilization*100:.1f}% of usable budget")
+        elif utilization >= 0.8:
+            warnings.append(f"NOTICE: Context at {utilization*100:.1f}% of usable budget")
+        
+        # Check individual segments
+        if budget.tool_outputs > 0:
+            tool_util = ledger.tool_outputs / budget.tool_outputs
+            if tool_util >= 0.9:
+                warnings.append(f"Tool outputs at {tool_util*100:.1f}% of budget")
+        
+        return warnings
+    
+    def _atomic_write(self, path: Path, content: str) -> None:
+        """Write content atomically using temp file + rename."""
+        # Ensure parent directory exists
+        path.parent.mkdir(parents=True, exist_ok=True)
+        
+        # Write to temp file
+        temp_path = path.with_suffix(path.suffix + ".tmp")
+        
+        try:
+            temp_path.write_text(content, encoding="utf-8")
+            # Atomic rename
+            temp_path.rename(path)
+        except Exception:
+            # Clean up temp file on error
+            if temp_path.exists():
+                temp_path.unlink()
+            raise
+    
+    def get_last_snapshot(self) -> Optional[ContextSnapshot]:
+        """Get the last snapshot."""
+        return self._last_snapshot
+    
+    def get_stats(self) -> Dict[str, Any]:
+        """Get monitor statistics."""
+        return {
+            "enabled": self.enabled,
+            "path": str(self.path),
+            "format": self.format,
+            "frequency": self.frequency,
+            "turn_count": self._turn_count,
+            "tool_call_count": self._tool_call_count,
+            "last_snapshot": self._last_snapshot.timestamp if self._last_snapshot else None,
+        }
+
+
+class MultiAgentMonitor:
+    """
+    Manages monitors for multiple agents.
+    
+    Creates per-agent monitors and optional combined view.
+    """
+    
+    def __init__(
+        self,
+        base_path: str = "./context",
+        format: Literal["human", "json"] = "human",
+        enabled: bool = False,
+        redact_sensitive: bool = True,
+    ):
+        """
+        Initialize multi-agent monitor.
+        
+        Args:
+            base_path: Base path for output files
+            format: Output format
+            enabled: Whether monitoring is enabled
+            redact_sensitive: Redact sensitive info
+        """
+        self.base_path = Path(base_path)
+        self.format = format
+        self.enabled = enabled
+        self.redact = redact_sensitive
+        
+        self._agents: Dict[str, ContextMonitor] = {}
+    
+    def get_agent_monitor(self, agent_id: str) -> ContextMonitor:
+        """Get or create monitor for an agent."""
+        if agent_id not in self._agents:
+            suffix = ".json" if self.format == "json" else ".txt"
+            safe_id = re.sub(r'[^\w\-]', '_', agent_id.lower())
+            path = self.base_path / f"context_{safe_id}{suffix}"
+            
+            self._agents[agent_id] = ContextMonitor(
+                enabled=self.enabled,
+                path=str(path),
+                format=self.format,
+                redact_sensitive=self.redact,
+                multi_agent_files=False,  # Already per-agent
+            )
+        
+        return self._agents[agent_id]
+    
+    def enable_all(self) -> None:
+        """Enable all monitors."""
+        self.enabled = True
+        for monitor in self._agents.values():
+            monitor.enable()
+    
+    def disable_all(self) -> None:
+        """Disable all monitors."""
+        self.enabled = False
+        for monitor in self._agents.values():
+            monitor.disable()
+    
+    def get_agent_ids(self) -> List[str]:
+        """Get list of monitored agent IDs."""
+        return list(self._agents.keys())

src/praisonai-agents/praisonaiagents/context/optimizer.py

@@ -0,0 +1,484 @@
+"""
+Context Optimizer for PraisonAI Agents.
+
+Provides strategies for reducing context size when approaching limits.
+"""
+
+from typing import Dict, List, Any, Optional
+from abc import ABC, abstractmethod
+from .models import ContextLedger, OptimizerStrategy, OptimizationResult
+from .tokens import estimate_messages_tokens
+
+
+class BaseOptimizer(ABC):
+    """Base class for optimization strategies."""
+    
+    @abstractmethod
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        """
+        Optimize messages to fit within target tokens.
+        
+        Args:
+            messages: Messages to optimize
+            target_tokens: Target token count
+            ledger: Current token ledger
+            
+        Returns:
+            Tuple of (optimized_messages, OptimizationResult)
+        """
+        pass
+
+
+class TruncateOptimizer(BaseOptimizer):
+    """Truncate oldest messages strategy."""
+    
+    def __init__(self, preserve_system: bool = True, preserve_recent: int = 5):
+        self.preserve_system = preserve_system
+        self.preserve_recent = preserve_recent
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        original_tokens = estimate_messages_tokens(messages)
+        
+        if original_tokens <= target_tokens:
+            return messages, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=original_tokens,
+                tokens_saved=0,
+                strategy_used=OptimizerStrategy.TRUNCATE,
+            )
+        
+        # Separate system and other messages
+        system_msgs = []
+        other_msgs = []
+        
+        for msg in messages:
+            if self.preserve_system and msg.get("role") == "system":
+                system_msgs.append(msg)
+            else:
+                other_msgs.append(msg)
+        
+        # Keep recent messages
+        recent = other_msgs[-self.preserve_recent:] if other_msgs else []
+        
+        result = system_msgs + recent
+        
+        # Continue removing until under target
+        while estimate_messages_tokens(result) > target_tokens and len(result) > 1:
+            for i, msg in enumerate(result):
+                if msg.get("role") != "system":
+                    result.pop(i)
+                    break
+        
+        optimized_tokens = estimate_messages_tokens(result)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.TRUNCATE,
+            messages_removed=len(messages) - len(result),
+        )
+
+
+class SlidingWindowOptimizer(BaseOptimizer):
+    """Keep a sliding window of recent messages."""
+    
+    def __init__(self, preserve_system: bool = True):
+        self.preserve_system = preserve_system
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        original_tokens = estimate_messages_tokens(messages)
+        
+        if original_tokens <= target_tokens:
+            return messages, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=original_tokens,
+                tokens_saved=0,
+                strategy_used=OptimizerStrategy.SLIDING_WINDOW,
+            )
+        
+        result = []
+        
+        # Keep system messages
+        for msg in messages:
+            if self.preserve_system and msg.get("role") == "system":
+                result.append(msg)
+        
+        # Add messages from end until target reached
+        non_system = [m for m in messages if m.get("role") != "system"]
+        
+        for msg in reversed(non_system):
+            test_result = result + [msg]
+            if estimate_messages_tokens(test_result) <= target_tokens:
+                result.insert(len([m for m in result if m.get("role") == "system"]), msg)
+            else:
+                break
+        
+        # Ensure order
+        system_msgs = [m for m in result if m.get("role") == "system"]
+        other_msgs = [m for m in result if m.get("role") != "system"]
+        result = system_msgs + other_msgs
+        
+        optimized_tokens = estimate_messages_tokens(result)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.SLIDING_WINDOW,
+            messages_removed=len(messages) - len(result),
+        )
+
+
+class PruneToolsOptimizer(BaseOptimizer):
+    """Prune old tool outputs while keeping tool calls."""
+    
+    def __init__(
+        self,
+        preserve_recent: int = 5,
+        max_output_chars: int = 500,
+        protected_tools: Optional[List[str]] = None,
+    ):
+        self.preserve_recent = preserve_recent
+        self.max_output_chars = max_output_chars
+        self.protected_tools = protected_tools or []
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        original_tokens = estimate_messages_tokens(messages)
+        
+        result = []
+        pruned_count = 0
+        
+        # Separate system and other messages
+        system_msgs = [m for m in messages if m.get("role") == "system"]
+        other_msgs = [m for m in messages if m.get("role") != "system"]
+        
+        result.extend(system_msgs)
+        
+        # Keep recent messages intact
+        recent = other_msgs[-self.preserve_recent:]
+        older = other_msgs[:-self.preserve_recent] if len(other_msgs) > self.preserve_recent else []
+        
+        # Prune older tool outputs
+        for msg in older:
+            role = msg.get("role", "")
+            content = msg.get("content", "")
+            
+            # Check if this is a tool result
+            if role == "tool" or msg.get("tool_call_id"):
+                # Check if protected
+                tool_name = msg.get("name", "")
+                if tool_name in self.protected_tools:
+                    result.append(msg)
+                    continue
+                
+                # Truncate if too long
+                if isinstance(content, str) and len(content) > self.max_output_chars:
+                    pruned_msg = msg.copy()
+                    pruned_msg["content"] = content[:self.max_output_chars] + "\n...[output truncated]..."
+                    pruned_msg["_pruned"] = True
+                    result.append(pruned_msg)
+                    pruned_count += 1
+                else:
+                    result.append(msg)
+            else:
+                result.append(msg)
+        
+        result.extend(recent)
+        
+        optimized_tokens = estimate_messages_tokens(result)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.PRUNE_TOOLS,
+            tool_outputs_pruned=pruned_count,
+        )
+
+
+class NonDestructiveOptimizer(BaseOptimizer):
+    """
+    Tag messages for exclusion without deleting them.
+    
+    Messages are tagged with _condense_parent and excluded from
+    effective history, but can be restored on rewind.
+    """
+    
+    def __init__(self, preserve_recent: int = 3):
+        self.preserve_recent = preserve_recent
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        import uuid
+        
+        original_tokens = estimate_messages_tokens(messages)
+        
+        if original_tokens <= target_tokens:
+            return messages, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=original_tokens,
+                tokens_saved=0,
+                strategy_used=OptimizerStrategy.NON_DESTRUCTIVE,
+            )
+        
+        condense_id = str(uuid.uuid4())
+        
+        # Separate system and other messages
+        system_msgs = [m for m in messages if m.get("role") == "system"]
+        other_msgs = [m for m in messages if m.get("role") != "system"]
+        
+        # Keep recent, tag older
+        keep_start = max(0, len(other_msgs) - self.preserve_recent)
+        
+        result = []
+        tagged_count = 0
+        
+        # Add system messages
+        result.extend(system_msgs)
+        
+        # Tag older messages
+        for i, msg in enumerate(other_msgs):
+            if i < keep_start:
+                tagged_msg = msg.copy()
+                if "_condense_parent" not in tagged_msg:
+                    tagged_msg["_condense_parent"] = condense_id
+                    tagged_count += 1
+                result.append(tagged_msg)
+            else:
+                result.append(msg)
+        
+        # Calculate effective tokens (excluding tagged)
+        effective_msgs = [m for m in result if "_condense_parent" not in m]
+        optimized_tokens = estimate_messages_tokens(effective_msgs)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.NON_DESTRUCTIVE,
+            messages_tagged=tagged_count,
+        )
+
+
+class SummarizeOptimizer(BaseOptimizer):
+    """
+    Summarize older messages using LLM.
+    
+    Note: This is a placeholder that creates a structured summary.
+    Actual LLM summarization should be done at the agent level.
+    """
+    
+    def __init__(self, preserve_recent: int = 5, max_summary_items: int = 10):
+        self.preserve_recent = preserve_recent
+        self.max_summary_items = max_summary_items
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        original_tokens = estimate_messages_tokens(messages)
+        
+        if original_tokens <= target_tokens:
+            return messages, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=original_tokens,
+                tokens_saved=0,
+                strategy_used=OptimizerStrategy.SUMMARIZE,
+            )
+        
+        # Separate system and other messages
+        system_msgs = [m for m in messages if m.get("role") == "system"]
+        other_msgs = [m for m in messages if m.get("role") != "system"]
+        
+        result = list(system_msgs)
+        
+        # Keep recent messages
+        recent = other_msgs[-self.preserve_recent:]
+        older = other_msgs[:-self.preserve_recent] if len(other_msgs) > self.preserve_recent else []
+        
+        if older:
+            # Create summary
+            summary_parts = []
+            for msg in older[:self.max_summary_items]:
+                role = msg.get("role", "unknown")
+                content = msg.get("content", "")
+                if isinstance(content, str) and content:
+                    summary_parts.append(f"[{role}]: {content[:150]}...")
+            
+            if summary_parts:
+                summary = (
+                    "[Previous conversation summary]\n"
+                    + "\n".join(summary_parts)
+                )
+                result.append({
+                    "role": "system",
+                    "content": summary,
+                    "_summary": True,
+                    "_original_count": len(older),
+                })
+        
+        result.extend(recent)
+        
+        optimized_tokens = estimate_messages_tokens(result)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.SUMMARIZE,
+            messages_removed=len(older),
+            summary_added=bool(older),
+        )
+
+
+class SmartOptimizer(BaseOptimizer):
+    """
+    Smart optimization combining multiple strategies.
+    
+    Applies strategies in order:
+    1. Prune tool outputs
+    2. Sliding window
+    3. Summarize if still over
+    """
+    
+    def __init__(
+        self,
+        preserve_recent: int = 5,
+        protected_tools: Optional[List[str]] = None,
+    ):
+        self.preserve_recent = preserve_recent
+        self.protected_tools = protected_tools or []
+        
+        self._prune = PruneToolsOptimizer(
+            preserve_recent=preserve_recent,
+            protected_tools=protected_tools,
+        )
+        self._window = SlidingWindowOptimizer()
+        self._summarize = SummarizeOptimizer(preserve_recent=preserve_recent)
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        target_tokens: int,
+        ledger: Optional[ContextLedger] = None,
+    ) -> tuple:
+        original_tokens = estimate_messages_tokens(messages)
+        
+        if original_tokens <= target_tokens:
+            return messages, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=original_tokens,
+                tokens_saved=0,
+                strategy_used=OptimizerStrategy.SMART,
+            )
+        
+        # Step 1: Prune tool outputs
+        result, prune_result = self._prune.optimize(messages, target_tokens, ledger)
+        
+        if estimate_messages_tokens(result) <= target_tokens:
+            return result, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=prune_result.optimized_tokens,
+                tokens_saved=original_tokens - prune_result.optimized_tokens,
+                strategy_used=OptimizerStrategy.SMART,
+                tool_outputs_pruned=prune_result.tool_outputs_pruned,
+            )
+        
+        # Step 2: Sliding window
+        result, window_result = self._window.optimize(result, target_tokens, ledger)
+        
+        if estimate_messages_tokens(result) <= target_tokens:
+            return result, OptimizationResult(
+                original_tokens=original_tokens,
+                optimized_tokens=window_result.optimized_tokens,
+                tokens_saved=original_tokens - window_result.optimized_tokens,
+                strategy_used=OptimizerStrategy.SMART,
+                tool_outputs_pruned=prune_result.tool_outputs_pruned,
+                messages_removed=window_result.messages_removed,
+            )
+        
+        # Step 3: Summarize
+        result, summary_result = self._summarize.optimize(result, target_tokens, ledger)
+        
+        optimized_tokens = estimate_messages_tokens(result)
+        
+        return result, OptimizationResult(
+            original_tokens=original_tokens,
+            optimized_tokens=optimized_tokens,
+            tokens_saved=original_tokens - optimized_tokens,
+            strategy_used=OptimizerStrategy.SMART,
+            tool_outputs_pruned=prune_result.tool_outputs_pruned,
+            messages_removed=window_result.messages_removed + summary_result.messages_removed,
+            summary_added=summary_result.summary_added,
+        )
+
+
+# Strategy registry
+OPTIMIZER_REGISTRY: Dict[OptimizerStrategy, type] = {
+    OptimizerStrategy.TRUNCATE: TruncateOptimizer,
+    OptimizerStrategy.SLIDING_WINDOW: SlidingWindowOptimizer,
+    OptimizerStrategy.PRUNE_TOOLS: PruneToolsOptimizer,
+    OptimizerStrategy.NON_DESTRUCTIVE: NonDestructiveOptimizer,
+    OptimizerStrategy.SUMMARIZE: SummarizeOptimizer,
+    OptimizerStrategy.SMART: SmartOptimizer,
+}
+
+
+def get_optimizer(
+    strategy: OptimizerStrategy,
+    **kwargs
+) -> BaseOptimizer:
+    """
+    Get an optimizer instance for a strategy.
+    
+    Args:
+        strategy: Optimization strategy
+        **kwargs: Strategy-specific arguments
+        
+    Returns:
+        Optimizer instance
+    """
+    optimizer_class = OPTIMIZER_REGISTRY.get(strategy, SmartOptimizer)
+    return optimizer_class(**kwargs)
+
+
+def get_effective_history(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """
+    Get effective history excluding tagged messages.
+    
+    Filters out messages with _condense_parent tags.
+    
+    Args:
+        messages: Full message history
+        
+    Returns:
+        Effective messages for API calls
+    """
+    return [m for m in messages if "_condense_parent" not in m]

src/praisonai-agents/praisonaiagents/context/tokens.py

@@ -0,0 +1,238 @@
+"""
+Token Estimation for PraisonAI Agents.
+
+Provides fast, offline token estimation with optional accurate tokenizer support.
+"""
+
+from typing import List, Dict, Any, Optional
+import json
+
+
+# Token estimation constants (based on OpenAI tokenizer patterns)
+ASCII_TOKENS_PER_CHAR = 0.25  # ~4 chars per token for ASCII
+NON_ASCII_TOKENS_PER_CHAR = 1.3  # CJK and other scripts are denser
+
+# Optional tokenizer cache
+_tokenizer_cache: Dict[str, Any] = {}
+
+
+def estimate_tokens_heuristic(text: str) -> int:
+    """
+    Estimate token count using character-based heuristic.
+    
+    Fast and works offline. Accuracy: ~85-95% for English text.
+    
+    Args:
+        text: Text to estimate tokens for
+        
+    Returns:
+        Estimated token count
+    """
+    if not text:
+        return 0
+    
+    total = 0.0
+    for char in text:
+        code_point = ord(char)
+        if code_point <= 127:
+            total += ASCII_TOKENS_PER_CHAR
+        else:
+            total += NON_ASCII_TOKENS_PER_CHAR
+    
+    return max(1, int(total))
+
+
+def estimate_tokens_accurate(text: str, model: str = "gpt-4") -> int:
+    """
+    Estimate tokens using tiktoken if available, else fallback to heuristic.
+    
+    Args:
+        text: Text to estimate tokens for
+        model: Model name for tokenizer selection
+        
+    Returns:
+        Token count
+    """
+    try:
+        import tiktoken
+        
+        # Cache tokenizer
+        if model not in _tokenizer_cache:
+            try:
+                _tokenizer_cache[model] = tiktoken.encoding_for_model(model)
+            except KeyError:
+                # Fallback to cl100k_base for unknown models
+                _tokenizer_cache[model] = tiktoken.get_encoding("cl100k_base")
+        
+        enc = _tokenizer_cache[model]
+        return len(enc.encode(text))
+    except ImportError:
+        return estimate_tokens_heuristic(text)
+
+
+def estimate_message_tokens(message: Dict[str, Any], use_accurate: bool = False) -> int:
+    """
+    Estimate tokens for a single message.
+    
+    Handles various message formats including tool calls and multi-part content.
+    
+    Args:
+        message: Message dict with role and content
+        use_accurate: Use tiktoken if available
+        
+    Returns:
+        Estimated token count
+    """
+    estimate_fn = estimate_tokens_accurate if use_accurate else estimate_tokens_heuristic
+    
+    total = 0
+    
+    # Role overhead (~4 tokens for role markers)
+    total += 4
+    
+    # Content
+    content = message.get("content", "")
+    if isinstance(content, str):
+        total += estimate_fn(content)
+    elif isinstance(content, list):
+        # Multi-part content (text, images, etc.)
+        for part in content:
+            if isinstance(part, dict):
+                if "text" in part:
+                    total += estimate_fn(str(part["text"]))
+                elif "type" in part:
+                    # Image or other media - estimate based on type
+                    if part.get("type") == "image_url":
+                        total += 85  # Base image token cost
+                    else:
+                        total += estimate_fn(json.dumps(part))
+            else:
+                total += estimate_fn(str(part))
+    
+    # Tool calls
+    if "tool_calls" in message:
+        for tool_call in message.get("tool_calls", []):
+            if isinstance(tool_call, dict):
+                # Function name and arguments
+                func = tool_call.get("function", {})
+                total += estimate_fn(func.get("name", ""))
+                total += estimate_fn(func.get("arguments", ""))
+                total += 10  # Overhead for tool call structure
+    
+    # Tool call ID (for tool responses)
+    if "tool_call_id" in message:
+        total += 10
+    
+    # Name field
+    if "name" in message:
+        total += estimate_fn(message["name"])
+    
+    return total
+
+
+def estimate_messages_tokens(
+    messages: List[Dict[str, Any]],
+    use_accurate: bool = False
+) -> int:
+    """
+    Estimate total tokens for a list of messages.
+    
+    Args:
+        messages: List of message dicts
+        use_accurate: Use tiktoken if available
+        
+    Returns:
+        Total estimated token count
+    """
+    if not messages:
+        return 0
+    
+    total = 0
+    for msg in messages:
+        total += estimate_message_tokens(msg, use_accurate)
+    
+    # Add overhead for message array structure
+    total += 3  # Array markers
+    
+    return total
+
+
+def estimate_tool_schema_tokens(
+    tools: List[Dict[str, Any]],
+    use_accurate: bool = False
+) -> int:
+    """
+    Estimate tokens for tool/function schemas.
+    
+    Args:
+        tools: List of tool definitions
+        use_accurate: Use tiktoken if available
+        
+    Returns:
+        Estimated token count
+    """
+    if not tools:
+        return 0
+    
+    estimate_fn = estimate_tokens_accurate if use_accurate else estimate_tokens_heuristic
+    
+    # Serialize tools to JSON and estimate
+    try:
+        tools_json = json.dumps(tools)
+        return estimate_fn(tools_json)
+    except (TypeError, ValueError):
+        # Fallback: estimate per-tool
+        total = 0
+        for tool in tools:
+            if isinstance(tool, dict):
+                total += estimate_fn(json.dumps(tool))
+            else:
+                total += 100  # Default estimate per tool
+        return total
+
+
+class TokenEstimatorImpl:
+    """
+    Token estimator implementation.
+    
+    Provides both heuristic and accurate estimation methods.
+    """
+    
+    def __init__(self, use_accurate: bool = False, model: str = "gpt-4"):
+        """
+        Initialize estimator.
+        
+        Args:
+            use_accurate: Use tiktoken if available
+            model: Model name for tokenizer selection
+        """
+        self.use_accurate = use_accurate
+        self.model = model
+    
+    def estimate(self, text: str) -> int:
+        """Estimate tokens for text."""
+        if self.use_accurate:
+            return estimate_tokens_accurate(text, self.model)
+        return estimate_tokens_heuristic(text)
+    
+    def estimate_messages(self, messages: List[Dict[str, Any]]) -> int:
+        """Estimate tokens for messages."""
+        return estimate_messages_tokens(messages, self.use_accurate)
+    
+    def estimate_tools(self, tools: List[Dict[str, Any]]) -> int:
+        """Estimate tokens for tool schemas."""
+        return estimate_tool_schema_tokens(tools, self.use_accurate)
+
+
+# Default estimator instance
+_default_estimator: Optional[TokenEstimatorImpl] = None
+
+
+def get_estimator(use_accurate: bool = False, model: str = "gpt-4") -> TokenEstimatorImpl:
+    """Get or create a token estimator."""
+    global _default_estimator
+    
+    if _default_estimator is None or _default_estimator.use_accurate != use_accurate:
+        _default_estimator = TokenEstimatorImpl(use_accurate, model)
+    
+    return _default_estimator

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

@@ -0,0 +1,76 @@
+"""
+PraisonAI RAG - Retrieval Augmented Generation Module.
+
+This module provides a thin orchestration layer over Knowledge for RAG workflows.
+Knowledge handles indexing/retrieval; RAG adds answer generation with citations.
+
+Usage:
+    from praisonaiagents.rag import RAG, RAGConfig, RAGResult, Citation
+    
+    # With existing Knowledge
+    rag = RAG(knowledge=my_knowledge)
+    result = rag.query("What is the main finding?")
+    print(result.answer)
+    for citation in result.citations:
+        print(f"  [{citation.id}] {citation.source}")
+
+All imports are lazy to avoid performance impact when RAG is not used.
+"""
+
+from typing import TYPE_CHECKING
+
+# Lazy loading to avoid import overhead
+_LAZY_IMPORTS = {
+    # Models
+    "Citation": ("praisonaiagents.rag.models", "Citation"),
+    "ContextPack": ("praisonaiagents.rag.models", "ContextPack"),
+    "RAGResult": ("praisonaiagents.rag.models", "RAGResult"),
+    "RAGConfig": ("praisonaiagents.rag.models", "RAGConfig"),
+    "RetrievalStrategy": ("praisonaiagents.rag.models", "RetrievalStrategy"),
+    # Unified retrieval config (Agent-first)
+    "RetrievalConfig": ("praisonaiagents.rag.retrieval_config", "RetrievalConfig"),
+    "RetrievalPolicy": ("praisonaiagents.rag.retrieval_config", "RetrievalPolicy"),
+    "CitationsMode": ("praisonaiagents.rag.retrieval_config", "CitationsMode"),
+    "create_retrieval_config": ("praisonaiagents.rag.retrieval_config", "create_retrieval_config"),
+    # Protocols
+    "ContextBuilderProtocol": ("praisonaiagents.rag.protocols", "ContextBuilderProtocol"),
+    "CitationFormatterProtocol": ("praisonaiagents.rag.protocols", "CitationFormatterProtocol"),
+    # Pipeline (internal - use Agent for primary access)
+    "RAG": ("praisonaiagents.rag.pipeline", "RAG"),
+    # Context utilities
+    "build_context": ("praisonaiagents.rag.context", "build_context"),
+    "truncate_context": ("praisonaiagents.rag.context", "truncate_context"),
+    "deduplicate_chunks": ("praisonaiagents.rag.context", "deduplicate_chunks"),
+}
+
+_cache = {}
+
+
+def __getattr__(name: str):
+    """Lazy load RAG components."""
+    if name in _cache:
+        return _cache[name]
+    
+    if name in _LAZY_IMPORTS:
+        module_path, attr_name = _LAZY_IMPORTS[name]
+        import importlib
+        module = importlib.import_module(module_path)
+        value = getattr(module, attr_name)
+        _cache[name] = value
+        return value
+    
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+def __dir__():
+    """List available attributes."""
+    return list(_LAZY_IMPORTS.keys())
+
+
+__all__ = list(_LAZY_IMPORTS.keys())
+
+if TYPE_CHECKING:
+    from .models import Citation, ContextPack, RAGResult, RAGConfig
+    from .protocols import ContextBuilderProtocol, CitationFormatterProtocol
+    from .pipeline import RAG
+    from .context import build_context, truncate_context, deduplicate_chunks

src/praisonai-agents/praisonaiagents/rag/context.py

@@ -0,0 +1,205 @@
+"""
+Context Building Utilities for RAG.
+
+Provides token-aware context assembly with deduplication.
+No heavy imports - only stdlib.
+"""
+
+import hashlib
+from typing import Any, Dict, List, Optional, Set, Tuple
+
+
+def _estimate_tokens(text: str) -> int:
+    """
+    Estimate token count for text.
+    
+    Uses simple heuristic: ~4 characters per token for English.
+    This avoids importing tokenizers for lightweight operation.
+    """
+    return len(text) // 4 + 1
+
+
+def _chunk_hash(text: str, source: Optional[str] = None) -> str:
+    """
+    Generate stable hash for chunk deduplication.
+    
+    Args:
+        text: Chunk text content
+        source: Optional source identifier
+        
+    Returns:
+        Hash string for deduplication
+    """
+    content = f"{source or ''}:{text}"
+    return hashlib.md5(content.encode()).hexdigest()[:16]
+
+
+def deduplicate_chunks(
+    results: List[Dict[str, Any]],
+    similarity_threshold: float = 0.9,
+) -> List[Dict[str, Any]]:
+    """
+    Deduplicate chunks by content hash.
+    
+    Args:
+        results: List of search results with 'text' or 'memory' key
+        similarity_threshold: Not used currently (hash-based dedup)
+        
+    Returns:
+        Deduplicated list of results
+    """
+    seen_hashes: Set[str] = set()
+    unique_results: List[Dict[str, Any]] = []
+    
+    for result in results:
+        # Skip None results
+        if result is None:
+            continue
+        # Handle different result formats
+        text = result.get("text") or result.get("memory", "")
+        source = result.get("metadata", {}).get("source", "")
+        
+        chunk_id = _chunk_hash(text, source)
+        
+        if chunk_id not in seen_hashes:
+            seen_hashes.add(chunk_id)
+            unique_results.append(result)
+    
+    return unique_results
+
+
+def truncate_context(
+    text: str,
+    max_tokens: int,
+    suffix: str = "\n\n[Context truncated...]",
+) -> str:
+    """
+    Truncate context to fit within token budget.
+    
+    Args:
+        text: Context text to truncate
+        max_tokens: Maximum tokens allowed
+        suffix: Suffix to add when truncated
+        
+    Returns:
+        Truncated text
+    """
+    estimated_tokens = _estimate_tokens(text)
+    
+    if estimated_tokens <= max_tokens:
+        return text
+    
+    # Calculate target character count
+    suffix_tokens = _estimate_tokens(suffix)
+    target_tokens = max_tokens - suffix_tokens
+    target_chars = target_tokens * 4
+    
+    # Truncate at word boundary
+    truncated = text[:target_chars]
+    last_space = truncated.rfind(" ")
+    if last_space > target_chars * 0.8:
+        truncated = truncated[:last_space]
+    
+    return truncated + suffix
+
+
+def build_context(
+    results: List[Dict[str, Any]],
+    max_tokens: int = 4000,
+    deduplicate: bool = True,
+    separator: str = "\n\n---\n\n",
+    include_source: bool = True,
+) -> Tuple[str, List[Dict[str, Any]]]:
+    """
+    Build context string from retrieval results.
+    
+    Args:
+        results: List of search results
+        max_tokens: Maximum tokens for context
+        deduplicate: Whether to deduplicate chunks
+        separator: Separator between chunks
+        include_source: Whether to include source info
+        
+    Returns:
+        Tuple of (context_string, used_results)
+    """
+    if not results:
+        return "", []
+    
+    # Deduplicate if requested
+    if deduplicate:
+        results = deduplicate_chunks(results)
+    
+    context_parts: List[str] = []
+    used_results: List[Dict[str, Any]] = []
+    current_tokens = 0
+    separator_tokens = _estimate_tokens(separator)
+    
+    for i, result in enumerate(results):
+        # Skip None results
+        if result is None:
+            continue
+        # Handle different result formats
+        text = result.get("text") or result.get("memory", "")
+        if not text:
+            continue
+        
+        # Build chunk text with optional source
+        if include_source:
+            source = result.get("metadata", {}).get("source", "")
+            filename = result.get("metadata", {}).get("filename", "")
+            source_label = filename or source or f"Source {i + 1}"
+            chunk_text = f"[{source_label}]\n{text}"
+        else:
+            chunk_text = text
+        
+        chunk_tokens = _estimate_tokens(chunk_text)
+        
+        # Check if we can fit this chunk
+        if current_tokens + chunk_tokens + separator_tokens > max_tokens:
+            # Try to fit partial chunk
+            remaining_tokens = max_tokens - current_tokens - separator_tokens
+            if remaining_tokens > 100:  # Only include if meaningful
+                truncated = truncate_context(chunk_text, remaining_tokens, "...")
+                context_parts.append(truncated)
+                used_results.append(result)
+            break
+        
+        context_parts.append(chunk_text)
+        used_results.append(result)
+        current_tokens += chunk_tokens + separator_tokens
+    
+    context = separator.join(context_parts)
+    return context, used_results
+
+
+class DefaultContextBuilder:
+    """
+    Default implementation of ContextBuilderProtocol.
+    
+    Provides token-aware context assembly with deduplication.
+    """
+    
+    def __init__(
+        self,
+        separator: str = "\n\n---\n\n",
+        include_source: bool = True,
+    ):
+        self.separator = separator
+        self.include_source = include_source
+    
+    def build(
+        self,
+        results: List[Dict[str, Any]],
+        max_tokens: int = 4000,
+        deduplicate: bool = True,
+    ) -> str:
+        """Build context string from results."""
+        context, _ = build_context(
+            results=results,
+            max_tokens=max_tokens,
+            deduplicate=deduplicate,
+            separator=self.separator,
+            include_source=self.include_source,
+        )
+        return context

src/praisonai-agents/praisonaiagents/rag/models.py

@@ -0,0 +1,256 @@
+"""
+RAG Data Models for PraisonAI Agents.
+
+Lightweight dataclasses for RAG results and configuration.
+No heavy imports - only stdlib and typing.
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+from enum import Enum
+
+
+class RetrievalStrategy(str, Enum):
+    """Available retrieval strategies for RAG."""
+    BASIC = "basic"
+    FUSION = "fusion"
+    HYBRID = "hybrid"
+
+
+@dataclass
+class Citation:
+    """
+    Source citation for RAG answers.
+    
+    Attributes:
+        id: Unique citation identifier (e.g., "[1]", "[2]")
+        source: Source document path or URL
+        text: Text snippet from the source
+        score: Relevance score (0-1)
+        doc_id: Optional document identifier
+        chunk_id: Optional chunk identifier within document
+        offset: Optional character offset in source
+        metadata: Additional metadata
+    """
+    id: str
+    source: str
+    text: str
+    score: float = 0.0
+    doc_id: Optional[str] = None
+    chunk_id: Optional[str] = None
+    offset: Optional[int] = None
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "id": self.id,
+            "source": self.source,
+            "text": self.text,
+            "score": self.score,
+            "doc_id": self.doc_id,
+            "chunk_id": self.chunk_id,
+            "offset": self.offset,
+            "metadata": self.metadata,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "Citation":
+        """Create from dictionary."""
+        return cls(
+            id=data.get("id", ""),
+            source=data.get("source", ""),
+            text=data.get("text", ""),
+            score=data.get("score", 0.0),
+            doc_id=data.get("doc_id"),
+            chunk_id=data.get("chunk_id"),
+            offset=data.get("offset"),
+            metadata=data.get("metadata", {}),
+        )
+    
+    def __str__(self) -> str:
+        """Human-readable string representation."""
+        snippet = self.text[:100] + "..." if len(self.text) > 100 else self.text
+        return f"[{self.id}] {self.source}: {snippet}"
+
+
+@dataclass
+class ContextPack:
+    """
+    Context pack for orchestrator pattern - retrieval without generation.
+    
+    Provides deterministic context that can be passed to Agent.chat_with_context().
+    
+    Attributes:
+        context: The formatted context string ready for injection
+        citations: List of source citations
+        query: The original query
+        metadata: Additional metadata (timing, retrieval stats, etc.)
+    """
+    context: str
+    citations: List[Citation] = field(default_factory=list)
+    query: str = ""
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "context": self.context,
+            "citations": [c.to_dict() for c in self.citations],
+            "query": self.query,
+            "metadata": self.metadata,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "ContextPack":
+        """Create from dictionary."""
+        return cls(
+            context=data.get("context", ""),
+            citations=[Citation.from_dict(c) for c in data.get("citations", [])],
+            query=data.get("query", ""),
+            metadata=data.get("metadata", {}),
+        )
+    
+    @property
+    def has_citations(self) -> bool:
+        """Check if context pack has citations."""
+        return len(self.citations) > 0
+    
+    def format_for_prompt(self, include_sources: bool = True) -> str:
+        """Format context for injection into a prompt."""
+        if not include_sources or not self.citations:
+            return self.context
+        
+        sources = "\n\nSources:\n"
+        for citation in self.citations:
+            sources += f"  [{citation.id}] {citation.source}\n"
+        return self.context + sources
+
+
+@dataclass
+class RAGResult:
+    """
+    Result from a RAG query.
+    
+    Attributes:
+        answer: The generated answer text
+        citations: List of source citations
+        context_used: The context string passed to the LLM
+        query: The original query
+        metadata: Additional metadata (timing, model info, etc.)
+    """
+    answer: str
+    citations: List[Citation] = field(default_factory=list)
+    context_used: str = ""
+    query: str = ""
+    metadata: Dict[str, Any] = field(default_factory=dict)
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "answer": self.answer,
+            "citations": [c.to_dict() for c in self.citations],
+            "context_used": self.context_used,
+            "query": self.query,
+            "metadata": self.metadata,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RAGResult":
+        """Create from dictionary."""
+        return cls(
+            answer=data.get("answer", ""),
+            citations=[Citation.from_dict(c) for c in data.get("citations", [])],
+            context_used=data.get("context_used", ""),
+            query=data.get("query", ""),
+            metadata=data.get("metadata", {}),
+        )
+    
+    @property
+    def has_citations(self) -> bool:
+        """Check if result has citations."""
+        return len(self.citations) > 0
+    
+    def format_answer_with_citations(self) -> str:
+        """Format answer with inline citation references."""
+        if not self.citations:
+            return self.answer
+        
+        # Build citation reference section
+        refs = "\n\nSources:\n"
+        for citation in self.citations:
+            refs += f"  {citation}\n"
+        
+        return self.answer + refs
+
+
+@dataclass
+class RAGConfig:
+    """
+    Configuration for RAG pipeline.
+    
+    Attributes:
+        top_k: Number of chunks to retrieve
+        min_score: Minimum relevance score threshold
+        max_context_tokens: Maximum tokens for context
+        include_citations: Whether to include citations in result
+        retrieval_strategy: Strategy for retrieval (basic, fusion, hybrid)
+        rerank: Whether to rerank results
+        rerank_top_k: Number of results after reranking
+        template: Prompt template with {context} and {question} placeholders
+        system_prompt: Optional system prompt for LLM
+        stream: Whether to stream responses
+    """
+    top_k: int = 5
+    min_score: float = 0.0
+    max_context_tokens: int = 4000
+    include_citations: bool = True
+    retrieval_strategy: RetrievalStrategy = RetrievalStrategy.BASIC
+    rerank: bool = False
+    rerank_top_k: int = 3
+    model: Optional[str] = None  # LLM model to use, defaults to gpt-4o-mini
+    template: str = """Answer the question based on the context below.
+
+Context:
+{context}
+
+Question: {question}
+
+Answer:"""
+    system_prompt: Optional[str] = None
+    stream: bool = False
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "top_k": self.top_k,
+            "min_score": self.min_score,
+            "max_context_tokens": self.max_context_tokens,
+            "include_citations": self.include_citations,
+            "retrieval_strategy": self.retrieval_strategy.value,
+            "rerank": self.rerank,
+            "rerank_top_k": self.rerank_top_k,
+            "template": self.template,
+            "system_prompt": self.system_prompt,
+            "stream": self.stream,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RAGConfig":
+        """Create from dictionary."""
+        strategy = data.get("retrieval_strategy", "basic")
+        if isinstance(strategy, str):
+            strategy = RetrievalStrategy(strategy)
+        
+        return cls(
+            top_k=data.get("top_k", 5),
+            min_score=data.get("min_score", 0.0),
+            max_context_tokens=data.get("max_context_tokens", 4000),
+            include_citations=data.get("include_citations", True),
+            retrieval_strategy=strategy,
+            rerank=data.get("rerank", False),
+            rerank_top_k=data.get("rerank_top_k", 3),
+            template=data.get("template", cls.template),
+            system_prompt=data.get("system_prompt"),
+            stream=data.get("stream", False),
+        )

