Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TDD_MODE | No | Enable TDD mode for testing | false |
| CLOUD_API_KEY_1 | No | API key for Cloud Backend 1 (Coding Specialist) | |
| CLOUD_API_KEY_2 | No | API key for Cloud Backend 2 (Analysis Specialist) | |
| CLOUD_API_KEY_3 | No | API key for Cloud Backend 3 (General Purpose) | |
| LOCAL_MODEL_ENDPOINT | No | The URL endpoint for your local model server (LM Studio, Ollama, vLLM, etc.) | http://localhost:1234/v1 |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review | 👀 Comprehensive code review - Security audit, performance analysis, best practices validation. Multi-file correlation analysis. Automated quality scoring and improvement suggestions. |
| read | 📖 Intelligent file operations - Smart context management with automatic chunking. Multi-file reading with relationship detection. Project structure analysis. Enhanced with fuzzy matching verification for pre-flight edit validation. |
| health | 🏥 OPTIMIZED System health and diagnostics - Smart differentiated health monitoring with BLAZING fast performance! Local endpoints get comprehensive inference testing (10s timeout), cloud endpoints get quick connectivity pings (3s timeout). Features performance metrics, NVIDIA cloud integration status, smart routing analytics, and FileModificationManager operation tracking. OPTIMIZER: Includes localhost priority discovery and cache invalidation! |
| write_files_atomic | ✍️ Write multiple files atomically with backup - Enterprise-grade file modification with safety mechanisms |
| edit_file | 🔧 ENHANCED Intelligent file editing - FileModificationManager orchestrated operations with smart AI routing. AI-powered targeted modifications with validation, rollback capability, and complexity-based endpoint selection for optimal performance. |
| validate_changes | ✅ Pre-flight validation for code changes - AI-powered syntax checking and impact analysis using DialoGPT-small. Validates proposed modifications before implementation. |
| multi_edit | 🔄 ENHANCED Atomic batch operations - FileModificationManager orchestrator with parallel processing and smart AI routing. Enterprise-grade multi-file editing with NVIDIA cloud escalation for complex operations, AI validation, and automatic rollback. |
| backup_restore | 💾 Enhanced backup management - Timestamped backup tracking with metadata, restore capability, and intelligent cleanup. Extends existing backup patterns with enterprise-grade management. |
| ask | 🤖 MULTI-AI Direct Query - Ask any backend with BLAZING FAST smart fallback chains! Features automatic Unity detection, dynamic token scaling, and response headers with backend tracking. |
| rate_limit_status | 📊 Rate Limit Status - Check current rate limit usage and remaining capacity |
| system_metrics | 📈 System Metrics - View system usage metrics, performance statistics, and tool usage breakdown |