Clean up: Remove docs, scripts, tests directories and simplify pyproject.toml and requirements.txt

app.py

@@ -18,10 +18,7 @@ demo = gr.ChatInterface(
     title="🧠 Topcoder MCP Agent",
     theme="soft",
     examples=[
-        "Active AI Challenges",
-        "get details about user abhishekrn",
-        "Tell me a joke",
-        "Show cache stats",
+        "Active AI Challenges", "Help", "Tell me a joke"
     ],
     type="messages",
 )

docs/conversation_history.md

@@ -1,182 +0,0 @@
-# Conversation History Feature
-
-## Overview
-
-The Topcoder MCP Agent now supports conversation history, allowing the LLM to maintain context across multiple interactions. This enables more coherent and contextual conversations with users.
-
-## Features
-
-### 1. **Sliding Window History**
-- Maintains a configurable number of recent messages (default: 20)
-- Automatically removes older messages when the limit is reached
-- Preserves conversation context while managing memory usage
-
-### 2. **Session Management**
-- Each conversation gets a unique session ID
-- Sessions persist for 24 hours by default
-- Automatic cleanup of expired sessions
-
-### 3. **Token Management**
-- Rough token estimation (4 characters per token)
-- Configurable token limits to prevent context overflow
-- Automatic trimming when approaching limits
-
-### 4. **Context-Aware Prompts**
-- Tool decision prompts include conversation context
-- Parameter extraction considers previous interactions
-- Response summarization maintains conversation flow
-
-## Configuration
-
-### Environment Variables
-
-Add these to your `.env` file:
-
-```bash
-# Conversation History Settings
-CONVERSATION_ENABLE_HISTORY=true
-CONVERSATION_MAX_HISTORY_LENGTH=20
-CONVERSATION_MAX_TOKENS=4000
-```
-
-### Settings Explained
-
-- `CONVERSATION_ENABLE_HISTORY`: Enable/disable conversation history (default: true)
-- `CONVERSATION_MAX_HISTORY_LENGTH`: Maximum number of messages to keep (default: 20)
-- `CONVERSATION_MAX_TOKENS`: Approximate token limit for conversation context (default: 4000)
-
-## Architecture
-
-### Core Components
-
-1. **ConversationHistoryService** (`src/domain/services/conversation_history.py`)
-   - Manages message storage and retrieval
-   - Implements sliding window logic
-   - Handles token estimation and limits
-
-2. **SessionManager** (`src/domain/services/session_manager.py`)
-   - Manages conversation sessions
-   - Handles session creation and cleanup
-   - Tracks session activity and expiration
-
-3. **Updated LLM Provider** (`src/infrastructure/providers/llm_provider.py`)
-   - New `chat_with_history()` method
-   - History-aware tool decision making
-   - Context-aware parameter extraction
-
-4. **Enhanced Prompt Service** (`src/application/services/prompt_service.py`)
-   - Builds prompts with conversation context
-   - Includes recent message history in tool decisions
-
-### Data Flow
-
-```
-User Input → Session Manager → Conversation History → LLM Provider → Response → History Update
-```
-
-## Usage Examples
-
-### Basic Conversation Flow
-
-1. **First Message**: User asks "Show me active challenges"
-   - System creates new session
-   - Stores user message in history
-   - LLM decides to use `query-tc-challenges` tool
-   - Response is stored in history
-
-2. **Follow-up**: User asks "What about AI challenges specifically?"
-   - System retrieves conversation history
-   - LLM considers previous context about challenges
-   - More specific query to `query-tc-challenges` with AI filter
-   - Response maintains conversation continuity
-
-### Context Preservation
-
-The system maintains context across interactions:
-
-```
-User: "Show me active challenges"
-Assistant: "Here are the active challenges..."
-
-User: "What about AI challenges?"
-Assistant: "Looking at the active challenges, here are the AI-specific ones..."
-```
-
-## Testing
-
-Run the conversation history tests:
-
-```bash
-pytest tests/unit/test_conversation_history.py -v
-```
-
-## Performance Considerations
-
-### Memory Usage
-- Each session stores messages in memory
-- Sessions are automatically cleaned up after 24 hours
-- Token limits prevent excessive memory usage
-
-### Response Time
-- History retrieval adds minimal overhead
-- Token estimation is fast (simple character count)
-- Context inclusion improves response quality
-
-### Scalability
-- Sessions are stored in memory (not persistent)
-- For production, consider database storage
-- Implement session cleanup for long-running applications
-
-## Future Enhancements
-
-### Planned Features
-1. **Persistent Storage**: Database-backed session storage
-2. **Advanced Token Counting**: More accurate token estimation
-3. **Context Summarization**: Automatic context compression
-4. **Multi-User Support**: User-specific session management
-5. **Context Analytics**: Track conversation patterns and effectiveness
-
-### Configuration Options
-1. **Session Persistence**: Choose between memory and database storage
-2. **Context Compression**: Automatic summarization of old messages
-3. **User Preferences**: Per-user history settings
-4. **Context Filtering**: Selective inclusion of relevant history
-
-## Troubleshooting
-
-### Common Issues
-
-1. **Memory Usage High**
-   - Reduce `CONVERSATION_MAX_HISTORY_LENGTH`
-   - Enable session cleanup more frequently
-   - Monitor active session count
-
-2. **Context Not Working**
-   - Verify `CONVERSATION_ENABLE_HISTORY=true`
-   - Check session creation in logs
-   - Ensure history is being passed to LLM calls
-
-3. **Slow Responses**
-   - Reduce `CONVERSATION_MAX_TOKENS`
-   - Limit history length
-   - Check token estimation accuracy
-
-### Debug Information
-
-Enable debug logging to see conversation flow:
-
-```python
-# Add to your application startup
-import logging
-logging.basicConfig(level=logging.DEBUG)
-```
-
-## Migration from v1
-
-The conversation history feature is backward compatible. Existing applications will continue to work without changes. To enable history:
-
-1. Set `CONVERSATION_ENABLE_HISTORY=true`
-2. Configure history limits as needed
-3. Restart the application
-
-The system will automatically start maintaining conversation context for new interactions. 