src/praisonai-agents/praisonaiagents/rag/pipeline.py

@@ -0,0 +1,652 @@
+"""
+RAG Pipeline for PraisonAI Agents.
+
+Thin orchestrator that uses Knowledge for retrieval and LLM for generation.
+Provides citations, streaming, and async support.
+"""
+
+import logging
+import time
+from typing import Any, AsyncIterator, Dict, Iterator, List, Optional
+
+from .models import Citation, ContextPack, RAGConfig, RAGResult
+from .context import build_context, DefaultContextBuilder
+
+logger = logging.getLogger(__name__)
+
+
+class DefaultCitationFormatter:
+    """
+    Default implementation of CitationFormatterProtocol.
+    
+    Creates Citation objects from search results with stable IDs.
+    """
+    
+    def format(
+        self,
+        results: List[Dict[str, Any]],
+        start_id: int = 1,
+    ) -> List[Citation]:
+        """Format retrieval results as citations."""
+        citations = []
+        
+        for i, result in enumerate(results):
+            # Handle different result formats
+            text = result.get("text") or result.get("memory", "")
+            metadata = result.get("metadata", {})
+            score = result.get("score", 0.0)
+            
+            # Extract source info
+            source = metadata.get("source", "")
+            filename = metadata.get("filename", "")
+            doc_id = result.get("id") or metadata.get("doc_id", "")
+            chunk_id = metadata.get("chunk_id", "")
+            
+            citation = Citation(
+                id=str(start_id + i),
+                source=filename or source or f"Source {start_id + i}",
+                text=text[:500] if text else "",  # Limit snippet length
+                score=float(score) if score else 0.0,
+                doc_id=str(doc_id) if doc_id else None,
+                chunk_id=str(chunk_id) if chunk_id else None,
+                metadata=metadata,
+            )
+            citations.append(citation)
+        
+        return citations
+
+
+class RAG:
+    """
+    Retrieval Augmented Generation Pipeline.
+    
+    Thin orchestrator that:
+    1. Retrieves relevant context from Knowledge
+    2. Optionally reranks results
+    3. Builds context with token-aware truncation
+    4. Generates answer using LLM
+    5. Returns answer with citations
+    
+    Usage:
+        from praisonaiagents.rag import RAG
+        from praisonaiagents.knowledge import Knowledge
+        
+        knowledge = Knowledge(config={...})
+        knowledge.add("document.pdf")
+        
+        rag = RAG(knowledge=knowledge)
+        result = rag.query("What is the main finding?")
+        print(result.answer)
+        for citation in result.citations:
+            print(f"  [{citation.id}] {citation.source}")
+    """
+    
+    def __init__(
+        self,
+        knowledge: Any,
+        llm: Optional[Any] = None,
+        config: Optional[RAGConfig] = None,
+        reranker: Optional[Any] = None,
+        context_builder: Optional[Any] = None,
+        citation_formatter: Optional[Any] = None,
+    ):
+        """
+        Initialize RAG pipeline.
+        
+        Args:
+            knowledge: Knowledge instance for retrieval
+            llm: Optional LLM instance (uses default if not provided)
+            config: RAG configuration
+            reranker: Optional reranker for result refinement
+            context_builder: Optional custom context builder
+            citation_formatter: Optional custom citation formatter
+        """
+        self.knowledge = knowledge
+        self._llm = llm
+        self.config = config or RAGConfig()
+        self.reranker = reranker
+        self.context_builder = context_builder or DefaultContextBuilder()
+        self.citation_formatter = citation_formatter or DefaultCitationFormatter()
+        
+        # Lazy LLM initialization
+        self._llm_initialized = False
+    
+    @property
+    def llm(self):
+        """Lazy load LLM if not provided."""
+        if self._llm is not None:
+            return self._llm
+        
+        if not self._llm_initialized:
+            try:
+                from praisonaiagents.llm import LLM
+                # Use default model from config or fallback to gpt-4o-mini
+                model = self.config.model if self.config.model else "gpt-4o-mini"
+                self._llm = LLM(model=model)
+                self._llm_initialized = True
+            except ImportError:
+                logger.warning("LLM not available, using simple completion")
+                self._llm = None
+                self._llm_initialized = True
+        
+        return self._llm
+    
+    def _retrieve(
+        self,
+        query: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> List[Dict[str, Any]]:
+        """
+        Retrieve relevant chunks from Knowledge.
+        
+        Args:
+            query: Search query
+            user_id: Optional user ID for scoping
+            agent_id: Optional agent ID for scoping
+            run_id: Optional run ID for scoping
+            
+        Returns:
+            List of search results
+        """
+        # Use Knowledge's search method
+        results = self.knowledge.search(
+            query=query,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            **kwargs,
+        )
+        
+        # Handle different result formats
+        if isinstance(results, dict):
+            results = results.get("results", [])
+        
+        # Filter by minimum score
+        if self.config.min_score > 0:
+            results = [
+                r for r in results
+                if r.get("score", 0) >= self.config.min_score
+            ]
+        
+        # Limit to top_k
+        results = results[:self.config.top_k]
+        
+        return results
+    
+    def _rerank(
+        self,
+        query: str,
+        results: List[Dict[str, Any]],
+    ) -> List[Dict[str, Any]]:
+        """
+        Rerank results if reranker is configured.
+        
+        Args:
+            query: Original query
+            results: Results to rerank
+            
+        Returns:
+            Reranked results
+        """
+        if not self.config.rerank or not self.reranker:
+            return results
+        
+        try:
+            reranked = self.reranker.rerank(
+                query=query,
+                results=results,
+                top_k=self.config.rerank_top_k,
+            )
+            return reranked
+        except Exception as e:
+            logger.warning(f"Reranking failed: {e}, using original order")
+            return results
+    
+    def _build_context(
+        self,
+        results: List[Dict[str, Any]],
+    ) -> tuple:
+        """
+        Build context from results.
+        
+        Returns:
+            Tuple of (context_string, used_results)
+        """
+        return build_context(
+            results=results,
+            max_tokens=self.config.max_context_tokens,
+            deduplicate=True,
+        )
+    
+    def _format_citations(
+        self,
+        results: List[Dict[str, Any]],
+    ) -> List[Citation]:
+        """Format results as citations."""
+        if not self.config.include_citations:
+            return []
+        
+        return self.citation_formatter.format(results)
+    
+    def _generate(
+        self,
+        prompt: str,
+        system_prompt: Optional[str] = None,
+        **kwargs,
+    ) -> str:
+        """
+        Generate answer using LLM.
+        
+        Args:
+            prompt: Full prompt with context
+            system_prompt: Optional system prompt
+            
+        Returns:
+            Generated answer
+        """
+        if self.llm is None:
+            return "LLM not available. Please configure an LLM."
+        
+        try:
+            # Try different LLM interfaces
+            if hasattr(self.llm, 'get_response'):
+                # PraisonAI LLM interface - prompt can be string or messages list
+                if system_prompt:
+                    response = self.llm.get_response(
+                        prompt=prompt,
+                        system_prompt=system_prompt,
+                        verbose=False,
+                        stream=False,
+                        **kwargs
+                    )
+                else:
+                    response = self.llm.get_response(
+                        prompt=prompt,
+                        verbose=False,
+                        stream=False,
+                        **kwargs
+                    )
+                return response if isinstance(response, str) else str(response)
+            elif hasattr(self.llm, 'chat'):
+                messages = []
+                if system_prompt:
+                    messages.append({"role": "system", "content": system_prompt})
+                messages.append({"role": "user", "content": prompt})
+                response = self.llm.chat(messages=messages, **kwargs)
+                return response if isinstance(response, str) else str(response)
+            elif hasattr(self.llm, 'generate'):
+                return self.llm.generate(prompt, **kwargs)
+            elif callable(self.llm):
+                return self.llm(prompt, **kwargs)
+            else:
+                return str(self.llm)
+        except Exception as e:
+            logger.error(f"LLM generation failed: {e}")
+            return f"Error generating response: {e}"
+    
+    def _build_prompt(
+        self,
+        question: str,
+        context: str,
+    ) -> str:
+        """Build prompt from template."""
+        return self.config.template.format(
+            question=question,
+            context=context,
+        )
+    
+    def retrieve(
+        self,
+        query: str,
+        *,
+        top_k: Optional[int] = None,
+        hybrid: Optional[bool] = None,
+        rerank: Optional[bool] = None,
+        filters: Optional[Dict[str, Any]] = None,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> ContextPack:
+        """
+        Retrieve context without LLM generation (Orchestrator pattern).
+        
+        Returns a ContextPack that can be passed to Agent.chat_with_context().
+        This enables conditional retrieval - only retrieve when needed.
+        
+        Args:
+            query: Search query
+            top_k: Override config top_k
+            hybrid: Override config hybrid retrieval
+            rerank: Override config rerank
+            filters: Optional metadata filters
+            user_id: Optional user ID for scoping
+            agent_id: Optional agent ID for scoping
+            run_id: Optional run ID for scoping
+            
+        Returns:
+            ContextPack with context string and citations (no LLM call)
+        """
+        start_time = time.time()
+        
+        # Apply overrides
+        original_top_k = self.config.top_k
+        original_rerank = self.config.rerank
+        
+        if top_k is not None:
+            self.config.top_k = top_k
+        if rerank is not None:
+            self.config.rerank = rerank
+        
+        try:
+            # 1. Retrieve
+            results = self._retrieve(
+                query=query,
+                user_id=user_id,
+                agent_id=agent_id,
+                run_id=run_id,
+                filters=filters,
+                **kwargs,
+            )
+            
+            # 2. Rerank (optional)
+            results = self._rerank(query, results)
+            
+            # 3. Build context
+            context, used_results = self._build_context(results)
+            
+            # 4. Format citations
+            citations = self._format_citations(used_results)
+            
+            elapsed = time.time() - start_time
+            
+            return ContextPack(
+                context=context,
+                citations=citations,
+                query=query,
+                metadata={
+                    "elapsed_seconds": elapsed,
+                    "num_results": len(results),
+                    "num_citations": len(citations),
+                    "retrieval_strategy": self.config.retrieval_strategy.value,
+                    "reranked": self.config.rerank,
+                    "top_k": self.config.top_k,
+                },
+            )
+        finally:
+            # Restore original config
+            self.config.top_k = original_top_k
+            self.config.rerank = original_rerank
+    
+    async def aretrieve(
+        self,
+        query: str,
+        *,
+        top_k: Optional[int] = None,
+        hybrid: Optional[bool] = None,
+        rerank: Optional[bool] = None,
+        filters: Optional[Dict[str, Any]] = None,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> ContextPack:
+        """
+        Async version of retrieve.
+        
+        Currently wraps sync version. Can be extended for true async.
+        """
+        import asyncio
+        loop = asyncio.get_event_loop()
+        return await loop.run_in_executor(
+            None,
+            lambda: self.retrieve(
+                query=query,
+                top_k=top_k,
+                hybrid=hybrid,
+                rerank=rerank,
+                filters=filters,
+                user_id=user_id,
+                agent_id=agent_id,
+                run_id=run_id,
+                **kwargs,
+            ),
+        )
+    
+    def query(
+        self,
+        question: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> RAGResult:
+        """
+        Execute RAG query.
+        
+        Args:
+            question: User's question
+            user_id: Optional user ID for scoping
+            agent_id: Optional agent ID for scoping
+            run_id: Optional run ID for scoping
+            
+        Returns:
+            RAGResult with answer and citations
+        """
+        start_time = time.time()
+        
+        # 1. Retrieve
+        results = self._retrieve(
+            query=question,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            **kwargs,
+        )
+        
+        # 2. Rerank (optional)
+        results = self._rerank(question, results)
+        
+        # 3. Build context
+        context, used_results = self._build_context(results)
+        
+        # 4. Generate answer
+        prompt = self._build_prompt(question, context)
+        answer = self._generate(
+            prompt=prompt,
+            system_prompt=self.config.system_prompt,
+        )
+        
+        # 5. Format citations
+        citations = self._format_citations(used_results)
+        
+        # Build result
+        elapsed = time.time() - start_time
+        
+        return RAGResult(
+            answer=answer,
+            citations=citations,
+            context_used=context,
+            query=question,
+            metadata={
+                "elapsed_seconds": elapsed,
+                "num_results": len(results),
+                "num_citations": len(citations),
+                "retrieval_strategy": self.config.retrieval_strategy.value,
+                "reranked": self.config.rerank,
+            },
+        )
+    
+    async def aquery(
+        self,
+        question: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> RAGResult:
+        """
+        Async version of query.
+        
+        Currently wraps sync version. Can be extended for true async.
+        """
+        # For now, wrap sync version
+        # TODO: Implement true async when Knowledge supports it
+        import asyncio
+        loop = asyncio.get_event_loop()
+        return await loop.run_in_executor(
+            None,
+            lambda: self.query(
+                question=question,
+                user_id=user_id,
+                agent_id=agent_id,
+                run_id=run_id,
+                **kwargs,
+            ),
+        )
+    
+    def stream(
+        self,
+        question: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> Iterator[str]:
+        """
+        Stream RAG response.
+        
+        Yields tokens as they are generated.
+        Final yield includes citation metadata.
+        
+        Args:
+            question: User's question
+            user_id: Optional user ID
+            agent_id: Optional agent ID
+            run_id: Optional run ID
+            
+        Yields:
+            Response tokens
+        """
+        # 1. Retrieve
+        results = self._retrieve(
+            query=question,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            **kwargs,
+        )
+        
+        # 2. Rerank
+        results = self._rerank(question, results)
+        
+        # 3. Build context
+        context, used_results = self._build_context(results)
+        
+        # 4. Build prompt
+        prompt = self._build_prompt(question, context)
+        
+        # 5. Stream generation
+        if self.llm is None:
+            yield "LLM not available."
+            return
+        
+        try:
+            # Try streaming interface
+            if hasattr(self.llm, 'stream'):
+                messages = []
+                if self.config.system_prompt:
+                    messages.append({"role": "system", "content": self.config.system_prompt})
+                messages.append({"role": "user", "content": prompt})
+                
+                for chunk in self.llm.stream(messages=messages, **kwargs):
+                    yield chunk
+            else:
+                # Fallback to non-streaming
+                answer = self._generate(prompt, self.config.system_prompt)
+                # Simulate streaming by yielding words
+                for word in answer.split():
+                    yield word + " "
+        except Exception as e:
+            logger.error(f"Streaming failed: {e}")
+            yield f"Error: {e}"
+    
+    async def astream(
+        self,
+        question: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> AsyncIterator[str]:
+        """
+        Async streaming RAG response.
+        
+        Yields tokens as they are generated.
+        """
+        # 1. Retrieve
+        results = self._retrieve(
+            query=question,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            **kwargs,
+        )
+        
+        # 2. Rerank
+        results = self._rerank(question, results)
+        
+        # 3. Build context
+        context, used_results = self._build_context(results)
+        
+        # 4. Build prompt
+        prompt = self._build_prompt(question, context)
+        
+        # 5. Stream generation
+        if self.llm is None:
+            yield "LLM not available."
+            return
+        
+        try:
+            # Try async streaming interface
+            if hasattr(self.llm, 'astream'):
+                messages = []
+                if self.config.system_prompt:
+                    messages.append({"role": "system", "content": self.config.system_prompt})
+                messages.append({"role": "user", "content": prompt})
+                
+                async for chunk in self.llm.astream(messages=messages, **kwargs):
+                    yield chunk
+            else:
+                # Fallback to sync streaming wrapped
+                for chunk in self.stream(question, user_id, agent_id, run_id, **kwargs):
+                    yield chunk
+        except Exception as e:
+            logger.error(f"Async streaming failed: {e}")
+            yield f"Error: {e}"
+    
+    def get_citations(
+        self,
+        question: str,
+        user_id: Optional[str] = None,
+        agent_id: Optional[str] = None,
+        run_id: Optional[str] = None,
+        **kwargs,
+    ) -> List[Citation]:
+        """
+        Get citations without generating answer.
+        
+        Useful for retrieval-only workflows.
+        """
+        results = self._retrieve(
+            query=question,
+            user_id=user_id,
+            agent_id=agent_id,
+            run_id=run_id,
+            **kwargs,
+        )
+        results = self._rerank(question, results)
+        return self._format_citations(results)

src/praisonai-agents/praisonaiagents/rag/protocols.py

@@ -0,0 +1,147 @@
+"""
+RAG Protocols for PraisonAI Agents.
+
+Defines minimal protocol interfaces for RAG components.
+No heavy imports - only stdlib and typing.
+"""
+
+from typing import Any, Dict, Iterator, List, Optional, Protocol, runtime_checkable
+
+from .models import Citation, RAGResult
+
+
+@runtime_checkable
+class ContextBuilderProtocol(Protocol):
+    """
+    Protocol for building context from retrieval results.
+    
+    Implementations must provide a build method that assembles
+    context from search results with token-aware truncation.
+    """
+    
+    def build(
+        self,
+        results: List[Dict[str, Any]],
+        max_tokens: int = 4000,
+        deduplicate: bool = True,
+    ) -> str:
+        """
+        Build context string from retrieval results.
+        
+        Args:
+            results: List of search results with 'text' and 'metadata' keys
+            max_tokens: Maximum tokens for context
+            deduplicate: Whether to deduplicate similar chunks
+            
+        Returns:
+            Assembled context string
+        """
+        ...
+
+
+@runtime_checkable
+class CitationFormatterProtocol(Protocol):
+    """
+    Protocol for formatting citations from retrieval results.
+    
+    Implementations must provide a format method that creates
+    Citation objects from search results.
+    """
+    
+    def format(
+        self,
+        results: List[Dict[str, Any]],
+        start_id: int = 1,
+    ) -> List[Citation]:
+        """
+        Format retrieval results as citations.
+        
+        Args:
+            results: List of search results
+            start_id: Starting citation ID number
+            
+        Returns:
+            List of Citation objects
+        """
+        ...
+
+
+@runtime_checkable
+class RerankerProtocol(Protocol):
+    """
+    Protocol for reranking retrieval results.
+    
+    Implementations must provide a rerank method that reorders
+    results by relevance to the query.
+    """
+    
+    name: str
+    
+    def rerank(
+        self,
+        query: str,
+        results: List[Dict[str, Any]],
+        top_k: Optional[int] = None,
+    ) -> List[Dict[str, Any]]:
+        """
+        Rerank results by relevance to query.
+        
+        Args:
+            query: The search query
+            results: List of results to rerank
+            top_k: Optional limit on results
+            
+        Returns:
+            Reranked list of results
+        """
+        ...
+
+
+@runtime_checkable
+class RAGProtocol(Protocol):
+    """
+    Protocol for RAG pipelines.
+    
+    Implementations must provide query, stream, and async variants.
+    """
+    
+    def query(self, question: str, **kwargs) -> RAGResult:
+        """Execute RAG query and return result with citations."""
+        ...
+    
+    async def aquery(self, question: str, **kwargs) -> RAGResult:
+        """Async version of query."""
+        ...
+    
+    def stream(self, question: str, **kwargs) -> Iterator[str]:
+        """Stream RAG response tokens."""
+        ...
+
+
+@runtime_checkable
+class GraphHookProtocol(Protocol):
+    """
+    Protocol for graph-based retrieval hooks (optional).
+    
+    Implementations can provide graph traversal for enhanced retrieval.
+    This is an optional extension point for GraphRAG tools.
+    """
+    
+    def get_related_nodes(
+        self,
+        query: str,
+        node_ids: List[str],
+        max_hops: int = 2,
+    ) -> List[Dict[str, Any]]:
+        """
+        Get related nodes from graph for context expansion.
+        
+        Args:
+            query: The search query
+            node_ids: Starting node IDs
+            max_hops: Maximum graph traversal hops
+            
+        Returns:
+            List of related nodes with metadata
+        """
+        ...

src/praisonai-agents/praisonaiagents/rag/retrieval_config.py

@@ -0,0 +1,316 @@
+"""
+RetrievalConfig - Unified configuration for Agent retrieval behavior.
+
+This is the SINGLE configuration surface for all retrieval settings.
+Replaces separate knowledge_config and rag_config parameters.
+"""
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, Optional
+from enum import Enum
+
+
+class RetrievalPolicy(str, Enum):
+    """Policy for when to perform retrieval."""
+    AUTO = "auto"      # Decide based on query heuristics
+    ALWAYS = "always"  # Always retrieve
+    NEVER = "never"    # Never retrieve (direct chat only)
+
+
+class CitationsMode(str, Enum):
+    """How to include citations in responses."""
+    APPEND = "append"    # Append sources at end
+    INLINE = "inline"    # Inline citation markers
+    HIDDEN = "hidden"    # Include in metadata only, not in response text
+
+
+@dataclass
+class RetrievalConfig:
+    """
+    Unified configuration for Agent retrieval behavior.
+    
+    This is the SINGLE configuration surface that replaces:
+    - knowledge_config
+    - rag_config
+    
+    Attributes:
+        enabled: Whether retrieval is enabled (default: True if knowledge provided)
+        policy: When to retrieve (auto, always, never)
+        top_k: Number of chunks to retrieve
+        min_score: Minimum relevance score threshold (0.0-1.0)
+        max_context_tokens: Maximum tokens for retrieved context
+        rerank: Whether to rerank results for better relevance
+        hybrid: Whether to use hybrid retrieval (dense + keyword)
+        citations: Whether to include source citations
+        citations_mode: How to include citations (append, inline, hidden)
+        
+        # Vector store configuration
+        vector_store_provider: Vector store provider (chroma, mongodb, etc.)
+        vector_store_config: Provider-specific configuration
+        collection_name: Collection/index name
+        persist_path: Path for persistent storage
+        
+        # Embedding configuration
+        embedder_provider: Embedding provider
+        embedder_model: Embedding model name
+        
+        # Advanced options
+        auto_keywords: Keywords that trigger retrieval in auto mode
+        auto_min_length: Minimum query length for auto retrieval
+        context_template: Template for formatting retrieved context
+        system_separation: Whether to use system prompt separation for safety
+    """
+    # Core retrieval settings
+    enabled: bool = True
+    policy: RetrievalPolicy = RetrievalPolicy.AUTO
+    top_k: int = 5
+    min_score: float = 0.0
+    max_context_tokens: int = 4000
+    rerank: bool = False
+    hybrid: bool = False
+    citations: bool = True
+    citations_mode: CitationsMode = CitationsMode.APPEND
+    
+    # Vector store configuration
+    vector_store_provider: str = "chroma"
+    vector_store_config: Dict[str, Any] = field(default_factory=dict)
+    collection_name: Optional[str] = None
+    persist_path: str = ".praison"
+    
+    # Embedding configuration
+    embedder_provider: Optional[str] = None
+    embedder_model: Optional[str] = None
+    
+    # Auto mode heuristics
+    auto_keywords: frozenset = field(default_factory=lambda: frozenset({
+        "what", "how", "why", "when", "where", "who", "which",
+        "explain", "describe", "summarize", "find", "search",
+        "tell me", "show me", "according to", "based on",
+        "cite", "source", "reference", "document", "paper",
+    }))
+    auto_min_length: int = 10
+    
+    # Context formatting
+    context_template: str = """<retrieved_context>
+{context}
+</retrieved_context>"""
+    system_separation: bool = True  # Use system prompt separation for safety
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        return {
+            "enabled": self.enabled,
+            "policy": self.policy.value if isinstance(self.policy, RetrievalPolicy) else self.policy,
+            "top_k": self.top_k,
+            "min_score": self.min_score,
+            "max_context_tokens": self.max_context_tokens,
+            "rerank": self.rerank,
+            "hybrid": self.hybrid,
+            "citations": self.citations,
+            "citations_mode": self.citations_mode.value if isinstance(self.citations_mode, CitationsMode) else self.citations_mode,
+            "vector_store_provider": self.vector_store_provider,
+            "vector_store_config": self.vector_store_config,
+            "collection_name": self.collection_name,
+            "persist_path": self.persist_path,
+            "embedder_provider": self.embedder_provider,
+            "embedder_model": self.embedder_model,
+            "auto_min_length": self.auto_min_length,
+            "context_template": self.context_template,
+            "system_separation": self.system_separation,
+        }
+    
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "RetrievalConfig":
+        """Create from dictionary."""
+        policy = data.get("policy", "auto")
+        if isinstance(policy, str):
+            policy = RetrievalPolicy(policy)
+        
+        citations_mode = data.get("citations_mode", "append")
+        if isinstance(citations_mode, str):
+            citations_mode = CitationsMode(citations_mode)
+        
+        auto_keywords = data.get("auto_keywords")
+        if auto_keywords is not None:
+            if isinstance(auto_keywords, (list, set)):
+                auto_keywords = frozenset(auto_keywords)
+        else:
+            auto_keywords = cls.__dataclass_fields__["auto_keywords"].default_factory()
+        
+        return cls(
+            enabled=data.get("enabled", True),
+            policy=policy,
+            top_k=data.get("top_k", 5),
+            min_score=data.get("min_score", 0.0),
+            max_context_tokens=data.get("max_context_tokens", 4000),
+            rerank=data.get("rerank", False),
+            hybrid=data.get("hybrid", False),
+            citations=data.get("citations", True),
+            citations_mode=citations_mode,
+            vector_store_provider=data.get("vector_store_provider", "chroma"),
+            vector_store_config=data.get("vector_store_config", {}),
+            collection_name=data.get("collection_name"),
+            persist_path=data.get("persist_path", ".praison"),
+            embedder_provider=data.get("embedder_provider"),
+            embedder_model=data.get("embedder_model"),
+            auto_keywords=auto_keywords,
+            auto_min_length=data.get("auto_min_length", 10),
+            context_template=data.get("context_template", cls.__dataclass_fields__["context_template"].default),
+            system_separation=data.get("system_separation", True),
+        )
+    
+    def to_knowledge_config(self) -> Dict[str, Any]:
+        """Convert to Knowledge-compatible config."""
+        config = {
+            "vector_store": {
+                "provider": self.vector_store_provider,
+                "config": {
+                    "path": self.persist_path,
+                    **self.vector_store_config,
+                }
+            }
+        }
+        if self.collection_name:
+            config["vector_store"]["config"]["collection_name"] = self.collection_name
+        
+        if self.embedder_provider or self.embedder_model:
+            config["embedder"] = {}
+            if self.embedder_provider:
+                config["embedder"]["provider"] = self.embedder_provider
+            if self.embedder_model:
+                config["embedder"]["config"] = {"model": self.embedder_model}
+        
+        if self.rerank:
+            config["reranker"] = {"enabled": True, "default_rerank": True}
+        
+        return config
+    
+    def to_rag_config(self) -> Dict[str, Any]:
+        """Convert to RAG pipeline config."""
+        from .models import RetrievalStrategy
+        
+        strategy = RetrievalStrategy.HYBRID if self.hybrid else RetrievalStrategy.BASIC
+        
+        return {
+            "top_k": self.top_k,
+            "min_score": self.min_score,
+            "max_context_tokens": self.max_context_tokens,
+            "include_citations": self.citations,
+            "retrieval_strategy": strategy,
+            "rerank": self.rerank,
+        }
+    
+    def should_retrieve(self, query: str, force: bool = False, skip: bool = False) -> bool:
+        """
+        Determine if retrieval should be performed for a query.
+        
+        Args:
+            query: The user query
+            force: Force retrieval regardless of policy
+            skip: Skip retrieval regardless of policy
+            
+        Returns:
+            True if retrieval should be performed
+        """
+        if not self.enabled:
+            return False
+        if skip:
+            return False
+        if force:
+            return True
+        
+        if self.policy == RetrievalPolicy.ALWAYS:
+            return True
+        elif self.policy == RetrievalPolicy.NEVER:
+            return False
+        else:  # AUTO
+            return self._needs_retrieval(query)
+    
+    def _needs_retrieval(self, query: str) -> bool:
+        """Check if query needs retrieval based on heuristics."""
+        # Check minimum length
+        if len(query.strip()) < self.auto_min_length:
+            return False
+        
+        # Check for keywords
+        query_lower = query.lower()
+        for keyword in self.auto_keywords:
+            if keyword in query_lower:
+                return True
+        
+        # Check for question marks
+        if "?" in query:
+            return True
+        
+        return False
+
+
+# Convenience function to create config from legacy parameters
+def create_retrieval_config(
+    knowledge_config: Optional[Dict[str, Any]] = None,
+    rag_config: Optional[Dict[str, Any]] = None,
+    retrieval_config: Optional[Dict[str, Any]] = None,
+) -> Optional[RetrievalConfig]:
+    """
+    Create RetrievalConfig from various input formats.
+    
+    Supports:
+    - New unified retrieval_config dict
+    - Legacy knowledge_config + rag_config dicts
+    - RetrievalConfig instance passthrough
+    
+    Args:
+        knowledge_config: Legacy knowledge configuration
+        rag_config: Legacy RAG configuration
+        retrieval_config: New unified configuration
+        
+    Returns:
+        RetrievalConfig instance or None
+    """
+    if retrieval_config is not None:
+        if isinstance(retrieval_config, RetrievalConfig):
+            return retrieval_config
+        return RetrievalConfig.from_dict(retrieval_config)
+    
+    if knowledge_config is None and rag_config is None:
+        return None
+    
+    # Merge legacy configs
+    merged = {}
+    
+    if knowledge_config:
+        # Extract vector store settings
+        vs = knowledge_config.get("vector_store", {})
+        if vs:
+            merged["vector_store_provider"] = vs.get("provider", "chroma")
+            merged["vector_store_config"] = vs.get("config", {})
+            if "collection_name" in vs.get("config", {}):
+                merged["collection_name"] = vs["config"]["collection_name"]
+            if "path" in vs.get("config", {}):
+                merged["persist_path"] = vs["config"]["path"]
+        
+        # Extract embedder settings
+        emb = knowledge_config.get("embedder", {})
+        if emb:
+            merged["embedder_provider"] = emb.get("provider")
+            if "config" in emb and "model" in emb["config"]:
+                merged["embedder_model"] = emb["config"]["model"]
+    
+    if rag_config:
+        # Map RAG config fields
+        if "top_k" in rag_config:
+            merged["top_k"] = rag_config["top_k"]
+        if "min_score" in rag_config:
+            merged["min_score"] = rag_config["min_score"]
+        if "max_context_tokens" in rag_config:
+            merged["max_context_tokens"] = rag_config["max_context_tokens"]
+        if "include_citations" in rag_config:
+            merged["citations"] = rag_config["include_citations"]
+        if "rerank" in rag_config:
+            merged["rerank"] = rag_config["rerank"]
+        if "retrieval_strategy" in rag_config:
+            strategy = rag_config["retrieval_strategy"]
+            if strategy == "hybrid":
+                merged["hybrid"] = True
+    
+    return RetrievalConfig.from_dict(merged) if merged else RetrievalConfig()

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

@@ -39,6 +39,11 @@ def __getattr__(name: str):
     if name in _module_cache:
         return _module_cache[name]
     
+    if name == "Session":
+        from .api import Session
+        _module_cache[name] = Session
+        return Session
+    
     if name == "DefaultSessionStore":
         from .store import DefaultSessionStore
         _module_cache[name] = DefaultSessionStore
@@ -63,6 +68,7 @@ def __getattr__(name: str):
 
 
 __all__ = [
+    "Session",
     "DefaultSessionStore",
     "SessionMessage", 
     "SessionData",

src/praisonai-agents/praisonaiagents/session/api.py

@@ -0,0 +1,532 @@
+"""
+Session Management for PraisonAI Agents
+
+A simple wrapper around existing stateful capabilities to provide a unified
+session API for developers building stateful agent applications.
+
+This module uses deferred imports to ensure `requests` is NOT loaded at import time.
+"""
+from __future__ import annotations
+
+import os
+import uuid
+import json
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from ..memory.memory import Memory
+    from ..knowledge.knowledge import Knowledge
+    from ..agent import Agent
+
+
+def _get_requests():
+    """Deferred import of requests library."""
+    import requests
+    return requests
+
+
+class Session:
+    """
+    A simple wrapper around PraisonAI's existing stateful capabilities.
+    
+    Provides a unified API for:
+    - Session management with persistent state
+    - Memory operations (short-term, long-term, user-specific)
+    - Knowledge base operations
+    - Agent state management
+    - Remote agent connectivity
+    
+    Examples:
+        # Local session with agent
+        session = Session(session_id="chat_123", user_id="user_456")
+        agent = session.Agent(name="Assistant", role="Helpful AI")
+        
+        # Remote agent session (similar to Google ADK)
+        session = Session(agent_url="192.168.1.10:8000/agent")
+        response = session.chat("Hello from remote client!")
+        
+        # Save session state
+        session.save_state({"conversation_topic": "AI research"})
+    """
+
+    def __init__(
+        self, 
+        session_id: Optional[str] = None,
+        user_id: Optional[str] = None,
+        agent_url: Optional[str] = None,
+        memory_config: Optional[Dict[str, Any]] = None,
+        knowledge_config: Optional[Dict[str, Any]] = None,
+        timeout: int = 30
+    ):
+        """
+        Initialize a new session with optional persistence or remote agent connectivity.
+        
+        Args:
+            session_id: Unique session identifier. Auto-generated if None.
+            user_id: User identifier for user-specific memory operations.
+            agent_url: URL of remote agent for direct connectivity (e.g., "192.168.1.10:8000/agent")
+            memory_config: Configuration for memory system (defaults to RAG)
+            knowledge_config: Configuration for knowledge base system  
+            timeout: HTTP timeout for remote agent calls (default: 30 seconds)
+        """
+        self.session_id = session_id or str(uuid.uuid4())[:8]
+        self.user_id = user_id or "default_user"
+        self.agent_url = agent_url
+        self.timeout = timeout
+        self.is_remote = agent_url is not None
+
+        # Validate agent_url format
+        if self.is_remote:
+            if not self.agent_url.startswith(('http://', 'https://')):
+                self.agent_url = f"http://{self.agent_url}"
+            self._test_remote_connection()
+
+        # Initialize memory with sensible defaults (only for local sessions)
+        if not self.is_remote:
+            default_memory_config = {
+                "provider": "rag",
+                "use_embedding": False,
+                "rag_db_path": f".praison/sessions/{self.session_id}/chroma_db"
+            }
+            if memory_config:
+                default_memory_config.update(memory_config)
+            self.memory_config = default_memory_config
+
+            default_knowledge_config = knowledge_config or {}
+            self.knowledge_config = default_knowledge_config
+
+            os.makedirs(f".praison/sessions/{self.session_id}", exist_ok=True)
+
+            self._memory = None
+            self._knowledge = None
+            self._agents_instance = None
+            self._agents = {}
+        else:
+            self.memory_config = {}
+            self.knowledge_config = {}
+            self._memory = None
+            self._knowledge = None
+            self._agents_instance = None
+            self._agents = {}
+
+    @property
+    def memory(self) -> "Memory":
+        """Lazy-loaded memory instance"""
+        if self.is_remote:
+            raise ValueError("Memory operations are not available for remote agent sessions")
+        if self._memory is None:
+            from ..memory.memory import Memory
+            self._memory = Memory(config=self.memory_config)
+        return self._memory
+
+    @property
+    def knowledge(self) -> "Knowledge":
+        """Lazy-loaded knowledge instance"""
+        if self.is_remote:
+            raise ValueError("Knowledge operations are not available for remote agent sessions")
+        if self._knowledge is None:
+            from ..knowledge.knowledge import Knowledge
+            self._knowledge = Knowledge(config=self.knowledge_config)
+        return self._knowledge
+
+    def Agent(
+        self,
+        name: str,
+        role: str = "Assistant", 
+        instructions: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
+        memory: bool = True,
+        knowledge: Optional[List[str]] = None,
+        **kwargs
+    ) -> "Agent":
+        """
+        Create an agent with session context.
+        
+        Args:
+            name: Agent name
+            role: Agent role
+            instructions: Agent instructions
+            tools: List of tools for the agent
+            memory: Enable memory for the agent
+            knowledge: Knowledge sources for the agent
+            **kwargs: Additional agent parameters
+        
+        Returns:
+            Configured Agent instance
+            
+        Raises:
+            ValueError: If this is a remote session (use chat() instead)
+        """
+        if self.is_remote:
+            raise ValueError("Cannot create local agents in remote sessions. Use chat() to communicate with the remote agent.")
+
+        from ..agent import Agent as AgentClass
+
+        agent_kwargs = {
+            "name": name,
+            "role": role,
+            "user_id": self.user_id,
+            **kwargs
+        }
+
+        if instructions:
+            agent_kwargs["instructions"] = instructions
+        if tools:
+            agent_kwargs["tools"] = tools
+        if memory:
+            agent_kwargs["memory"] = self.memory
+        if knowledge:
+            agent_kwargs["knowledge"] = knowledge
+            agent_kwargs["knowledge_config"] = self.knowledge_config
+
+        agent = AgentClass(**agent_kwargs)
+        
+        agent_key = f"{name}:{role}"
+        
+        if agent_key in self._agents:
+            agent.chat_history = self._agents[agent_key].get("chat_history", [])
+        else:
+            restored_history = self._restore_agent_chat_history(agent_key)
+            agent.chat_history = restored_history
+        
+        self._agents[agent_key] = {"agent": agent, "chat_history": agent.chat_history}
+        
+        return agent
+
+    def create_agent(self, *args, **kwargs) -> "Agent":
+        """Backward compatibility wrapper for Agent method"""
+        return self.Agent(*args, **kwargs)
+
+    def save_state(self, state_data: Dict[str, Any]) -> None:
+        """
+        Save session state data to memory.
+        
+        Args:
+            state_data: Dictionary of state data to save
+            
+        Raises:
+            ValueError: If this is a remote session
+        """
+        if self.is_remote:
+            raise ValueError("State operations are not available for remote agent sessions")
+            
+        self._save_agent_chat_histories()
+        
+        state_text = f"Session state: {state_data}"
+        self.memory.store_short_term(
+            text=state_text,
+            metadata={
+                "type": "session_state",
+                "session_id": self.session_id,
+                "user_id": self.user_id,
+                **state_data
+            }
+        )
+
+    def restore_state(self) -> Dict[str, Any]:
+        """
+        Restore session state from memory.
+        
+        Returns:
+            Dictionary of restored state data
+            
+        Raises:
+            ValueError: If this is a remote session
+        """
+        if self.is_remote:
+            raise ValueError("State operations are not available for remote agent sessions")
+        results = self.memory.search_short_term(
+            query="Session state:",
+            limit=10
+        )
+
+        self._restore_agent_chat_histories()
+        
+        for result in results:
+            metadata = result.get("metadata", {})
+            if (metadata.get("type") == "session_state" and 
+                metadata.get("session_id") == self.session_id):
+                state_data = {k: v for k, v in metadata.items() 
+                             if k not in ["type", "session_id", "user_id"]}
+                return state_data
+
+        return {}
+
+    def _restore_agent_chat_history(self, agent_key: str) -> List[Dict[str, Any]]:
+        """
+        Restore agent chat history from memory.
+        
+        Args:
+            agent_key: Unique identifier for the agent
+            
+        Returns:
+            List of chat history messages or empty list if not found
+        """
+        if self.is_remote:
+            return []
+        
+        results = self.memory.search_short_term(
+            query="Agent chat history for",
+            limit=10
+        )
+        
+        for result in results:
+            metadata = result.get("metadata", {})
+            if (metadata.get("type") == "agent_chat_history" and 
+                metadata.get("session_id") == self.session_id and
+                metadata.get("agent_key") == agent_key):
+                chat_history = metadata.get("chat_history", [])
+                return chat_history
+        
+        return []
+
+    def _restore_agent_chat_histories(self) -> None:
+        """Restore all agent chat histories from memory."""
+        if self.is_remote:
+            return
+        
+        results = self.memory.search_short_term(
+            query="Agent chat history for",
+            limit=50
+        )
+        
+        for result in results:
+            metadata = result.get("metadata", {})
+            if (metadata.get("type") == "agent_chat_history" and 
+                metadata.get("session_id") == self.session_id):
+                agent_key = metadata.get("agent_key")
+                chat_history = metadata.get("chat_history", [])
+                
+                if agent_key and chat_history:
+                    self._agents[agent_key] = {
+                        "agent": None,
+                        "chat_history": chat_history
+                    }
+
+    def _save_agent_chat_histories(self) -> None:
+        """Save all agent chat histories to memory."""
+        if self.is_remote:
+            return
+        
+        for agent_key, agent_data in self._agents.items():
+            agent = agent_data.get("agent")
+            chat_history = None
+            
+            if agent and hasattr(agent, 'chat_history'):
+                chat_history = agent.chat_history
+                agent_data["chat_history"] = chat_history
+            else:
+                chat_history = agent_data.get("chat_history")
+            
+            if chat_history is not None:
+                history_text = f"Agent chat history for {agent_key}"
+                self.memory.store_short_term(
+                    text=history_text,
+                    metadata={
+                        "type": "agent_chat_history",
+                        "session_id": self.session_id,
+                        "user_id": self.user_id,
+                        "agent_key": agent_key,
+                        "chat_history": chat_history
+                    }
+                )
+
+    def get_state(self, key: str, default: Any = None) -> Any:
+        """Get a specific state value"""
+        state = self.restore_state()
+        return state.get(key, default)
+
+    def set_state(self, key: str, value: Any) -> None:
+        """Set a specific state value"""
+        current_state = self.restore_state()
+        current_state[key] = value
+        self.save_state(current_state)
+
+    def increment_state(self, key: str, increment: int = 1, default: int = 0) -> None:
+        """Increment a numeric state value"""
+        current_value = self.get_state(key, default)
+        self.set_state(key, current_value + increment)
+
+    def add_memory(self, text: str, memory_type: str = "long", **metadata) -> None:
+        """
+        Add information to session memory.
+        
+        Args:
+            text: Text to store
+            memory_type: "short" or "long" term memory
+            **metadata: Additional metadata
+        """
+        metadata.update({
+            "session_id": self.session_id,
+            "user_id": self.user_id
+        })
+
+        if memory_type == "short":
+            self.memory.store_short_term(text, metadata=metadata)
+        else:
+            self.memory.store_long_term(text, metadata=metadata)
+
+    def search_memory(self, query: str, memory_type: str = "long", limit: int = 5) -> List[Dict[str, Any]]:
+        """
+        Search session memory.
+        
+        Args:
+            query: Search query
+            memory_type: "short" or "long" term memory
+            limit: Maximum results to return
+
+        Returns:
+            List of memory results
+        """
+        if memory_type == "short":
+            return self.memory.search_short_term(query, limit=limit)
+        return self.memory.search_long_term(query, limit=limit)
+
+    def add_knowledge(self, source: str) -> None:
+        """
+        Add knowledge source to session.
+        
+        Args:
+            source: File path, URL, or text content
+        """
+        self.knowledge.add(source, user_id=self.user_id, agent_id=self.session_id)
+
+    def search_knowledge(self, query: str, limit: int = 5) -> List[Dict[str, Any]]:
+        """
+        Search session knowledge base.
+        
+        Args:
+            query: Search query
+            limit: Maximum results to return
+
+        Returns:
+            List of knowledge results
+        """
+        return self.knowledge.search(query, agent_id=self.session_id, limit=limit)
+
+    def clear_memory(self, memory_type: str = "all") -> None:
+        """
+        Clear session memory.
+        
+        Args:
+            memory_type: "short", "long", or "all"
+        """
+        if memory_type in ["short", "all"]:
+            self.memory.reset_short_term()
+        if memory_type in ["long", "all"]:
+            self.memory.reset_long_term()
+
+    def get_context(self, query: str, max_items: int = 3) -> str:
+        """
+        Build context from session memory and knowledge.
+        
+        Args:
+            query: Query to build context for
+            max_items: Maximum items per section
+
+        Returns:
+            Formatted context string
+        """
+        return self.memory.build_context_for_task(
+            task_descr=query,
+            user_id=self.user_id,
+            max_items=max_items
+        )
+
+    def _test_remote_connection(self) -> None:
+        """
+        Test connectivity to the remote agent.
+        
+        Raises:
+            ConnectionError: If unable to connect to the remote agent
+        """
+        requests = _get_requests()
+        try:
+            test_url = self.agent_url.rstrip('/') + '/health' if '/health' not in self.agent_url else self.agent_url
+            response = requests.get(test_url, timeout=self.timeout)
+            if response.status_code != 200:
+                response = requests.head(self.agent_url, timeout=self.timeout)
+                if response.status_code not in [200, 405]:
+                    raise ConnectionError(f"Remote agent returned status code: {response.status_code}")
+            print(f"✅ Successfully connected to remote agent at {self.agent_url}")
+        except requests.exceptions.Timeout:
+            raise ConnectionError(f"Timeout connecting to remote agent at {self.agent_url}")
+        except requests.exceptions.ConnectionError:
+            raise ConnectionError(f"Failed to connect to remote agent at {self.agent_url}")
+        except Exception as e:
+            raise ConnectionError(f"Error connecting to remote agent: {str(e)}")
+
+    def chat(self, message: str, **kwargs) -> str:
+        """
+        Send a message to the remote agent or handle local session.
+        
+        Args:
+            message: The message to send to the agent
+            **kwargs: Additional parameters for the request
+            
+        Returns:
+            The agent's response
+            
+        Raises:
+            ValueError: If this is not a remote session
+            ConnectionError: If unable to communicate with remote agent
+        """
+        if not self.is_remote:
+            raise ValueError("chat() method is only available for remote agent sessions. Use Agent.chat() for local agents.")
+        
+        requests = _get_requests()
+        try:
+            payload = {
+                "query": message,
+                "session_id": self.session_id,
+                "user_id": self.user_id,
+                **kwargs
+            }
+            
+            response = requests.post(
+                self.agent_url,
+                json=payload,
+                headers={"Content-Type": "application/json"},
+                timeout=self.timeout
+            )
+            
+            response.raise_for_status()
+            
+            result = response.json()
+            
+            if isinstance(result, dict):
+                return result.get("response", str(result))
+            else:
+                return str(result)
+                
+        except requests.exceptions.Timeout:
+            raise ConnectionError(f"Timeout communicating with remote agent at {self.agent_url}")
+        except requests.exceptions.ConnectionError:
+            raise ConnectionError(f"Failed to communicate with remote agent at {self.agent_url}")
+        except requests.exceptions.HTTPError as e:
+            raise ConnectionError(f"HTTP error from remote agent: {e}")
+        except json.JSONDecodeError:
+            return response.text
+        except Exception as e:
+            raise ConnectionError(f"Error communicating with remote agent: {str(e)}")
+
+    def send_message(self, message: str, **kwargs) -> str:
+        """
+        Alias for chat() method to match Google ADK pattern.
+        
+        Args:
+            message: The message to send to the agent
+            **kwargs: Additional parameters for the request
+            
+        Returns:
+            The agent's response
+        """
+        return self.chat(message, **kwargs)
+
+    def __str__(self) -> str:
+        if self.is_remote:
+            return f"Session(id='{self.session_id}', user='{self.user_id}', remote_agent='{self.agent_url}')"
+        return f"Session(id='{self.session_id}', user='{self.user_id}')"
+
+    def __repr__(self) -> str:
+        return self.__str__()

src/praisonai-agents/praisonaiagents/session/store.py

@@ -170,11 +170,8 @@ class FileLock:
             finally:
                 self._lock_file.close()
                 self._lock_file = None
-                # Clean up lock file
-                try:
-                    os.remove(self._lock_path)
-                except (IOError, OSError):
-                    pass
+                # Note: We don't remove the lock file to avoid race conditions
+                # where another process has opened but not yet locked the file
 
 
 class DefaultSessionStore:

