IT Center Changes

Features:

• Added support for the /api/v1/responses endpoint
• Added support for the Responses endpoint in the chat frontend
• Added support for new models:
  • gpt-5.2-codex, gpt-5.3-codex, gpt-5.4-mini, gpt-5.4-nano, and the latest GWDG models

Bugfixes and Improvements:

• Improved mobile sidebar and user menu
• Improved API validation and error handling, particularly for incorrect model types and provider errors
• Improved token calculation performance
• Fixed an issue with custom Tailwind color names after a package update

Bugfixes and Improvements:

• The model selection list is now scrollable when it becomes too long
• The model overview has been redesigned for improved clarity

Features:

• Added support for new models:
  • gpt-5.3-chat, Mistral-Small-4-119B-2603

Bugfixes and Improvements:

• No spaces or special characters are allowed anymore in internal deployment names
• Improved performance when accessing the API
• For image generation, the input image is now only displayed if it was manually selected
• Minor improvements to shared chats, especially regarding model selection and chats with images
• Improved behavior when manually cancelling a completion
• Fixed an issue with title generation when it takes longer than the actual prompt
• Fixed a problem with database indexes that prevented the app from starting

Features:

• Added support for new models:
  • Mistral-Large-3-675B-Instruct-2512, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemma-3-27b-it, gemma-3n-e4b-it

Bugfixes and Improvements:

• Title generation is no longer counted toward the maximum number of parallel requests per user
• Added support for the encoding_format parameter in the embedding endpoint
• Improved parameter selection behavior for image generation
• Restricted access to own chats in user groups that are no longer accessible

Features:

• Added support for embedding models:
  • e5-mistral-7b-instruct, multilingual-e5-large-instruct, qwen3-embedding-8b, text-embedding-3-large , text-embedding-3-small , text-embedding-ada-002
• Added image input for image models; image models now use the most recently generated image as the default input
• Model switching within an active chat is now possible
• Expanded and updated model catalog

Bugfixes and Improvements:

• Improved Azure OpenAI support and compatibility (more consistent behavior across providers)
• Refined Sidebar & User Menu UX (dropdown menus, modals, improved usability)
• Corrected default deployment selection
• Improved syntax highlighting in code output
• Logos now display correctly after tenant switching
• Fixed API key inactivity/expiration logic
• Fixed file upload via keyboard
• Various minor UI and stability fixes

Features:

• Support for new models:
  • gpt-5.1, gpt-5.2
• Support for new image generation models:
  • gpt-image-1, gpt-image-1-mini und gpt-image-1.5
• New overview page showing all current deployments for a user group
• Deployments can now be created as API-only
• Long chats (context windows) are no longer cut off

Bugfixes and Improvements: 

• Improved deployment selection design
• Redesigned mobile layout
• Long words without spaces now wrap correctly in chat messages
• Optimized search performance
• Improved error message for temporarily inactive API keys
• Redesigned API key modal
• Title generation now runs in parallel with completions
• API key expiration can now be dynamically configured per user group
• Ctrl+Home and Ctrl+End now work correctly in the input form
• [ADMIN] Improved deployment modal design
• [ADMIN] Added auto-scroll when drag-and-drop sorting deployments
• Search now only shows chats from the current user group
• The copy icon is no longer shown on “waiting” messages
• An error modal is now displayed when the hard limit is reached

Features:

• Support for the DALL·E 3 image generation model

Bugfixes and Improvements: 

• Improved UI/UX in the API key modal
• API access can now be configured at the deployment level instead of the user group level
• When multiple quotas exist per deployment, all quotas are now displayed

Features:

• Users can now create and manage their own API keys
• [ADMIN] API access can now be enabled or disabled per user group
• [ADMIN] Reporting has been expanded to include API usage analytics
• [ADMIN] New setting for maximum parallel requests per user

Bugfixes and Improvements: 

• Fixed issues with title generation for chats with long completions

Features:

• Support for new models:
  • gpt-oss-120b and gpt-oss-20b
• Chat export function added
• [ADMIN] Admins can now see and use all user groups

Bugfixes and Improvements:

• Improved display of formulas
• Document content is now sent to LLMs as a user message (previously system)
• Strict role sequence in prompts (no two consecutive messages with the same role)
• Improvements to timeouts and retries
• Various design optimizations
• [ADMIN] Added soft delete function for deployments
• [ADMIN] Added translatable labels for user groups
• The correct time period is now displayed when message limits are reached
• Title generation with Mistral Small now works correctly
• The sidebar can now be expanded and collapsed again