MCTS Optimization: Added Redis caching and metrics tracking

[MVPandey]

No description provided.

[Copilot]

Pull Request Overview

This PR implements Redis caching and comprehensive metrics tracking to optimize MCTS performance. The main purpose is to enhance the Monte Carlo Tree Search algorithm with semantic caching for response optimization and add production-ready monitoring capabilities.

Key changes:

• Added Redis-based semantic caching for MCTS nodes to improve performance through cache hits
• Implemented comprehensive Prometheus metrics collection for HTTP requests, LLM calls, MCTS runs, and system health
• Added cache management with eviction policies, similarity search strategies, and performance monitoring

Reviewed Changes

Copilot reviewed 42 out of 46 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
pyproject.toml	Added Redis, numpy, and prometheus-client dependencies
env.example	Added Redis and cache configuration variables
docker-compose.yml	Added Redis service container configuration
app/utils/metrics.py	New centralized metrics collection system with Prometheus integration
app/utils/config.py	Added Redis and cache configuration settings
app/services/mcts/algorithm.py	Enhanced MCTS with semantic caching integration and cache statistics
app/services/embeddings/embedding_service.py	New embedding service with Redis caching and batch processing
app/services/cache/	Multiple new cache-related modules for Redis management, semantic caching, and eviction policies
tests/	Comprehensive test coverage for all new functionality
servers/mcp/mcts_analysis_server.py	Added MCP metrics tracking integration

Comments suppressed due to low confidence (1)

tests/unit/utils/test_logger_simple.py:38

• The test sets up a ValueError side effect but the actual InterceptHandler.emit method doesn't appear to handle this exception path. This test may not be testing realistic behavior.

        mock_logger.level.side_effect = ValueError("Unknown level")