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.6.4"
+version = "0.7.1"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 readme = "README.md"
 requires-python = ">=3.10"

src/praisonai-agents/tests/conftest.py

@@ -0,0 +1,46 @@
+"""
+Pytest configuration for PraisonAI Agents tests.
+
+Provides fixtures and markers for testing, including:
+- live: Tests that require real API keys (opt-in)
+- slow: Tests that take longer to run
+"""
+
+import os
+import pytest
+
+
+def pytest_configure(config):
+    """Register custom markers."""
+    config.addinivalue_line(
+        "markers", "live: mark test as requiring real API keys (deselect with '-m \"not live\"')"
+    )
+    config.addinivalue_line(
+        "markers", "slow: mark test as slow running"
+    )
+
+
+def pytest_collection_modifyitems(config, items):
+    """Skip live tests unless PRAISONAI_LIVE_TESTS=1 is set."""
+    if os.environ.get("PRAISONAI_LIVE_TESTS") != "1":
+        skip_live = pytest.mark.skip(reason="Live tests disabled. Set PRAISONAI_LIVE_TESTS=1 to enable.")
+        for item in items:
+            if "live" in item.keywords:
+                item.add_marker(skip_live)
+
+
+@pytest.fixture
+def openai_api_key():
+    """Get OpenAI API key from environment, skip if not available."""
+    key = os.environ.get("OPENAI_API_KEY")
+    if not key:
+        pytest.skip("OPENAI_API_KEY not set")
+    return key
+
+
+@pytest.fixture
+def live_test_enabled():
+    """Check if live tests are enabled."""
+    if os.environ.get("PRAISONAI_LIVE_TESTS") != "1":
+        pytest.skip("Live tests disabled. Set PRAISONAI_LIVE_TESTS=1 to enable.")
+    return True

src/praisonai-agents/tests/integration/agent/test_agent_rag_live.py

@@ -0,0 +1,230 @@
+"""
+Live integration tests for Agent + RAG integration.
+
+These tests require:
+- PRAISONAI_LIVE_TESTS=1 environment variable
+- OPENAI_API_KEY environment variable
+
+Run with: PRAISONAI_LIVE_TESTS=1 pytest -m live tests/integration/agent/ -v
+"""
+
+import pytest
+import tempfile
+from pathlib import Path
+
+
+@pytest.fixture
+def sample_documents():
+    """Create sample documents for testing."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        # Create sample documents
+        doc1 = Path(tmpdir) / "doc1.txt"
+        doc1.write_text("""
+        The capital of France is Paris.
+        Paris is known for the Eiffel Tower.
+        France is a country in Western Europe.
+        """)
+        
+        doc2 = Path(tmpdir) / "doc2.txt"
+        doc2.write_text("""
+        Python was created by Guido van Rossum.
+        Python is a high-level programming language.
+        Python emphasizes code readability.
+        """)
+        
+        doc3 = Path(tmpdir) / "doc3.txt"
+        doc3.write_text("""
+        Machine learning is a subset of artificial intelligence.
+        Deep learning uses neural networks with many layers.
+        AI is transforming many industries.
+        """)
+        
+        yield tmpdir
+
+
+@pytest.fixture
+def openai_api_key():
+    """Get OpenAI API key from environment."""
+    import os
+    key = os.environ.get("OPENAI_API_KEY")
+    if not key:
+        pytest.skip("OPENAI_API_KEY not set")
+    return key
+
+
+@pytest.mark.live
+class TestAgentRAGLiveQuery:
+    """Live tests for Agent RAG query functionality."""
+    
+    def test_agent_rag_query_with_citations(self, openai_api_key, sample_documents):
+        """Test Agent.rag_query returns answer with citations."""
+        from praisonaiagents import Agent
+        from praisonaiagents.knowledge import Knowledge
+        
+        # Create knowledge base
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_agent_live",
+                    "path": f"{sample_documents}/.chroma",
+                }
+            }
+        }
+        
+        # Pre-index documents
+        knowledge = Knowledge(config=knowledge_config)
+        user_id = "test_user_agent"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        # Create agent with knowledge and rag_config
+        agent = Agent(
+            name="TestAgent",
+            instructions="You are a helpful assistant that answers questions based on provided knowledge.",
+            knowledge=[str(doc) for doc in Path(sample_documents).glob("*.txt")],
+            knowledge_config=knowledge_config,
+            rag_config={"include_citations": True, "top_k": 3},
+            user_id=user_id,
+        )
+        
+        # Use agent.rag_query for RAG with citations
+        result = agent.rag_query("What is the capital of France?")
+        
+        # Assertions
+        assert result.answer is not None
+        assert len(result.answer) > 0
+        assert "paris" in result.answer.lower() or "france" in result.answer.lower()
+        assert result.citations is not None
+        assert len(result.citations) > 0
+    
+    def test_agent_rag_property_access(self, openai_api_key, sample_documents):
+        """Test Agent.rag property provides RAG instance."""
+        from praisonaiagents import Agent
+        from praisonaiagents.knowledge import Knowledge
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_agent_rag_prop",
+                    "path": f"{sample_documents}/.chroma_prop",
+                }
+            }
+        }
+        
+        # Pre-index
+        knowledge = Knowledge(config=knowledge_config)
+        user_id = "test_user_prop"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=[str(doc) for doc in Path(sample_documents).glob("*.txt")],
+            knowledge_config=knowledge_config,
+            rag_config={"include_citations": True},
+            user_id=user_id,
+        )
+        
+        # Access RAG through property
+        rag = agent.rag
+        assert rag is not None
+        
+        # Query through RAG directly
+        result = rag.query("Who created Python?", user_id=user_id)
+        assert "guido" in result.answer.lower() or "rossum" in result.answer.lower()
+
+
+@pytest.mark.live
+class TestAgentRAGLiveStreaming:
+    """Live tests for Agent RAG streaming functionality."""
+    
+    def test_agent_rag_stream(self, openai_api_key, sample_documents):
+        """Test Agent.rag.stream produces chunks."""
+        from praisonaiagents import Agent
+        from praisonaiagents.knowledge import Knowledge
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_agent_stream",
+                    "path": f"{sample_documents}/.chroma_stream",
+                }
+            }
+        }
+        
+        # Pre-index
+        knowledge = Knowledge(config=knowledge_config)
+        user_id = "test_user_stream"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=[str(doc) for doc in Path(sample_documents).glob("*.txt")],
+            knowledge_config=knowledge_config,
+            rag_config={"stream": True},
+            user_id=user_id,
+        )
+        
+        # Stream through RAG
+        chunks = []
+        for chunk in agent.rag.stream("Tell me about machine learning", user_id=user_id):
+            chunks.append(chunk)
+        
+        # Should have multiple chunks
+        assert len(chunks) >= 1
+        
+        # Combined response should be meaningful
+        full_response = "".join(chunks)
+        assert len(full_response) > 10
+
+
+@pytest.mark.live
+class TestAgentRAGLiveCitations:
+    """Live tests for Agent RAG citation functionality."""
+    
+    def test_agent_citations_have_source_info(self, openai_api_key, sample_documents):
+        """Test that Agent RAG citations have proper source information."""
+        from praisonaiagents import Agent
+        from praisonaiagents.knowledge import Knowledge
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_agent_citations",
+                    "path": f"{sample_documents}/.chroma_citations",
+                }
+            }
+        }
+        
+        # Pre-index
+        knowledge = Knowledge(config=knowledge_config)
+        user_id = "test_user_citations"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=[str(doc) for doc in Path(sample_documents).glob("*.txt")],
+            knowledge_config=knowledge_config,
+            rag_config={"include_citations": True, "top_k": 5},
+            user_id=user_id,
+        )
+        
+        result = agent.rag_query("What is the capital of France?")
+        
+        # Check citations
+        assert result.has_citations
+        
+        # Citations should have scores
+        for citation in result.citations:
+            assert citation.id is not None
+            assert citation.text is not None
+            assert len(citation.text) > 0

src/praisonai-agents/tests/integration/rag/__init__.py

@@ -0,0 +1 @@
+"""RAG integration tests."""

src/praisonai-agents/tests/integration/rag/test_rag_live.py

@@ -0,0 +1,241 @@
+"""
+Live integration tests for RAG with real API keys.
+
+These tests require:
+- PRAISONAI_LIVE_TESTS=1
+- OPENAI_API_KEY set
+
+Run with:
+    PRAISONAI_LIVE_TESTS=1 pytest -m live tests/integration/rag/ -v
+"""
+
+import pytest
+import tempfile
+from pathlib import Path
+
+
+@pytest.fixture
+def sample_documents():
+    """Create sample documents for testing."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        doc1 = Path(tmpdir) / "doc1.txt"
+        doc1.write_text("""
+        The capital of France is Paris.
+        Paris is known for the Eiffel Tower.
+        France is a country in Western Europe.
+        """)
+        
+        doc2 = Path(tmpdir) / "doc2.txt"
+        doc2.write_text("""
+        Python is a programming language.
+        Python was created by Guido van Rossum.
+        Python is widely used for data science and AI.
+        """)
+        
+        doc3 = Path(tmpdir) / "doc3.txt"
+        doc3.write_text("""
+        Machine learning is a subset of artificial intelligence.
+        Deep learning uses neural networks.
+        AI is transforming many industries.
+        """)
+        
+        yield tmpdir
+
+
+@pytest.mark.live
+class TestRAGLiveQuery:
+    """Live tests for RAG query functionality."""
+    
+    def test_rag_query_with_citations(self, openai_api_key, sample_documents):
+        """Test RAG query returns answer with citations."""
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        
+        # Create knowledge base
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_live",
+                    "path": f"{sample_documents}/.chroma",
+                }
+            }
+        }
+        
+        knowledge = Knowledge(config=knowledge_config)
+        
+        # Index documents with user_id (required by mem0)
+        user_id = "test_user"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        # Create RAG
+        rag = RAG(
+            knowledge=knowledge,
+            config=RAGConfig(top_k=3, include_citations=True)
+        )
+        
+        # Query with user_id
+        result = rag.query("What is the capital of France?", user_id=user_id)
+        
+        # Assertions
+        assert result.answer is not None
+        assert len(result.answer) > 0
+        assert "paris" in result.answer.lower() or "france" in result.answer.lower()
+        assert result.citations is not None
+        assert len(result.citations) > 0
+    
+    def test_rag_query_python_topic(self, openai_api_key, sample_documents):
+        """Test RAG query on Python topic."""
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_python",
+                    "path": f"{sample_documents}/.chroma_python",
+                }
+            }
+        }
+        
+        knowledge = Knowledge(config=knowledge_config)
+        
+        user_id = "test_user_python"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        rag = RAG(
+            knowledge=knowledge,
+            config=RAGConfig(top_k=3, include_citations=True)
+        )
+        
+        result = rag.query("Who created Python?", user_id=user_id)
+        
+        assert result.answer is not None
+        assert "guido" in result.answer.lower() or "rossum" in result.answer.lower()
+
+
+@pytest.mark.live
+class TestRAGLiveStreaming:
+    """Live tests for RAG streaming functionality."""
+    
+    def test_rag_stream_produces_chunks(self, openai_api_key, sample_documents):
+        """Test RAG streaming produces multiple chunks."""
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_stream",
+                    "path": f"{sample_documents}/.chroma_stream",
+                }
+            }
+        }
+        
+        knowledge = Knowledge(config=knowledge_config)
+        
+        user_id = "test_user_stream"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        rag = RAG(
+            knowledge=knowledge,
+            config=RAGConfig(top_k=3, stream=True)
+        )
+        
+        # Collect streamed chunks
+        chunks = []
+        for chunk in rag.stream("Tell me about machine learning", user_id=user_id):
+            chunks.append(chunk)
+        
+        # Should have multiple chunks
+        assert len(chunks) >= 1
+        
+        # Combined response should be meaningful
+        full_response = "".join(chunks)
+        assert len(full_response) > 10
+
+
+@pytest.mark.live
+class TestRAGLiveCitations:
+    """Live tests for RAG citation functionality."""
+    
+    def test_citations_reference_correct_sources(self, openai_api_key, sample_documents):
+        """Test that citations reference the correct source documents."""
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_citations",
+                    "path": f"{sample_documents}/.chroma_citations",
+                }
+            }
+        }
+        
+        knowledge = Knowledge(config=knowledge_config)
+        
+        user_id = "test_user_citations"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        rag = RAG(
+            knowledge=knowledge,
+            config=RAGConfig(top_k=5, include_citations=True)
+        )
+        
+        result = rag.query("What is the capital of France?", user_id=user_id)
+        
+        # Check citations
+        assert result.has_citations
+        
+        # At least one citation should be from doc1 (France content)
+        citation_sources = [c.source for c in result.citations]
+        assert len(citation_sources) > 0
+        
+        # Citations should have scores
+        for citation in result.citations:
+            assert citation.score is not None or citation.score >= 0
+    
+    def test_get_citations_without_generation(self, openai_api_key, sample_documents):
+        """Test getting citations without generating an answer."""
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": "test_citations_only",
+                    "path": f"{sample_documents}/.chroma_citations_only",
+                }
+            }
+        }
+        
+        knowledge = Knowledge(config=knowledge_config)
+        
+        user_id = "test_user_citations_only"
+        for doc in Path(sample_documents).glob("*.txt"):
+            knowledge.add(str(doc), user_id=user_id)
+        
+        rag = RAG(
+            knowledge=knowledge,
+            config=RAGConfig(top_k=3)
+        )
+        
+        citations = rag.get_citations("Python programming", user_id=user_id)
+        
+        assert citations is not None
+        assert len(citations) > 0
+        
+        # Check citation structure
+        for citation in citations:
+            assert citation.id is not None
+            assert citation.text is not None
+            assert len(citation.text) > 0

src/praisonai-agents/tests/live/test_retrieval_live.py

@@ -0,0 +1,166 @@
+"""
+Live smoke tests for Agent retrieval functionality.
+
+These tests require real API keys and are gated by RUN_LIVE_TESTS=1.
+
+Run with:
+    RUN_LIVE_TESTS=1 python -m pytest tests/live/test_retrieval_live.py -v
+"""
+
+import os
+import pytest
+import tempfile
+import shutil
+
+# Skip all tests if RUN_LIVE_TESTS is not set
+pytestmark = pytest.mark.skipif(
+    os.environ.get("RUN_LIVE_TESTS") != "1",
+    reason="Live tests require RUN_LIVE_TESTS=1"
+)
+
+
+@pytest.fixture
+def test_knowledge_dir():
+    """Create a temporary directory with test documents."""
+    temp_dir = tempfile.mkdtemp(prefix="praison_test_")
+    
+    # Create test document
+    doc_content = """
+    # Test Document
+    
+    This is a test document for retrieval testing.
+    
+    ## Key Points
+    
+    1. The capital of France is Paris.
+    2. Python is a programming language.
+    3. PraisonAI is an AI agents framework.
+    
+    ## Details
+    
+    Paris is known for the Eiffel Tower.
+    Python was created by Guido van Rossum.
+    PraisonAI supports multi-agent workflows.
+    """
+    
+    with open(os.path.join(temp_dir, "test_doc.txt"), "w") as f:
+        f.write(doc_content)
+    
+    yield temp_dir
+    
+    # Cleanup
+    shutil.rmtree(temp_dir, ignore_errors=True)
+
+
+class TestLiveRetrieval:
+    """Live tests for retrieval functionality."""
+    
+    def test_agent_chat_with_knowledge(self, test_knowledge_dir):
+        """Test Agent.chat() with knowledge retrieval."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Answer questions based on the provided knowledge. Be concise.",
+            knowledge=[test_knowledge_dir],
+            retrieval_config={
+                "policy": "always",
+                "top_k": 3,
+            }
+        )
+        
+        response = agent.chat("What is the capital of France?")
+        
+        assert response is not None
+        assert len(response) > 0
+        assert "Paris" in response or "paris" in response.lower()
+    
+    def test_agent_chat_skip_retrieval(self, test_knowledge_dir):
+        """Test Agent.chat() with skip_retrieval=True."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="You are a helpful assistant.",
+            knowledge=[test_knowledge_dir],
+            retrieval_config={"policy": "always"}
+        )
+        
+        # Skip retrieval - should still work but not use knowledge
+        response = agent.chat("What is 2 + 2?", skip_retrieval=True)
+        
+        assert response is not None
+        assert "4" in response
+    
+    def test_retrieval_config_policy_auto(self, test_knowledge_dir):
+        """Test auto retrieval policy."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig, RetrievalPolicy
+        
+        config = RetrievalConfig(
+            policy=RetrievalPolicy.AUTO,
+            top_k=3,
+        )
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Answer questions based on knowledge when relevant.",
+            knowledge=[test_knowledge_dir],
+            retrieval_config=config,
+        )
+        
+        # This should trigger retrieval (contains question keywords)
+        response = agent.chat("What is PraisonAI?")
+        
+        assert response is not None
+        assert len(response) > 0
+
+
+class TestLiveExports:
+    """Test that all exports work with real imports."""
+    
+    def test_all_exports_importable(self):
+        """Test all retrieval-related exports are importable."""
+        from praisonaiagents import (
+            Agent,
+            RetrievalConfig,
+            RetrievalPolicy,
+            CitationsMode,
+            ContextPack,
+            RAGResult,
+            Citation,
+        )
+        
+        assert Agent is not None
+        assert RetrievalConfig is not None
+        assert RetrievalPolicy is not None
+        assert CitationsMode is not None
+        assert ContextPack is not None
+        assert RAGResult is not None
+        assert Citation is not None
+    
+    def test_retrieval_config_creation(self):
+        """Test RetrievalConfig can be created with various options."""
+        from praisonaiagents import RetrievalConfig, RetrievalPolicy, CitationsMode
+        
+        config = RetrievalConfig(
+            enabled=True,
+            policy=RetrievalPolicy.ALWAYS,
+            top_k=10,
+            min_score=0.5,
+            max_context_tokens=8000,
+            rerank=True,
+            hybrid=True,
+            citations=True,
+            citations_mode=CitationsMode.INLINE,
+        )
+        
+        assert config.policy == RetrievalPolicy.ALWAYS
+        assert config.top_k == 10
+        assert config.rerank is True
+
+
+if __name__ == "__main__":
+    # Allow running directly with: python test_retrieval_live.py
+    os.environ["RUN_LIVE_TESTS"] = "1"
+    pytest.main([__file__, "-v"])

src/praisonai-agents/tests/unit/agent/test_agent_rag.py

@@ -0,0 +1,187 @@
+"""
+Tests for Agent RAG integration.
+
+Tests that Agent can access RAG features through the knowledge parameter.
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+
+
+class TestAgentRAGConfig:
+    """Tests for Agent rag_config parameter."""
+    
+    def test_agent_accepts_rag_config(self):
+        """Test that Agent accepts rag_config parameter."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"],
+            rag_config={"include_citations": True, "top_k": 5}
+        )
+        
+        assert agent._rag_config == {"include_citations": True, "top_k": 5}
+    
+    def test_agent_without_rag_config(self):
+        """Test that Agent works without rag_config."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"]
+        )
+        
+        assert agent._rag_config is None
+    
+    def test_agent_without_knowledge_has_no_rag_config(self):
+        """Test that Agent without knowledge has no rag_config."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent"
+        )
+        
+        assert agent._rag_config is None
+        assert agent._rag_instance is None
+
+
+class TestAgentRAGProperty:
+    """Tests for Agent.rag property."""
+    
+    def test_agent_has_rag_property(self):
+        """Test that Agent has rag property."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"],
+            rag_config={"include_citations": True}
+        )
+        
+        assert hasattr(agent, 'rag')
+    
+    def test_agent_rag_returns_none_without_knowledge(self):
+        """Test that Agent.rag returns None without knowledge."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent"
+        )
+        
+        assert agent.rag is None
+    
+    @patch('praisonaiagents.knowledge.Knowledge')
+    @patch('praisonaiagents.rag.RAG')
+    @patch('praisonaiagents.rag.RAGConfig')
+    def test_agent_rag_lazy_loads(self, mock_rag_config, mock_rag, mock_knowledge):
+        """Test that Agent.rag lazy loads RAG instance."""
+        from praisonaiagents import Agent
+        
+        mock_knowledge_instance = MagicMock()
+        mock_knowledge.return_value = mock_knowledge_instance
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"],
+            rag_config={"include_citations": True}
+        )
+        
+        # RAG should not be loaded yet
+        assert agent._rag_instance is None
+        
+        # Access rag property - this triggers lazy loading
+        # Note: In real usage, knowledge processing would happen first
+
+
+class TestAgentRAGQuery:
+    """Tests for Agent.rag_query method."""
+    
+    def test_agent_has_rag_query_method(self):
+        """Test that Agent has rag_query method."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"],
+            rag_config={"include_citations": True}
+        )
+        
+        assert hasattr(agent, 'rag_query')
+        assert callable(agent.rag_query)
+    
+    def test_rag_query_raises_without_knowledge(self):
+        """Test that rag_query raises error without knowledge."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent"
+        )
+        
+        with pytest.raises(ValueError, match="No knowledge sources configured"):
+            agent.rag_query("What is the answer?")
+
+
+class TestAgentKnowledgeContext:
+    """Tests for Agent._get_knowledge_context method."""
+    
+    def test_agent_has_get_knowledge_context_method(self):
+        """Test that Agent has _get_knowledge_context method."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"]
+        )
+        
+        assert hasattr(agent, '_get_knowledge_context')
+        assert callable(agent._get_knowledge_context)
+    
+    def test_get_knowledge_context_returns_tuple(self):
+        """Test that _get_knowledge_context returns tuple."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent"
+        )
+        
+        result = agent._get_knowledge_context("test query")
+        
+        assert isinstance(result, tuple)
+        assert len(result) == 2
+        assert result[0] == ""  # No knowledge, empty context
+        assert result[1] is None  # No citations
+
+
+class TestAgentRAGIntegration:
+    """Integration tests for Agent + RAG."""
+    
+    def test_agent_rag_config_passed_to_rag_instance(self):
+        """Test that rag_config is passed to RAG instance."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test agent",
+            knowledge=["test.txt"],
+            rag_config={
+                "include_citations": True,
+                "top_k": 10,
+                "min_score": 0.5
+            }
+        )
+        
+        # Verify config is stored
+        assert agent._rag_config["include_citations"] is True
+        assert agent._rag_config["top_k"] == 10
+        assert agent._rag_config["min_score"] == 0.5

src/praisonai-agents/tests/unit/agent/test_agent_retrieval.py

@@ -0,0 +1,378 @@
+"""
+Tests for Agent retrieval integration.
+
+Tests cover:
+1. Agent with retrieval_config parameter
+2. Agent.query() method
+3. Agent.retrieve() method
+4. Retrieval policy in chat()
+5. force_retrieval and skip_retrieval
+6. Shared Knowledge instances
+7. Lazy loading of retrieval dependencies
+"""
+
+import pytest
+from unittest.mock import Mock, patch, MagicMock
+
+
+class TestAgentRetrievalConfig:
+    """Test Agent initialization with retrieval_config."""
+    
+    def test_agent_accepts_retrieval_config_dict(self):
+        """Test Agent accepts retrieval_config as dict."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            retrieval_config={
+                "policy": "always",
+                "top_k": 10,
+                "citations": True,
+            },
+        )
+        
+        assert agent._retrieval_config is not None
+        assert agent._retrieval_config.top_k == 10
+        assert agent._retrieval_config.citations is True
+    
+    def test_agent_accepts_retrieval_config_object(self):
+        """Test Agent accepts RetrievalConfig object."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig, RetrievalPolicy
+        
+        config = RetrievalConfig(
+            policy=RetrievalPolicy.NEVER,
+            top_k=15,
+        )
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            retrieval_config=config,
+        )
+        
+        assert agent._retrieval_config is config
+        assert agent._retrieval_config.top_k == 15
+    
+    def test_agent_creates_default_config_with_knowledge(self):
+        """Test Agent creates default RetrievalConfig when knowledge is provided."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+        )
+        
+        assert agent._retrieval_config is not None
+        assert agent._retrieval_config.enabled is True
+    
+    def test_agent_no_config_without_knowledge(self):
+        """Test Agent has no retrieval_config without knowledge."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+        )
+        
+        assert agent._retrieval_config is None
+    
+    def test_legacy_knowledge_config_migration(self):
+        """Test legacy knowledge_config is migrated to retrieval_config."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+            knowledge_config={
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {"collection_name": "legacy_test"}
+                }
+            },
+        )
+        
+        assert agent._retrieval_config is not None
+        assert agent._retrieval_config.collection_name == "legacy_test"
+    
+    def test_legacy_rag_config_migration(self):
+        """Test legacy rag_config is migrated to retrieval_config."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+            rag_config={
+                "top_k": 20,
+                "include_citations": True,
+            },
+        )
+        
+        assert agent._retrieval_config is not None
+        assert agent._retrieval_config.top_k == 20
+        assert agent._retrieval_config.citations is True
+
+
+class TestAgentRetrievalConfigProperty:
+    """Test Agent.retrieval_config property."""
+    
+    def test_retrieval_config_property(self):
+        """Test retrieval_config property returns the config."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig
+        
+        config = RetrievalConfig(top_k=25)
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            retrieval_config=config,
+        )
+        
+        assert agent.retrieval_config is config
+
+
+class TestAgentSharedKnowledge:
+    """Test Agent with shared Knowledge instances."""
+    
+    def test_agent_accepts_knowledge_instance(self):
+        """Test Agent accepts a Knowledge instance directly."""
+        from praisonaiagents import Agent
+        
+        mock_knowledge = Mock()
+        mock_knowledge.search = Mock(return_value=[])
+        mock_knowledge.add = Mock()
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=mock_knowledge,
+        )
+        
+        assert agent.knowledge is mock_knowledge
+        assert agent._knowledge_processed is True
+    
+    def test_two_agents_share_knowledge(self):
+        """Test two agents can share the same Knowledge instance."""
+        from praisonaiagents import Agent
+        
+        mock_knowledge = Mock()
+        mock_knowledge.search = Mock(return_value=[])
+        mock_knowledge.add = Mock()
+        
+        agent1 = Agent(
+            name="Agent1",
+            instructions="Test 1",
+            knowledge=mock_knowledge,
+        )
+        
+        agent2 = Agent(
+            name="Agent2",
+            instructions="Test 2",
+            knowledge=mock_knowledge,
+        )
+        
+        assert agent1.knowledge is agent2.knowledge
+
+
+class TestAgentQueryMethod:
+    """Test Agent.query() method."""
+    
+    def test_query_raises_without_knowledge(self):
+        """Test query() raises ValueError without knowledge."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+        )
+        
+        with pytest.raises(ValueError, match="No knowledge configured"):
+            agent.query("What is the answer?")
+    
+    def test_query_returns_rag_result(self):
+        """Test query() returns RAGResult with mocked RAG."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.models import RAGResult, Citation
+        
+        mock_rag_result = RAGResult(
+            answer="The answer is 42",
+            citations=[Citation(id="1", source="test.txt", text="42 is the answer")],
+            context_used="Context here",
+            query="What is the answer?",
+        )
+        
+        mock_rag = Mock()
+        mock_rag.query = Mock(return_value=mock_rag_result)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+        )
+        agent._rag_instance = mock_rag
+        agent._knowledge_processed = True
+        agent.knowledge = Mock()
+        
+        result = agent.query("What is the answer?")
+        
+        assert result.answer == "The answer is 42"
+        assert len(result.citations) == 1
+        mock_rag.query.assert_called_once()
+
+
+class TestAgentRetrieveMethod:
+    """Test Agent.retrieve() method."""
+    
+    def test_retrieve_raises_without_knowledge(self):
+        """Test retrieve() raises ValueError without knowledge."""
+        from praisonaiagents import Agent
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+        )
+        
+        with pytest.raises(ValueError, match="No knowledge configured"):
+            agent.retrieve("search query")
+    
+    def test_retrieve_returns_context_pack(self):
+        """Test retrieve() returns ContextPack with mocked RAG."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.models import ContextPack, Citation
+        
+        mock_context_pack = ContextPack(
+            context="Retrieved context",
+            citations=[Citation(id="1", source="test.txt", text="content")],
+            query="search query",
+        )
+        
+        mock_rag = Mock()
+        mock_rag.retrieve = Mock(return_value=mock_context_pack)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+        )
+        agent._rag_instance = mock_rag
+        agent._knowledge_processed = True
+        agent.knowledge = Mock()
+        
+        result = agent.retrieve("search query")
+        
+        assert result.context == "Retrieved context"
+        assert len(result.citations) == 1
+        mock_rag.retrieve.assert_called_once()
+
+
+class TestAgentChatRetrieval:
+    """Test retrieval in Agent.chat() method."""
+    
+    def test_chat_with_force_retrieval(self):
+        """Test chat() with force_retrieval=True."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig, RetrievalPolicy
+        
+        config = RetrievalConfig(policy=RetrievalPolicy.NEVER)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+            retrieval_config=config,
+        )
+        
+        # Verify force parameter is accepted
+        # Full integration test would require mocking LLM
+        assert hasattr(agent.chat, '__call__')
+    
+    def test_chat_with_skip_retrieval(self):
+        """Test chat() with skip_retrieval=True."""
+        from praisonaiagents import Agent
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig, RetrievalPolicy
+        
+        config = RetrievalConfig(policy=RetrievalPolicy.ALWAYS)
+        
+        agent = Agent(
+            name="TestAgent",
+            instructions="Test",
+            knowledge=["test.txt"],
+            retrieval_config=config,
+        )
+        
+        # Verify skip parameter is accepted
+        assert hasattr(agent.chat, '__call__')
+
+
+class TestLazyLoading:
+    """Test lazy loading of retrieval dependencies."""
+    
+    def test_import_agent_does_not_import_chromadb(self):
+        """Test importing Agent does not import chromadb."""
+        import sys
+        
+        # Clear any cached imports
+        modules_before = set(sys.modules.keys())
+        
+        from praisonaiagents import Agent
+        
+        # Agent import should not trigger chromadb import
+        # (chromadb is only imported when knowledge is actually used)
+        agent = Agent(name="Test", instructions="Test")
+        
+        # This is a soft check - chromadb may be imported by other tests
+        # The key is that Agent init without knowledge doesn't require it
+        assert agent is not None
+    
+    def test_retrieval_config_import_is_lightweight(self):
+        """Test RetrievalConfig import is lightweight."""
+        import sys
+        import time
+        
+        start = time.perf_counter()
+        from praisonaiagents.rag.retrieval_config import RetrievalConfig
+        elapsed = time.perf_counter() - start
+        
+        # Should import in under 50ms (no heavy deps)
+        assert elapsed < 0.5  # Allow some slack for slow systems
+        
+        config = RetrievalConfig()
+        assert config is not None
+
+
+class TestExportsAvailable:
+    """Test that all expected exports are available."""
+    
+    def test_retrieval_config_exported(self):
+        """Test RetrievalConfig is exported from top level."""
+        from praisonaiagents import RetrievalConfig
+        assert RetrievalConfig is not None
+    
+    def test_retrieval_policy_exported(self):
+        """Test RetrievalPolicy is exported from top level."""
+        from praisonaiagents import RetrievalPolicy
+        assert RetrievalPolicy is not None
+    
+    def test_citations_mode_exported(self):
+        """Test CitationsMode is exported from top level."""
+        from praisonaiagents import CitationsMode
+        assert CitationsMode is not None
+    
+    def test_context_pack_exported(self):
+        """Test ContextPack is exported from top level."""
+        from praisonaiagents import ContextPack
+        assert ContextPack is not None
+    
+    def test_rag_result_exported(self):
+        """Test RAGResult is exported from top level."""
+        from praisonaiagents import RAGResult
+        assert RAGResult is not None
+    
+    def test_citation_exported(self):
+        """Test Citation is exported from top level."""
+        from praisonaiagents import Citation
+        assert Citation is not None

src/praisonai-agents/tests/unit/context/__init__.py

@@ -0,0 +1 @@
+"""Unit tests for context management module."""

src/praisonai-agents/tests/unit/context/test_budgeter.py

@@ -0,0 +1,201 @@
+"""Tests for context budgeter module."""
+
+
+class TestContextBudgeter:
+    """Tests for ContextBudgeter class."""
+    
+    def test_default_initialization(self):
+        """Test default budgeter initialization."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter()
+        assert budgeter.model == "gpt-4o-mini"
+        assert budgeter.model_limit > 0
+        assert budgeter.output_reserve > 0
+        assert budgeter.usable == budgeter.model_limit - budgeter.output_reserve
+    
+    def test_model_limit_lookup(self):
+        """Test model limit lookup."""
+        from praisonaiagents.context.budgeter import get_model_limit
+        
+        assert get_model_limit("gpt-4o") == 128000
+        assert get_model_limit("gpt-4") == 8192
+        assert get_model_limit("claude-3-5-sonnet") == 200000
+        assert get_model_limit("gemini-1.5-pro") == 2097152
+    
+    def test_model_limit_partial_match(self):
+        """Test partial model name matching."""
+        from praisonaiagents.context.budgeter import get_model_limit
+        
+        # Should match gpt-4o
+        assert get_model_limit("gpt-4o-2024-05-13") == 128000
+    
+    def test_model_limit_unknown(self):
+        """Test unknown model uses default."""
+        from praisonaiagents.context.budgeter import get_model_limit
+        
+        limit = get_model_limit("unknown-model-xyz")
+        assert limit == 128000  # Default
+    
+    def test_output_reserve_lookup(self):
+        """Test output reserve lookup."""
+        from praisonaiagents.context.budgeter import get_output_reserve
+        
+        assert get_output_reserve("gpt-4o") == 16384
+        assert get_output_reserve("claude-3-opus") == 8192
+    
+    def test_allocate_returns_budget(self):
+        """Test allocate returns BudgetAllocation."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        from praisonaiagents.context.models import BudgetAllocation
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        allocation = budgeter.allocate()
+        
+        assert isinstance(allocation, BudgetAllocation)
+        assert allocation.model_limit == budgeter.model_limit
+        assert allocation.output_reserve == budgeter.output_reserve
+    
+    def test_allocate_segment_budgets(self):
+        """Test segment budgets in allocation."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(
+            system_prompt_budget=3000,
+            rules_budget=1000,
+        )
+        allocation = budgeter.allocate()
+        
+        assert allocation.system_prompt == 3000
+        assert allocation.rules == 1000
+    
+    def test_history_budget_dynamic(self):
+        """Test history budget is computed dynamically."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        allocation = budgeter.allocate()
+        
+        # History budget should be remainder after fixed segments
+        assert allocation.history_budget > 0
+        assert allocation.history_budget < allocation.usable
+    
+    def test_history_ratio_override(self):
+        """Test history_ratio overrides dynamic calculation."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(
+            model="gpt-4o",
+            history_ratio=0.5,
+        )
+        allocation = budgeter.allocate()
+        
+        expected = int(budgeter.usable * 0.5)
+        assert allocation.history == expected
+    
+    def test_check_overflow_under_threshold(self):
+        """Test overflow check when under threshold."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        
+        # 50% of usable should not trigger at 80% threshold
+        current = int(budgeter.usable * 0.5)
+        assert not budgeter.check_overflow(current, threshold=0.8)
+    
+    def test_check_overflow_over_threshold(self):
+        """Test overflow check when over threshold."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        
+        # 90% of usable should trigger at 80% threshold
+        current = int(budgeter.usable * 0.9)
+        assert budgeter.check_overflow(current, threshold=0.8)
+    
+    def test_get_remaining(self):
+        """Test remaining tokens calculation."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        
+        current = 50000
+        remaining = budgeter.get_remaining(current)
+        assert remaining == budgeter.usable - current
+    
+    def test_get_utilization(self):
+        """Test utilization calculation."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        
+        current = budgeter.usable // 2
+        util = budgeter.get_utilization(current)
+        assert 0.49 <= util <= 0.51
+    
+    def test_to_dict(self):
+        """Test dictionary conversion."""
+        from praisonaiagents.context.budgeter import ContextBudgeter
+        
+        budgeter = ContextBudgeter(model="gpt-4o")
+        data = budgeter.to_dict()
+        
+        assert "model" in data
+        assert "model_limit" in data
+        assert "usable" in data
+        assert "allocation" in data
+
+
+class TestBudgetAllocation:
+    """Tests for BudgetAllocation dataclass."""
+    
+    def test_usable_property(self):
+        """Test usable property calculation."""
+        from praisonaiagents.context.models import BudgetAllocation
+        
+        allocation = BudgetAllocation(
+            model_limit=128000,
+            output_reserve=8000,
+        )
+        assert allocation.usable == 120000
+    
+    def test_fixed_total(self):
+        """Test fixed total calculation."""
+        from praisonaiagents.context.models import BudgetAllocation
+        
+        allocation = BudgetAllocation(
+            system_prompt=2000,
+            rules=500,
+            skills=500,
+            memory=1000,
+            tools_schema=2000,
+            tool_outputs=20000,
+            buffer=1000,
+        )
+        
+        expected = 2000 + 500 + 500 + 1000 + 2000 + 20000 + 1000
+        assert allocation.fixed_total == expected
+    
+    def test_history_budget_computed(self):
+        """Test history budget is computed from remainder."""
+        from praisonaiagents.context.models import BudgetAllocation
+        
+        allocation = BudgetAllocation(
+            model_limit=128000,
+            output_reserve=8000,
+            history=-1,  # Dynamic
+        )
+        
+        expected = allocation.usable - allocation.fixed_total
+        assert allocation.history_budget == expected
+    
+    def test_to_dict(self):
+        """Test dictionary conversion."""
+        from praisonaiagents.context.models import BudgetAllocation
+        
+        allocation = BudgetAllocation()
+        data = allocation.to_dict()
+        
+        assert "model_limit" in data
+        assert "usable" in data
+        assert "history_budget" in data