pyproject.toml

@@ -11,165 +11,24 @@ license = {text = "MIT"}
 authors = [
     {name = "Topcoder Team", email = "support@topcoder.com"}
 ]
-classifiers = [
-    "Development Status :: 4 - Beta",
-    "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Software Development :: Libraries :: Python Modules",
-    "Topic :: Scientific/Engineering :: Artificial Intelligence",
-]
 requires-python = ">=3.9"
 dependencies = [
-    # Core dependencies
     "pydantic>=2.5.0",
     "dependency-injector>=4.41.0",
-    
-    # HTTP and async
     "aiohttp>=3.9.0",
     "asyncio-mqtt>=0.16.0",
-    
-    # Configuration
     "python-dotenv>=1.0.0",
     "pyyaml>=6.0.0",
-    
-    # UI
     "gradio>=4.0.0",
-    
-    # Data handling
     "orjson>=3.9.0",
     "jsonschema>=4.20.0",
-    
-    # Logging and monitoring
     "structlog>=23.2.0",
     "prometheus-client>=0.19.0",
-    
-    # Testing utilities
-    "pytest>=7.4.0",
-    "pytest-asyncio>=0.21.0",
-    "pytest-cov>=4.1.0",
-    "httpx>=0.25.0",  # For testing HTTP clients
-    
-    # Development utilities
-    "black>=23.0.0",
-    "isort>=5.12.0",
-    "mypy>=1.7.0",
-    "ruff>=0.1.0",
-]
-
-[project.optional-dependencies]
-dev = [
-    "pre-commit>=3.0.0",
-    "tox>=4.0.0",
-    "sphinx>=7.0.0",
-    "sphinx-rtd-theme>=1.3.0",
 ]
 
-[project.urls]
-Homepage = "https://github.com/topcoder/mcp-agent-zephyr"
-Repository = "https://github.com/topcoder/mcp-agent-zephyr"
-Documentation = "https://topcoder.github.io/mcp-agent-zephyr"
-"Bug Tracker" = "https://github.com/topcoder/mcp-agent-zephyr/issues"
-
 [project.scripts]
 topcoder-agent = "src.main:main"
 
