Release v9.2.2

• (Eistee82) Fix: AI chat mode tooltip no longer covers the dropdown options (issue #2201) — moved tooltip to the left of the selector
• (Eistee82) Clarified the AI chat mode descriptions in the tooltip: Agent is for larger models with tool support and handles both analysis and script creation, Code is for smaller models without tool support (uses two-step plan-then-code) — translations updated in all 11 languages
• (@GermanBluefox) Added the "is state exists" block to blockly

Release v9.2.1

• (@GermanBluefox) See previous changelog entries

Release v9.2.0

• (Eistee82) AI Chat panel with multi-provider support, tool calling, inline completions, and smart-apply
• (Eistee82) Fix: prevent duplicate 'Stopping script' log when script is not running
• (Eistee82) Fix: only restart scripts on the instance that owns them
• (Eistee82) Added OID display mode toggle for Blockly editor: 4 display modes (Name, Name path, State ID, Full ID) with toolbar dropdown, context menu, optional object icons, and translations in 11 languages
• (Eistee82) Node 25 compatibility: replaced deprecated rmdirSync with rmSync in build tasks
• (@GermanBluefox) Added support for plain import/export
• (@GermanBluefox) Correcting error in configuration
• (@GermanBluefox) disallow writing into node_modules folder by scripts
• (@GermanBluefox) Correcting start of the script more than one time if restart is triggered
• (@GermanBluefox) All delayed writings are stopped by the script stop
• (@GermanBluefox) Added check if a script has been modified by another user/window
• (@GermanBluefox) Make the instance number more prominent

Release v9.1.1

• (GermanBluefox) Small GUI optimizations
• Added support for custom OpenAI-compatible API endpoints (e.g. Ollama, LM Studio, Google Gemini, DeepSeek, OpenRouter)
• Added configurable base URL in adapter settings
• Models are now fetched dynamically from the configured API endpoint
• Added the "Test API connection" button in adapter settings
• Added error handling with user-friendly messages for unreachable providers
• Added retry functionality for failed model loading
• All API calls (models + chat) are proxied server-side to avoid CORS issues with local providers
• Strip LLM thinking artifacts from responses (for local models like Ollama)

Release v9.1.0

• Added support for custom OpenAI-compatible API endpoints (e.g. Ollama, LM Studio, Google Gemini, DeepSeek, OpenRouter)
• Added configurable base URL in adapter settings
• Models are now fetched dynamically from the configured API endpoint
• Added the "Test API connection" button in adapter settings
• Added error handling with user-friendly messages for unreachable providers
• Added retry functionality for failed model loading
• All API calls (models + chat) are proxied server-side to avoid CORS issues with local providers
• Strip LLM thinking artifacts from responses (for local models like Ollama)

Release v9.0.18

• (@GermanBluefox) Corrected error message with lastSync
• (@klein0r) Corrected JavaScript filter

Release v9.0.17

• (@GermanBluefox) Added possibility to encrypt scripts with password (only for vendors)

Release v9.0.12

• (@GermanBluefox) Added possibility to encrypt scripts with password (only for vendors)

Release v9.0.11

• (@GermanBluefox) Corrected the rule editor if the condition is empty
• (@GermanBluefox) Corrected types for TypeScript

Release v9.0.10

• (@klein0r) Added Blockly block to format a numeric value
• (@GermanBluefox) Fixing some blocks in blockly: cron, time
• (@GermanBluefox) Added new block: "unconditional return"
• (@GermanBluefox) Type definitions for TypeScript were updated
• (@GermanBluefox) Corrected bug with deleting of sub-folders