src/praisonai-agents/tests/unit/context/test_monitor.py

@@ -0,0 +1,284 @@
+"""Tests for context monitor module."""
+
+import tempfile
+import os
+from pathlib import Path
+
+
+class TestContextMonitor:
+    """Tests for ContextMonitor class."""
+    
+    def test_monitor_disabled_by_default(self):
+        """Test monitor is disabled by default."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor()
+        assert not monitor.enabled
+    
+    def test_monitor_enable_disable(self):
+        """Test enable/disable methods."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor()
+        
+        monitor.enable()
+        assert monitor.enabled
+        
+        monitor.disable()
+        assert not monitor.enabled
+    
+    def test_should_write_when_disabled(self):
+        """Test should_write returns False when disabled."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(enabled=False)
+        assert not monitor.should_write("turn")
+        assert not monitor.should_write("manual")
+    
+    def test_should_write_frequency_turn(self):
+        """Test should_write with turn frequency."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(enabled=True, frequency="turn")
+        
+        assert monitor.should_write("turn")
+        assert monitor.should_write("overflow")
+        assert not monitor.should_write("tool_call")
+    
+    def test_should_write_frequency_tool_call(self):
+        """Test should_write with tool_call frequency."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(enabled=True, frequency="tool_call")
+        
+        assert monitor.should_write("tool_call")
+        assert monitor.should_write("overflow")
+    
+    def test_should_write_frequency_manual(self):
+        """Test should_write with manual frequency."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(enabled=True, frequency="manual")
+        
+        assert monitor.should_write("manual")
+        assert not monitor.should_write("turn")
+    
+    def test_snapshot_writes_file(self):
+        """Test snapshot writes file to disk."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        from praisonaiagents.context.models import ContextLedger, BudgetAllocation
+        
+        with tempfile.TemporaryDirectory() as tmpdir:
+            path = os.path.join(tmpdir, "context.txt")
+            monitor = ContextMonitor(enabled=True, path=path)
+            
+            ledger = ContextLedger(history=1000, system_prompt=500)
+            budget = BudgetAllocation()
+            
+            result_path = monitor.snapshot(
+                ledger=ledger,
+                budget=budget,
+                messages=[{"role": "user", "content": "Hello"}],
+                trigger="manual",
+            )
+            
+            assert result_path is not None
+            assert os.path.exists(path)
+            
+            content = Path(path).read_text()
+            assert "PRAISONAI CONTEXT SNAPSHOT" in content
+    
+    def test_snapshot_json_format(self):
+        """Test snapshot with JSON format."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        from praisonaiagents.context.models import ContextLedger, BudgetAllocation
+        import json
+        
+        with tempfile.TemporaryDirectory() as tmpdir:
+            path = os.path.join(tmpdir, "context.json")
+            monitor = ContextMonitor(enabled=True, path=path, format="json")
+            
+            ledger = ContextLedger(history=1000)
+            budget = BudgetAllocation()
+            
+            monitor.snapshot(
+                ledger=ledger,
+                budget=budget,
+                messages=[],
+                trigger="manual",
+            )
+            
+            content = Path(path).read_text()
+            data = json.loads(content)
+            
+            assert "ledger" in data
+            assert "timestamp" in data
+    
+    def test_snapshot_not_written_when_disabled(self):
+        """Test snapshot not written when disabled."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        from praisonaiagents.context.models import ContextLedger, BudgetAllocation
+        
+        with tempfile.TemporaryDirectory() as tmpdir:
+            path = os.path.join(tmpdir, "context.txt")
+            monitor = ContextMonitor(enabled=False, path=path)
+            
+            result = monitor.snapshot(
+                ledger=ContextLedger(),
+                budget=BudgetAllocation(),
+                messages=[],
+                trigger="turn",
+            )
+            
+            assert result is None
+            assert not os.path.exists(path)
+    
+    def test_set_path(self):
+        """Test set_path method."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor()
+        monitor.set_path("/new/path/context.txt")
+        
+        assert str(monitor.path) == "/new/path/context.txt"
+    
+    def test_set_format(self):
+        """Test set_format method."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(format="human")
+        monitor.set_format("json")
+        
+        assert monitor.format == "json"
+    
+    def test_get_stats(self):
+        """Test get_stats method."""
+        from praisonaiagents.context.monitor import ContextMonitor
+        
+        monitor = ContextMonitor(enabled=True, path="./test.txt")
+        stats = monitor.get_stats()
+        
+        assert "enabled" in stats
+        assert "path" in stats
+        assert "format" in stats
+        assert stats["enabled"] is True
+
+
+class TestRedaction:
+    """Tests for sensitive data redaction."""
+    
+    def test_redact_api_key(self):
+        """Test API key redaction."""
+        from praisonaiagents.context.monitor import redact_sensitive
+        
+        text = "My API key is sk-proj-abc123def456ghi789jkl012mno345pqr678"
+        result = redact_sensitive(text)
+        
+        assert "sk-proj-" not in result
+        assert "[REDACTED]" in result
+    
+    def test_redact_password(self):
+        """Test password redaction."""
+        from praisonaiagents.context.monitor import redact_sensitive
+        
+        text = 'password: "mysecretpassword123"'
+        result = redact_sensitive(text)
+        
+        assert "mysecretpassword" not in result
+    
+    def test_redact_preserves_normal_text(self):
+        """Test normal text is preserved."""
+        from praisonaiagents.context.monitor import redact_sensitive
+        
+        text = "Hello, how are you today?"
+        result = redact_sensitive(text)
+        
+        assert result == text
+
+
+class TestFormatting:
+    """Tests for snapshot formatting."""
+    
+    def test_format_human_snapshot(self):
+        """Test human-readable format."""
+        from praisonaiagents.context.monitor import format_human_snapshot
+        from praisonaiagents.context.models import ContextSnapshot, ContextLedger, BudgetAllocation
+        
+        snapshot = ContextSnapshot(
+            timestamp="2025-01-07T12:00:00Z",
+            session_id="test-session",
+            agent_name="TestAgent",
+            model_name="gpt-4o",
+            budget=BudgetAllocation(),
+            ledger=ContextLedger(history=5000, system_prompt=1000),
+            utilization=0.5,
+            warnings=["Test warning"],
+        )
+        
+        result = format_human_snapshot(snapshot)
+        
+        assert "PRAISONAI CONTEXT SNAPSHOT" in result
+        assert "TestAgent" in result
+        assert "gpt-4o" in result
+        assert "Test warning" in result
+    
+    def test_format_json_snapshot(self):
+        """Test JSON format."""
+        from praisonaiagents.context.monitor import format_json_snapshot
+        from praisonaiagents.context.models import ContextSnapshot, ContextLedger, BudgetAllocation
+        import json
+        
+        snapshot = ContextSnapshot(
+            timestamp="2025-01-07T12:00:00Z",
+            session_id="test-session",
+            ledger=ContextLedger(),
+            budget=BudgetAllocation(),
+        )
+        
+        result = format_json_snapshot(snapshot)
+        data = json.loads(result)
+        
+        assert data["timestamp"] == "2025-01-07T12:00:00Z"
+        assert data["session_id"] == "test-session"
+
+
+class TestMultiAgentMonitor:
+    """Tests for MultiAgentMonitor class."""
+    
+    def test_get_agent_monitor(self):
+        """Test getting agent-specific monitor."""
+        from praisonaiagents.context.monitor import MultiAgentMonitor
+        
+        multi = MultiAgentMonitor(base_path="./context")
+        
+        monitor1 = multi.get_agent_monitor("agent1")
+        monitor2 = multi.get_agent_monitor("agent2")
+        
+        assert monitor1 is not monitor2
+        assert "agent1" in str(monitor1.path)
+        assert "agent2" in str(monitor2.path)
+    
+    def test_enable_all(self):
+        """Test enabling all monitors."""
+        from praisonaiagents.context.monitor import MultiAgentMonitor
+        
+        multi = MultiAgentMonitor()
+        multi.get_agent_monitor("agent1")
+        multi.get_agent_monitor("agent2")
+        
+        multi.enable_all()
+        
+        assert multi.enabled
+    
+    def test_get_agent_ids(self):
+        """Test getting list of agent IDs."""
+        from praisonaiagents.context.monitor import MultiAgentMonitor
+        
+        multi = MultiAgentMonitor()
+        multi.get_agent_monitor("agent1")
+        multi.get_agent_monitor("agent2")
+        
+        ids = multi.get_agent_ids()
+        
+        assert "agent1" in ids
+        assert "agent2" in ids

src/praisonai-agents/tests/unit/context/test_optimizer.py

@@ -0,0 +1,208 @@
+"""Tests for context optimizer module."""
+
+
+class TestOptimizers:
+    """Tests for optimizer strategies."""
+    
+    def test_truncate_optimizer_no_change_needed(self):
+        """Test truncate when under limit."""
+        from praisonaiagents.context.optimizer import TruncateOptimizer
+        
+        messages = [
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi"},
+        ]
+        
+        optimizer = TruncateOptimizer()
+        result, stats = optimizer.optimize(messages, target_tokens=10000)
+        
+        assert len(result) == 2
+        assert stats.tokens_saved == 0
+    
+    def test_truncate_optimizer_removes_old(self):
+        """Test truncate removes old messages."""
+        from praisonaiagents.context.optimizer import TruncateOptimizer
+        
+        messages = [
+            {"role": "system", "content": "You are helpful"},
+            {"role": "user", "content": "a" * 1000},
+            {"role": "assistant", "content": "b" * 1000},
+            {"role": "user", "content": "c" * 1000},
+            {"role": "assistant", "content": "d" * 1000},
+        ]
+        
+        optimizer = TruncateOptimizer(preserve_recent=2)
+        result, stats = optimizer.optimize(messages, target_tokens=500)
+        
+        # Should keep system + recent
+        assert len(result) < len(messages)
+        assert stats.messages_removed > 0
+    
+    def test_truncate_preserves_system(self):
+        """Test truncate preserves system messages."""
+        from praisonaiagents.context.optimizer import TruncateOptimizer
+        
+        messages = [
+            {"role": "system", "content": "Important system prompt"},
+            {"role": "user", "content": "a" * 1000},
+            {"role": "assistant", "content": "b" * 1000},
+        ]
+        
+        optimizer = TruncateOptimizer(preserve_system=True)
+        result, stats = optimizer.optimize(messages, target_tokens=100)
+        
+        # System message should be preserved
+        system_msgs = [m for m in result if m.get("role") == "system"]
+        assert len(system_msgs) >= 1
+    
+    def test_sliding_window_optimizer(self):
+        """Test sliding window keeps recent."""
+        from praisonaiagents.context.optimizer import SlidingWindowOptimizer
+        
+        # Create messages with enough content to exceed target
+        messages = [
+            {"role": "user", "content": f"Message {i} " * 50} 
+            for i in range(10)
+        ]
+        
+        optimizer = SlidingWindowOptimizer()
+        result, stats = optimizer.optimize(messages, target_tokens=100)
+        
+        # Should keep most recent messages (fewer than original)
+        assert len(result) <= len(messages)
+    
+    def test_prune_tools_optimizer(self):
+        """Test prune tools truncates old outputs."""
+        from praisonaiagents.context.optimizer import PruneToolsOptimizer
+        
+        messages = [
+            {"role": "user", "content": "Get weather"},
+            {"role": "assistant", "content": "", "tool_calls": [{"id": "1"}]},
+            {"role": "tool", "tool_call_id": "1", "content": "x" * 2000},
+            {"role": "user", "content": "Thanks"},
+            {"role": "assistant", "content": "You're welcome"},
+        ]
+        
+        optimizer = PruneToolsOptimizer(preserve_recent=2, max_output_chars=100)
+        result, stats = optimizer.optimize(messages, target_tokens=10000)
+        
+        # Tool output should be truncated
+        tool_msg = [m for m in result if m.get("role") == "tool"][0]
+        assert len(tool_msg["content"]) < 2000
+    
+    def test_prune_tools_protects_recent(self):
+        """Test prune tools protects recent outputs."""
+        from praisonaiagents.context.optimizer import PruneToolsOptimizer
+        
+        messages = [
+            {"role": "user", "content": "Get weather"},
+            {"role": "tool", "tool_call_id": "1", "content": "x" * 2000},
+        ]
+        
+        optimizer = PruneToolsOptimizer(preserve_recent=5)
+        result, stats = optimizer.optimize(messages, target_tokens=10000)
+        
+        # Recent should not be truncated
+        tool_msg = [m for m in result if m.get("role") == "tool"][0]
+        assert len(tool_msg["content"]) == 2000
+    
+    def test_non_destructive_optimizer(self):
+        """Test non-destructive tags messages."""
+        from praisonaiagents.context.optimizer import NonDestructiveOptimizer
+        
+        messages = [
+            {"role": "user", "content": f"Message {i}"} 
+            for i in range(10)
+        ]
+        
+        optimizer = NonDestructiveOptimizer(preserve_recent=3)
+        result, stats = optimizer.optimize(messages, target_tokens=50)
+        
+        # All messages should still be present
+        assert len(result) == len(messages)
+        
+        # Older messages should be tagged
+        tagged = [m for m in result if "_condense_parent" in m]
+        assert len(tagged) > 0
+        assert stats.messages_tagged > 0
+    
+    def test_summarize_optimizer(self):
+        """Test summarize creates summary."""
+        from praisonaiagents.context.optimizer import SummarizeOptimizer
+        
+        messages = [
+            {"role": "user", "content": f"Long message {i} " * 50} 
+            for i in range(10)
+        ]
+        
+        optimizer = SummarizeOptimizer(preserve_recent=3)
+        result, stats = optimizer.optimize(messages, target_tokens=100)
+        
+        # Should have summary message
+        assert stats.summary_added
+        summary_msgs = [m for m in result if m.get("_summary")]
+        assert len(summary_msgs) >= 1
+    
+    def test_smart_optimizer_combines_strategies(self):
+        """Test smart optimizer applies multiple strategies."""
+        from praisonaiagents.context.optimizer import SmartOptimizer
+        
+        messages = [
+            {"role": "user", "content": "Get data"},
+            {"role": "tool", "tool_call_id": "1", "content": "x" * 5000},
+        ]
+        messages.extend([
+            {"role": "user", "content": f"Message {i} " * 100} 
+            for i in range(10)
+        ])
+        
+        optimizer = SmartOptimizer()
+        result, stats = optimizer.optimize(messages, target_tokens=500)
+        
+        assert stats.optimized_tokens < stats.original_tokens
+    
+    def test_get_optimizer_factory(self):
+        """Test get_optimizer factory function."""
+        from praisonaiagents.context.optimizer import get_optimizer
+        from praisonaiagents.context.models import OptimizerStrategy
+        
+        for strategy in OptimizerStrategy:
+            optimizer = get_optimizer(strategy)
+            assert optimizer is not None
+    
+    def test_get_effective_history(self):
+        """Test get_effective_history filters tagged."""
+        from praisonaiagents.context.optimizer import get_effective_history
+        
+        messages = [
+            {"role": "user", "content": "Old", "_condense_parent": "abc"},
+            {"role": "user", "content": "Recent"},
+        ]
+        
+        effective = get_effective_history(messages)
+        
+        assert len(effective) == 1
+        assert effective[0]["content"] == "Recent"
+
+
+class TestOptimizationResult:
+    """Tests for OptimizationResult dataclass."""
+    
+    def test_reduction_percent(self):
+        """Test reduction percentage calculation."""
+        from praisonaiagents.context.models import OptimizationResult
+        
+        result = OptimizationResult(
+            original_tokens=1000,
+            optimized_tokens=600,
+            tokens_saved=400,
+        )
+        
+        assert result.reduction_percent == 40.0
+    
+    def test_reduction_percent_zero_original(self):
+        """Test reduction with zero original."""
+        from praisonaiagents.context.models import OptimizationResult
+        
+        result = OptimizationResult(original_tokens=0)
+        assert result.reduction_percent == 0.0

src/praisonai-agents/tests/unit/context/test_tokens.py

@@ -0,0 +1,184 @@
+"""Tests for token estimation module."""
+
+import pytest
+
+
+class TestTokenEstimation:
+    """Tests for token estimation functions."""
+    
+    def test_estimate_tokens_heuristic_empty(self):
+        """Test empty string returns 0."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        assert estimate_tokens_heuristic("") == 0
+    
+    def test_estimate_tokens_heuristic_ascii(self):
+        """Test ASCII text estimation."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        # ~4 chars per token for ASCII
+        text = "Hello world"  # 11 chars
+        tokens = estimate_tokens_heuristic(text)
+        assert 2 <= tokens <= 4  # Should be ~2-3 tokens
+    
+    def test_estimate_tokens_heuristic_long_text(self):
+        """Test longer text estimation."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        text = "a" * 400  # 400 ASCII chars
+        tokens = estimate_tokens_heuristic(text)
+        assert 90 <= tokens <= 110  # Should be ~100 tokens
+    
+    def test_estimate_tokens_heuristic_non_ascii(self):
+        """Test non-ASCII text has higher token count."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        ascii_text = "hello"
+        non_ascii_text = "你好世界"  # Chinese
+        
+        ascii_tokens = estimate_tokens_heuristic(ascii_text)
+        non_ascii_tokens = estimate_tokens_heuristic(non_ascii_text)
+        
+        # Non-ASCII should have higher token density
+        assert non_ascii_tokens > ascii_tokens
+    
+    def test_estimate_message_tokens_simple(self):
+        """Test simple message token estimation."""
+        from praisonaiagents.context.tokens import estimate_message_tokens
+        
+        msg = {"role": "user", "content": "Hello world"}
+        tokens = estimate_message_tokens(msg)
+        
+        # Should include role overhead + content
+        assert tokens > 0
+        assert tokens < 20
+    
+    def test_estimate_message_tokens_empty_content(self):
+        """Test message with empty content."""
+        from praisonaiagents.context.tokens import estimate_message_tokens
+        
+        msg = {"role": "user", "content": ""}
+        tokens = estimate_message_tokens(msg)
+        
+        # Should have role overhead
+        assert tokens >= 4
+    
+    def test_estimate_message_tokens_multipart(self):
+        """Test multipart content message."""
+        from praisonaiagents.context.tokens import estimate_message_tokens
+        
+        msg = {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Hello"},
+                {"type": "text", "text": "World"},
+            ]
+        }
+        tokens = estimate_message_tokens(msg)
+        assert tokens > 0
+    
+    def test_estimate_message_tokens_tool_call(self):
+        """Test message with tool calls."""
+        from praisonaiagents.context.tokens import estimate_message_tokens
+        
+        msg = {
+            "role": "assistant",
+            "content": "",
+            "tool_calls": [
+                {
+                    "id": "call_123",
+                    "function": {
+                        "name": "get_weather",
+                        "arguments": '{"location": "NYC"}'
+                    }
+                }
+            ]
+        }
+        tokens = estimate_message_tokens(msg)
+        assert tokens > 10  # Should include tool call overhead
+    
+    def test_estimate_messages_tokens_list(self):
+        """Test estimating tokens for message list."""
+        from praisonaiagents.context.tokens import estimate_messages_tokens
+        
+        messages = [
+            {"role": "system", "content": "You are helpful"},
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi there!"},
+        ]
+        tokens = estimate_messages_tokens(messages)
+        assert tokens > 0
+        assert tokens < 100
+    
+    def test_estimate_messages_tokens_empty(self):
+        """Test empty message list."""
+        from praisonaiagents.context.tokens import estimate_messages_tokens
+        assert estimate_messages_tokens([]) == 0
+    
+    def test_estimate_tool_schema_tokens(self):
+        """Test tool schema token estimation."""
+        from praisonaiagents.context.tokens import estimate_tool_schema_tokens
+        
+        tools = [
+            {
+                "type": "function",
+                "function": {
+                    "name": "get_weather",
+                    "description": "Get weather for a location",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {"type": "string"}
+                        }
+                    }
+                }
+            }
+        ]
+        tokens = estimate_tool_schema_tokens(tools)
+        assert tokens > 0
+    
+    def test_estimate_tool_schema_tokens_empty(self):
+        """Test empty tool list."""
+        from praisonaiagents.context.tokens import estimate_tool_schema_tokens
+        assert estimate_tool_schema_tokens([]) == 0
+    
+    def test_token_estimator_impl(self):
+        """Test TokenEstimatorImpl class."""
+        from praisonaiagents.context.tokens import TokenEstimatorImpl
+        
+        estimator = TokenEstimatorImpl(use_accurate=False)
+        
+        assert estimator.estimate("Hello") > 0
+        assert estimator.estimate_messages([{"role": "user", "content": "Hi"}]) > 0
+        assert estimator.estimate_tools([]) == 0
+    
+    def test_get_estimator(self):
+        """Test get_estimator factory."""
+        from praisonaiagents.context.tokens import get_estimator
+        
+        estimator = get_estimator(use_accurate=False)
+        assert estimator is not None
+        assert estimator.estimate("test") > 0
+
+
+class TestTokenEstimationAccuracy:
+    """Tests for estimation accuracy."""
+    
+    def test_consistency(self):
+        """Test that estimation is consistent."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        
+        text = "The quick brown fox jumps over the lazy dog"
+        
+        # Should return same value each time
+        result1 = estimate_tokens_heuristic(text)
+        result2 = estimate_tokens_heuristic(text)
+        assert result1 == result2
+    
+    def test_proportional_scaling(self):
+        """Test that longer text has more tokens."""
+        from praisonaiagents.context.tokens import estimate_tokens_heuristic
+        
+        short = "Hello"
+        long = "Hello " * 100
+        
+        short_tokens = estimate_tokens_heuristic(short)
+        long_tokens = estimate_tokens_heuristic(long)
+        
+        assert long_tokens > short_tokens * 50

src/praisonai-agents/tests/unit/rag/__init__.py

@@ -0,0 +1 @@
+"""Unit tests for RAG module."""

src/praisonai-agents/tests/unit/rag/test_context.py

@@ -0,0 +1,225 @@
+"""Tests for RAG context building utilities."""
+
+
+class TestEstimateTokens:
+    """Tests for token estimation."""
+    
+    def test_estimate_tokens_short(self):
+        """Test token estimation for short text."""
+        from praisonaiagents.rag.context import _estimate_tokens
+        
+        tokens = _estimate_tokens("Hello world")
+        assert tokens >= 2  # At least 2 tokens for 2 words
+    
+    def test_estimate_tokens_empty(self):
+        """Test token estimation for empty string."""
+        from praisonaiagents.rag.context import _estimate_tokens
+        
+        tokens = _estimate_tokens("")
+        assert tokens == 1  # Minimum 1
+
+
+class TestChunkHash:
+    """Tests for chunk hashing."""
+    
+    def test_chunk_hash_deterministic(self):
+        """Test that hash is deterministic."""
+        from praisonaiagents.rag.context import _chunk_hash
+        
+        hash1 = _chunk_hash("test content", "source.pdf")
+        hash2 = _chunk_hash("test content", "source.pdf")
+        assert hash1 == hash2
+    
+    def test_chunk_hash_different_content(self):
+        """Test that different content produces different hash."""
+        from praisonaiagents.rag.context import _chunk_hash
+        
+        hash1 = _chunk_hash("content A", "source.pdf")
+        hash2 = _chunk_hash("content B", "source.pdf")
+        assert hash1 != hash2
+    
+    def test_chunk_hash_different_source(self):
+        """Test that different source produces different hash."""
+        from praisonaiagents.rag.context import _chunk_hash
+        
+        hash1 = _chunk_hash("same content", "source1.pdf")
+        hash2 = _chunk_hash("same content", "source2.pdf")
+        assert hash1 != hash2
+
+
+class TestDeduplicateChunks:
+    """Tests for chunk deduplication."""
+    
+    def test_deduplicate_empty(self):
+        """Test deduplication of empty list."""
+        from praisonaiagents.rag.context import deduplicate_chunks
+        
+        result = deduplicate_chunks([])
+        assert result == []
+    
+    def test_deduplicate_no_duplicates(self):
+        """Test deduplication with no duplicates."""
+        from praisonaiagents.rag.context import deduplicate_chunks
+        
+        results = [
+            {"text": "Content A", "metadata": {"source": "a.pdf"}},
+            {"text": "Content B", "metadata": {"source": "b.pdf"}},
+        ]
+        deduped = deduplicate_chunks(results)
+        assert len(deduped) == 2
+    
+    def test_deduplicate_with_duplicates(self):
+        """Test deduplication removes duplicates."""
+        from praisonaiagents.rag.context import deduplicate_chunks
+        
+        results = [
+            {"text": "Same content", "metadata": {"source": "a.pdf"}},
+            {"text": "Same content", "metadata": {"source": "a.pdf"}},
+            {"text": "Different", "metadata": {"source": "b.pdf"}},
+        ]
+        deduped = deduplicate_chunks(results)
+        assert len(deduped) == 2
+    
+    def test_deduplicate_memory_format(self):
+        """Test deduplication with 'memory' key instead of 'text'."""
+        from praisonaiagents.rag.context import deduplicate_chunks
+        
+        results = [
+            {"memory": "Content A", "metadata": {}},
+            {"memory": "Content A", "metadata": {}},
+        ]
+        deduped = deduplicate_chunks(results)
+        assert len(deduped) == 1
+
+
+class TestTruncateContext:
+    """Tests for context truncation."""
+    
+    def test_truncate_short_text(self):
+        """Test that short text is not truncated."""
+        from praisonaiagents.rag.context import truncate_context
+        
+        text = "Short text"
+        result = truncate_context(text, max_tokens=100)
+        assert result == text
+    
+    def test_truncate_long_text(self):
+        """Test that long text is truncated."""
+        from praisonaiagents.rag.context import truncate_context
+        
+        text = "A" * 10000  # Very long text
+        result = truncate_context(text, max_tokens=100)
+        assert len(result) < len(text)
+        assert "[Context truncated...]" in result
+    
+    def test_truncate_custom_suffix(self):
+        """Test truncation with custom suffix."""
+        from praisonaiagents.rag.context import truncate_context
+        
+        text = "A" * 10000
+        result = truncate_context(text, max_tokens=100, suffix="...")
+        assert result.endswith("...")
+
+
+class TestBuildContext:
+    """Tests for context building."""
+    
+    def test_build_context_empty(self):
+        """Test building context from empty results."""
+        from praisonaiagents.rag.context import build_context
+        
+        context, used = build_context([])
+        assert context == ""
+        assert used == []
+    
+    def test_build_context_single(self):
+        """Test building context from single result."""
+        from praisonaiagents.rag.context import build_context
+        
+        results = [{"text": "Content here", "metadata": {"filename": "doc.pdf"}}]
+        context, used = build_context(results)
+        
+        assert "Content here" in context
+        assert "doc.pdf" in context
+        assert len(used) == 1
+    
+    def test_build_context_multiple(self):
+        """Test building context from multiple results."""
+        from praisonaiagents.rag.context import build_context
+        
+        results = [
+            {"text": "First chunk", "metadata": {"filename": "a.pdf"}},
+            {"text": "Second chunk", "metadata": {"filename": "b.pdf"}},
+        ]
+        context, used = build_context(results, separator="\n---\n")
+        
+        assert "First chunk" in context
+        assert "Second chunk" in context
+        assert len(used) == 2
+    
+    def test_build_context_respects_token_limit(self):
+        """Test that context respects token limit."""
+        from praisonaiagents.rag.context import build_context
+        
+        # Create results that exceed token limit
+        results = [
+            {"text": "A" * 1000, "metadata": {}},
+            {"text": "B" * 1000, "metadata": {}},
+            {"text": "C" * 1000, "metadata": {}},
+        ]
+        context, used = build_context(results, max_tokens=500)
+        
+        # Should not include all results
+        assert len(used) < 3
+    
+    def test_build_context_deduplicates(self):
+        """Test that context deduplicates by default."""
+        from praisonaiagents.rag.context import build_context
+        
+        results = [
+            {"text": "Same content", "metadata": {"source": "a.pdf"}},
+            {"text": "Same content", "metadata": {"source": "a.pdf"}},
+        ]
+        context, used = build_context(results, deduplicate=True)
+        
+        # Should only include once
+        assert context.count("Same content") == 1
+    
+    def test_build_context_no_source(self):
+        """Test building context without source info."""
+        from praisonaiagents.rag.context import build_context
+        
+        results = [{"text": "Content", "metadata": {}}]
+        context, used = build_context(results, include_source=False)
+        
+        assert "Content" in context
+        assert "[" not in context  # No source label
+
+
+class TestDefaultContextBuilder:
+    """Tests for DefaultContextBuilder class."""
+    
+    def test_default_builder_build(self):
+        """Test DefaultContextBuilder.build method."""
+        from praisonaiagents.rag.context import DefaultContextBuilder
+        
+        builder = DefaultContextBuilder()
+        results = [{"text": "Test content", "metadata": {"filename": "test.pdf"}}]
+        
+        context = builder.build(results, max_tokens=1000)
+        
+        assert "Test content" in context
+        assert "test.pdf" in context
+    
+    def test_default_builder_custom_separator(self):
+        """Test DefaultContextBuilder with custom separator."""
+        from praisonaiagents.rag.context import DefaultContextBuilder
+        
+        builder = DefaultContextBuilder(separator="\n\n")
+        results = [
+            {"text": "A", "metadata": {}},
+            {"text": "B", "metadata": {}},
+        ]
+        
+        context = builder.build(results)
+        assert "\n\n" in context

src/praisonai-agents/tests/unit/rag/test_imports.py

@@ -0,0 +1,122 @@
+"""Tests for RAG module import performance and lazy loading."""
+
+import time
+import sys
+
+
+class TestImportPerformance:
+    """Tests for import performance."""
+    
+    def test_rag_module_import_time(self):
+        """Test that RAG module imports quickly (< 100ms)."""
+        # Clear any cached imports
+        modules_to_clear = [k for k in sys.modules.keys() if 'praisonaiagents.rag' in k]
+        for mod in modules_to_clear:
+            del sys.modules[mod]
+        
+        start = time.time()
+        from praisonaiagents.rag import RAG, RAGConfig, RAGResult
+        elapsed = time.time() - start
+        
+        # Should import in under 100ms (generous for CI)
+        assert elapsed < 0.1, f"RAG import took {elapsed:.3f}s, expected < 0.1s"
+    
+    def test_no_heavy_deps_on_import(self):
+        """Test that importing RAG doesn't pull heavy dependencies."""
+        # Clear modules
+        modules_to_clear = [k for k in sys.modules.keys() if 'praisonaiagents.rag' in k]
+        for mod in modules_to_clear:
+            del sys.modules[mod]
+        
+        # Track loaded modules before
+        before = set(sys.modules.keys())
+        
+        # Import RAG
+        from praisonaiagents.rag import RAG, RAGConfig, Citation
+        
+        # Track loaded modules after
+        after = set(sys.modules.keys())
+        new_modules = after - before
+        
+        # These heavy modules should NOT be imported
+        heavy_deps = ['chromadb', 'torch', 'transformers', 'sentence_transformers', 
+                      'faiss', 'mem0', 'litellm']
+        
+        for dep in heavy_deps:
+            matching = [m for m in new_modules if dep in m]
+            assert not matching, f"Heavy dependency {dep} was imported: {matching}"
+    
+    def test_lazy_loading_works(self):
+        """Test that lazy loading mechanism works."""
+        from praisonaiagents.rag import __getattr__, _LAZY_IMPORTS
+        
+        # All expected exports should be in lazy imports
+        expected = ['RAG', 'RAGConfig', 'RAGResult', 'Citation', 
+                    'build_context', 'truncate_context', 'deduplicate_chunks']
+        
+        for name in expected:
+            assert name in _LAZY_IMPORTS, f"{name} not in lazy imports"
+
+
+class TestProtocolCompliance:
+    """Tests for protocol compliance."""
+    
+    def test_rag_protocol_compliance(self):
+        """Test that RAG class implements RAGProtocol."""
+        from praisonaiagents.rag.protocols import RAGProtocol
+        from praisonaiagents.rag.pipeline import RAG
+        from unittest.mock import MagicMock
+        
+        mock_knowledge = MagicMock()
+        rag = RAG(knowledge=mock_knowledge)
+        
+        # Check required methods exist
+        assert hasattr(rag, 'query')
+        assert hasattr(rag, 'aquery')
+        assert hasattr(rag, 'stream')
+        assert callable(rag.query)
+        assert callable(rag.aquery)
+        assert callable(rag.stream)
+    
+    def test_context_builder_protocol(self):
+        """Test ContextBuilderProtocol."""
+        from praisonaiagents.rag.protocols import ContextBuilderProtocol
+        from praisonaiagents.rag.context import DefaultContextBuilder
+        
+        builder = DefaultContextBuilder()
+        
+        # Should have build method
+        assert hasattr(builder, 'build')
+        assert callable(builder.build)
+    
+    def test_citation_formatter_protocol(self):
+        """Test CitationFormatterProtocol."""
+        from praisonaiagents.rag.protocols import CitationFormatterProtocol
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        
+        # Should have format method
+        assert hasattr(formatter, 'format')
+        assert callable(formatter.format)
+
+
+class TestMainPackageExports:
+    """Tests for main package exports."""
+    
+    def test_rag_in_all(self):
+        """Test that RAG is in __all__."""
+        import praisonaiagents
+        
+        assert 'RAG' in praisonaiagents.__all__
+        assert 'RAGConfig' in praisonaiagents.__all__
+        assert 'RAGResult' in praisonaiagents.__all__
+    
+    def test_rag_accessible_from_main(self):
+        """Test that RAG classes are accessible from main package."""
+        from praisonaiagents import RAG, RAGConfig, RAGResult
+        
+        # Should be the actual classes
+        assert RAG.__name__ == 'RAG'
+        assert RAGConfig.__name__ == 'RAGConfig'
+        assert RAGResult.__name__ == 'RAGResult'

src/praisonai-agents/tests/unit/rag/test_models.py

@@ -0,0 +1,229 @@
+"""Tests for RAG data models."""
+
+import pytest
+
+
+class TestCitation:
+    """Tests for Citation dataclass."""
+    
+    def test_citation_defaults(self):
+        """Test Citation with default values."""
+        from praisonaiagents.rag.models import Citation
+        
+        citation = Citation(id="1", source="test.pdf", text="Sample text")
+        
+        assert citation.id == "1"
+        assert citation.source == "test.pdf"
+        assert citation.text == "Sample text"
+        assert citation.score == 0.0
+        assert citation.doc_id is None
+        assert citation.chunk_id is None
+        assert citation.offset is None
+        assert citation.metadata == {}
+    
+    def test_citation_full(self):
+        """Test Citation with all values."""
+        from praisonaiagents.rag.models import Citation
+        
+        citation = Citation(
+            id="1",
+            source="doc.pdf",
+            text="Important finding",
+            score=0.95,
+            doc_id="doc123",
+            chunk_id="chunk456",
+            offset=100,
+            metadata={"page": 5}
+        )
+        
+        assert citation.score == 0.95
+        assert citation.doc_id == "doc123"
+        assert citation.metadata["page"] == 5
+    
+    def test_citation_to_dict(self):
+        """Test Citation serialization."""
+        from praisonaiagents.rag.models import Citation
+        
+        citation = Citation(id="1", source="test.pdf", text="Sample")
+        data = citation.to_dict()
+        
+        assert data["id"] == "1"
+        assert data["source"] == "test.pdf"
+        assert "metadata" in data
+    
+    def test_citation_from_dict(self):
+        """Test Citation deserialization."""
+        from praisonaiagents.rag.models import Citation
+        
+        data = {
+            "id": "2",
+            "source": "doc.pdf",
+            "text": "Content",
+            "score": 0.8,
+            "metadata": {"key": "value"}
+        }
+        citation = Citation.from_dict(data)
+        
+        assert citation.id == "2"
+        assert citation.score == 0.8
+        assert citation.metadata["key"] == "value"
+    
+    def test_citation_str(self):
+        """Test Citation string representation."""
+        from praisonaiagents.rag.models import Citation
+        
+        citation = Citation(id="1", source="test.pdf", text="Short text")
+        s = str(citation)
+        
+        assert "[1]" in s
+        assert "test.pdf" in s
+
+
+class TestRAGResult:
+    """Tests for RAGResult dataclass."""
+    
+    def test_rag_result_defaults(self):
+        """Test RAGResult with default values."""
+        from praisonaiagents.rag.models import RAGResult
+        
+        result = RAGResult(answer="The answer is 42.")
+        
+        assert result.answer == "The answer is 42."
+        assert result.citations == []
+        assert result.context_used == ""
+        assert result.query == ""
+        assert result.metadata == {}
+    
+    def test_rag_result_with_citations(self):
+        """Test RAGResult with citations."""
+        from praisonaiagents.rag.models import RAGResult, Citation
+        
+        citations = [
+            Citation(id="1", source="doc1.pdf", text="Evidence 1"),
+            Citation(id="2", source="doc2.pdf", text="Evidence 2"),
+        ]
+        result = RAGResult(
+            answer="Based on the evidence...",
+            citations=citations,
+            query="What is the answer?"
+        )
+        
+        assert len(result.citations) == 2
+        assert result.has_citations is True
+    
+    def test_rag_result_no_citations(self):
+        """Test has_citations property."""
+        from praisonaiagents.rag.models import RAGResult
+        
+        result = RAGResult(answer="No sources")
+        assert result.has_citations is False
+    
+    def test_rag_result_to_dict(self):
+        """Test RAGResult serialization."""
+        from praisonaiagents.rag.models import RAGResult, Citation
+        
+        result = RAGResult(
+            answer="Answer",
+            citations=[Citation(id="1", source="s", text="t")],
+            metadata={"elapsed": 0.5}
+        )
+        data = result.to_dict()
+        
+        assert data["answer"] == "Answer"
+        assert len(data["citations"]) == 1
+        assert data["metadata"]["elapsed"] == 0.5
+    
+    def test_rag_result_format_with_citations(self):
+        """Test formatting answer with citations."""
+        from praisonaiagents.rag.models import RAGResult, Citation
+        
+        result = RAGResult(
+            answer="The main finding is X.",
+            citations=[Citation(id="1", source="paper.pdf", text="X is important")]
+        )
+        formatted = result.format_answer_with_citations()
+        
+        assert "The main finding is X." in formatted
+        assert "Sources:" in formatted
+        assert "paper.pdf" in formatted
+
+
+class TestRAGConfig:
+    """Tests for RAGConfig dataclass."""
+    
+    def test_rag_config_defaults(self):
+        """Test RAGConfig default values."""
+        from praisonaiagents.rag.models import RAGConfig, RetrievalStrategy
+        
+        config = RAGConfig()
+        
+        assert config.top_k == 5
+        assert config.min_score == 0.0
+        assert config.max_context_tokens == 4000
+        assert config.include_citations is True
+        assert config.retrieval_strategy == RetrievalStrategy.BASIC
+        assert config.rerank is False
+        assert config.stream is False
+        assert "{context}" in config.template
+        assert "{question}" in config.template
+    
+    def test_rag_config_custom(self):
+        """Test RAGConfig with custom values."""
+        from praisonaiagents.rag.models import RAGConfig, RetrievalStrategy
+        
+        config = RAGConfig(
+            top_k=10,
+            min_score=0.5,
+            retrieval_strategy=RetrievalStrategy.HYBRID,
+            rerank=True,
+            rerank_top_k=5
+        )
+        
+        assert config.top_k == 10
+        assert config.min_score == 0.5
+        assert config.retrieval_strategy == RetrievalStrategy.HYBRID
+        assert config.rerank is True
+    
+    def test_rag_config_to_dict(self):
+        """Test RAGConfig serialization."""
+        from praisonaiagents.rag.models import RAGConfig
+        
+        config = RAGConfig(top_k=3)
+        data = config.to_dict()
+        
+        assert data["top_k"] == 3
+        assert data["retrieval_strategy"] == "basic"
+    
+    def test_rag_config_from_dict(self):
+        """Test RAGConfig deserialization."""
+        from praisonaiagents.rag.models import RAGConfig, RetrievalStrategy
+        
+        data = {
+            "top_k": 8,
+            "retrieval_strategy": "fusion",
+            "rerank": True
+        }
+        config = RAGConfig.from_dict(data)
+        
+        assert config.top_k == 8
+        assert config.retrieval_strategy == RetrievalStrategy.FUSION
+        assert config.rerank is True
+
+
+class TestRetrievalStrategy:
+    """Tests for RetrievalStrategy enum."""
+    
+    def test_strategy_values(self):
+        """Test strategy enum values."""
+        from praisonaiagents.rag.models import RetrievalStrategy
+        
+        assert RetrievalStrategy.BASIC.value == "basic"
+        assert RetrievalStrategy.FUSION.value == "fusion"
+        assert RetrievalStrategy.HYBRID.value == "hybrid"
+    
+    def test_strategy_from_string(self):
+        """Test creating strategy from string."""
+        from praisonaiagents.rag.models import RetrievalStrategy
+        
+        strategy = RetrievalStrategy("basic")
+        assert strategy == RetrievalStrategy.BASIC