 [tool.setuptools.packages.find]
 where = ["."]
-include = ["src*"]
-exclude = ["tests*"]
-
-[tool.pytest.ini_options]
-testpaths = ["tests"]
-python_files = ["test_*.py", "*_test.py"]
-python_classes = ["Test*"]
-python_functions = ["test_*"]
-addopts = [
-    "--strict-markers",
-    "--strict-config",
-    "--cov=src",
-    "--cov-report=html",
-    "--cov-report=term-missing",
-    "--cov-report=xml",
-]
-markers = [
-    "unit: Unit tests",
-    "integration: Integration tests", 
-    "e2e: End-to-end tests",
-    "slow: Slow running tests",
-]
-
-[tool.black]
-line-length = 100
-target-version = ['py39']
-include = '\.pyi?$'
-extend-exclude = '''
-/(
-  # directories
-  \.eggs
-  | \.git
-  | \.hg
-  | \.mypy_cache
-  | \.tox
-  | \.venv
-  | build
-  | dist
-)/
-'''
-
-[tool.isort]
-profile = "black"
-line_length = 100
-multi_line_output = 3
-include_trailing_comma = true
-force_grid_wrap = 0
-use_parentheses = true
-ensure_newline_before_comments = true
-
-[tool.mypy]
-python_version = "3.9"
-warn_return_any = true
-warn_unused_configs = true
-disallow_untyped_defs = true
-disallow_incomplete_defs = true
-check_untyped_defs = true
-disallow_untyped_decorators = true
-no_implicit_optional = true
-warn_redundant_casts = true
-warn_unused_ignores = true
-warn_no_return = true
-warn_unreachable = true
-strict_equality = true
-show_error_codes = true
-
-[[tool.mypy.overrides]]
-module = [
-    "gradio.*",
-    "dependency_injector.*",
-]
-ignore_missing_imports = true
-
-[tool.ruff]
-target-version = "py39"
-line-length = 100
-select = [
-    "E",  # pycodestyle errors
-    "W",  # pycodestyle warnings
-    "F",  # pyflakes
-    "I",  # isort
-    "C",  # flake8-comprehensions
-    "B",  # flake8-bugbear
-    "UP", # pyupgrade
-]
-ignore = [
-    "E501",  # line too long, handled by black
-    "B008",  # do not perform function calls in argument defaults
-    "C901",  # too complex
-]
-
-[tool.ruff.per-file-ignores]
-"__init__.py" = ["F401"]
-"tests/*" = ["S101"]  # Use of assert in tests
+include = ["src*"]

requirements.txt

@@ -1,19 +1,11 @@
-# Core dependencies
-gradio>=4.0.0
-aiohttp>=3.8.0
+pydantic>=2.5.0
+dependency-injector>=4.41.0
+aiohttp>=3.9.0
+asyncio-mqtt>=0.16.0
 python-dotenv>=1.0.0
-pyyaml>=6.0
-
-# Data handling
-dataclasses; python_version<"3.7"
-
-# MCP (Model Context Protocol) - if available
-# mcp  # Uncomment if using official MCP package
-
-# Development dependencies (optional)
-# pytest>=7.0.0
-# pytest-asyncio>=0.21.0
-
-# Note: Built-in Python packages used:
-# - json, os, sys, uuid, asyncio, logging, pathlib, datetime, enum, typing
-# These are included with Python standard library
+pyyaml>=6.0.0
+gradio>=4.0.0
+orjson>=3.9.0
+jsonschema>=4.20.0
+structlog>=23.2.0
+prometheus-client>=0.19.0

scripts/generate_compact_specs.py

@@ -1,56 +0,0 @@
-#!/usr/bin/env python3
-"""
-Script to generate compact API specifications from MCP catalog.
-This condenses large Swagger and tools documents into compact form.
-"""
-
-import asyncio
-import sys
-import os
-from pathlib import Path
-
-# Add src to path and set up environment
-project_root = Path(__file__).parent.parent
-src_path = project_root / "src"
-sys.path.insert(0, str(src_path))
-os.chdir(project_root)
-
-# Now import with absolute imports
-from src.mcp.specs_generator import SpecsGenerator
-
-
-async def main():
-    """Generate compact API specifications."""
-    print("🔧 Generating compact API specifications...")
-    
-    try:
-        # Initialize specs generator
-        generator = SpecsGenerator()
-        
-        # Generate compact specs
-        specs = await generator.generate_compact_specs()
-        
-        # Save to file
-        generator.save_compact_specs(specs)
-        
-        # Print summary
-        generator.print_summary(specs)
-        
-        print("\n✅ Compact specs generation completed successfully!")
-        print(f"📁 Output saved to: {generator.output_path}")
-        print(f"📂 Data folder location: data/compact_api_specs.py")
-        
-        # Test the compact utils
-        print("\n🧪 Testing compact utils...")
-        from src.mcp.compact_utils import CompactSpecsUtils
-        
-        utils = CompactSpecsUtils()
-        utils.print_compact_summary()
-        
-    except Exception as e:
-        print(f"❌ Error generating compact specs: {e}")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    asyncio.run(main()) 

src/presentation/gradio_interface.py

@@ -173,7 +173,7 @@ def launch_ui():
         fn=agent_response,
         title="🧠 Topcoder MCP Agent",
         theme="soft",
-        examples=["Active AI Challenges", "get details about user abhishekrn", "Tell me a joke"],
+        examples=["Active AI Challenges", "Help", "Tell me a joke"],
         type="messages"  # Fix deprecation warning
     )
     demo.launch()

