health_check – System Verification

Comprehensive LM Studio connection verification and system status diagnostics

Perfect For

Initial Setup Verification
Confirm Houtini LM is properly connected to LM Studio and all systems are operational before beginning development work.

Troubleshooting Connection Issues
Diagnose connectivity problems between Claude and your local LM Studio instance with detailed error reporting.

Performance Monitoring
Regular system health checks to ensure optimal performance and identify potential issues before they impact workflow.

Development Environment Validation
Verify system readiness before starting intensive analysis tasks or batch processing operations.

Model Status Assessment
Confirm loaded model capabilities, memory usage, and processing capacity for optimal function selection.

Quick Start

houtini-lm:health_check

Detailed system analysis:

houtini-lm:health_check with:
- detailed: true

System Diagnostics

Connection Status

• LM Studio Connectivity: WebSocket connection verification and response time measurement
• Model Loading Status: Confirmation that a compatible model is loaded and ready for processing
• API Endpoint Verification: Validates all required endpoints are accessible and functioning correctly

Performance Metrics

• Response Time Analysis: Connection latency and processing speed measurements
• Memory Usage Assessment: Available system resources and model memory consumption
• Processing Capacity: Token handling capabilities and recommended analysis complexity levels

Configuration Validation

• Model Compatibility: Verification that loaded model supports required function complexity
• Function Availability: Complete function library accessibility confirmation
• File Access Permissions: Directory access validation for analysis and generation functions

Health Check Output

Basic Health Report

✅ LM Studio Connection: Active
✅ Model Status: Loaded (13B parameters)
✅ Response Time: 1.2s
✅ Function Library: 50+ functions available
✅ File Access: Configured

Status: All systems operational
Recommended Complexity: Up to "comprehensive"

Detailed System Analysis

🔧 System Configuration:
- LM Studio Version: 0.2.19
- Model: CodeLlama-13B-Instruct
- Connection: ws://127.0.0.1:1234
- Memory Usage: 8.2GB / 16GB available

⚡ Performance Metrics:
- Connection Latency: 45ms
- Average Response Time: 1.2s
- Token Processing Rate: 850 tokens/sec
- Concurrent Request Limit: 4

📊 Function Categories:
- Analysis Functions: 19 available
- Generation Functions: 12 available
- Creative Functions: 3 available
- System Functions: 6 available

Common Issues & Solutions

Connection Failures

• LM Studio Not Running: Start LM Studio application and load a compatible model
• Model Not Loaded: Select and load a model in LM Studio (recommended: 13B+ parameters)
• Port Conflicts: Verify LM Studio is running on default port 1234 or update configuration

Performance Issues

• Slow Response Times: Consider using smaller model or reducing analysis complexity levels
• Memory Constraints: Free system memory or switch to more efficient model variant
• Processing Timeouts: Reduce maxDepth parameters or use “basic” analysis depth

Parameters

Output Levels

• Basic: Essential connection status and quick operational verification (default)
• Detailed: Comprehensive system analysis including performance metrics and configuration details

Model Recommendations

Optimal Model Sizes

• 13B+ Parameters: Recommended for comprehensive analysis and professional-quality generation
• 7B Parameters: Suitable for basic analysis and simple generation tasks
• 3B Parameters: Minimal functionality, basic file analysis only

Compatible Model Types

• Code-Focused Models: CodeLlama, Code-Qwen, DeepSeek-Coder for programming analysis
• General Models: Llama-2, Mistral, Qwen for balanced performance across all functions
• Instruct-Tuned: Models with instruction following capability for best results

Integration Workflow

Daily Development Routine:

1. Run health_check to verify system readiness
2. Review performance recommendations for optimal function usage
3. Proceed with analysis and generation tasks based on system capacity
4. Monitor performance and adjust complexity levels as needed

Pro Tips

Morning Routine: Start each development session with a health check to ensure optimal system performance and identify any overnight configuration changes.

Performance Optimisation: Use detailed health checks to establish baseline performance metrics and track system performance over time.

Troubleshooting Strategy: When experiencing issues with other functions, always run health_check first to isolate system-level problems from function-specific issues.

Related Functions

• list_functions – Complete function library overview and availability confirmation
• count_files – Test file access permissions with basic project analysis
• analyze_single_file – Verify analysis capabilities with a simple file assessment