src/praisonai-agents/tests/unit/rag/test_pipeline.py

@@ -0,0 +1,317 @@
+"""Tests for RAG pipeline."""
+
+from unittest.mock import MagicMock, patch
+
+
+class TestDefaultCitationFormatter:
+    """Tests for DefaultCitationFormatter."""
+    
+    def test_format_empty(self):
+        """Test formatting empty results."""
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        citations = formatter.format([])
+        assert citations == []
+    
+    def test_format_single_result(self):
+        """Test formatting single result."""
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        results = [
+            {
+                "text": "Important finding",
+                "score": 0.95,
+                "metadata": {"filename": "paper.pdf", "source": "/docs/paper.pdf"}
+            }
+        ]
+        citations = formatter.format(results)
+        
+        assert len(citations) == 1
+        assert citations[0].id == "1"
+        assert citations[0].source == "paper.pdf"
+        assert citations[0].score == 0.95
+    
+    def test_format_multiple_results(self):
+        """Test formatting multiple results."""
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        results = [
+            {"text": "A", "metadata": {"filename": "a.pdf"}},
+            {"text": "B", "metadata": {"filename": "b.pdf"}},
+            {"text": "C", "metadata": {"filename": "c.pdf"}},
+        ]
+        citations = formatter.format(results)
+        
+        assert len(citations) == 3
+        assert citations[0].id == "1"
+        assert citations[1].id == "2"
+        assert citations[2].id == "3"
+    
+    def test_format_with_start_id(self):
+        """Test formatting with custom start ID."""
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        results = [{"text": "Content", "metadata": {}}]
+        citations = formatter.format(results, start_id=5)
+        
+        assert citations[0].id == "5"
+    
+    def test_format_memory_key(self):
+        """Test formatting with 'memory' key instead of 'text'."""
+        from praisonaiagents.rag.pipeline import DefaultCitationFormatter
+        
+        formatter = DefaultCitationFormatter()
+        results = [{"memory": "Memory content", "metadata": {}}]
+        citations = formatter.format(results)
+        
+        assert citations[0].text == "Memory content"
+
+
+class TestRAGPipeline:
+    """Tests for RAG pipeline class."""
+    
+    def test_rag_init_defaults(self):
+        """Test RAG initialization with defaults."""
+        from praisonaiagents.rag.pipeline import RAG
+        from praisonaiagents.rag.models import RAGConfig
+        
+        mock_knowledge = MagicMock()
+        rag = RAG(knowledge=mock_knowledge)
+        
+        assert rag.knowledge == mock_knowledge
+        assert isinstance(rag.config, RAGConfig)
+        assert rag.reranker is None
+    
+    def test_rag_init_custom_config(self):
+        """Test RAG initialization with custom config."""
+        from praisonaiagents.rag.pipeline import RAG
+        from praisonaiagents.rag.models import RAGConfig
+        
+        mock_knowledge = MagicMock()
+        config = RAGConfig(top_k=10, rerank=True)
+        rag = RAG(knowledge=mock_knowledge, config=config)
+        
+        assert rag.config.top_k == 10
+        assert rag.config.rerank is True
+    
+    def test_rag_retrieve(self):
+        """Test RAG retrieval."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "Result 1", "score": 0.9, "metadata": {}},
+            {"text": "Result 2", "score": 0.8, "metadata": {}},
+        ]
+        
+        rag = RAG(knowledge=mock_knowledge)
+        results = rag._retrieve("test query")
+        
+        mock_knowledge.search.assert_called_once()
+        assert len(results) == 2
+    
+    def test_rag_retrieve_with_min_score(self):
+        """Test RAG retrieval filters by min_score."""
+        from praisonaiagents.rag.pipeline import RAG
+        from praisonaiagents.rag.models import RAGConfig
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "High", "score": 0.9, "metadata": {}},
+            {"text": "Low", "score": 0.3, "metadata": {}},
+        ]
+        
+        config = RAGConfig(min_score=0.5)
+        rag = RAG(knowledge=mock_knowledge, config=config)
+        results = rag._retrieve("test")
+        
+        assert len(results) == 1
+        assert results[0]["text"] == "High"
+    
+    def test_rag_retrieve_respects_top_k(self):
+        """Test RAG retrieval respects top_k limit."""
+        from praisonaiagents.rag.pipeline import RAG
+        from praisonaiagents.rag.models import RAGConfig
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": f"Result {i}", "score": 0.9, "metadata": {}}
+            for i in range(10)
+        ]
+        
+        config = RAGConfig(top_k=3)
+        rag = RAG(knowledge=mock_knowledge, config=config)
+        results = rag._retrieve("test")
+        
+        assert len(results) == 3
+    
+    def test_rag_build_prompt(self):
+        """Test RAG prompt building."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        rag = RAG(knowledge=mock_knowledge)
+        
+        prompt = rag._build_prompt("What is X?", "Context about X")
+        
+        assert "What is X?" in prompt
+        assert "Context about X" in prompt
+    
+    def test_rag_query_full_pipeline(self):
+        """Test full RAG query pipeline."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        # Mock knowledge
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "The answer is 42", "score": 0.95, "metadata": {"filename": "guide.pdf"}}
+        ]
+        
+        # Mock LLM
+        mock_llm = MagicMock()
+        mock_llm.get_response.return_value = "Based on the context, the answer is 42."
+        
+        rag = RAG(knowledge=mock_knowledge, llm=mock_llm)
+        result = rag.query("What is the answer?")
+        
+        assert "42" in result.answer
+        assert len(result.citations) == 1
+        assert result.citations[0].source == "guide.pdf"
+        assert result.query == "What is the answer?"
+        assert "elapsed_seconds" in result.metadata
+    
+    def test_rag_query_no_results(self):
+        """Test RAG query with no results."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = []
+        
+        mock_llm = MagicMock()
+        mock_llm.get_response.return_value = "I don't have information about that."
+        
+        rag = RAG(knowledge=mock_knowledge, llm=mock_llm)
+        result = rag.query("Unknown topic")
+        
+        assert result.citations == []
+        assert result.context_used == ""
+    
+    def test_rag_query_with_reranker(self):
+        """Test RAG query with reranker."""
+        from praisonaiagents.rag.pipeline import RAG
+        from praisonaiagents.rag.models import RAGConfig
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "A", "score": 0.7, "metadata": {}},
+            {"text": "B", "score": 0.8, "metadata": {}},
+        ]
+        
+        mock_reranker = MagicMock()
+        mock_reranker.rerank.return_value = [
+            {"text": "B", "score": 0.95, "metadata": {}},
+            {"text": "A", "score": 0.6, "metadata": {}},
+        ]
+        
+        mock_llm = MagicMock()
+        mock_llm.chat.return_value = "Answer"
+        
+        config = RAGConfig(rerank=True)
+        rag = RAG(knowledge=mock_knowledge, llm=mock_llm, config=config, reranker=mock_reranker)
+        result = rag.query("Test")
+        
+        mock_reranker.rerank.assert_called_once()
+        assert result.metadata["reranked"] is True
+    
+    def test_rag_get_citations(self):
+        """Test getting citations without generating answer."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "Content", "score": 0.9, "metadata": {"filename": "doc.pdf"}}
+        ]
+        
+        rag = RAG(knowledge=mock_knowledge)
+        citations = rag.get_citations("Query")
+        
+        assert len(citations) == 1
+        assert citations[0].source == "doc.pdf"
+    
+    def test_rag_stream_fallback(self):
+        """Test RAG streaming with fallback to non-streaming."""
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "Context", "metadata": {}}
+        ]
+        
+        mock_llm = MagicMock()
+        mock_llm.get_response.return_value = "Word1 Word2 Word3"
+        # No stream method, should fallback
+        del mock_llm.stream
+        
+        rag = RAG(knowledge=mock_knowledge, llm=mock_llm)
+        chunks = list(rag.stream("Question"))
+        
+        assert len(chunks) > 0
+        assert "Word1" in "".join(chunks)
+
+
+class TestRAGAsync:
+    """Tests for RAG async methods."""
+    
+    def test_aquery(self):
+        """Test async query."""
+        import asyncio
+        from praisonaiagents.rag.pipeline import RAG
+        
+        mock_knowledge = MagicMock()
+        mock_knowledge.search.return_value = [
+            {"text": "Async content", "metadata": {}}
+        ]
+        
+        mock_llm = MagicMock()
+        mock_llm.get_response.return_value = "Async answer"
+        
+        rag = RAG(knowledge=mock_knowledge, llm=mock_llm)
+        
+        async def run_test():
+            result = await rag.aquery("Async question")
+            return result
+        
+        result = asyncio.run(run_test())
+        assert "Async answer" in result.answer
+
+
+class TestRAGImports:
+    """Tests for RAG module imports."""
+    
+    def test_lazy_import_rag(self):
+        """Test that RAG can be imported from main package."""
+        from praisonaiagents import RAG
+        assert RAG is not None
+    
+    def test_lazy_import_rag_config(self):
+        """Test that RAGConfig can be imported from main package."""
+        from praisonaiagents import RAGConfig
+        assert RAGConfig is not None
+    
+    def test_lazy_import_rag_result(self):
+        """Test that RAGResult can be imported from main package."""
+        from praisonaiagents import RAGResult
+        assert RAGResult is not None
+    
+    def test_import_from_rag_module(self):
+        """Test direct import from rag module."""
+        from praisonaiagents.rag import RAG, RAGConfig, RAGResult, Citation
+        
+        assert RAG is not None
+        assert RAGConfig is not None
+        assert RAGResult is not None
+        assert Citation is not None

src/praisonai-agents/tests/unit/rag/test_retrieval_config.py

@@ -0,0 +1,311 @@
+"""
+Tests for RetrievalConfig - Unified retrieval configuration.
+
+Tests cover:
+1. RetrievalConfig creation and defaults
+2. Policy-based retrieval decisions
+3. Conversion to knowledge_config and rag_config
+4. Legacy config migration
+5. Heuristic-based auto retrieval
+"""
+
+import pytest
+from praisonaiagents.rag.retrieval_config import (
+    RetrievalConfig,
+    RetrievalPolicy,
+    CitationsMode,
+    create_retrieval_config,
+)
+
+
+class TestRetrievalConfigDefaults:
+    """Test default values for RetrievalConfig."""
+    
+    def test_default_values(self):
+        """Test that default values are set correctly."""
+        config = RetrievalConfig()
+        
+        assert config.enabled is True
+        assert config.policy == RetrievalPolicy.AUTO
+        assert config.top_k == 5
+        assert config.min_score == 0.0
+        assert config.max_context_tokens == 4000
+        assert config.rerank is False
+        assert config.hybrid is False
+        assert config.citations is True
+        assert config.citations_mode == CitationsMode.APPEND
+        assert config.vector_store_provider == "chroma"
+        assert config.auto_min_length == 10
+        assert config.system_separation is True
+    
+    def test_custom_values(self):
+        """Test custom values are preserved."""
+        config = RetrievalConfig(
+            enabled=False,
+            policy=RetrievalPolicy.ALWAYS,
+            top_k=10,
+            min_score=0.5,
+            max_context_tokens=8000,
+            rerank=True,
+            hybrid=True,
+            citations=False,
+            citations_mode=CitationsMode.HIDDEN,
+        )
+        
+        assert config.enabled is False
+        assert config.policy == RetrievalPolicy.ALWAYS
+        assert config.top_k == 10
+        assert config.min_score == 0.5
+        assert config.max_context_tokens == 8000
+        assert config.rerank is True
+        assert config.hybrid is True
+        assert config.citations is False
+        assert config.citations_mode == CitationsMode.HIDDEN
+
+
+class TestRetrievalPolicy:
+    """Test retrieval policy decisions."""
+    
+    def test_policy_always(self):
+        """Test ALWAYS policy always retrieves."""
+        config = RetrievalConfig(policy=RetrievalPolicy.ALWAYS)
+        
+        assert config.should_retrieve("hi") is True
+        assert config.should_retrieve("") is True
+        assert config.should_retrieve("what is the answer?") is True
+    
+    def test_policy_never(self):
+        """Test NEVER policy never retrieves."""
+        config = RetrievalConfig(policy=RetrievalPolicy.NEVER)
+        
+        assert config.should_retrieve("what is the answer?") is False
+        assert config.should_retrieve("explain this document") is False
+    
+    def test_policy_auto_with_keywords(self):
+        """Test AUTO policy retrieves for keyword queries."""
+        config = RetrievalConfig(policy=RetrievalPolicy.AUTO)
+        
+        # Should retrieve - contains keywords
+        assert config.should_retrieve("what is the main finding?") is True
+        assert config.should_retrieve("explain the concept") is True
+        assert config.should_retrieve("how does this work?") is True
+        assert config.should_retrieve("find the relevant section") is True
+    
+    def test_policy_auto_with_question_mark(self):
+        """Test AUTO policy retrieves for questions."""
+        config = RetrievalConfig(policy=RetrievalPolicy.AUTO)
+        
+        assert config.should_retrieve("is this correct?") is True
+        assert config.should_retrieve("can you help?") is True
+    
+    def test_policy_auto_short_queries(self):
+        """Test AUTO policy skips short queries."""
+        config = RetrievalConfig(policy=RetrievalPolicy.AUTO, auto_min_length=10)
+        
+        assert config.should_retrieve("hi") is False
+        assert config.should_retrieve("hello") is False
+        assert config.should_retrieve("ok") is False
+    
+    def test_force_retrieval(self):
+        """Test force_retrieval overrides policy."""
+        config = RetrievalConfig(policy=RetrievalPolicy.NEVER)
+        
+        assert config.should_retrieve("hi", force=True) is True
+    
+    def test_skip_retrieval(self):
+        """Test skip_retrieval overrides policy."""
+        config = RetrievalConfig(policy=RetrievalPolicy.ALWAYS)
+        
+        assert config.should_retrieve("what is the answer?", skip=True) is False
+    
+    def test_disabled_config(self):
+        """Test disabled config never retrieves."""
+        config = RetrievalConfig(enabled=False, policy=RetrievalPolicy.ALWAYS)
+        
+        assert config.should_retrieve("what is the answer?") is False
+        assert config.should_retrieve("what is the answer?", force=True) is False
+
+
+class TestConfigConversion:
+    """Test conversion to knowledge_config and rag_config."""
+    
+    def test_to_knowledge_config(self):
+        """Test conversion to Knowledge-compatible config."""
+        config = RetrievalConfig(
+            vector_store_provider="chroma",
+            persist_path=".praison/test",
+            collection_name="test_collection",
+        )
+        
+        knowledge_config = config.to_knowledge_config()
+        
+        assert knowledge_config["vector_store"]["provider"] == "chroma"
+        assert knowledge_config["vector_store"]["config"]["path"] == ".praison/test"
+        assert knowledge_config["vector_store"]["config"]["collection_name"] == "test_collection"
+    
+    def test_to_knowledge_config_with_rerank(self):
+        """Test rerank is included in knowledge config."""
+        config = RetrievalConfig(rerank=True)
+        
+        knowledge_config = config.to_knowledge_config()
+        
+        assert "reranker" in knowledge_config
+        assert knowledge_config["reranker"]["enabled"] is True
+    
+    def test_to_rag_config(self):
+        """Test conversion to RAG pipeline config."""
+        config = RetrievalConfig(
+            top_k=10,
+            min_score=0.5,
+            max_context_tokens=8000,
+            citations=True,
+            hybrid=True,
+            rerank=True,
+        )
+        
+        rag_config = config.to_rag_config()
+        
+        assert rag_config["top_k"] == 10
+        assert rag_config["min_score"] == 0.5
+        assert rag_config["max_context_tokens"] == 8000
+        assert rag_config["include_citations"] is True
+        assert rag_config["rerank"] is True
+
+
+class TestLegacyConfigMigration:
+    """Test migration from legacy knowledge_config and rag_config."""
+    
+    def test_create_from_knowledge_config(self):
+        """Test creation from legacy knowledge_config."""
+        knowledge_config = {
+            "vector_store": {
+                "provider": "mongodb",
+                "config": {
+                    "collection_name": "my_collection",
+                    "path": ".praison/custom",
+                }
+            }
+        }
+        
+        config = create_retrieval_config(knowledge_config=knowledge_config)
+        
+        assert config.vector_store_provider == "mongodb"
+        assert config.collection_name == "my_collection"
+        assert config.persist_path == ".praison/custom"
+    
+    def test_create_from_rag_config(self):
+        """Test creation from legacy rag_config."""
+        rag_config = {
+            "top_k": 10,
+            "min_score": 0.3,
+            "max_context_tokens": 6000,
+            "include_citations": True,
+            "rerank": True,
+            "retrieval_strategy": "hybrid",
+        }
+        
+        config = create_retrieval_config(rag_config=rag_config)
+        
+        assert config.top_k == 10
+        assert config.min_score == 0.3
+        assert config.max_context_tokens == 6000
+        assert config.citations is True
+        assert config.rerank is True
+        assert config.hybrid is True
+    
+    def test_create_from_merged_configs(self):
+        """Test creation from both legacy configs merged."""
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {"collection_name": "merged"}
+            }
+        }
+        rag_config = {
+            "top_k": 15,
+            "rerank": True,
+        }
+        
+        config = create_retrieval_config(
+            knowledge_config=knowledge_config,
+            rag_config=rag_config,
+        )
+        
+        assert config.collection_name == "merged"
+        assert config.top_k == 15
+        assert config.rerank is True
+    
+    def test_create_from_retrieval_config_passthrough(self):
+        """Test that RetrievalConfig instance is passed through."""
+        original = RetrievalConfig(top_k=20)
+        
+        result = create_retrieval_config(retrieval_config=original)
+        
+        assert result is original
+    
+    def test_create_from_retrieval_config_dict(self):
+        """Test creation from retrieval_config dict."""
+        config_dict = {
+            "top_k": 25,
+            "policy": "always",
+            "citations_mode": "inline",
+        }
+        
+        config = create_retrieval_config(retrieval_config=config_dict)
+        
+        assert config.top_k == 25
+        assert config.policy == RetrievalPolicy.ALWAYS
+        assert config.citations_mode == CitationsMode.INLINE
+
+
+class TestSerialization:
+    """Test serialization and deserialization."""
+    
+    def test_to_dict(self):
+        """Test conversion to dictionary."""
+        config = RetrievalConfig(
+            policy=RetrievalPolicy.ALWAYS,
+            top_k=10,
+            citations_mode=CitationsMode.INLINE,
+        )
+        
+        data = config.to_dict()
+        
+        assert data["policy"] == "always"
+        assert data["top_k"] == 10
+        assert data["citations_mode"] == "inline"
+    
+    def test_from_dict(self):
+        """Test creation from dictionary."""
+        data = {
+            "policy": "never",
+            "top_k": 15,
+            "citations_mode": "hidden",
+            "rerank": True,
+        }
+        
+        config = RetrievalConfig.from_dict(data)
+        
+        assert config.policy == RetrievalPolicy.NEVER
+        assert config.top_k == 15
+        assert config.citations_mode == CitationsMode.HIDDEN
+        assert config.rerank is True
+    
+    def test_roundtrip(self):
+        """Test serialization roundtrip."""
+        original = RetrievalConfig(
+            policy=RetrievalPolicy.ALWAYS,
+            top_k=20,
+            min_score=0.7,
+            hybrid=True,
+            citations_mode=CitationsMode.INLINE,
+        )
+        
+        data = original.to_dict()
+        restored = RetrievalConfig.from_dict(data)
+        
+        assert restored.policy == original.policy
+        assert restored.top_k == original.top_k
+        assert restored.min_score == original.min_score
+        assert restored.hybrid == original.hybrid
+        assert restored.citations_mode == original.citations_mode

src/praisonai-agents/tests/unit/session/test_session_store.py

@@ -133,18 +133,21 @@ class TestFileLock:
         with tempfile.TemporaryDirectory() as tmpdir:
             filepath = os.path.join(tmpdir, "test.json")
             results = []
+            lock_obj = threading.Lock()  # For thread-safe list append
             
             def worker(worker_id):
-                with FileLock(filepath, timeout=5.0):
-                    results.append(f"start-{worker_id}")
-                    time.sleep(0.1)
-                    results.append(f"end-{worker_id}")
+                with FileLock(filepath, timeout=10.0):
+                    with lock_obj:
+                        results.append(f"start-{worker_id}")
+                    time.sleep(0.05)  # Reduced sleep for faster test
+                    with lock_obj:
+                        results.append(f"end-{worker_id}")
             
             threads = [threading.Thread(target=worker, args=(i,)) for i in range(3)]
             for t in threads:
                 t.start()
             for t in threads:
-                t.join()
+                t.join(timeout=15.0)  # Add timeout to prevent hanging
             
             # Check that starts and ends are paired (no interleaving)
             for i in range(3):

src/praisonai-agents/tests/unit/test_advanced_features.py

@@ -230,12 +230,12 @@ class TestModelSwitching:
         from praisonaiagents.agent import Agent
         
         agent = Agent(instructions="Test", llm="gpt-4o-mini")
-        original_llm = agent._llm_instance
+        original_llm = getattr(agent, 'llm_instance', None) or getattr(agent, '_llm_instance', None)
         
         agent.switch_model("gpt-4o")
         
-        # LLM instance should be recreated
-        assert agent._llm_instance != original_llm or agent.llm == "gpt-4o"
+        # LLM model should be updated
+        assert agent.llm == "gpt-4o"
 
 
 # ============================================================================
@@ -395,7 +395,8 @@ class TestLSPDiagnostics:
         with patch.object(hook, '_get_lsp_diagnostics', return_value=mock_diagnostics):
             diagnostics = hook.on_file_edit("/path/to/file.py")
             assert len(diagnostics) == 1
-            assert diagnostics[0]["severity"] == "error"
+            # Diagnostic is an object, not a dict
+            assert diagnostics[0].severity == "error"
 
 
 # ============================================================================

src/praisonai-agents/tests/unit/test_lazy_imports.py

@@ -9,9 +9,9 @@ import pytest
 
 
 def clear_modules():
-    """Clear all praisonai and litellm related modules from cache."""
+    """Clear all praisonai, litellm, and requests related modules from cache."""
     to_remove = [m for m in list(sys.modules.keys()) 
-                 if 'praison' in m or 'litellm' in m]
+                 if 'praison' in m or 'litellm' in m or m == 'requests' or m.startswith('requests.')]
     for mod in to_remove:
         del sys.modules[mod]
 
@@ -59,14 +59,13 @@ class TestLazyImports:
         assert hasattr(Agent, 'chat')
     
     def test_session_available_via_getattr(self):
-        """Session should be available via lazy loading.
+        """Session should be available via lazy loading."""
+        import praisonaiagents
         
-        NOTE: Currently skipped due to session.py/session/ naming conflict.
-        The Session class in session.py uses relative imports that don't work
-        when loaded dynamically to avoid the package conflict.
-        """
-        import pytest
-        pytest.skip("Session import has naming conflict with session/ directory")
+        # Access Session - this triggers lazy loading
+        Session = praisonaiagents.Session
+        
+        assert Session is not None
     
     def test_knowledge_available_via_getattr(self):
         """Knowledge should be available via lazy loading."""
@@ -98,12 +97,7 @@ class TestLazyImports:
         """All items in __all__ should be accessible."""
         import praisonaiagents
         
-        # Skip Session due to naming conflict with session/ directory
-        skip_items = {"Session"}
-        
         for name in praisonaiagents.__all__:
-            if name in skip_items:
-                continue
             # Some items may be None if optional deps not installed
             try:
                 _ = getattr(praisonaiagents, name)

src/praisonai-agents/uv.lock

@@ -2422,7 +2422,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.6.4"
+version = "0.7.1"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

src/praisonai/.gitignore

@@ -1 +1,2 @@
-chainlit.md
+chainlit.md
+tests/fixtures

src/praisonai/README.md

@@ -36,10 +36,10 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 ---
 
 > **Quick Paths:**
-> - 🚀 **New here?** → [Quick Start](#-quick-start)
+> - 🆕 **New here?** → [Quick Start](#-quick-start) *(1 minute to first agent)*
 > - 📦 **Installing?** → [Installation](#-installation)
-> - 💻 **Python SDK?** → [Python Examples](#-using-python-code)
-> - 🎯 **CLI user?** → [CLI Reference](#-cli--no-code-interface)
+> - 🐍 **Python SDK?** → [Python Examples](#-using-python-code)
+> - 🎯 **CLI user?** → [CLI Quick Reference](#cli-quick-reference)
 > - 🔧 **Need config?** → [Configuration](#-configuration--integration)
 > - 🤝 **Contributing?** → [Development](#-development)
 
@@ -47,96 +47,81 @@ PraisonAI is a production-ready Multi-AI Agents framework with self-reflection,
 
 ## 📑 Table of Contents
 
-### Getting Started
-- [⚡ Performance](#-performance)
+<details open>
+<summary><strong>Getting Started</strong></summary>
+
 - [🚀 Quick Start](#-quick-start)
 - [📦 Installation](#-installation)
-  - [Python SDK](#python-sdk)
-  - [JavaScript SDK](#javascript-sdk)
-  - [Environment Variables](#environment-variables)
+- [⚡ Performance](#-performance)
 
-### Core Concepts
-- [✨ Key Features](#-key-features)
-- [🌐 Supported Providers](#-supported-providers)
+</details>
+
+<details>
+<summary><strong>Python SDK</strong></summary>
 
-### Python SDK
 - [📘 Python Examples](#-using-python-code)
-  - [1. Single Agent](#1-single-agent)
-  - [2. Multi Agents](#2-multi-agents)
-  - [3. Planning Mode](#3-agent-with-planning-mode)
-  - [4. Deep Research](#4-deep-research-agent)
-  - [5. Query Rewriter](#5-query-rewriter-agent)
-  - [6. Agent Memory](#6-agent-memory-zero-dependencies)
-  - [7. Rules & Instructions](#7-rules--instructions)
-  - [8. Auto-Generated Memories](#8-auto-generated-memories)
-  - [9. Agentic Workflows](#9-agentic-workflows)
-  - [10. Hooks](#10-hooks)
-  - [11. Shadow Git Checkpoints](#11-shadow-git-checkpoints)
-  - [12. Background Tasks](#12-background-tasks)
-  - [13. Policy Engine](#13-policy-engine)
-  - [14. Thinking Budgets](#14-thinking-budgets)
-  - [15. Output Styles](#15-output-styles)
-  - [16. Context Compaction](#16-context-compaction)
-  - [17. Field Names Reference](#17-field-names-reference-a-i-g-s)
-  - [18. Extended agents.yaml](#18-extended-agentsyaml-with-workflow-patterns)
-  - [19. MCP Protocol](#19-mcp-model-context-protocol)
-  - [20. A2A Protocol](#20-a2a-agent2agent-protocol)
+  - [1. Single Agent](#1-single-agent) | [2. Multi Agents](#2-multi-agents) | [3. Planning Mode](#3-agent-with-planning-mode)
+  - [4. Deep Research](#4-deep-research-agent) | [5. Query Rewriter](#5-query-rewriter-agent) | [6. Agent Memory](#6-agent-memory-zero-dependencies)
+  - [7. Rules & Instructions](#7-rules--instructions) | [8. Auto-Generated Memories](#8-auto-generated-memories) | [9. Agentic Workflows](#9-agentic-workflows)
+  - [10. Hooks](#10-hooks) | [11. Shadow Git Checkpoints](#11-shadow-git-checkpoints) | [12. Background Tasks](#12-background-tasks)
+  - [13. Policy Engine](#13-policy-engine) | [14. Thinking Budgets](#14-thinking-budgets) | [15. Output Styles](#15-output-styles)
+  - [16. Context Compaction](#16-context-compaction) | [17. Field Names Reference](#17-field-names-reference-a-i-g-s) | [18. Extended agents.yaml](#18-extended-agentsyaml-with-workflow-patterns)
+  - [19. MCP Protocol](#19-mcp-model-context-protocol) | [20. A2A Protocol](#20-a2a-agent2agent-protocol)
 - [🛠️ Custom Tools](#️-custom-tools)
 
-### JavaScript SDK
+</details>
+
+<details>
+<summary><strong>JavaScript SDK</strong></summary>
+
 - [💻 JavaScript Examples](#-using-javascript-code)
 
-### CLI Reference
-- [🎯 CLI Overview](#-cli--no-code-interface)
-  - [Auto Mode](#auto-mode)
-  - [Interactive Mode](#interactive-mode-cli)
-  - [Deep Research CLI](#deep-research-cli)
-  - [Planning Mode CLI](#planning-mode-cli)
-  - [Memory CLI](#memory-cli)
-  - [Workflow CLI](#workflow-cli)
-  - [Knowledge CLI](#knowledge-cli)
-  - [Session CLI](#session-cli)
-  - [Tools CLI](#tools-cli)
-  - [MCP Config CLI](#mcp-config-cli)
-  - [External Agents CLI](#external-agents-cli)
-- [CLI Features Summary](#cli-features)
+</details>
 
-### Configuration
-- [🔧 Configuration & Integration](#-configuration--integration)
-  - [Ollama Integration](#ollama-integration)
-  - [Groq Integration](#groq-integration)
-  - [100+ Models Support](#100-models-support)
+<details>
+<summary><strong>CLI Reference</strong></summary>
+
+- [🎯 CLI Overview](#-cli--no-code-interface) | [CLI Quick Reference](#cli-quick-reference)
+- [Auto Mode](#auto-mode) | [Interactive Mode](#interactive-mode-cli) | [Deep Research CLI](#deep-research-cli) | [Planning Mode CLI](#planning-mode-cli)
+- [Memory CLI](#memory-cli) | [Workflow CLI](#workflow-cli) | [Knowledge CLI](#knowledge-cli) | [Session CLI](#session-cli)
+- [Tools CLI](#tools-cli) | [MCP Config CLI](#mcp-config-cli) | [External Agents CLI](#external-agents-cli) | [CLI Features Summary](#cli-features)
+
+</details>
+
+<details>
+<summary><strong>Configuration & Features</strong></summary>
+
+- [✨ Key Features](#-key-features) | [🌐 Supported Providers](#-supported-providers)
+- [🔧 Configuration & Integration](#-configuration--integration) | [Ollama](#ollama-integration) | [Groq](#groq-integration) | [100+ Models](#100-models-support)
 - [📋 Agents Playbook](#-agents-playbook)
-
-### Advanced Features
 - [🔬 Advanced Features](#-advanced-features)
-  - [Research & Intelligence](#research--intelligence)
-  - [Memory & Caching](#memory--caching)
-  - [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)
 
-### Architecture
+</details>
+
+<details>
+<summary><strong>Architecture & Patterns</strong></summary>
+
 - [📊 Process Types & Patterns](#-process-types--patterns)
-  - [Sequential Process](#sequential-process)
-  - [Hierarchical Process](#hierarchical-process)
-  - [Workflow Process](#workflow-process)
-  - [Agentic Patterns](#agentic-patterns)
+- [Sequential](#sequential-process) | [Hierarchical](#hierarchical-process) | [Workflow](#workflow-process) | [Agentic Patterns](#agentic-patterns)
+
+</details>
+
+<details>
+<summary><strong>Data & Persistence</strong></summary>
 
-### Data & Persistence
 - [💾 Persistence (Databases)](#-persistence-databases)
 - [📚 Knowledge & Retrieval (RAG)](#-knowledge--retrieval-rag)
 - [🔧 Tools Table](#-tools-table)
 
-### Learning & Community
-- [🎓 Video Tutorials](#-video-tutorials)
-- [⭐ Star History](#-star-history)
-- [👥 Contributing](#-contributing)
-- [🔧 Development](#-development)
-- [❓ FAQ & Troubleshooting](#-faq--troubleshooting)
+</details>
+
+<details>
+<summary><strong>Learning & Community</strong></summary>
+
+- [🎓 Video Tutorials](#-video-tutorials) | [⭐ Star History](#-star-history)
+- [👥 Contributing](#-contributing) | [🔧 Development](#-development) | [❓ FAQ & Troubleshooting](#-faq--troubleshooting)
+
+</details>
 
 ---
 
@@ -181,6 +166,8 @@ export OPENAI_API_KEY=your_key_here
 python -c "from praisonaiagents import Agent; Agent(instructions='You are a helpful AI assistant').start('Write a haiku about AI')"
 ```
 
+> **Next Steps:** [Single Agent Example](#1-single-agent) | [Multi Agents](#2-multi-agents) | [CLI Auto Mode](#auto-mode)
+
 ---
 
 ## 📦 Installation
@@ -231,28 +218,6 @@ export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 
 ---
 
-## 💻 Usage
-
-### Python Code Examples
-
-- [📘 Complete Python Examples](#using-python-code)
-- [🔧 Custom Tools](#️-custom-tools)
-- [🧠 Memory Configuration](#-memory--context)
-
-### CLI / No-Code Interface
-
-- [🎯 Auto Mode](#auto-mode)
-- [🔬 Deep Research](#deep-research-cli)
-- [📋 Planning Mode](#planning-mode-cli)
-- [💾 Memory Management](#memory-cli)
-- [🔄 Workflow Execution](#workflow-cli)
-
-### JavaScript Code Examples
-
-- [💻 JavaScript Usage](#using-javascript-code)
-
----
-
 ## ✨ Key Features
 
 <details open>
@@ -519,6 +484,9 @@ export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 
 PraisonAI supports 100+ LLM providers through seamless integration:
 
+<details>
+<summary><strong>View all 24 providers</strong></summary>
+
 | Provider | Example |
 |----------|:-------:|
 | OpenAI | [Example](examples/python/providers/openai/openai_gpt4_example.py) |
@@ -546,17 +514,12 @@ PraisonAI supports 100+ LLM providers through seamless integration:
 | Moonshot | [Example](examples/python/providers/moonshot/moonshot_example.py) |
 | vLLM | [Example](examples/python/providers/vllm/vllm_example.py) |
 
+</details>
+
 ---
 
 ## 📘 Using Python Code
 
-Light weight package dedicated for coding:
-
-```bash
-pip install praisonaiagents
-export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
-```
-
 ### 1. Single Agent
 
 Create app.py file and add the code below:
@@ -2405,6 +2368,9 @@ agent.start('Write a movie script about a robot in Mars');
 
 ## 📊 Process Types & Patterns
 
+<details>
+<summary><strong>View architecture diagrams and workflow patterns</strong></summary>
+
 ### AI Agents Flow
 
 ```mermaid
@@ -2744,6 +2710,8 @@ flowchart LR
     style Out fill:#8B0000,color:#fff
 ```
 
+</details>
+
 ---
 
 ## 🔧 Configuration & Integration
@@ -2891,77 +2859,179 @@ PraisonAI provides zero-dependency persistent memory for agents. For detailed ex
 
 PraisonAI provides a complete knowledge stack for building RAG applications with multiple vector stores, retrieval strategies, rerankers, and query modes.
 
+### RAG Quickstart (Agent-first)
+
+```python
+from praisonaiagents import Agent
+from praisonaiagents.rag.models import RetrievalStrategy
+
+# Agent with RAG - simplest approach
+agent = Agent(
+    name="Research Assistant",
+    knowledge=["docs/manual.pdf", "data/faq.txt"],
+    knowledge_config={"vector_store": {"provider": "chroma"}},
+    rag_config={
+        "include_citations": True,
+        "retrieval_strategy": RetrievalStrategy.HYBRID,  # Dense + BM25
+        "rerank": True,
+    }
+)
+
+# Query with citations
+result = agent.rag_query("How do I authenticate?")
+print(result.answer)
+for citation in result.citations:
+    print(f"  [{citation.id}] {citation.source}")
+```
+
+### RAG CLI Commands
+
+| Command | Description |
+|---------|-------------|
+| `praisonai rag query "<question>"` | One-shot question answering with citations |
+| `praisonai rag chat` | Interactive RAG chat session |
+| `praisonai rag serve` | Start RAG as a microservice API |
+| `praisonai rag eval <test_file>` | Evaluate RAG retrieval quality |
+
+### RAG CLI Examples
+
+```bash
+# Query with hybrid retrieval (dense + BM25 keyword search)
+praisonai rag query "What are the key findings?" --hybrid
+
+# Query with hybrid + reranking for best quality
+praisonai rag query "Summarize conclusions" --hybrid --rerank
+
+# Interactive chat with hybrid retrieval
+praisonai rag chat --collection research --hybrid --rerank
+
+# Start API server with OpenAI-compatible endpoint
+praisonai rag serve --hybrid --rerank --openai-compat --port 8080
+
+# Query with profiling
+praisonai rag query "Summary?" --profile --profile-out ./profile.json
+```
+
 ### Knowledge CLI Commands
 
 | Command | Description |
 |---------|-------------|
-| `praisonai knowledge add <file\|dir\|url>` | Add documents to knowledge base |
-| `praisonai knowledge query <question>` | Query knowledge base with RAG |
+| `praisonai knowledge index <sources>` | Index documents into knowledge base |
+| `praisonai knowledge search <query>` | Search knowledge base (no LLM generation) |
 | `praisonai knowledge list` | List indexed documents |
-| `praisonai knowledge clear` | Clear knowledge base |
-| `praisonai knowledge stats` | Show knowledge base statistics |
-
-### Knowledge CLI Options
-
-| Option | Values | Description |
-|--------|--------|-------------|
-| `--vector-store` | `memory`, `chroma`, `pinecone`, `qdrant`, `weaviate` | Vector store backend |
-| `--retrieval` | `basic`, `fusion`, `recursive`, `auto_merge` | Retrieval strategy |
-| `--reranker` | `simple`, `llm`, `cross_encoder`, `cohere` | Reranking method |
-| `--index-type` | `vector`, `keyword`, `hybrid` | Index type |
-| `--query-mode` | `default`, `sub_question`, `summarize` | Query mode |
 
 ### Knowledge CLI Examples
 
 ```bash
-# Add documents
-praisonai knowledge add ./docs/
-praisonai knowledge add https://example.com/page.html
-praisonai knowledge add "*.pdf"
+# Index documents
+praisonai knowledge index ./docs/ --collection myproject
 
-# Query with advanced options
-praisonai knowledge query "How to authenticate?" --retrieval fusion --reranker llm
+# Search with hybrid retrieval
+praisonai knowledge search "authentication" --hybrid --collection myproject
 
-# Full advanced query
-praisonai knowledge query "authentication flow" \
-  --vector-store chroma \
-  --retrieval fusion \
-  --reranker llm \
-  --index-type hybrid \
-  --query-mode sub_question
+# Index with profiling
+praisonai knowledge index ./data --profile --profile-out ./profile.json
 ```
 
-### Knowledge SDK Usage
+### Knowledge vs RAG vs AutoRagAgent
+
+- **Knowledge** is the indexing and retrieval substrate - use for indexing and raw search
+- **RAG** orchestrates on top - use for question answering with LLM-generated responses and citations
+- **AutoRagAgent** wraps an Agent with automatic retrieval decision - use when you want the agent to decide when to retrieve
+- All share the same underlying index
+
+### AutoRagAgent (Automatic RAG)
+
+AutoRagAgent automatically decides when to retrieve context from knowledge bases vs direct chat, based on query heuristics.
 
 ```python
-from praisonaiagents import Agent, Knowledge
+from praisonaiagents import Agent, AutoRagAgent
 
-# Simple usage with Agent
+# Create agent with knowledge
 agent = Agent(
     name="Research Assistant",
-    knowledge=["docs/manual.pdf", "data/faq.txt"],
-    knowledge_config={
-        "vector_store": {"provider": "chroma"}
-    }
+    knowledge=["docs/manual.pdf"],
+    user_id="user123",  # Required for RAG retrieval
 )
-response = agent.chat("How do I authenticate?")
 