tests/unit/test_conversation_history.py

@@ -1,110 +0,0 @@
-import pytest
-from datetime import datetime
-from src.domain.services.conversation_history import ConversationHistoryService, Message, ConversationSession
-
-class TestConversationHistory:
-    
-    def setup_method(self):
-        """Set up test fixtures."""
-        self.history_service = ConversationHistoryService(default_max_history=5, default_max_tokens=1000)
-        self.session_id = "test_session_123"
-    
-    def test_add_message(self):
-        """Test adding messages to conversation history."""
-        # Add user message
-        self.history_service.add_message(self.session_id, "user", "Hello, how are you?")
-        
-        # Add assistant message
-        self.history_service.add_message(self.session_id, "assistant", "I'm doing well, thank you!")
-        
-        # Get conversation history
-        history = self.history_service.get_conversation_history(self.session_id)
-        
-        assert len(history) == 2
-        assert history[0]["role"] == "user"
-        assert history[0]["content"] == "Hello, how are you?"
-        assert history[1]["role"] == "assistant"
-        assert history[1]["content"] == "I'm doing well, thank you!"
-    
-    def test_history_limits(self):
-        """Test that history limits are applied correctly."""
-        # Add more messages than the limit
-        for i in range(10):
-            self.history_service.add_message(self.session_id, "user", f"Message {i}")
-            self.history_service.add_message(self.session_id, "assistant", f"Response {i}")
-        
-        # Should only keep the last 5 messages (due to default_max_history=5)
-        history = self.history_service.get_conversation_history(self.session_id)
-        assert len(history) == 5
-        
-        # Should be the last 5 messages from the conversation
-        # With 10 pairs (20 messages total), we should have the last 5 messages
-        # which would be: Message 8, Response 8, Message 9, Response 9, Message 9 (or similar)
-        # Let's just verify we have the right number and they're recent
-        assert len(history) == 5
-        # The last message should be from the last iteration (9)
-        assert "9" in history[-1]["content"] or "9" in history[-2]["content"]
-    
-    def test_get_recent_messages(self):
-        """Test getting recent messages."""
-        # Add several messages
-        for i in range(5):
-            self.history_service.add_message(self.session_id, "user", f"Message {i}")
-            self.history_service.add_message(self.session_id, "assistant", f"Response {i}")
-        
-        # Get last 3 messages
-        recent = self.history_service.get_recent_messages(self.session_id, count=3)
-        assert len(recent) == 3
-        # Should be the last 3 messages from the conversation
-        # With 5 pairs (10 messages total), last 3 would be from the end
-        assert len(recent) == 3
-        # The last message should be from the last iteration (4)
-        assert "4" in recent[-1]["content"] or "4" in recent[-2]["content"]
-    
-    def test_clear_history(self):
-        """Test clearing conversation history."""
-        # Add some messages
-        self.history_service.add_message(self.session_id, "user", "Test message")
-        self.history_service.add_message(self.session_id, "assistant", "Test response")
-        
-        # Clear history
-        self.history_service.clear_history(self.session_id)
-        
-        # Verify history is empty
-        history = self.history_service.get_conversation_history(self.session_id)
-        assert len(history) == 0
-    
-    def test_session_info(self):
-        """Test getting session information."""
-        # Add some messages
-        self.history_service.add_message(self.session_id, "user", "Test message")
-        self.history_service.add_message(self.session_id, "assistant", "Test response")
-        
-        # Get session info
-        info = self.history_service.get_session_info(self.session_id)
-        
-        assert info["session_id"] == self.session_id
-        assert info["message_count"] == 2
-        assert info["max_history_length"] == 5
-        assert info["max_tokens"] == 1000
-        assert "created_at" in info
-        assert "last_updated" in info
-    
-    def test_token_estimation(self):
-        """Test token estimation functionality."""
-        text = "This is a test message with some content."
-        estimated_tokens = self.history_service._estimate_tokens(text)
-        
-        # Should be roughly 1/4 of the character count
-        expected_tokens = len(text) // 4
-        assert estimated_tokens == expected_tokens
-    
-    def test_total_tokens(self):
-        """Test total token calculation."""
-        # Add messages with known content
-        self.history_service.add_message(self.session_id, "user", "Hello")
-        self.history_service.add_message(self.session_id, "assistant", "Hi there")
-        
-        total_tokens = self.history_service.get_total_tokens(self.session_id)
-        expected_tokens = (len("Hello") + len("Hi there")) // 4
-        assert total_tokens == expected_tokens