Skip to content

Releases: ioBroker/ioBroker.javascript

Release v9.2.0

11 Apr 20:24
24701bc

Choose a tag to compare

  • (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

19 Mar 23:48
8c24356

Choose a tag to compare

  • (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

19 Mar 18:59
f92fe2f

Choose a tag to compare

  • 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

11 Jan 20:27
e42441f

Choose a tag to compare

Release v9.0.17

14 Dec 20:41
d118bc5

Choose a tag to compare

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

Release v9.0.12

01 Dec 18:40
c699785

Choose a tag to compare

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

Release v9.0.11

29 Jul 21:45
c83fff6

Choose a tag to compare

Release v9.0.10

27 Jul 09:34
844ab26

Choose a tag to compare

Release v9.0.9

25 Jul 07:30
756a820

Choose a tag to compare

  • (@klein0r) Added Blockly block to format a numeric value
  • (@GermanBluefox) Fixing some blocks in blockly: cron, time

Release v9.0.8

10 Jul 08:57
06346de

Choose a tag to compare

  • (@klein0r) Added Blockly block to format a numeric value
  • (@GermanBluefox) Fixing some blocks in blockly: cron, time