-# Direct Knowledge usage
-knowledge = Knowledge()
-knowledge.add("document.pdf")
-results = knowledge.search("authentication", limit=5)
+# Wrap with AutoRagAgent
+auto_rag = AutoRagAgent(
+    agent=agent,
+    retrieval_policy="auto",  # auto, always, never
+    top_k=5,
+    hybrid=True,
+    rerank=True,
+)
+
+# Auto-decides: retrieves for questions, skips for greetings
+result = auto_rag.chat("What are the key findings?")  # Retrieves
+result = auto_rag.chat("Hello!")  # Skips retrieval
+
+# Force retrieval or skip per-call
+result = auto_rag.chat("Hi", force_retrieval=True)
+result = auto_rag.chat("Summary?", skip_retrieval=True)
+```
+
+**CLI Usage:**
+```bash
+# Enable auto-rag with default policy (auto)
+praisonai --auto-rag "What are the key findings?"
+
+# Always retrieve
+praisonai --auto-rag --rag-policy always "Tell me about X"
+
+# With hybrid retrieval and reranking
+praisonai --auto-rag --rag-hybrid --rag-rerank "Summarize the document"
+```
+
+### Configuration Precedence
+
+Settings are applied in this order (highest priority first):
+1. **CLI flags** - `--hybrid`, `--rerank`, `--top-k`
+2. **Environment variables** - `PRAISONAI_HYBRID=true`
+3. **Config file** - YAML configuration (`--config`)
+4. **Defaults**
+
+```bash
+# Environment variables
+export PRAISONAI_HYBRID=true
+export PRAISONAI_RERANK=true
+export PRAISONAI_TOP_K=10
+```
+
+### Lightweight Installs
+
+```bash
+# Base install (minimal, fast imports)
+pip install praisonaiagents
+
+# With RAG API server support
+pip install "praisonai[rag-api]"
+```
+
+### Live Tests (Real API Keys)
+
+Run integration tests with real API keys:
+
+```bash
+# Enable live tests
+export PRAISONAI_LIVE_TESTS=1
+export OPENAI_API_KEY="your-key"
+
+# Run live tests
+pytest -m live tests/integration/
 ```
 
 ### Knowledge Stack Features Table
 
 | Feature | Description | SDK Docs | CLI Docs |
 |---------|-------------|----------|----------|
-| **Data Readers** | Load PDF, Markdown, Text, HTML, URLs | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Hybrid Retrieval** | Dense vectors + BM25 keyword search with RRF fusion | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
+| **Reranking** | LLM, Cross-Encoder, Cohere rerankers | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
+| **RAG Serve** | Microservice API with OpenAI-compatible mode | [SDK](/docs/rag/module) | [CLI](/docs/cli/rag) |
 | **Vector Stores** | ChromaDB, Pinecone, Qdrant, Weaviate, In-Memory | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Retrieval Strategies** | Basic, Fusion (RRF), Recursive, Auto-Merge | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Rerankers** | Simple, LLM, Cross-Encoder, Cohere | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Index Types** | Vector, Keyword (BM25), Hybrid | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
-| **Query Engines** | Default, Sub-Question, Summarize | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Data Readers** | Load PDF, Markdown, Text, HTML, URLs | [SDK](/docs/sdk/praisonaiagents/knowledge/protocols) | [CLI](/docs/cli/knowledge) |
+| **Profiling** | Performance profiling with `--profile` flag | [SDK](/docs/features/profiling) | [CLI](/docs/cli/rag) |
 
 ---
 
@@ -3079,43 +3149,7 @@ agent.chat("Hello!")  # Auto-persists messages, runs, traces
 | `praisonai persistence migrate` | Apply schema migrations |
 | `praisonai persistence status` | Show schema status |
 
-### Knowledge CLI Commands {#knowledge-cli}
-
-| Command | Description |
-|---------|-------------|
-| `praisonai knowledge add <source>` | Add file, directory, URL, or glob pattern |
-| `praisonai knowledge query "<question>"` | Query knowledge base with RAG |
-| `praisonai knowledge list` | List indexed documents |
-| `praisonai knowledge clear` | Clear knowledge base |
-| `praisonai knowledge stats` | Show knowledge base statistics |
-
-**Knowledge Query Flags:**
-
-| Flag | Values | Default |
-|------|--------|---------|
-| `--vector-store` | `memory`, `chroma`, `pinecone`, `qdrant`, `weaviate` | `chroma` |
-| `--retrieval-strategy` | `basic`, `fusion`, `recursive`, `auto_merge` | `basic` |
-| `--reranker` | `none`, `simple`, `llm`, `cross_encoder`, `cohere` | `none` |
-| `--index-type` | `vector`, `keyword`, `hybrid` | `vector` |
-| `--query-mode` | `default`, `sub_question`, `summarize` | `default` |
-| `--workspace` | Path to workspace directory | Current dir |
-| `--session` | Session ID for persistence | - |
-
-**Examples:**
-
-```bash
-# Add documents
-praisonai knowledge add document.pdf
-praisonai knowledge add ./docs/
-praisonai knowledge add "*.md"
-
-# Query with options
-praisonai knowledge query "How to authenticate?" \
-  --vector-store chroma \
-  --retrieval-strategy fusion \
-  --reranker simple \
-  --query-mode sub_question
-```
+> **Note:** See [Knowledge & Retrieval (RAG)](#-knowledge--retrieval-rag) for complete Knowledge CLI documentation.
 
 ### Databases Table
 
@@ -3191,6 +3225,9 @@ Install all tools with: `pip install "praisonai[tools]"`
 
 Learn PraisonAI through our comprehensive video series:
 
+<details>
+<summary><strong>View all 22 video tutorials</strong></summary>
+
 | Topic | Video |
 |-------|--------|
 | AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |
@@ -3216,6 +3253,8 @@ Learn PraisonAI through our comprehensive video series:
 | Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |
 | Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |
 
+</details>
+
 ---
 
 ## 👥 Contributing

src/praisonai/api.py

@@ -1,10 +1,10 @@
 from flask import Flask
-from praisonai import PraisonAI
 import markdown
 
 app = Flask(__name__)
 
 def basic():
+    from praisonai import PraisonAI
     praisonai = PraisonAI(agent_file="agents.yaml")
     return praisonai.run()
 

src/praisonai/praisonai.rb

@@ -3,8 +3,8 @@ class Praisonai < Formula
   
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.1.4.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.1.4.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.2.1.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.2.1.tar.gz | shasum -a 256`.split.first
     license "MIT"
   
     depends_on "[email protected]"

src/praisonai/praisonai/adapters/retrievers.py

@@ -376,6 +376,179 @@ class AutoMergeRetriever:
         return self.retrieve(query, top_k, filter, **kwargs)
 
 
+class HybridRetriever:
+    """
+    Hybrid retriever combining dense vector retrieval with BM25 keyword retrieval.
+    
+    Uses Reciprocal Rank Fusion (RRF) to combine results from both retrievers.
+    This provides better recall than either method alone, especially for
+    queries that benefit from exact keyword matching.
+    """
+    
+    name: str = "hybrid"
+    
+    def __init__(
+        self,
+        vector_store: Any,
+        embedding_fn: Optional[Callable[[str], List[float]]] = None,
+        keyword_index: Optional[Any] = None,
+        top_k: int = 10,
+        rrf_k: int = 60,
+        dense_weight: float = 0.5,
+        sparse_weight: float = 0.5,
+        **kwargs
+    ):
+        """
+        Initialize HybridRetriever.
+        
+        Args:
+            vector_store: Vector store for dense retrieval
+            embedding_fn: Function to generate embeddings
+            keyword_index: Optional KeywordIndex for BM25 retrieval (created if not provided)
+            top_k: Number of results to return
+            rrf_k: RRF constant (default 60)
+            dense_weight: Weight for dense retrieval results (default 0.5)
+            sparse_weight: Weight for sparse/BM25 results (default 0.5)
+        """
+        self.vector_store = vector_store
+        self.embedding_fn = embedding_fn
+        self.top_k = top_k
+        self.rrf_k = rrf_k
+        self.dense_weight = dense_weight
+        self.sparse_weight = sparse_weight
+        
+        # Create or use provided keyword index
+        if keyword_index is None:
+            from praisonaiagents.knowledge.index import KeywordIndex
+            self.keyword_index = KeywordIndex()
+        else:
+            self.keyword_index = keyword_index
+    
+    def add_to_keyword_index(
+        self,
+        texts: List[str],
+        ids: Optional[List[str]] = None,
+        metadatas: Optional[List[Dict[str, Any]]] = None,
+    ) -> List[str]:
+        """
+        Add documents to the keyword index.
+        
+        Call this when adding documents to keep the keyword index in sync
+        with the vector store.
+        
+        Args:
+            texts: List of text content
+            ids: Optional list of document IDs
+            metadatas: Optional list of metadata dicts
+            
+        Returns:
+            List of document IDs
+        """
+        return self.keyword_index.add_documents(
+            texts=texts,
+            ids=ids,
+            metadatas=metadatas,
+        )
+    
+    def retrieve(
+        self,
+        query: str,
+        top_k: Optional[int] = None,
+        filter: Optional[Dict[str, Any]] = None,
+        **kwargs
+    ) -> List[Any]:
+        """
+        Retrieve using hybrid dense + sparse approach with RRF fusion.
+        
+        Args:
+            query: Search query
+            top_k: Number of results to return
+            filter: Optional metadata filter
+            
+        Returns:
+            List of RetrievalResult objects sorted by fused score
+        """
+        from praisonaiagents.knowledge.retrieval import RetrievalResult, reciprocal_rank_fusion
+        
+        k = top_k or self.top_k
+        # Fetch more results for fusion
+        fetch_k = k * 2
+        
+        dense_results = []
+        sparse_results = []
+        
+        # 1. Dense retrieval from vector store
+        if self.embedding_fn:
+            try:
+                query_embedding = self.embedding_fn(query)
+                raw_results = self.vector_store.query(
+                    embedding=query_embedding,
+                    top_k=fetch_k,
+                    filter=filter,
+                )
+                
+                for r in raw_results:
+                    dense_results.append(RetrievalResult(
+                        text=r.text if hasattr(r, 'text') else str(r),
+                        score=r.score if hasattr(r, 'score') else 1.0,
+                        metadata=r.metadata if hasattr(r, 'metadata') else {},
+                        doc_id=r.id if hasattr(r, 'id') else None,
+                    ))
+            except Exception as e:
+                logger.warning(f"Dense retrieval failed: {e}")
+        
+        # 2. Sparse retrieval from keyword index (BM25)
+        try:
+            raw_sparse = self.keyword_index.query(
+                query=query,
+                top_k=fetch_k,
+                filter=filter,
+            )
+            
+            for r in raw_sparse:
+                sparse_results.append(RetrievalResult(
+                    text=r.get("text", ""),
+                    score=r.get("score", 0.0),
+                    metadata=r.get("metadata", {}),
+                    doc_id=r.get("id"),
+                ))
+        except Exception as e:
+            logger.warning(f"Sparse retrieval failed: {e}")
+        
+        # 3. Fuse results using RRF
+        if dense_results and sparse_results:
+            # Apply weights by duplicating results based on weight
+            # Higher weight = more influence in RRF
+            result_lists = []
+            
+            # Add dense results (weighted)
+            if self.dense_weight > 0:
+                result_lists.append(dense_results)
+            
+            # Add sparse results (weighted)
+            if self.sparse_weight > 0:
+                result_lists.append(sparse_results)
+            
+            fused = reciprocal_rank_fusion(result_lists, k=self.rrf_k)
+            return fused[:k]
+        elif dense_results:
+            return dense_results[:k]
+        elif sparse_results:
+            return sparse_results[:k]
+        else:
+            return []
+    
+    async def aretrieve(
+        self,
+        query: str,
+        top_k: Optional[int] = None,
+        filter: Optional[Dict[str, Any]] = None,
+        **kwargs
+    ) -> List[Any]:
+        """Async version (wraps sync for now)."""
+        return self.retrieve(query, top_k, filter, **kwargs)
+
+
 def register_default_retrievers():
     """Register all default retrievers with the registry."""
     from praisonaiagents.knowledge.retrieval import get_retriever_registry
@@ -386,6 +559,7 @@ def register_default_retrievers():
     registry.register("fusion", FusionRetriever)
     registry.register("recursive", RecursiveRetriever)
     registry.register("auto_merge", AutoMergeRetriever)
+    registry.register("hybrid", HybridRetriever)
     
     logger.debug("Registered default retrievers")
 

src/praisonai/praisonai/cli/app.py

@@ -4,8 +4,6 @@ PraisonAI CLI Typer Application.
 Main Typer app that registers all command groups and handles global options.
 """
 
-import os
-import sys
 from enum import Enum
 from typing import Optional
 
@@ -192,6 +190,8 @@ def register_commands():
     from .commands.workflow import app as workflow_app
     from .commands.tools import app as tools_app
     from .commands.knowledge import app as knowledge_app
+    from .commands.rag import app as rag_app
+    from .commands import retrieval as retrieval_module
     from .commands.deploy import app as deploy_app
     from .commands.agents import app as agents_app
     from .commands.skills import app as skills_app
@@ -230,9 +230,9 @@ def register_commands():
     app.add_typer(profile_app, name="profile", help="Performance profiling and diagnostics")
     app.add_typer(benchmark_app, name="benchmark", help="Comprehensive performance benchmarking")
     
-    # Register sub-apps - Previously legacy-only commands (now visible in --help)
-    app.add_typer(chat_app, name="chat", help="Interactive chat mode")
-    app.add_typer(code_app, name="code", help="Code assistant mode")
+    # Register sub-apps - Terminal-native commands
+    app.add_typer(chat_app, name="chat", help="Terminal-native interactive chat (REPL)")
+    app.add_typer(code_app, name="code", help="Terminal-native code assistant")
     app.add_typer(call_app, name="call", help="Voice/call interaction mode")
     app.add_typer(realtime_app, name="realtime", help="Realtime interaction mode")
     app.add_typer(train_app, name="train", help="Model training and fine-tuning")
@@ -242,7 +242,11 @@ def register_commands():
     app.add_typer(memory_app, name="memory", help="Memory management")
     app.add_typer(workflow_app, name="workflow", help="Workflow management")
     app.add_typer(tools_app, name="tools", help="Tool management")
-    app.add_typer(knowledge_app, name="knowledge", help="Knowledge base management")
+    app.add_typer(knowledge_app, name="knowledge", help="Knowledge base management (legacy)")
+    app.add_typer(rag_app, name="rag", help="RAG commands (legacy - use index/query instead)")
+    
+    # Register unified retrieval commands (Agent-first)
+    retrieval_module.register_commands(app)
     app.add_typer(deploy_app, name="deploy", help="Deployment management")
     app.add_typer(agents_app, name="agents", help="Agent management")
     app.add_typer(skills_app, name="skills", help="Skill management")

src/praisonai/praisonai/cli/commands/__init__.py

@@ -22,6 +22,7 @@ __all__ = [
     'doctor_app',
     'acp_app',
     'mcp_app',
+    'rag_app',
 ]
 
 
@@ -72,4 +73,7 @@ def __getattr__(name: str):
     elif name == 'mcp_app':
         from .mcp import app as mcp_app
         return mcp_app
+    elif name == 'rag_app':
+        from .rag import app as rag_app
+        return rag_app
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

src/praisonai/praisonai/cli/commands/chat.py

@@ -1,14 +1,15 @@
 """
 Chat command group for PraisonAI CLI.
 
-Provides interactive chat commands.
+Provides terminal-native interactive chat mode.
+This command NEVER opens a browser - it runs entirely in the terminal.
 """
 
-from typing import Optional
+from typing import List, Optional
 
 import typer
 
-app = typer.Typer(help="Interactive chat mode")
+app = typer.Typer(help="Terminal-native interactive chat mode")
 
 
 @app.callback(invoke_without_command=True)
@@ -21,40 +22,193 @@ def chat_main(
     tools: Optional[str] = typer.Option(None, "--tools", "-t", help="Tools file path"),
     user_id: Optional[str] = typer.Option(None, "--user-id", help="User ID for memory isolation"),
     session_id: Optional[str] = typer.Option(None, "--session", "-s", help="Session ID to resume"),
+    continue_session: bool = typer.Option(False, "--continue", "-c", help="Continue last session"),
+    file: Optional[List[str]] = typer.Option(None, "--file", "-f", help="Attach file(s) to prompt"),
+    workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Workspace directory"),
+    no_acp: bool = typer.Option(False, "--no-acp", help="Disable ACP tools"),
+    no_lsp: bool = typer.Option(False, "--no-lsp", help="Disable LSP tools"),
+    profile: bool = typer.Option(False, "--profile", help="Enable CLI profiling (timing breakdown)"),
+    profile_deep: bool = typer.Option(False, "--profile-deep", help="Enable deep profiling (cProfile stats, higher overhead)"),
 ):
     """
-    Start interactive chat mode.
+    Start terminal-native interactive chat mode.
+    
+    This is a terminal REPL with streaming responses, slash commands,
+    and multi-turn conversation support. It NEVER opens a browser.
+    
+    For browser-based chat UI, use: praisonai ui chat
     
     Examples:
         praisonai chat
         praisonai chat "Hello, how are you?"
         praisonai chat --model gpt-4o --memory
+        praisonai chat --continue  # Resume last session
+        praisonai chat "Summarize this" --file README.md
+        praisonai chat "What is 2+2?" --profile
     """
-    from praisonai.cli.main import PraisonAI
-    import sys
+    import asyncio
+    import os
     
-    # Build args for legacy handler
-    argv = ['chat']
-    if prompt:
-        argv.append(prompt)
-    if model:
-        argv.extend(['--model', model])
-    if verbose:
-        argv.append('--verbose')
-    if memory:
-        argv.append('--memory')
-    if tools:
-        argv.extend(['--tools', tools])
-    if user_id:
-        argv.extend(['--user-id', user_id])
+    # Set workspace if provided
+    if workspace:
+        os.environ["PRAISONAI_WORKSPACE"] = workspace
     
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
+    # Handle profiling for single prompt mode
+    if prompt and (profile or profile_deep):
+        _run_profiled_chat(
+            prompt=prompt,
+            model=model,
+            verbose=verbose,
+            profile_deep=profile_deep,
+        )
+        return
     
+    # Warn if profiling requested without prompt (REPL mode doesn't support profiling)
+    if (profile or profile_deep) and not prompt:
+        typer.echo("⚠️  Profiling is only supported for single prompt mode.", err=True)
+        typer.echo("   Use: praisonai chat \"your prompt\" --profile", err=True)
+    
+    # Try InteractiveCore first (preferred terminal-native implementation)
     try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
+        from praisonai.cli.interactive import InteractiveCore, InteractiveConfig
+        from praisonai.cli.interactive.frontends import RichFrontend
+        
+        config = InteractiveConfig(
+            model=model,
+            session_id=session_id,
+            continue_session=continue_session,
+            workspace=workspace or None,
+            verbose=verbose,
+            memory=memory,
+            files=list(file) if file else [],
+        )
+        
+        core = InteractiveCore(config=config)
+        
+        if prompt:
+            # Single prompt mode
+            async def run_prompt():
+                if continue_session:
+                    core.continue_session()
+                response = await core.prompt(prompt)
+                print(response)
+            
+            asyncio.run(run_prompt())
+        else:
+            # Interactive REPL mode
+            frontend = RichFrontend(core=core, config=config)
+            asyncio.run(frontend.run())
+            
+    except ImportError:
+        # Fallback to legacy terminal-native interactive mode
+        _run_legacy_terminal_chat(
+            prompt=prompt,
+            model=model,
+            verbose=verbose,
+            memory=memory,
+            tools=tools,
+            user_id=user_id,
+            session_id=session_id,
+            continue_session=continue_session,
+            workspace=workspace,
+            no_acp=no_acp,
+            no_lsp=no_lsp,
+        )
+
+
+def _run_profiled_chat(
+    prompt: str,
+    model: Optional[str] = None,
+    verbose: bool = False,
+    profile_deep: bool = False,
+):
+    """Run chat with profiling enabled."""
+    from praisonai.cli.features.cli_profiler import (
+        CLIProfileConfig,
+        CLIProfiler,
+    )
+    
+    config = CLIProfileConfig(enabled=True, deep=profile_deep)
+    profiler = CLIProfiler(config)
+    
+    if profile_deep:
+        typer.echo("⚠️  Deep profiling enabled - this adds significant overhead", err=True)
+    
+    profiler.start()
+    
+    # Import phase
+    profiler.mark_import_start()
+    try:
+        from praisonaiagents import Agent
+    except ImportError:
+        typer.echo("Error: praisonaiagents not installed", err=True)
+        raise typer.Exit(1)
+    profiler.mark_import_end()
+    
+    # Agent initialization phase
+    profiler.mark_init_start()
+    agent_config = {
+        "name": "ChatAgent",
+        "role": "Assistant",
+        "goal": "Help the user",
+        "verbose": verbose,
+    }
+    if model:
+        agent_config["llm"] = model
+    
+    agent = Agent(**agent_config)
+    profiler.mark_init_end()
+    
+    # Execution phase
+    profiler.mark_exec_start()
+    response = agent.start(prompt)
+    profiler.mark_exec_end()
+    
+    profiler.stop()
+    
+    # Print response
+    if response:
+        print(response)
+    
+    # Print profiling report
+    profiler.print_report()
+
+
+def _run_legacy_terminal_chat(
+    prompt: Optional[str] = None,
+    model: Optional[str] = None,
+    verbose: bool = False,
+    memory: bool = False,
+    tools: Optional[str] = None,
+    user_id: Optional[str] = None,
+    session_id: Optional[str] = None,
+    continue_session: bool = False,
+    workspace: Optional[str] = None,
+    no_acp: bool = False,
+    no_lsp: bool = False,
+):
+    """Run terminal-native chat using legacy _start_interactive_mode."""
+    import argparse
+    
+    # Build args namespace for _start_interactive_mode
+    args = argparse.Namespace()
+    args.llm = model
+    args.verbose = verbose
+    args.memory = memory
+    args.tools = tools
+    args.user_id = user_id
+    args.resume_session = session_id if session_id else ('last' if continue_session else None)
+    args.no_acp = no_acp
+    args.no_lsp = no_lsp
+    
+    # Import and run the terminal-native interactive mode
+    from praisonai.cli.main import PraisonAI
+    
+    praison = PraisonAI()
+    
+    if prompt:
+        # Single prompt mode - use _run_chat_mode
+        praison._run_chat_mode(prompt, args)
+    else:
+        # Interactive REPL mode - use _start_interactive_mode
+        praison._start_interactive_mode(args)

src/praisonai/praisonai/cli/commands/code.py

@@ -1,14 +1,15 @@
 """
 Code command group for PraisonAI CLI.
 
-Provides code assistant commands.
+Provides terminal-native code assistant mode.
+This command NEVER opens a browser - it runs entirely in the terminal.
 """
 
-from typing import Optional
+from typing import List, Optional
 
 import typer
 
-app = typer.Typer(help="Code assistant mode")
+app = typer.Typer(help="Terminal-native code assistant mode")
 
 
 @app.callback(invoke_without_command=True)
@@ -19,35 +20,129 @@ def code_main(
     verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
     tools: Optional[str] = typer.Option(None, "--tools", "-t", help="Tools file path"),
     workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Workspace directory"),
+    file: Optional[List[str]] = typer.Option(None, "--file", "-f", help="Attach file(s) to context"),
+    no_acp: bool = typer.Option(False, "--no-acp", help="Disable ACP tools (file operations)"),
+    no_lsp: bool = typer.Option(False, "--no-lsp", help="Disable LSP tools (code intelligence)"),
+    session_id: Optional[str] = typer.Option(None, "--session", "-s", help="Session ID to resume"),
+    continue_session: bool = typer.Option(False, "--continue", "-c", help="Continue last session"),
+    profile: bool = typer.Option(False, "--profile", help="Enable CLI profiling (timing breakdown)"),
+    profile_deep: bool = typer.Option(False, "--profile-deep", help="Enable deep profiling (cProfile stats, higher overhead)"),
 ):
     """
-    Start code assistant mode.
+    Start terminal-native code assistant mode.
+    
+    This is a terminal-based code assistant with file awareness, diff display,
+    and ACP/LSP tools enabled by default. It NEVER opens a browser.
+    
+    For browser-based code UI, use: praisonai ui code
     
     Examples:
         praisonai code
         praisonai code "Refactor this function"
         praisonai code --model gpt-4o --workspace ./src
+        praisonai code "Fix the bug" --file main.py
+        praisonai code "What is 2+2?" --profile
     """
+    import os
+    import argparse
+    
+    # Set workspace if provided
+    if workspace:
+        os.environ["PRAISONAI_WORKSPACE"] = workspace
+    
+    # Enable code-specific environment
+    os.environ["PRAISONAI_CODE_MODE"] = "true"
+    
+    # Handle profiling for single prompt mode
+    if prompt and (profile or profile_deep):
+        _run_profiled_code(
+            prompt=prompt,
+            model=model,
+            verbose=verbose,
+            profile_deep=profile_deep,
+        )
+        return
+    
+    # Warn if profiling requested without prompt (REPL mode doesn't support profiling)
+    if (profile or profile_deep) and not prompt:
+        typer.echo("⚠️  Profiling is only supported for single prompt mode.", err=True)
+        typer.echo("   Use: praisonai code \"your prompt\" --profile", err=True)
+    
+    # Build args namespace for _start_interactive_mode
+    args = argparse.Namespace()
+    args.llm = model
+    args.verbose = verbose
+    args.tools = tools
+    args.no_acp = no_acp
+    args.no_lsp = no_lsp
+    args.resume_session = session_id if session_id else ('last' if continue_session else None)
+    
+    # Import and run the terminal-native interactive mode
     from praisonai.cli.main import PraisonAI
-    import sys
     
-    argv = ['code']
+    praison = PraisonAI()
+    
     if prompt:
-        argv.append(prompt)
-    if model:
-        argv.extend(['--model', model])
-    if verbose:
-        argv.append('--verbose')
-    if tools:
-        argv.extend(['--tools', tools])
+        # Single prompt mode - use _run_chat_mode with code context
+        praison._run_chat_mode(prompt, args)
+    else:
+        # Interactive REPL mode - use _start_interactive_mode
+        praison._start_interactive_mode(args)
+
+
+def _run_profiled_code(
+    prompt: str,
+    model: Optional[str] = None,
+    verbose: bool = False,
+    profile_deep: bool = False,
+):
+    """Run code assistant with profiling enabled."""
+    from praisonai.cli.features.cli_profiler import (
+        CLIProfileConfig,
+        CLIProfiler,
+    )
     
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
+    config = CLIProfileConfig(enabled=True, deep=profile_deep)
+    profiler = CLIProfiler(config)
     
+    if profile_deep:
+        typer.echo("⚠️  Deep profiling enabled - this adds significant overhead", err=True)
+    
+    profiler.start()
+    
+    # Import phase
+    profiler.mark_import_start()
     try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
+        from praisonaiagents import Agent
+    except ImportError:
+        typer.echo("Error: praisonaiagents not installed", err=True)
+        raise typer.Exit(1)
+    profiler.mark_import_end()
+    
+    # Agent initialization phase
+    profiler.mark_init_start()
+    agent_config = {
+        "name": "CodeAgent",
+        "role": "Code Assistant",
+        "goal": "Help with coding tasks",
+        "verbose": verbose,
+    }
+    if model:
+        agent_config["llm"] = model
+    
+    agent = Agent(**agent_config)
+    profiler.mark_init_end()
+    
+    # Execution phase
+    profiler.mark_exec_start()
+    response = agent.start(prompt)
+    profiler.mark_exec_end()
+    
+    profiler.stop()
+    
+    # Print response
+    if response:
+        print(response)
+    
+    # Print profiling report
+    profiler.print_report()

src/praisonai/praisonai/cli/commands/knowledge.py

@@ -1,76 +1,383 @@
 """
 Knowledge command group for PraisonAI CLI.
 
-Provides knowledge base management commands.
+Provides knowledge base management commands:
+- index: Add/index documents into a knowledge base (canonical indexing command)
+- search: Search/retrieve from knowledge base (no generation)
+- list: List available knowledge bases
+
+Knowledge is the canonical substrate for indexing and retrieval.
+For answering questions with citations, use `praisonai rag query`.
 """
 
 import typer
+from typing import Optional, List
+from pathlib import Path
+from contextlib import contextmanager
+import time
+import json as json_module
 
-app = typer.Typer(help="Knowledge base management")
+app = typer.Typer(help="Knowledge base management (indexing and retrieval)")
 
 
-@app.command("add")
-def knowledge_add(
-    source: str = typer.Argument(..., help="Source file or URL"),
-    name: str = typer.Option(None, "--name", "-n", help="Knowledge base name"),
+@contextmanager
+def knowledge_profiler(enabled: bool, profile_out: Optional[Path], profile_top: int = 20):
+    """
+    Context manager for knowledge command profiling.
+    
+    Uses the existing praisonai.profiler infrastructure when available,
+    falls back to basic timing if not.
+    """
+    if not enabled:
+        yield None
+        return
+    
+    import sys
+    start_time = time.perf_counter()
+    start_modules = set(sys.modules.keys())
+    
+    # Try to use the full profiler
+    profiler = None
+    try:
+        from praisonai.profiler import Profiler
+        Profiler.enable()
+        Profiler.clear()
+        profiler = Profiler
+    except ImportError:
+        pass
+    
+    # Try tracemalloc for memory
+    try:
+        import tracemalloc
+        tracemalloc.start()
+    except Exception:
+        tracemalloc = None
+    
+    profile_data = {
+        "command": "knowledge",
+        "start_time": time.time(),
+        "metrics": {},
+        "imports": [],
+        "top_functions": [],
+    }
+    
+    try:
+        yield profile_data
+    finally:
+        end_time = time.perf_counter()
+        elapsed_ms = (end_time - start_time) * 1000
+        
+        # Collect metrics
+        profile_data["metrics"]["wall_time_ms"] = elapsed_ms
+        profile_data["metrics"]["wall_time_s"] = elapsed_ms / 1000
+        
+        # Memory usage
+        if tracemalloc:
+            try:
+                current, peak = tracemalloc.get_traced_memory()
+                tracemalloc.stop()
+                profile_data["metrics"]["peak_memory_mb"] = peak / (1024 * 1024)
+                profile_data["metrics"]["current_memory_mb"] = current / (1024 * 1024)
+            except Exception:
+                pass
+        
+        # New imports during execution
+        end_modules = set(sys.modules.keys())
+        new_modules = end_modules - start_modules
+        profile_data["imports"] = sorted(list(new_modules))[:profile_top]
+        profile_data["metrics"]["modules_imported"] = len(new_modules)
+        
+        # Get profiler data if available
+        if profiler:
+            try:
+                profiler.disable()
+                stats = profiler.get_statistics()
+                if stats:
+                    profile_data["top_functions"] = stats.get("top_functions", [])[:profile_top]
+                    profile_data["metrics"].update(stats.get("summary", {}))
+            except Exception:
+                pass
+        
+        # Save to file if requested
+        if profile_out:
+            try:
+                profile_out.parent.mkdir(parents=True, exist_ok=True)
+                with open(profile_out, "w") as f:
+                    json_module.dump(profile_data, f, indent=2, default=str)
+            except Exception as e:
+                print(f"Warning: Failed to save profile: {e}")
+        
+        # Print summary
+        from rich.console import Console
+        console = Console(stderr=True)
+        console.print(f"\n[dim]Profile: {elapsed_ms:.2f}ms wall time[/dim]")
+        if "peak_memory_mb" in profile_data["metrics"]:
+            console.print(f"[dim]Profile: {profile_data['metrics']['peak_memory_mb']:.2f}MB peak memory[/dim]")
+        console.print(f"[dim]Profile: {len(new_modules)} modules imported[/dim]")
+        if profile_out:
+            console.print(f"[dim]Profile saved to: {profile_out}[/dim]")
+
+
+@app.command("index")
+def knowledge_index(
+    sources: List[str] = typer.Argument(..., help="Source files, directories, or URLs to index"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection/knowledge base name"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
 ):
-    """Add knowledge from a source."""
-    from praisonai.cli.main import PraisonAI
-    import sys
+    """
+    Index documents into a knowledge base.
     
-    argv = ['knowledge', 'add', source]
-    if name:
-        argv.extend(['--name', name])
+    This is the canonical command for adding documents to a knowledge base.
+    Use `praisonai rag query` to answer questions using the indexed knowledge.
     
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
+    Examples:
+        praisonai knowledge index ./docs
+        praisonai knowledge index paper.pdf --collection research
+        praisonai knowledge index ./data --profile --profile-out ./profile.json
+    """
+    from rich.console import Console
+    from rich.progress import Progress, SpinnerColumn, TextColumn
     
-    try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
-
-
-@app.command("list")
-def knowledge_list():
-    """List knowledge bases."""
-    from praisonai.cli.main import PraisonAI
-    import sys
+    console = Console()
     
-    argv = ['knowledge', 'list']
-    
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
-    
-    try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
+    with knowledge_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            # Lazy import to avoid startup cost
+            from praisonaiagents.knowledge import Knowledge
+            
+            # Build config
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Load config file if provided
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            # Initialize Knowledge
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            
+            # Index sources
+            with Progress(
+                SpinnerColumn(),
+                TextColumn("[progress.description]{task.description}"),
+                console=console,
+                transient=True,
+            ) as progress:
+                for source in sources:
+                    task = progress.add_task(f"Indexing {source}...", total=None)
+                    try:
+                        result = knowledge.add(source)
+                        count = len(result.get("results", [])) if isinstance(result, dict) else 0
+                        console.print(f"[green]✓[/green] Indexed {source}: {count} chunks")
+                    except Exception as e:
+                        console.print(f"[red]✗[/red] Failed to index {source}: {e}")
+                    progress.remove_task(task)
+            
+            console.print(f"\n[bold green]Indexing complete![/bold green] Collection: {collection}")
+            if profile_data:
+                profile_data["command"] = "knowledge index"
+                profile_data["collection"] = collection
+                profile_data["sources"] = sources
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            raise typer.Exit(1)
 
 
 @app.command("search")
 def knowledge_search(
     query: str = typer.Argument(..., help="Search query"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to search"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results to retrieve"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + BM25)"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
 ):
-    """Search knowledge base."""
-    from praisonai.cli.main import PraisonAI
-    import sys
+    """
+    Search/retrieve from a knowledge base (no LLM generation).
     
-    argv = ['knowledge', 'search', query]
+    Returns raw search results without generating an answer.
+    For answers with citations, use `praisonai rag query`.
     
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
+    Examples:
+        praisonai knowledge search "capital of France"
+        praisonai knowledge search "main findings" --collection research --top-k 10
+        praisonai knowledge search "Python tutorial" --hybrid
+    """
+    from rich.console import Console
+    from rich.table import Table
     
-    try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
+    console = Console()
+    
+    with knowledge_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            from praisonaiagents.knowledge import Knowledge
+            
+            # Build config
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Add hybrid retrieval config if enabled
+            if hybrid:
+                knowledge_config["retrieval"] = {
+                    "strategy": "hybrid",
+                }
+            
+            # Load config file if provided
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            # Initialize and search
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            
+            # Use hybrid search if enabled
+            if hybrid:
+                if verbose:
+                    console.print("[dim]Using hybrid retrieval (dense + BM25)...[/dim]")
+                results = knowledge.search(query, limit=top_k, hybrid=True)
+            else:
+                results = knowledge.search(query, limit=top_k)
+            
+            if not results:
+                console.print("[yellow]No results found.[/yellow]")
+                return
+            
+            # Display results
+            table = Table(title=f"Search Results for: {query}")
+            table.add_column("#", style="dim", width=3)
+            table.add_column("Score", width=8)
+            table.add_column("Source", width=20)
+            table.add_column("Content", width=60)
+            
+            result_list = results.get('results', results) if isinstance(results, dict) else results
+            for i, result in enumerate(result_list[:top_k], 1):
+                if isinstance(result, dict):
+                    score = f"{result.get('score', 0):.3f}" if result.get('score') else "-"
+                    source = result.get('metadata', {}).get('filename', result.get('metadata', {}).get('source', '-'))
+                    content = result.get('memory', result.get('text', ''))[:100] + "..."
+                else:
+                    score = "-"
+                    source = "-"
+                    content = str(result)[:100] + "..."
+                
+                table.add_row(str(i), score, source, content)
+            
+            console.print(table)
+            
+            if profile_data:
+                profile_data["command"] = "knowledge search"
+                profile_data["collection"] = collection
+                profile_data["query"] = query
+                profile_data["num_results"] = len(result_list)
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            if verbose:
+                import traceback
+                console.print(traceback.format_exc())
+            raise typer.Exit(1)
+
+
+@app.command("add")
+def knowledge_add(
+    sources: List[str] = typer.Argument(..., help="Source files, directories, or URLs to index"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection/knowledge base name"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Add documents to a knowledge base (alias for 'index').
+    
+    This is a backward-compatible alias for `praisonai knowledge index`.
+    
+    Examples:
+        praisonai knowledge add ./docs
+        praisonai knowledge add paper.pdf --collection research
+    """
+    # Delegate to index command
+    knowledge_index(
+        sources=sources,
+        collection=collection,
+        config=config,
+        verbose=verbose,
+        profile=profile,
+        profile_out=profile_out,
+        profile_top=profile_top,
+    )
+
+
+@app.command("list")
+def knowledge_list(
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+):
+    """List available knowledge bases/collections."""
+    from rich.console import Console
+    from rich.table import Table
+    import os
+    
+    console = Console()
+    
+    # Check for knowledge directories
+    knowledge_dirs = ["./.praison/knowledge", "./.praison/rag", ".praison"]
+    collections = set()
+    
+    for base_dir in knowledge_dirs:
+        if os.path.exists(base_dir):
+            for item in os.listdir(base_dir):
+                item_path = os.path.join(base_dir, item)
+                if os.path.isdir(item_path):
+                    collections.add((item, base_dir))
+    
+    if not collections:
+        console.print("[yellow]No knowledge bases found.[/yellow]")
+        console.print("Create one with: praisonai knowledge index ./docs --collection myknowledge")
+        return
+    
+    table = Table(title="Knowledge Bases")
+    table.add_column("Collection", style="cyan")
+    table.add_column("Path", style="dim")
+    
+    for name, path in sorted(collections):
+        table.add_row(name, os.path.join(path, name))
+    
+    console.print(table)

src/praisonai/praisonai/cli/commands/rag.py

@@ -0,0 +1,904 @@
+"""
+RAG command group for PraisonAI CLI.
+
+Provides RAG (Retrieval Augmented Generation) commands:
+- index: Build/update an index from sources
+- query: One-shot question -> answer with citations
+- chat: Interactive RAG chat loop
+- eval: Evaluate retrieval quality
+- serve: Start RAG microservice (optional)
+
+All commands support --profile for performance profiling using the existing
+praisonai profile infrastructure.
+"""
+
+import typer
+from typing import Optional, List
+from pathlib import Path
+from contextlib import contextmanager
+import time
+import json as json_module
+
+app = typer.Typer(help="RAG (Retrieval Augmented Generation) commands")
+
+
+@contextmanager
+def rag_profiler(enabled: bool, profile_out: Optional[Path], profile_top: int = 20):
+    """
+    Context manager for RAG command profiling.
+    
+    Uses the existing praisonai.profiler infrastructure when available,
+    falls back to basic timing if not.
+    """
+    if not enabled:
+        yield None
+        return
+    
+    import sys
+    start_time = time.perf_counter()
+    start_modules = set(sys.modules.keys())
+    
+    # Try to use the full profiler
+    profiler = None
+    try:
+        from praisonai.profiler import Profiler
+        Profiler.enable()
+        Profiler.clear()
+        profiler = Profiler
+    except ImportError:
+        pass
+    
+    # Try tracemalloc for memory
+    try:
+        import tracemalloc
+        tracemalloc.start()
+    except Exception:
+        tracemalloc = None
+    
+    profile_data = {
+        "command": "rag",
+        "start_time": time.time(),
+        "metrics": {},
+        "imports": [],
+        "top_functions": [],
+    }
+    
+    try:
+        yield profile_data
+    finally:
+        end_time = time.perf_counter()
+        elapsed_ms = (end_time - start_time) * 1000
+        
+        # Collect metrics
+        profile_data["metrics"]["wall_time_ms"] = elapsed_ms
+        profile_data["metrics"]["wall_time_s"] = elapsed_ms / 1000
+        
+        # Memory usage
+        if tracemalloc:
+            try:
+                current, peak = tracemalloc.get_traced_memory()
+                tracemalloc.stop()
+                profile_data["metrics"]["peak_memory_mb"] = peak / (1024 * 1024)
+                profile_data["metrics"]["current_memory_mb"] = current / (1024 * 1024)
+            except Exception:
+                pass
+        
+        # New imports during execution
+        end_modules = set(sys.modules.keys())
+        new_modules = end_modules - start_modules
+        profile_data["imports"] = sorted(list(new_modules))[:profile_top]
+        profile_data["metrics"]["modules_imported"] = len(new_modules)
+        
+        # Get profiler data if available
+        if profiler:
+            try:
+                profiler.disable()
+                stats = profiler.get_statistics()
+                if stats:
+                    profile_data["top_functions"] = stats.get("top_functions", [])[:profile_top]
+                    profile_data["metrics"].update(stats.get("summary", {}))
+            except Exception:
+                pass
+        
+        # Save to file if requested
+        if profile_out:
+            try:
+                profile_out.parent.mkdir(parents=True, exist_ok=True)
+                with open(profile_out, "w") as f:
+                    json_module.dump(profile_data, f, indent=2, default=str)
+            except Exception as e:
+                print(f"Warning: Failed to save profile: {e}")
+        
+        # Print summary
+        from rich.console import Console
+        console = Console(stderr=True)
+        console.print(f"\n[dim]Profile: {elapsed_ms:.2f}ms wall time[/dim]")
+        if "peak_memory_mb" in profile_data["metrics"]:
+            console.print(f"[dim]Profile: {profile_data['metrics']['peak_memory_mb']:.2f}MB peak memory[/dim]")
+        console.print(f"[dim]Profile: {len(new_modules)} modules imported[/dim]")
+        if profile_out:
+            console.print(f"[dim]Profile saved to: {profile_out}[/dim]")
+
+
+@app.command("index")
+def rag_index(
+    sources: List[str] = typer.Argument(..., help="Source files, directories, or URLs to index"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection/index name"),
+    chunking: str = typer.Option("recursive", "--chunking", help="Chunking strategy: token, sentence, recursive, semantic"),
+    chunk_size: int = typer.Option(512, "--chunk-size", help="Chunk size in tokens"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Index documents for RAG retrieval.
+    
+    This command uses the Knowledge substrate for indexing.
+    Equivalent to: praisonai knowledge index
+    
+    Examples:
+        praisonai rag index ./docs
+        praisonai rag index paper.pdf --collection research
+        praisonai rag index ./data --chunking semantic --chunk-size 256
+        praisonai rag index ./docs --profile --profile-out ./profile.json
+    """
+    from rich.console import Console
+    from rich.progress import Progress, SpinnerColumn, TextColumn
+    
+    console = Console()
+    
+    with rag_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            # Lazy import to avoid startup cost
+            from praisonaiagents.knowledge import Knowledge
+            
+            # Build config - use unified knowledge path
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Load config file if provided
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            # Initialize Knowledge
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            
+            # Index sources
+            with Progress(
+                SpinnerColumn(),
+                TextColumn("[progress.description]{task.description}"),
+                console=console,
+                transient=True,
+            ) as progress:
+                for source in sources:
+                    task = progress.add_task(f"Indexing {source}...", total=None)
+                    try:
+                        result = knowledge.add(source)
+                        count = len(result.get("results", [])) if isinstance(result, dict) else 0
+                        console.print(f"[green]✓[/green] Indexed {source}: {count} chunks")
+                    except Exception as e:
+                        console.print(f"[red]✗[/red] Failed to index {source}: {e}")
+                    progress.remove_task(task)
+            
+            console.print(f"\n[bold green]Indexing complete![/bold green] Collection: {collection}")
+            if profile_data:
+                profile_data["command"] = "rag index"
+                profile_data["collection"] = collection
+                profile_data["sources"] = sources
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            raise typer.Exit(1)
+
+
+@app.command("query")
+def rag_query(
+    question: str = typer.Argument(..., help="Question to answer"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to query"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results to retrieve"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + BM25)"),
+    rerank: bool = typer.Option(False, "--rerank", help="Enable reranking of results"),
