AI-Studio/app/MindWork AI Studio/wwwroot/changelog/v0.9.51.md

v0.9.51, build 226 (2025-09-04 18:02 UTC)

• Added support for predefined chat templates in configuration plugins to help enterprises roll out consistent templates across the organization.
• Added the ability to choose between automatic and manual update installation to the app settings (default is manual).
• Added the ability to control the update installation behavior by configuration plugins.
• Added the option for LLM providers to stream citations or sources.
• Added support for citations to the chat interface. This feature is invisible unless an LLM model is streaming citations or sources.
• Added the Responses API according to the OpenAI documentation. It is currently only used by OpenAI, but we could use the API for other providers as soon as someone offers it. This means that all text-based LLMs from OpenAI can now be used in MindWork AI Studio. For example, the Deep Research models for comprehensive research tasks.
• Added support for web searches. Currently supported by some OpenAI models (e.g., GPT5, newer Omni models, Deep Research models) and Perplexity. Used sources are displayed visually in the chat interface.
• Improved memory usage in several areas of the app.
• Improved plugin management for configuration plugins so that hot reload detects when a provider or chat template has been removed.
• Improved the dialog for naming chats and workspaces to ensure valid inputs are entered.
• Improved the dialog invocation by making parameter provision more robust.
• Improved the text summarizer assistant by allowing users to specify important aspects & optimized the generated prompt.
• Improved the OpenAI provider by supporting more models and capabilities.
• Improved the German translation.
• Improved the enterprise configuration of complex objects, such as chat templates: the corresponding Lua tables are now optional. This ensures existing enterprise configurations remain valid when new configuration options are added and don't require adjustments with every update.
• Changed the configuration plugin setting name for how often to check for updates from UpdateBehavior to UpdateInterval.
• Fixed a bug in various assistants where some text fields were not reset when resetting.
• Fixed the input field header in the dialog for naming chats and workspaces.
• Fixed a rare chat-related bug that could occur when a workspace was not created correctly. Thank you, Naomi, for reporting this issue.
• Fixed a bug in the web content reader where a preconfigured LLM provider was not recognized, resulting in an error message.
• Fixed another bug in the web content reader: the system incorrectly evaluated whether the content cleaning agent was preselected. Users had to first deactivate the agent and then reactivate it to make it work correctly.
• Fixed a bug in the assistants for text summarization, translations, and legal check: the web content reader preferences were not being applied when resetting the assistant.
• Fixed the bottom margin of code blocks in chat. The bottom margins were too small. This was particularly problematic when horizontal scrollbars were necessary.
• Fixed a bug in assistants: the selected profile wasn't reset when resetting the assistant.
• Upgraded dependencies.