v1.2.0

Release Notes - v1.2.0

🎯 Overview

This release significantly improves reliability and performance of the integration, with special focus on optimization for resource-constrained devices (Raspberry Pi, Proxmox VMs) and critical bug fixes.

---

✨ What's New

🚀 Performance Improvements

• Separate API vs Local Timing: Now you can see how much time the xAI API takes vs local processing

  • Helps identify if slowness comes from the API or your system
  • Visible in INFO logs chat_start and chat_end with api_time and local_process_time

• Faster Operations: Save operations (tokens, memory) no longer block conversations

  • Everything is saved in background while you continue talking to the assistant
  • Less waiting time between voice commands

• Reduced System Load: Optimizations for Raspberry Pi and low-power devices

  • Reduced CPU usage when not necessary
  • Better log handling (no resource waste when logging is disabled)

💰 Cost Tracking Fixed

• Pricing Issue Resolved: Cost sensors now show correct values in USD
  • Previous conversion error showing wrong prices fixed
  • Cost display is now accurate and reliable

🐛 Bug Fixes

• Fixed Crash with Tools Mode and Memory Disabled:
• Faster Historical Messages: When server-side memory is disabled
• Fixed errors in image generation and analysis

---

🔧 Technical Improvements

Code Optimizations

• Improved code organization
• Constants instead of "magic numbers" for better clarity
• Better defined data types
• Lazy logging evaluation for performance on low-end devices

New Helper Modules

• log_time_services.py: Automatically handles API call timing
• token_storage.py: Saves token statistics more efficiently
• integration_setup.py: Centralizes integration setup logic
• model_manager.py: Manages model information and pricing

---

Full Changelog: v1.1.0...v1.2.0