+    citations: bool = typer.Option(True, "--citations/--no-citations", help="Include citations"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Query the RAG system with a question.
+    
+    Examples:
+        praisonai rag query "What is the main finding?"
+        praisonai rag query "Summarize the document" --collection research
+        praisonai rag query "Key points?" --top-k 10 --no-citations
+        praisonai rag query "Summary?" --hybrid --rerank
+        praisonai rag query "Summary?" --profile --profile-out ./profile.json
+    """
+    from rich.console import Console
+    from rich.panel import Panel
+    from rich.markdown import Markdown
+    
+    console = Console()
+    
+    with rag_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            from praisonaiagents.knowledge import Knowledge
+            from praisonaiagents.rag import RAG, RAGConfig
+            from praisonaiagents.rag.models import RetrievalStrategy
+            
+            # Build config - use unified knowledge path
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Add hybrid retrieval config if enabled
+            if hybrid:
+                knowledge_config["retrieval"] = {
+                    "strategy": "hybrid",
+                }
+            
+            # Load config file if provided
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            # Initialize
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            
+            # Determine retrieval strategy
+            retrieval_strategy = RetrievalStrategy.HYBRID if hybrid else RetrievalStrategy.BASIC
+            
+            rag_config = RAGConfig(
+                top_k=top_k,
+                include_citations=citations,
+                retrieval_strategy=retrieval_strategy,
+                rerank=rerank,
+            )
+            rag = RAG(knowledge=knowledge, config=rag_config)
+            
+            # Query
+            if verbose:
+                strategy_str = "hybrid (dense + BM25)" if hybrid else "dense"
+                rerank_str = " with reranking" if rerank else ""
+                console.print(f"[dim]Querying collection '{collection}' using {strategy_str}{rerank_str}, top_k={top_k}...[/dim]")
+            
+            result = rag.query(question)
+            
+            # Display answer
+            console.print(Panel(
+                Markdown(result.answer),
+                title="[bold]Answer[/bold]",
+                border_style="green",
+            ))
+            
+            # Display citations
+            if citations and result.citations:
+                console.print("\n[bold]Sources:[/bold]")
+                for citation in result.citations:
+                    score_str = f"[dim](score: {citation.score:.2f})[/dim]" if citation.score else ""
+                    console.print(f"  [{citation.id}] {citation.source} {score_str}")
+                    if verbose:
+                        snippet = citation.text[:200] + "..." if len(citation.text) > 200 else citation.text
+                        console.print(f"      [dim]{snippet}[/dim]")
+            
+            # Show metadata if verbose
+            if verbose:
+                console.print(f"\n[dim]Elapsed: {result.metadata.get('elapsed_seconds', 0):.2f}s[/dim]")
+            
+            if profile_data:
+                profile_data["command"] = "rag query"
+                profile_data["collection"] = collection
+                profile_data["question"] = question
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            if verbose:
+                import traceback
+                console.print(traceback.format_exc())
+            raise typer.Exit(1)
+
+
+@app.command("chat")
+def rag_chat(
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to chat with"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results per query"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + BM25)"),
+    rerank: bool = typer.Option(False, "--rerank", help="Enable reranking of results"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    stream: bool = typer.Option(True, "--stream/--no-stream", help="Stream responses"),
+):
+    """
+    Interactive RAG chat session.
+    
+    Examples:
+        praisonai rag chat
+        praisonai rag chat --collection research
+        praisonai rag chat --hybrid --rerank
+        praisonai rag chat --no-stream
+    """
+    from rich.console import Console
+    from rich.panel import Panel
+    from rich.markdown import Markdown
+    
+    console = Console()
+    
+    try:
+        from praisonaiagents.knowledge import Knowledge
+        from praisonaiagents.rag import RAG, RAGConfig
+        from praisonaiagents.rag.models import RetrievalStrategy
+        
+        # Build config - use unified knowledge path
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": collection,
+                    "path": f"./.praison/knowledge/{collection}",
+                }
+            }
+        }
+        
+        # Add hybrid retrieval config if enabled
+        if hybrid:
+            knowledge_config["retrieval"] = {
+                "strategy": "hybrid",
+            }
+        
+        # Load config file if provided
+        if config and config.exists():
+            import yaml
+            with open(config) as f:
+                file_config = yaml.safe_load(f)
+                if "knowledge" in file_config:
+                    knowledge_config.update(file_config["knowledge"])
+        
+        # Initialize
+        knowledge = Knowledge(config=knowledge_config)
+        retrieval_strategy = RetrievalStrategy.HYBRID if hybrid else RetrievalStrategy.BASIC
+        rag_config = RAGConfig(
+            top_k=top_k,
+            include_citations=True,
+            stream=stream,
+            retrieval_strategy=retrieval_strategy,
+            rerank=rerank,
+        )
+        rag = RAG(knowledge=knowledge, config=rag_config)
+        
+        console.print(Panel(
+            f"[bold]RAG Chat[/bold] - Collection: {collection}\n"
+            "Type your questions. Use 'exit' or Ctrl+C to quit.",
+            border_style="blue",
+        ))
+        
+        while True:
+            try:
+                question = console.input("\n[bold blue]You:[/bold blue] ").strip()
+                
+                if not question:
+                    continue
+                if question.lower() in ("exit", "quit", "q"):
+                    console.print("[dim]Goodbye![/dim]")
+                    break
+                
+                console.print("\n[bold green]Assistant:[/bold green]")
+                
+                if stream:
+                    # Stream response
+                    full_response = ""
+                    for chunk in rag.stream(question):
+                        console.print(chunk, end="")
+                        full_response += chunk
+                    console.print()  # Newline after streaming
+                    
+                    # Get citations separately
+                    citations = rag.get_citations(question)
+                else:
+                    result = rag.query(question)
+                    console.print(Markdown(result.answer))
+                    citations = result.citations
+                
+                # Show citations
+                if citations:
+                    console.print("\n[dim]Sources:[/dim]")
+                    for c in citations[:3]:  # Show top 3
+                        console.print(f"  [dim][{c.id}] {c.source}[/dim]")
+                
+            except KeyboardInterrupt:
+                console.print("\n[dim]Goodbye![/dim]")
+                break
+            except Exception as e:
+                console.print(f"[red]Error:[/red] {e}")
+        
+    except ImportError as e:
+        console.print(f"[red]Error:[/red] Missing dependency: {e}")
+        console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+
+
+@app.command("eval")
+def rag_eval(
+    test_file: Path = typer.Argument(..., help="JSON file with test queries"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to evaluate"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results to retrieve"),
+    output: Optional[Path] = typer.Option(None, "--output", "-o", help="Output results to file"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Evaluate RAG retrieval quality.
+    
+    Test file format (JSON):
+    [
+        {"query": "What is X?", "expected_doc": "doc1.pdf", "expected_answer_contains": "answer"},
+        ...
+    ]
+    
+    Examples:
+        praisonai rag eval golden_queries.json
+        praisonai rag eval tests.json --collection research --output results.json
+        praisonai rag eval tests.json --profile --profile-out ./profile.json
+    """
+    import json
+    from rich.console import Console
+    from rich.table import Table
+    
+    console = Console()
+    
+    with rag_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            from praisonaiagents.knowledge import Knowledge
+            from praisonaiagents.rag import RAG, RAGConfig
+            
+            # Load test file
+            if not test_file.exists():
+                console.print(f"[red]Error:[/red] Test file not found: {test_file}")
+                raise typer.Exit(1)
+            
+            with open(test_file) as f:
+                tests = json.load(f)
+            
+            if not isinstance(tests, list):
+                console.print("[red]Error:[/red] Test file must contain a JSON array")
+                raise typer.Exit(1)
+            
+            # Build config - use unified knowledge path
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Initialize
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            rag_config = RAGConfig(top_k=top_k, include_citations=True)
+            rag = RAG(knowledge=knowledge, config=rag_config)
+            
+            # Run evaluation
+            results = []
+            passed = 0
+            failed = 0
+            
+            console.print(f"\n[bold]Evaluating {len(tests)} queries...[/bold]\n")
+            
+            for i, test in enumerate(tests):
+                query = test.get("query", "")
+                expected_doc = test.get("expected_doc", "")
+                expected_contains = test.get("expected_answer_contains", "")
+                
+                result = rag.query(query)
+                
+                # Check if expected doc is in citations
+                doc_found = any(
+                    expected_doc in c.source for c in result.citations
+                ) if expected_doc else True
+                
+                # Check if answer contains expected text
+                answer_ok = (
+                    expected_contains.lower() in result.answer.lower()
+                ) if expected_contains else True
+                
+                test_passed = doc_found and answer_ok
+                
+                if test_passed:
+                    passed += 1
+                    status = "[green]PASS[/green]"
+                else:
+                    failed += 1
+                    status = "[red]FAIL[/red]"
+                
+                results.append({
+                    "query": query,
+                    "passed": test_passed,
+                    "doc_found": doc_found,
+                    "answer_ok": answer_ok,
+                    "answer": result.answer[:200],
+                    "citations": [c.source for c in result.citations],
+                })
+                
+                if verbose:
+                    console.print(f"  {status} Query: {query[:50]}...")
+            
+            # Summary table
+            table = Table(title="Evaluation Results")
+            table.add_column("Metric", style="bold")
+            table.add_column("Value")
+            
+            table.add_row("Total Tests", str(len(tests)))
+            table.add_row("Passed", f"[green]{passed}[/green]")
+            table.add_row("Failed", f"[red]{failed}[/red]")
+            table.add_row("Pass Rate", f"{passed/len(tests)*100:.1f}%")
+            
+            console.print(table)
+            
+            # Save results if output specified
+            if output:
+                with open(output, "w") as f:
+                    json.dump(results, f, indent=2)
+                console.print(f"\n[dim]Results saved to {output}[/dim]")
+            
+            # Exit with error if any failed
+            if failed > 0:
+                raise typer.Exit(1)
+            
+            if profile_data:
+                profile_data["command"] = "rag eval"
+                profile_data["collection"] = collection
+                profile_data["test_file"] = str(test_file)
+                profile_data["metrics"]["tests_total"] = len(tests)
+                profile_data["metrics"]["tests_passed"] = passed
+                profile_data["metrics"]["tests_failed"] = failed
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except typer.Exit:
+            raise
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            if verbose:
+                import traceback
+                console.print(traceback.format_exc())
+            raise typer.Exit(1)
+
+
+@app.command("serve")
+def rag_serve(
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to serve"),
+    host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind"),
+    port: int = typer.Option(8080, "--port", "-p", help="Port to bind"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + BM25)"),
+    rerank: bool = typer.Option(False, "--rerank", help="Enable reranking of results"),
+    openai_compat: bool = typer.Option(False, "--openai-compat", help="Enable OpenAI-compatible /v1/chat/completions endpoint"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Start RAG microservice API.
+    
+    Endpoints:
+        GET  /health - Health check
+        POST /rag/query - Query with JSON body {"question": "...", "top_k": 5, "hybrid": false}
+        POST /rag/chat - Streaming chat (SSE)
+        POST /v1/chat/completions - OpenAI-compatible endpoint (with --openai-compat)
+    
+    Examples:
+        praisonai rag serve
+        praisonai rag serve --collection research --port 9000
+        praisonai rag serve --hybrid --rerank
+        praisonai rag serve --openai-compat --port 8080
+        praisonai rag serve --profile --profile-out ./profile.json
+    """
+    from rich.console import Console
+    
+    console = Console()
+    
+    with rag_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            import uvicorn
+            from fastapi import FastAPI, HTTPException
+            from fastapi.responses import StreamingResponse
+            from pydantic import BaseModel, Field
+            from typing import List as TypingList, Optional as TypingOptional
+        except ImportError:
+            console.print("[red]Error:[/red] FastAPI/uvicorn not installed")
+            console.print("Install with: pip install 'praisonai[rag-api]'")
+            raise typer.Exit(1)
+        
+        try:
+            from praisonaiagents.knowledge import Knowledge
+            from praisonaiagents.rag import RAG, RAGConfig
+            from praisonaiagents.rag.models import RetrievalStrategy
+            
+            # Build config - use unified knowledge path
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            # Add hybrid retrieval config if enabled
+            if hybrid:
+                knowledge_config["retrieval"] = {
+                    "strategy": "hybrid",
+                }
+            
+            # Load config file if provided
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            # Initialize
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            retrieval_strategy = RetrievalStrategy.HYBRID if hybrid else RetrievalStrategy.BASIC
+            rag_config = RAGConfig(
+                retrieval_strategy=retrieval_strategy,
+                rerank=rerank,
+            )
+            rag = RAG(knowledge=knowledge, config=rag_config)
+            
+            # Create FastAPI app
+            api = FastAPI(
+                title="PraisonAI RAG API",
+                version="1.0.0",
+                description="RAG microservice with hybrid retrieval and OpenAI-compatible mode",
+            )
+            
+            # Request/Response models
+            class QueryRequest(BaseModel):
+                question: str
+                top_k: int = 5
+                include_citations: bool = True
+                hybrid: bool = Field(default=False, description="Use hybrid retrieval")
+                rerank: bool = Field(default=False, description="Enable reranking")
+            
+            class CitationModel(BaseModel):
+                id: str
+                source: str
+                text: str
+                score: float = 0.0
+                doc_id: TypingOptional[str] = None
+                chunk_id: TypingOptional[str] = None
+            
+            class QueryResponse(BaseModel):
+                answer: str
+                citations: TypingList[CitationModel]
+                metadata: dict
+            
+            # OpenAI-compatible models
+            class ChatMessage(BaseModel):
+                role: str
+                content: str
+            
+            class ChatCompletionRequest(BaseModel):
+                model: str = "rag"
+                messages: TypingList[ChatMessage]
+                temperature: float = 0.7
+                max_tokens: TypingOptional[int] = None
+                stream: bool = False
+                rag: bool = Field(default=True, description="Enable RAG retrieval")
+            
+            class ChatCompletionChoice(BaseModel):
+                index: int
+                message: ChatMessage
+                finish_reason: str = "stop"
+            
+            class ChatCompletionResponse(BaseModel):
+                id: str
+                object: str = "chat.completion"
+                created: int
+                model: str
+                choices: TypingList[ChatCompletionChoice]
+                usage: dict = Field(default_factory=dict)
+            
+            @api.get("/health")
+            def health():
+                return {
+                    "status": "healthy",
+                    "collection": collection,
+                    "hybrid": hybrid,
+                    "rerank": rerank,
+                    "openai_compat": openai_compat,
+                }
+            
+            @api.post("/rag/query", response_model=QueryResponse)
+            def query_endpoint(request: QueryRequest):
+                try:
+                    # Update config based on request
+                    rag.config.top_k = request.top_k
+                    rag.config.include_citations = request.include_citations
+                    
+                    # Override retrieval strategy if requested
+                    if request.hybrid:
+                        rag.config.retrieval_strategy = RetrievalStrategy.HYBRID
+                    if request.rerank:
+                        rag.config.rerank = True
+                    
+                    result = rag.query(request.question)
+                    
+                    return QueryResponse(
+                        answer=result.answer,
+                        citations=[
+                            CitationModel(
+                                id=c.id,
+                                source=c.source,
+                                text=c.text,
+                                score=c.score,
+                                doc_id=c.doc_id,
+                                chunk_id=c.chunk_id,
+                            )
+                            for c in result.citations
+                        ],
+                        metadata=result.metadata,
+                    )
+                except Exception as e:
+                    raise HTTPException(status_code=500, detail=str(e))
+            
+            @api.post("/rag/chat")
+            def chat_endpoint(request: QueryRequest):
+                """Streaming RAG chat endpoint using Server-Sent Events."""
+                import json as json_lib
+                
+                def generate():
+                    try:
+                        # Update config
+                        rag.config.top_k = request.top_k
+                        if request.hybrid:
+                            rag.config.retrieval_strategy = RetrievalStrategy.HYBRID
+                        if request.rerank:
+                            rag.config.rerank = True
+                        
+                        for chunk in rag.stream(request.question):
+                            yield f"data: {json_lib.dumps({'content': chunk})}\n\n"
+                        
+                        # Send citations at the end
+                        if request.include_citations:
+                            citations = rag.get_citations(request.question)
+                            yield f"data: {json_lib.dumps({'citations': [c.to_dict() for c in citations]})}\n\n"
+                        
+                        yield "data: [DONE]\n\n"
+                    except Exception as e:
+                        yield f"data: {json_lib.dumps({'error': str(e)})}\n\n"
+                
+                return StreamingResponse(
+                    generate(),
+                    media_type="text/event-stream",
+                    headers={"Cache-Control": "no-cache", "Connection": "keep-alive"},
+                )
+            
+            # OpenAI-compatible endpoint (only if enabled)
+            if openai_compat:
+                @api.post("/v1/chat/completions")
+                def openai_chat_completions(request: ChatCompletionRequest):
+                    """OpenAI-compatible chat completions endpoint with RAG."""
+                    import time as time_module
+                    import uuid
+                    
+                    try:
+                        # Extract the last user message as the question
+                        user_messages = [m for m in request.messages if m.role == "user"]
+                        if not user_messages:
+                            raise HTTPException(status_code=400, detail="No user message found")
+                        
+                        question = user_messages[-1].content
+                        
+                        # Use RAG if enabled
+                        if request.rag:
+                            result = rag.query(question)
+                            answer = result.answer
+                        else:
+                            # Direct LLM call without RAG
+                            if rag.llm:
+                                answer = rag._generate(question)
+                            else:
+                                answer = "LLM not available"
+                        
+                        response = ChatCompletionResponse(
+                            id=f"chatcmpl-{uuid.uuid4().hex[:8]}",
+                            created=int(time_module.time()),
+                            model=request.model,
+                            choices=[
+                                ChatCompletionChoice(
+                                    index=0,
+                                    message=ChatMessage(role="assistant", content=answer),
+                                    finish_reason="stop",
+                                )
+                            ],
+                            usage={
+                                "prompt_tokens": 0,  # Not tracked
+                                "completion_tokens": 0,
+                                "total_tokens": 0,
+                            },
+                        )
+                        
+                        return response
+                    except HTTPException:
+                        raise
+                    except Exception as e:
+                        raise HTTPException(status_code=500, detail=str(e))
+            
+            # Print startup info
+            console.print("\n[bold green]Starting RAG API server[/bold green]")
+            console.print(f"  Collection: {collection}")
+            console.print(f"  Hybrid retrieval: {'enabled' if hybrid else 'disabled'}")
+            console.print(f"  Reranking: {'enabled' if rerank else 'disabled'}")
+            console.print(f"  OpenAI-compat: {'enabled' if openai_compat else 'disabled'}")
+            console.print(f"  URL: http://{host}:{port}")
+            console.print(f"  Docs: http://{host}:{port}/docs")
+            console.print("\n[dim]Endpoints:[/dim]")
+            console.print("  GET  /health")
+            console.print("  POST /rag/query")
+            console.print("  POST /rag/chat (SSE streaming)")
+            if openai_compat:
+                console.print("  POST /v1/chat/completions (OpenAI-compatible)")
+            console.print()
+            
+            if profile_data:
+                profile_data["command"] = "rag serve"
+                profile_data["collection"] = collection
+                profile_data["hybrid"] = hybrid
+                profile_data["rerank"] = rerank
+                profile_data["openai_compat"] = openai_compat
+            
+            uvicorn.run(api, host=host, port=port)
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            if verbose:
+                import traceback
+                console.print(traceback.format_exc())
+            raise typer.Exit(1)

src/praisonai/praisonai/cli/commands/retrieval.py

@@ -0,0 +1,377 @@
+"""
+Unified Retrieval CLI Commands - Agent-First Experience
+
+This module provides the unified CLI commands for knowledge and retrieval:
+- `praisonai index` - Index documents into knowledge base
+- `praisonai query` - Query with structured answer and citations
+- `praisonai chat` - Conversational interface with knowledge (handled by chat.py)
+
+These commands replace the separate `knowledge` and `rag` command families.
+"""
+
+import typer
+from pathlib import Path
+from typing import List, Optional
+from contextlib import contextmanager
+import time
+import sys
+
+app = typer.Typer(
+    name="retrieval",
+    help="Knowledge indexing and retrieval commands",
+    no_args_is_help=True,
+)
+
+
+@contextmanager
+def retrieval_profiler(profile: bool, profile_out: Optional[Path], profile_top: int):
+    """Context manager for profiling retrieval operations."""
+    if not profile:
+        yield None
+        return
+    
+    import json as json_module
+    
+    start_time = time.perf_counter()
+    start_modules = set(sys.modules.keys())
+    
+    profile_data = {
+        "metrics": {},
+        "modules_loaded": [],
+    }
+    
+    try:
+        import tracemalloc
+        tracemalloc.start()
+        has_tracemalloc = True
+    except ImportError:
+        has_tracemalloc = False
+    
+    yield profile_data
+    
+    elapsed_ms = (time.perf_counter() - start_time) * 1000
+    profile_data["metrics"]["elapsed_ms"] = elapsed_ms
+    
+    if has_tracemalloc:
+        current, peak = tracemalloc.get_traced_memory()
+        tracemalloc.stop()
+        profile_data["metrics"]["peak_memory_mb"] = peak / 1024 / 1024
+    
+    new_modules = set(sys.modules.keys()) - start_modules
+    profile_data["modules_loaded"] = sorted(list(new_modules))[:profile_top]
+    
+    if profile_out:
+        try:
+            profile_out.parent.mkdir(parents=True, exist_ok=True)
+            with open(profile_out, "w") as f:
+                json_module.dump(profile_data, f, indent=2, default=str)
+        except Exception as e:
+            print(f"Warning: Failed to save profile: {e}")
+    
+    from rich.console import Console
+    console = Console(stderr=True)
+    console.print(f"\n[dim]Profile: {elapsed_ms:.2f}ms wall time[/dim]")
+    if "peak_memory_mb" in profile_data["metrics"]:
+        console.print(f"[dim]Profile: {profile_data['metrics']['peak_memory_mb']:.2f}MB peak memory[/dim]")
+    console.print(f"[dim]Profile: {len(new_modules)} modules imported[/dim]")
+    if profile_out:
+        console.print(f"[dim]Profile saved to: {profile_out}[/dim]")
+
+
+@app.command("index")
+def index_command(
+    sources: List[str] = typer.Argument(..., help="Source files, directories, or URLs to index"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection/knowledge base name"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Index documents into a knowledge base.
+    
+    This is the canonical command for adding documents to a knowledge base.
+    Use `praisonai query` to get answers with citations from the indexed knowledge.
+    
+    Examples:
+        praisonai index ./docs
+        praisonai index paper.pdf --collection research
+        praisonai index ./data --profile --profile-out ./profile.json
+    """
+    from rich.console import Console
+    from rich.progress import Progress, SpinnerColumn, TextColumn
+    
+    console = Console()
+    
+    with retrieval_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            from praisonaiagents.knowledge import Knowledge
+            
+            knowledge_config = {
+                "vector_store": {
+                    "provider": "chroma",
+                    "config": {
+                        "collection_name": collection,
+                        "path": f"./.praison/knowledge/{collection}",
+                    }
+                }
+            }
+            
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "knowledge" in file_config:
+                        knowledge_config.update(file_config["knowledge"])
+            
+            knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+            
+            with Progress(
+                SpinnerColumn(),
+                TextColumn("[progress.description]{task.description}"),
+                console=console,
+                transient=True,
+            ) as progress:
+                for source in sources:
+                    task = progress.add_task(f"Indexing {source}...", total=None)
+                    try:
+                        result = knowledge.add(source)
+                        count = len(result.get("results", [])) if isinstance(result, dict) else 0
+                        console.print(f"[green]✓[/green] Indexed {source}: {count} chunks")
+                    except Exception as e:
+                        console.print(f"[red]✗[/red] Failed to index {source}: {e}")
+                    progress.remove_task(task)
+            
+            console.print(f"\n[bold green]Indexing complete![/bold green] Collection: {collection}")
+            if profile_data:
+                profile_data["command"] = "index"
+                profile_data["collection"] = collection
+                profile_data["sources"] = sources
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            raise typer.Exit(1)
+
+
+@app.command("query")
+def query_command(
+    question: str = typer.Argument(..., help="Question to answer"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to query"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results to retrieve"),
+    min_score: float = typer.Option(0.0, "--min-score", help="Minimum relevance score (0.0-1.0)"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + keyword)"),
+    rerank: bool = typer.Option(False, "--rerank", help="Enable reranking of results"),
+    citations: bool = typer.Option(True, "--citations/--no-citations", help="Include citations"),
+    citations_mode: str = typer.Option("append", "--citations-mode", help="Citations mode: append, inline, hidden"),
+    max_context_tokens: int = typer.Option(4000, "--max-context-tokens", help="Maximum context tokens"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+    profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
+    profile_out: Optional[Path] = typer.Option(None, "--profile-out", help="Save profile to JSON file"),
+    profile_top: int = typer.Option(20, "--profile-top", help="Top N items in profile"),
+):
+    """
+    Query knowledge and get a structured answer with citations.
+    
+    Uses the Agent-first retrieval pipeline with token-aware context building.
+    
+    Examples:
+        praisonai query "What is the main finding?"
+        praisonai query "Summarize the document" --collection research
+        praisonai query "Key points?" --top-k 10 --no-citations
+        praisonai query "Summary?" --hybrid --rerank
+    """
+    from rich.console import Console
+    from rich.panel import Panel
+    from rich.markdown import Markdown
+    
+    console = Console()
+    
+    with retrieval_profiler(profile, profile_out, profile_top) as profile_data:
+        try:
+            from praisonaiagents import Agent
+            from praisonaiagents.rag.retrieval_config import RetrievalConfig, RetrievalPolicy, CitationsMode
+            
+            retrieval_config = RetrievalConfig(
+                enabled=True,
+                policy=RetrievalPolicy.ALWAYS,
+                top_k=top_k,
+                min_score=min_score,
+                max_context_tokens=max_context_tokens,
+                rerank=rerank,
+                hybrid=hybrid,
+                citations=citations,
+                citations_mode=CitationsMode(citations_mode),
+                vector_store_provider="chroma",
+                persist_path=f"./.praison/knowledge/{collection}",
+                collection_name=collection,
+            )
+            
+            if config and config.exists():
+                import yaml
+                with open(config) as f:
+                    file_config = yaml.safe_load(f)
+                    if "retrieval" in file_config:
+                        for key, value in file_config["retrieval"].items():
+                            if hasattr(retrieval_config, key):
+                                setattr(retrieval_config, key, value)
+            
+            agent = Agent(
+                name="QueryAgent",
+                instructions="You are a helpful assistant that answers questions based on the provided knowledge.",
+                knowledge=[],  # Empty - we'll use existing indexed knowledge
+                retrieval_config=retrieval_config,
+                verbose=verbose,
+            )
+            
+            agent._ensure_knowledge_processed = lambda: None
+            from praisonaiagents.knowledge import Knowledge
+            agent.knowledge = Knowledge(config=retrieval_config.to_knowledge_config(), verbose=verbose)
+            agent._knowledge_processed = True
+            
+            if verbose:
+                strategy_str = "hybrid (dense + keyword)" if hybrid else "dense"
+                rerank_str = " with reranking" if rerank else ""
+                console.print(f"[dim]Querying collection '{collection}' using {strategy_str}{rerank_str}, top_k={top_k}...[/dim]")
+            
+            result = agent.query(question)
+            
+            console.print(Panel(
+                Markdown(result.answer),
+                title="[bold]Answer[/bold]",
+                border_style="green",
+            ))
+            
+            if citations and result.citations:
+                console.print("\n[bold]Sources:[/bold]")
+                for citation in result.citations:
+                    score_str = f"[dim](score: {citation.score:.2f})[/dim]" if citation.score else ""
+                    console.print(f"  [{citation.id}] {citation.source} {score_str}")
+                    if verbose:
+                        snippet = citation.text[:200] + "..." if len(citation.text) > 200 else citation.text
+                        console.print(f"      [dim]{snippet}[/dim]")
+            
+            if verbose and result.metadata:
+                elapsed = result.metadata.get('elapsed_seconds', 0)
+                console.print(f"\n[dim]Elapsed: {elapsed:.2f}s[/dim]")
+            
+            if profile_data:
+                profile_data["command"] = "query"
+                profile_data["collection"] = collection
+                profile_data["question"] = question
+            
+        except ImportError as e:
+            console.print(f"[red]Error:[/red] Missing dependency: {e}")
+            console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+            raise typer.Exit(1)
+        except Exception as e:
+            console.print(f"[red]Error:[/red] {e}")
+            if verbose:
+                import traceback
+                console.print(traceback.format_exc())
+            raise typer.Exit(1)
+
+
+@app.command("search")
+def search_command(
+    query: str = typer.Argument(..., help="Search query"),
+    collection: str = typer.Option("default", "--collection", "-c", help="Collection to search"),
+    top_k: int = typer.Option(5, "--top-k", "-k", help="Number of results to retrieve"),
+    hybrid: bool = typer.Option(False, "--hybrid", help="Use hybrid retrieval (dense + keyword)"),
+    config: Optional[Path] = typer.Option(None, "--config", "-f", help="Config file path"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
+):
+    """
+    Search/retrieve from a knowledge base (no LLM generation).
+    
+    Returns raw search results without generating an answer.
+    For answers with citations, use `praisonai query`.
+    
+    Examples:
+        praisonai search "capital of France"
+        praisonai search "main findings" --collection research --top-k 10
+    """
+    from rich.console import Console
+    from rich.table import Table
+    
+    console = Console()
+    
+    try:
+        from praisonaiagents.knowledge import Knowledge
+        
+        knowledge_config = {
+            "vector_store": {
+                "provider": "chroma",
+                "config": {
+                    "collection_name": collection,
+                    "path": f"./.praison/knowledge/{collection}",
+                }
+            }
+        }
+        
+        if hybrid:
+            knowledge_config["retrieval"] = {"strategy": "hybrid"}
+        
+        if config and config.exists():
+            import yaml
+            with open(config) as f:
+                file_config = yaml.safe_load(f)
+                if "knowledge" in file_config:
+                    knowledge_config.update(file_config["knowledge"])
+        
+        knowledge = Knowledge(config=knowledge_config, verbose=verbose)
+        
+        if verbose:
+            console.print(f"[dim]Searching collection '{collection}' for: {query}[/dim]")
+        
+        results = knowledge.search(query)
+        
+        if not results:
+            console.print("[yellow]No results found.[/yellow]")
+            return
+        
+        if isinstance(results, dict) and 'results' in results:
+            result_list = results['results']
+        elif isinstance(results, list):
+            result_list = results
+        else:
+            result_list = [results]
+        
+        table = Table(title=f"Search Results ({len(result_list[:top_k])} of {len(result_list)})")
+        table.add_column("#", style="dim", width=3)
+        table.add_column("Score", width=8)
+        table.add_column("Content", overflow="fold")
+        
+        for i, result in enumerate(result_list[:top_k], 1):
+            if isinstance(result, dict):
+                content = result.get('memory', result.get('text', str(result)))
+                score = result.get('score', result.get('distance', 'N/A'))
+            else:
+                content = str(result)
+                score = 'N/A'
+            
+            content_preview = content[:300] + "..." if len(content) > 300 else content
+            score_str = f"{score:.3f}" if isinstance(score, float) else str(score)
+            table.add_row(str(i), score_str, content_preview)
+        
+        console.print(table)
+        
+    except ImportError as e:
+        console.print(f"[red]Error:[/red] Missing dependency: {e}")
+        console.print("Install with: pip install 'praisonaiagents[knowledge]'")
+        raise typer.Exit(1)
+    except Exception as e:
+        console.print(f"[red]Error:[/red] {e}")
+        raise typer.Exit(1)
+
+
+def register_commands(main_app: typer.Typer):
+    """Register unified retrieval commands with the main CLI app."""
+    main_app.command("index")(index_command)
+    main_app.command("query")(query_command)
+    main_app.command("search")(search_command)

src/praisonai/praisonai/cli/commands/run.py

@@ -27,6 +27,8 @@ def run_main(
     memory: bool = typer.Option(False, "--memory", help="Enable memory"),
     tools: Optional[str] = typer.Option(None, "--tools", "-t", help="Tools file path"),
     max_tokens: int = typer.Option(16000, "--max-tokens", help="Maximum output tokens"),
+    profile: bool = typer.Option(False, "--profile", help="Enable CLI profiling (timing breakdown)"),
+    profile_deep: bool = typer.Option(False, "--profile-deep", help="Enable deep profiling (cProfile stats, higher overhead)"),
 ):
     """
     Run agents from a file or prompt.
@@ -35,9 +37,10 @@ def run_main(
         praisonai run agents.yaml
         praisonai run "What is the weather?"
         praisonai run agents.yaml --interactive
+        praisonai run "What is 2+2?" --profile
     """
     output = get_output_controller()
-    context = get_current_context()
+    _ = get_current_context()  # Initialize context
     
     if not target:
         output.print_panel(
@@ -71,6 +74,27 @@ def run_main(
     import os
     is_file = os.path.exists(target) and (target.endswith('.yaml') or target.endswith('.yml'))
     
+    # Handle profiling
+    if profile or profile_deep:
+        if is_file:
+            # Profiling for YAML file execution
+            _run_from_file_profiled(
+                target,
+                model=model,
+                framework=framework,
+                verbose=verbose,
+                profile_deep=profile_deep,
+            )
+        else:
+            # Profiling for direct prompt
+            _run_prompt_profiled(
+                target,
+                model=model,
+                verbose=verbose,
+                profile_deep=profile_deep,
+            )
+        return
+    
     if is_file:
         # Run from file
         _run_from_file(
@@ -226,3 +250,116 @@ def _run_prompt(
         output.emit_error(message=str(e))
         output.print_error(str(e))
         raise typer.Exit(1)
+
+
+def _run_from_file_profiled(
+    file_path: str,
+    model: Optional[str] = None,
+    framework: Optional[str] = None,
+    verbose: bool = False,
+    profile_deep: bool = False,
+):
+    """Run agents from a YAML file with profiling enabled."""
+    from praisonai.cli.features.cli_profiler import (
+        CLIProfileConfig,
+        CLIProfiler,
+    )
+    
+    config = CLIProfileConfig(enabled=True, deep=profile_deep)
+    profiler = CLIProfiler(config)
+    
+    if profile_deep:
+        typer.echo("⚠️  Deep profiling enabled - this adds significant overhead", err=True)
+    
+    profiler.start()
+    
+    # Import phase
+    profiler.mark_import_start()
+    try:
+        from praisonai.cli.main import PraisonAI
+    except ImportError as e:
+        typer.echo(f"Error: {e}", err=True)
+        raise typer.Exit(1)
+    profiler.mark_import_end()
+    
+    # Agent initialization phase
+    profiler.mark_init_start()
+    praison = PraisonAI(
+        agent_file=file_path,
+        framework=framework or "praisonai",
+    )
+    if model:
+        praison.config_list[0]['model'] = model
+    profiler.mark_init_end()
+    
+    # Execution phase
+    profiler.mark_exec_start()
+    result = praison.run()
+    profiler.mark_exec_end()
+    
+    profiler.stop()
+    
+    # Print result
+    if result:
+        print(result)
+    
+    # Print profiling report
+    profiler.print_report()
+
+
+def _run_prompt_profiled(
+    prompt: str,
+    model: Optional[str] = None,
+    verbose: bool = False,
+    profile_deep: bool = False,
+):
+    """Run a direct prompt with profiling enabled."""
+    from praisonai.cli.features.cli_profiler import (
+        CLIProfileConfig,
+        CLIProfiler,
+    )
+    
+    config = CLIProfileConfig(enabled=True, deep=profile_deep)
+    profiler = CLIProfiler(config)
+    
+    if profile_deep:
+        typer.echo("⚠️  Deep profiling enabled - this adds significant overhead", err=True)
+    
+    profiler.start()
+    
+    # Import phase
+    profiler.mark_import_start()
+    try:
+        from praisonaiagents import Agent
+    except ImportError:
+        typer.echo("Error: praisonaiagents not installed", err=True)
+        raise typer.Exit(1)
+    profiler.mark_import_end()
+    
+    # Agent initialization phase
+    profiler.mark_init_start()
+    agent_config = {
+        "name": "RunAgent",
+        "role": "Assistant",
+        "goal": "Complete the task",
+        "verbose": verbose,
+    }
+    if model:
+        agent_config["llm"] = model
+    
+    agent = Agent(**agent_config)
+    profiler.mark_init_end()
+    
+    # Execution phase
+    profiler.mark_exec_start()
+    response = agent.start(prompt)
+    profiler.mark_exec_end()
+    
+    profiler.stop()
+    
+    # Print response
+    if response:
+        print(response)
+    
+    # Print profiling report
+    profiler.print_report()

src/praisonai/praisonai/cli/commands/session.py

@@ -210,3 +210,39 @@ def session_show(
         f"Workspace: {session.workspace or '-'}",
         title="Session Details"
     )
+
+
+@app.command("import")
+def session_import(
+    input_file: str = typer.Argument(..., help="Session file to import (JSON format)"),
+):
+    """Import a session from a file."""
+    import json
+    
+    output = get_output_controller()
+    
+    try:
+        with open(input_file, "r", encoding="utf-8") as f:
+            data = json.load(f)
+    except FileNotFoundError:
+        output.print_error(f"File not found: {input_file}")
+        raise typer.Exit(1)
+    except json.JSONDecodeError as e:
+        output.print_error(f"Invalid JSON: {e}")
+        raise typer.Exit(1)
+    
+    # Use InteractiveCore to import
+    try:
+        from praisonai.cli.interactive import InteractiveCore
+        
+        core = InteractiveCore()
+        session_id = core.import_session(data)
+        
+        if output.is_json_mode:
+            output.print_json({"imported": True, "session_id": session_id})
+        else:
+            output.print_success(f"Imported session: {session_id}")
+            
+    except Exception as e:
+        output.print_error(f"Import failed: {e}")
+        raise typer.Exit(1)

src/praisonai/praisonai/cli/commands/ui.py

@@ -1,47 +1,181 @@
 """
 UI command group for PraisonAI CLI.
 
-Provides web UI commands.
+Provides all browser-based UI commands.
+ALL browser UIs are under this namespace - nothing outside 'praisonai ui' opens a browser.
 """
 
-from typing import Optional
-
 import typer
 
-app = typer.Typer(help="Web UI management")
+app = typer.Typer(help="Browser-based web UI (all browser modes)")
 
 
 @app.callback(invoke_without_command=True)
 def ui_main(
     ctx: typer.Context,
-    port: int = typer.Option(8080, "--port", "-p", help="Port to run UI on"),
+    port: int = typer.Option(8082, "--port", "-p", help="Port to run UI on"),
     host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind to"),
     public: bool = typer.Option(False, "--public", help="Make UI publicly accessible"),
 ):
     """
-    Start the web UI.
+    Start the default web UI (agents management).
+    
+    All browser-based UIs are under this namespace:
+    - praisonai ui         - Default agents UI
+    - praisonai ui chat    - Chat interface
+    - praisonai ui code    - Code assistant interface
+    - praisonai ui realtime - Voice/realtime interface
+    - praisonai ui gradio  - Gradio interface
     
     Examples:
         praisonai ui
         praisonai ui --port 3000
         praisonai ui --public
     """
-    from praisonai.cli.main import PraisonAI
+    # If a subcommand was invoked, don't run the default
+    if ctx.invoked_subcommand is not None:
+        return
+    
+    # Default: launch agents UI (Chainlit)
+    _launch_chainlit_ui("agents", port, host, public)
+
+
+@app.command("chat")
+def ui_chat(
+    port: int = typer.Option(8084, "--port", "-p", help="Port to run UI on"),
+    host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind to"),
+    public: bool = typer.Option(False, "--public", help="Make UI publicly accessible"),
+):
+    """
+    Start the browser-based chat UI (Chainlit).
+    
+    For terminal-native chat, use: praisonai chat
+    
+    Examples:
+        praisonai ui chat
+        praisonai ui chat --port 3000
+    """
+    _launch_chainlit_ui("chat", port, host, public)
+
+
+@app.command("code")
+def ui_code(
+    port: int = typer.Option(8086, "--port", "-p", help="Port to run UI on"),
+    host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind to"),
+    public: bool = typer.Option(False, "--public", help="Make UI publicly accessible"),
+):
+    """
+    Start the browser-based code assistant UI (Chainlit).
+    
+    For terminal-native code assistant, use: praisonai code
+    
+    Examples:
+        praisonai ui code
+        praisonai ui code --port 3000
+    """
+    _launch_chainlit_ui("code", port, host, public)
+
+
+@app.command("realtime")
+def ui_realtime(
+    port: int = typer.Option(8088, "--port", "-p", help="Port to run UI on"),
+    host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind to"),
+    public: bool = typer.Option(False, "--public", help="Make UI publicly accessible"),
+):
+    """
+    Start the browser-based realtime/voice UI (Chainlit).
+    
+    Examples:
+        praisonai ui realtime
+        praisonai ui realtime --port 3000
+    """
+    _launch_chainlit_ui("realtime", port, host, public)
+
+
+@app.command("gradio")
+def ui_gradio(
+    port: int = typer.Option(8080, "--port", "-p", help="Port to run UI on"),
+    host: str = typer.Option("127.0.0.1", "--host", "-h", help="Host to bind to"),
+    public: bool = typer.Option(False, "--public", help="Make UI publicly accessible"),
+):
+    """
+    Start the Gradio-based web UI.
+    
+    Examples:
+        praisonai ui gradio
+        praisonai ui gradio --port 3000
+    """
+    _launch_gradio_ui(port, host, public)
+
+
+def _launch_chainlit_ui(ui_type: str, port: int, host: str, public: bool):
+    """Launch a Chainlit-based UI."""
+    import os
     import sys
     
-    argv = ['ui']
-    argv.extend(['--port', str(port)])
-    argv.extend(['--host', host])
-    if public:
-        argv.append('--public')
-    
-    original_argv = sys.argv
-    sys.argv = ['praisonai'] + argv
-    
     try:
-        praison = PraisonAI()
-        praison.main()
-    except SystemExit:
-        pass
-    finally:
-        sys.argv = original_argv
+        import importlib.util
+        CHAINLIT_AVAILABLE = importlib.util.find_spec("chainlit") is not None
+    except ImportError:
+        CHAINLIT_AVAILABLE = False
+    
+    if not CHAINLIT_AVAILABLE:
+        install_extra = {
+            "agents": "ui",
+            "chat": "chat",
+            "code": "code",
+            "realtime": "realtime",
+        }.get(ui_type, "ui")
+        print(f"[red]ERROR: {ui_type.title()} UI is not installed. Install with:[/red]")
+        print(f'\npip install "praisonai[{install_extra}]"\n')
+        sys.exit(1)
+    
+    import praisonai
+    
+    # Set environment variables
+    os.environ["CHAINLIT_PORT"] = str(port)
+    os.environ["CHAINLIT_HOST"] = host
+    
+    root_path = os.path.join(os.path.expanduser("~"), ".praison")
+    if "CHAINLIT_APP_ROOT" not in os.environ:
+        os.environ["CHAINLIT_APP_ROOT"] = root_path
+    
+    # Determine UI script path
+    ui_scripts = {
+        "agents": "chainlit_ui.py",
+        "chat": os.path.join("ui", "chat.py"),
+        "code": os.path.join("ui", "code.py"),
+        "realtime": os.path.join("ui", "realtime.py"),
+    }
+    
+    ui_script = ui_scripts.get(ui_type, "chainlit_ui.py")
+    ui_path = os.path.join(os.path.dirname(praisonai.__file__), ui_script)
+    
+    # Get chainlit run function
+    from chainlit.cli import run as chainlit_run
+    
+    # Build args
+    args = [ui_path]
+    if host:
+        args.extend(["--host", host])
+    args.extend(["--port", str(port)])
+    
+    print(f"Starting {ui_type} UI at http://{host}:{port}")
+    chainlit_run(args)
+
+
+def _launch_gradio_ui(port: int, host: str, public: bool):
+    """Launch the Gradio-based UI."""
+    import sys
+    import importlib.util
+    
+    GRADIO_AVAILABLE = importlib.util.find_spec("gradio") is not None
+    
+    if not GRADIO_AVAILABLE:
+        print("[red]ERROR: Gradio UI is not installed. Install with:[/red]")
+        print('\npip install "praisonai[gradio]"\n')
+        sys.exit(1)
+    
+    from praisonai.cli.main import PraisonAI
+    praison = PraisonAI()
+    praison.create_gradio_interface()

src/praisonai/praisonai/cli/config_loader.py

@@ -0,0 +1,298 @@
+"""
+Shared configuration loader for PraisonAI CLI commands.
+
+Implements strict precedence:
+1. CLI flags (highest priority)
+2. Environment variables
+3. Config file (YAML)
+4. Defaults (lowest priority)
+
+This module is DRY - used by both knowledge and rag commands.
+"""
+
+import os
+import logging
+from pathlib import Path
+from typing import Any, Dict, Optional
+from dataclasses import dataclass, field
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class RAGCliConfig:
+    """
+    Configuration for RAG/Knowledge CLI commands.
+    
+    Supports loading from multiple sources with proper precedence.
+    """
+    # Collection settings
+    collection: str = "default"
+    
+    # Retrieval settings
+    top_k: int = 5
+    hybrid: bool = False
+    rerank: bool = False
+    min_score: float = 0.0
+    
+    # RAG settings
+    include_citations: bool = True
+    max_context_tokens: int = 4000
+    
+    # Vector store settings
+    vector_store_provider: str = "chroma"
+    vector_store_path: Optional[str] = None
+    
+    # Server settings (for serve command)
+    host: str = "127.0.0.1"
+    port: int = 8080
+    openai_compat: bool = False
+    
+    # LLM settings
+    model: Optional[str] = None
+    
+    # Misc
+    verbose: bool = False
+    
+    def to_knowledge_config(self) -> Dict[str, Any]:
+        """Convert to knowledge config dict."""
+        path = self.vector_store_path or f"./.praison/knowledge/{self.collection}"
+        
+        config = {
+            "vector_store": {
+                "provider": self.vector_store_provider,
+                "config": {
+                    "collection_name": self.collection,
+                    "path": path,
+                }
+            }
+        }
+        
+        if self.hybrid:
+            config["retrieval"] = {
+                "strategy": "hybrid",
+            }
+        
+        return config
+    
+    def to_rag_config_dict(self) -> Dict[str, Any]:
+        """Convert to RAGConfig dict."""
+        config = {
+            "top_k": self.top_k,
+            "include_citations": self.include_citations,
+            "max_context_tokens": self.max_context_tokens,
+            "min_score": self.min_score,
+            "rerank": self.rerank,
+        }
+        
+        if self.hybrid:
+            config["retrieval_strategy"] = "hybrid"
+        
+        if self.model:
+            config["model"] = self.model
+        
+        return config
+
+
+# Environment variable mappings
+ENV_MAPPINGS = {
+    "PRAISONAI_COLLECTION": "collection",
+    "PRAISONAI_TOP_K": ("top_k", int),
+    "PRAISONAI_HYBRID": ("hybrid", lambda x: x.lower() in ("true", "1", "yes")),
+    "PRAISONAI_RERANK": ("rerank", lambda x: x.lower() in ("true", "1", "yes")),
+    "PRAISONAI_MIN_SCORE": ("min_score", float),
+    "PRAISONAI_CITATIONS": ("include_citations", lambda x: x.lower() in ("true", "1", "yes")),
+    "PRAISONAI_MAX_CONTEXT_TOKENS": ("max_context_tokens", int),
+    "PRAISONAI_VECTOR_STORE": "vector_store_provider",
+    "PRAISONAI_VECTOR_STORE_PATH": "vector_store_path",
+    "PRAISONAI_HOST": "host",
+    "PRAISONAI_PORT": ("port", int),
+    "PRAISONAI_OPENAI_COMPAT": ("openai_compat", lambda x: x.lower() in ("true", "1", "yes")),
+    "PRAISONAI_MODEL": "model",
+    "PRAISONAI_VERBOSE": ("verbose", lambda x: x.lower() in ("true", "1", "yes")),
+}
+
+
+def load_config_file(config_path: Path) -> Dict[str, Any]:
+    """
+    Load configuration from a YAML file.
+    
+    Args:
+        config_path: Path to the YAML config file
+        
+    Returns:
+        Dict with configuration values
+    """
+    if not config_path.exists():
+        logger.warning(f"Config file not found: {config_path}")
+        return {}
+    
+    try:
+        import yaml
+        with open(config_path) as f:
+            config = yaml.safe_load(f) or {}
+        return config
+    except Exception as e:
+        logger.error(f"Failed to load config file: {e}")
+        return {}
+
+
+def load_from_env() -> Dict[str, Any]:
+    """
+    Load configuration from environment variables.
+    
+    Returns:
+        Dict with configuration values from environment
+    """
+    config = {}
+    
+    for env_var, mapping in ENV_MAPPINGS.items():
+        value = os.environ.get(env_var)
+        if value is not None:
+            if isinstance(mapping, tuple):
+                attr_name, converter = mapping
+                try:
+                    config[attr_name] = converter(value)
+                except (ValueError, TypeError) as e:
+                    logger.warning(f"Invalid value for {env_var}: {e}")
+            else:
+                config[mapping] = value
+    
+    return config
+
+
+def merge_configs(
+    defaults: Dict[str, Any],
+    file_config: Dict[str, Any],
+    env_config: Dict[str, Any],
+    cli_config: Dict[str, Any],
+) -> Dict[str, Any]:
+    """
+    Merge configurations with proper precedence.
+    
+    Precedence (highest to lowest):
+    1. CLI flags
+    2. Environment variables
+    3. Config file
+    4. Defaults
+    
+    Args:
+        defaults: Default configuration values
+        file_config: Configuration from YAML file
+        env_config: Configuration from environment variables
+        cli_config: Configuration from CLI flags
+        
+    Returns:
+        Merged configuration dict
+    """
+    result = defaults.copy()
+    
+    # Apply file config (lowest priority after defaults)
+    for key, value in file_config.items():
+        if value is not None:
+            result[key] = value
+    
+    # Apply env config (higher priority)
+    for key, value in env_config.items():
+        if value is not None:
+            result[key] = value
+    
+    # Apply CLI config (highest priority)
+    for key, value in cli_config.items():
+        if value is not None:
+            result[key] = value
+    
+    return result
+
+
+def load_cli_config(
+    config_file: Optional[Path] = None,
+    cli_overrides: Optional[Dict[str, Any]] = None,
+) -> RAGCliConfig:
+    """
+    Load CLI configuration with proper precedence.
+    
+    Args:
+        config_file: Optional path to YAML config file
+        cli_overrides: Dict of CLI flag values (only non-None values)
+        
+    Returns:
+        RAGCliConfig instance with merged configuration
+    """
+    # Start with defaults
+    defaults = {
+        "collection": "default",
+        "top_k": 5,
+        "hybrid": False,
+        "rerank": False,
+        "min_score": 0.0,
+        "include_citations": True,
+        "max_context_tokens": 4000,
+        "vector_store_provider": "chroma",
+        "vector_store_path": None,
+        "host": "127.0.0.1",
+        "port": 8080,
+        "openai_compat": False,
+        "model": None,
+        "verbose": False,
+    }
+    
+    # Load from config file
+    file_config = {}
+    if config_file:
+        raw_config = load_config_file(config_file)
+        # Flatten nested config
+        if "knowledge" in raw_config:
+            file_config.update(raw_config["knowledge"])
+        if "rag" in raw_config:
+            file_config.update(raw_config["rag"])
+        if "retrieval" in raw_config:
+            file_config.update(raw_config["retrieval"])
+        # Also check for top-level keys
+        for key in defaults.keys():
+            if key in raw_config:
+                file_config[key] = raw_config[key]
+    
+    # Load from environment
+    env_config = load_from_env()
+    
+    # CLI overrides (filter out None values)
+    cli_config = {k: v for k, v in (cli_overrides or {}).items() if v is not None}
+    
+    # Merge with precedence
+    merged = merge_configs(defaults, file_config, env_config, cli_config)
+    
+    # Create config object
+    return RAGCliConfig(**{k: v for k, v in merged.items() if k in RAGCliConfig.__dataclass_fields__})
+
+
+def get_config_schema() -> Dict[str, Any]:
+    """
+    Get the configuration schema for documentation.
+    
+    Returns:
+        Dict describing the configuration schema
+    """
+    return {
+        "knowledge": {
+            "collection": "Collection/index name (default: 'default')",
+            "vector_store_provider": "Vector store provider (default: 'chroma')",
+            "vector_store_path": "Path to vector store (default: './.praison/knowledge/{collection}')",
+        },
+        "retrieval": {
+            "top_k": "Number of results to retrieve (default: 5)",
+            "hybrid": "Enable hybrid retrieval (default: false)",
+            "rerank": "Enable reranking (default: false)",
+            "min_score": "Minimum relevance score (default: 0.0)",
+        },
+        "rag": {
+            "include_citations": "Include citations in response (default: true)",
+            "max_context_tokens": "Maximum context tokens (default: 4000)",
+            "model": "LLM model to use (default: gpt-4o-mini)",
+        },
+        "server": {
+            "host": "Server host (default: '127.0.0.1')",
+            "port": "Server port (default: 8080)",
+            "openai_compat": "Enable OpenAI-compatible endpoint (default: false)",
+        },
+    }

src/praisonai/praisonai/cli/features/cli_profiler.py

@@ -0,0 +1,335 @@
+"""
+CLI Profiler - Unified profiling for terminal-native CLI commands.
+
+Provides --profile and --profile-deep flags for eligible commands:
+- praisonai "prompt"
+- praisonai chat
+- praisonai chat "prompt"
+- praisonai code
+- praisonai code "prompt"
+- praisonai run agents.yaml
+
+NOT supported for:
+- praisonai ui ... (browser-based)
+- praisonai tui (Textual TUI)
+- praisonai call (long-running server)
+"""
+
+import time
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+import typer
+
+
+# Commands that support profiling
+PROFILING_ELIGIBLE_COMMANDS = frozenset({
+    "chat",
+    "code",
+    "run",
+    # Direct prompt is handled separately in main.py
+})
+
+# Commands that explicitly reject profiling
+PROFILING_INELIGIBLE_COMMANDS = frozenset({
+    "ui",
+    "tui",
+    "call",
+    "realtime",
+    "serve",
+    "schedule",
+    "acp",
+    "mcp",
+    "lsp",
+})
+
+
+@dataclass
+class CLIProfileConfig:
+    """Configuration for CLI profiling."""
+    enabled: bool = False
+    deep: bool = False
+    output_format: str = "text"  # text or json
+    save_path: Optional[str] = None
+    
+    @classmethod
+    def from_flags(cls, profile: bool = False, profile_deep: bool = False) -> 'CLIProfileConfig':
+        """Create config from CLI flags."""
+        return cls(
+            enabled=profile or profile_deep,
+            deep=profile_deep,
+        )
+
+
+@dataclass
+class CLIProfileResult:
+    """Result from CLI profiling."""
+    import_time_ms: float = 0.0
+    agent_init_time_ms: float = 0.0
+    execution_time_ms: float = 0.0
+    total_time_ms: float = 0.0
+    response: str = ""
+    
+    # Deep profiling data (only if deep=True)
+    function_stats: Optional[list] = None
+    call_graph: Optional[dict] = None
+    
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert to dictionary."""
+        result = {
+            "import_time_ms": self.import_time_ms,
+            "agent_init_time_ms": self.agent_init_time_ms,
+            "execution_time_ms": self.execution_time_ms,
+            "total_time_ms": self.total_time_ms,
+        }
+        if self.function_stats:
+            result["function_stats"] = self.function_stats
+        if self.call_graph:
+            result["call_graph"] = self.call_graph
+        return result
+
+
+def print_profile_report(result: CLIProfileResult, config: CLIProfileConfig):
+    """Print profiling report to console."""
+    try:
+        from rich.console import Console
+        from rich.table import Table
+        from rich.panel import Panel
+        console = Console()
+    except ImportError:
+        # Fallback to simple output
+        print("\n─── Profiling ───")
+        print(f"Import:      {result.import_time_ms:.1f}ms")
+        print(f"Agent setup: {result.agent_init_time_ms:.1f}ms")
+        print(f"Execution:   {result.execution_time_ms:.1f}ms")
+        print(f"Total:       {result.total_time_ms:.1f}ms")
+        return
+    
+    # Create timing table
+    table = Table(show_header=False, box=None, padding=(0, 1))
+    table.add_column("Phase", style="cyan")
+    table.add_column("Time", style="green", justify="right")
+    
+    table.add_row("Import", f"{result.import_time_ms:.1f}ms")
+    table.add_row("Agent setup", f"{result.agent_init_time_ms:.1f}ms")
+    table.add_row("Execution", f"{result.execution_time_ms:.1f}ms")
+    table.add_row("─" * 12, "─" * 10)
+    table.add_row("Total", f"{result.total_time_ms:.1f}ms")
+    
+    console.print("\n")
+    console.print(Panel(table, title="[bold]Profiling[/bold]", border_style="dim"))
+    
+    # Deep profiling output
+    if config.deep and result.function_stats:
+        console.print("\n[bold yellow]⚠️  Deep profiling enabled - overhead included in measurements[/bold yellow]")
+        
+        func_table = Table(title="Top Functions by Cumulative Time")
+        func_table.add_column("Function", style="cyan")
+        func_table.add_column("Calls", justify="right")
+        func_table.add_column("Cumul (ms)", justify="right", style="green")
+        
+        for func in result.function_stats[:15]:
+            name = func.get("name", "")[:40]
+            calls = func.get("calls", 0)
+            cumtime = func.get("cumulative_time_ms", 0)
+            func_table.add_row(name, str(calls), f"{cumtime:.2f}")
+        
+        console.print(func_table)
+
+
+def reject_profiling_for_command(command_name: str):
+    """Raise error if profiling is attempted on ineligible command."""
+    if command_name in PROFILING_INELIGIBLE_COMMANDS:
+        raise typer.BadParameter(
+            f"Profiling is not supported for '{command_name}' command.\n"
+            f"Profiling is only available for terminal-native execution commands:\n"
+            f"  praisonai \"prompt\" --profile\n"
+            f"  praisonai chat \"prompt\" --profile\n"
+            f"  praisonai code \"prompt\" --profile\n"
+            f"  praisonai run agents.yaml --profile"
+        )
+
+
+class CLIProfiler:
+    """
+    CLI Profiler for wrapping command execution.
+    
+    Usage:
+        profiler = CLIProfiler(config)
+        with profiler.profile():
+            # execution code
+        profiler.print_report()
+    """
+    
+    def __init__(self, config: CLIProfileConfig):
+        self.config = config
+        self._result = CLIProfileResult()
+        self._start_time: float = 0.0
+        self._cprofile = None
+        
+        # Phase timestamps
+        self._import_start: float = 0.0
+        self._import_end: float = 0.0
+        self._init_start: float = 0.0
+        self._init_end: float = 0.0
+        self._exec_start: float = 0.0
+        self._exec_end: float = 0.0
+    
+    def start(self):
+        """Start profiling."""
+        if not self.config.enabled:
+            return
+        
+        self._start_time = time.perf_counter()
+        
+        if self.config.deep:
+            import cProfile
+            self._cprofile = cProfile.Profile()
+            self._cprofile.enable()
+    
+    def stop(self):
+        """Stop profiling and compute results."""
+        if not self.config.enabled:
+            return
+        
+        end_time = time.perf_counter()
+        
+        if self._cprofile:
+            self._cprofile.disable()
+            self._extract_cprofile_stats()
+        
+        self._result.total_time_ms = (end_time - self._start_time) * 1000
+    
+    def mark_import_start(self):
+        """Mark start of import phase."""
+        if self.config.enabled:
+            self._import_start = time.perf_counter()
+    
+    def mark_import_end(self):
+        """Mark end of import phase."""
+        if self.config.enabled:
+            self._import_end = time.perf_counter()
+            self._result.import_time_ms = (self._import_end - self._import_start) * 1000
+    
+    def mark_init_start(self):
+        """Mark start of agent initialization."""
+        if self.config.enabled:
+            self._init_start = time.perf_counter()
+    
+    def mark_init_end(self):
+        """Mark end of agent initialization."""
+        if self.config.enabled:
+            self._init_end = time.perf_counter()
+            self._result.agent_init_time_ms = (self._init_end - self._init_start) * 1000
+    
+    def mark_exec_start(self):
+        """Mark start of execution."""
+        if self.config.enabled:
+            self._exec_start = time.perf_counter()
+    
+    def mark_exec_end(self):
+        """Mark end of execution."""
+        if self.config.enabled:
+            self._exec_end = time.perf_counter()
+            self._result.execution_time_ms = (self._exec_end - self._exec_start) * 1000
+    
+    def set_response(self, response: str):
+        """Set the response for the profile result."""
+        self._result.response = response
+    
+    def _extract_cprofile_stats(self):
+        """Extract statistics from cProfile."""
+        if not self._cprofile:
+            return
+        
+        import pstats
+        
+        stats = pstats.Stats(self._cprofile)
+        stats.sort_stats("cumulative")
+        
+        function_stats = []
+        for (filename, line, name), (cc, nc, tt, ct, callers) in stats.stats.items():
+            if len(function_stats) >= 100:
+                break
+            function_stats.append({
+                "name": name,
+                "file": filename,
+                "line": line,
+                "calls": nc,
+                "total_time_ms": tt * 1000,
+                "cumulative_time_ms": ct * 1000,
+            })
+        
+        function_stats.sort(key=lambda x: x["cumulative_time_ms"], reverse=True)
+        self._result.function_stats = function_stats[:30]
+    
+    def get_result(self) -> CLIProfileResult:
+        """Get the profiling result."""
+        return self._result
+    
+    def print_report(self):
+        """Print the profiling report."""
+        if self.config.enabled:
+            print_profile_report(self._result, self.config)
+
+
+def run_with_profiling(
+    prompt: str,
+    config: CLIProfileConfig,
+    model: Optional[str] = None,
+    verbose: bool = False,
+    tools: Optional[str] = None,
+) -> tuple:
+    """
+    Run a prompt with profiling enabled.
+    
+    Returns:
+        Tuple of (response, CLIProfileResult)
+    """
+    profiler = CLIProfiler(config)
+    profiler.start()
+    
+    # Import phase
+    profiler.mark_import_start()
+    try:
+        from praisonaiagents import Agent
+    except ImportError:
+        raise ImportError("praisonaiagents not installed. Install with: pip install praisonaiagents")
+    profiler.mark_import_end()
+    
+    # Agent initialization phase
+    profiler.mark_init_start()
+    agent_config = {
+        "name": "ProfiledAgent",
+        "role": "Assistant",
+        "goal": "Complete the task",
+        "verbose": verbose,
+    }
+    if model:
+        agent_config["llm"] = model
+    
+    agent = Agent(**agent_config)
+    profiler.mark_init_end()
+    
+    # Execution phase
+    profiler.mark_exec_start()
+    response = agent.start(prompt)
+    profiler.mark_exec_end()
+    
+    profiler.stop()
+    profiler.set_response(str(response) if response else "")
+    
+    return response, profiler.get_result()
+
+
+# Export all
+__all__ = [
+    "CLIProfileConfig",
+    "CLIProfileResult",
+    "CLIProfiler",
+    "PROFILING_ELIGIBLE_COMMANDS",
+    "PROFILING_INELIGIBLE_COMMANDS",
+    "print_profile_report",
+    "reject_profiling_for_command",
+    "run_with_profiling",
+]

src/praisonai/praisonai/cli/features/context_manager.py

@@ -0,0 +1,525 @@
+"""
+Context Management CLI Feature for PraisonAI.
+
+Provides CLI commands and integration for context budgeting,
+optimization, and monitoring.
+"""
+
+import os
+from typing import Dict, List, Any, Optional, Literal
+from dataclasses import dataclass
+
+
+@dataclass
+class ContextManagerConfig:
+    """Configuration for context management."""
+    # Auto-compaction
+    auto_compact: bool = True
+    compact_threshold: float = 0.8
+    strategy: str = "smart"
+    
+    # Output reserve
+    output_reserve: int = 8000
+    
+    # Monitoring
+    monitor_enabled: bool = False
+    monitor_path: str = "./context.txt"
+    monitor_format: Literal["human", "json"] = "human"
+    monitor_frequency: Literal["turn", "tool_call", "manual", "overflow"] = "turn"
+    redact_sensitive: bool = True
+    
+    @classmethod
+    def from_env(cls) -> "ContextManagerConfig":
+        """Load config from environment variables."""
+        return cls(
+            auto_compact=os.getenv("PRAISONAI_CONTEXT_AUTO_COMPACT", "true").lower() == "true",
+            compact_threshold=float(os.getenv("PRAISONAI_CONTEXT_THRESHOLD", "0.8")),
+            strategy=os.getenv("PRAISONAI_CONTEXT_STRATEGY", "smart"),
+            output_reserve=int(os.getenv("PRAISONAI_CONTEXT_OUTPUT_RESERVE", "8000")),
+            monitor_enabled=os.getenv("PRAISONAI_CONTEXT_MONITOR", "false").lower() == "true",
+            monitor_path=os.getenv("PRAISONAI_CONTEXT_MONITOR_PATH", "./context.txt"),
+            monitor_format=os.getenv("PRAISONAI_CONTEXT_MONITOR_FORMAT", "human"),
+            monitor_frequency=os.getenv("PRAISONAI_CONTEXT_MONITOR_FREQUENCY", "turn"),
+            redact_sensitive=os.getenv("PRAISONAI_CONTEXT_REDACT", "true").lower() == "true",
+        )
+    
+    def merge_cli_args(
+        self,
+        auto_compact: Optional[bool] = None,
+        strategy: Optional[str] = None,
+        threshold: Optional[float] = None,
+        monitor: Optional[bool] = None,
+        monitor_path: Optional[str] = None,
+        monitor_format: Optional[str] = None,
+        monitor_frequency: Optional[str] = None,
+        redact: Optional[bool] = None,
+        output_reserve: Optional[int] = None,
+    ) -> "ContextManagerConfig":
+        """Merge CLI arguments (highest precedence)."""
+        return ContextManagerConfig(
+            auto_compact=auto_compact if auto_compact is not None else self.auto_compact,
+            compact_threshold=threshold if threshold is not None else self.compact_threshold,
+            strategy=strategy if strategy is not None else self.strategy,
+            output_reserve=output_reserve if output_reserve is not None else self.output_reserve,
+            monitor_enabled=monitor if monitor is not None else self.monitor_enabled,
+            monitor_path=monitor_path if monitor_path is not None else self.monitor_path,
+            monitor_format=monitor_format if monitor_format is not None else self.monitor_format,
+            monitor_frequency=monitor_frequency if monitor_frequency is not None else self.monitor_frequency,
+            redact_sensitive=redact if redact is not None else self.redact_sensitive,
+        )
+
+
+class ContextManagerHandler:
+    """
+    Handles context management for interactive CLI sessions.
+    
+    Integrates budgeting, composition, optimization, and monitoring.
+    """
+    
+    def __init__(
+        self,
+        config: Optional[ContextManagerConfig] = None,
+        model: str = "gpt-4o-mini",
+        session_id: str = "",
+        agent_name: str = "Assistant",
+    ):
+        """
+        Initialize context manager.
+        
+        Args:
+            config: Context management configuration
+            model: Model name for budget calculation
+            session_id: Session identifier
+            agent_name: Agent name for monitoring
+        """
+        self.config = config or ContextManagerConfig.from_env()
+        self.model = model
+        self.session_id = session_id
+        self.agent_name = agent_name
+        
+        # Lazy-loaded components
+        self._budgeter = None
+        self._composer = None
+        self._monitor = None
+        self._ledger = None
+    
+    @property
+    def budgeter(self):
+        """Get or create budgeter."""
+        if self._budgeter is None:
+            from praisonaiagents.context import ContextBudgeter
+            self._budgeter = ContextBudgeter(
+                model=self.model,
+                output_reserve=self.config.output_reserve,
+            )
+        return self._budgeter
+    
+    @property
+    def composer(self):
+        """Get or create composer."""
+        if self._composer is None:
+            from praisonaiagents.context import ContextComposer
+            self._composer = ContextComposer(
+                budget=self.budgeter.allocate(),
+            )
+        return self._composer
+    
+    @property
+    def monitor(self):
+        """Get or create monitor."""
+        if self._monitor is None:
+            from praisonaiagents.context import ContextMonitor
+            self._monitor = ContextMonitor(
+                enabled=self.config.monitor_enabled,
+                path=self.config.monitor_path,
+                format=self.config.monitor_format,
+                frequency=self.config.monitor_frequency,
+                redact_sensitive=self.config.redact_sensitive,
+            )
+        return self._monitor
+    
+    @property
+    def ledger(self):
+        """Get or create ledger manager."""
+        if self._ledger is None:
+            from praisonaiagents.context import ContextLedgerManager
+            self._ledger = ContextLedgerManager(agent_id=self.agent_name)
+            self._ledger.set_budget(self.budgeter.allocate())
+        return self._ledger
+    
+    def set_model(self, model: str) -> None:
+        """Update model and reset budgeter."""
+        self.model = model
+        self._budgeter = None
+        self._composer = None
+    
+    def get_stats(self) -> Dict[str, Any]:
+        """Get current context statistics."""
+        budget = self.budgeter.allocate()
+        ledger_data = self.ledger.to_dict()
+        
+        return {
+            "model": self.model,
+            "model_limit": budget.model_limit,
+            "output_reserve": budget.output_reserve,
+            "usable": budget.usable,
+            "total_tokens": self.ledger.get_total(),
+            "utilization": self.ledger.get_utilization(),
+            "turn_count": self.ledger.get_ledger().turn_count,
+            "message_count": self.ledger.get_ledger().message_count,
+            "segments": ledger_data.get("segments", {}),
+            "warnings": self.ledger.get_warnings(),
+            "auto_compact": self.config.auto_compact,
+            "monitor_enabled": self.config.monitor_enabled,
+        }
+    
+    def track_history(self, messages: List[Dict[str, Any]]) -> int:
+        """Track conversation history tokens."""
+        return self.ledger.track_history(messages)
+    
+    def track_system_prompt(self, content: str) -> int:
+        """Track system prompt tokens."""
+        return self.ledger.track_system_prompt(content)
+    
+    def track_tools(self, tools: List[Dict[str, Any]]) -> int:
+        """Track tool schema tokens."""
+        return self.ledger.track_tools(tools)
+    
+    def check_overflow(self) -> bool:
+        """Check if context is approaching limit."""
+        return self.budgeter.check_overflow(
+            self.ledger.get_total(),
+            threshold=self.config.compact_threshold,
+        )
+    
+    def should_auto_compact(self) -> bool:
+        """Check if auto-compaction should trigger."""
+        return self.config.auto_compact and self.check_overflow()
+    
+    def optimize(
+        self,
+        messages: List[Dict[str, Any]],
+        strategy: Optional[str] = None,
+    ) -> tuple:
+        """
+        Optimize messages using configured strategy.
+        
+        Args:
+            messages: Messages to optimize
+            strategy: Override strategy
+            
+        Returns:
+            Tuple of (optimized_messages, result)
+        """
+        from praisonaiagents.context import get_optimizer, OptimizerStrategy
+        
+        strategy_name = strategy or self.config.strategy
+        try:
+            strategy_enum = OptimizerStrategy(strategy_name)
+        except ValueError:
+            strategy_enum = OptimizerStrategy.SMART
+        
+        optimizer = get_optimizer(strategy_enum)
+        target = int(self.budgeter.usable * self.config.compact_threshold)
+        
+        return optimizer.optimize(messages, target, self.ledger.get_ledger())
+    
+    def write_snapshot(
+        self,
+        messages: List[Dict[str, Any]],
+        trigger: str = "manual",
+    ) -> Optional[str]:
+        """
+        Write context snapshot to disk.
+        
+        Args:
+            messages: Current messages
+            trigger: What triggered the snapshot
+            
+        Returns:
+            Path to written file, or None
+        """
+        return self.monitor.snapshot(
+            ledger=self.ledger.get_ledger(),
+            budget=self.budgeter.allocate(),
+            messages=messages,
+            session_id=self.session_id,
+            agent_name=self.agent_name,
+            model_name=self.model,
+            trigger=trigger,
+        )
+    
+    def enable_monitor(self) -> None:
+        """Enable context monitoring."""
+        self.config.monitor_enabled = True
+        self.monitor.enable()
+    
+    def disable_monitor(self) -> None:
+        """Disable context monitoring."""
+        self.config.monitor_enabled = False
+        self.monitor.disable()
+    
+    def set_monitor_path(self, path: str) -> None:
+        """Set monitor output path."""
+        self.config.monitor_path = path
+        self.monitor.set_path(path)
+    
+    def set_monitor_format(self, format: str) -> None:
+        """Set monitor output format."""
+        self.config.monitor_format = format
+        self.monitor.set_format(format)
+    
+    def set_monitor_frequency(self, frequency: str) -> None:
+        """Set monitor update frequency."""
+        self.config.monitor_frequency = frequency
+        self.monitor.set_frequency(frequency)
+
+
+def handle_context_command(
+    console,
+    args: str,
+    session_state: Dict[str, Any],
+    context_manager: Optional[ContextManagerHandler] = None,
+) -> None:
+    """
+    Handle /context command and subcommands.
+    
+    Usage:
+        /context              - Show context stats
+        /context show         - Show summary + budgets
+        /context stats        - Token ledger table
+        /context budget       - Budget allocation details
+        /context dump         - Write snapshot now
+        /context on           - Enable monitoring
+        /context off          - Disable monitoring
+        /context path <path>  - Set snapshot path
+        /context format <fmt> - Set format (human/json)
+        /context frequency <f>- Set frequency
+        /context compact      - Trigger optimization
+    """
+    args = args.strip().lower() if args else ""
+    parts = args.split(maxsplit=1)
+    subcommand = parts[0] if parts else ""
+    subargs = parts[1] if len(parts) > 1 else ""
+    
+    # Get or create context manager
+    if context_manager is None:
+        context_manager = session_state.get("context_manager")
+        if context_manager is None:
+            context_manager = ContextManagerHandler(
+                model=session_state.get("current_model", "gpt-4o-mini"),
+                session_id=session_state.get("session_id", ""),
+            )
+            session_state["context_manager"] = context_manager
+    
+    # Update history tracking
+    history = session_state.get("conversation_history", [])
+    context_manager.track_history(history)
+    
+    if subcommand in ("", "show"):
+        _show_context_summary(console, context_manager)
+    elif subcommand == "stats":
+        _show_context_stats(console, context_manager)
+    elif subcommand == "budget":
+        _show_budget_details(console, context_manager)
+    elif subcommand == "dump":
+        _dump_context(console, context_manager, history)
+    elif subcommand == "on":
+        context_manager.enable_monitor()
+        console.print("[green]✓ Context monitoring enabled[/green]")
+        console.print(f"[dim]Output: {context_manager.config.monitor_path}[/dim]")
+    elif subcommand == "off":
+        context_manager.disable_monitor()
+        console.print("[yellow]Context monitoring disabled[/yellow]")
+    elif subcommand == "path":
+        if subargs:
+            context_manager.set_monitor_path(subargs)
+            console.print(f"[green]✓ Monitor path set to: {subargs}[/green]")
+        else:
+            console.print(f"[cyan]Current path: {context_manager.config.monitor_path}[/cyan]")
+    elif subcommand == "format":
+        if subargs in ("human", "json"):
+            context_manager.set_monitor_format(subargs)
+            console.print(f"[green]✓ Monitor format set to: {subargs}[/green]")
+        else:
+            console.print("[yellow]Format must be 'human' or 'json'[/yellow]")
+    elif subcommand == "frequency":
+        valid = ("turn", "tool_call", "manual", "overflow")
+        if subargs in valid:
+            context_manager.set_monitor_frequency(subargs)
+            console.print(f"[green]✓ Monitor frequency set to: {subargs}[/green]")
+        else:
+            console.print(f"[yellow]Frequency must be one of: {', '.join(valid)}[/yellow]")
+    elif subcommand == "compact":
+        _compact_context(console, context_manager, session_state)
+    else:
+        console.print("[yellow]Unknown subcommand. Use: show, stats, budget, dump, on, off, path, format, frequency, compact[/yellow]")
+
+
+def _show_context_summary(console, manager: ContextManagerHandler) -> None:
+    """Show context summary."""
+    stats = manager.get_stats()
+    
+    console.print("\n[bold cyan]Context Summary[/bold cyan]")
+    console.print(f"  Model:          {stats['model']}")
+    console.print(f"  Model Limit:    {stats['model_limit']:,} tokens")
+    console.print(f"  Output Reserve: {stats['output_reserve']:,} tokens")
+    console.print(f"  Usable Budget:  {stats['usable']:,} tokens")
+    console.print(f"  Current Usage:  {stats['total_tokens']:,} tokens ({stats['utilization']*100:.1f}%)")
+    console.print(f"  Turns:          {stats['turn_count']}")
+    console.print(f"  Messages:       {stats['message_count']}")
+    console.print(f"  Auto-Compact:   {'enabled' if stats['auto_compact'] else 'disabled'}")
+    console.print(f"  Monitoring:     {'enabled' if stats['monitor_enabled'] else 'disabled'}")
+    
+    if stats['warnings']:
+        console.print("\n[yellow]Warnings:[/yellow]")
+        for warning in stats['warnings']:
+            console.print(f"  ⚠ {warning}")
+    console.print("")
+
+
+def _show_context_stats(console, manager: ContextManagerHandler) -> None:
+    """Show detailed token stats."""
+    stats = manager.get_stats()
+    segments = stats.get("segments", {})
+    
+    console.print("\n[bold cyan]Token Ledger[/bold cyan]")
+    console.print(f"{'Segment':<20} {'Tokens':>10} {'Budget':>10} {'Used':>8}")
+    console.print("-" * 50)
+    
+    for name, data in segments.items():
+        tokens = data.get("tokens", 0)
+        budget = data.get("budget", 0)
+        util = data.get("utilization", 0) * 100
+        console.print(f"{name:<20} {tokens:>10,} {budget:>10,} {util:>7.1f}%")
+    
+    console.print("-" * 50)
+    console.print(f"{'TOTAL':<20} {stats['total_tokens']:>10,} {stats['usable']:>10,} {stats['utilization']*100:>7.1f}%")
+    console.print("")
+
+
+def _show_budget_details(console, manager: ContextManagerHandler) -> None:
+    """Show budget allocation details."""
+    budget = manager.budgeter.allocate()
+    
+    console.print("\n[bold cyan]Budget Allocation[/bold cyan]")
+    console.print(f"  Model Limit:     {budget.model_limit:,}")
+    console.print(f"  Output Reserve:  {budget.output_reserve:,}")
+    console.print(f"  Usable:          {budget.usable:,}")
+    console.print("")
+    console.print("  Segment Budgets:")
+    console.print(f"    System Prompt: {budget.system_prompt:,}")
+    console.print(f"    Rules:         {budget.rules:,}")
+    console.print(f"    Skills:        {budget.skills:,}")
+    console.print(f"    Memory:        {budget.memory:,}")
+    console.print(f"    Tool Schemas:  {budget.tools_schema:,}")
+    console.print(f"    Tool Outputs:  {budget.tool_outputs:,}")
+    console.print(f"    History:       {budget.history_budget:,}")
+    console.print(f"    Buffer:        {budget.buffer:,}")
+    console.print("")
+
+
+def _dump_context(console, manager: ContextManagerHandler, messages: List[Dict[str, Any]]) -> None:
+    """Dump context snapshot to file."""
+    # Temporarily enable if needed
+    was_enabled = manager.config.monitor_enabled
+    if not was_enabled:
+        manager.enable_monitor()
+    
+    path = manager.write_snapshot(messages, trigger="manual")
+    
+    if not was_enabled:
+        manager.disable_monitor()
+    
+    if path:
+        console.print(f"[green]✓ Context snapshot written to: {path}[/green]")
+    else:
+        console.print("[yellow]Failed to write context snapshot[/yellow]")
+
+
+def _compact_context(console, manager: ContextManagerHandler, session_state: Dict[str, Any]) -> None:
+    """Trigger context compaction."""
+    history = session_state.get("conversation_history", [])
+    
+    if len(history) < 4:
+        console.print("[yellow]Not enough history to compact (need at least 4 messages)[/yellow]")
+        return
+    
+    console.print("[dim]Optimizing context...[/dim]")
+    
+    optimized, result = manager.optimize(history)
+    
+    if result.tokens_saved > 0:
+        session_state["conversation_history"] = optimized
+        console.print(f"[green]✓ Optimized: {result.original_tokens:,} → {result.optimized_tokens:,} tokens[/green]")
+        console.print(f"[dim]Saved {result.tokens_saved:,} tokens ({result.reduction_percent:.1f}%)[/dim]")
+        console.print(f"[dim]Strategy: {result.strategy_used.value}[/dim]")
+    else:
+        console.print("[yellow]No optimization needed[/yellow]")
+
+
+# CLI argument definitions for argparse integration
+CONTEXT_CLI_ARGS = [
+    {
+        "flags": ["--context-auto-compact", "--no-context-auto-compact"],
+        "dest": "context_auto_compact",
+        "action": "store_true",
+        "default": None,
+        "help": "Enable/disable auto-compaction",
+    },
+    {
+        "flags": ["--context-strategy"],
+        "dest": "context_strategy",
+        "choices": ["smart", "truncate", "sliding_window", "summarize", "prune_tools"],
+        "default": None,
+        "help": "Context optimization strategy",
+    },
+    {
+        "flags": ["--context-threshold"],
+        "dest": "context_threshold",
+        "type": float,
+        "default": None,
+        "help": "Auto-compact threshold (0.0-1.0)",
+    },
+    {
+        "flags": ["--context-monitor"],
+        "dest": "context_monitor",
+        "action": "store_true",
+        "default": None,
+        "help": "Enable context monitoring",
+    },
+    {
+        "flags": ["--context-monitor-path"],
+        "dest": "context_monitor_path",
+        "default": None,
+        "help": "Context monitor output path",
+    },
+    {
+        "flags": ["--context-monitor-format"],
+        "dest": "context_monitor_format",
+        "choices": ["human", "json"],
+        "default": None,
+        "help": "Context monitor output format",
+    },
+    {
+        "flags": ["--context-monitor-frequency"],
+        "dest": "context_monitor_frequency",
+        "choices": ["turn", "tool_call", "manual", "overflow"],
+        "default": None,
+        "help": "Context monitor update frequency",
+    },
+    {
+        "flags": ["--context-redact", "--no-context-redact"],
+        "dest": "context_redact",
+        "action": "store_true",
+        "default": None,
+        "help": "Enable/disable sensitive data redaction",
+    },
+    {
+        "flags": ["--context-output-reserve"],
+        "dest": "context_output_reserve",
+        "type": int,
+        "default": None,
+        "help": "Output token reserve",
+    },
+]

src/praisonai/praisonai/cli/features/interactive_runtime.py

@@ -144,7 +144,16 @@ class InteractiveRuntime:
     
     @property
     def read_only(self) -> bool:
-        """Check if runtime is in read-only mode."""
+        """Check if runtime is in read-only mode.
+        
+        Note: When PRAISON_APPROVAL_MODE=auto, we allow writes even without ACP
+        to support non-interactive automation and testing scenarios.
+        """
+        # Auto-approval mode bypasses read-only for automation
+        import os as _os
+        approval_mode = _os.environ.get("PRAISON_APPROVAL_MODE", "").lower()
+        if approval_mode == "auto":
+            return False
         return self._read_only or not self.acp_ready
     
     def get_status(self) -> Dict[str, Any]:

src/praisonai/praisonai/cli/features/tui/cli.py

@@ -10,7 +10,6 @@ Provides Typer-based CLI commands for:
 
 import asyncio
 import json
-import os
 import sys
 from typing import Optional
 
@@ -34,12 +33,13 @@ def create_tui_app():
     
     app = typer.Typer(
         name="tui",
-        help="PraisonAI TUI and Queue commands",
-        no_args_is_help=True,
+        help="Terminal UI (Textual-based full TUI)",
+        no_args_is_help=False,  # Allow running without subcommand
     )
     
-    @app.command("launch")
-    def tui_launch(
+    @app.callback(invoke_without_command=True)
+    def tui_main(
+        ctx: typer.Context,
         workspace: Optional[str] = typer.Option(
             None, "--workspace", "-w",
             help="Workspace directory"
@@ -65,7 +65,21 @@ def create_tui_app():
             help="Disable LSP tools (code intelligence: symbols, definitions)"
         ),
     ):
-        """Launch the interactive TUI with ACP + LSP tools enabled by default."""
+        """
+        Launch the interactive TUI (Textual-based).
+        
+        This is a full terminal UI with rich widgets. For simpler terminal
+        chat, use: praisonai chat
+        
+        Examples:
+            praisonai tui
+            praisonai tui --workspace ./project
+            praisonai tui --session abc123
+        """
+        # If a subcommand was invoked, don't run the default
+        if ctx.invoked_subcommand is not None:
+            return
+            
         try:
             from .app import run_tui
         except ImportError:

src/praisonai/praisonai/cli/features/tui/debug.py

@@ -33,20 +33,35 @@ def create_debug_app():
     
     app = typer.Typer(
         name="tui",
-        help="TUI and simulation commands",
-        no_args_is_help=True,
+        help="Terminal UI (Textual-based full TUI)",
+        no_args_is_help=False,  # Allow running without subcommand
     )
     
-    @app.command("launch")
-    def tui_launch(
-        workspace: Optional[str] = typer.Option(None, "--workspace", "-w"),
-        session: Optional[str] = typer.Option(None, "--session", "-s"),
-        model: Optional[str] = typer.Option(None, "--model", "-m"),
+    @app.callback(invoke_without_command=True)
+    def tui_main(
+        ctx: typer.Context,
+        workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Workspace directory"),
+        session: Optional[str] = typer.Option(None, "--session", "-s", help="Session ID to resume"),
+        model: Optional[str] = typer.Option(None, "--model", "-m", help="Default model"),
         debug: bool = typer.Option(False, "--debug", "-d", help="Enable debug overlays"),
         log_jsonl: Optional[str] = typer.Option(None, "--log-jsonl", help="Write events to JSONL file"),
         profile: bool = typer.Option(False, "--profile", help="Enable performance profiling"),
     ):
-        """Launch the interactive TUI."""
+        """
+        Launch the interactive TUI (Textual-based).
+        
+        This is a full terminal UI with rich widgets. For simpler terminal
+        chat, use: praisonai chat
+        
+        Examples:
+            praisonai tui
+            praisonai tui --workspace ./project
+            praisonai tui --session abc123
+        """
+        # If a subcommand was invoked, don't run the default
+        if ctx.invoked_subcommand is not None:
+            return
+            
         try:
             from .app import run_tui
         except ImportError:

src/praisonai/praisonai/cli/interactive/__init__.py

@@ -0,0 +1,48 @@
+"""
+Unified Interactive Core for PraisonAI CLI.
+
+This module provides a single core runtime that powers all interactive modes:
+- `praisonai run --interactive`
+- `praisonai chat`
+- `praisonai tui launch`
+
+All UIs consume the same event model; only rendering differs.
+"""
+
+__all__ = [
+    "InteractiveCore",
+    "InteractiveConfig",
+    "InteractiveEvent",
+    "InteractiveEventType",
+    "ApprovalRequest",
+    "ApprovalResponse",
+    "ApprovalDecision",
+]
+
+# Lazy imports to avoid loading heavy dependencies on import
+_lazy_cache = {}
+
+
+def __getattr__(name: str):
+    """Lazy load interactive components."""
+    if name in _lazy_cache:
+        return _lazy_cache[name]
+    
+    if name == "InteractiveCore":
+        from .core import InteractiveCore
+        _lazy_cache[name] = InteractiveCore
+        return InteractiveCore
+    
+    if name == "InteractiveConfig":
+        from .config import InteractiveConfig
+        _lazy_cache[name] = InteractiveConfig
+        return InteractiveConfig
+    
+    if name in ("InteractiveEvent", "InteractiveEventType", "ApprovalRequest", 
+                "ApprovalResponse", "ApprovalDecision"):
+        from . import events
+        obj = getattr(events, name)
+        _lazy_cache[name] = obj
+        return obj
+    
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")